The present disclosure is directed toward systems, methods, and non-transitory computer readable media for generating and searching a hybrid search index. In some embodiments, the disclosed systems generate a hybrid search index that comprises one or more content items stored at a content management system or at external network locations linked to the content management system via software connectors along with world state data associated with the one or more content items. The disclosed systems can generate a search result from the hybrid search index in response to receiving a search query of the hybrid search index. In some cases, the disclosed systems can rank one or more content items included in the search result based on observation layer data of the one or more content items.
The present technology addresses a need in the art for providing additional context to a recipient receiving a shared object(s). Sharing messages are generally limited to a brief statement indicating that a user account has shared the object(s). The present technology can automatically create a summary for an object(s) to be shared. Moreover, the present technology provides a user interface that is part of a sharing process for the creation of the summary so that the creation of the summary is very convenient for the user, and can even be completely automatic. Additionally, the present technology includes carefully engineered prompts that result in summaries that are appropriate for the sharing context in which they are intended.
H04L 51/02 - User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail using automatic reactions or user delegation, e.g. automatic replies or chatbot-generated messages
3.
CLASSIFYING AND ORGANIZING DIGITAL CONTENT ITEMS AUTOMATICALLY UTILIZING CONTENT ITEM CLASSIFICATION MODELS
The present disclosure relates to systems, methods, and non-transitory computer-readable media that utilize machine-learning models to classify content items and automatically organize the content items within a file structure according to their content item classifications. For instance, a content item classification system generates one or more content item classification models to determine classifications for content items and/or folders. In some instances, the classification system detects when new content items are added to a smart folder, determines destination folders to which the content items belong based on classifying the content items, and automatically moves the content items accordingly. In various instances, the classification system generates and utilizes a classification model to organize content items into dynamically-generated folders. In example implementations, the classification system generates and utilizes a classification model to automatically organize existing content items into existing folders.
The present disclosure relates to systems, methods, and non-transitory computer-readable media that utilize machine-learning models to classify content items and automatically organize the content items within a file structure according to their content item classifications. For instance, a content item classification system generates one or more content item classification models to determine classifications for content items and/or folders. In some instances, the classification system detects when new content items are added to a smart folder, determines destination folders to which the content items belong based on classifying the content items, and automatically moves the content items accordingly. In various instances, the classification system generates and utilizes a classification model to organize content items into dynamically-generated folders. In example implementations, the classification system generates and utilizes a classification model to automatically organize existing content items into existing folders.
The present disclosure relates to systems, non-transitory computer-readable media, and methods for generating block content elements from meeting data of multiple video calls to add to data blocks of a virtual space. In particular, in one or more embodiments, the discloses systems utilize a large language model to process meeting data across multiple video calls and generate the block content elements for data blocks. For example, in some embodiments, the disclosed systems generate new block content elements based on detecting meeting data from additional video calls. Further, in one or more embodiments, the disclosed systems generate block content elements according to block type of a data block and extract meeting data to generate summaries, action items, document elements, or dates. Moreover, in some embodiments, the disclosed systems provide options and prompts to generate or update a virtual space using meeting date from video calls.
G06F 3/0481 - Interaction techniques based on graphical user interfaces [GUI] based on specific properties of the displayed interaction object or a metaphor-based environment, e.g. interaction with desktop elements like windows or icons, or assisted by a cursor's changing behaviour or appearance
G06F 3/0484 - Interaction techniques based on graphical user interfaces [GUI] for the control of specific functions or operations, e.g. selecting or manipulating an object, an image or a displayed text element, setting a parameter value or selecting a range
This disclosure describes systems that generate a selection of large language model (LLM) function buttons in a floating widget within a web browser of a client device. The disclosed systems can generate or otherwise select the LLM function buttons to include based on context of a webpage within the web browser. Responsive to detecting an indication of an interaction with an LLM function button, the disclosed systems can generate a side panel within the web browser according to the LLM function button. In some embodiments, the disclosed systems can display and utilize a customized LLM function button responsive to detecting a certain webpage or content within the webpage. Further, in some embodiments, the disclosed systems can generate an LLM function button to perform a customized workflow responsive to detecting a certain webpage or content within the webpage.
G06F 3/04817 - Interaction techniques based on graphical user interfaces [GUI] based on specific properties of the displayed interaction object or a metaphor-based environment, e.g. interaction with desktop elements like windows or icons, or assisted by a cursor's changing behaviour or appearance using icons
G06F 3/04842 - Selection of displayed objects or displayed text elements
G06F 9/451 - Execution arrangements for user interfaces
The present disclosure relates to systems, non-transitory computer-readable media, and methods for selecting machine-learning models and hardware environments for executing a task. In particular, in one or more embodiments, the disclosed systems select a designated machine-learning model for executing a task based on workload features of the task and task routing metrics for a plurality of machine-learning models. In addition, in one or more embodiments, the disclosed systems select a designated hardware environment for executing the task based on workload features for the task and task routing metrics for a plurality of hardware environments. In some embodiments, the disclosed systems select a fallback machine-learning model and a fallback hardware environment for executing the task if the designated machine-learning model or designated hardware environment are unavailable. Moreover, in one or more embodiments, the disclosed systems can pause and initiate tasks based on bandwidth availability.
G06F 9/50 - Allocation of resources, e.g. of the central processing unit [CPU]
G06F 9/48 - Program initiatingProgram switching, e.g. by interrupt
G06F 11/14 - Error detection or correction of the data by redundancy in operation, e.g. by using different operation sequences leading to the same result
G06F 11/20 - Error detection or correction of the data by redundancy in hardware using active fault-masking, e.g. by switching out faulty elements or by switching in spare elements
H04L 41/16 - Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks using machine learning or artificial intelligence
Methods and systems provide for rich media presentation of recommendations in generative media. In one embodiment, the system presents, via a trained generative AI, a set of media content to a user in a communication session within a platform, the media content including a number of sorted recommended items; monitors and quantifies one or more user responses from the user to the presented media content and one or more associated generative responses from the trained generative AI; based on the monitoring and quantifying, detects one or more mentions of the user to one of the plurality of sorted recommended items; generates, from the one or more detected mentions, one or more labeled training examples; and further trains the trained generative AI based on the one or more labeled training examples to improve the presentation of the media content in future communication sessions.
The present disclosure relates to systems, non-transitory computer-readable media, and methods for capturing snapshots of digital content displayed on a client device and searching through the captured content. The disclosed systems provide a search function for effectively traveling back in time to identify digital content previously displayed on a client device. The disclosed systems provide options for capturing snapshots of content displayed on a display screen, extracting data from the snapshots, and storing the snapshots for use when populating search results. The disclosed systems utilize machine learning models to extract text and/or to generate text versions of snapshots including extracted text, descriptions of images, transcripts of videos, and/or textual summaries from displayed documents or webpages. In response to a search query, the disclosed systems can produce search results that include digital videos including captured snapshots of content displayed by a client device over time.
G06F 16/783 - Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
10.
GENERATING AND ADAPTING VIRTUAL ASSISTANTS FOR USER ACCOUNTS
This disclosure describes systems that identify one or more models (e.g., large language models and/or virtual assistants) permitted to access content items stored for user accounts within a content management system. The disclosed systems can determine a model available to a user account within the content management system from among the one or more models. For example, the disclosed systems can determine one or more relationships between the user accounts within the content management system, large language models utilized by the user accounts, virtual assistants utilized by the user accounts, and content items accessed by the user accounts. The disclosed systems can determine the model for the user account according to the one or more relationships. The disclosed systems can provide a notification corresponding to the model via a user interface of a client device associated with the user account.
G06N 3/006 - Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
G06F 9/451 - Execution arrangements for user interfaces
This disclosure describes systems that identify one or more models (e.g., large language models and/or virtual assistants) permitted to access content items stored for user accounts within a content management system. The disclosed systems can determine a model available to a user account within the content management system from among the one or more models. For example, the disclosed systems can determine one or more relationships between the user accounts within the content management system, large language models utilized by the user accounts, virtual assistants utilized by the user accounts, and content items accessed by the user accounts. The disclosed systems can determine the model for the user account according to the one or more relationships. The disclosed systems can provide a notification corresponding to the model via a user interface of a client device associated with the user account.
The present technology enhances workload management of data storage systems by using an internal copy function and/or a zone-append technology. The internal copy function is used, e.g., in merge operations to move data between locations on a disk without using off-disk resources (e.g., processing or memory of a CPU). Zone-append technology uses nameless writes (e.g., write instruction without an assigned destination address on the disk) to combine IO units from different threads to be written to a common zone of a disk (e.g., a shingled magnetic recording (SMR) disk). Sequential addresses are assigned to IO units from different threads based on their order in the write queue, reducing the latency and seek time typically associated with random writes. The zone-append technology, e.g., uses sequential write operations within specified zones, allowing the disk to determine the actual write location and to report post-write logical block addresses (LBAs).
One or more embodiments of a content system provide machine-learned storage location recommendations for storing content items. Specifically, an online content management system can train a machine-learning model to identify a storage pattern from previously stored content items in a plurality of storage locations corresponding to a user account of a user. Training the machine-learning model includes training a plurality of classifiers for the plurality of storage locations. The online content management system uses the classifiers to determine whether a content item is similar to the content items in any of the storage locations, and based on the output of the classifiers, provides graphical elements indicating recommended storage locations within a graphical user interface. The user can select a graphical element to move the content item to the corresponding storage location.
Systems and methods for providing a folder activity user interface, such as a folder activity dashboard, that can provide viewing members with an overview of the sync progress of their own activities, like uploading content items, as well as the activities of other activity-initiating members, such as uploads to shared folders that the viewing members have access to. The folder activity user interface includes status indicators that correspond to the progress related to folder activity information and the respective content items of the shared folder, such as indicating progress towards when a respective content item will be accessible to the viewing member.
The present disclosure is directed toward systems, methods, and non-transitory computer readable media for generating and searching a hybrid search index. In some embodiments, the disclosed systems generate a hybrid search index that comprises one or more content items stored at a content management system or at external network locations linked to the content management system via software connectors along with world state data associated with the one or more content items. The disclosed systems can generate a search result from the hybrid search index in response to receiving a search query of the hybrid search index. In some cases, the disclosed systems can rank one or more content items included in the search result based on observation layer data of the one or more content items.
The present disclosure is directed toward systems, methods, and non-transitory computer-readable media for providing a streamed presentation of a video proxy referencing a cloud-based location of a digital video. For example, the disclosed systems receive a request to edit a digital video stored in a cloud-based location of a content management system. In addition, the disclosed systems generate a video proxy that include a reference to the cloud-based location of the digital video and modifies the video proxy in response to an editing operation. Further, the disclosed systems provide for display a streamed presentation of the video proxy depicting modifications defined by the editing operation.
G11B 27/031 - Electronic editing of digitised analogue information signals, e.g. audio or video signals
G06F 3/04845 - Interaction techniques based on graphical user interfaces [GUI] for the control of specific functions or operations, e.g. selecting or manipulating an object, an image or a displayed text element, setting a parameter value or selecting a range for image manipulation, e.g. dragging, rotation, expansion or change of colour
G06F 3/04847 - Interaction techniques to control parameter settings, e.g. interaction with sliders or dials
18.
GENERATING A HYBRID SEARCH INDEX FOR UNIFIED SEARCH
The present disclosure is directed toward systems, methods, and non-transitory computer readable media for generating and searching a hybrid search index. In some embodiments, the disclosed systems generate a hybrid search index that comprises one or more content items stored at a content management system or at external network locations linked to the content management system via software connectors along with world state data associated with the one or more content items. The disclosed systems can generate a search result from the hybrid search index in response to receiving a search query of the hybrid search index. In some cases, the disclosed systems can rank one or more content items included in the search result based on observation layer data of the one or more content items.
This disclosure generally covers systems and methods that identify relevant information for a user based on an object graph for documents and other files hosted by a document hosting system. In particular, certain embodiments of the disclosed systems and methods generate an object graph comprising interconnected nodes representing relationships among documents and other files on the document hosting system. Using the object graph, the disclosed systems and methods can identify relevant information and provide results or recommendations corresponding to that information based on a query or on user input, respectively.
Methods and systems provide content searching and retrieval using generative artificial intelligence (AI) Models. The system is configured to receive a user search for content, media or item listings. The user search is provided to a generative AI based search sub-system and to a traditional search sub-system. A first search result listing is generated by the generative AI based subsystem, and a second search result listing is generated by the traditional search sub-system. The first search result listing and the second search result listing are aggregated together and provided for display to a user client device.
The present disclosure relates to systems, methods, and non-transitory computer-readable media that dynamically capture, organize, and utilize digital media clips. For example, in one or more implementations, the disclosed systems can capture and generate digital media clips of content items that include both content metadata of the content items as well as contextual metadata of contextual signals surrounding the content item. Additionally, in some implementations, the disclosed systems analyze contextual metadata to search, retrieve, discover, and organize new and existing digital media clips. Further, in various implementations, the disclosed systems facilitate generating digital media clip libraries as well as the creation of digital media collections, where different types of digital media clips can be combined in a cohesive interactive graphical user interface.
The present technology pertains to a predictive thermal model that can be used to intelligently manage thermal events in a data center. The predictive thermal model can be used to predict future temperatures of servers to take action before the server experiences higher than desired temperatures. The present technology also includes several innovative amelioration techniques that can help to keep servers cool when it is predicted that heat in their environment is about to increase. One such amelioration technique is a heat-responsive operation change for storage servers, or at least individual hosts within a storage server. For example, a host can be switched into a mode where it can batch read and write operations to limit the amount of seeking the host needs to perform, which produces less heat.
The present disclosure relates to systems, non-transitory computer-readable media, and methods for modifying a fillable digital document. In particular, the disclosed systems can receive a user interaction requesting to populate one or more aggregated data fields in a fillable digital document. In response to the request, the field object generation system can determine the data relevant to one or more aggregated data fields in the fillable digital document by utilizing a large language model to process one or more source content items for a user account. Further the systems and generate a field object from the data relevant to one or more aggregated data field and modify the fillable digital document by including the field object in the fillable digital document.
A preferred method for dynamically displaying virtual and augmented reality scenes can include determining input parameters, calculating virtual photometric parameters, and rendering a VAR scene with a set of simulated photometric parameters.
The present disclosure is directed toward systems, methods, and non-transitory computer readable media for generating and implementing workflow states across multiple devices. In some embodiments, the disclosed systems generate, utilizing a meta layer integrated with a suite of computer applications, a workflow state defining an active computer application and interaction data within the active computer application on a first client device. Further, in some embodiments, the disclosed systems detect a handoff trigger comprising computer instructions for transferring the workflow state from the first client device to a second client device. In response to detecting the handoff trigger, in some embodiments, the disclosed systems access, via the meta layer, the workflow state to cause the second client device to instantiate the active computer application and the interaction data.
The present disclosure is directed toward systems, methods, and non-transitory computer readable media for generating content clusters from topic data and focus data, generating content collections from content clusters, storing and restoring desktop scene layouts, and storing and arranging video call scenes. In some embodiments, the disclosed systems generate content clusters based on topic data and focus data associated with content items within a content management system and/or accessed via the internet. The disclosed systems can also generate content collections for a user account of the content management system from the content clusters. In some embodiments, the content scene system can further store and restore desktop scene layouts for arranging application windows presenting content items. Further, the disclosed systems can store and arrange particular desktop scene layouts for video call scenes.
G06F 11/14 - Error detection or correction of the data by redundancy in operation, e.g. by using different operation sequences leading to the same result
G06F 16/9535 - Search customisation based on user profiles and personalisation
27.
Autonomous process execution for large language model function buttons
This disclosure describes systems that generate a selection of large language model (LLM) function buttons in a floating widget within a web browser of a client device. The disclosed systems can generate or otherwise select the LLM function buttons to include based on context of a webpage within the web browser. Responsive to detecting an indication of an interaction with an LLM function button, the disclosed systems can generate a side panel within the web browser according to the LLM function button. In some embodiments, the disclosed systems can display and utilize a customized LLM function button responsive to detecting a certain webpage or content within the webpage. Further, in some embodiments, the disclosed systems can generate an LLM function button to perform a customized workflow responsive to detecting a certain webpage or content within the webpage.
The present disclosure relates to systems, non-transitory computer-readable media, and methods for generating a hybrid prompt for a retrieval augmented generation (RAG) model. In particular, the disclosed systems can generate utilizing a large language model at indexing time for a content item, a topic summary for a topic within the content item. Moreover, the disclosed systems can add the topic summary to a summary knowledge corpus that includes topic summary for a plurality of topics extracted from content items. In one or more cases, at runtime for the RAG model, the disclosed systems can receive prompt language and in response, determine one or more topic summaries that correspond to the prompt language. The disclosed systems can further generate a hybrid prompt by combining the one or more topic summaries with retrieved data accessed by the RAG model in response to the prompt language.
The present disclosure is directed toward systems, methods, and non-transitory computer-readable media for generating a dynamic facet by using a large language model. For example, the disclosed systems extract raw facet data from a plurality of content items stored in a content management system. In addition, the disclosed systems determine one or more facet content groups by grouping the plurality of content items according to the raw facet data. Further, the disclosed systems generate a facet prompt from the one or more facet content groups. Moreover, the disclosed systems generate a dynamic facet by providing the facet prompt to a large language model.
The present disclosure is directed toward systems, methods, and non-transitory computer-readable media for generating function code and test code to determine that the function code satisfies an intent query. For example, the disclosed systems utilize a large language model to process an intent query and generate function code that defines one or more processes whose execution satisfies the intent query. In addition, the disclosed systems also utilize the large language model to generate test code that defines a function test for determining that the function code satisfies the intent query. Moreover, the disclosed systems can execute the test code to determine that the function code satisfies the intent query.
The present disclosure relates to systems, non-transitory computer-readable media, and methods for generating, storing, and accessing persisted data elements in a large language model framework. For instance, the disclosed systems can generate a code segment that includes a set of parameters and a function with a large language model associated with a context engine. In some cases, the disclosed systems can determine the serialized state of the interpreter based on executing the code segment. In one or more implementations, the disclosed systems can generate a persisted data element from the serialized state of the interpreter and store the persisted data element in an interpreter data store. The disclosed systems can further access the persisted data element from the data store to generate responses or perform tasks in the same or subsequent sessions.
The present disclosure relates to systems, non-transitory computer-readable media, and methods for maintaining context during multi-turn interactions. In one or more embodiments, the disclosed systems can detect an interruption event during the execution of computer code by an interpreter that pauses the execution of computer code by the interpreter. The disclosed systems can store, based on the interruption event, a serialized state of the interpreter that indicates a pause location in the computer code by encoding the code execution data. In some cases, the disclosed systems can resume execution of the computer code from the serialized state of the interpreter.
The present disclosure relates to systems, non-transitory computer-readable media, and methods for combining sessions of a large language model. For instance, the disclosed systems can receive a first query from a first collaborating user account and a second query from a second collaborating user account. In one or more cases, the disclosed systems can generate a merged prompt based on the from the first query and second query. In some implementations, the disclosed systems can generate a response to the first query and/or the second query by processing the merged prompt utilizing the large language model.
The present disclosure relates to systems, non-transitory computer-readable media, and methods for linking third-party applications to a user account on a content management system. In particular, the disclosed systems can receive browsing data related to browsing activity from a user associated with a user account on a content management system via a software extension on a browser application. The disclosed systems can identify a third-party application external to the content management system based on the browsing data. Upon identifying the third-party application, the disclosed systems can provide for display a selectable connector suggestion on a graphical user interface of a client device. In one or more implementations, based on receiving an indication of a selection of the selectable connector suggestion, the disclosed systems can generate a digital connection that communicatively links the third-party application to the user account on the content management system.
The present disclosure relates to systems, non-transitory computer-readable media, and methods for ingesting a dataset from a computer application that is external to a content management system. In particular, the disclosed systems can perform an ingestion process comprising a plurality of transfer runs by linking a content management system to the computer application with a connector. The disclosed systems can utilize a coordinator with computer logic to control the connector to determine a cursor location within a page of data at a failure point during a first transfer run. Moreover, the disclosed systems can store a subset of data from the page that comes after the cursor location and ingest the subset of data from the object queue by continuing the ingestion process according to the cursor location at the failure point of the first transfer run.
G06F 15/16 - Combinations of two or more digital computers each having at least an arithmetic unit, a program unit and a register, e.g. for a simultaneous processing of several programs
G06F 16/25 - Integrating or interfacing systems involving database management systems
G06F 16/27 - Replication, distribution or synchronisation of data between databases or within a distributed database systemDistributed database system architectures therefor
The present technology improves the ability of a technician to navigate within a data center by making use of lights on servers, switches, and other infrastructure devices to provide navigation queues to a technician. In particular, the present technology can instruct infrastructure devices along a path to a particular infrastructure device that a technician might need to service to operate lights, (e.g., light emitting diodes (LEDs)) in a way that signals a path to the particular infrastructure device. When a number of infrastructure devices are so instructed, an easy-to-follow and understand pattern can be created. The particular infrastructure device can be instructed to operate its lights in a way that differentiates itself from other surrounding devices that might help the technician recognize the device.
The present disclosure relates to systems, non-transitory computer-readable media, and methods for generating information flow patterns utilizing a large language model and content item embeddings, and utilizing information flow patterns to determine notifications and modifications. To illustrate, the disclosed methods can extract content item embeddings from content items and provide content item embeddings to a large language model in order to generate information flow patterns that include communication between teams. Accordingly, the disclosed methods can utilize document embeddings from new modifications to generate information flow patterns for a corresponding project. Thus, the disclosed methods can utilize the information flow pattern to determine corresponding notifications or modifications to projects or content indicated by the information flow pattern.
G06F 16/27 - Replication, distribution or synchronisation of data between databases or within a distributed database systemDistributed database system architectures therefor
38.
CONTEXTUALIZING DATA TO PROVIDE COMPUTING ACTIVITY SYNTHESIS
This disclosure describes systems that aggregate activity data items for one or more data sources for a user account. The disclosed systems can utilize a large language model to transform the activity data items to synthesized activity items. For example, the disclosed systems can utilize the large language model to transform the activity data items to the synthesized activity items by extracting the contextual content from the activity data items. The disclosed systems can utilize the large language model to process the synthesized activity items to generate an activity meta summary for a specified timeframe. Based on the activity meta summary, the disclosed systems can further identify a subset of synthesized activity items for the specified timeframe. Thereafter, the disclosed systems can provide the subset of synthesized activity items for the specified timeframe for display on a client device associated with the user account.
The present technology provides a versatile content management system that can also support bi-directional synchronization of an organization account. The organization account is maintained as a plurality of root directories that can be mounted under an organization directory top-level folder. The organization directory top-level folder can appear in a user account's view of the organization account, by does not actually exist as a directory in the content management system. The organization directory top-level folder can be a folder created on a client device in which root directories of an organization account are mounted, but the organization directory top-level folder is not a synchronized directory. The organization directory top-level folder gives the appearance of a single directory structure for an organization even though the organization content is actually organized into the plurality of root directories.
The present disclosure is directed toward systems, methods, and non-transitory computer readable media for generating and searching a hybrid search index. In some embodiments, the disclosed systems generate a hybrid search index that comprises one or more content items stored at a content management system or at external network locations linked to the content management system via software connectors along with world state data associated with the one or more content items. The disclosed systems can generate a search result from the hybrid search index in response to receiving a search query of the hybrid search index. In some cases, the disclosed systems can rank one or more content items included in the search result based on observation layer data of the one or more content items.
Methods and systems provide content searching and retrieval using generative artificial intelligence (AI) Models. The system is configured to receive a user search for content, media or item listings. The system receives a natural language-based input associated with a client device of a user. The system generates a search criterion for the received natural language-based input. The system provides a data set of retrieved content items to one or more large language models that annotate each of the content items in the data set. The system receives a new data set with the content items each including a relevancy annotation. Based on the relevancy annotations in the new data the system determines what additional processing to perform.
Methods and systems provide content searching and retrieval using generative artificial intelligence (AI) Models. The system is configured to receive a user search for content, media or item listings. The system receives a natural language-based input associated with a client device of a user. The system generates a search criterion for the received natural language-based input. The system, via the generative AI-bases search and retrieval system, generates a relevancy-ranked output listing of content items. The relevancy-ranked output listing content items responsive to the generated search criterion content items having an associated content identifier and a content description. The system generates a carousel display structure definition of the relevancy-ranked content items. The system transmits the carousel display structure definition of the relevancy-ranked content items and the content items to the client device. The client device displays, via a user interface of the client device, relevancy-ranked content items according to the carousel display structure definition.
Methods and systems provide content searching and retrieval using generative artificial intelligence (AI) Models. The system is configured to receive a user search for content, media or item listings. The system receives a natural language-based input associated with a client device of a user. The system generates a search criterion for the received natural language-based input. The system, via the generative AI-bases search and retrieval system, generates a relevancy-ranked output listing of content items. The relevancy-ranked output listing content items responsive to the generated search criterion content items having an associated content identifier and a content description. The system causes portions of the relevancy-ranked output listing to be rendered at the client device of the user.
The present disclosure is directed toward systems, methods, and non-transitory computer-readable media for generating unified data items from source-specific data items originating from third-party sources. For example, the disclosed systems receive a plurality of source-specific data items from a first third-party source and a second third-party source. For instance, the source-specific data items include data that represents digital activity of multiple client devices using the third-party sources. Further, the disclosed systems generate a plurality of unified data items from the source-specific data items by using a translation layer that maps source-specific data structures to a unified data structure. Moreover, the disclosed systems identify a subset of unified data items based on a request from an administrator device and further provides the subset of unified data items to the administrator device.
The present technology pertains to storing blocks in a storage system that requires fewer I/O operations for processes that are non-latency-sensitive. The present technology collects blocks in a buffer and then performs erasure coding while writing the blocks into storage. The erasure coding can occur without the blocks first being replicated. And the present technology can acknowledge the request to store the blocks to a client providing the blocks even before the blocks are written into the storage.
G06F 16/27 - Replication, distribution or synchronisation of data between databases or within a distributed database systemDistributed database system architectures therefor
46.
GENERATING COACHING PROMPTS FROM KNOWLEDGE GRAPH DATA SOURCES
The present disclosure is directed toward systems, methods, and non-transitory computer readable media for generating and providing coaching insights using a large language model to process coaching prompts. In some embodiments, the disclosed systems generate a coaching prompt from a knowledge graph encoding data from data sources, such as an observation layer and a world state. The disclosed systems also determine a pulse status of a user account to inform a coaching prompt. Additionally, the disclosed systems provide the coaching prompt to a large language model for generating a coaching insight to improve the pulse status.
The present disclosure is directed toward systems, methods, and non-transitory computer readable media for generating and providing coaching insights using a large language model to process coaching prompts. In some embodiments, the disclosed systems generate a coaching prompt from a knowledge graph encoding data from data sources, such as an observation layer and a world state. The disclosed systems also determine a pulse status of a user account to inform a coaching prompt. Additionally, the disclosed systems provide the coaching prompt to a large language model for generating a coaching insight to improve the pulse status.
This disclosure describes embodiments of systems, methods, and non-transitory computer readable storage media that utilize a large language model with user activity data to generate objective timelines for a user account. In particular, the disclosed systems can identify user activity data from a variety of electronic applications utilized by the user account to generate a user account data stream. Furthermore, the disclosed systems can utilize the user account data stream and an identified time objective to generate navigable objective timelines for the user account utilizing a large language model. For instance, the disclosed systems can utilize a large language model with one or more prompts (e.g., time expenditure prompts) generated utilizing the user activity data stream and the time objective. Indeed, the disclosed systems can utilize the large language model with the prompts to generate a navigable objective timeline based on the user activities.
The present disclosure relates to systems, non-transitory computer-readable media, and methods for selecting machine-learning models and hardware environments for executing a task. In particular, in one or more embodiments, the disclosed systems select a designated machine-learning model for executing a task based on workload features of the task and task routing metrics for a plurality of machine-learning models. In addition, in one or more embodiments, the disclosed systems select a designated hardware environment for executing the task based on workload features for the task and task routing metrics for a plurality of hardware environments. In some embodiments, the disclosed systems select a fallback machine-learning model and a fallback hardware environment for executing the task if the designated machine-learning model or designated hardware environment are unavailable. Moreover, in one or more embodiments, the disclosed systems can pause and initiate tasks based on bandwidth availability.
G06F 9/50 - Allocation of resources, e.g. of the central processing unit [CPU]
G06F 9/48 - Program initiatingProgram switching, e.g. by interrupt
G06F 11/14 - Error detection or correction of the data by redundancy in operation, e.g. by using different operation sequences leading to the same result
G06F 11/20 - Error detection or correction of the data by redundancy in hardware using active fault-masking, e.g. by switching out faulty elements or by switching in spare elements
H04L 41/16 - Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks using machine learning or artificial intelligence
This disclosure describes systems that generate a selection of large language model (LLM) function buttons in a floating widget within a web browser of a client device. The disclosed systems can generate or otherwise select the LLM function buttons to include based on context of a webpage within the web browser. Responsive to detecting an indication of an interaction with an LLM function button, the disclosed systems can generate a side panel within the web browser according to the LLM function button. In some embodiments, the disclosed systems can display and utilize a customized LLM function button responsive to detecting a certain webpage or content within the webpage. Further, in some embodiments, the disclosed systems can generate an LLM function button to perform a customized workflow responsive to detecting a certain webpage or content within the webpage.
G06F 3/04817 - Interaction techniques based on graphical user interfaces [GUI] based on specific properties of the displayed interaction object or a metaphor-based environment, e.g. interaction with desktop elements like windows or icons, or assisted by a cursor's changing behaviour or appearance using icons
The present disclosure relates to systems, methods, and non-transitory computer-readable media that utilize machine learning models to generate identifier embeddings from digital content identifiers and then leverage these identifier embeddings to determine digital connections between digital content items. In particular, the disclosed systems can utilize an embedding machine-learning model that comprises a character-level embedding machine-learning model and a word-level embedding machine-learning model. For example, the disclosed systems can combine a character embedding from the character-level embedding machine-learning model and a token embedding from the word-level embedding machine-learning model. The disclosed systems can determine digital connections between the plurality of digital content items by processing these identifier embeddings for a plurality of digital content items utilizing a content management model. Based on the digital connections, the disclosed systems can surface one or more digital content suggestions to a user interface of a client device.
Systems and methods are disclosed herein for enabling consistent caching. The disclosed approach enables consistent caching by maintaining a timestamp that tracks an upper bound for the most recent observed write attempt to any key, regardless of whether the write attempt was successful or unsuccessful. When a server attempts to read a value of a key, it compares the upper bound timestamp of the key to a read timestamp of the key. The read timestamp is stored in the cache and represents a time at which the key was most recently read. If the upper bound timestamp is after the read timestamp, the cache is stale, so the server retrieves the value of the key from data storage rather than the cache. If the upper bound timestamp is before the read timestamp, the server retrieves the value of the key from the cache.
The present disclosure is directed toward systems and methods that efficiently and effectively generate and utilize collections of content items. For example, systems and methods described herein generate a collection content item including one or more content item references. In one or more embodiments, the collection content item can include content item references for content items located internally or externally, with granular levels of permissions settings and version controls. Additionally, in response to a detected selection of a content item reference, systems and methods described herein generate a rendering of the associated content item that can be viewed regardless of any third party software installed on the viewing client computing device.
The present disclosure relates to systems, non-transitory computer-readable media, and methods for generating a content stack utilizing one or more machine-learning models. In some implementations, the disclosed systems generate and provide, to a user account, a content stack that includes content items corresponding to a topic prompt for the user account. For instance, in some implementations, the disclosed systems utilize content-based signals and account-based signals to generate an account-specific stack formulation graph that represents a plurality of content items and relationships of the content items with each other and with the user account. Additionally, in some implementations, the disclosed systems analyze the account-specific stack formulation graph to generate a content stack from the plurality of content items, the content stack comprising a set of content items corresponding to the topic prompt.
The present disclosure relates to systems, non-transitory computer-readable media, and methods for utilizing a large language model to generate computer code executable to generate a series of calendar events for completing a target objective. Furthermore, the disclosed systems provide a catalyst calendar interface which includes a chat window and an integrated calendar window to interface to display the series of calendar events. For instance, the disclosed systems utilize the large language model to generate a task curriculum which includes a set of executable tasks whose completion accomplishes the target objective. Furthermore, the disclosed systems can generate computer code executable by a calendar application to generate the series of calendar events corresponding to the set of executable tasks. The disclosed systems can interact with the chat window to provide the series of calendar events incorporating an integrated view of the calendar application, via the integrated calendar window, using rich calendar content.
The present disclosure relates to systems, non-transitory computer-readable media, and methods for utilizing a large language model to generate computer code executable to generate a series of calendar events for completing a target objective. Furthermore, the disclosed systems provide a catalyst calendar interface which includes a chat window and an integrated calendar window to interface to display the series of calendar events. For instance, the disclosed systems utilize the large language model to generate a task curriculum which includes a set of executable tasks whose completion accomplishes the target objective. Furthermore, the disclosed systems can generate computer code executable by a calendar application to generate the series of calendar events corresponding to the set of executable tasks. The disclosed systems can interact with the chat window to provide the series of calendar events incorporating an integrated view of the calendar application, via the integrated calendar window, using rich calendar content.
The present disclosure relates to systems, non-transitory computer-readable media, and methods for generating personal responses through retrieval-augmented generation. In particular, the disclosed systems can generate a query embedding from a query generated by an entity and determine data context specific to the entity by comparing the query embedding with a plurality of vectorized segments of content items associated with the entity. The disclosed systems can provide the data context to a large language model and generate a personalized response informed by the data context. Subsequently, the disclosed systems can provide the personalized response for display on a client device associated with the entity.
Systems, methods, and non-transitory computer readable media for managing content items having multiple resolutions may be provided. In some embodiments, a user device may send a request to access one or more images from a content management system. The one or more images may be categorized on the user device by an expected use that determines that the one or more images be in a first version. A second version of the one or more images may be received while a background download of the first version of the one or more images may be performed. In some embodiments, the first version may correspond to a high-resolution image whereas the second version may correspond to a lower resolution image.
H04L 67/61 - Scheduling or organising the servicing of application requests, e.g. requests for application data transmissions using the analysis and optimisation of the required network resources taking into account QoS or priority requirements
G06F 16/50 - Information retrievalDatabase structures thereforFile system structures therefor of still image data
G06F 16/58 - Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
G06F 16/587 - Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using geographical or spatial information, e.g. location
G06F 16/957 - Browsing optimisation, e.g. caching or content distillation
H04M 1/72445 - User interfaces specially adapted for cordless or mobile telephones with means for local support of applications that increase the functionality for supporting Internet browser applications
H04N 1/00 - Scanning, transmission or reproduction of documents or the like, e.g. facsimile transmissionDetails thereof
59.
MODIFYING A FILE STORAGE STRUCTURE UTILIZING A MULTI-SECTION GRAPHICAL USER INTERFACE
This disclosure describes embodiments of systems, methods, and non-transitory computer readable storage media that can display icons for target digital content items and candidate destination folders within different sections of a multi-section graphical user interface (GUI) and adjust a corresponding file storage structure to reflect organization changes indicated by user interactions that move digital-content-items icons into folder icons. For example, the disclosed system can (i) display, within a first section of a multi-section GUI, icons representing digital content items and (ii) display, within a second section of the multi-section GUI, icons representing folders as candidate destination folders. Then, the disclosed systems can detect user interactions that move digital-content-item icons to folder icons and adjust an underlying file storage structure to reflect the organization indicated by the user interaction.
G06F 3/04817 - Interaction techniques based on graphical user interfaces [GUI] based on specific properties of the displayed interaction object or a metaphor-based environment, e.g. interaction with desktop elements like windows or icons, or assisted by a cursor's changing behaviour or appearance using icons
G06F 3/0482 - Interaction with lists of selectable items, e.g. menus
G06F 16/16 - File or folder operations, e.g. details of user interfaces specifically adapted to file systems
60.
Protecting content from generative artificial intelligence
The present technology introduces a simple to use interface that integrates a mechanism to protect content items from use by one or more machine learning algorithms into interfaces of a content management system. In this way, the present technology can make it easy to protect content items where they are stored. The present technology protects against this use by providing options to obfuscate content in a way that can confound artificial intelligence systems during both training and use of the artificial intelligence systems. Additionally, the present technology can control access to content items shared using a link. The content management system can determine not to serve content items when requested by known artificial intelligence systems or services that train them. The present technology can also include automatic content protection rules that can cause the content management system to automatically protect content items when the content item is to be shared.
H04L 29/06 - Communication control; Communication processing characterised by a protocol
H04L 9/32 - Arrangements for secret or secure communicationsNetwork security protocols including means for verifying the identity or authority of a user of the system
61.
MODIFYING A FILE STORAGE STRUCTURE UTILIZING A MULTI-SECTION GRAPHICAL USER INTERFACE
This disclosure describes embodiments of systems, methods, and non-transitory computer readable storage media that can display icons for target digital content items and candidate destination folders within different sections of a multi-section graphical user interface (GUI) and adjust a corresponding file storage structure to reflect organization changes indicated by user interactions that move digital-content-items icons into folder icons. For example, the disclosed system can (i) display, within a first section of a multi-section GUI, icons representing digital content items and (ii) display, within a second section of the multi-section GUI, icons representing folders as candidate destination folders. Then, the disclosed systems can detect user interactions that move digital-content-item icons to folder icons and adjust an underlying file storage structure to reflect the organization indicated by the user interaction.
G06F 3/04817 - Interaction techniques based on graphical user interfaces [GUI] based on specific properties of the displayed interaction object or a metaphor-based environment, e.g. interaction with desktop elements like windows or icons, or assisted by a cursor's changing behaviour or appearance using icons
G06F 3/0482 - Interaction with lists of selectable items, e.g. menus
G06F 16/16 - File or folder operations, e.g. details of user interfaces specifically adapted to file systems
The present disclosure is directed toward systems, methods, and non-transitory computer readable media for generating content clusters from topic data and focus data, generating content collections from content clusters, storing and restoring desktop scene layouts, and storing and arranging video call scenes. In some embodiments, the disclosed systems generate content clusters based on topic data and focus data associated with content items within a content management system and/or accessed via the internet. The disclosed systems can also generate content collections for a user account of the content management system from the content clusters. In some embodiments, the content scene system can further store and restore desktop scene layouts for arranging application windows presenting content items. Further, the disclosed systems can store and arrange particular desktop scene layouts for video call scenes.
G06F 9/451 - Execution arrangements for user interfaces
G06F 3/0481 - Interaction techniques based on graphical user interfaces [GUI] based on specific properties of the displayed interaction object or a metaphor-based environment, e.g. interaction with desktop elements like windows or icons, or assisted by a cursor's changing behaviour or appearance
G06F 3/0484 - Interaction techniques based on graphical user interfaces [GUI] for the control of specific functions or operations, e.g. selecting or manipulating an object, an image or a displayed text element, setting a parameter value or selecting a range
G06F 11/14 - Error detection or correction of the data by redundancy in operation, e.g. by using different operation sequences leading to the same result
63.
Generating responses using a context engine coupled with a logic engine and time phrase resolution
The present disclosure relates to systems, non-transitory computer-readable media, and methods for generating responses to prompts by utilizing a context engine and a logic engine. In one or more embodiments, the disclosed systems can determine a prompt received from a client device involves one or more logical problems with a prompt classification model. Based on identifying the one or more logical problems, the disclosed systems can generate a logic code segment by processing the prompt with one or more large language models within a context engine. The disclosed systems can generate a logic result for the prompt by processing the logic code segment with a logic engine that solves one or more logical problems within the prompt according to the structure of the logic code segment. The disclosed systems can generate a response to the prompt based, at least in part, on the logic result.
The present disclosure is directed toward systems, methods, and non-transitory computer-readable media for generating function code and test code to determine that the function code satisfies an intent query. For example, the disclosed systems utilize a large language model to process an intent query and generate function code that defines one or more processes whose execution satisfies the intent query. In addition, the disclosed systems also utilize the large language model to generate test code that defines a function test for determining that the function code satisfies the intent query. Moreover, the disclosed systems can execute the test code to determine that the function code satisfies the intent query.
Methods and systems provide for dynamic contextual generation of creative content for product listings. In one embodiment, the system receives initial product facts for a product, user engagement data for a user of a platform, and one or more pieces of contextual information related to how the product will be viewed within the platform; uses this data to train a generative AI model for dynamic creative content generation for the listing; uses the trained generative AI model to dynamically generate creative content for the listing; displays the creative content for the listing on a client device associated with the user; receives feedback regarding user engagement with the creative content in terms of whether an engagement objective has been achieved; and refines the generative AI model based on the received feedback, including optimizing the generative AI model to generate or modify the creative content to achieve the engagement objective.
Disclosed herein is a system and method to determine whether to place an advertisement to a user requesting an address from the user. The system can iteratively determine multiple advertisement metrics of multiple advertisements to obtain multiple metrics. An advertisement metric among the multiple advertising metrics can indicate the value of placing the advertisement to the user. The system can rank multiple advertisements based on the multiple advertisement metrics and present a predetermined percentage of top-ranking advertisements among the multiple advertisements.
In some embodiments, a client application at a client device can receive, from a browser application at the client device, a first message including a unique identifier associated with a session of the browser application at a website associated with a content management system. The client application can extract the unique identifier from the first message, and establish a connection between the client application and the content management system by sending, from the client application to the content management system, a second message including the unique identifier. The client application can then receive, from the content management system through the connection, a third message relayed by the content management system from the website, where the third message is associated with the unique identifier.
Disclosed are systems, methods, and non-transitory computer-readable storage media for providing an embedded web view of a folder in a content management system on a web page. For example, a user can request from a content management system code for embedding a web view of a content item or group of content items (e.g., folder) into a web page. After the code is embedded into the webpage, the web page can present a web view of the content item or group of content items that is dynamically updated when the content item or group of content items is updated. Thus, the user is relieved of the burden of updating the web page with new links to reflect changes in content items stored in the online content management system.
Methods and systems provide for a unified presentation of cross-platform content to a user visiting a platform. In one embodiment, the system connects a client device associated with a user to a first content platform; receives a request from the client device to present content to the user at the first content platform; receives content associated with one or more additional content platforms; determines a subset of the content to present to the user; standardizes the subset of the content in a format to be used at the first content platform; presents the subset of the content to the user at the first content platform; processes a set of unified cross-platform metrics for user events related to the user interacting with the subset of the content at the first content platform; and provides a report of the set of unified cross-platform metrics for the user events.
Disclosed here is a system that can obtain attributes of an advertisement, where an attribute has a continuous value, and a range of acceptable values is uncertain. The system can create a file including contents that when provided to a predetermined function produce a value of the attribute. Based on the file, the system can generate values corresponding to the attributes. Based on the generated values, the system can create the advertisement. The system can obtain a response data to the created advertisement and can fit a multidimensional function to the attributes and the user response data. Based on the multidimensional function, the system can determine next values and next ranges, where the next values and the next ranges indicate an improvement in the response data.
This disclosure describes embodiments of systems, methods, and non-transitory computer readable storage media that can detect scene types across various portions of media content and display collections that organize segments (or portions) of media content (e.g., videos or images) according to the detected scene types for the media content files. For example, the disclosed systems can automatically identify content segments of media content that belong to one or more identified scene types and display the content segments organized by the different scene types. In order to determine the scene types for the content segments of the media content files, the disclosed systems can utilize machine learning that determines relevancies between data of the media content files and the scene types. Furthermore, the disclosed systems can display, within a GUI, the groupings of media content segments organized by the different scene types.
G06F 16/783 - Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
Methods and systems provide content searching and retrieval using generative artificial intelligence (AI) Models. The system is configured to receive a user search for content, media or item listings. The system receives a natural language-based input associated with a client device of a user. The system generates a search criterion for the received natural language-based input. The system, via the generative AI-bases search and retrieval system, generates a relevancy-ranked output listing of content items. The relevancy-ranked output listing content items responsive to the generated search criterion content items having an associated content identifier and a content description. The system generates a carousel display structure definition of the relevancy-ranked content items. The system transmits the carousel display structure definition of the relevancy-ranked content items and the content items to the client device. The client device renders, via a user interface, at least a portion of the relevancy-ranked content items.
G06F 16/2457 - Query processing with adaptation to user needs
G06F 7/08 - Sorting, i.e. grouping record carriers in numerical or other ordered sequence according to the classification of at least some of the information they carry
The present disclosure is directed toward systems, methods, and non-transitory computer-readable media for initiating, monitoring, and performing data backups from remote devices using web-based applications. For example, the disclosed systems receive a backup request from a remote device running a web-based application that does not include backup functionality, where the backup request triggers a data backup for data stored locally on a different client device. In some embodiments, the disclosed systems can establish a connection between the remote web-based application and a desktop application installed locally on the device to be backed up, where the connection facilitates triggering and managing a data backup executed by the desktop application via the remote web-based application. In some cases, the disclosed systems determine whether data backups are synchronous, asynchronous, and/or for user accounts within a team, and the disclosed systems facilitate data backups accordingly.
G06F 11/14 - Error detection or correction of the data by redundancy in operation, e.g. by using different operation sequences leading to the same result
74.
USING GENERATIVE AI MODELS FOR CONTENT SEARCHING AND GENERATION OF CONFABULATED SEARCH RESULTS
Methods and systems provide content searching and retrieval using generative artificial intelligence (AI) Models. The system is configured to receive a user search for content, media or item listings. The user search is provided to a generative AI based search sub-system and to a traditional search sub-system. A first search result listing is generated by the generative AI based subsystem, and a second search result listing is generated by the traditional search sub-system. The first search result listing and the second search result listing are aggregated together and provided for display to a user client device.
The present disclosure relates to systems, methods, and non-transitory computer-readable media for segmenting a digital video to segment a digital video by employing a chapterization approach to video transcripts based on contextual data from audio signals and video signals together. In some embodiments, the disclosed systems can extract various types of audio signals and various types of video signals from a digital video. From the extracted signals, the disclosed systems can determine a set of break points to segment a video transcript. In some embodiments, the disclosed systems can further recommend, via a notification on a client device, inserting corresponding breaks from the segmented transcript into the digital video.
G06V 20/40 - ScenesScene-specific elements in video content
G06T 7/90 - Determination of colour characteristics
G06V 10/44 - Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersectionsConnectivity analysis, e.g. of connected components
G10L 15/18 - Speech classification or search using natural language modelling
H04N 19/172 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding the unit being an image region, e.g. an object the region being a picture, frame or field
76.
DIRECTED ACYCLIC GRAPH FRAMEWORK FOR EXECUTING SEARCH FUNCTION OPERATIONS
The present disclosure is directed toward systems, methods, and non-transitory computer-readable media for performing a data search for a search request by utilizing a directed acyclic graph. For example, the disclosed systems receive a search request at a search engine of a content management system. In addition, the disclosed systems determine (e.g., in response to the search request) a node path from a directed acyclic graph that includes a plurality of interconnected nodes defining computer operations. Further, the determined node path includes a set of nodes that corresponds to the search request. Moreover, the disclosed systems perform the data search for the search request by executing operations defined by nodes along the node path within the directed acyclic graph.
The present disclosure relates to systems, non-transitory computer-readable media, and methods for generating and providing content update synopses using a large language model. In particular, in some embodiments, the disclosed systems determine, for a collaborative workspace of a content management system, activity metadata defining user account activity across a plurality of user accounts performing actions within the collaborative workspace. Further, the disclosed systems can generate, from the activity metadata, a text representation of the user account activity indicating the actions within the collaborative workspace that occur between a first timestamp and a second timestamp. Additionally, the disclosed systems can generate a summary generation prompt from the text representation of the user account activity. Moreover, the disclosed systems can generate an activity summary for the user account activity within the collaborative workspace between the first timestamp and the second timestamp by providing the summary generation prompt to a large language model.
The present disclosure is directed toward systems, methods, and non-transitory computer-readable media for providing a streamed presentation of a video proxy referencing a cloud-based location of a digital video. For example, the disclosed systems receive a request to edit a digital video stored in a cloud-based location of a content management system. In addition, the disclosed systems generate a video proxy that include a reference to the cloud-based location of the digital video and modifies the video proxy in response to an editing operation. Further, the disclosed systems provide for display a streamed presentation of the video proxy depicting modifications defined by the editing operation.
G11B 27/031 - Electronic editing of digitised analogue information signals, e.g. audio or video signals
G06F 3/04845 - Interaction techniques based on graphical user interfaces [GUI] for the control of specific functions or operations, e.g. selecting or manipulating an object, an image or a displayed text element, setting a parameter value or selecting a range for image manipulation, e.g. dragging, rotation, expansion or change of colour
G06F 3/04847 - Interaction techniques to control parameter settings, e.g. interaction with sliders or dials
79.
GENERATING AND PROVIDING SYNTHESIZED TASKS PRESENTED IN A CONSOLIDATED GRAPHICAL USER INTERFACE
The present disclosure relates to systems, non-transitory computer-readable media, and methods for collecting, organizing, and managing third-party content from multiple sources associated with a user account to present as synthesized tasks in a consolidated graphical user interface and minimize the distraction provided by multiple interfaces. In particular, in one or more embodiments, the disclosed systems analyze content from various web-based data sources, collect relevant content, create synthesized tasks associated with the relevant content, and present the relevant content to the user grouped into synthesized tasks in a single graphical user interface. Additionally, the disclosed systems can prioritize the generated synthesized tasks within the graphical user interface and provide productivity metrics based on the degree to which an associated user interacts with the synthesized tasks.
G06F 9/48 - Program initiatingProgram switching, e.g. by interrupt
G06F 3/0481 - Interaction techniques based on graphical user interfaces [GUI] based on specific properties of the displayed interaction object or a metaphor-based environment, e.g. interaction with desktop elements like windows or icons, or assisted by a cursor's changing behaviour or appearance
G06F 9/451 - Execution arrangements for user interfaces
80.
INTELLIGENTLY GENERATING AND MANAGING THIRD-PARTY SOURCES WITHIN A CONTEXTUAL HUB
The present disclosure is directed toward systems, methods, and non-transitory computer readable media for generating contextual hubs for organizing and presenting web-accessible content from third-party sources. In particular, the systems described herein can organize and manage within a contextual hub. For instance, the disclosed systems may perform actions on tabs based on analyzing usage signals associated with the tabs. Furthermore, the disclosed systems can organize contextually related content within contextual hubs. The disclosed systems may also facilitate collaboration between users within a contextual hub by synchronizing interactions with content within a contextual hub.
G06F 16/957 - Browsing optimisation, e.g. caching or content distillation
G06F 3/0481 - Interaction techniques based on graphical user interfaces [GUI] based on specific properties of the displayed interaction object or a metaphor-based environment, e.g. interaction with desktop elements like windows or icons, or assisted by a cursor's changing behaviour or appearance
G06F 9/451 - Execution arrangements for user interfaces
G06F 16/954 - Navigation, e.g. using categorised browsing
G06F 16/955 - Retrieval from the web using information identifiers, e.g. uniform resource locators [URL]
G06F 16/958 - Organisation or management of web site content, e.g. publishing, maintaining pages or automatic linking
H04L 67/125 - Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks involving control of end-device applications over a network
The present disclosure is directed toward systems, methods, and non-transitory computer readable media for generating, arranging, and providing subgroupings of content items according to content attributes and dynamic facets. For example, the disclosed systems generate dynamic facets reflecting content attributes, where the dynamic facets are selectable interface elements for arranging content items into subgroups. In certain cases, as part of generating a subgrouping of content items, the disclosed systems can identify portions of content items (e.g., segments of a digital video or sections of a digital document) that correspond to a dynamic facet. The disclosed systems can also provide filtering options for creating or refining subgroupings from a content collection by, for example, filtering according to recency criteria such as file type, recency of interaction, collaborative user accounts, or others.
G06F 3/04842 - Selection of displayed objects or displayed text elements
G06F 3/04817 - Interaction techniques based on graphical user interfaces [GUI] based on specific properties of the displayed interaction object or a metaphor-based environment, e.g. interaction with desktop elements like windows or icons, or assisted by a cursor's changing behaviour or appearance using icons
82.
UTILIZING A FEATURE EXTRACTION FUNCTION WITHIN A DIGITAL SEARCH PLATFORM
This disclosure describes embodiments of systems, methods, and non-transitory computer readable storage media that can enable integration of functionalities for a content item search platform within a search platform prototyping tool. For example, the disclosed systems can utilize a search platform prototyping tool that enables a quick selection of a feature extraction function (or component). Based on the selected feature extraction function, the disclosed systems can prototype the feature extraction function on live data of a content management system to emulate a fully onboarded implementation of the feature extraction function (as a new functionality) on a search platform. Moreover, the disclosed systems can also display, within a search platform graphical user interface, selectable elements to display consolidated metadata associated with search results within a single user interface.
The present disclosure is directed toward systems, methods, and non-transitory computer readable media for utilizing a catalyst application to analyze digital content of another computer application to generate or extract tasks. The catalyst application can accompany and operate in conjunction with another computer application to extract data from the application and generate tasks. For example, the disclosed systems can scan displayed (or otherwise presented) digital content in an application and can generate a prompt for causing a large language model to identify or extract tasks from the digital content. Through the catalyst application, the disclosed systems can thus implement a large language model to generate a task list from the digital content of another computer application. The disclosed systems can further utilize the catalyst application to automatically execute or perform extracted tasks.
This disclosure describes systems that identify one or more models (e.g., large language models and/or virtual assistants) permitted to access content items stored for user accounts within a content management system. The disclosed systems can determine a model available to a user account within the content management system from among the one or more models. For example, the disclosed systems can determine one or more relationships between the user accounts within the content management system, large language models utilized by the user accounts, virtual assistants utilized by the user accounts, and content items accessed by the user accounts. The disclosed systems can determine the model for the user account according to the one or more relationships. The disclosed systems can provide a notification corresponding to the model via a user interface of a client device associated with the user account.
The present disclosure relates to systems, non-transitory computer-readable media, and methods for selecting machine-learning models and hardware environments for executing a task. In particular, in one or more embodiments, the disclosed systems select a designated machine-learning model for executing a task based on workload features of the task and task routing metrics for a plurality of machine-learning models. In addition, in one or more embodiments, the disclosed systems select a designated hardware environment for executing the task based on workload features for the task and task routing metrics for a plurality of hardware environments. In some embodiments, the disclosed systems select a fallback machine-learning model and a fallback hardware environment for executing the task if the designated machine-learning model or designated hardware environment are unavailable. Moreover, in one or more embodiments, the disclosed systems can pause and initiate tasks based on bandwidth availability.
The present disclosure is directed toward systems, methods, and non-transitory computer-readable media for generating a dynamic facet by using a large language model. For example, the disclosed systems extract raw facet data from a plurality of content items stored in a content management system. In addition, the disclosed systems determine one or more facet content groups by grouping the plurality of content items according to the raw facet data. Further, the disclosed systems generate a facet prompt from the one or more facet content groups. Moreover, the disclosed systems generate a dynamic facet by providing the facet prompt to a large language model.
The present disclosure relates to systems, non-transitory computer-readable media, and methods for selecting machine-learning models and hardware environments for executing a task. In particular, in one or more embodiments, the disclosed systems select a designated machine-learning model for executing a task based on workload features of the task and task routing metrics for a plurality of machine-learning models. In addition, in one or more embodiments, the disclosed systems select a designated hardware environment for executing the task based on workload features for the task and task routing metrics for a plurality of hardware environments. In some embodiments, the disclosed systems select a fallback machine-learning model and a fallback hardware environment for executing the task if the designated machine-learning model or designated hardware environment are unavailable. Moreover, in one or more embodiments, the disclosed systems can pause and initiate tasks based on bandwidth availability.
G06F 9/50 - Allocation of resources, e.g. of the central processing unit [CPU]
G06F 9/48 - Program initiatingProgram switching, e.g. by interrupt
G06F 11/14 - Error detection or correction of the data by redundancy in operation, e.g. by using different operation sequences leading to the same result
G06F 11/20 - Error detection or correction of the data by redundancy in hardware using active fault-masking, e.g. by switching out faulty elements or by switching in spare elements
H04L 41/16 - Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks using machine learning or artificial intelligence
H04L 43/08 - Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters
The present disclosure relates to systems, non-transitory computer-readable media, and methods for selecting machine-learning models and hardware environments for executing a task. In particular, in one or more embodiments, the disclosed systems select a designated machine-learning model for executing a task based on workload features of the task and task routing metrics for a plurality of machine-learning models. In addition, in one or more embodiments, the disclosed systems select a designated hardware environment for executing the task based on workload features for the task and task routing metrics for a plurality of hardware environments. In some embodiments, the disclosed systems select a fallback machine-learning model and a fallback hardware environment for executing the task if the designated machine-learning model or designated hardware environment are unavailable. Moreover, in one or more embodiments, the disclosed systems can pause and initiate tasks based on bandwidth availability.
G06F 9/50 - Allocation of resources, e.g. of the central processing unit [CPU]
G06F 11/14 - Error detection or correction of the data by redundancy in operation, e.g. by using different operation sequences leading to the same result
G06F 11/20 - Error detection or correction of the data by redundancy in hardware using active fault-masking, e.g. by switching out faulty elements or by switching in spare elements
90.
DYNAMICALLY SELECTING ARTIFICIAL INTELLIGENCE MODELS AND HARDWARE ENVIRONMENTS TO EXECUTE TASKS
The present disclosure relates to systems, non-transitory computer-readable media, and methods for selecting machine-learning models and hardware environments for executing a task. In particular, in one or more embodiments, the disclosed systems select a designated machine-learning model for executing a task based on workload features of the task and task routing metrics for a plurality of machine-learning models. In addition, in one or more embodiments, the disclosed systems select a designated hardware environment for executing the task based on workload features for the task and task routing metrics for a plurality of hardware environments. In some embodiments, the disclosed systems select a fallback machine-learning model and a fallback hardware environment for executing the task if the designated machine-learning model or designated hardware environment are unavailable. Moreover, in one or more embodiments, the disclosed systems can pause and initiate tasks based on bandwidth availability.
H04L 41/16 - Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks using machine learning or artificial intelligence
The present disclosure relates to systems, non-transitory computer-readable media, and methods for generating personal responses through retrieval-augmented generation. In particular, the disclosed systems can generate a query embedding from a query generated by an entity and determine data context specific to the entity by comparing the query embedding with a plurality of vectorized segments of content items associated with the entity. The disclosed systems can provide the data context to a large language model and generate a personalized response informed by the data context. Subsequently, the disclosed systems can provide the personalized response for display on a client device associated with the entity.
The present disclosure relates to systems, non-transitory computer-readable media, and methods for selecting machine-learning models and hardware environments for executing a task. In particular, in one or more embodiments, the disclosed systems select a designated machine-learning model for executing a task based on workload features of the task and task routing metrics for a plurality of machine-learning models. In addition, in one or more embodiments, the disclosed systems select a designated hardware environment for executing the task based on workload features for the task and task routing metrics for a plurality of hardware environments. In some embodiments, the disclosed systems select a fallback machine-learning model and a fallback hardware environment for executing the task if the designated machine-learning model or designated hardware environment are unavailable. Moreover, in one or more embodiments, the disclosed systems can pause and initiate tasks based on bandwidth availability.
G06F 11/20 - Error detection or correction of the data by redundancy in hardware using active fault-masking, e.g. by switching out faulty elements or by switching in spare elements
G06F 9/50 - Allocation of resources, e.g. of the central processing unit [CPU]
G06F 11/14 - Error detection or correction of the data by redundancy in operation, e.g. by using different operation sequences leading to the same result
93.
SYNTHESIZING VISUALIZATIONS FOR CONTENT COLLECTIONS
The present disclosure is directed toward systems, methods, and non-transitory computer readable media for generating and providing synthetic visualizations representative of content collections within a content management system. In some cases, the disclosed systems generate a synthetic visualization based on content features that indicate relevance of content items with respect to a user account to emphasize more relevant content items within the synthetic visualization and/or to represent descriptive content attributes of the content items. For example, the disclosed systems can generate a synthetic phrase that represents a content collection and can further generate a synthetic visualization from the synthetic phrase utilizing a synthetic visualization machine learning model.
The present disclosure relates to systems, non-transitory computer-readable media, and methods for capturing snapshots of digital content displayed on a client device and searching through the captured content. The disclosed systems provide a search function for effectively traveling back in time to identify digital content previously displayed on a client device. The disclosed systems provide options for capturing snapshots of content displayed on a display screen, extracting data from the snapshots, and storing the snapshots for use when populating search results. The disclosed systems utilize machine learning models to extract text and/or to generate text versions of snapshots including extracted text, descriptions of images, transcripts of videos, and/or textual summaries from displayed documents or webpages. In response to a search query, the disclosed systems can produce search results that include digital videos including captured snapshots of content displayed by a client device over time.
G06F 16/783 - Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
95.
Dynamically selecting artificial intelligence models and hardware environments to execute tasks
The present disclosure relates to systems, non-transitory computer-readable media, and methods for selecting machine-learning models and hardware environments for executing a task. In particular, in one or more embodiments, the disclosed systems select a designated machine-learning model for executing a task based on workload features of the task and task routing metrics for a plurality of machine-learning models. In addition, in one or more embodiments, the disclosed systems select a designated hardware environment for executing the task based on workload features for the task and task routing metrics for a plurality of hardware environments. In some embodiments, the disclosed systems select a fallback machine-learning model and a fallback hardware environment for executing the task if the designated machine-learning model or designated hardware environment are unavailable. Moreover, in one or more embodiments, the disclosed systems can pause and initiate tasks based on bandwidth availability.
A content management system obtains at least a portion of a meeting transcript based on an audio stream of a meeting attended by a plurality of users, the meeting transcript obtained in an ongoing manner as words are uttered during the meeting. The content management system detects text entered by a user of the plurality of users into a content item during the meeting. The content management system matches the detected text to at least part of the at least the portion of the meeting transcript. The content management system provides the at least part of the at least the portion of the meeting transcript to the user as a suggested subsequent text.
The present disclosure is directed toward systems, methods, and non-transitory computer-readable media for the intelligent generation and completion of digital documents. For example, the disclosed systems provide a document creation interface for entering inputs to generate and modify digital documents. In some instances, the disclosed systems receive a document generation prompt, generate a digital document using a large language model, and provide an indication of the digital document within the document creation interface. Moreover, the disclosed systems can further generate a document summary of the digital document and provide the document summary for a recipient device via a document review interface. Additionally, the disclosed systems can further generate a suggested document modification element and modify the digital document in response to a user interaction with the suggested document modification element using the large language model.
The present disclosure is directed toward systems, methods, and non-transitory computer-readable media for the intelligent generation and completion of digital documents. For example, the disclosed systems provide a document creation interface for entering inputs to generate and modify digital documents. In some instances, the disclosed systems receive a document generation prompt, generate a digital document using a large language model, and provide an indication of the digital document within the document creation interface. Moreover, the disclosed systems can further generate a document summary of the digital document and provide the document summary for a recipient device via a document review interface. Additionally, the disclosed systems can further generate a suggested document modification element and modify the digital document in response to a user interaction with the suggested document modification element using the large language model.
A client application sends an application programming interface call to an interface of a content management system. The call specifies one or more content item search criteria. Sending the call causes the content management system to perform a lookup in a content item index to identify at least one content item that satisfies the one or more content item search criteria. Based on sending the call, the client application receives from the content management system a suggestion to attach the at least one content item to a text being displayed by at the computing system.
The present disclosure is directed toward systems, methods, and non-transitory computer-readable media for editing and collaborating with digital videos through interactions with video transcripts. For example, the disclosed systems can provide a user interface for interacting with a video transcript associated with a digital video. Based on interacting with the video transcript, the disclosed systems can perform editing operations and/or collaborating operations in relation to the digital video. For instance, the disclosed systems can edit a digital video at a video portion corresponding to transcript location where a user interaction occurs within a video transcript.
