Various embodiments of the present disclosure provide a synthetic data driven training scheme that improves the functionality of a computer in various aspects. The techniques comprise determining a labeled entity from an annotated training datapoint determined from a domain-specific training corpus. The techniques comprise determining a set of related entities from a domain-specific dictionary based on the labeled entity. The techniques comprise generating a generative prompt based on the annotated training datapoint and the set of related entities and generating, using a generative model, a set of synthetic training datapoints based on the generative prompt. The techniques comprise training the task-specific NER model using the set of synthetic training datapoints.
Various embodiments of the present disclosure disclose machine-learning based evaluation techniques for detecting feature bias. An evaluation framework is provided that utilizes new evaluation data structures for comprehensibly evaluating feature bias in machine learning models. The evaluation framework includes receiving evaluation dataset for a machine learning model that includes one or more different feature classes of an evaluation feature. The evaluation framework includes generating, using an evaluation function, at least two performance metrics for the machine learning model and generating a unitless dissimilarity metric for the evaluation feature based at least in part on the first performance metric, the second performance metric, and an average between the first and second performance metrics. In this way, the unitless dissimilarity metric is based on a variability associated with the evaluation feature.
The disclosed techniques route data records to reviewers in a manner that improves performance metrics (e.g., throughput, accuracy, etc.), and in some embodiments dynamically adapts to changes in a reviewer pool. The techniques segment reviewers into clusters based at least in part on reviewer feature sets (e.g., performance-based review metrics such as accuracy, completeness, and/or variability), and assign labels to the reviewers based on the segmenting. The techniques also generate subject-specific performance indicators (e.g., vectors, scores, etc.) for the reviewers. For a given data record that is to be reviewed, the techniques determine a propensity metric indicating the probability that the data record pertains to a particular subject, and generate a routing decision by applying the propensity metric, subject-specific performance indicators, and label assignments as input to a routing model. The techniques then route the data record to a particular reviewer based at least in part on the routing decision.
The disclosure is directed to determining one or more indications for a prescribed medication that should be present in claim data for an individual, e.g., when an indication is missing from the claim data. To this end, the disclosed techniques generate a set of features that includes a first feature vector reflective of frequencies with which a provider has previously prescribed the medication, and a second feature vector reflective of frequencies with which the medication has been prescribed to the individual, with the feature vectors being in vector spaces having dimensions that correspond to different candidate indications for the medication. The techniques may also include generating an additional feature based on structured metadata related to the claim, and/or the techniques may use an ensemble machine-learned model to select one of the candidate indication codes (e.g., to confirm the claim indications or provide a missing indication).
G16H 20/10 - ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to drugs or medications, e.g. for ensuring correct administration to patients
G16H 10/60 - ICT specially adapted for the handling or processing of patient-related medical or healthcare data for patient-specific data, e.g. for electronic patient records
6.
PRIVACY PRESERVING WORKFLOW FOR REPRODUCIBLE MACHINE LEARNING TRAINING ITERATIONS
Techniques for tracking machine learning model training iterations that preserve privacy, increase security, and reduce memory and other computing resources are disclosed herein. An example computer-implemented method comprises generating one or more hash values corresponding to raw data associated with a machine-learned model training process, the raw data comprising a first raw data point associated with a first key and the one or more hash values comprising a first hash value; storing the first hash values in a database in association with the first key; executing a first processing stage using the first raw data point to generate a processed data point; generating a hash value for the first processed data point; storing the second hash value in association with the first key; training a machine-learned model using processed data to generate a trained machine-learned model; and registering the trained machine-learned model.
H04L 9/06 - Arrangements for secret or secure communicationsNetwork security protocols the encryption apparatus using shift registers or memories for blockwise coding, e.g. D.E.S. systems
7.
MULTI-GRAPH FRAMEWORK AND WEIGHTED VECTORIZATION APPROACH FOR CLASSIFIER MODEL TRAINING AND INFERENCE
Various embodiments of the present disclosure provide a graph-based vectorization process that improves the functionality of a computer in various aspects. The techniques comprise receiving a request that comprises entity identifier corresponding to a set of class value combinations, generating a class-specific graph representation of the entity identifier based on the set of class value combinations, generating a weighted class-specific graph representation from the class-specific graph representation, generating a class-specific vector representation for the entity identifier based on the weighted class-specific graph representation, inputting the class-specific vector representation to a machine learned classifier to receive a classification for the entity identifier, and then providing a response to the request based on the classification.
Methods, systems, and computer program products for processing a periodontal chart to store the information items therein in a construct that preserves the relationships between the information items
A method includes receiving a periodontal chart image; processing the periodontal chart image using optical character recognition to obtain pocket measurements associated with a plurality of teeth along with positional coordinates of each of the pocket measurements; applying layout rules associated with the periodontal chart image to identify which respective ones of the pocket measurements correspond to which respective ones of the plurality of teeth; and storing the pocket measurements in a computer-readable construct having a specified data format that preserves relationships between the respective ones of the pocket measurements and the respective one of the plurality of teeth.
Various embodiments of the present disclosure provide a diverse preference training framework that improves the functionality of a computer in various aspects. The techniques comprise receiving a training sample that comprises a training context, and a positive sample response and a negative sample response for the training context. The techniques comprise generating, using a positive loss function of the diverse preference training framework, a positive training signal, generating, using a contrastive loss function of the diverse preference training framework, a contrastive training signal, and generating, using a negative loss function of the diverse preference training framework, a negative training signal for the training sample. The techniques comprise generating an aggregated training signal based on the positive training signal, the contrastive training signal, and/or the negative training signal and training, based on the aggregated training signal, a pre-trained language model.
Various embodiments of the present disclosure provide an authorization request augmentation process that improves the functionality of a computer in various aspects. The techniques comprise receiving an authorization request, generating a candidate code from among a set of defined codes, storing, a set of data objects associated with the authorization request, generating, a tagged data object by associating a token of the data object with a tagged code from the set of defined codes, and based at least in part on determining that the candidate code matches the tagged code, providing an augmented authorization request to an entity repository.
Various embodiments of the present disclosure provide a multi-modal machine learning framework for generating an aggregated classification score for a data object. The techniques comprise generating (i) a first object feature set for a first machine learned model, (ii) a second object feature set for a second machine learned model, and (iii) a domain knowledge feature set associated with a domain knowledge profile for a data object, applying the first machine learned model to the first object feature set and the domain knowledge feature set to generate a first classification score for the data object, applying the second machine learned model to the second object feature set and the domain knowledge feature set to generate a second classification score for the data object, and generating an aggregated classification score for the data object based on the first classification score and the second classification score.
Various embodiments of the present disclosure provide a multi-modal machine learning framework for generating an aggregated classification score for a data object. The techniques comprise generating (i) a first object feature set for a first machine learned model, (ii) a second object feature set for a second machine learned model, and (iii) a domain knowledge feature set associated with a domain knowledge profile for a data object, applying the first machine learned model to the first object feature set and the domain knowledge feature set to generate a first classification score for the data object, applying the second machine learned model to the second object feature set and the domain knowledge feature set to generate a second classification score for the data object, and generating an aggregated classification score for the data object based on the first classification score and the second classification score.
Various embodiments of the present disclosure provide an authorization request augmentation process that improves the functionality of a computer in various aspects. The techniques comprise receiving an authorization request, generating a candidate code from among a set of defined codes, storing, a set of data objects associated with the authorization request, generating, a tagged data object by associating a token of the data object with a tagged code from the set of defined codes, and based at least in part on determining that the candidate code matches the tagged code, providing an augmented authorization request to an entity repository.
42 - Scientific, technological and industrial services, research and design
44 - Medical, veterinary, hygienic and cosmetic services; agriculture, horticulture and forestry services
Goods & Services
Providing temporary use of on-line non-downloadable software for monitoring of data indicative of the health or condition of an individual or group of individuals Remote monitoring of data indicative of the health or condition of an individual or group of individuals for medical diagnosis and treatment purposes
A method comprising: obtaining a graph comprising a plurality of nodes and a plurality of edges, wherein: the nodes include behavior nodes that correspond to respective behavior reasons in a plurality of predefined behavior reasons, the edges correspond to transitions between the nodes and are associated with weights; obtaining one or more interaction records, wherein the one or more interaction records are records of interactions of representatives of an organization with a current client; applying a trained machine learning (ML) model to the one or more interaction records to identify one or more behavior reasons associated with the current client; generating a behavior vector based on the one or more behavior reasons associated with the current client; and performing a communication action based on the graph and the behavior vector.
Systems, methods, and apparatuses implementing a display optimization system are provided herein. In some embodiments, an example display optimization system may be configured to perform an optimal anchor-prior matching operation to identify optimal anchor-prior image pairs or series pairs from new medical imaging data (e.g., one or more anchor image series) and historical medical imaging data (e.g., one or more prior image series).
G16H 30/20 - ICT specially adapted for the handling or processing of medical images for handling medical images, e.g. DICOM, HL7 or PACS
18.
Methods, systems, and computer program products for selecting criteria subsets for performing a medical necessity review with automatic evidence highlighting
A method includes receiving input information associated with a health record of a patient, the input information comprising a plurality of input variable tokens; embedding the plurality of input variable tokens to generate a plurality of input variable token vectors, respectively; aggregating the plurality of input variable token vectors to generate a patient health record vector; generating, using an artificial intelligence model, an identification of a criterion used for determining an appropriateness of a care plan for the patient based on the patient health record vector; and generating a ranking of respective ones of the plurality of input variable tokens based on how much each of the plurality of input variable tokens contributed to the identification of the criterion.
G16H 50/20 - ICT specially adapted for medical diagnosis, medical simulation or medical data miningICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
Techniques for accurately and efficiently assessing compatibility between resource users (e.g., patients) and resources (e.g., healthcare providers, facilities having certain medical equipment, etc.) obtain both user-side responses and resource-side responses to respective sets of queries (e.g., survey questions), and use those responses to compute a compatibility metric. The computation includes applying a rule set, which maps candidate responses of the resource user to candidate responses associated with the resource, including at least one rule that defines a one-to many or many-to-many mapping, i.e., maps a candidate user-side response to two or more candidate resource-side responses, or maps a candidate resource-side response to two or more candidate user-side responses. The rule set also defines computational rules that are associated with particular mappings.
Various embodiments of the present disclosure provide methods, apparatus, systems, computing devices, computing entities, and/or the like for generating domain-specific queries that are semantically similar to a search query by spell-correcting and tokenizing a search query, and then generating, using an embeddings dictionary data object associated with one or more domain vocabulary data objects, queries semantically related to the search query based on proximity of one or more similar embeddings to an embedding associated with the tokenized query within a domain vector space.
Various embodiments of the present disclosure provide a hybrid machine learning process that improves the functionality of a computer in various aspects. The techniques comprise generating, using a supervised machine learning model of a connected model framework, a predictive feature for an entity of a set of entities based on a set of entity attributes corresponding to the entity. The techniques comprise generating, using a clustering model of the connected model framework, a refined entity cluster by (i) generating an initial cluster for the entity that comprises a first subset of the set of entities, (ii) generating, based on the predictive feature, a coefficient of variation for the initial cluster, and (iii) generating the refined cluster from the initial cluster based on the coefficient of variation. The techniques comprise generating a modified predictive feature for the entity based on the refined cluster.
G06F 18/23213 - Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
22.
SYSTEMS AND METHODS FOR EFFICIENT DETERMINATION OF MULTI PAYER ELIGIBILITY
The present disclosure generally relates to multiple payer eligibility determinations, and more particularly, to using machine learning (ML) to predict payer lists and rankings for members. A first ML component determines/predicts/infers that a set of member identifiers, from among multiple such identifiers included in membership data of various coverage providers, is associated with a particular member. A second ML component determines a ranked coverage provider set associated with the member. The second ML component may estimate a relationship between interdependent variables, such as claims, enrollment, eligibility, and plan details, for example.
Various embodiments of the present disclosure provide for training and/or deploying a machine learned model based on a training vector associated with a text document embedding and an attribute set. The techniques may include receiving a user attribute feature set associated with a user identifier for a user-text pair, generating an input text document embedding for the user identifier, generating an input vector by concatenating the user attribute feature set with the input text document embedding, generating, using a machine learned model that is trained based on a ground truth label and a training vector associated with a text document embedding generated by a text encoder model, a classification score for the input text document embedding based on the input vector, and generating a transcript corresponding to the input text document embedding upon determining that the classification score satisfies a predetermined threshold.
Various embodiments of the present disclosure provide a data augmentation technique that improves the functionality of a computer in various aspects. The technique comprises receiving a training dataset, wherein (i) the training dataset comprises a set of datapoints and (ii) a datapoint of the set of datapoints comprises (a) a set of elements and (b) a training label that corresponds to the set of elements and is based on an element-specific label of an element within the set of elements; generating an augmented training dataset from the training dataset by (i) determining, from the set of elements, an element subset, (ii) determining a synthetic training label for the element subset based on the element-specific label, and (iii) generating a synthetic datapoint for the augmented training dataset based on the element subset and the synthetic training label; and training, using the augmented training dataset, the deep set neural network.
Techniques for accurately and efficiently assessing compatibility between resource users (e.g., patients) and resources (e.g., healthcare providers, facilities having certain medical equipment, etc.) obtain both user-side responses and resource-side responses to respective sets of queries (e.g., survey questions), and use those responses to compute a compatibility metric. The computation includes applying a rule set, which maps candidate responses of the resource user to candidate responses associated with the resource, including at least one rule that defines a one-to many or many-to-many mapping, i.e., maps a candidate user-side response to two or more candidate resource-side responses, or maps a candidate resource-side response to two or more candidate user-side responses. The rule set also defines computational rules that are associated with particular mappings.
The present disclosure generally relates to multiple payer eligibility determinations, and more particularly, to using machine learning (ML) to predict payer lists and rankings for members. A first ML component determines/predicts/infers that a set of member identifiers, from among multiple such identifiers included in membership data of various coverage providers, is associated with a particular member. A second ML component determines a ranked coverage provider set associated with the member. The second ML component may estimate a relationship between interdependent variables, such as claims, enrollment, eligibility, and plan details, for example.
Various embodiments of the present disclosure provide agnostic image segmentation techniques that improves the functionality of a computer in various aspects. The techniques comprise receiving image segmentation data that identifies a set of bounding boxes within an image; generating, using a clustering algorithm, and based on a y-axis distance between at least two bounding boxes within the set of bounding boxes, an initial bounding box cluster that comprises a first subset of bounding boxes; generating based on an x-axis distance between at least two bounding boxes within the initial bounding box cluster, a refined bounding box cluster from the initial bounding box cluster that comprises a second subset of bounding boxes; generating, a feature vector for the refined bounding box cluster based on a raw feature set; generating a segment classification for the refined bounding box cluster; and storing the raw feature set and the segment classification.
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
G06V 10/762 - Arrangements for image or video recognition or understanding using pattern recognition or machine learning using clustering, e.g. of similar faces in social networks
G06V 10/764 - Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
G06V 10/77 - Processing image or video features in feature spacesArrangements for image or video recognition or understanding using pattern recognition or machine learning using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]Blind source separation
G06V 30/168 - Smoothing or thinning of the patternSkeletonisation
G06V 30/18 - Extraction of features or characteristics of the image
Techniques for standardized interaction classification across multiple communication channels may comprise receiving interaction data associated with a user interaction with a device associated with a communication channel and generating an interaction summary of the user interaction. The techniques may further comprise generating a feature vector of the interaction summary and determining semantic similarity values of the interaction summary feature vector and one or more feature vectors representing interaction description taxonomies of a standardized interaction classification schema. The techniques may further comprise determining an interaction label of the schema that corresponds to the interaction summary and generating a data object that indicates the interaction label. These techniques generate accurate, generalizable interaction labels without performing significantly redundant computing processes and/or otherwise occupying substantial computing resources.
Various embodiments of the present disclosure provide message ingestion interfaces that improves the functionality of a computer in various aspects. The techniques comprise receiving an incoming message that corresponds to stored record and comprises self-referencing data structures. The techniques comprise converting the incoming message to a message graph that maintains the self-referencing integrity of the incoming message, generating, using a hashing algorithm, an incoming message hash for the incoming message based on the message graph, detecting a record modification for the stored record based on a hash comparison between the incoming message hash and a recorded hash of the stored record, and storing a portion of the incoming message that corresponds to the record modification.
A computer-implemented method includes receiving, by one or more processors, a set of structured records containing clinical information associated with one or more patients; extracting, by the one or more processors, a set of medical entities from the clinical information; determining, by the one or more processors, relationship strengths between pairs of the medical entities; and configuring, by the one or more processors, a computer-readable memory with a knowledge graph data structure in which nodes of the knowledge graph data structure represent the medical entities and the nodes are related to one another in the knowledge graph data structure based on the relationship strengths.
G16H 50/70 - ICT specially adapted for medical diagnosis, medical simulation or medical data miningICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
Hierarchical data objects are generated via a computer-based system for applying a series of rules to establish episode-specific data objects reflecting a plurality of discrete claim records before further dissecting the generated episode-specific data objects prior to finalization of those episode-specific data objects to identify claim records within the episode-specific data objects that are eligible for generation of one or more sub-episodes within the episode-specific data objects. The identified sub-episodes are reflected within the episode-specific data object to designate complete episodes of care that additionally reflect interactions with the corresponding parent episode.
G16H 50/30 - ICT specially adapted for medical diagnosis, medical simulation or medical data miningICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indicesICT specially adapted for medical diagnosis, medical simulation or medical data miningICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for individual health risk assessment
G16H 10/65 - ICT specially adapted for the handling or processing of patient-related medical or healthcare data for patient-specific data, e.g. for electronic patient records stored on portable record carriers, e.g. on smartcards, RFID tags or CD
G16H 20/10 - ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to drugs or medications, e.g. for ensuring correct administration to patients
G16H 50/70 - ICT specially adapted for medical diagnosis, medical simulation or medical data miningICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
G16H 70/40 - ICT specially adapted for the handling or processing of medical references relating to drugs, e.g. their side effects or intended usage
32.
AUTOMATED LANGUAGE MODEL-BASED TRAINING FRAMEWORK FOR MACHINE LEARNING CLASSIFIERS
Various embodiments of the present disclosure provide an automated language model-based training framework for machine learning classifiers. The techniques comprise receiving a data request that includes a search parameter to be applied to a plurality of data elements, generating a search embedding corresponding to the search parameter via an encoder language model, detecting a first subset of data elements among the plurality of data elements that comprise corresponding embeddings that align with the search embedding in accordance with a first threshold, detecting a second subset of data elements among the first subset of data elements that comprise corresponding classification scores that satisfy a second threshold, and transmitting one or more data packets that comprises one or more data elements of the second subset of data elements in response to the data request.
Various embodiments of the present disclosure provide a machine learning framework for machine learning classifiers based on labeled binary vectors for a data object. The techniques comprise generating a data matrix object based on a group of partially masked sets and a group of training predictions respectively generated by a pre-trained classifier using a group of partially masked sets, training a tabular machine learning model using the data matrix object as a training dataset, determining a set of importance scores that respectively correspond to the set of text segments based on one or more parameters of the tabular machine learning model determined during the training, and providing at least one text segment of the set of text segments to associate with the original prediction as a reason the original prediction was generated.
Various embodiments of the present disclosure provide hallucination mitigation techniques for text-to-code conversions that improves the functionality of a computer in various aspects. The techniques comprise receiving a text-based file that defines a set of standards for a prediction domain; generating, using a machine learning model, a decision tree based on (i) the text-based file and (ii) a decisioning prompt for the text-based file; generating, using the machine learning model, computer programmable code for the set of standards based on the decision tree and a code conversion prompt for the decision tree; and providing the computer programmable code to implement an automated task for the prediction domain.
G16H 10/00 - ICT specially adapted for the handling or processing of patient-related medical or healthcare data
G16H 40/00 - ICT specially adapted for the management or administration of healthcare resources or facilitiesICT specially adapted for the management or operation of medical equipment or devices
35.
AUTONOMOUS ENCODING AND CANDIDATE ROUTE MAPPING FRAMEWORK
Various embodiments of the present disclosure provide an autonomous encoding and candidate route mapping technique that improves the functionality of a computer in various aspects. The techniques comprise receiving, using a data collection service of a routing pipeline for a graphical user interface, input data from one or more of a plurality of data sources. The techniques comprise generating using an encoding service of the routing pipeline for the graphical user interface, encoded data. The techniques comprise generating, using an optimization service for the graphical user interface, a candidate route mapping by applying a set of weighted hard parameters and a set of weighted soft parameters to the encoded data. The techniques comprise initiating, using a provisioning service of the routing pipeline for the graphical user interface, an update to a real-time view of the graphical user interface based on the candidate route mapping.
Various embodiments of the present disclosure provide a data feature engineering technique that improves the functionality of a computer in various aspects. The techniques comprise receiving an unclassified data object representative of an incident associated with a software system; generating a domain-enhanced data object based on the unclassified data object and a domain that is associated with the software system; generating an enhanced entity-level vector for a pre-processed unclassified entity from the domain-enhanced data object by combining a weighted frequency measure vector with an entity-level vector for the pre-processed unclassified entity; generating an incident representation vector for the domain-enhanced data object based on the enhanced entity-level vector; and providing the incident representation vector as input to a classifier ensemble model to receive a set of classification outputs that respectively corresponds to a set of incident attribute labels for the incident.
Various embodiments of the present disclosure provide a gesture translation pipeline that improves the functionality of a computer in various aspects. The techniques comprise receiving an image that depicts a facial expression and a hand position of a user, generating, using a parallel feature extraction model of a multi-stage machine learning architecture, a set of facial features and a set of hand features from the image, generating, using an aggregation model of the multi-stage machine learning architecture, a text prediction corresponding to the image based on the set of facial features, the set of hand features, and a set of defined terms associated with the multi-stage machine learning architecture, and initiating a prediction-based action based on the text prediction.
The present disclosure generally relates to generating a summary for an encounter between an individual and a provider of medical services. More specifically, the disclosure relates to systems and methods for generating a concise and dynamic summary related to a reason for the encounter by accurately and efficiently curating and analyzing data from a variety of sources. In one aspect, the techniques are directed to generating a summary prior to the encounter by curating data from a variety of sources and analyzing temporal data to determine temporal patterns and/or other factors within the data that are relevant to at least one symptom that was a reason for the encounter. In another aspect, the techniques are directed to obtaining an audio including a conversation during the encounter and updating the summary (e.g., in real time) based on analyzing the audio and, in some examples, obtaining additional data based on the analysis.
G16H 10/60 - ICT specially adapted for the handling or processing of patient-related medical or healthcare data for patient-specific data, e.g. for electronic patient records
39.
Systems and Methods for Analyzing and Condensing Audio Information Relating to an Encounter
The present disclosure generally relates to generating a summary for an encounter between an individual and a provider of medical services. More specifically, the disclosure relates to systems and methods for generating a concise and dynamic summary related to a reason for the encounter by accurately and efficiently curating and analyzing data from a variety of sources. In one aspect, the techniques are directed to generating a summary prior to the encounter by curating data from a variety of sources and analyzing temporal data to determine temporal patterns and/or other factors within the data that are relevant to at least one symptom that was a reason for the encounter. In another aspect, the techniques are directed to obtaining an audio including a conversation during the encounter and updating the summary (e.g., in real time) based on analyzing the audio and, in some examples, obtaining additional data based on the analysis.
G16H 50/70 - ICT specially adapted for medical diagnosis, medical simulation or medical data miningICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
G06F 40/289 - Phrasal analysis, e.g. finite state techniques or chunking
G10L 15/06 - Creation of reference templatesTraining of speech recognition systems, e.g. adaptation to the characteristics of the speaker's voice
G10L 15/183 - Speech classification or search using natural language modelling using context dependencies, e.g. language models
G10L 25/66 - Speech or voice analysis techniques not restricted to a single one of groups specially adapted for particular use for comparison or discrimination for extracting parameters related to health condition
40.
ADVERSARIAL TRAINING OF CLASSIFIERS TO LEARN EXPLAINABLE FEATURES
Various embodiments of the present disclosure provide an improved adversarial training technique that improves the functionality of a computer in various aspects by to removing spurious correlations within machine learning models. The techniques comprise receiving, from an embedding layer of a machine learning encoder, a set of token embeddings associated with a labeled data object. The techniques comprise generating a set of perturbed token embeddings by applying a noise hyperparameter to a portion of the set of token embeddings, providing, to an encoding layer of the machine learning encoder, the set of perturbed token embeddings to generate a perturbed encoded representation of the labeled data object, and providing the perturbed encoded representation for training a classifier model based on the perturbed encoded representation and a label for the labeled data object.
Various embodiments of the present disclosure provide a gesture translation pipeline that improves the functionality of a computer in various aspects. The techniques comprise receiving an image that depicts a facial expression and a hand position of a user, generating, using a parallel feature extraction model of a multi-stage machine learning architecture, a set of facial features and a set of hand features from the image, generating, using an aggregation model of the multi-stage machine learning architecture, a text prediction corresponding to the image based on the set of facial features, the set of hand features, and a set of defined terms associated with the multi-stage machine learning architecture, and initiating a prediction-based action based on the text prediction.
G10L 13/08 - Text analysis or generation of parameters for speech synthesis out of text, e.g. grapheme to phoneme translation, prosody generation or stress or intonation determination
G06F 3/01 - Input arrangements or combined input and output arrangements for interaction between user and computer
G06V 10/40 - Extraction of image or video features
G06V 40/10 - Human or animal bodies, e.g. vehicle occupants or pedestriansBody parts, e.g. hands
G06V 40/16 - Human faces, e.g. facial parts, sketches or expressions
G06V 40/18 - Eye characteristics, e.g. of the iris
42.
GENETIC ALGORITHM-BASED GENERATIVE LEARNING SYSTEM FOR SYNTHETIC TEXT GENERATION
Various embodiments of the present disclosure provide a genetic algorithm-based generative learning system for synthetic text generation that comprises generating using an encoder of a generative machine learning model, a sample text embedding of a corpus sample; generating using a decoder of the generative machine learning model, a synthetic sample based on the sample text embedding of the corpus sample; generating using the encoder, a synthetic text embedding of the synthetic sample; generating using a cost function, a similarity measure for the synthetic sample based on a first comparison between the synthetic text embedding and the sample text embedding; generating using the cost function, a variation measure for the synthetic sample based on a second comparison between the synthetic text embedding and the sample text embedding; and providing a model performance score for the generative machine learning model based on a comparison between the similarity measure and the variation measure.
Various embodiments of the present disclosure provide hallucination mitigation techniques for text-to-code conversions that improves the functionality of a computer in various aspects. The techniques comprise receiving a text-based file that defines a set of standards for a prediction domain; generating, using a machine learning model, a decision tree based on (i) the text-based file and (ii) a decisioning prompt for the text-based file; generating, using the machine learning model, computer programmable code for the set of standards based on the decision tree and a code conversion prompt for the decision tree; and providing the computer programmable code to implement an automated task for the prediction domain.
Techniques for automated query response determination using a hybrid AI are disclosed herein. An example computer-implemented method includes receiving a data file and a request including at least one query associated with the data file and applying a hybrid model to the data file. Applying the hybrid model includes segmenting the data file into one or more portions, embedding the one or more portions into a vector space, extracting, from the data file, data associated with one or more classifications, storing (i) the embedded portions in a first database and (ii) the extracted data in a second database, and determining a response to request queries based on the embedded portions and the extracted data, wherein the hybrid model constrains each response based on a parametric input prompt associated with the extracted data. The example computer-implemented method further includes storing one or more data objects indicating each response.
Various embodiments of the present invention address technical challenges associated with performing machine learning operations on timeseries/periodic data by introducing a machine learning framework that has a first periodic tier for determining predicted evaluation scores for those predictive entities that are associated with a single evaluation period (e.g., a single year of data) and a second periodic tier for determining predicted evaluation scores for those predictive entities that are associated with multiple evaluation periods. The noted framework addresses the existing shortcomings of machine learning frameworks that operate on timeseries/periodic data with respect to inadequacy of data associated with shorter periods to determine parameters needed to perform comprehensive predictive data analysis with respect to longer periods.
Systems and methods for field-level encryption using multiple groups of data encryption keys are provided. Multi-device keys for encrypting a message may be received. The multi-device keys may include (1) a first data encryption key (DEK) from among a first group of DEKs that permits a first consuming device to access a first field of the message and (2) a second DEK from among a second group of DEKs that permits a second consuming device to access a second field of the message. The message may be encrypted by encrypting (1) the first field using the first DEK and (2) the second field using the second DEK. The encrypted message may be transmitted to a stream processing platform to permit (1) the first consuming device to decrypt the first field and (2) the second consuming device to decrypt the second field.
Systems and methods are disclosed for processing multidimensional data using machine-learning models to classify an entity, predict metrics, and/or generate transcripts. The method includes receiving multi-dimensional data that include a first value of a first dimension indicating a comparison of an entity with a group of entities, and a second value of a second dimension indicating an attribute of the entity irrespective of the group of entities; inputting the multi-dimensional data to a first machine-learning model to output a prediction value determined based on applying first and second weights to the first and second values, respectively; and upon determining the prediction value satisfies first threshold associated with an adverse event: filtering historical text data associated with the entity to exclude data that satisfies second threshold associated with acceptable operations; and generating, by inputting the filtered historical text data into a second machine-learning model, a transcript of recommended actions.
Various embodiments of the present disclosure provide security vulnerability detection and remediation infrastructure for a computing ecosystem that improves the functionality of a computing ecosystem in various aspects. The techniques comprise receiving a security vulnerability detection for a computing ecosystem, determining a vulnerability graph for the computing ecosystem that defines a set of component nodes, a set of vulnerability nodes, and a set of graph edges, determining a degree measure and a betweenness measure for a vulnerability node of the plurality of vulnerability nodes within the vulnerability graph, determining a set of prioritized vulnerability nodes from the vulnerability graph based on the degree measure and the betweenness measure, comparing the results derived from using different methods, and providing a prioritized list of security vulnerabilities for the computing ecosystem in response to the security vulnerability detection.
G06F 21/57 - Certifying or maintaining trusted computer platforms, e.g. secure boots or power-downs, version controls, system software checks, secure updates or assessing vulnerabilities
49.
SYSTEM AND METHOD FOR FIELD-LEVEL ENCRYPTION USING MULTIPLE GROUPS OF DATA ENCRYPTION KEYS
Systems and methods for field-level encryption using multiple groups of data encryption keys are provided. Multi-device keys for encrypting a message may be received. The multi-device keys may include (1) a first data encryption key (DEK) from among a first group of DEKs that permits a first consuming device to access a first field of the message and (2) a second DEK from among a second group of DEKs that permits a second consuming device to access a second field of the message. The message may be encrypted by encrypting (1) the first field using the first DEK and (2) the second field using the second DEK. The encrypted message may be transmitted to a stream processing platform to permit (1) the first consuming device to decrypt the first field and (2) the second consuming device to decrypt the second field.
Embodiments of the present disclosure relate to a chute cover mechanism for a dispenser. An example chute cover mechanism comprises a slide cover and a chute cover. The chute cover comprises a bias mechanism and a channel and is attached to the dispenser to position the chute cover over an entry void of a dispensing chute. The slide cover is positioned within the channel and includes a protruding member positioned to receive a force from a dispensing reservoir to transition the chute cover mechanism from an engaged state to a disengaged state as the dispensing reservoir is inserted into the dispenser. In the engaged state, the slide cover is positioned to at least partially cover the entry void of the dispensing chute. In the disengaged state, the slide cover is positioned to expose the entry void of the dispensing chute.
Techniques for accurately assessing the vulnerability status of a collection of software applications are disclosed herein. An example computer-implemented method includes computing a metric indicative of time-to-vulnerability-remediation for each software application in the collection of software applications. The method further includes classifying each software application as one of a predefined set of classifications using at least the computed metrics indicative of time-to-vulnerability-remediation. The method also predicts at least one future classification for each software application in the collection of software applications. The method also outputs at least one data object indicative of, for each software application in the collection of software applications, the software application, the classification of the software application, and the predicted classification(s) of the software application.
G06F 21/57 - Certifying or maintaining trusted computer platforms, e.g. secure boots or power-downs, version controls, system software checks, secure updates or assessing vulnerabilities
G06N 7/01 - Probabilistic graphical models, e.g. probabilistic networks
52.
DECISION SUPPORT SYSTEM INCLUDING SPARSIFIED MACHINE-LEARNED MODEL FOR AUTOMATIC GENERATION OF APPEALS
A computer-implemented method includes receiving, by one or more processors, a denial notification for a health care claim associated with a patient; generating, by the one or more processors, an appeal support data set, the appeal support data set comprising clinical data associated with the patient and administrative data associated with the patient, the appeal support data set being a sparsified subset of a larger appeal support data set and having a reduced dimensionality relative to the larger appeal support data set; applying, by the one or more processors and to the appeal support data set and the health care claim, a machine-learned prediction model that is trained to generate an appeal success prediction score; generating, by the one or more processors, an appeal of the denial notification in a format compatible with a standard defined by a payor that issued the denial notification when the appeal success prediction score satisfies an appeal success threshold; and transmitting, by the one or more processors, the appeal to the payor that issued the denial notification using a communication protocol compatible with a system used by the payor in processing the appeal.
Techniques for data clustering and outcome generation may comprise determining a state sequence associated with a sample of one or more samples that satisfies an occurrence threshold and generating one or more timing features for the state sequence. The techniques may further comprise clustering, by executing a machine-learned model, the sample corresponding to at least the state sequence into a cluster of a set of clusters based on the state sequence and the one or more timing features. The techniques may further comprise generating a data object indicating one or more outcomes associated with the cluster that includes the sample. These data objects indicate outcomes that are specific enough to provide meaningful insights contained in associations between the input data and the associated clusters and eliminate/reduce the misleading information commonly output by typical techniques.
The disclosed techniques can avoid or otherwise mitigate/reduce errors or other deficiencies in automatically generated text using a multi-language model (multi-LM) architecture. The architecture includes one or more text generation LMs that generate candidate text of a desired type, and a set of validation LMs that analyze the candidate text. The disclosed techniques prompt the validation LMs to generate respective metrics indicating quality of the candidate text according to an evaluation instrument. The disclosed techniques can then determine whether to validate the candidate text based at least in part on those metrics, and either release (e.g., approve, transmit, etc.) the candidate text or refrain from releasing the candidate text accordingly. Also disclosed is an expanded multi-LM architecture that implements feedback to improve the quality of text when candidate text cannot be validated.
Techniques for accurately assessing the vulnerability status of a collection of software applications are disclosed herein. An example computer-implemented method includes computing a metric indicative of time-to-vulnerability-remediation for each software application in the collection of software applications. The method further includes classifying each software application as one of a predefined set of classifications using at least the computed metrics indicative of time-to-vulnerability-remediation. The method also predicts at least one future classification for each software application in the collection of software applications. The method also outputs at least one data object indicative of, for each software application in the collection of software applications, the software application, the classification of the software application, and the predicted classification(s) of the software application.
G06F 21/57 - Certifying or maintaining trusted computer platforms, e.g. secure boots or power-downs, version controls, system software checks, secure updates or assessing vulnerabilities
G06F 18/2415 - Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
56.
MULTI-CHANNEL SEARCH AND AGGREGATED SCORING TECHNIQUES FOR COMPLEX SEARCH DOMAINS
Various embodiments of the present disclosure provide query processing techniques for resolving queries in a complex search domain to improve upon traditional search resolutions within such domains. The techniques may include generating a keyword and an embedding representation for an agnostic search query. The keyword representation may be compared against source text attributes within one or more domain channels to generate a plurality of keyword similarity scores between the search query and features within a search domain. The embedding representation may be compared against source embedding attributes within the one or more domain channels to generate a plurality of embedding similarity scores between the search query and the features within the search domain. The keyword and embedding similarity scores may be aggregated to generate aggregated similarity scores for identifying an intermediate query resolution for the search query. The intermediate query resolution may be leveraged to resolve the query.
Various embodiments of the present disclosure provide machine learning architectures for improving predictive functionality of a computer. The techniques apply a multi-stage machine learning automated coding pipeline to a coding domain to generate a code prediction for a text segment. During a first stage, the techniques may include inputting a text segment from a file to a machine learning encoder to generate a text segment vector and extracting a subset of searching codes from a vector data store based on a comparison between the text segment vector and a plurality of code vectors within the vector data store. During a second stage, the techniques may include generating a generative model prompt based on the subset of searching codes and inputting the generative model prompt to a generative model to generate a code prediction for the text segment.
Various embodiments of the present disclosure provide automated data storage and code-based retrieval techniques for improving search engine performance. The techniques apply a multi-stage machine learned autonomous coding pipeline to generate a search template for an input document by extracting a text segment from the input document, executing a coding query to receive a query response, determining that the query response is a null query response, and responsive to the null query response, generating a segment embedding based on the text segment, generating a text-code pair for the text segment based on an embedding similarity score between the segment embedding and a code embedding, storing the text-code pair within the text-code datastore, and modifying the search template by storing a code of the text-code pair in association with the text segment.
are disclosed. A pill identification request, including one or more images of a pill and a user identifier of a user associated with the pill, is received. A first machine learning system is used to generate one or more image embeddings based on the one or more images. The user identifier is used to retrieve claims data of the user, and the claims data are encoded to generate a claims embedding. A second machine learning system is used to identify the pill based on the one or more image embeddings and the claims embedding. A response to the pill identification request is generated based on the identifying.
G06V 10/764 - Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
G06V 10/774 - Generating sets of training patternsBootstrap methods, e.g. bagging or boosting
G16H 10/60 - ICT specially adapted for the handling or processing of patient-related medical or healthcare data for patient-specific data, e.g. for electronic patient records
G16H 70/40 - ICT specially adapted for the handling or processing of medical references relating to drugs, e.g. their side effects or intended usage
60.
SYSTEMS AND METHODS FOR EXTRACTING KEY PERFORMANCE INDICATORS FROM TEXTUAL DATA
A method includes: determining a first bounding box in textual data; categorizing the first bounding box into a paragraph category among a list of categories including a header category, a section header category, the paragraph category, and a noise category; extracting a candidate noun from the text in the categorized first bounding box, as a candidate paragraph noun; extracting a candidate value from the text in the categorized first bounding box; generating a relationship between the candidate paragraph noun and the extracted candidate value; associating the candidate paragraph noun with a candidate header noun; and generating a key performance indicator using the candidate header noun, the candidate paragraph noun, the candidate value, and the generated relationship.
Systems and methods for using generative language models to generate individual-specific instructions are disclosed herein. When receiving a request for instructions for a condition, the disclosed techniques map the condition to a condition concept of an ontological representation, map individual-specific information to an individual-specific concept of the ontological representation, determine from the ontological representation whether the individual-specific concept is a comorbidity concept with respect to the condition concept, and generate a prompt based on the request for instructions and on property data associated with the condition concept and the comorbidity concept. The disclosed techniques generate the requested instructions by applying the prompt to a generative language model.
G16H 50/70 - ICT specially adapted for medical diagnosis, medical simulation or medical data miningICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
G16H 70/20 - ICT specially adapted for the handling or processing of medical references relating to practices or guidelines
62.
DATA COMPRESSION AND MATCHING TECHNIQUES FOR HIGH-DIMENSIONAL DATA PROCESSING
Various embodiments of the present disclosure provide data compression, retrieval, and matching techniques that leverage latent representations to improve the functionality of a computer in various aspects. The techniques apply a multi-stage data compression technique to transform input data into binarized feature vector and latent representation pairs. These reference entries may be stored within a reference dataset and accessed to process data matching requests at improved processing speeds. To do so, the data matching techniques comprise receiving a data matching request that identifies a first reference entry from the reference dataset, determining a matching score for a second reference entry from the reference dataset based on the latent representation, and outputting, based on the matching score, the second reference entry in response to the data matching request.
Various embodiments of the present disclosure provide object identification, tracking, and counting techniques for high-speed environments. The techniques include generating denoised image frame based on a contrast threshold corresponding to a shared object attribute for a tracked target object. The techniques include generating, using an object detection model, an object matrix indicative of target object candidates based on the denoised image frame. The techniques include generating object-specific attributes for the target object candidates based on the object matrix. The techniques include identifying the tracked target object from the target object candidates based on the object-specific attributes and, in response to identifying the tracked target object, tracking and recording a tracked target object corresponding to the target object based on the object attributes recorded previously and, if necessary, modifying an object-specific count for the recorded target object.
Techniques for autonomously validating cloud-based policies can obtain information about a policy deployed in a cloud computing environment, automatically determine which scenario(s)/resource configuration(s) to test, and cause the cloud computing environment to automatically instantiate, modify, or disable one or more cloud resources according to the scenario(s)/resource configuration(s). After the cloud computing environment applies the policy to the new, modified, and/or disabled resource(s), the techniques can generate/store data indicating the compliance status of the resource(s) according to the policy. The techniques can improve the functioning of the cloud computing environment and/or related frontend systems, and provide cloud policy validation in an efficient, accurate, and scalable manner.
A method includes receiving, a record containing clinical information associated with a patient; applying the record a set of machine-learned models including: a medical entity extraction model that is configured to extract medical entities from the clinical information; a medical ontology mapping model that is configured to associate one or more candidate medical codes with each of the medical entities based on vector embedding similarities and to rank each of the one or more candidate medical codes based on their similarities, respectively, with the associated medical entity; and a validation model that is configured to categorize an association between one or more pairs of the one or more candidate medical codes into one or more confidence ratings, respectively; generating a suggested medical code for each of the medical entities based on the rank of the one or more candidate medical codes associated therewith and the one or more confidence ratings of the one or more candidate medical codes, respectively; and causing, via a graphical user interface (GUI), display of the suggested medical code for each of the medical entities and, for each of the suggested medical codes, a corresponding visual indicator that is representative of the confidence rating that is associated with the respective suggested medical code.
G16H 10/60 - ICT specially adapted for the handling or processing of patient-related medical or healthcare data for patient-specific data, e.g. for electronic patient records
G16H 15/00 - ICT specially adapted for medical reports, e.g. generation or transmission thereof
G16H 50/20 - ICT specially adapted for medical diagnosis, medical simulation or medical data miningICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
66.
TECHNIQUES FOR IMPROVED USER EXPERIENCE PREDICTION
Techniques for improved user experience prediction are disclosed herein. An example computer-implemented method includes receiving a sequence of web pages visited by a user and applying a machine learning model to (i) the sequence of web pages and (ii) a set of metrics data corresponding to the sequence of web pages. Applying the machine learning model includes generating embeddings of web page identifiers associated with the sequence of web pages, determining, by a first hidden layer, a first modified embedding based on respective cross-effects associated with one or more other embeddings, determining, by a second hidden layer, a second modified embedding based on the set of metrics data associated with a respective first modified embedding, and outputting a user experience value for each second modified embedding. The example computer-implemented method further includes generating one or more data objects indicating one or more of the user experience values.
G06N 3/0442 - Recurrent networks, e.g. Hopfield networks characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
G06N 20/10 - Machine learning using kernel methods, e.g. support vector machines [SVM]
67.
AUTOMATED ROBOTIC OBJECT DISPENSING AND TRANSFERRING SYSTEMS AND PROCESSES
Various embodiments of the present disclosure provide improved robotic systems and system configurations for various use cases. The system of the present disclosure may comprise a dispensing station comprising a dispenser mechanism, a robotic picking device, a labeling mechanism, and a first scanning device and a second scanning device positioned adjacent to the dispenser mechanism and the labeling mechanism, respectively; and a conveyance assembly positioned within a threshold distance to the dispensing station, wherein the dispenser mechanism of the dispensing station is physically separated from the conveyance assembly by the robotic picking device and the labeling mechanism.
G07F 11/32 - Coin-freed apparatus for dispensing, or the like, discrete articles from non-movable magazines in which the magazines are inclined two or more magazines having a common delivery chute
G07F 11/52 - Coin-freed apparatus for dispensing, or the like, discrete articles from movable storage containers or supports the storage containers or supports being rotatably mounted about horizontal axes
G07F 11/54 - Coin-freed apparatus for dispensing, or the like, discrete articles from movable storage containers or supports the storage containers or supports being rotatably mounted about vertical axes
G07F 17/00 - Coin-freed apparatus for hiring articlesCoin-freed facilities or services
Various embodiments of the present disclosure provide a rotary dispenser mechanism. The rotary dispenser mechanism comprises a rotating drum attached to a rotary table and comprising a set of vertical channels arranged in a circular array around an outer circumference of the rotary table. The rotary dispenser mechanism comprises a motor positioned within the outer circumference of the rotary table and configured to rotate the rotating drum about a fixed center axis of the rotary table. The rotary dispenser mechanism comprises a nested dispensing location positioned at least partially outside of the outer circumference of the rotary table and at least one dispensing actuator configured to exert a force on a physical object to push the physical object to the nested dispensing location and from a vertical channel of the set of vertical channels that is aligned with the nested dispensing location.
G07F 11/32 - Coin-freed apparatus for dispensing, or the like, discrete articles from non-movable magazines in which the magazines are inclined two or more magazines having a common delivery chute
G07F 11/52 - Coin-freed apparatus for dispensing, or the like, discrete articles from movable storage containers or supports the storage containers or supports being rotatably mounted about horizontal axes
G07F 11/54 - Coin-freed apparatus for dispensing, or the like, discrete articles from movable storage containers or supports the storage containers or supports being rotatably mounted about vertical axes
G07F 17/00 - Coin-freed apparatus for hiring articlesCoin-freed facilities or services
69.
AUTOMATED ROBOTIC OBJECT DISPENSING AND TRANSFERRING SYSTEMS AND PROCESSES
Various embodiments of the present disclosure provide improved robotic systems and system configurations for various use cases. The system of the present disclosure may receive a request that identifies a requested object type associated with a dispenser mechanism, determine a dispensing channel from a set of dispensing channels of the dispenser mechanism and that corresponds to the requested object type, provide a first control instruction to position the dispenser mechanism in a dispensing orientation that aligns the dispensing channel over a nested dispensing location, and provide a second control instruction to dispense a physical object from an object canister within the dispensing channel.
G07F 11/32 - Coin-freed apparatus for dispensing, or the like, discrete articles from non-movable magazines in which the magazines are inclined two or more magazines having a common delivery chute
G07F 11/52 - Coin-freed apparatus for dispensing, or the like, discrete articles from movable storage containers or supports the storage containers or supports being rotatably mounted about horizontal axes
G07F 11/54 - Coin-freed apparatus for dispensing, or the like, discrete articles from movable storage containers or supports the storage containers or supports being rotatably mounted about vertical axes
G07F 17/00 - Coin-freed apparatus for hiring articlesCoin-freed facilities or services
Various embodiments of the present disclosure provide network interfaces and messaging schemes for enabling cross-entity collaboration through a sequential, multi-party authorization process. The multi-party authorization process may include receiving a request with an automation indicator and, in response to the automation indicator, identifying an automated decision tree for an automated query message request. The automated query message request may be provided to a querying entity that may execute the automated decision tree and respond with an automated query message response with a sequence of query responses. The multi-party authorization process may include determining a query completion status of the automated query message response based on the sequence of query responses and, in response to the query completion status identifying a complete query response, providing an authorization message response with a predictive response derived from the sequence of query responses.
An example device is configured to encode first sensed data using a first encoder and to predict a first behavior based on the encoded first sensed data to create a first prediction using a first prediction model. The example device is configured to store the encoded first sensed data in the one or more memory units. The example device is configured to control the communication unit to transmit the encoded first sensed data in a first batch to a computing system. The example device is configured to receive, from the computing system via the communication unit, a second encoder, the second encoder being based at least in part on the encoded first sensed data. The example device is also configured to receive, from the computing system via the communication unit, a second prediction model, the second prediction model being based at least in part on the encoded first sensed data.
Techniques for enhancing language model capabilities are disclosed herein. An example computer-implemented method comprises receiving an input prompt comprising textual data and generating output data by a large language model (LLM) based at least in part on the input prompt. The output data includes a file identifier associated with a file stored in a storage location. The example computer-implemented method further comprises retrieving, based on the file identifier, a file resource identifier that indicates the storage location and replacing the file identifier within the output data into the file resource identifier. The example computer-implemented method further comprises causing the output data to be displayed to a user, which includes causing an image associated with the file resource identifier to be displayed.
Various embodiments of the present disclosure provide methods, apparatus, systems, computing devices, computing entities, and/or the like for receiving pre-imaging data for a plurality of pre-imaged computing devices; generating, using the pre-imaging data, a plurality of data objects that respectively correspond to the plurality of pre-imaged computing devices, wherein a first data object of the plurality of data objects comprises a data construct that describes a first computing device of the plurality of pre-imaged computing devices; receiving a computing device provisioning request comprising one or more hardware specifications and application criteria; determining a computing device from the plurality of pre-imaged computing devices based at least in part on the one or more hardware specifications and the plurality of data objects; generating a custom build instruction identifying the application criteria; and transmitting the custom build instruction to the computing device.
H04L 41/5054 - Automatic deployment of services triggered by the service manager, e.g. service implementation by automatic configuration of network components
75.
SYSTEM AND METHOD FOR PREDICTION-BASED IMAGING OF COMPUTING DEVICES
Various embodiments of the present disclosure provide methods, apparatus, systems, computing devices, computing entities, and/or the like for receiving pre-imaging data for a plurality of pre-imaged computing devices; generating, using the pre-imaging data, a plurality of data objects that respectively correspond to the plurality of pre-imaged computing devices, wherein a first data object of the plurality of data objects comprises a data construct that describes a first computing device of the plurality of pre-imaged computing devices; receiving a computing device provisioning request comprising one or more hardware specifications and application criteria; determining a computing device from the plurality of pre-imaged computing devices based at least in part on the one or more hardware specifications and the plurality of data objects; generating a custom build instruction identifying the application criteria; and transmitting the custom build instruction to the computing device.
Various embodiments of the present invention provide methods, apparatuses, systems, computing devices, computing entities, and/or the like for facilitating efficient and effective execution of database management operations. For example, various embodiments describe generating data associated with a database association management platform that enables an end user to generate/maintain database association metadata for a database using a sequence of record relationship instructions, such as a sequence comprising at least one of record-structure inclusion (RSI) instructions, record-structure exclusion (RSE) instructions, record-structure non-inclusion (RSNI) instructions, record-structure non-exclusion (RSEI) instructions, and new structure creation (NSC) instructions. As another example, various embodiments describe performing hierarchical database record aggregation/matching by defining hierarchically-differentiated tiers of a cross-record matching logic, for example by defining a superseding/referential hierarchical matching logic that may be generated based at least in part on manually-entered record relationship instructions as reflected in the database association metadata
Techniques for generating graphical user interface (GUI) code based on images of GUI components include obtaining an image depicting a GUI component and determining whether the component can be implemented by any existing GUI components stored in an asset database. When determining that the graphical user interface component can be implemented by at least one existing graphical user interface component, the techniques include retrieving from the asset database auxiliary data associated with the at least one existing graphical user interface component. When determining that the GUI component cannot be implemented by any existing GUI component, the techniques include (i) generating a new GUI component by generating an image associated with the GUI and auxiliary data, and (ii) storing the new GUI component in the asset database. The method further includes generating an abstract syntax tree on auxiliary data associated with the new graphical user interface components.
Various embodiments of the present disclosure provide an automated asynchronous decisioning process that improves the functionality of a computer in various aspects. The process may comprise receiving, an input data object that comprising a set of unstructured data elements and converting the input data object to a structured data object by (i) extracting, using an optical character recognition model, a set of input features from the input data object, (ii) generating, using a structuring ruleset, a structured data element based on the set of input features, and (iii) storing the structured data element within a polling queue and in association with the request identifier. The process may comprise receiving, from a polling component, a polling request and responsive to receiving the polling request, providing, to the polling component, at least one of the request identifier, the structured data element, or a conversion status for the structured data object.
Various embodiments of the present disclosure provide a machine learning framework integrated within a dynamic querying process that improves the functionality of a computer in various aspects. The techniques comprise receiving a model input comprising a set of entity attributes and a set of initial query responses. The techniques comprise generating, using a machine learned model, a model prediction based on the model input and determining, based on the model prediction, an influential parameter from the first subset of independent parameters for the model prediction. The techniques comprise providing a set of subsequent queries based on the influential parameter to receive a set of subsequent query responses that correspond to a second subset of independent parameters and generating, using the machine learned model, an updated model prediction based on the model input and the set of subsequent query responses.
Systems and methods for routing data using an artificial intelligence (AI) model are disclosed. The method includes receiving a data request associated with one or more data gaps, determining, by an AI model, a plurality of ranking values for a plurality of candidate data sources respectively based on one or more attributes, each of the plurality of ranking values indicative of a likelihood of filling the one or more data gaps associated with the data request; and routing, over a network, the data request to a first candidate data source of the plurality of candidate data sources based on a first ranking value of the plurality of ranking values; and blocking routing of the data request over the network to a second candidate data source of the plurality of candidate data sources based on a second ranking value of the plurality of ranking values.
Systems and computer-implemented methods are disclosed for detecting a system anomaly. A computer-implemented method comprises: receiving, by a data storage module, time-series data from a plurality of sensors of an information technology infrastructure, each sensor corresponding to a respective metric; detecting a plurality of anomalies in the time-series data stored in the data storage module; generating a knowledge graph by: determining connections between the plurality of metrics based on the time-series data; and for each connection, determining a respective weight based on an impact score for metrics joined by the connection; and configuring a root cause determination engine to output one or more metrics as root cause candidates, the one or more metrics based on the knowledge graph, in response to input of a query associated with at least one metric.
Techniques for automatically detecting inactive addresses of providers using unsupervised learning approaches are provided. The techniques include determining an activity trend of an address. Responsive to determining that the address is associated with increasing activity, determining an active metric of the address, which indicates a likelihood of the address being active. Responsive to determining that the address is associated with decreasing activity, determining an inactive metric of the address, which indicates a likelihood of the address being inactive. The techniques further include determining whether the address is active or inactive based on the active metric and/or inactive metric. In some embodiments, the active metric or inactive metric is a weighted sum of z scores determined based on Gaussian distributions generated with respect to various benchmarks or provider features. In some embodiments, the weights used to determine the active metric or inactive metric are determined using RLHF techniques.
Various embodiments of the present disclosure provide image and prediction processing techniques for providing improved image-based predictions. The techniques may include generating a plurality of derivative images from a production line image by cutting the production line image into a plurality of portions. The techniques include generating a plurality of comparable derivative images by rotating each of the plurality of derivative images to a particular orientation relative to a production line item reflected by the production line image. The techniques include generating, using a machine learning model, an anomaly prediction for the production line image based on an image comparison between the plurality of comparable derivative images. The techniques include initiating the performance of the prediction-based action based on the anomaly prediction.
Various embodiments of the present disclosure provide production line conformance measurement techniques using intelligent optimization of model input data for a machine learning detection model. The techniques may include generating a cropped image from a production line image based on an outer circumference associated with a production line item, generating a derivative cropped image from the cropped image based on an interior circumference associated with the production line item, generating a transformed input image from the derivative cropped image based on one or more model parameters of a machine learning detection model, and generating, using the machine learning detection model, a prediction output based on the transformed input image.
G06V 10/26 - Segmentation of patterns in the image fieldCutting or merging of image elements to establish the pattern region, e.g. clustering-based techniquesDetection of occlusion
G06T 7/62 - Analysis of geometric attributes of area, perimeter, diameter or volume
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
G06V 10/774 - Generating sets of training patternsBootstrap methods, e.g. bagging or boosting
85.
Database management systems using hierarchically-enforced database association metadata
Various embodiments of the present invention provide methods, apparatuses, systems, computing devices, computing entities, and/or the like for facilitating efficient and effective execution of database management operations. For example, various embodiments describe generating data associated with a database association management platform that enables an end user to generate/maintain database association metadata for a database using a sequence of record relationship instructions, such as a sequence comprising at least one of record-structure inclusion (RSI) instructions, record-structure exclusion (RSE) instructions, record-structure non-inclusion (RSNI) instructions, record-structure non-exclusion (RSEI) instructions, and new structure creation (NSC) instructions. As another example, various embodiments describe performing hierarchical database record aggregation/matching by defining hierarchically-differentiated tiers of a cross-record matching logic, for example by defining a superseding/referential hierarchical matching logic that may be generated based at least in part on manually-entered record relationship instructions as reflected in the database association metadata.
Various embodiments of the present disclosure provide model-based domain-aware autocomplete techniques for generating autocomplete suggestions in a complex search domain. Example embodiments are configured to generate, using a domain-aware autocomplete model, a label for an autocomplete suggestion based on a set of keywords within an autocomplete suggestion training dataset associated with a target domain source. Example embodiments are also configured to generate, using a weak-labeling model, an updated label for the autocomplete suggestion by decorrelating the set of keywords from the label. Example embodiments are also configured to generate, using a sentence classification model, a category for the autocomplete suggestion based on the updated label. Example embodiments are also configured to, using the domain-aware autocomplete model, generate a suggestion-category pair (SCP) based on the autocomplete suggestion and the category for the autocomplete suggestion. Example embodiments are also configured for initiating performance of a search query resolution based on the SCP.
Various embodiments of the present disclosure provide prompt engineering and text quality assessment techniques for improving generative text outputs. The techniques include identifying a training cluster for an input document, generating a candidate prompt for a generative machine learning model based on the training cluster and a prompt template, providing the candidate prompt to the generative machine learning model to receive at least a portion of a candidate document, generating a plurality of quality metrics for the candidate prompt based on the candidate document, and selecting the candidate prompt from a plurality of candidate prompts based on the plurality of quality metrics.
Various embodiments of the present disclosure provide machine learning architectures and data processing techniques for improving computer-based text comprehension. The techniques include generating, using a trained classifier model, target classification probabilities for labelled text-based objects from a testing portion of a labelled training dataset and identifying predictive text-based objects from the labelled text-based objects based on the target classification probabilities. The techniques include applying a staged prompting mechanism with a generative extraction model to identify a target set of explanatory text segments from the predictive text-based objects that may be clustered into semantic segment clusters. The techniques include generating explanatory summary segments respectively corresponding to the semantic segment clusters and generating a target classification signature based on a plurality of terms from the one or more explanatory summary segments.
G06F 18/2413 - Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on distances to training or reference patterns
Various embodiments of the present invention provide methods, apparatus, systems, computing devices, computing entities, and/or the like for performing personalized autocomplete predictions. Certain embodiments of the present invention utilize systems, methods, and computer program products that perform personalized autocomplete predictions using a general search corpus and/or individual curated search corpus.
Various embodiments of the present disclosure provide methods, apparatus, systems, computing devices, computing entities, and/or the like for identifying stale or vibrant open-source packages by training a predictive machine learning model with a labeled dataset, wherein the labeled dataset is created by generating package-basis features and version-basis features based on repository data, generating package-basis clusters based on the package-basis features, generating version-basis clusters based on the version-basis features, and generating labels for the labeled dataset based on the package-basis clusters and the version-basis clusters.
A computer-implemented method includes receiving first query data associated with a first query, identifying a system error that is associated with the first unique entity identifier based on an indication that the first query was improperly approved, extracting a cause of the system error from the first query data, determining a machine-readable invalidity code that corresponds to the cause of the system error, updating a system error database with the first unique entity identifier and the machine-readable invalidity code as a first pair, and outputting, the first pair including the first unique entity identifier and the machine-readable invalidity code from the system error database, the first pair being configured to be processed by a front-end system for identifying a potential system error associated with second query data for a second query.
Techniques for summarizing conversations in real-time are disclosed. The techniques include generating a transcript of the communication session and, during the communication session, obtaining a user-selected intent from a user. Based on the user-selected intent and at least a portion of the transcript, a prompt for a large language model (LLM) is generated. The prompt is then inputted into an LLM to provide a summary of the communication session that aligns with the selected intent. The summary can then be displayed to the user, e.g., for review and/or editing. The process may repeat for multiple user-selected intents, for example. These techniques can enhance the accuracy and/or efficiency of communication session summarization, including summarization of complex, multi-intent conversations.
Techniques for summarizing conversations in real-time are disclosed. The techniques receive streaming data indicating a set of digital interactions between a first user and a second user. The techniques predict a span of time over which a portion of the set of digital interactions are associated with a first intent. The techniques classify a first intent classification associated with the portion of the set of digital interactions. The techniques then generate a first prompt based at least in part on the first intent classification and the portion of the set of digital interactions. The techniques generate a first summary of the set of digital interactions. The summary can then be displayed to a user, e.g., for review and/or editing. The process may repeat within any given digital interaction(s) for multiple intents. These techniques can enhance the accuracy and efficiency of interaction summarization, including summarization of complex, multi-intent interactions.
Various embodiments of the present disclosure provide predictive mapped formatting for data. The techniques may include receiving an input structured data object, identifying a format inconsistency error for the input structured data object, generating a predictive mapped format data object for an input data format of the input structured data object by using a predictive machine learning model, initiating a presentation of a validation user interface that reflects the predictive mapped format data object, and storing the predictive mapped format data object in response to a confirmation input to the validation user interface.
Various embodiments of the present disclosure provide a text interpretation technique. The text interpretation technique includes generating a plurality of text segment embeddings from a plurality of input text documents and identifying prompt embeddings associated with a predictive task. The technique includes generating task-specific similarity scores for the plurality of text segments based on a comparison between the plurality of text segment embeddings and the prompt embeddings, The technique includes identifying a set of task-specific text segments from the plurality of text segments based on the plurality of task-specific similarity scores and training a target machine learning model based on the set of task-specific text segments.
Various embodiments of the present disclosure provide a language model training technique. The language model training technique may include a data blending preprocessing step to improve the performance of the language model at an enterprise level. The data blending technique includes receiving an enterprise data partition from a plurality of enterprise data partitions associated with an enterprise data source, receiving a domain-specific data partition from a plurality of domain-specific data partitions associated with one or more domain data sources that are different than the enterprise data source, storing the enterprise data partition as an initial training partition of a plurality of balanced training partitions within a balanced training dataset, and generating a balanced training partition by appending a portion of the domain-specific data partition to the initial training partition. A domain-specific language model may then be trained based on the balanced training dataset.
Techniques for improving the reliability of digitized text may comprise receiving data corresponding to a data extraction program. The techniques may further comprise executing a confidence algorithm to generate a dictionary of words from fields in a file, determine, based at least in part on a confidence score from the dictionary of words, a content confidence score corresponding to a first field of the file, and determine, based on the content confidence score and a position confidence score, a certainty score for the first field. The techniques may further comprise determining, based at least in part on the certainty score, a certainty quotient for the file indicating a reliability of the data corresponding to the data extraction program, and generating a data object that indicates the certainty quotient. These techniques generate reliable indications of the accuracy of digitized text extracted from a file and substantially reduce false positives/negatives.
Various embodiments of the present invention provide methods, apparatus, systems, computing devices, computing entities, and/or the like for performing intervention recommendation operations. Certain embodiments of the present invention utilize systems, methods, and computer program products that perform intervention recommendations by using at least one of reinforcement learning machine learning models and event scoring machine learning models.
Various embodiments of the present disclosure provide methods, apparatus, systems, computing devices, computing entities, and/or the like for integrating traditionally disparate machine learning models by determining a plurality of changes to a first variable based on a plurality of changes to one or more second variables, determining estimated effects in a first variable model based on an optimization of the one or more second variables, generating a plurality of first prediction outputs based on the estimated effects, and generating a set of combined prediction outputs by combining the plurality of first prediction outputs with a plurality of second prediction outputs that is associated with estimated effects in the one or more second variables.
