Microsoft Corporation

États‑Unis d’Amérique

Retour au propriétaire

1-100 de 64 207 pour Microsoft Corporation et 24 filiales Trier par
Recheche Texte
Affiner par
Type PI
        Brevet 61 073
        Marque 3 134
Juridiction
        États-Unis 41 716
        International 20 666
        Canada 1 238
        Europe 587
Propriétaire / Filiale
Microsoft Technology Licensing, LLC 54 510
[Owner] Microsoft Corporation 9 107
LinkedIn Corporation 244
Skype 133
Skype Limited 81
Voir plus
Date
Nouveautés (dernières 4 semaines) 218
2026 septembre (MACJ) 49
2026 août 169
2026 juillet 218
2026 juin 168
Voir plus
Classe IPC
G06F 17/30 - Recherche documentaire; Structures de bases de données à cet effet 4 843
H04L 29/06 - Commande de la communication; Traitement de la communication caractérisés par un protocole 3 933
H04L 29/08 - Procédure de commande de la transmission, p.ex. procédure de commande du niveau de la liaison 2 989
G06F 9/44 - Dispositions pour exécuter des programmes spécifiques 2 700
G06F 15/16 - Associations de plusieurs calculateurs numériques comportant chacun au moins une unité arithmétique, une unité programme et un registre, p. ex. pour le traitement simultané de plusieurs programmes 2 603
Voir plus
Classe NICE
09 - Appareils et instruments scientifiques et électriques 2 419
42 - Services scientifiques, technologiques et industriels, recherche et conception 1 391
41 - Éducation, divertissements, activités sportives et culturelles 858
38 - Services de télécommunications 474
35 - Publicité; Affaires commerciales 443
Voir plus
Statut
En Instance 3 843
Enregistré / En vigueur 60 364
  1     2     3     ...     100        Prochaine page

1.

METHOD OF FABRICATING A SEMICONDUCTOR DEVICE USING MASKED DEPOSITION

      
Numéro d'application 18995698
Statut En instance
Date de dépôt 2022-08-16
Date de la première publication 2026-09-03
Propriétaire Microsoft Technology Licensing, LLC (USA)
Inventeur(s)
  • Van Woerkom, David Johannes
  • Griggio, Flavio
  • Thiyagarajah, Naganivetha
  • Kloster, Maren Elisabeth
  • Upadhyay, Shivendra
  • Kostamo, Pasi

Abrégé

A method of fabricating a semiconductor device comprises providing a workpiece comprising a substrate, a semiconductor component arranged on the substrate, a capping layer arranged on the semiconductor component, and a dielectric layer arranged on the capping layer; forming a mask by patterning the dielectric layer and the capping layer to form an opening, the opening exposing a portion of the semiconductor component; depositing a material onto the mask, and onto the exposed portion of the semiconductor component via the opening in the mask; subsequently filling the opening with a sacrificial filler; and subsequently removing the material deposited onto the mask, wherein the sacrificial filler prevents removal of the material deposited onto the semiconductor component. The method is useful for fabricating semiconductor devices having a clean interface between the semiconductor component and the deposited material.

Classes IPC  ?

2.

NETWORK TRAFFIC MEASUREMENT AND CONTROL SYSTEM

      
Numéro d'application 19655987
Statut En instance
Date de dépôt 2026-04-23
Date de la première publication 2026-09-03
Propriétaire Microsoft Technology Licensing, LLC (USA)
Inventeur(s)
  • Rutkowski, Bradley David
  • Chen, Yu
  • Wang, Yehan
  • Zhou, Jinyang
  • Zheng, Boyang
  • Yang, Zhenguo
  • Luttinen, Todd Carlyle
  • Mealiffe, Jeffrey Kramer
  • Dai, Yuchao

Abrégé

A network traffic computing system obtains on-router traffic data, on-server traffic data and application log data. A data processing system extracts features from the data sources, splits the extracted features based upon destination and source ports and performs component-level aggregation of the features. The aggregated data is surfaced for monitoring and traffic control.

Classes IPC  ?

  • H04L 43/026 - Capture des données de surveillance en utilisant l’identification du flux
  • H04L 43/091 - Surveillance ou test en fonction de métriques spécifiques, p. ex. la qualité du service [QoS], la consommation d’énergie ou les paramètres environnementaux en mesurant la contribution de chaque composant du réseau au niveau du service réel
  • H04L 47/24 - Trafic caractérisé par des attributs spécifiques, p. ex. la priorité ou QoS

3.

SYSTEM AND METHOD FOR MULTILAYER DESIGN GENERATION GUIDED BY AN ANONYMOUS REGION LAYOUT

      
Numéro d'application 19068252
Statut En instance
Date de dépôt 2025-03-03
Date de la première publication 2026-09-03
Propriétaire Microsoft Technology Licensing, LLC (USA)
Inventeur(s)
  • Huang, Danqing
  • Li, Ji
  • Tang, Zhicong
  • Cheng, Mingxi
  • Yuan, Yuhui
  • Chen, Dong
  • Bao, Jianmin
  • Pu, Yifan
  • Zhao, Yiming
  • Liang, Zhanhao

Abrégé

A data processing system implements receiving a text prompt to create a multilayer graphic design; predicting, by a first generative model based on the text prompt, a layout including anonymous regions each defined by a bounding box without content or region-wise prompt annotations; concurrently generating, by a diffusion transformer, multilayer image latents of a global reference image, a background layer, and transparent foreground layers using a Gaussian noise conditioned on the layout and the text prompt, each of the transparent foreground layers corresponding to one of the anonymous regions; decoding, by a vision transformer, the multilayer image latents into the global reference image, the background layer, and the transparent foreground layers as the multilayer graphic design; composing an output based on the background layer and the transparent foreground layers; providing the output to a client device; and causing a user interface of the client device to display the output.

Classes IPC  ?

4.

GRANULAR SECURE USER ACCESS TO PRIVATE RESOURCES

      
Numéro d'application 19653817
Statut En instance
Date de dépôt 2026-04-21
Date de la première publication 2026-09-03
Propriétaire Microsoft Technology Licensing, LLC (USA)
Inventeur(s)
  • Jain, Ashish
  • Greenstein, Ronnie
  • Gendelman, Mordhai
  • Carmon, Avraham
  • O’donovan, Sinead C.
  • Tor, Yair

Abrégé

Methods, systems and computer program products are provided for granular secure user access to private resources. Increased granularity of security policies for user access may reduce security threats to resources. Security policies indicating user access to secure resources may be based on various combinations of user identities, client-side process (e.g., sub-process) identities, device identities, device types, device locations, resource access types, intelligent access (e.g., selective traffic routing), etc. For example, a security policy may indicate user A, using computing device B executing process C with process signature S (e.g., a signing signature thumbprint, etc.) may access private resource D. A process identity may be indicated by at least one of a process name, a code signing signature, a thumbprint, a process version, or a process publisher. Resource access security policy determinations and/or enforcement may be performed by security clients and/or security engines (e.g., SASE providing ZTNA).

Classes IPC  ?

  • H04L 9/40 - Protocoles réseaux de sécurité

5.

CONTEXTUALLY AWARE MANAGEMENT OF INTERACTIVE SOFTWARE APPLICATION ACCESS

      
Numéro d'application 19656138
Statut En instance
Date de dépôt 2026-04-23
Date de la première publication 2026-09-03
Propriétaire Microsoft Technology Licensing, LLC (USA)
Inventeur(s)
  • Henderson, Jared E.
  • Kennett, Daniel G.
  • Brown, Morgan Asher
  • Farkas, Shawn
  • Wheeler, Joseph
  • Tsinaroglou, Stylianos
  • Chien, Yi-An

Abrégé

A content management system may obtain a promoted content trigger event from an interactive software application based at least partially on content of the interactive software application. A content management system may suspend a user's interaction with the interactive software application based on the promoted content trigger event. A content management system may obtain promoted audiovisual content. A content management system may present the promoted audiovisual content to the user. A content management system may commence the user's interaction with the interactive software application. A content management system may establish a credit based at least partially on the promoted audiovisual content, wherein the credit delays suspension of the user's interaction with the interactive software application during a credit duration.

Classes IPC  ?

  • G06Q 30/0217 - Remises ou incitations, p. ex. coupons ou rabais impliquant une contribution sur des produits ou des services en échange d’une incitation ou d’une récompense
  • G06F 9/451 - Dispositions d’exécution pour interfaces utilisateur
  • G06F 9/54 - Communication interprogramme

6.

COMPRESSED SIGNAL PROPAGATION PIPELINE

      
Numéro d'application 19657457
Statut En instance
Date de dépôt 2026-04-24
Date de la première publication 2026-09-03
Propriétaire Microsoft Technology Licensing, LLC (USA)
Inventeur(s)
  • Xie, Yin
  • Mohamed, Amed Hassan
  • Benzatti, Danilo Landucci

Abrégé

A computer-implemented method for compressed compact data storage and processing within a cloud-based environment is disclosed. In one aspect, the method for processing data signals, includes receiving a plurality of data signals corresponding to a user, the plurality of data signals includes a plurality of user raw records at corresponding time values, compressing the plurality of data signals using an incremental compression algorithm to form a single compressed iterative record, organizing the single compressed iterative record into hierarchical segments based on predefined time intervals using a waterfall data model, and storing the single compressed iterative record in a first cloud storage system.

Classes IPC  ?

  • G06F 16/174 - Élimination de redondances par le système de fichiers
  • G06F 16/182 - Systèmes de fichiers distribués

7.

Context-Dependent Generation of Supplemental Information on a Per-Level Basis in a Neural Network

      
Numéro d'application 19067898
Statut En instance
Date de dépôt 2025-03-01
Date de la première publication 2026-09-03
Propriétaire Microsoft Technology Licensing, LLC (USA)
Inventeur(s)
  • Fayyaz, Mohsen
  • Sengupta, Sunando
  • Sommerlade, Eric Chris Wolfgang

Abrégé

A technique processes input information using a machine-trained model in a context-specific manner. The technique includes, for a particular processing block: receiving a set of input tokens; transforming the set of input tokens into a set of output tokens; and generating a control decision based on the output tokens. For a first state, the technique appends at least one of the output tokens to the input tokens to define a new set of input tokens and then repeats the transforming and generating operations. For a second state, the technique passes at least some of the set of output tokens to a next processing block. The token(s) passed to the next processing block convey supplemental information that does not necessarily have a verbal counterpart. The technique has the end effect of invoking transformation operations in a context-based as-needed basis, which, in turn, reduces latency and the consumption of resources.

Classes IPC  ?

  • G06F 40/284 - Analyse lexicale, p. ex. segmentation en unités ou cooccurrence

8.

MACHINE READING COMPREHENSION SYSTEM FOR ANSWERING QUERIES RELATED TO A DOCUMENT

      
Numéro d'application 19432781
Statut En instance
Date de dépôt 2025-12-24
Date de la première publication 2026-09-03
Propriétaire Microsoft Technology Licensing, LLC (USA)
Inventeur(s)
  • Adada, Mahmoud
  • Mcnamara, Andrew James
  • Suleman, Kaheer
  • Lin, Xihui
  • Zhuang, En Hui

Abrégé

A machine reading comprehension system (MRCS) can analyze a larger-sized document that includes multiple pages to predict an answer to a query. For example, the document can have two, five, tens, or hundreds of pages. The MRCS divides the document into multiple sections with each section including a portion of the document. Each section is processed separately by one or more processing circuitries to determine a score for that section. The score indicates how related the section is to the query and/or a probability that the section provides a possible answer to the query. Once all of the sections have been analyzed, the sections are ranked by their scores and a subset of the ranked sections are processed again to determine a predicted answer to the query.

Classes IPC  ?

  • G06F 16/2457 - Traitement des requêtes avec adaptation aux besoins de l’utilisateur
  • G06F 16/3329 - Formulation de requêtes en langage naturel
  • G06F 16/93 - Systèmes de gestion de documents
  • G06F 16/951 - IndexationTechniques d’exploration du Web
  • G06F 40/205 - Analyse syntaxique
  • G06F 40/258 - Extraction des en-têtesInsertion automatique des titresNumérotation
  • G06N 20/00 - Apprentissage automatique

9.

AUTOMATICALLY BUILDING BUSINESS INTELLIGENCE MODELS

      
Numéro d'application 19650643
Statut En instance
Date de dépôt 2026-04-17
Date de la première publication 2026-09-03
Propriétaire Microsoft Technology Licensing, LLC (USA)
Inventeur(s)
  • He, Yeye
  • Lin, Yiming
  • Chaudhuri, Surajit

Abrégé

The present disclosure relates to methods and systems that automatically predict a business intelligence model for tables of data provided as input. The methods and systems automatically generate a graph representing the business intelligence model and provide the graph as output. The graph provides a visual representation of the business intelligence model with nodes of the graph representing each input table and edges of the graph representing weighted edges joining pairs of tables together.

Classes IPC  ?

  • G06Q 10/067 - Modélisation d’entreprise ou d’organisation
  • G06F 16/21 - Conception, administration ou maintenance des bases de données
  • G06F 16/2453 - Optimisation des requêtes
  • G06F 16/2458 - Types spéciaux de requêtes, p. ex. requêtes statistiques, requêtes floues ou requêtes distribuées

10.

AUTOMATIC LANGUAGE MODEL (LM) INPUT OPTIMIZATION USING TEXTUAL GRADIENTS

      
Numéro d'application 19653905
Statut En instance
Date de dépôt 2026-04-21
Date de la première publication 2026-09-03
Propriétaire Microsoft Technology Licensing, LLC (USA)
Inventeur(s)
  • Pryzant, Reid Allen
  • Li, Jerry Zheng
  • Iter, Dan
  • Lee, Yin Tat
  • Zhu, Chenguang
  • Zeng, Nanshan
  • Shirgaonkar, Anup

Abrégé

Systems and methods are provided for implementing automatic prompt optimization using textual gradients. In various embodiments, a feedback prompt, input into a large language model (“LLM”), is used to generate textual gradients that criticize a current prompt. The feedback prompt includes the current prompt and predictions that are incorrect compared with corresponding labels associated with minibatch data processed by the LLM using the current prompt. The textual gradients and current prompt are used in an editing prompt to the LLM to obtain a set of optimized prompts, which may be expanded using a paraphrasing prompt that is input into the LLM to generate a set of paraphrased prompts. A selection algorithm is used to select one or more optimized prompts from the set of optimized prompts and/or the set of paraphrased prompts, and the process is repeated with the selected one or more optimized prompts replacing the current prompt.

Classes IPC  ?

  • G06F 40/20 - Analyse du langage naturel
  • G06F 16/90 - Détails des fonctions des bases de données indépendantes des types de données cherchés
  • G06F 40/166 - Édition, p. ex. insertion ou suppression

11.

COMPOUND BACKLIGHT WITH A REFLECTIVE LAYER

      
Numéro d'application 19655090
Statut En instance
Date de dépôt 2026-04-22
Date de la première publication 2026-09-03
Propriétaire Microsoft Technology Licensing, LLC (USA)
Inventeur(s)
  • Piecuch, Scott
  • Suzuki, Nobuyuki
  • Zheng, Ying

Abrégé

Display devices, display systems, backlight assemblies, and methods described herein provide compound backlights with edge lighting. In an aspect, the backlight includes a waveguide, first lights, and an array layer. The first lights are arranged along an edge of the waveguide. Each of the first lights transmits light into the waveguide. The array layer is coupled to the waveguide and comprises a reflective layer and second lights. The reflective layer reflects the light transmitted by the first lights into the waveguide. The second lights are arranged between the waveguide and the reflective layer. Each of the second lights transmits light into the waveguide layer through the first surface. In a further aspect, the second lights are oriented away from the waveguide and toward the reflective surface. In another aspect, a compound backlight includes a reflective surface, arranged between a waveguide and second lights, that reflects a portion of received light.

Classes IPC  ?

  • G02F 1/1335 - Association structurelle de cellules avec des dispositifs optiques, p. ex. des polariseurs ou des réflecteurs
  • F21V 8/00 - Utilisation de guides de lumière, p. ex. dispositifs à fibres optiques, dans les dispositifs ou systèmes d'éclairage
  • G02F 1/13357 - Dispositifs d'éclairage

12.

BRANCH TARGET BUFFER VICTIM CACHE

      
Numéro d'application 19653306
Statut En instance
Date de dépôt 2026-04-21
Date de la première publication 2026-09-03
Propriétaire Microsoft Technology Licensing, LLC (USA)
Inventeur(s)
  • Gago Alonso, Julio
  • Galan, Santiago
  • Juan Hormigo, Antonio
  • Pizarro, Ivan

Abrégé

Improved branch target buffer (BTB) structures are provided. A device can include branch target buffers storing entries corresponding to branch instructions and corresponding targets of the branch instructions. The device can include a victim cache storing a branch target buffer entry that has been evicted from a branch target buffer of the branch target buffers. The device can include branch prediction circuitry configured to access the victim cache responsive to receiving respective miss indications from each branch target buffer of the branch target buffers.

Classes IPC  ?

  • G06F 9/38 - Exécution simultanée d'instructions, p. ex. pipeline ou lecture en mémoire

13.

DRAWING ONTO A SURFACE OF A THREE-DIMENSIONAL MESH

      
Numéro d'application 19068576
Statut En instance
Date de dépôt 2025-03-03
Date de la première publication 2026-09-03
Propriétaire Microsoft Technology Licensing, LLC (USA)
Inventeur(s)
  • Diaz, Miguel Angel Susffalich
  • Edmonds, Christopher Douglas
  • Wang, Yanwei

Abrégé

A parallel processing drawing method operable on a computing device, such as a mixed- or virtual-reality head-mounted display (HMD) device, is utilized to provide a drawing tool that enables a user to virtually draw a line on a mesh of primitive geometric objects (e.g., triangles) that model three-dimensional (3D) surfaces of virtual or real-world objects. A device user provides inputs to a user interface on the computing device to virtually draw a line that the drawing tool then renders on a display system. The parallel processing drawing method simultaneously computes each of the individual line segments to conform the virtually drawn line to the mesh. The method is computationally efficient compared to conventional ray tracing which facilitates applications such as quick marking and drawing on meshes including complex meshes representing terrain and irregularly shaped objects.

Classes IPC  ?

  • G06T 17/20 - Description filaire, p. ex. polygonalisation ou tessellation
  • G02B 27/01 - Dispositifs d'affichage "tête haute"
  • G06T 19/20 - Édition d'images tridimensionnelles [3D], p. ex. modification de formes ou de couleurs, alignement d'objets ou positionnements de parties

14.

GENERATING AN LLM AGENT HUB AND AGENT WORKFLOW

      
Numéro d'application 19067437
Statut En instance
Date de dépôt 2025-02-28
Date de la première publication 2026-09-03
Propriétaire Microsoft Technology Licensing, LLC (USA)
Inventeur(s)
  • Sankaran, Anush
  • Abdi, Amir Hossein
  • Wang, Tong
  • Albada, Michael Charles

Abrégé

Techniques for automatically enhancing a hub of LLM agents are disclosed. A service accesses a computer-based task that includes a set of parameters and requirements. The service accesses the hub of LLM agents. The service queries the hub of LLM agents using the set of parameters and requirements to identify one or more LLM agents whose functionalities and score cards are determined to satisfy the set of parameters and requirements. Based on the query, the service identifies a set of LLM agents that are tasked with attempting to generate a solution for the computer-based task. The service tasks the set of LLM agents to operate in an attempt to generate the solution for the computer-based task.

Classes IPC  ?

  • G06F 16/383 - Recherche caractérisée par l’utilisation de métadonnées, p. ex. de métadonnées ne provenant pas du contenu ou de métadonnées générées manuellement utilisant des métadonnées provenant automatiquement du contenu
  • G06F 40/20 - Analyse du langage naturel

15.

DATE CLASSIFIER MACHINE LEARNING MODEL

      
Numéro d'application 19067688
Statut En instance
Date de dépôt 2025-02-28
Date de la première publication 2026-09-03
Propriétaire Microsoft Technology Licensing, LLC (USA)
Inventeur(s)
  • Wagle, Justin James
  • Sengupta, Sunando
  • Ravi, Rajath Kumar

Abrégé

A computing system including one or more processing devices configured to receive an input query. At a query parsing machine learning (ML) model, the one or more processing devices extract a temporal substring from the input query. At a sentence embedding ML model, the one or more processing devices compute a sentence embedding of the temporal substring. At a date classifier ML model, the one or more processing devices compute a date embedding based at least in part on the sentence embedding and perform classification on the date embedding to identify an output date including a day, a month, and a year indicated by the temporal substring. The one or more processing devices output the output date to an additional computing process.

Classes IPC  ?

  • G06F 16/2458 - Types spéciaux de requêtes, p. ex. requêtes statistiques, requêtes floues ou requêtes distribuées
  • G06N 3/0499 - Réseaux à propagation avant

16.

HYBRID CONTROL PLANE FOR CLOUD AND EDGE DEPLOYMENTS

      
Numéro d'application US2025058670
Numéro de publication 2026/182812
Statut Délivré - en vigueur
Date de dépôt 2025-12-09
Date de publication 2026-09-03
Propriétaire MICROSOFT TECHNOLOGY LICENSING, LLC (USA)
Inventeur(s)
  • Qadri, Faraz H.
  • Giner, David B.
  • Navali, Vikas A.
  • Waghmare, Tanmay

Abrégé

Systems and methods are provided for implementing a hybrid control plane for cloud and edge deployments. When a local control plane platform receives, from a requesting device, a request to access a first resource from a cloud-based control plane platform, an authentication proxy of a local resource manager of the local control plane platform maps a first identifier ("ID") to a second ID. The first ID and second ID are associated with the cloud-based control plane platform and the local control plane platform, respectively. The authentication proxy impersonates the requesting user, by generating a query for the first resource using the second ID, and sending the first query to a local resource provider(s) of the local control plane platform. The local control plane platform receives, from the local resource provider(s), a second resource corresponding to the first resource, and sends the second resource to the requesting device.

Classes IPC  ?

  • H04L 67/10 - Protocoles dans lesquels une application est distribuée parmi les nœuds du réseau
  • G06F 9/50 - Allocation de ressources, p. ex. de l'unité centrale de traitement [UCT]
  • H04L 9/40 - Protocoles réseaux de sécurité

17.

BIOMETRIC AUTHENTICATION-BASED ACCESS TO DISPLAYED DOCUMENTS OR CONTENT WITH MODIFIABLE FREQUENCY OR SCHEDULE FOR TRIGGERING AUTHENTICATION PROCESSES

      
Numéro d'application US2025058666
Numéro de publication 2026/182808
Statut Délivré - en vigueur
Date de dépôt 2025-12-09
Date de publication 2026-09-03
Propriétaire MICROSOFT TECHNOLOGY LICENSING, LLC (USA)
Inventeur(s)
  • Holdsworth, Katharine Ormond
  • Bhargav-Spantzel, Abhilasha
  • Sakib, Md. Nazmus
  • Olatunji, Ayobami Peter

Abrégé

Systems and methods are provided for implementing biometric authentication-based access to displayed documents or content with modifiable frequency or schedule for triggering authentication processes. A computing system receives a plurality of data including at least one of location data indicating a current location of the computing system, user access level data indicating an access level of a first user accessing one or more documents on the computing system, or document security level data indicating a security level for each document among the one or more documents being accessed. The computing system determines a security risk level for display of the one or more documents on a display screen of the computing system while the computing system is located within the current location, based on a combination of data among the plurality of data. The computing system sets or modifies a frequency and/or a schedule for triggering an authentication verification process.

Classes IPC  ?

  • G06F 21/32 - Authentification de l’utilisateur par données biométriques, p. ex. empreintes digitales, balayages de l’iris ou empreintes vocales
  • G06F 21/62 - Protection de l’accès à des données via une plate-forme, p. ex. par clés ou règles de contrôle de l’accès
  • H04L 9/40 - Protocoles réseaux de sécurité
  • H04W 12/06 - Authentification
  • G06F 21/53 - Contrôle des utilisateurs, des programmes ou des dispositifs de préservation de l’intégrité des plates-formes, p. ex. des processeurs, des micrologiciels ou des systèmes d’exploitation au stade de l’exécution du programme, p. ex. intégrité de la pile, débordement de tampon ou prévention d'effacement involontaire de données par exécution dans un environnement restreint, p. ex. "boîte à sable" ou machine virtuelle sécurisée

18.

THREAT INTELLIGENCE APPROACH FOR SECURING LANGUAGE MODELS

      
Numéro d'application US2025058665
Numéro de publication 2026/182807
Statut Délivré - en vigueur
Date de dépôt 2025-12-09
Date de publication 2026-09-03
Propriétaire MICROSOFT TECHNOLOGY LICENSING, LLC (USA)
Inventeur(s)
  • Harari, Asaf
  • Hen, Idan
  • Salman, Tamer
  • Keller, Ron

Abrégé

A method of detecting malicious input to a language model includes obtaining a first input directed to the language model; generating a first embedding that embeds content of the first input; abd determining values of a similarity metric computed between the first embedding and a plurality of embeddings stored in a known threat database. The plurality of embeddings corresponding to malicious inputs that exemplify attempts to extract unauthorized information from the language model or other artificial intelligence tool. The method further includes analyzing the values of the similarity metric to identify a select similar embedding within the known threat database that satisfies predefined similarity criteria with the first embedding and, in response to identifying the select similar embedding, identifying the first input as malicious and preventing the first input from being processed by the language model.

Classes IPC  ?

  • G06F 21/55 - Détection d’intrusion locale ou mise en œuvre de contre-mesures
  • G06F 21/57 - Certification ou préservation de plates-formes informatiques fiables, p. ex. démarrages ou arrêts sécurisés, suivis de version, contrôles de logiciel système, mises à jour sécurisées ou évaluation de vulnérabilité
  • H04L 9/40 - Protocoles réseaux de sécurité
  • G06F 21/54 - Contrôle des utilisateurs, des programmes ou des dispositifs de préservation de l’intégrité des plates-formes, p. ex. des processeurs, des micrologiciels ou des systèmes d’exploitation au stade de l’exécution du programme, p. ex. intégrité de la pile, débordement de tampon ou prévention d'effacement involontaire de données par ajout de routines ou d’objets de sécurité aux programmes
  • G06F 40/30 - Analyse sémantique

19.

AUTOMATIC SYSTEM PROMPT HARDENING FOR GENERATIVE ARTIFICIAL INTELLIGENCE SYSTEMS

      
Numéro d'application US2025058669
Numéro de publication 2026/182811
Statut Délivré - en vigueur
Date de dépôt 2025-12-09
Date de publication 2026-09-03
Propriétaire MICROSOFT TECHNOLOGY LICENSING, LLC (USA)
Inventeur(s)
  • Harari, Asaf
  • Hen, Idan
  • Brukman, Ariel
  • Keller, Ron

Abrégé

Techniques are disclosed for automatically generating and/or updating system prompts for applications that interface with generative artificial intelligence (AI) models. In an aspect, data associated with an application for facilitating interactions with a generative AI model is received. A security vulnerability is identified based on the data. A system prompt is generated. The system prompt has instructions specifying how the generative AI model is to respond to a user prompt. The instructions include a rule for mitigating the identified security vulnerability. The system prompt is provided to the application, causing the application to provide the system prompt to the generative AI model such that the generative AI model responds to user prompts in accordance with the rule. In a further example, the data corresponds to a communication session between the application and the generative AI model. In another aspect, the rule is determined utilizing the generative AI model.

Classes IPC  ?

  • G06F 21/55 - Détection d’intrusion locale ou mise en œuvre de contre-mesures
  • G06F 21/57 - Certification ou préservation de plates-formes informatiques fiables, p. ex. démarrages ou arrêts sécurisés, suivis de version, contrôles de logiciel système, mises à jour sécurisées ou évaluation de vulnérabilité
  • G06F 40/279 - Reconnaissance d’entités textuelles
  • H04L 9/40 - Protocoles réseaux de sécurité

20.

ZONED NEUTRAL ATOM QUANTUM COMPUTER SCHEDULE OPTIMIZATION

      
Numéro d'application US2025059072
Numéro de publication 2026/182815
Statut Délivré - en vigueur
Date de dépôt 2025-12-11
Date de publication 2026-09-03
Propriétaire MICROSOFT TECHNOLOGY LICENSING, LLC (USA)
Inventeur(s)
  • Aasen, David Alexander
  • Vaschillo, Alexander
  • Da Silva, Marcus Palmer
  • Basov, Ivan
  • Gavranovic, Haris
  • Fernandez, Diego Olivier

Abrégé

The invention relates to neutral atom quantum computers having a zoned architecture that includes a storage zone and an interaction zone as part of an array of atoms that form the quantum register in an optical lattice. A schedule optimizer determines an optimized atom schedule for moving atoms between the storage zone and the interaction zone using optical tweezers generated by an optical trap generator responsive to the optimized atom schedule. The schedule optimizer may be implemented according to several variations of algorithms that include an annealing solver and a mathematical optimization engine. The schedule optimizer receives an objective function that includes selectable factors that correlate to minimizing the logical error rate for a set of operational tasks, various hardware constraints such as zone geometries and circuit schedules.

Classes IPC  ?

  • G06N 10/40 - Réalisations ou architectures physiques de processeurs ou de composants quantiques pour la manipulation de qubits, p. ex. couplage ou commande de qubit
  • G06N 10/70 - Correction, détection ou prévention d’erreur quantique, p. ex. codes de surface ou distillation d’état magique

21.

COMPOSITIONAL PROGRAM SYNTHESIS ENGINE IN AN ARTIFICIAL INTELLIGENCE SYSTEM

      
Numéro d'application US2025059071
Numéro de publication 2026/182814
Statut Délivré - en vigueur
Date de dépôt 2025-12-11
Date de publication 2026-09-03
Propriétaire MICROSOFT TECHNOLOGY LICENSING, LLC (USA)
Inventeur(s)
  • Tiwari, Ashish
  • Gulwani, Sumit
  • Le, Vu Minh
  • Verbruggen, Gust Ben Anneloes

Abrégé

Methods, systems, and computer storage media for providing compositional program synthesis using a compositional program synthesis engine in an artificial intelligence (AI) system are described. Compositional program synthesis in this context is guided by a Large Language Model (LLL) and refers to the iterative process of using the LLM to generate, refine, and compose program segments, addressing errors by systematically breaking down tasks, salvaging correct parts, and synthesizing subprograms that are integrated using composition operators until a program satisfies the given specification. The compositional program synthesis engine iteratively generates, refines, and integrates program components by leveraging program decomposition, synthesis of subprograms, and composition operators to construct a program that meets the specified requirements. Compositional program synthesis engine supports several decomposition strategies associated with refining suffixes, refining prefixes, and IfThenElse distinct cases; and for synthesizing the new candidate programs the engine supports program composition operators including sequential composition and conditional composition.

Classes IPC  ?

  • G06F 8/30 - Création ou génération de code source
  • G06F 8/70 - Maintenance ou gestion de logiciel
  • G06N 20/00 - Apprentissage automatique

22.

DATA MAPPING MANAGEMENT FOR DATA COMPUTING

      
Numéro d'application 19656402
Statut En instance
Date de dépôt 2026-04-23
Date de la première publication 2026-09-03
Propriétaire Microsoft Technology Licensing, LLC (USA)
Inventeur(s)
  • Subramaniam, Venkata
  • Sharma, Piyush
  • Singh, Fnu Harkirat
  • Roy, Ashis Kumar

Abrégé

Systems, methods, devices, and computer readable storage media described herein provide techniques for simplifying data access and management for data computing. In an aspect, a request to load data is received. The request comprises an aliased name associated with the data. A call is transmitted to a name resolution service executing on a computing device. The call comprises the aliased name and is configured to cause the name resolution service to identify the data associated with the aliased name. A response is received from the first resolution service. The response comprises metadata of the data. The data is obtained from a data source based on the metadata. A dataset is generated based on the obtained data. A response to the request is provided. The response comprises the generated dataset. In a further aspect, an application is configured to import a library into a computer program under development.

Classes IPC  ?

  • G06F 21/62 - Protection de l’accès à des données via une plate-forme, p. ex. par clés ou règles de contrôle de l’accès
  • G06F 16/25 - Systèmes d’intégration ou d’interfaçage impliquant les systèmes de gestion de bases de données
  • G06F 16/955 - Recherche dans le Web utilisant des identifiants d’information, p. ex. des localisateurs uniformisés de ressources [uniform resource locators - URL]
  • H04L 67/02 - Protocoles basés sur la technologie du Web, p. ex. protocole de transfert hypertexte [HTTP]
  • H04L 67/10 - Protocoles dans lesquels une application est distribuée parmi les nœuds du réseau
  • H04L 61/4511 - Répertoires de réseauCorrespondance nom-adresse en utilisant des répertoires normalisésRépertoires de réseauCorrespondance nom-adresse en utilisant des protocoles normalisés d'accès aux répertoires en utilisant le système de noms de domaine [DNS]

23.

TESTING, TRAINING OR VALIDATING REASONING MODELS

      
Numéro d'application 19096501
Statut En instance
Date de dépôt 2025-03-31
Date de la première publication 2026-09-03
Propriétaire Microsoft Technology Licensing, LLC (USA)
Inventeur(s)
  • Falck, Fabian Maximilian
  • Dubey, Kshitij
  • Pandey, Atharva
  • Xu, Xinnuo
  • Ueno, Risa
  • Nori, Aditya Vithal
  • Sharma, Amit
  • Sharma, Rahul
  • González Hernández, Javier
  • Lawrence, Rachel Shannon

Abrégé

In one aspect herein, a symbolic representation is generated from a natural language reasoning problem, which can then be mutated to produce a symbolic problem variant and a natural language problem variant. This data synthesis techniques provides reasoning data that in some example applications is used to test a model's reasoning capabilities. Example applications include comparing model-generated answers against programmatically derived ground truth to distinguish genuine reasoning from memorized patterns. As another example, certain training applications repeatedly expose a model to newly synthesized data for iterative refinement.

Classes IPC  ?

  • G06F 11/3604 - Analyse de logiciel pour vérifier les propriétés des programmes

24.

ZONED NEUTRAL ATOM QUANTUM COMPUTER SCHEDULE OPTIMIZATION

      
Numéro d'application 19066949
Statut En instance
Date de dépôt 2025-02-28
Date de la première publication 2026-09-03
Propriétaire Microsoft Technology Licensing, LLC (USA)
Inventeur(s)
  • Aasen, David Alexander
  • Vaschillo, Alexander
  • Da Silva, Marcus Palmer
  • Basov, Ivan
  • Gavranovic, Haris
  • Fernandez, Diego Olivier

Abrégé

The invention relates to neutral atom quantum computers having a zoned architecture that includes a storage zone and an interaction zone as part of an array of atoms that form the quantum register in an optical lattice. A schedule optimizer determines an optimized atom schedule for moving atoms between the storage zone and the interaction zone using optical tweezers generated by an optical trap generator responsive to the optimized atom schedule. The schedule optimizer may be implemented according to several variations of algorithms that include an annealing solver and a mathematical optimization engine. The schedule optimizer receives an objective function that includes selectable factors that correlate to minimizing the logical error rate for a set of operational tasks, various hardware constraints such as zone geometries and circuit schedules.

Classes IPC  ?

  • G21K 1/30 -
  • G06N 10/40 - Réalisations ou architectures physiques de processeurs ou de composants quantiques pour la manipulation de qubits, p. ex. couplage ou commande de qubit

25.

MIXED-REALITY WAVEGUIDE COMBINER WITH REDUCED WORLD-SIDE LEAKAGE

      
Numéro d'application 19066903
Statut En instance
Date de dépôt 2025-02-28
Date de la première publication 2026-09-03
Propriétaire Microsoft Technology Licensing, LLC (USA)
Inventeur(s)
  • Singh, Manisha
  • Koc, Mehmet

Abrégé

A mixed-reality waveguide combiner for use in an optical display system of a head-mounted display (HMD) device for mixed-reality applications in which virtual images are displayed over views of the real world by an HMD device user is disclosed. A gradient refractive index is utilized in a surface relief grating having depth-modulated grating structures along with a thickness-modulated residual layer. A foundation layer, providing a contrasting refractive index to that of the gratings and the residual layer, may be utilized to provide increased resistance against parasitic diffraction away from the HMD device user towards the surrounding world-side environment. Such world-side leakage causes a phenomenon known as “eye glow” which can reduce social comfort by obscuring the user's eyes or undesirably increase HMD device observability.

Classes IPC  ?

  • F21V 8/00 - Utilisation de guides de lumière, p. ex. dispositifs à fibres optiques, dans les dispositifs ou systèmes d'éclairage
  • G02B 27/01 - Dispositifs d'affichage "tête haute"

26.

ARTICULATED OBJECT MESH RECOVERY

      
Numéro d'application 19066861
Statut En instance
Date de dépôt 2025-02-28
Date de la première publication 2026-09-03
Propriétaire Microsoft Technology Licensing, LLC (USA)
Inventeur(s)
  • Ali Akbarian, Mohammad Sadegh
  • Saleh, Fatemehsadat
  • Hewitt, Charles Thomas
  • Baltrusaitis, Tadas

Abrégé

A method for recovering a three-dimensional mesh model of an articulated object from a two-dimensional image is disclosed. The method includes extracting features from the two-dimensional image by generating image patches and processing them through a vision transformer encoder to produce visual tokens and a classification (CLS) token. Landmarks are predicted by generating landmark heatmaps, determining initial landmark coordinates and confidence scores, and refining these coordinates using the CLS token. The method further involves estimating a three-dimensional pose of the articulated object through landmark-based feature pooling and processing the features through transformer decoder blocks to generate pose parameters. Finally, a three-dimensional mesh of the articulated object is generated using the pose parameters and a parametric model.

Classes IPC  ?

  • G06T 17/20 - Description filaire, p. ex. polygonalisation ou tessellation
  • G06T 7/73 - Détermination de la position ou de l'orientation des objets ou des caméras utilisant des procédés basés sur les caractéristiques

27.

CENTRAL NODES DISCOVERY IN SECURITY KNOWLEDGE GRAPHS

      
Numéro d'application 19067731
Statut En instance
Date de dépôt 2025-02-28
Date de la première publication 2026-09-03
Propriétaire MICROSOFT TECHNOLOGY LICENSING, LLC (USA)
Inventeur(s)
  • Pirogovsky, Amir
  • Lahav, Chen
  • Salman, Tamer
  • Basash, Lital
  • Karpovsky, Andrey
  • Feitelson, Yotam Dan

Abrégé

Disclosed are techniques for determining the probability that a computing resource will be compromised during a cyberattack. In some configurations, a collection of computing resources is modeled with a resource graph. Computing resources are represented by nodes while connections between computing resources are represented by edges. Random walks are performed through the resource graph. Different random walk algorithms may be applied to identify different properties of the resource graph. For example, nodes that are visited frequently by the random walks may correspond to computing resources that are likely to be compromised during a cyberattack. Various security operations may be performed in response to determining that a computing resource is likely to be compromised, including increased security measures, introduction of honeypots or honeytokens, sending or prioritizing security alerts, etc.

Classes IPC  ?

  • G06F 21/57 - Certification ou préservation de plates-formes informatiques fiables, p. ex. démarrages ou arrêts sécurisés, suivis de version, contrôles de logiciel système, mises à jour sécurisées ou évaluation de vulnérabilité

28.

DIGITAL AGENTS FOR PRESENCE IN COMMUNICATION SESSIONS

      
Numéro d'application 19629347
Statut En instance
Date de dépôt 2026-03-26
Date de la première publication 2026-09-03
Propriétaire Microsoft Technology Licensing, LLC (USA)
Inventeur(s) White, Ryen W.

Abrégé

One or more digital agents are instantiated to monitor to monitor one or more communication sessions on behalf of a user. Respective digital agents are configured to identify, in the information shared during respective communication sessions, respective one or more subsets of information including one or more items of information relevant to the user. The respective one or more subsets of information identified, by the respective one or more digital agents, are obtained from the one or more digital agents. At least some of the information in the respective subsets of information is presented to the user.

Classes IPC  ?

  • H04L 51/02 - Messagerie d'utilisateur à utilisateur dans des réseaux à commutation de paquets, transmise selon des protocoles de stockage et de retransmission ou en temps réel, p. ex. courriel en utilisant des réactions automatiques ou la délégation par l’utilisateur, p. ex. des réponses automatiques ou des messages générés par un agent conversationnel
  • H04L 65/403 - Dispositions pour la communication multipartite, p. ex. pour les conférences

29.

EFFICIENT MODEL AGENT COMMUNICATION WITH CACHE SHARING

      
Numéro d'application 19067128
Statut En instance
Date de dépôt 2025-02-28
Date de la première publication 2026-09-03
Propriétaire Microsoft Technology Licensing, LLC (USA)
Inventeur(s)
  • Choukse, Esha
  • Musuvathi, Madanlal S.
  • Lu, Shan
  • Liu, Yuhan

Abrégé

Example solutions for context sharing between GAI models includes: identifying a pair of GAI models including a first model and a second model; generating a first key-value (KV) cache of the first model; populating a second KV cache of the second model with one or more layers of the first KV cache; recomputing one or more other layers of the second KV cache; computing an output performance score for the second model based on a baseline metric; and transmitting a reuse pattern to a host device for use in context sharing between an instance of first model and an instance of second model, the reuse pattern identifying the plurality of first KV cache layers to be reused, thereby causing the host device to generate a local KV cache for the instance of second model by reusing the plurality of first KV cache layers from a KV cache of first model.

Classes IPC  ?

  • G06F 12/084 - Systèmes de mémoire cache multi-utilisateurs, multiprocesseurs ou multitraitement avec mémoire cache partagée

30.

DATA TRANSMISSION THROUGH SUPERCONDUCTING CABLES

      
Numéro d'application 19067265
Statut En instance
Date de dépôt 2025-02-28
Date de la première publication 2026-09-03
Propriétaire Microsoft Technology Licensing, LLC (USA)
Inventeur(s) Nagimov, Ruslan

Abrégé

Technology is disclosed for data transmission over superconducting cables without a dedicated data transmission line. Control data associated with the superconducting cables is transmitted between terminations of the superconducting cable. In some embodiments, inductive coils at the termination may be used to superimpose data at a higher frequency than the electrical power for transmission over the superconductors to other terminations. In other embodiments, changes in parameters of the cryogenic fluid used to cool the superconductors may be used to transmit control data between terminations. For example, pressure changes and/or flow rate changes may be used to encode the control data. In either case, the dedicated transmission line typically accompanying a superconducting cable is not needed.

Classes IPC  ?

  • H01B 12/16 - Conducteurs, câbles ou lignes de transmission supraconducteurs ou hyperconducteurs caractérisés par le refroidissement
  • G01D 21/02 - Mesure de plusieurs variables par des moyens non couverts par une seule autre sous-classe
  • G01K 13/02 - Thermomètres spécialement adaptés à des fins spécifiques pour mesurer la température de fluides en mouvement ou de matériaux granulaires capables de s'écouler

31.

ADAPTIVE DETERMINATION OF STYLUS TILT

      
Numéro d'application 19015012
Statut En instance
Date de dépôt 2025-01-09
Date de la première publication 2026-09-03
Propriétaire Microsoft Technology Licensing, LLC (USA)
Inventeur(s)
  • Rosenblat, Itai
  • Menashof, Roei Shlomo
  • Istrin, Oren

Abrégé

Methods, devices, systems, and computer program products are provided for adaptive determination of stylus tilt by selectively using gyroscopic and sensor data for accuracy of tilt determinations as signal conditions change. A device comprises an orientation detector that determines stylus tilt using a first tilt detector based on a first set of conditions detected at a first time. The device detects a second set of conditions at a second time. The device adapts tilt determination from the first tilt detector to a second tilt detector for determination of tilt at the second time. The device determines tilt at the second time using the second tilt detector. Adaptive tilt detection can vary tilt calculations by using different equations, using the same equation with different weights, blending the results of calculations using multiple equations, etc., to maintain the accuracy of tilt determinations as signal conditions change.

Classes IPC  ?

  • G06F 3/0346 - Dispositifs de pointage déplacés ou positionnés par l'utilisateurLeurs accessoires avec détection de l’orientation ou du mouvement libre du dispositif dans un espace en trois dimensions [3D], p. ex. souris 3D, dispositifs de pointage à six degrés de liberté [6-DOF] utilisant des capteurs gyroscopiques, accéléromètres ou d’inclinaison
  • G01C 9/06 - Moyens d'indication ou de lecture électriques ou photo-électriques
  • G01C 19/5776 - Traitement de signal non spécifique à l'un des dispositifs couverts par les groupes
  • G06F 3/0354 - Dispositifs de pointage déplacés ou positionnés par l'utilisateurLeurs accessoires avec détection des mouvements relatifs en deux dimensions [2D] entre le dispositif de pointage ou une partie agissante dudit dispositif, et un plan ou une surface, p. ex. souris 2D, boules traçantes, crayons ou palets
  • G06F 3/038 - Dispositions de commande et d'interface à cet effet, p. ex. circuits d'attaque ou circuits de contrôle incorporés dans le dispositif

32.

SYSTEMS AND METHODS FOR THERMAL MANAGEMENT

      
Numéro d'application 19194750
Statut En instance
Date de dépôt 2025-04-30
Date de la première publication 2026-09-03
Propriétaire Microsoft Technology Licensing, LLC (USA)
Inventeur(s)
  • Farias Moguel, Oscar
  • Hurbi, Erin Elizabeth
  • Schubert, Alexis Grace
  • Trieu, Dennis

Abrégé

A device may include a plurality of dissociated unitary cells adjacent to one another. A dissociated unitary cell may include a base supporting a body having at least one sidewall. A dissociated unitary cell may include a top surface. A dissociated unitary cell may include a plurality of fins to direct a cooling fluid through the body in a three-dimensional flow path through the plurality of dissociated unitary cells.

Classes IPC  ?

  • H05K 7/20 - Modifications en vue de faciliter la réfrigération, l'aération ou le chauffage
  • G06F 1/20 - Moyens de refroidissement
  • H10W 40/22 -

33.

Speculative Decoding using Expanded Token Matching

      
Numéro d'application 19067886
Statut En instance
Date de dépôt 2025-03-01
Date de la première publication 2026-09-03
Propriétaire Microsoft Technology Licensing, LLC (USA)
Inventeur(s)
  • Pathak, Sayan Dev
  • Kesavamoorthy, Harini
  • Basoglu, Christopher Hakan
  • Vikram, Ayush
  • Shah, Amy Parag
  • Kelkar, Rakesh

Abrégé

A speculative decoding technique generates tokens of a response using a verifying model and drafting model. In operation, the verifying model receives a set of draft tokens produced by the drafting model. The verifying model then verifies whether the draft tokens are correct by comparing probability information generated by the verifying model with probability information generated by the drafting model. The verifying model then determines whether any draft token that is rejected by the verifying is otherwise accepted based on a specified matching criterion. The above process is repeated one or more times to generate the response. The technique has the overall effect of expanding a number of draft tokens that are accepted, thereby reducing use of resources and deceasing latency.

Classes IPC  ?

  • G06F 40/284 - Analyse lexicale, p. ex. segmentation en unités ou cooccurrence
  • G06F 16/3329 - Formulation de requêtes en langage naturel
  • G06F 16/34 - NavigationVisualisation à cet effet

34.

DIRECTIVE GENERATIVE THREAD-BASED USER ASSISTANCE SYSTEM

      
Numéro d'application 19661543
Statut En instance
Date de dépôt 2026-04-28
Date de la première publication 2026-09-03
Propriétaire Microsoft Technology Licensing, LLC (USA)
Inventeur(s)
  • Amatriain-Rubio, Xavier
  • Bremer, Christopher M.
  • Lopez, Carlos H.
  • Monestie, Pierre Y.
  • Teclemariam, Laura
  • Kasera, Yamini
  • Kazi, Michaeel
  • Fu, Zhoutong
  • Wu, Muchen
  • Narang, Winnie
  • Tu, Yiyuan
  • Munoz Alcalde, Jaime
  • Pasumarthy, Nitin
  • Bach, Thao
  • Williams, David
  • Gariba, Priyanka

Abrégé

Embodiments of the disclosed technologies include generating a first thread classification prompt based on a first thread portion of an online dialog involving a user of a computing device, sending the first thread classification prompt to a first large language model, receiving a first thread classification generated and output by the first large language model based on the first thread classification prompt, formulating a plan execution prompt based on the first thread classification, sending the plan execution prompt to a second large language model, receiving a second thread portion generated and output by the second large language model based on the plan execution prompt and the online dialog, and generating a label for a third thread portion of the online dialog.

Classes IPC  ?

  • G06F 40/35 - Représentation du discours ou du dialogue
  • G06F 9/445 - Chargement ou démarrage de programme
  • G06Q 10/0631 - Planification, affectation, distribution ou ordonnancement de ressources d’entreprises ou d’organisations
  • G06Q 10/1053 - Emploi ou embauche

35.

AUTO-PRESENT MODE FOR PRESENTATION APPLICATIONS

      
Numéro d'application 19066733
Statut En instance
Date de dépôt 2025-02-28
Date de la première publication 2026-09-03
Propriétaire Microsoft Technology Licensing, LLC (USA)
Inventeur(s)
  • Kumar, Priyankar
  • Jain, Ankit
  • Biswas, Sanjib
  • Agarwal, Abhishek

Abrégé

The techniques disclosed herein provide a system and method for automated presentation delivery utilizing artificial intelligence and speech processing technologies. The system processes presentation content, delivers it conversationally, and handles real-time audience interactions while maintaining contextual awareness. The disclosed systems enable dynamic presentation experiences by combining large language models with speech processing technologies to create an interactive presentation agent. Embodiments provide an Auto-Present mode in presentation applications that utilize Large Language Models powered AI agent to automatically present the content of a slide deck file, e.g., a PowerPoint file, just like how a human would, including audience interactions, slide navigations, live Question & Answer sessions and human-like narration of the slides.

Classes IPC  ?

  • H04N 7/15 - Systèmes pour conférences
  • G10L 13/08 - Analyse de texte ou génération de paramètres pour la synthèse de la parole à partir de texte, p. ex. conversion graphème-phonème, génération de prosodie ou détermination de l'intonation ou de l'accent tonique

36.

SYSTEMS AND METHODS FOR PROVISIONING A SOVEREIGN CLOUD ROOT CERTIFICATE

      
Numéro d'application 19067825
Statut En instance
Date de dépôt 2025-02-28
Date de la première publication 2026-09-03
Propriétaire Microsoft Technology Licensing, LLC (USA)
Inventeur(s)
  • Liu, Pu
  • Wu, Zhixuan
  • Chen, Buyu
  • Kamma, Vasu Deva Rao
  • Levinn, Benjamin Allen
  • Chavan, Sahil Sandeep

Abrégé

Systems and methods for provisioning a sovereign cloud root certificate, retrieve, during a boot process of a sovereign cloud, a root certificate from a first source; measure a cryptographic measurement of the root certificate in a Trusted Platform Module (TPM) of the sovereign cloud, which is stored in a Platform Configuration Register (PCR) of the TPM; generate a Certificate Signing Request (CSR) including the TPM-stored measurement for a leaf certificate based on the PCR; transmit the CSR to a certificate authority for verification; wherein the CSR is forwarded to a Hardware Attestation Service (HAS) for attestation; receiving an attestation result at the certificate authority, the attestation result indicating whether the CSR is valid; and based on the attestation result, receive by the sovereign cloud, the leaf certificate when the attestation result is positive, or a rejection of the CSR when a discrepancy is detected.

Classes IPC  ?

  • H04L 9/32 - Dispositions pour les communications secrètes ou protégéesProtocoles réseaux de sécurité comprenant des moyens pour vérifier l'identité ou l'autorisation d'un utilisateur du système
  • G06F 21/57 - Certification ou préservation de plates-formes informatiques fiables, p. ex. démarrages ou arrêts sécurisés, suivis de version, contrôles de logiciel système, mises à jour sécurisées ou évaluation de vulnérabilité

37.

PATCHING SOURCE CODE VULNERABILITIES

      
Numéro d'application 19066992
Statut En instance
Date de dépôt 2025-02-28
Date de la première publication 2026-09-03
Propriétaire Microsoft Technology Licensing, LLC (USA)
Inventeur(s)
  • Badawi, Ahmed Mahmoud Abdelmottaleb Mohamed
  • Guibourge, Nicolas Jerome

Abrégé

In various examples there is a computer-implemented method of generating a patch to fix a vulnerability in a downstream software package. An upstream source code and an upstream patch are received. A downstream software package corresponding to the upstream source code is identified. A training shot is selected from a store of training shots. Input for a generative model is generated, the input comprising the training shot and an inference shot, the inference shot comprising the upstream source code, upstream patch, rejected hunks of the upstream patch and downstream source code. The input is provided to the generative model which generates the downstream patch.

Classes IPC  ?

  • G06F 21/57 - Certification ou préservation de plates-formes informatiques fiables, p. ex. démarrages ou arrêts sécurisés, suivis de version, contrôles de logiciel système, mises à jour sécurisées ou évaluation de vulnérabilité

38.

DETECTING AND MITIGATING REGRESSIONS ASSOCIATED WITH CODE CHANGES

      
Numéro d'application 19067237
Statut En instance
Date de dépôt 2025-02-28
Date de la première publication 2026-09-03
Propriétaire Microsoft Technology Licensing, LLC (USA)
Inventeur(s)
  • Mutha, Akshay Navneetlal
  • Moulhaud, Patrick Eugene
  • Kakhandiki, Abhishek Anil
  • Munot, Aditya Rajkumar
  • Kim, Minjeong

Abrégé

The present disclosure relates to systems, methods, and computer-readable media for detecting and mitigation regression in a computer system. In particular, this disclosure relates to correlating changes to subroutines to log instances from a trace log and determining, based on these correlations, whether a subroutine or set of subroutines has caused a regression as a result of a change to the subroutine(s). The examples described herein involve determining which usage metrics are attributable to specific subroutine changes and detecting whether a regression has occurred. The disclosure further involves performing or causing to perform mitigation actions that reduce a negative impact of the regression as a result of the change(s) to the subroutine(s).

Classes IPC  ?

39.

LOAD BALANCING AND DISTRIBUTING ISSUE REQUESTS FOR RESOLUTION BY ASSIGNABLE RESOURCES

      
Numéro d'application 19066349
Statut En instance
Date de dépôt 2025-02-28
Date de la première publication 2026-09-03
Propriétaire Microsoft Technology Licensing, LLC (USA)
Inventeur(s)
  • Daouphars, Julien
  • Moore, Josh Charles
  • Nag, Amitabh
  • Veluswami, Senthilkumar
  • Lin, Zhenfeng
  • Patel, Rachit Narendrakumar

Abrégé

Load balancing and distributing issue requests for resolution by assignable resources is described. A multimodal model determines attributes of an input issue request. A lower dimensional representation of the input issue request is generated based on the attributes; and compared to other lower dimensional representations of other issue requests to identify prior similar issue requests. The multi modal model outputs indications of similarity strength for the prior similar issue requests, and the resources assigned to resolve the prior similar issue requests. An expertise level for each assignable resource is determined based on the similarity strength and the previously assigned resources. A routing metric for each assignable resource is determined based on a combination of the expertise level and an availability of each assignable resource; and the input issue request is routed to an assignable resource in the assignable resources based on the routing metric.

Classes IPC  ?

  • G06F 9/50 - Allocation de ressources, p. ex. de l'unité centrale de traitement [UCT]

40.

FACILITATING EFFECTIVE GENERATION OF IMAGES BASED ON A DESIRED COLOR SET

      
Numéro d'application 19064394
Statut En instance
Date de dépôt 2025-02-26
Date de la première publication 2026-09-03
Propriétaire Microsoft Technology Licensing, LLC (USA)
Inventeur(s)
  • Cheng, Mingxi
  • Yuan, Yuhui
  • Huang, Danqing
  • Tandon, Varun
  • Li, Ji

Abrégé

Methods, computer systems, and computer storage media are provided for generating new images in association with a desired set of colors. In embodiments, a text prompt including a first color signal representing a textual description of a color and a second color signal representing a color code associated with the color is generated. Further, an image prompt is generated that includes a color-enhanced reference image generated in accordance with the color. The text prompt including the first color signal and the second color signal and the image prompt including the color-enhanced reference image are used to generate a new image, which may be presented via a user interface.

Classes IPC  ?

  • G06T 11/00 - Génération d'images bidimensionnelles [2D]
  • G06T 11/40 - Remplissage d'une surface plane par addition d'attributs de surface, p. ex. de couleur ou de texture
  • G06T 11/60 - Édition de figures et de texteCombinaison de figures ou de texte

41.

COMPOSITIONAL PROGRAM SYNTHESIS ENGINE IN AN ARTIFICIAL INTELLIGENCE SYSTEM

      
Numéro d'application 19067689
Statut En instance
Date de dépôt 2025-02-28
Date de la première publication 2026-09-03
Propriétaire Microsoft Technology Licensing, LLC (USA)
Inventeur(s)
  • Tiwari, Ashish
  • Gulwani, Sumit
  • Le, Vu Minh
  • Verbruggen, Gust Ben Anneloes

Abrégé

Methods, systems, and computer storage media for providing compositional program synthesis using a compositional program synthesis engine in an artificial intelligence (AI) system are described. Compositional program synthesis in this context is guided by a Large Language Model (LLL) and refers to the iterative process of using the LLM to generate, refine, and compose program segments, addressing errors by systematically breaking down tasks, salvaging correct parts, and synthesizing subprograms that are integrated using composition operators until a program satisfies the given specification. The compositional program synthesis engine iteratively generates, refines, and integrates program components by leveraging program decomposition, synthesis of subprograms, and composition operators to construct a program that meets the specified requirements. Compositional program synthesis engine supports several decomposition strategies associated with refining suffixes, refining prefixes, and IfThenElse distinct cases; and for synthesizing the new candidate programs the engine supports program composition operators including sequential composition and conditional composition.

Classes IPC  ?

  • G06F 8/35 - Création ou génération de code source fondée sur un modèle

42.

SEMANTIC FILE PLACEHOLDERS

      
Numéro d'application US2025058668
Numéro de publication 2026/182810
Statut Délivré - en vigueur
Date de dépôt 2025-12-09
Date de publication 2026-09-03
Propriétaire MICROSOFT TECHNOLOGY LICENSING, LLC (USA)
Inventeur(s) Shah, Hardik Rajiv

Abrégé

Information is received that indicates files that are associated with a context of a user's activity. Based on the information, a temporary placeholder folder and placeholder files corresponding to the files are generated. The temporary placeholder folder and placeholder files are rendered on a user interface indicating the placeholder folder and placeholder files as folders and files within a file system running on the device. The placeholder files are not hydrated on the device. A mapping of the placeholder files to underlying files represented by the placeholder files is maintained.

Classes IPC  ?

  • H04W 12/10 - Intégrité
  • G06F 16/16 - Opérations sur les fichiers ou les dossiers, p. ex. détails des interfaces utilisateur spécialement adaptées aux systèmes de fichiers
  • G06F 16/178 - Techniques de synchronisation des fichiers dans les systèmes de fichiers
  • H04L 67/1095 - Réplication ou mise en miroir des données, p. ex. l’ordonnancement ou le transport pour la synchronisation des données entre les nœuds du réseau

43.

MIGRATING A CONFIDENTIAL VIRTUAL MACHINE FROM CLOUD TO AN EDGE DEVICE

      
Numéro d'application US2025058667
Numéro de publication 2026/182809
Statut Délivré - en vigueur
Date de dépôt 2025-12-09
Date de publication 2026-09-03
Propriétaire MICROSOFT TECHNOLOGY LICENSING, LLC (USA)
Inventeur(s)
  • Lin, Jin
  • Viswanathan, Giridhar
  • Ebersol, Michael Bishop

Abrégé

Methods and systems are disclosed for migrating a confidential virtual machine (CVM) to a remote computer system. A method that is implemented in a virtualized firmware layer of a CVM involves receiving a migration signal from an orchestration component at a host partition, validating the security state of the remote system, and upon validation, removing a first secret from the virtualized firmware layer. The guest state file associated with the CVM is encrypted using a second secret from the remote system, capturing the state of the firmware layer. Subsequently, the CVM migration is initiated by transmitting the encrypted guest state file to the remote system, ensuring a secure and confidential transfer of the CVM to the designated destination.

Classes IPC  ?

  • G06F 21/53 - Contrôle des utilisateurs, des programmes ou des dispositifs de préservation de l’intégrité des plates-formes, p. ex. des processeurs, des micrologiciels ou des systèmes d’exploitation au stade de l’exécution du programme, p. ex. intégrité de la pile, débordement de tampon ou prévention d'effacement involontaire de données par exécution dans un environnement restreint, p. ex. "boîte à sable" ou machine virtuelle sécurisée
  • G06F 9/455 - ÉmulationInterprétationSimulation de logiciel, p. ex. virtualisation ou émulation des moteurs d’exécution d’applications ou de systèmes d’exploitation
  • G06F 21/57 - Certification ou préservation de plates-formes informatiques fiables, p. ex. démarrages ou arrêts sécurisés, suivis de version, contrôles de logiciel système, mises à jour sécurisées ou évaluation de vulnérabilité

44.

AUTOMATICALLY CHOOSING RANKING STRATEGY TO FILL LANGUAGE MODEL PROMPTS WITH MOST RELEVANT DATA

      
Numéro d'application US2025059070
Numéro de publication 2026/182813
Statut Délivré - en vigueur
Date de dépôt 2025-12-11
Date de publication 2026-09-03
Propriétaire MICROSOFT TECHNOLOGY LICENSING, LLC (USA)
Inventeur(s)
  • Ho, Kwan Chak Vincent
  • Braunhofer, Matthias
  • Grell, Stephen
  • Ronen, Royi

Abrégé

A data processing system implements receiving a first prompt template; comparing features of the first prompt template with features of a plurality of second prompt templates of a prompt template dataset to identify a set of similar prompt templates, associating a set of candidate ranking strategies with the first prompt template; in response to a plurality of requests to hydrate the first prompt template, identify a ranking strategy from the set of candidate ranking strategies to associate with the first prompt template: receiving user feedback received in response to hydrating the first prompt template using the set of candidate ranking strategies; selecting a ranking strategy from among the set of candidate ranking strategies based on the user feedback; and utilizing the ranking strategy selected from among the set of candidate ranking strategies to rank the data in response to subsequent requests to hydrate the first prompt template.

Classes IPC  ?

45.

HEAT SINK AND THERMAL MANAGEMENT DEVICE COMPRISING THE HEAT SINK

      
Numéro d'application US2025059075
Numéro de publication 2026/182818
Statut Délivré - en vigueur
Date de dépôt 2025-12-11
Date de publication 2026-09-03
Propriétaire MICROSOFT TECHNOLOGY LICENSING, LLC (USA)
Inventeur(s)
  • Farias Moguel, Oscar
  • Hurbi, Erin Elizabeth
  • Schubert, Alexis Grace
  • Trieu, Dennis

Abrégé

A device may include a plurality of dissociated unitary cells adjacent to one another. A dissociated unitary cell may include a base supporting a body having at least one sidewall. A dissociated unitary cell may include a top surface. A dissociated unitary cell may include a plurality of fins to direct a cooling fluid through the body in a three-dimensional flow path through the plurality of dissociated unitary cells.

Classes IPC  ?

46.

GENERATING AN LLM AGENT HUB AND AGENT WORKFLOW

      
Numéro d'application US2025059074
Numéro de publication 2026/182817
Statut Délivré - en vigueur
Date de dépôt 2025-12-11
Date de publication 2026-09-03
Propriétaire MICROSOFT TECHNOLOGY LICENSING, LLC (USA)
Inventeur(s)
  • Sankaran, Anush
  • Abdi, Amir Hossein
  • Wang, Tong
  • Albada, Michael Charles

Abrégé

Techniques for automatically enhancing a hub of LLM agents are disclosed. A service accesses a computer-based task that includes a set of parameters and requirements. The service accesses the hub of LLM agents. The service queries the hub of LLM agents using the set of parameters and requirements to identify one or more LLM agents whose functionalities and score cards are determined to satisfy the set of parameters and requirements. Based on the query, the service identifies a set of LLM agents that are tasked with attempting to generate a solution for the computer-based task. The service tasks the set of LLM agents to operate in an attempt to generate the solution for the computer-based task.

Classes IPC  ?

47.

DATA TRANSMISSION THROUGH SUPERCONDUCTING CABLES

      
Numéro d'application US2025059073
Numéro de publication 2026/182816
Statut Délivré - en vigueur
Date de dépôt 2025-12-11
Date de publication 2026-09-03
Propriétaire MICROSOFT TECHNOLOGY LICENSING, LLC (USA)
Inventeur(s) Nagimov, Ruslan

Abrégé

Technology is disclosed for data transmission over superconducting cables without a dedicated data transmission line. Control data associated with the superconducting cables is transmitted between terminations of the superconducting cable. In some embodiments, inductive coils at the termination may be used to superimpose data at a higher frequency than the electrical power for transmission over the superconductors to other terminations. In other embodiments, changes in parameters of the cryogenic fluid used to cool the superconductors may be used to transmit control data between terminations. For example, pressure changes and/or flow rate changes may be used to encode the control data. In either case, the dedicated transmission line typically accompanying a superconducting cable is not needed.

Classes IPC  ?

  • H02G 15/34 - Accessoires de câble pour câbles cryogéniques

48.

Hybrid flexible energy solution using geothermal and hydrogen for data center applications

      
Numéro d'application 19209118
Numéro de brevet 12723572
Statut Délivré - en vigueur
Date de dépôt 2025-05-15
Date de la première publication 2026-09-01
Date d'octroi 2026-09-01
Propriétaire MICROSOFT TECHNOLOGY LICENSING, LLC (USA)
Inventeur(s)
  • Nasr Azadani, Ehsan
  • Maleky, Sonia
  • James, Sean Michael

Abrégé

Technology is disclosed for providing high availability electrical power to a data center using renewable energy sources. A system includes a geothermal extraction well and an underground hydrogen storage. In some cases, the underground hydrogen storage leverages the exterior cavity of the geothermal extraction well created during a pipe-in-pipe drilling process. The system further includes a turbine-generator system that converts the geothermal energy from the well into primary power for the data center. When a control system detects a disruption in the primary power, a fuel cell is used to generate backup power for the data center by leveraging the hydrogen in the underground storage to generate electricity. In some cases, a battery provides transitional backup power while the fuel cell performs its startup process.

Classes IPC  ?

  • F03G 4/00 - Dispositifs produisant une puissance mécanique à partir d'énergie géothermique
  • H02J 3/0012 -
  • H02J 3/32 - Dispositions pour l'équilibrage de charge dans un réseau par emmagasinage d'énergie utilisant des batteries avec moyens de conversion
  • H02J 3/38 - Dispositions pour l’alimentation en parallèle d’un seul réseau, par plusieurs générateurs, convertisseurs ou transformateurs
  • H02J 3/46 - Dispositions pour l’alimentation en parallèle d’un seul réseau, par plusieurs générateurs, convertisseurs ou transformateurs contrôlant la répartition de puissance entre les générateurs, convertisseurs ou transformateurs
  • H02J 13/181 -
  • H02J 15/50 -
  • H02J 101/20 -
  • H02J 101/30 -
  • H02J 105/42 -

49.

LINKEDIN PULSE

      
Numéro de série 50084861
Statut En instance
Date de dépôt 2026-09-01
Propriétaire LinkedIn Corporation (USA)
Classes de Nice  ? 41 - Éducation, divertissements, activités sportives et culturelles

Produits et services

Providing online non-downloadable news articles relating to business, finance, current events, education, entertainment, technology, culture, entrepreneurship, leadership, management, marketing, recruiting, career, and professional development; online publication of journals and non-downloadable articles in the field of business, finance, current events, education, entertainment, technology, culture, entrepreneurship, leadership, management, marketing, recruiting, career, and professional development; publication of online text, graphics, content, information, and multimedia content of business, finance, current events, education, entertainment, technology, culture, entrepreneurship, leadership, management, marketing, recruiting, career, and professional development; publication of online content regarding current events and news, employment, workforce, career and personal development, jobs, finance, economy, careers, and recruiting; Providing online information in the fields of finding finance, employment, staffing, recruiting, career development, professional networking, and employment training for job seekers to improve employment skills in the field of professional development; providing online digital libraries containing online training courses, videos, articles, and customized content in the field of employment skills; providing online resources in the fields of finance, business skills, technical skills, and professional development; providing online educational programs in the fields of finance, employment, staffing, recruiting, career development, professional networking, and employment training for job seekers to improve employment skills in the field of professional development; education and entertainment services, namely, providing non-downloadable publications in the nature of newsletters featuring text, graphics, audio and video clips featuring news, information, and commentary relating to business, finance, current events, education, entertainment; technology, culture, entrepreneurship, leadership, management, marketing, recruiting, career and professional development; providing online educational courses and educational course materials in the fields of finance, employment, staffing, recruiting, career development, and professional networking; providing educational and professional development training assessments; providing educational and professional conversation assessments rendered with Artificial Intelligence (AI); entertainment services, namely, providing podcasts and webcasts in the field of wide field of topics particularly finance, employment, recruitment of personnel, careers, job resources and listings, news and current events, professional networking; Providing educational content and information online in the field of finance, global labor markets, workforce reports, skills reports, green skills reports, economic development, and the global economy; providing an online newsletter featuring financial information, economic data, economic insights, workforce data and research, data sets, and policy information on the global economy; Providing educational and learning services, namely, providing a website featuring generative artificial intelligence that develops and simulates speaking, listening, interpersonal and conversational skills; educational services, namely, providing training and education preparation programs to certify job skills online; Business education and training services; Educational services in the nature of business schools; Teaching and training in business; Providing continuing business education courses; college level educational services, namely, conducting distance learning instruction; Educating at university or colleges; Providing information about education; Educational services, namely, conducting classes, seminars, conferences, and workshops in the field of business and distribution of educational materials in connection therewith

50.

CONSTRAINTS ON LOCATIONS OF REFERENCE BLOCKS FOR INTRA BLOCK COPY PREDICTION

      
Numéro d'application 19651424
Statut En instance
Date de dépôt 2026-04-17
Date de la première publication 2026-08-27
Propriétaire Microsoft Technology Licensing, LLC (USA)
Inventeur(s)
  • Zhou, You
  • Lin, Chih-Lung
  • Lee, Ming-Chieh

Abrégé

When encoding/decoding a current block of a current picture using intra block copy (“BC”) prediction, the location of a reference block is constrained so that it can be entirely within an inner search area of the current picture or entirely within an outer search area of the current picture, but cannot overlap both the inner search area and the outer search area. In some hardware-based implementations, on-chip memory buffers sample values of the inner search area, and off-chip memory buffers sample values of the outer search area. By enforcing this constraint on the location of the reference block, an encoder/decoder can avoid memory access operations that are split between on-chip memory and off-chip memory when retrieving the sample values of the reference block. At the same time, a reference block close to the current block may be used for intra BC prediction, helping compression efficiency.

Classes IPC  ?

  • H04N 19/176 - Procédés ou dispositions pour le codage, le décodage, la compression ou la décompression de signaux vidéo numériques utilisant le codage adaptatif caractérisés par l’unité de codage, c.-à-d. la partie structurelle ou sémantique du signal vidéo étant l’objet ou le sujet du codage adaptatif l’unité étant une zone de l'image, p. ex. un objet la zone étant un bloc, p. ex. un macrobloc
  • H04N 19/103 - Sélection du mode de codage ou du mode de prédiction
  • H04N 19/105 - Sélection de l’unité de référence pour la prédiction dans un mode de codage ou de prédiction choisi, p. ex. choix adaptatif de la position et du nombre de pixels utilisés pour la prédiction
  • H04N 19/139 - Analyse des vecteurs de mouvement, p. ex. leur amplitude, leur direction, leur variance ou leur précision
  • H04N 19/593 - Procédés ou dispositions pour le codage, le décodage, la compression ou la décompression de signaux vidéo numériques utilisant le codage prédictif mettant en œuvre des techniques de prédiction spatiale

51.

Al-POWERED CONCEPT-DRIVEN VISUALIZATION AUTHORING

      
Numéro d'application 19651546
Statut En instance
Date de dépôt 2026-04-17
Date de la première publication 2026-08-27
Propriétaire Microsoft Technology Licensing, LLC (USA)
Inventeur(s)
  • Lee, Bongshin
  • Wang, Chenglong
  • Thompson, John Roger

Abrégé

A method, computer program product, and computing system for processing a request to generate a visualization concerning a plurality of data concepts. A new data concept for the visualization is generated by transforming an existing data concept using a program synthesizer and a generative model. The visualization is rendered by processing a mapping of the new data concept to a visual channel of the visualization.

Classes IPC  ?

  • G06F 16/215 - Amélioration de la qualité des donnéesNettoyage des données, p. ex. déduplication, suppression des entrées non valides ou correction des erreurs typographiques
  • G06N 3/02 - Réseaux neuronaux
  • G06N 3/0475 - Réseaux génératifs

52.

TEMPERATURE SENSING OF REGIONS WITHIN A SUPERCONDUCTING INTEGRATED CIRCUIT USING IN-SITU RESONATORS

      
Numéro d'application 19652121
Statut En instance
Date de dépôt 2026-04-20
Date de la première publication 2026-08-27
Propriétaire Microsoft Technology Licensing, LLC (USA)
Inventeur(s)
  • Griggio, Flavio
  • Rouse, Richard P.
  • Talanov, Vladimir V.
  • Garcia, Cougar Alessandro Tomas
  • Strong, Joshua A.

Abrégé

Circuits and methods related to temperature sensing of regions within a superconducting integrated circuit (IC) using in-situ resonators are described. An example relates to a superconducting IC including a first resonator having a first spatial location in relation to a floor plan of the superconducting IC. The superconducting IC further includes a second resonator having a second spatial location in relation to the floor plan of the superconducting IC. The superconducting IC further includes a feed line configured to provide a test signal to each of the first resonator and the second resonator in order to elicit a frequency response from the first resonator or the second resonator, where the frequency response is correlated with a first region within the superconducting IC corresponding to the first spatial location or with a second region within the superconducting IC corresponding to the second spatial location.

Classes IPC  ?

  • H10N 60/80 - Détails de structure
  • G01K 7/01 - Mesure de la température basée sur l'utilisation d'éléments électriques ou magnétiques directement sensibles à la chaleur utilisant des éléments semi-conducteurs à jonctions PN
  • H10N 60/12 - Dispositifs à effet Josephson
  • H10N 60/85 - Matériaux actifs supraconducteurs
  • H10N 69/00 - Dispositifs intégrés, ou ensembles de plusieurs dispositifs, comportant au moins un élément supraconducteur couvert par le groupe

53.

INTELLIGENT AGENT FOR AUTO-SUMMONING TO MEETINGS

      
Numéro d'application 19652319
Statut En instance
Date de dépôt 2026-04-20
Date de la première publication 2026-08-27
Propriétaire Microsoft Technology Licensing, LLC (USA)
Inventeur(s)
  • White, Ryen W.
  • Haslhofer, Gerald

Abrégé

An intelligent agent may assume a ghost presence in a meeting on behalf of a non-participant, monitor data communications between participants of the meeting, and identify appropriate triggers or events relating to the non-participant. For example, the agent may detect questions directed at the non-participant or that the non-participant has the knowledge to answer. The non-participant may be auto-summoned with respect to the meeting when the events relating to the non-participant are identified. The auto-summoning may be performed by communicating information about identified event to the non-participant, for example in real-time. The communication about the identified event may be transmitted over any of a variety of communication channels or modalities, including instant message chat, SMS, phone call, establishing a video call, or pager.

Classes IPC  ?

  • H04L 65/403 - Dispositions pour la communication multipartite, p. ex. pour les conférences
  • H04L 12/18 - Dispositions pour la fourniture de services particuliers aux abonnés pour la diffusion ou les conférences
  • H04L 65/1069 - Établissement ou terminaison d'une session
  • H04L 65/1093 - Procédures en session en ajoutant des participantsProcédures en session en supprimant des participants
  • H04L 65/401 - Prise en charge des services ou des applications dans laquelle les services impliquent une session principale en temps réel et une ou plusieurs sessions parallèles additionnelles en temps réel ou sensibles au temps, p. ex. accès partagé à un tableau blanc ou mise en place d’une sous-conférence
  • H04L 67/306 - Profils des utilisateurs
  • H04L 67/54 - Gestion de la présence, p. ex. surveillance ou enregistrement pour la réception des informations de connexion des utilisateurs ou état de connexion des utilisateurs

54.

RESOURCE MANAGEMENT FOR TRAINING MACHINE LEARNING MODELS

      
Numéro d'application 18726406
Statut En instance
Date de dépôt 2023-02-03
Date de la première publication 2026-08-27
Propriétaire Microsoft Technology Licensing, LLC (USA)
Inventeur(s)
  • Constantin, Ana-Maria
  • Ghelman, Raphael
  • Goyal, Pulak

Abrégé

A system and method for managing resources for training machine learning (ML) models is described. A processor collects time-series data corresponding to an interval of time, generates a partitioning schema file for the collected time-series data, partitions the collected time-series data according to the partitioning schema file based on metadata characteristics of the time-series data, and transmits the partitioned time-series data and the partitioning schema file to a storage device. The processor further assigns a plurality of worker nodes to the partitioned time-series data based at least in part on the partitioning schema file stored in the storage device. The worker nodes reconstruct a sequence of time-series data for a plurality of intervals of time from the storage. The intervals include the partitioned time-series data and the previous intervals of time-series data. The worker nodes train, in parallel, a ML model using the reconstructed sequence of time-series data.

Classes IPC  ?

  • G06F 11/34 - Enregistrement ou évaluation statistique de l'activité du calculateur, p. ex. des interruptions ou des opérations d'entrée–sortie
  • G06F 9/50 - Allocation de ressources, p. ex. de l'unité centrale de traitement [UCT]

55.

AUTOMATED DEPLOYMENT AND MAINTENANCE OF A CLOUD FLEET

      
Numéro d'application 19059428
Statut En instance
Date de dépôt 2025-02-21
Date de la première publication 2026-08-27
Propriétaire Microsoft Technology Licensing, LLC (USA)
Inventeur(s)
  • Khandelwal, Yash
  • Patwa, Pritesh
  • Mohammed, Yunus
  • Ramachandran, Rajeesh
  • Sharma, Rahul

Abrégé

Automated deployment and maintenance of a cloud fleet, including: receiving a request to generate a cloud fleet in a cloud computing environment, the request including a listing of selectable cloud computing instance configurations, an allocation strategy, and a resource allocation; selecting, for each cloud computing instance configuration of one or more cloud computing instance configurations included in the listing of selectable cloud computing instance configurations, based a capacity of the cloud computing environment, a corresponding number of instances to satisfy the resource allocation, including selecting one or more cloud computing instance configurations from the listing of selectable cloud computing instance configurations based on the allocation strategy; and creating based on the corresponding number of instances for each cloud computing instance configuration, the cloud fleet comprising at least one of: one or more on-demand cloud computing instances and one or more spot cloud computing instances.

Classes IPC  ?

  • H04L 41/085 - Récupération de la configuration du réseauSuivi de l’historique de configuration du réseau
  • G06F 9/50 - Allocation de ressources, p. ex. de l'unité centrale de traitement [UCT]
  • H04L 47/76 - Contrôle d'admissionAllocation des ressources en utilisant l'allocation dynamique des ressources, p. ex. renégociation en cours d'appel sur requête de l'utilisateur ou sur requête du réseau en réponse à des changements dans les conditions du réseau
  • H04L 67/10 - Protocoles dans lesquels une application est distribuée parmi les nœuds du réseau

56.

THREAT EMULATION ENGINE(S) FOR EVALUATING VULNERABILITIES IN ARTIFICIAL INTELLIGENCE MODELS

      
Numéro d'application 19059530
Statut En instance
Date de dépôt 2025-02-21
Date de la première publication 2026-08-27
Propriétaire Microsoft Technology Licensing, LLC (USA)
Inventeur(s)
  • Natarajan, Sasikumar
  • Karabey, Bugra
  • Gangwani, Tvisha Rajesh
  • Garcia Lazo, Edir Vincio
  • Mansueto, Jenna Sara

Abrégé

Systems and methods herein provide a threat emulation engine and its related functions. In an aspect, a threat emulation engine is provided for detecting vulnerabilities of a target artificial intelligence (AI) model. For example, the threat emulation engine identifies a first adversarial action to identify vulnerabilities and instructs a first attack agent to generate a first adversarial prompt to perform a first adversarial action for detecting the vulnerability. The threat emulation engine then submits the first adversarial prompt as an input into the target AI model and responsively receives a response from the target AI model. The threat emulation engine generates a score for the response in view of the adversarial action. Using the score, the threat emulation engine detects one or more vulnerabilities of the target AI model.

Classes IPC  ?

  • G06F 21/57 - Certification ou préservation de plates-formes informatiques fiables, p. ex. démarrages ou arrêts sécurisés, suivis de version, contrôles de logiciel système, mises à jour sécurisées ou évaluation de vulnérabilité

57.

ENABLING DISPLAYS FROM MULTIPLE CLIENT DEVICES TO INTERACT WITH A VIRTUAL MACHINE

      
Numéro d'application 19059644
Statut En instance
Date de dépôt 2025-02-21
Date de la première publication 2026-08-27
Propriétaire Microsoft Technology Licensing, LLC. (USA)
Inventeur(s)
  • Patnaik, Sandeep
  • Hammond, Andrew Charles
  • Marchese, Jordan Emil
  • Gacad-Sioson, Angelo Alberto Vergel De Dios

Abrégé

The technology described herein enables a remote desktop application to provide visual content to displays associated with multiple client devices, not just the primary client device serving as the active endpoint. Remote desktop software allows a user to access and control a computer or server from a remote location. Conventionally, a remote desktop session is limited to display of content through displays communicatively coupled to the primary client. The technology described herein expands display options to include displays associated with a user's other client devices that have a remote desktop application installed. For example, a user may access a virtual machine on a primary client but use the screen on a secondary client to view additional content provided by the virtual machine.

Classes IPC  ?

  • G06F 9/451 - Dispositions d’exécution pour interfaces utilisateur
  • G06F 9/455 - ÉmulationInterprétationSimulation de logiciel, p. ex. virtualisation ou émulation des moteurs d’exécution d’applications ou de systèmes d’exploitation

58.

SOURCE CODE VIEW PARTITIONING FOR PRODUCTIVE INNER LOOP IN HIGH PERFORMANCE SYSTEMS

      
Numéro d'application 19059757
Statut En instance
Date de dépôt 2025-02-21
Date de la première publication 2026-08-27
Propriétaire MICROSOFT TECHNOLOGY LICENSING, LLC (USA)
Inventeur(s)
  • Todirel, Ion
  • Mihalcea, Bogdan Ionut

Abrégé

Systems and methods are provided for facilitating the management of code during software development by dynamically partitioning the code and by generating visualizations of logical presentations of the partitioned code. Context and scope are determined for the code. The code is partitioned according to the determined context and scope. Partitioned segments are presented within a coherent virtual file view while omitting less relevant code from the coherent virtual file view. The partitioned view can help facilitate navigation and editing efficiencies during code development, particularly for large source files.

Classes IPC  ?

  • G06F 8/30 - Création ou génération de code source

59.

GRAPHICALLY REPRESENTING AN AI AGENT PARTICIPANT IN A COLLABORATION SESSION

      
Numéro d'application 19059918
Statut En instance
Date de dépôt 2025-02-21
Date de la première publication 2026-08-27
Propriétaire MICROSOFT TECHNOLOGY LICENSING, LLC (USA)
Inventeur(s)
  • Rosenstein, Daniel
  • Ortega, Richard Jason

Abrégé

A system implements techniques for executing a collaboration session between at least one human participant, at least one robotic device participant, and at least one artificial intelligence agent participant. The collaboration session can be executed in relation to a mission to be completed within a geographical environment. The system graphically represents artificial intelligence agent participants, in the context of the collaboration session, based on different types (e.g., a general-purpose artificial intelligence agent participant, a specific-purpose artificial intelligence agent participant). The graphical representations of artificial intelligence agent participants ensures smooth collaboration and provides an element of a visual feedback, to human participants, as to which artificial intelligence agent participants are actively engaged and/or what the actively engaged artificial intelligence agent participants are currently doing to in the context of the collaboration session.

Classes IPC  ?

  • G06T 13/40 - Animation tridimensionnelle [3D] de personnages, p. ex. d’êtres humains, d’animaux ou d’êtres virtuels
  • G06T 13/80 - Animation bidimensionnelle [2D], p. ex. utilisant des motifs graphiques programmables
  • H04L 65/1093 - Procédures en session en ajoutant des participantsProcédures en session en supprimant des participants
  • H04L 65/403 - Dispositions pour la communication multipartite, p. ex. pour les conférences

60.

COMPUTING SYSTEM FEATURING TRAY-MOUNTED BACKPLANE INTERCONNECTION MODULES

      
Numéro d'application 19060340
Statut En instance
Date de dépôt 2025-02-21
Date de la première publication 2026-08-27
Propriétaire Microsoft Technology Licensing, LLC (USA)
Inventeur(s)
  • Adrian, Jason David
  • Vu, Wilson V.
  • Jaramillo, Joel Jonothan
  • Bojja, Harsha

Abrégé

A computing system includes an equipment rack, a plurality of backplane devices mounted to the equipment rack to form a connector array, and a plurality of rack trays mounted to the equipment rack. Each rack tray is dockable with a set of the backplane devices by independently translating relative to the equipment rack along a tray-specific translation path. Computing units and backplane interconnection modules can be mounted to each rack tray. A rear set of connectors of each module connects to a set of connectors of the connector array when the rack tray is docked with the set of backplane devices. Each computing unit is dockable with a module by independently translating relative to the rack tray along a unit-specific translation path. Each computing unit includes a set of connectors that connect to a unit-specific set of connectors of the module when the computing unit is docked with the module.

Classes IPC  ?

  • H05K 7/14 - Montage de la structure de support dans l'enveloppe, sur cadre ou sur bâti

61.

AUTO-COMPLETION OF FORM FIELDS

      
Numéro d'application 19061349
Statut En instance
Date de dépôt 2025-02-24
Date de la première publication 2026-08-27
Propriétaire Microsoft Technology Licensing, LLC (USA)
Inventeur(s)
  • Gu, Liang
  • Hohensee, Matthew Reinhard
  • Imse, Nathan Joseph

Abrégé

Techniques for providing autocomplete predictions in a web form in a low latency manner are disclosed. A service accesses a field in the web form. The service causes its client device to operate in an active state in which the client device is permitted to submit autocomplete prediction requests to a server. Prior to receiving user input directed to the field, the service receives an indexed data structure comprising autocomplete predictions for the field. The service causes the client device to then operate in a paused state. The indexed data structure is saved locally. The service then locally queries the locally saved data structure to display predictions for the field and avoids sending network calls to the server for more predictions.

Classes IPC  ?

  • G06F 40/274 - Conversion de symboles en motsAnticipation des mots à partir des lettres déjà entrées
  • G06F 3/023 - Dispositions pour convertir sous une forme codée des éléments d'information discrets, p. ex. dispositions pour interpréter des codes générés par le clavier comme codes alphanumériques, comme codes d'opérande ou comme codes d'instruction
  • G06F 40/174 - Remplissage de formulairesFusion

62.

CONTEXT-AWARE RENAMING OF OBJECTS IN APPLICATIONS

      
Numéro d'application 19061511
Statut En instance
Date de dépôt 2025-02-24
Date de la première publication 2026-08-27
Propriétaire Microsoft Technology Licensing, LLC (USA)
Inventeur(s)
  • Cooper, Emma Margaret Belle
  • Malik, Mansi
  • Lin, Chen-Mi
  • Patel, Akshar Virendrabhai
  • Fu, Zhiqi
  • Truong, Anh Ngoc Tuan
  • Pakhare, Shantanu Kiran
  • Dhawan, Jayant
  • Ansu, Anshuman

Abrégé

A system may access names of the named objects stored in memory and context information within the application including object attributes of the named objects and an object hierarchy specifying hierarchical relationships among the named objects. The system may generate a generative artificial intelligence model input including at least a portion of the context information and request generation of one or more suggested names based on the at least the portion of the context information included in the generative artificial intelligence model input. The system may present the one or more suggested names for the named object. The system may receive a selection of a suggested name to yield a selected suggested name corresponding to the named object. The system may rename the named object in the memory with the selected suggested name.

Classes IPC  ?

63.

COMPUTING DEVICE FAN CONTROL

      
Numéro d'application 19062459
Statut En instance
Date de dépôt 2025-02-25
Date de la première publication 2026-08-27
Propriétaire Microsoft Technology Licensing, LLC (USA)
Inventeur(s)
  • Nielsen, Gregory Allen
  • Shiflett, Kristen Brooke
  • Kacker, Karan
  • Wu, Teng
  • Lu, Yimeng
  • Chong, Cho Yu

Abrégé

A mobile computing device comprises a chassis, a fan inside the chassis, a temperature sensor, a processor, and memory storing instructions executable by the processor to determine a current temperature and a future temperature of the computing device. Operation of the fan is controlled based at least in part on the current temperature and the future temperature of the computing device.

Classes IPC  ?

  • H05K 7/20 - Modifications en vue de faciliter la réfrigération, l'aération ou le chauffage
  • G06F 1/20 - Moyens de refroidissement

64.

CROSS-PLATFORM NEURAL CODECS USING TRANSMITTED ENTROPY DISTRIBUTION PARAMETERS

      
Numéro d'application 19063070
Statut En instance
Date de dépôt 2025-02-25
Date de la première publication 2026-08-27
Propriétaire Microsoft Technology Licensing, LLC (USA)
Inventeur(s)
  • Pärnamaa, Tanel
  • Indenbom, Evgenii
  • Lumiste, Martin
  • Loot, Ardi
  • Saabas, Ando

Abrégé

Cross-platform neural network codecs implemented using transmitted entropy distribution parameters are disclosed. In some examples, a neural network codec system is implemented with a first platform used to encode digital media, such as image, video, or other media that is different than a second platform used to decode the digital media. Some of the entropy distribution parameters used to decode the digital media are losslessly coded. In some examples of the disclosed technology, decoding digital media having encoded latents and hyperlatents includes producing entropy distribution parameters from hyperlatents decoded from the digital media that are shared by at least two groups of latents encoded in the digital media and used to decode latents encoded in the digital media.

Classes IPC  ?

  • H04N 19/13 - Codage entropique adaptatif, p. ex. codage adaptatif à longueur variable [CALV] ou codage arithmétique binaire adaptatif en fonction du contexte [CABAC]
  • H04N 19/124 - Quantification
  • H04N 19/154 - Qualité visuelle après décodage mesurée ou estimée de façon subjective, p. ex. mesure de la distorsion
  • H04N 19/196 - Procédés ou dispositions pour le codage, le décodage, la compression ou la décompression de signaux vidéo numériques utilisant le codage adaptatif caractérisés par le procédé d’adaptation, l’outil d’adaptation ou le type d’adaptation utilisés pour le codage adaptatif étant spécialement adaptés au calcul de paramètres de codage, p. ex. en faisant la moyenne de paramètres de codage calculés antérieurement

65.

PACKET MIRRORING IN VIRTUAL NETWORKS USING DISAGGREGATED NETWORK FUNCTIONS

      
Numéro d'application 19063256
Statut En instance
Date de dépôt 2025-02-25
Date de la première publication 2026-08-27
Propriétaire Microsoft Technology Licensing, LLC (USA)
Inventeur(s)
  • Raje, Chaitanya Kiran
  • Tewari, Rishabh
  • Zygmunt, Michal Czeslaw
  • Gupta, Avijit
  • Shrivastava, Pranjal

Abrégé

Packet mirroring in virtual networks (VNets) uses disaggregated network functions, in which packet mirroring functionality is implemented on remotely-located switches positioned as intermediate hops between origin (source) virtual machines (VMs) and destination VMs. An origin VM transmits an original packet to the switch, which acts as a mirroring node and where the mirroring is offloaded to fast hardware. Application-specific integrated circuits (ASICs) may be used for speed and reduced complexity. This approach of leveraging hardware-based mirroring at an intermediary position eliminates the need for mirroring operations on the origin VM or host, preserving bandwidth and computational resources for the primary workload. The original packet, which carries the data intended for the destination VM, is encapsulated twice at the origin-once for transport across a VNet, and again with metadata for the mirroring included within the encapsulating packet. Some examples use Geneve packets, with the mirror metadata within the Geneve header.

Classes IPC  ?

66.

VIRTUAL FUNCTION BINDING BY A RUNTIME FOR ENHANCED RUNTIME PERFORMANCE

      
Numéro d'application 19064170
Statut En instance
Date de dépôt 2025-02-26
Date de la première publication 2026-08-27
Propriétaire Microsoft Technology Licensing, LLC (USA)
Inventeur(s)
  • Natalie, Jesse Tyler
  • Elliott, Jack Andrew

Abrégé

Methods and systems for creating a runtime object for bypassing a runtime and calling directly into a driver. A method includes receiving a call from an application requesting a runtime object, which includes a virtual function for issuing commands to a driver via the runtime. The method also includes creating the runtime object with a first member containing a pointer to a virtual function table in the runtime's memory space. This table maps the virtual function to a memory address in the driver's memory space, corresponding to a function implementation by the driver. Additionally, a second member includes a pointer to another memory address in the driver's memory space, corresponding to an internal driver object related to the runtime object. The method also includes returning a memory address corresponding to the runtime object to the application.

Classes IPC  ?

  • G06F 9/48 - Lancement de programmes Commutation de programmes, p. ex. par interruption

67.

MIGRATING A CONFIDENTIAL VIRTUAL MACHINE FROM CLOUD TO AN EDGE DEVICE

      
Numéro d'application 19064454
Statut En instance
Date de dépôt 2025-02-26
Date de la première publication 2026-08-27
Propriétaire Microsoft Technology Licensing, LLC (USA)
Inventeur(s)
  • Lin, Jin
  • Viswanathan, Giridhar
  • Ebersol, Michael Bishop

Abrégé

Methods and systems are disclosed for migrating a confidential virtual machine (CVM) to a remote computer system. A method that is implemented in a virtualized firmware layer of a CVM involves receiving a migration signal from an orchestration component at a host partition, validating the security state of the remote system, and upon validation, removing a first secret from the virtualized firmware layer. The guest state file associated with the CVM is encrypted using a second secret from the remote system, capturing the state of the firmware layer. Subsequently, the CVM migration is initiated by transmitting the encrypted guest state file to the remote system, ensuring a secure and confidential transfer of the CVM to the designated destination.

Classes IPC  ?

  • G06F 9/455 - ÉmulationInterprétationSimulation de logiciel, p. ex. virtualisation ou émulation des moteurs d’exécution d’applications ou de systèmes d’exploitation
  • G06F 21/57 - Certification ou préservation de plates-formes informatiques fiables, p. ex. démarrages ou arrêts sécurisés, suivis de version, contrôles de logiciel système, mises à jour sécurisées ou évaluation de vulnérabilité

68.

AUTOMATIC SYSTEM PROMPT HARDENING FOR GENRATIVE ARTIFICIAL INTELLIGENCE SYSTEMS

      
Numéro d'application 19064472
Statut En instance
Date de dépôt 2025-02-26
Date de la première publication 2026-08-27
Propriétaire Microsoft Technology Licensing, LLC (USA)
Inventeur(s)
  • Harari, Asaf
  • Hen, Idan
  • Brukman, Ariel
  • Keller, Ron

Abrégé

Techniques are disclosed for automatically generating and/or updating system prompts for applications that interface with generative artificial intelligence (AI) models. In an aspect, data associated with an application for facilitating interactions with a generative AI model is received. A security vulnerability is identified based on the data. A system prompt is generated. The system prompt has instructions specifying how the generative AI model is to respond to a user prompt. The instructions include a rule for mitigating the identified security vulnerability. The system prompt is provided to the application, causing the application to provide the system prompt to the generative AI model such that the generative AI model responds to user prompts in accordance with the rule. In a further example, the data corresponds to a communication session between the application and the generative AI model. In another aspect, the rule is determined utilizing the generative AI model.

Classes IPC  ?

  • G06F 21/57 - Certification ou préservation de plates-formes informatiques fiables, p. ex. démarrages ou arrêts sécurisés, suivis de version, contrôles de logiciel système, mises à jour sécurisées ou évaluation de vulnérabilité

69.

SECURITY FEATURE ENFORCEMENT USING AI-BASED SECURITY POLICY GAP SUMMARIZATION

      
Numéro d'application 19065615
Statut En instance
Date de dépôt 2025-02-27
Date de la première publication 2026-08-27
Propriétaire Microsoft Technology Licensing, LLC (USA)
Inventeur(s)
  • Rupela, Anil Narsinhbhai
  • Schorr, Ariel Nathan
  • Jian, Huimin
  • Slater, Sheldon Aare Prescott
  • Konnireddy, Swetha
  • Dhokia, Dilesh
  • Boreddy, Nikhil Reddy

Abrégé

Techniques are described herein that are capable of using an AI model to summarize a gap in a security policy for security feature enforcement. A determination is made that a subset of reference security features is absent from enforced security features that are enforced in a system. The reference security features define a security policy template. The enforced security features define a security policy. A summary of the subset of the reference security features is generated using an AI model. The summary and an explanation may be caused to be presented via a user interface. The explanation indicates that the subset of the reference security features is absent from the enforced security features. The subset of the reference security features is caused to be enforced in the system by redefining the security policy, which comprises adding the subset of the reference security features to the enforced security features.

Classes IPC  ?

  • H04L 9/40 - Protocoles réseaux de sécurité
  • H04L 41/16 - Dispositions pour la maintenance, l’administration ou la gestion des réseaux de commutation de données, p. ex. des réseaux de commutation de paquets en utilisant l'apprentissage automatique ou l'intelligence artificielle

70.

AUTOMATICALLY CHOOSING RANKING STRATEGY TO FILL LANGUAGE MODEL PROMPTS WITH MOST RELEVANT DATA

      
Numéro d'application 19065675
Statut En instance
Date de dépôt 2025-02-27
Date de la première publication 2026-08-27
Propriétaire Microsoft Technology Licensing, LLC (USA)
Inventeur(s)
  • Ho, Kwan Chak Vincent
  • Braunhofer, Matthias
  • Grell, Stephen
  • Ronen, Royi

Abrégé

A data processing system implements receiving a first prompt template; comparing features of the first prompt template with features of a plurality of second prompt templates of a prompt template dataset to identify a set of similar prompt templates, associating a set of candidate ranking strategies with the first prompt template; in response to a plurality of requests to hydrate the first prompt template, identify a ranking strategy from the set of candidate ranking strategies to associate with the first prompt template: receiving user feedback received in response to hydrating the first prompt template using the set of candidate ranking strategies; selecting a ranking strategy from among the set of candidate ranking strategies based on the user feedback; and utilizing the ranking strategy selected from among the set of candidate ranking strategies to rank the data in response to subsequent requests to hydrate the first prompt template.

Classes IPC  ?

71.

HYBRID CONTROL PLANE FOR CLOUD AND EDGE DEPLOYMENTS

      
Numéro d'application 19065866
Statut En instance
Date de dépôt 2025-02-27
Date de la première publication 2026-08-27
Propriétaire Microsoft Technology Licensing, LLC (USA)
Inventeur(s)
  • Qadri, Faraz H.
  • Giner, David B.
  • Navali, Vikas A.
  • Waghmare, Tanmay

Abrégé

Systems and methods are provided for implementing a hybrid control plane for cloud and edge deployments. When a local control plane platform receives, from a requesting device, a request to access a first resource from a cloud-based control plane platform, an authentication proxy of a local resource manager of the local control plane platform maps a first identifier (“ID”) to a second ID. The first ID and second ID are associated with the cloud-based control plane platform and the local control plane platform, respectively. The authentication proxy impersonates the requesting user, by generating a query for the first resource using the second ID, and sending the first query to a local resource provider(s) of the local control plane platform. The local control plane platform receives, from the local resource provider(s), a second resource corresponding to the first resource, and sends the second resource to the requesting device.

Classes IPC  ?

  • G06F 9/50 - Allocation de ressources, p. ex. de l'unité centrale de traitement [UCT]

72.

HYBRID QUERY PROCESSING WITH HARDWARE ACCELERATORS

      
Numéro d'application 19065886
Statut En instance
Date de dépôt 2025-02-27
Date de la première publication 2026-08-27
Propriétaire Microsoft Technology Licensing, LLC (USA)
Inventeur(s)
  • Ding, Bailu
  • Li, Yinan
  • Chaudhuri, Surajit
  • Gehrke, Johannes Ernst

Abrégé

The present disclosure relates to systems and methods that perform hybrid query processing using a central processing unit and a graphics processing unit. The systems and methods produce an offloaded query plan for processing by a graphics processing unit. The systems and methods generate filtered data for the offloaded query plan and transfer the offloaded query plan and the filtered data to the graphics processing unit.

Classes IPC  ?

73.

COMPUTING SYSTEM FOR MANAGING A MEMORY SYSTEM OF A GENERATIVE MODEL

      
Numéro d'application 19211033
Statut En instance
Date de dépôt 2025-05-16
Date de la première publication 2026-08-27
Propriétaire Microsoft Technology Licensing, LLC (USA)
Inventeur(s)
  • Krabach, Brian Scott
  • Jabbour, Michael Jameel
  • Goodner, Marc A
  • Schillace, Samuel Edward

Abrégé

A computing system implements an interaction interface, a client, and the memory system comprising short-term memory, working memory, and long-term memory. The client is configured to receive a request including a message having natural language input from the interaction interface, compile the message into a contextual bundle, input the contextual bundle into the generative model to generate a response, and output the response. The message is appended to the short-term memory, the short-term memory is aggregated into the working memory, and the working memory is stored into the long-term memory based on predetermined criteria. The contextual bundle is compiled to include one or more relevant entries of the long-term memory.

Classes IPC  ?

  • G06F 12/02 - Adressage ou affectationRéadressage

74.

PRINTED CIRCUIT BOARD HARDWARE INTERFACE WITH REDUCED CROSSTALK

      
Numéro d'application US2025058484
Numéro de publication 2026/177785
Statut Délivré - en vigueur
Date de dépôt 2025-12-05
Date de publication 2026-08-27
Propriétaire MICROSOFT TECHNOLOGY LICENSING, LLC (USA)
Inventeur(s) Ouyang, Gong

Abrégé

A hardware interface (200) includes a printed circuit board (PCB) (202), including a plurality of PCB dog-bone structures (211) electrically connecting a plurality of PCB vias (210) to a corresponding plurality of socket pins (208). Each PCB dog-bone structure (211) includes a respective PCB (210), an intermediary trace (214), and a socket interface pad (212) electrically connected to a respective socket pin (208). The plurality of PCB dog-bone structures (211) includes first (300A) and second (300B) PCB dog-bone structures, which respectively include first and second PCB vias and socket interface pads. The first socket interface pad (204A) is adjacent to the second socket interface pad (204B), and the first PCB via (202A) is adjacent to the second PCB via (202B). The first socket interface pad (204A) and the second socket interface pad (204B) are arranged parallel to a first direction (308), and the first PCB via (202A) and the second PCB via (202B) are arranged parallel to a second direction (310B), different from the first direction (308A).

Classes IPC  ?

  • H05K 1/02 - Circuits imprimés Détails
  • H05K 1/11 - Éléments imprimés pour réaliser des connexions électriques avec ou entre des circuits imprimés
  • H05K 3/32 - Connexions électriques des composants électriques ou des fils à des circuits imprimés

75.

GRAPHICALLY REPRESENTING AN AI AGENT PARTICIPANT IN A COLLABORATION SESSION

      
Numéro d'application US2025058488
Numéro de publication 2026/177787
Statut Délivré - en vigueur
Date de dépôt 2025-12-05
Date de publication 2026-08-27
Propriétaire MICROSOFT TECHNOLOGY LICENSING, LLC (USA)
Inventeur(s)
  • Rosenstein, Daniel
  • Ortega, Richard Jason

Abrégé

A system implements techniques for executing a collaboration session between at least one human participant, at least one robotic device participant, and at least one artificial intelligence agent participant. The collaboration session can be executed in relation to a mission to be completed within a geographical environment. The system graphically represents artificial intelligence agent participants, in the context of the collaboration session, based on different types (e.g., a general-purpose artificial intelligence agent participant, a specific-purpose artificial intelligence agent participant). The graphical representations of artificial intelligence agent participants ensures smooth collaboration and provides an element of a visual feedback, to human participants, as to which artificial intelligence agent participants are actively engaged and/or what the actively engaged artificial intelligence agent participants are currently doing to in the context of the collaboration session.

Classes IPC  ?

76.

ENHANCED CONTROLS FOR SENSORY GROUP TIMERS

      
Numéro d'application US2025058496
Numéro de publication 2026/177788
Statut Délivré - en vigueur
Date de dépôt 2025-12-06
Date de publication 2026-08-27
Propriétaire MICROSOFT TECHNOLOGY LICENSING, LLC (USA)
Inventeur(s)
  • Euclide, Edward Richard
  • Kudela, Defne
  • Lau, Tiphanie
  • Steiteyeh, Dima Mohd Said Kamal
  • Porena, Eleonora
  • Hornakova Hruba, Iva

Abrégé

The disclosed techniques provide enhanced controls for sensory group timers. In an online conference, a system allows a user to designate a subgroup comprising a subset of the conference attendees. This subgroup can be a subset of attendees making a presentation in the meeting, a confidential subgroup in an online negotiation meeting, or any other subgroup that want a private group timer only displayed to them while they still maintain communication with the others outside of the subset of attendees. The system allows the subset of attendees to control the group timer that is to be shared only within the designated subset group in the online meeting that includes all of the attendees. The group timer is displayed to the subset without providing notifications showing the other users outside the subgroup that the group timer exists, while the subgroup is still sharing content with the others outside the subgroup.

Classes IPC  ?

  • H04L 12/18 - Dispositions pour la fourniture de services particuliers aux abonnés pour la diffusion ou les conférences
  • H04L 51/224 - Surveillance ou traitement des messages en fournissant une notification sur les messages entrants, p. ex. des poussées de notifications des messages reçus
  • H04L 51/04 - Messagerie en temps réel ou quasi en temps réel, p. ex. messagerie instantanée [IM]

77.

THREAT EMULATION ENGINE(S) FOR EVALUATING VULNERABILITIES IN ARTIFICIAL INTELLIGENCE MODELS

      
Numéro d'application US2025058497
Numéro de publication 2026/177789
Statut Délivré - en vigueur
Date de dépôt 2025-12-06
Date de publication 2026-08-27
Propriétaire MICROSOFT TECHNOLOGY LICENSING, LLC (USA)
Inventeur(s)
  • Natarajan, Sasikumar
  • Karabey, Bugra
  • Gangwani, Tvisha Rajesh
  • Garcia Lazo, Edir Vincio
  • Mansueto, Jenna Sara

Abrégé

Systems and methods herein provide a threat emulation engine and its related functions. In an aspect, a threat emulation engine is provided for detecting vulnerabilities of a target artificial intelligence (AI) model. For example, the threat emulation engine identifies a first adversarial action to identify vulnerabilities and instructs a first attack agent to generate a first adversarial prompt to perform a first adversarial action for detecting the vulnerability. The threat emulation engine then submits the first adversarial prompt as an input into the target AI model and responsively receives a response from the target AI model. The threat emulation engine generates a score for the response in view of the adversarial action. Using the score, the threat emulation engine detects one or more vulnerabilities of the target AI model.

Classes IPC  ?

  • G06F 21/57 - Certification ou préservation de plates-formes informatiques fiables, p. ex. démarrages ou arrêts sécurisés, suivis de version, contrôles de logiciel système, mises à jour sécurisées ou évaluation de vulnérabilité
  • G06N 3/08 - Méthodes d'apprentissage
  • G06N 3/094 - Apprentissage antagoniste
  • G06N 20/00 - Apprentissage automatique
  • H04L 9/40 - Protocoles réseaux de sécurité
  • G06F 21/55 - Détection d’intrusion locale ou mise en œuvre de contre-mesures

78.

CONTEXT-AWARE RENAMING OF OBJECTS IN APPLICATIONS

      
Numéro d'application US2025058498
Numéro de publication 2026/177790
Statut Délivré - en vigueur
Date de dépôt 2025-12-06
Date de publication 2026-08-27
Propriétaire MICROSOFT TECHNOLOGY LICENSING, LLC (USA)
Inventeur(s)
  • Cooper, Emma Margaret Belle
  • Malik, Mansi
  • Lin, Chen-Mi
  • Patel, Akshar Virendrabhai
  • Fu, Zhiqi
  • Truong, Anh Ngoc Tuan
  • Pakhare, Shantanu Kiran
  • Dhawan, Jayant
  • Ansu, Anshuman

Abrégé

A system may access names of the named objects stored in memory and context information within the application including object attributes of the named objects and an object hierarchy specifying hierarchical relationships among the named objects. The system may generate a generative artificial intelligence model input including at least a portion of the context information and request generation of one or more suggested names based on the at least the portion of the context information included in the generative artificial intelligence model input. The system may present the one or more suggested names for the named object. The system may receive a selection of a suggested name to yield a selected suggested name corresponding to the named object. The system may rename the named object in the memory with the selected suggested name.

Classes IPC  ?

  • G06F 8/33 - Éditeurs intelligents
  • G06N 3/00 - Agencements informatiques fondés sur des modèles biologiques
  • G06N 5/00 - Agencements informatiques utilisant des modèles fondés sur la connaissance
  • G06N 20/00 - Apprentissage automatique
  • G06N 99/00 - Matière non prévue dans les autres groupes de la présente sous-classe

79.

AUTO-COMPLETION OF FORM FIELDS

      
Numéro d'application US2025058499
Numéro de publication 2026/177791
Statut Délivré - en vigueur
Date de dépôt 2025-12-06
Date de publication 2026-08-27
Propriétaire MICROSOFT TECHNOLOGY LICENSING, LLC (USA)
Inventeur(s)
  • Gu, Liang
  • Hohensee, Matthew Reinhard
  • Imse, Nathan Joseph

Abrégé

Techniques for providing autocomplete predictions in a web form in a low latency manner are disclosed. A service accesses a field in the web form. The service causes its client device to operate in an active state in which the client device is permitted to submit autocomplete prediction requests to a server. Prior to receiving user input directed to the field, the service receives an indexed data structure comprising autocomplete predictions for the field. The service causes the client device to then operate in a paused state. The indexed data structure is saved locally. The service then locally queries the locally saved data structure to display predictions for the field and avoids sending network calls to the server for more predictions.

Classes IPC  ?

  • G06F 40/174 - Remplissage de formulairesFusion
  • G06F 40/274 - Conversion de symboles en motsAnticipation des mots à partir des lettres déjà entrées

80.

COMPUTING SYSTEM FOR MANAGING A MEMORY SYSTEM OF A GENERATIVE MODEL

      
Numéro d'application US2025058500
Numéro de publication 2026/177792
Statut Délivré - en vigueur
Date de dépôt 2025-12-06
Date de publication 2026-08-27
Propriétaire MICROSOFT TECHNOLOGY LICENSING, LLC (USA)
Inventeur(s)
  • Krabach, Brian Scott
  • Jabbour, Michael Jameel
  • Goodner, Marc A
  • Schillace, Samuel Edward

Abrégé

A computing system (10) implements an interaction interface (26), a client (46), and the memory system (48) comprising short-term memory (50), working memory (52), and long-term memory (54). The client (46) is configured to receive a request (64) including a message (28) having natural language input from the interaction interface (26), compile the message (28) into a contextual bundle (58), input the contextual bundle (58) into the generative model (44d) to generate a response (66), and output the response (66). The message (28) is appended to the short-term memory (50), the short-term memory (50) is aggregated into the working memory (52), and the working memory (52) is stored into the long-term memory (54) based on predetermined criteria. The contextual bundle (58) is compiled to include one or more relevant entries of the long-term memory (54).

Classes IPC  ?

  • G06N 3/045 - Combinaisons de réseaux
  • G06F 12/00 - Accès à, adressage ou affectation dans des systèmes ou des architectures de mémoires
  • G06F 40/00 - Maniement de données en langage naturel
  • G06N 3/0475 - Réseaux génératifs
  • G06N 3/092 - Apprentissage par renforcement
  • G06N 20/00 - Apprentissage automatique

81.

NATURAL LANGUAGE-BASED MANAGEMENT OF COMPUTING RESOURCES EXECUTING RADIO ACCESS NETWORK WORKLOADS

      
Numéro d'application 19644270
Statut En instance
Date de dépôt 2026-04-10
Date de la première publication 2026-08-27
Propriétaire MICROSOFT TECHNOLOGY LICENSING, LLC (USA)
Inventeur(s)
  • Mehrotra, Sanjeev
  • Kalia, Anuj
  • Kotaru, Manikanta

Abrégé

The techniques disclosed herein manage computing environments using a natural language interface. This is achieved through utilizing natural language processing to analyze user generated inputs and generate robust queries. In various examples, the queries can include documentation, diagnostic data, and past interactions to provide custom context to an artificial intelligence application. Accordingly, the query can cause the artificial intelligence application to generate an operation sequence comprising a plurality of commands to interface with a resource management tool and control computing resources and supporting components. In this way, the present techniques can alleviate the technical burden on end users and minimize the risk of errors.

Classes IPC  ?

  • G06F 40/40 - Traitement ou traduction du langage naturel
  • H04W 24/02 - Dispositions pour optimiser l'état de fonctionnement

82.

PERFORMING COMPUTING OPERATIONS USING A COLLECTIVE PROPERTY OF ELECTROMAGNETIC ENERGY OBSERVED THROUGH TRANSPARENT DISPLAYS BACKGROUND

      
Numéro d'application 19651350
Statut En instance
Date de dépôt 2026-04-17
Date de la première publication 2026-08-27
Propriétaire Microsoft Technology Licensing, LLC (USA)
Inventeur(s) Nick, Teresa A.

Abrégé

A computing system includes a plurality of processing units and a plurality of emitters. Each emitter is coupled to at least one of the plurality of processing units and is configured to display an electromagnetic signal at a location of the emitter based on instructions from an associated processing unit. The computing system further includes an electromagnetic sensor configured to detect a collective electromagnetic signal from the plurality of emitters.

Classes IPC  ?

  • G09G 3/34 - Dispositions ou circuits de commande présentant un intérêt uniquement pour l'affichage utilisant des moyens de visualisation autres que les tubes à rayons cathodiques pour la présentation d'un ensemble de plusieurs caractères, p. ex. d'une page, en composant l'ensemble par combinaison d'éléments individuels disposés en matrice en commandant la lumière provenant d'une source indépendante
  • G09G 5/02 - Dispositions ou circuits de commande de l'affichage communs à l'affichage utilisant des tubes à rayons cathodiques et à l'affichage utilisant d'autres moyens de visualisation caractérisés par la manière dont la couleur est visualisée

83.

CONSTRAINTS ON LOCATIONS OF REFERENCE BLOCKS FOR INTRA BLOCK COPY PREDICTION

      
Numéro d'application 19651404
Statut En instance
Date de dépôt 2026-04-17
Date de la première publication 2026-08-27
Propriétaire Microsoft Technology Licensing, LLC (USA)
Inventeur(s)
  • Zhou, You
  • Lin, Chih-Lung
  • Lee, Ming-Chieh

Abrégé

When encoding/decoding a current block of a current picture using intra block copy (“BC”) prediction, the location of a reference block is constrained so that it can be entirely within an inner search area of the current picture or entirely within an outer search area of the current picture, but cannot overlap both the inner search area and the outer search area. In some hardware-based implementations, on-chip memory buffers sample values of the inner search area, and off-chip memory buffers sample values of the outer search area. By enforcing this constraint on the location of the reference block, an encoder/decoder can avoid memory access operations that are split between on-chip memory and off-chip memory when retrieving the sample values of the reference block. At the same time, a reference block close to the current block may be used for intra BC prediction, helping compression efficiency.

Classes IPC  ?

  • H04N 19/176 - Procédés ou dispositions pour le codage, le décodage, la compression ou la décompression de signaux vidéo numériques utilisant le codage adaptatif caractérisés par l’unité de codage, c.-à-d. la partie structurelle ou sémantique du signal vidéo étant l’objet ou le sujet du codage adaptatif l’unité étant une zone de l'image, p. ex. un objet la zone étant un bloc, p. ex. un macrobloc
  • H04N 19/103 - Sélection du mode de codage ou du mode de prédiction
  • H04N 19/105 - Sélection de l’unité de référence pour la prédiction dans un mode de codage ou de prédiction choisi, p. ex. choix adaptatif de la position et du nombre de pixels utilisés pour la prédiction
  • H04N 19/139 - Analyse des vecteurs de mouvement, p. ex. leur amplitude, leur direction, leur variance ou leur précision
  • H04N 19/593 - Procédés ou dispositions pour le codage, le décodage, la compression ou la décompression de signaux vidéo numériques utilisant le codage prédictif mettant en œuvre des techniques de prédiction spatiale

84.

DYNAMICALLY MODIFYING PRESENTATIONS OF PARTITIONED CODE

      
Numéro d'application 19059747
Statut En instance
Date de dépôt 2025-02-21
Date de la première publication 2026-08-27
Propriétaire MICROSOFT TECHNOLOGY LICENSING, LLC (USA)
Inventeur(s)
  • Todirel, Ion
  • Mihalcea, Bogdan Ionut

Abrégé

Systems and methods are provided for facilitating the management of code during software development by dynamically partitioning the code and by generating visualizations of logical presentations of the partitioned code. Context and scope are determined for the code. The code is partitioned according to the determined context and scope. Partitioned segments are presented within a coherent virtual file view while omitting less relevant code from the coherent virtual file view. The partitioned view can help facilitate navigation and editing efficiencies during code development, particularly for large source files.

Classes IPC  ?

  • G06F 8/30 - Création ou génération de code source

85.

LOCATION AND NAVIGATION ASSISTANT

      
Numéro d'application 19059968
Statut En instance
Date de dépôt 2025-02-21
Date de la première publication 2026-08-27
Propriétaire MICROSOFT TECHNOLOGY LICENSING, LLC (USA)
Inventeur(s)
  • Sahu, Tezan
  • Bhandakkar, Pravin Vithalrao

Abrégé

The techniques presented herein are directed to a system for automated navigation assistance in indoor environments. In general, navigating an unfamiliar indoor environment can be a daunting task. This is especially true for large environments such as corporate offices, university campuses, shopping centers, and hospitals. Accordingly, the present system utilizes a reference database containing information associated with the indoor environment such as images depicting various locations, annotations describing the images, and floorplans illustrating the layout of the indoor environment. The reference database is deployed in conjunction with a multimodal language model that utilizes the collected knowledge of the reference database to provide location identification and intuitive navigation instructions. Often referred to as retrieval-augmented generation (RAG), the reference database enables the multimodal language model to respond to user requests using domain-specific information and ensure accurate outputs that are relevant to an end user's context (e.g., the indoor environment).

Classes IPC  ?

  • G01C 21/20 - Instruments pour effectuer des calculs de navigation
  • G06F 40/20 - Analyse du langage naturel
  • G06K 7/14 - Méthodes ou dispositions pour la lecture de supports d'enregistrement par radiation électromagnétique, p. ex. lecture optiqueMéthodes ou dispositions pour la lecture de supports d'enregistrement par radiation corpusculaire utilisant la lumière sans sélection des longueurs d'onde, p. ex. lecture de la lumière blanche réfléchie

86.

ENHANCED CONTROLS FOR SENSORY GROUP TIMERS

      
Numéro d'application 19060454
Statut En instance
Date de dépôt 2025-02-21
Date de la première publication 2026-08-27
Propriétaire Microsoft Technology Licensing, LLC (USA)
Inventeur(s)
  • Euclide, Edward Richard
  • Kudela, Defne
  • Lau, Tiphanie
  • Steiteyeh, Dima Mohd Said Kamal
  • Porena, Eleonora
  • Hornakova Hruba, Iva

Abrégé

The disclosed techniques provide enhanced controls for sensory group timers. In an online conference, a system allows a user to designate a subgroup comprising a subset of the conference attendees. This subgroup can be a subset of attendees making a presentation in the meeting, a confidential subgroup in an online negotiation meeting, or any other subgroup that want a private group timer only displayed to them while they still maintain communication with the others outside of the subset of attendees. The system allows the subset of attendees to control the group timer that is to be shared only within the designated subset group in the online meeting that includes all of the attendees. The group timer is displayed to the subset without providing notifications showing the other users outside the subgroup that the group timer exists, while the subgroup is still sharing content with the others outside the subgroup.

Classes IPC  ?

  • G06F 3/14 - Sortie numérique vers un dispositif de visualisation
  • G06F 3/0481 - Techniques d’interaction fondées sur les interfaces utilisateur graphiques [GUI] fondées sur des propriétés spécifiques de l’objet d’interaction affiché ou sur un environnement basé sur les métaphores, p. ex. interaction avec des éléments du bureau telles les fenêtres ou les icônes, ou avec l’aide d’un curseur changeant de comportement ou d’aspect
  • G06F 3/0484 - Techniques d’interaction fondées sur les interfaces utilisateur graphiques [GUI] pour la commande de fonctions ou d’opérations spécifiques, p. ex. sélection ou transformation d’un objet, d’une image ou d’un élément de texte affiché, détermination d’une valeur de paramètre ou sélection d’une plage de valeurs

87.

ENHANCED VISUAL INDICATORS FOR DESIGNATED PARTICIPANTS COMMUNICATING REAL-TIME TEXT

      
Numéro d'application 19060475
Statut En instance
Date de dépôt 2025-02-21
Date de la première publication 2026-08-27
Propriétaire Microsoft Technology Licensing, LLC (USA)
Inventeur(s)
  • Sano, Christopher M.
  • Humphrey, Brett D.
  • Barragan, Noe

Abrégé

The disclosed techniques provide enhanced control of visual indicators providing attribution to participants communicating via real-time text (RTT) in an online meeting. The disclosed techniques also provide dynamic control of text-to-speech conversion of RTT during online meetings. The display of RTT and the text-to-speech conversion for RTT allows users to hear and visualize content shared through RTT. A person's name and/or image is highlighted if that person is designated as having a prerequisite while they are communicating text in RTT mode. The system also acknowledges such users as an “active speaker” so the content shared in RTT is also recorded equitably in meeting records and used in AI models for generating transcripts, summaries, tasks, etc.

Classes IPC  ?

  • H04L 51/04 - Messagerie en temps réel ou quasi en temps réel, p. ex. messagerie instantanée [IM]
  • G06F 40/30 - Analyse sémantique

88.

BIOMETRIC AUTHENTICATION-BASED ACCESS TO DISPLAYED DOCUMENTS OR CONTENT WITH MODIFIABLE FREQUENCY OR SCHEDULE FOR TRIGGERING AUTHENTICATION PROCESSES

      
Numéro d'application 19062434
Statut En instance
Date de dépôt 2025-02-25
Date de la première publication 2026-08-27
Propriétaire Microsoft Technology Licensing, LLC (USA)
Inventeur(s)
  • Holdsworth, Katharine Ormond
  • Bhargav-Spantzel, Abhilasha
  • Sakib, Md. Nazmus
  • Olatunji, Ayobami Peter

Abrégé

Systems and methods are provided for implementing biometric authentication-based access to displayed documents or content with modifiable frequency or schedule for triggering authentication processes. A computing system receives a plurality of data including at least one of location data indicating a current location of the computing system, user access level data indicating an access level of a first user accessing one or more documents on the computing system, or document security level data indicating a security level for each document among the one or more documents being accessed. The computing system determines a security risk level for display of the one or more documents on a display screen of the computing system while the computing system is located within the current location, based on a combination of data among the plurality of data. The computing system sets or modifies a frequency and/or a schedule for triggering an authentication verification process.

Classes IPC  ?

  • G06F 21/32 - Authentification de l’utilisateur par données biométriques, p. ex. empreintes digitales, balayages de l’iris ou empreintes vocales

89.

THREAT INTELLIGENCE APPROACH FOR SECURING LANGUAGE MODELS

      
Numéro d'application 19062703
Statut En instance
Date de dépôt 2025-02-25
Date de la première publication 2026-08-27
Propriétaire Microsoft Technology Licensing, LLC (USA)
Inventeur(s)
  • Harari, Asaf
  • Hen, Idan
  • Salman, Tamer
  • Keller, Ron

Abrégé

A method of detecting malicious input to a language model includes obtaining a first input directed to the language model; generating a first embedding that embeds content of the first input; and determining values of a similarity metric computed between the first embedding and a plurality of embeddings stored in a known threat database. The plurality of embeddings corresponding to malicious inputs that exemplify attempts to extract unauthorized information from the language model or other artificial intelligence tool. The method further includes analyzing the values of the similarity metric to identify a select similar embedding within the known threat database that satisfies predefined similarity criteria with the first embedding and, in response to identifying the select similar embedding, identifying the first input as malicious and preventing the first input from being processed by the language model.

Classes IPC  ?

  • G06F 21/56 - Détection ou gestion de programmes malveillants, p. ex. dispositions anti-virus

90.

SCHEDULING TASKS FOR DISTRIBUTED QUERY EXECUTION

      
Numéro d'application 19062817
Statut En instance
Date de dépôt 2025-02-25
Date de la première publication 2026-08-27
Propriétaire Microsoft Technology Licensing, LLC (USA)
Inventeur(s)
  • Guo, Run Sheng
  • Sen, Rathijit
  • Srinivasan, Krishnan
  • Aguilar Saborit, Jose
  • Dash, Sumeet Priyadarshee
  • Haynes, Brandon Barry

Abrégé

Methods, apparatuses, and products for scheduling tasks for distributed query execution, including: assigning, to a plurality of tasks associated with one or more database queries, a corresponding priority value based on at least one of: an estimated runtime for each of the plurality of tasks and one or more task dependencies; and generating a schedule for executing the plurality of tasks in the distributed computing system by iteratively scheduling, for each task of the plurality of tasks, execution of a highest priority pending task able to be executed in a distributed computing system, wherein the highest priority pending task is included in a pending subset of the plurality of tasks pending execution in the distributed computing system.

Classes IPC  ?

  • G06F 9/48 - Lancement de programmes Commutation de programmes, p. ex. par interruption
  • G06F 16/2458 - Types spéciaux de requêtes, p. ex. requêtes statistiques, requêtes floues ou requêtes distribuées

91.

COMPONENT-BASED SCHEDULING AND RELEASE READINESS DETERMINATION

      
Numéro d'application 19063932
Statut En instance
Date de dépôt 2025-02-26
Date de la première publication 2026-08-27
Propriétaire Microsoft Technology Licensing, LLC (USA)
Inventeur(s)
  • Chen, Yingying
  • Moore, Josh Charles
  • Nag, Amitabh
  • Wooldridge, James
  • Veluswami, Senthilkumar
  • Persembe, Ahu
  • Bapat, Akshay Sudhir
  • Kravsov, Irina
  • Franke, Madeleine
  • Pieressa Pizarro, Fernando Andrés
  • Daouphars, Julien

Abrégé

Systems and methods are provided for implementing component-based scheduling and release readiness determination. A computing system automatically registers new hardware and virtual machines, establishing dependencies to avoid invalid scenarios. The computing system dynamically generates testing plans by combining reusable components (e.g., shared components) and continuously updates coverage based on existing configurations. In some examples, artificial intelligence (“AI”) tools recommend coverage and scheduling plans to enhance efficiency. Additionally, the computing system utilizes an actionable test scheduling and diagnostics tool, which is based on a product validation standard, that identifies critical configurations, assesses software release readiness, and estimates realistic shipping targets. The actionable test scheduling and diagnostics tool assists users in meeting their software product shipping goals while ensuring reliable product performance and minimizing the validation workload.

Classes IPC  ?

92.

SEMANTIC FILE PLACEHOLDERS

      
Numéro d'application 19064518
Statut En instance
Date de dépôt 2025-02-26
Date de la première publication 2026-08-27
Propriétaire MICROSOFT TECHNOLOGY LICENSING, LLC (USA)
Inventeur(s) Shah, Hardik Rajiv

Abrégé

Information is received that indicates files that are associated with a context of a user's activity. Based on the information, a temporary placeholder folder and placeholder files corresponding to the files are generated. The temporary placeholder folder and placeholder files are rendered on a user interface indicating the placeholder folder and placeholder files as folders and files within a file system running on the device. The placeholder files are not hydrated on the device. A mapping of the placeholder files to underlying files represented by the placeholder files is maintained.

Classes IPC  ?

  • G06F 16/178 - Techniques de synchronisation des fichiers dans les systèmes de fichiers
  • G06F 16/16 - Opérations sur les fichiers ou les dossiers, p. ex. détails des interfaces utilisateur spécialement adaptées aux systèmes de fichiers
  • G06F 16/182 - Systèmes de fichiers distribués

93.

EXECUTING A SIMULATED VERSION OF A ROBOTIC DEVICE TASK VIA A SIMULATION ENVIRONMENT IN A COLLABORATION SESSION

      
Numéro d'application 19065315
Statut En instance
Date de dépôt 2025-02-27
Date de la première publication 2026-08-27
Propriétaire MICROSOFT TECHNOLOGY LICENSING, LLC (USA)
Inventeur(s)
  • Rosenstein, Daniel
  • Stevens, Mark Alan
  • Knight, Brian Thomas
  • Chung, Timothy Hahndeut
  • Guagliano, Christopher Scott

Abrégé

A system implements techniques for executing a collaboration session between at least one human participant, at least one robotic device participant, and at least one artificial intelligence agent participant. The collaboration session can be executed in relation to a mission to be completed within a geographical environment. The system described herein generates a simulation environment in the context of the collaboration session. The simulation environment enables the simulated execution of a simulated version of an actual robotic device for validation purposes. For instance, a dangerous task to be executed by the actual robotic device may be simulated before actual execution to ensure the safety of the task is validated. Or, a complex task to be executed by the actual robotic device may be simulated before actual execution to ensure the effectiveness and/or efficiency of the task is validated.

Classes IPC  ?

  • H04L 65/403 - Dispositions pour la communication multipartite, p. ex. pour les conférences
  • B25J 9/16 - Commandes à programme

94.

ADAPTIVE ATTENTION SAMPLING OF DATA SEQUENCES FOR MACHINE LEARNING

      
Numéro d'application 19065422
Statut En instance
Date de dépôt 2025-02-27
Date de la première publication 2026-08-27
Propriétaire Microsoft Technology Licensing, LLC (USA)
Inventeur(s)
  • Usuyama, Naoto
  • Zhao, Zhengde
  • Poon, Hoifung
  • Preston, Joseph Samuel
  • Wei, Mu-Hsin
  • Kiblawi, Sid Hilmi
  • Lee, Peter

Abrégé

This document relates to adaptive attention sampling of a data sequence. In the disclosed implementations, sparse attention is implemented by sampling from a probability distribution to select a subset of portions of the data sequence for attention processing. The attention sampling can be performed over multiple iterations, updating the sampling probabilities at each subsequent iteration. This allows attention processing to focus computational resources on relevant portions of a data sequence while utilizing fewer computational resources on relatively less-relevant portions of the data sequence.

Classes IPC  ?

  • G06V 10/74 - Appariement de motifs d’image ou de vidéoMesures de proximité dans les espaces de caractéristiques
  • G06V 10/44 - Extraction de caractéristiques locales par analyse des parties du motif, p. ex. par détection d’arêtes, de contours, de boucles, d’angles, de barres ou d’intersectionsAnalyse de connectivité, p. ex. de composantes connectées
  • G06V 10/764 - Dispositions pour la reconnaissance ou la compréhension d’images ou de vidéos utilisant la reconnaissance de formes ou l’apprentissage automatique utilisant la classification, p. ex. des objets vidéo

95.

ADAPTIVE TACTILE FEEDBACK TOUCHPAD WITH CUSTOMIZABLE TEXTURE SIMULATOR

      
Numéro d'application 19065869
Statut En instance
Date de dépôt 2025-02-27
Date de la première publication 2026-08-27
Propriétaire Microsoft Technology Licensing, LLC (USA)
Inventeur(s)
  • Menashof, Roei Shlomo
  • Zagiel, Lior
  • Istrin, Oren

Abrégé

An adaptive tactile feedback touchpad with customizable texture simulation adapts feedback to provide realistic, nuanced sensations associated with different textures by sensing touch input attributes, such as input location and force, and determining additional touch attributes, such as direction and velocity, from a time-series set of touch inputs. Touchpad haptic actuators implemented in one or more axes of a touchpad can be controlled with varying amplitudes (e.g., weights) to provide consistent tactile sensations regardless of the location and direction that a user touches and moves a finger on the touchpad. A haptic waveform can be selected, for example, based on the simulated texture and input velocity while a waveform amplitude can be determined based on input force, direction, and velocity. The haptic actuator(s) can be controlled by the selected waveform and determined amplitude to provide realistic tactile sensations regardless where the user interacts with the touchpad.

Classes IPC  ?

  • G06F 3/01 - Dispositions d'entrée ou dispositions d'entrée et de sortie combinées pour l'interaction entre l'utilisateur et le calculateur
  • G06F 3/041 - Numériseurs, p. ex. pour des écrans ou des pavés tactiles, caractérisés par les moyens de transduction
  • G06F 3/044 - Numériseurs, p. ex. pour des écrans ou des pavés tactiles, caractérisés par les moyens de transduction par des moyens capacitifs

96.

GUIDED SYNTHETIC DATA GENERATION FOR CONTEXTUAL REPRESENTATION

      
Numéro d'application 19220439
Statut En instance
Date de dépôt 2025-05-28
Date de la première publication 2026-08-27
Propriétaire Microsoft Technology Licensing, LLC (USA)
Inventeur(s) Lavallée, Jean-François

Abrégé

A contextualized dataset generator selects one or more first deterministic annotations from a set of candidate deterministic annotations, wherein the set of candidate deterministic annotations correspond to a first data type identified in accordance with annotation selection rules. The contextualized dataset generator generates a first synthesizing instruction for input to a synthesizing language model based on the one or more first deterministic annotations, a synthesizing instruction template, and a scenario description specifying a task of a specified domain for which the machine learning model is to be trained or evaluated. The contextualized dataset generator synthesizes a first input prompt and one or more first probabilistic annotations by the synthesizing language model based on the first synthesizing instruction. The contextualized dataset generator adds a first datapoint to the annotated contextualized dataset, the first datapoint including the one or more first deterministic annotations, the first input prompt, and the first probabilistic annotations.

Classes IPC  ?

  • G06F 40/44 - Méthodes statistiques, p. ex. modèles probabilistes
  • G06F 17/18 - Opérations mathématiques complexes pour l'évaluation de données statistiques

97.

LAYERED INGRESS SHARDING

      
Numéro d'application US2025058485
Numéro de publication 2026/177786
Statut Délivré - en vigueur
Date de dépôt 2025-12-05
Date de publication 2026-08-27
Propriétaire MICROSOFT TECHNOLOGY LICENSING, LLC (USA)
Inventeur(s)
  • Pippari, Suresh Chandra
  • Tiwari, Abhishek K.
  • Chawla, Varun
  • Uthaman, Karthik
  • Nandoori, Ashok Kumar
  • Devuyst, Matthew David

Abrégé

Layered ingress sharding for multi-tenant services outperforms current sharding techniques, to enhance the reliability and scalability of services. A sharding controller assigns clients and service instances to shards in each of multiple layers. Assignments differ among the layers, at least for clients and may also for service instances. This minimizes adverse effects on clients assigned to a shard with a noisy neighbor, because there are other layers (with a high probability) in which they are not sharing a shard with that noisy neighbor. The sharding controller monitors service instance health and available capacity, which indicates shard health and capacity. Client requests are routed to healthy shards, where retries will eventually find a healthy service instance or, in some examples, requests are routed directly to healthy service instances, eliminating the need for a retry.

Classes IPC  ?

  • G06F 9/50 - Allocation de ressources, p. ex. de l'unité centrale de traitement [UCT]

98.

DECODING METADATA ENCODED IN ERROR CORRECTION CODES

      
Numéro d'application 19489545
Statut En instance
Date de dépôt 2024-04-24
Date de la première publication 2026-08-20
Propriétaire Microsoft Technology Licensing, LLC (USA)
Inventeur(s)
  • Dakshinamoorthy, Srikanth
  • Nemati, Majid Anaraki
  • Remaklus, Jr., Perry Willmann
  • Kumar, Ravinder

Abrégé

Embodiments of the present disclosure include techniques for encoding and decoding metadata in error correction codes. During read operation, a decoder generates a first output corresponding to the at least one metadata bit having a first state and a second output corresponding to the at least one metadata bit having a second state. When one of the first and second outputs have a zero value, the decoder sets a value of the at least one metadata bit to the first state or the second state corresponding to the first output or the second output having the zero value. When both the first and second outputs are non-zero, the decoder decodes the codeword with the assumption of both the metadata bit having the first state and the second state to determine if the codeword is correctable with the at least one metadata bit.

Classes IPC  ?

  • H03M 13/11 - Détection d'erreurs ou correction d'erreurs transmises par redondance dans la représentation des données, c.-à-d. mots de code contenant plus de chiffres que les mots source utilisant un codage par blocs, c.-à-d. un nombre prédéterminé de bits de contrôle ajouté à un nombre prédéterminé de bits d'information utilisant plusieurs bits de parité
  • H03M 13/15 - Codes cycliques, c.-à-d. décalages cycliques de mots de code produisant d'autres mots de code, p. ex. codes définis par un générateur polynomial, codes de Bose-Chaudhuri-Hocquenghen [BCH]

99.

PROVIDING MULTI-REQUEST ARBITRATION GRANT POLICIES FOR TIME-SENSITIVE ARBITRATION DECISIONS IN PROCESSOR-BASED DEVICES

      
Numéro d'application 19496960
Statut En instance
Date de dépôt 2024-06-20
Date de la première publication 2026-08-20
Propriétaire MICROSOFT TECHNOLOGY LICENSING, LLC (USA)
Inventeur(s)
  • Srikumar, Rahul
  • Kaseridis, Dimitrios

Abrégé

Providing multi-request arbitration grant policies for time-sensitive arbitration decisions in processor-based devices is disclosed. In this regard, a processor-based device provides an arbitration circuit that is configured to select a request tracker entry of a plurality of request tracker entries of a request tracker circuit to apply a multi-request arbitration grant policy. The arbitration circuit determines a count N of a plurality of requests associated with the request tracker entry, and determines a count R of resource elements that are available of a plurality of resource elements of an arbitrated resource. The arbitration circuit determines whether the count R of resource elements that are available is equal to or greater than N, and if so. issues a single arbitration grant for the plurality of requests associated with the request tracker entry to the request tracker circuit.

Classes IPC  ?

  • G06F 13/364 - Gestion de demandes d'interconnexion ou de transfert pour l'accès au bus ou au système à bus communs avec commande d'accès centralisée utilisant des signaux indépendants de demande ou d'autorisation, p. ex. utilisant des lignes séparées de demande et d'autorisation

100.

GENERATING UNIVERSAL WEB PROFILES FROM DIVERSE EVENT DATA USING GENERATIVE ARTIFICIAL INTELLIGENCE (AI) MODELS

      
Numéro d'application 19641931
Statut En instance
Date de dépôt 2026-04-08
Date de la première publication 2026-08-20
Propriétaire Microsoft Technology Licensing, LLC (USA)
Inventeur(s)
  • Ginotra, Kamal
  • Kaushal, Nabeel
  • Yu, Dongfei
  • Zolaktaf, Sedigheh
  • Mcnamara, Andrew James
  • Liu, Jikun

Abrégé

This disclosure describes a universal user web profile generation system that utilizes one or more generative artificial intelligence (AI) models to generate universal web profiles for users. For example, the universal user web profile generation system uses a combination of neural networks and generative AI models to distill relevant information from the vast amounts and types of user event data and generate relevant universal user event taxonomies. Upon generating the universal user event taxonomies, the universal user web profile generation system can efficiently and accurately generate user profiles based on user web data that aligns with the universal user event taxonomies, ensuring profile compatibility with most or all downstream processes and services that access the user web profiles. Indeed, the universal user web profile generation system generates universal web profiles for users by consolidating extensive user data into a concise and insightful format.

Classes IPC  ?

  • G06F 16/9535 - Adaptation de la recherche basée sur les profils des utilisateurs et la personnalisation
  • G06F 40/30 - Analyse sémantique
  1     2     3     ...     100        Prochaine page