A method includes receiving an untransformed transaction including unstructured data. An embedding model generates a vector from the unstructured data. A cluster model matches the vector to a vector cluster. A cluster ID is assigned to the vector. The unstructured data in the untransformed transaction is replaced with the cluster ID to obtain a transformed transaction. A query including the cluster ID and based on the transformed transaction is generated. The query is processed to generate a query result from features of prior transformed transactions. A fraud determination model processes the query result to generate a fraud score for the transformed transaction. The fraud score is presented to a user of a software application. The cluster model is updated to add or delete or modify vector clusters to generate cluster IDs, whereby generating the set of cluster IDs does not affect an input or output of the fraud determination model.
G06Q 20/40 - Autorisation, p. ex. identification du payeur ou du bénéficiaire, vérification des références du client ou du magasinExamen et approbation des payeurs, p. ex. contrôle des lignes de crédit ou des listes négatives
A method implements brand engine for extracting and presenting brand data with user interfaces. The method includes receiving a blueprint with a set of structure blocks extracted from a selected content. A structure block of the set of structure blocks includes a set of style parameter requests for a section of the selected content. The method further includes processing the set of structure blocks with a first set of smart blocks to generate a set of scores. A smart block of the first set of smart blocks includes brand data with style parameter selections. The method further includes selecting a second set of smart blocks, for the set of structure blocks, from the first set of smart blocks, using the set of scores. The method further includes presenting the second set of smart blocks with the brand data.
A contrastive in-context learning protocol for large language models. The protocol includes inputting positive and negative examples to a large language model. Additionally, the large language model may be instructed to analyze the reasons behind the positive examples being positive and the negative examples being negative. The large language model with such contrastive in-context learning can generate specific responses/answers based on user preferences, generally not possible using conventional models.
Embodiments disclosed herein generate a strategy insight report for a user's business, leveraging generative artificial intelligence—particularly large language models—and pre-stored data associated with the user. The large language models are used to capture subjective information associated with different insight areas, e.g., strength, weakness, opportunity, and threat (SWOT) of a SWOT model. The captured subjective information is augmented, supplemented, and/or modified by the pre-stored data to generate the strategy insight report. In contrast to conventional results and reports, the disclosed strategy insight report provides a current state of the user's business as well as next steps and recommendations.
G06Q 10/0637 - Gestion ou analyse stratégiques, p. ex. définition d’un objectif ou d’une cible pour une organisationPlanification des actions en fonction des objectifsAnalyse ou évaluation de l’efficacité des objectifs
5.
SYSTEMS AND METHODS FOR SOLVING MATHEMATICAL WORD PROBLEMS USING LARGE LANGUAGE MODELS
Output sentences of a primary large language model is provided to a criteria model including a second large language model. The criteria model compares the output to a reference source. As a result of comparing, the criteria model generates a first data structure including a first vector. The first vector stores, an evaluation of the output as being consistent or inconsistent with the reference source, and a corresponding reason for the evaluation. The criteria model identifies an inconsistent sentence, in the sentences, that is inconsistent with the reference source. The method also includes rewriting, by a reason improver model including a third large language model, the inconsistent sentence into a consistent sentence. The consistent sentence is consistent with the reference source. The output is modified by replacing the inconsistent sentence in the sentences with the consistent sentence. Modifying generates a modified output. The method also includes returning the modified output.
Providing an output of a primary large language model to a criteria model including a second large language model. The criteria model compares each of the sentences to a reference source and generates a first data structure including a first vector. The first vector stores, for each of the sentences, a corresponding evaluation of a given sentence as being consistent or inconsistent with the reference source, and a corresponding reason for the corresponding evaluation of the given sentence. The first data structure is provided to a converter model including a third large language model. The converter model converts the first data structure to a second data structure. The second data structure includes a second vector storing scores indicating a corresponding consistency value for each of the sentences. A metric, indicating an overall consistency of the output with respect to the reference source, is generated from the second data structure.
A method including receiving a digital image including text arranged in a layout. The method also includes generating, by an optical character recognition model, a layout text vector that encodes at least one word in the text of the digital image and a position of the at least one word in the layout of the digital image. The method also includes generating, by a visual encoder model, a visual representation vector embedding a content of the digital image. The method also includes converting both the layout text vector and the visual representation vector into a projected text vector including a digital format suitable for input to a large language model. The method also includes combining, into a prompt, the projected text vector, a system message, and a task instruction. The method also includes generating an output including a key-value pair.
G06V 30/416 - Extraction de la structure logique, p. ex. chapitres, sections ou numéros de pageIdentification des éléments de document, p. ex. des auteurs
G06V 10/82 - Dispositions pour la reconnaissance ou la compréhension d’images ou de vidéos utilisant la reconnaissance de formes ou l’apprentissage automatique utilisant les réseaux neuronaux
G06V 30/19 - Reconnaissance utilisant des moyens électroniques
G06V 30/414 - Extraction de la structure géométrique, p. ex. arborescenceDécoupage en blocs, p. ex. boîtes englobantes pour les éléments graphiques ou textuels
9.
WORKFLOW ASSISTANT WITH GENERATIVE ARTIFICIAL INTELLIGENCE
Certain aspects of the disclosure pertain to workflow creation assistance with generative artificial intelligence. A problem statement can be received that is specified by a user in a natural language. At least one machine learning model can infer a workflow template that maps to the problem statement. Workflow template parameters can be determined, and parameter values generated based on the problem statement. Additional interaction with the user in the natural language can be performed to request and receive further data associated with the workflow template with the at least one machine-learning model. Subsequently, the workflow template can be populated with generated parameter values and provided to a workflow system that generates a workflow based on the workflow template.
Certain aspects of the disclosure provide techniques for translating a prompt into a structured input to resolve the natural langue query as a planning problem. A method generally includes identifying and classifying tokens in a prompt using a large language model (LLM); extracting from a domain description in a planning domain definition language (PDDL): object types used to categorize objects; and predicates identifying relationships between the objects that may be true or false; categorizing at least one token in the prompt as one or more of the objects, one or more of the object types, or one or more of the predicates based on the classification of the at least one token determined by the LLM; and generating a task description in the PDDL based on the categorization, the task description comprising a translation of the prompt into a structured input for a planner.
Certain aspects of the disclosure provide techniques for prompt processing. A method generally includes generating a representation of a prompt using a large language model (LLM), the representation comprising semantic features of the prompt, wherein the prompt requests a state change from an initial state to a desired goal state; generating a task description based on using the representation and a domain description; generating an execution plan for the task description, the execution plan comprising a sequence of steps used to transform the initial state to the desired goal state; executing the sequence of steps; and generating a natural language response to the prompt after completing the execution of the sequence of steps, wherein the natural language response is based on the information obtained or the desired goal state.
Embodiments disclosed herein provide automated account recommendations for a hierarchical account structure. For an incoming transaction data record, a first language model is used to generate a recommended account name that is agnostic to the existing list of accounts. The recommended account name is appended to the existing list of accounts, which is consolidated to remove synonymous accounts. Additionally, a hierarchical relationship between the different accounts in the consolidated list of accounts is determined. A second language model is used to select an account name from the list of accounts. The selected account name along with any hierarchically related account name may be displayed to the user for selection.
G06Q 20/40 - Autorisation, p. ex. identification du payeur ou du bénéficiaire, vérification des références du client ou du magasinExamen et approbation des payeurs, p. ex. contrôle des lignes de crédit ou des listes négatives
Certain aspects of the disclosure provide systems and methods for generating meaningful insights from a data frame based on an insight score. An insight score may quantify the significance and confidence of a given insight. Aspects of the disclosure provide for optimizing the most meaningful insight based on a greedy binary search approach. Aspects of the disclosure further provide for obtaining the optimal insight based on a gradient search approach.
A method for providing certified reviews on a third-party review service includes obtaining one or more tokens associated with a transaction between a buyer and a seller to purchase an item from the seller. The method includes authenticating the buyer to provide a review of at least one of the seller or the item based on the one or more tokens. The method includes receiving a review generated by the buyer and, based on the authenticating, publishing the review so that the review is publicly accessible via the third-party-review service. The method includes providing a public indication that the published review is certified.
G06Q 30/0282 - Notation ou évaluation d’opérateurs commerciaux ou de produits
G06Q 20/36 - Architectures, schémas ou protocoles de paiement caractérisés par l'emploi de dispositifs spécifiques utilisant des portefeuilles électroniques ou coffres-forts électroniques
G06Q 20/38 - Protocoles de paiementArchitectures, schémas ou protocoles de paiement leurs détails
G06Q 20/40 - Autorisation, p. ex. identification du payeur ou du bénéficiaire, vérification des références du client ou du magasinExamen et approbation des payeurs, p. ex. contrôle des lignes de crédit ou des listes négatives
15.
DYNAMICALLY GENERATING USER INTERFACES BASED ON MACHINE LEARNING MODELS
Certain aspects of the present disclosure provide techniques for rendering visual artifacts in virtual worlds using machine learning models. An example method generally includes identifying, based on a machine learning model and a streaming natural language input, an intent associated with the streaming natural language input; generating, based on the identified intent associated with the streaming natural language input, one or more virtual objects for rendering in a virtual environment displayed on one or more displays of an electronic device; and rendering the generated one or more virtual objects in the virtual environment.
Systems and methods are described for batch materialization of an incremental change data capture (CDC) changeset with full row changes. The primary keys are extracted from the incremental CDC changeset and an indication of the extracted primary keys are broadcast to a plurality of executors. The primary keys may be added to Bloom filter or a plurality of Bloom filters that are broadcast to the executors. Each executor filters a baseline data table based on the extracted primary keys to generate a baseline match dataframe with all primary keys matching the extracted primary keys, and a baseline unmatched dataframe with all primary keys not matching the extracted primary keys. Each executor receives full row changes from a partitioned incremental CDC changeset and combines the changes with the baseline unmatched dataframe to produce a final changed baseline data table.
Certain aspects of the disclosure provide techniques for access control policy management. A method generally includes factorizing a user access co-occurrence data element to generate two data sub-elements, wherein: the user access co-occurrence data element represents co-occurrences between users of a system and resources of the system, a product of the two data sub-elements approximates the user access co-occurrence data element, and each of the two data sub-elements has reduced dimensionality compared to the user access co-occurrence data element; generating an approximated user access co-occurrence data element based on the product of the two data sub-elements; comparing the user access co-occurrence data element and the approximated user access co-occurrence data element to determine one or more anomalies, wherein each of the one or more anomalies relates to access for a user to a resource of the system; and taking one or more actions to rectify the one or more anomalies.
Systems and methods for adapting an onboarding session to a user are disclosed. An example method is performed by one or more processors of a system and includes receiving a transmission over a communications network from a computing device associated with a user of the onboarding system, the transmission including one or more files, extracting data from each of the one or more files using one or more parser plugins, transforming the extracted data into a set of arrays, feeding a prompt including the set of arrays to a large language model (LLM), inferring characteristics of the user based on a response to the prompt from the LLM, mapping the inferred characteristics to a predefined list of system features, and optimizing components of an onboarding session for the user based on the mapping.
Systems and methods for intelligently repairing data are disclosed. An example method is performed by one or more processors of a data quality management (DQM) system and includes receiving a transmission over a communications network from a computing device associated with the DQM system, the transmission including an indication that source data stored in a source database was ingested and stored as target data in a target database at a time of ingestion, comparing, using an advanced DQM algorithm, the target data with the source data, the advanced DQM algorithm including generating a first set of parity results based on changes occurring before the time of ingestion, generating a second set of parity results based on changes occurring after the time of ingestion, and generating differential results based on the first and the second set of parity results, and selectively repairing ones of the changes based on the differential results.
G06F 16/20 - Recherche d’informationsStructures de bases de données à cet effetStructures de systèmes de fichiers à cet effet de données structurées, p. ex. de données relationnelles
G06F 16/215 - Amélioration de la qualité des donnéesNettoyage des données, p. ex. déduplication, suppression des entrées non valides ou correction des erreurs typographiques
Systems and methods for detecting errors in a data transfer uses a machine learning model to identify potential anomalies in the data transfer based on metadata. Mismatches between input data from the data transfer and output data after importing the data transfer may additionally be identified. User review and correction of data errors and potential anomalies identified using the machine learning model may be proactively prompted to ensure any errors or discrepancies are addressed before finalizing the import of the data transfer. User corrections are further used to retrain the machine learning model to enable continuous improvement and learning from the data transfer process.
A method includes detecting, in a written electronic communication, an input sentence satisfying a readability metric threshold, and processing, by a sentence transformer model responsive to the input sentence satisf)fing the readability metric threshold, the input sentence to output a suggested set of sentences. The method further includes evaluating the first suggested set of sentences along a set of acceptability criteria, and determining, based on the evaluating, that the set of acceptability criteria is satisfied. The method further includes modifying, based on determining that the set of acceptability criteria is satisfied, the written electronic communication with the suggested set of sentences to obtain a modified written electronic communication, and storing the modified written electronic communication.
A method of blank detection involves receiving a document from a user, where the document includes derived text; applying a trained blank detection model to the document to make a first prediction, where the first prediction indicates whether at least one field in the document is blank; comparing the first prediction with a second prediction, where the second prediction is made by an extraction model; and extracting the at least one field using the extraction model.
The one or more embodiments provide for a method. The method includes receiving a digital image stored in an object notation data format. The method also includes converting the digital image into hypertext markup language (HTML) data format. The method also includes caching the HTML data format to generate cached HTML data. The method also includes receiving a first request to reload the digital image. The method also includes rendering, responsive to receiving the first request to reload, the digital image using the cached HTML data to generate a rendered digital image.
G06F 3/14 - Sortie numérique vers un dispositif de visualisation
G06F 16/50 - Recherche d’informationsStructures de bases de données à cet effetStructures de systèmes de fichiers à cet effet de données d’images fixes
G06F 16/957 - Optimisation de la navigation, p. ex. mise en cache ou distillation de contenus
G06F 17/00 - Équipement ou méthodes de traitement de données ou de calcul numérique, spécialement adaptés à des fonctions spécifiques
Certain aspects of the present disclosure provide techniques for providing smart content to a user of an application. Embodiments include receiving a request from a client for content. The request may include context data. Embodiments include identifying a content template for the content based on the request. Embodiments include identifying a rule associated with the content template. Embodiments include evaluating the rule based on the context data in order to determine a value of a variable. Embodiments include generating personalized content based on the content template and the value of the variable. Embodiments include providing the personalized content to the client.
Systems and methods are disclosed for converting natural language queries to a query instruction set for searching a data warehouse. To generate a query instruction set from a natural language query, a system iteratively uses a generative artificial intelligence (AI) model and database query tools to generate a query instruction set in a stepwise manner. The system and generative AI model do not require a priori knowledge of data table contents in the data warehouse, which may include sensitive information. In addition, the system does not require access to the data warehouse to generate the query instruction set. Instead, the system is implemented to use structure information from the data warehouse, including table lists (such as table names) and table format information (such as column names) of tables in the data warehouse, and the generative AI model is a generally trained model to generate the query instruction set.
Certain aspects of the present disclosure provide techniques for automatically healing a product flow for a mobile application. The techniques include an auto-healer capable of performing one or more actions, such as healing a product flow or generating an alert for a product flow, in response to determining an issue with the health status of the product flow. The health status can be determined from metrics included in a signal sent from mobile devices executing a mobile application including the product flow and hosted on a mobile application distribution platform. The metrics may be collected at flags or checkpoints in the mobile application and sent to a metrics server. In some cases, artificial intelligence may be used to analyze the metrics to determine health status issues or anomalies.
Certain aspects of the present disclosure provide techniques retrieval augmented generation of language model responses using an embedding database. Embeddings for data is stored in an embedding database. When a prompt related to the data is received, relevant embeddings may be retrieved from the database and used generate an augmented prompt based on the initial prompt and the retrieved embeddings from the database. The augmented prompt can be input into a machine learning model. Although the model may be unaware of the data from which the embeddings of the embedding database were generated, the augmented prompt enables the model to use the data to improve breadth and depth of responses.
H04L 51/02 - Messagerie d'utilisateur à utilisateur dans des réseaux à commutation de paquets, transmise selon des protocoles de stockage et de retransmission ou en temps réel, p. ex. courriel en utilisant des réactions automatiques ou la délégation par l’utilisateur, p. ex. des réponses automatiques ou des messages générés par un agent conversationnel
29.
DETECTION OF CYBER ATTACKS DRIVEN BY COMPROMISED LARGE LANGUAGE MODEL APPLICATIONS
A method including receiving, at a large language model, a prompt injection cyberattack. The method also includes executing the large language model. The large language model takes, as input, the prompt injection cyberattack and generates a first output. The method also includes receiving, by a guardian controller, the first output of the large language model. The guardian controller includes a machine learning model and a security application. The method also includes determining a probability that the first output of the large language model is poisoned by the prompt injection cyberattack. The method also includes determining whether the probability satisfies a threshold. The method also includes enforcing, by the guardian controller and responsive to the probability satisfying the threshold, a security scheme on use of the first output of the large language model by a control application. Enforcing the security scheme mitigates the prompt injection cyberattack.
G06F 21/56 - Détection ou gestion de programmes malveillants, p. ex. dispositions anti-virus
G06F 21/54 - Contrôle des utilisateurs, des programmes ou des dispositifs de préservation de l’intégrité des plates-formes, p. ex. des processeurs, des micrologiciels ou des systèmes d’exploitation au stade de l’exécution du programme, p. ex. intégrité de la pile, débordement de tampon ou prévention d'effacement involontaire de données par ajout de routines ou d’objets de sécurité aux programmes
G06F 21/55 - Détection d’intrusion locale ou mise en œuvre de contre-mesures
30.
SECURITY MARKER INJECTION FOR LARGE LANGUAGE MODELS
A method includes receiving, at a server from a user device, a user query to a large language model (LLM), creating an LLM query from the user query, inserting an security marker instruction into the LLM query to trigger an injection of a security marker, and sending the LLM query to the LLM. The method further includes receiving, from the LLM, an LLM response to the LLM query, evaluating the LLM response to detect whether the security marker is present in the LLM response, and setting a prompt injection signal based on whether the security marker is present in the LLM response.
G06F 21/54 - Contrôle des utilisateurs, des programmes ou des dispositifs de préservation de l’intégrité des plates-formes, p. ex. des processeurs, des micrologiciels ou des systèmes d’exploitation au stade de l’exécution du programme, p. ex. intégrité de la pile, débordement de tampon ou prévention d'effacement involontaire de données par ajout de routines ou d’objets de sécurité aux programmes
G06F 21/57 - Certification ou préservation de plates-formes informatiques fiables, p. ex. démarrages ou arrêts sécurisés, suivis de version, contrôles de logiciel système, mises à jour sécurisées ou évaluation de vulnérabilité
31.
PROMPT INJECTION DETECTION FOR LARGE LANGUAGE MODELS
A method includes receiving, at a server from a user device, a user query to a large language model (LLM), creating an LLM query from the user query, inserting a system prohibited request into the LLM query to generate a revised LLM query, and sending the revised LLM query to the LLM. The method further includes receiving, from the LLM, a first LLM response to the LLM query, testing the first LLM response to detect whether a prohibited response to the system prohibited request is included in the first LLM response, and setting a prompt injection signal based on whether the prohibited response to the system prohibited request is included in the first LLM response.
The present disclosure relates to dynamic targeting of network invitations. Embodiments include clustering, based on network usage data, a plurality of in-network entities into active network users and passive network users. Embodiments include generating, for each active in-network entity, a vector representation based on connections between the active in-network entity and one or more other entities. Embodiments include generating, for each out-of-network entity, a corresponding vector representation based on connections between the out-of-network entity and one or more in-network entities. Embodiments include determining, for each out-of-network, a probability that the out-of-network entity will join the network based on comparing the corresponding vector representation of the out-of-network entity to a vector that is determined based on the vector representation of each active in-network entity. Embodiments include selecting an out-of-network entity to invite to the network based on the probability that the out-of-network entity will join the network.
Systems and methods for determining ownership of cloud computing resources are disclosed. An example method includes identifying a first active table whose ownership is not defined in a central repository, determining, based on a write log associated with the first active table, a first timestamp and a first internet address associated with a most recent write to the first active table, determining, based on the first internet address, whether or not the first timestamp is more recent than a creation time of a first cloud computing instance corresponding to the most recent write, and in response to the first timestamp being more recent than the creation time of the first cloud computing instance, identifying a first owner of the first active table based on a first cost allocation tag associated with the first cloud computing instance.
G06F 9/455 - ÉmulationInterprétationSimulation de logiciel, p. ex. virtualisation ou émulation des moteurs d’exécution d’applications ou de systèmes d’exploitation
34.
CUSTOMIZATION AND ENRICHMENT OF USER INTERFACES USING LARGE LANGUAGE MODELS
A method including generating a revised prompt from user customization data for customizing a user interface of an application, a pre-engineered prompt, and an application artifact from the application. The method also includes generating an output by executing a large language model on the revised prompt. The method also includes receiving a modified template generated from the user customization data and at least one of a set of templates. The method also includes transforming the output of the large language model and the modified template into both a consumable user interface component and a user interface artifact. The method also includes modifying a user interface of the application by applying the consumable user interface component and the user interface artifact to the application.
Systems and methods are disclosed for managing categorization problem solutions and identifying miscategorizations. The identification of a miscategorization of an object is based on the object's first embedding being different than the first embeddings of other objects in a cluster. The objects in the cluster are clustered together based on second embeddings of the objects, with the first embedding generated based on a first description associated with an object and the second embedding generated based on a second description associated with the object. As such, while the clustering of second embeddings may initially indicate that the objects in the cluster are similar, the comparison between first embeddings of the objects in the cluster (such as calculating a distance between a first embedding and a center of the cluster based on the first embeddings) can confirm whether an object in the cluster is different and thus is potentially miscategorized.
A method includes receiving, at a server from a user device, a user query to a large language model (LLM), creating an LLM query from the user query and an application context, gathering confidential information from the LLM query, and sending the LLM query to the LLM. The method includes receiving, from the LLM, an LLM response to the LLM query, comparing the LLM response to the confidential information to generate comparison result, and setting a leakage detection signal based on comparison result.
A method for automatically generating content for a document for an individual includes providing input data to a trained artificial intelligence model. The input data includes a plurality of input features specific to the individual, and the trained artificial intelligence model is trained through a supervised learning process using training data that includes a plurality of input features for each of a plurality of individual other than the individual for whom the document is being created. The method includes receiving output data from the artificial intelligence model that is based, at least in part, on the input data and includes the content the artificial intelligence model automatically generated for the document for the individual. The method includes receiving user feedback on the content automatically generated by the artificial intelligence model and generating updated training data for the artificial intelligence model based, at least in part, on the user feedback.
Certain aspects of the disclosure provide systems and methods for resolving ambiguities encountered by a decision machine learning (ML) model during processing of input data. For example, a method may include identifying an ambiguity during decision processing of first input data by a decision ML model; conveying the ambiguity to an expert agent for evaluation; receiving, by an LLM, feedback regarding the ambiguity from the expert agent; determining, by the LLM, that the feedback, received from the expert agent, resolves the ambiguity; generating second input data by the LLM, the second input data having the first input data and the feedback determined to resolve the ambiguity; processing the second input data by the decision ML model to generate a decision based on processing of the second input data; and outputting, by the LLM, the decision received from the ML model.
09 - Appareils et instruments scientifiques et électriques
36 - Services financiers, assurances et affaires immobilières
42 - Services scientifiques, technologiques et industriels, recherche et conception
Produits et services
Computer software for management of employee benefit plans, insurance plans, health care plans, workers’ compensation plans, and retirement plan; Business management software for health care practice management Providing information about health care insurance plans Providing temporary use of computer software for management of employee benefits, insurance plans, workers’ compensation plans, and retirement plans; Providing temporary use of business management software for health care practice management
A method including receiving an input including a number of texts from a source of text and a number of images from a source of images. The texts are separate from the images. The input is embedded into a first data structure that defines first relationships among the images from the source of images and the texts from the source of text. The first data structure is compared to an index including a second data structure that defines second relationships among a number of pre-determined texts and a number of pre-determined images. The pre-determined texts have known relationships to the pre-determined images. Each pre-determined image in the pre-determined images is related to one or more instances of the pre-determined texts. A subset of images, those images in the pre-determined images for which matches exist between the first relationships and the second relationships, is returned from the pre-determined images.
G06F 16/583 - Recherche caractérisée par l’utilisation de métadonnées, p. ex. de métadonnées ne provenant pas du contenu ou de métadonnées générées manuellement utilisant des métadonnées provenant automatiquement du contenu
G06F 16/951 - IndexationTechniques d’exploration du Web
G06F 40/40 - Traitement ou traduction du langage naturel
43.
Search and semantic similarity domain determination
A method includes generating a new user query embedding for a new user query received from a user, obtaining an indexed user query matching the new user query from a search engine index, a vector index corresponding to the indexed user query, and a relevancy score corresponding to the indexed user query. The method further includes selecting a vector structure corresponding to the vector index from a plurality of vector structures in a vector store, obtaining, from the vector structure, a result embedding matching the new user query embedding, transmitting, by a user query answer service to an answer generation model, the result embedding and receiving, by the user query answer service, an answer to the new user query from the answer generation model.
Certain aspects of the disclosure provide techniques for information retrieval for large datasets. A method comprises receiving input text files and a query for the files; obtaining an index associated with the input text files to process the query, wherein: the index comprises key-value mappings, each key of a respective mapping identifying a voronoi cell of the index, and each value of a respective mapping identifying vector embeddings associated with text files associated with a voronoi cell of the index; creating a query embedding based on the query; identifying a first key-value mapping having a first key associated with a first voronoi cell in the index and corresponding to the query embedding; obtaining a set of vector embeddings associated with the first value; comparing the query embedding to the set of vector embeddings to determine closest vector embeddings; and generating a textual output based on the closest vector embeddings.
A first large language model (LLM) instance may be instructed to request data while being prevented from performing calculations using the data. A second LLM instance may be instructed to provide a response to the request for data based on a known complete data set. The response may be translated into a machine-readable response in a format configured for processing by a calculation engine. The calculation engine may process the machine-readable response, thereby generating a calculation engine output. A mismatch between the calculation engine output and a known result obtained using the known complete data set may be identified, and the instruction to the first LLM may be modified in response.
Systems and methods are disclosed for detecting hallucinations in large language models (LLMs). An example method includes receiving a first prompt for submission to the first LLM, generating, using the first LLM, a plurality of semantically equivalent prompts to the first prompt, generating, using the first LLM, a first response to the first prompt and a plurality of second responses to the plurality of semantically equivalent prompts, generating, using a second LLM, a plurality of third responses to the semantically equivalent prompts, generating a semantic consistency score for the first response based at least in part on the first prompt, the plurality of semantically equivalent prompts, the plurality of second responses, and the plurality of third responses, and determining whether or not the first response is an accurate response to the first prompt based at least in part on the semantic consistency score.
The present disclosure provides techniques for fast record matching using machine learning. One example method includes receiving a request indicating one or more attributes, identifying, from a plurality of records using a first machine learning model, a set of records, wherein each record of the set of records indicates the one or more attributes, computing, for each record of the set of records using a second machine learning model, a first relevance score for the record, computing, for each record of the set of records using a third machine learning model, a second relevance score for the record, and identifying, based on the first relevance score for each record of the set of records and the second relevance score for each record of the set of records, a given record of the set of records best matching the request.
A method for generating supplemental content for an explanation for a particular result determined by a software application includes receiving data indicative of a user selecting a first modality of a plurality of different modalities for supplementing the explanation. In response to receiving the data, the method includes providing inputs to a generative artificial intelligence model. The inputs include data indicative of the explanation and data indicative of a first natural language prompt associated with the first modality. The method includes receiving an output from the generative artificial intelligence model. The output includes supplemental content for the explanation. The method includes displaying the supplemental content for viewing via a user interface.
Systems and methods for training an encoder-decoder model are disclosed. An example method includes receiving, over a communications network, a plurality of extraction model outputs from a corresponding plurality of extraction models, each extraction model output received from a corresponding extraction model and each extraction model output including a respective plurality of key-value pairs corresponding to extracted text from one or more training documents, receiving, over the communications network, character recognition data corresponding to the one or more training documents, receiving, over the communications network, ground truth key-value data corresponding to the one or more training documents, and training the encoder-decoder model based at least in part on the plurality of extraction model outputs, the character recognition data, and the ground truth key-value data, wherein the trained encoder-decoder model is configured to generate key-value pairs for subsequent outputs of the plurality of extraction models.
G06V 30/19 - Reconnaissance utilisant des moyens électroniques
G06V 30/416 - Extraction de la structure logique, p. ex. chapitres, sections ou numéros de pageIdentification des éléments de document, p. ex. des auteurs
51.
SYSTEMS AND METHODS FOR DETECTING HALLUCINATIONS IN MACHINE LEARNING MODELS
Certain aspects of the disclosure provide systems and methods for detecting hallucinations in machine learning models. A method generally includes generating a potential answer from an initial prompt received from a user. The method generally includes interrogating the machine learning model with a verification prompt formulated to elicit a positive or negative response from the machine learning model based on the potential answer and initial prompt. A negative response by the neural network model to the verification prompt is indicative of the potential answer being a hallucination. A positive response by the neural network model to the verification prompt is indicative of the potential answer being free from a hallucination. The method generally includes outputting to the user the potential answer as a final answer upon receiving a positive response to the verification prompt.
Certain aspects of the present disclosure provide techniques for selecting between a model output of a machine learning (ML) model and a generic output. A method generally includes processing user-specific data with the ML model to generate the model output and a model predicted score associated with the model output; calculating a Shapley Additive Explanations (SHAP) score based on the model output, the model predicted score, and the user-specific data; and providing the model output or the generic output as output from the ML model based on the SHAP score.
Certain aspects of the disclosure provide a method for detecting data collection errors by processing error data with a plurality of regression models to generate a plurality of predicted error rates over a plurality of time intervals. The method includes determining an error mode by applying a set of policy rules optimized for determining the error mode to the plurality of predicted error rates.
Aspects of the present disclosure provide techniques for providing a graphical user interface for customizable application navigation. Embodiments include displaying a list of pages associated with a software application in a navigation customization screen and receiving selections of two or more pages of the pages as bookmarks. Embodiments include receiving drag and drop input via the navigation customization screen that changes an ordering of the two or more pages within the list of the plurality of pages and receiving a search query comprising a text string. Embodiments include moving one or more pages matching the search query to a top of the list of the pages within the navigation customization screen and displaying an indication in the navigation customization screen that one of the two or more pages also matches the search query without changing the ordering of the two or more pages within the list of the pages.
G06F 16/955 - Recherche dans le Web utilisant des identifiants d’information, p. ex. des localisateurs uniformisés de ressources [uniform resource locators - URL]
G06F 3/04817 - Techniques d’interaction fondées sur les interfaces utilisateur graphiques [GUI] fondées sur des propriétés spécifiques de l’objet d’interaction affiché ou sur un environnement basé sur les métaphores, p. ex. interaction avec des éléments du bureau telles les fenêtres ou les icônes, ou avec l’aide d’un curseur changeant de comportement ou d’aspect utilisant des icônes
G06F 3/0482 - Interaction avec des listes d’éléments sélectionnables, p. ex. des menus
A method for automatically populating a document being prepared via a software application based on extracted data from one or more of a plurality of different source documents may include displaying a graphical user interface associated with the software application and include a first area configured to display data associated with the document and a second area displaying a queue including at least a first graphical object descriptive of a first source document of the plurality of source documents. The method includes automatically populating one or more data fields of the document that are displayed within the first area of the graphical user interface with the extracted data from the first source document. In response to the automatically populating, the method includes automatically updating the second area of the graphical user interface to reflect the data fields have been auto populated with the extracted data from the first source document.
G06F 3/0481 - Techniques d’interaction fondées sur les interfaces utilisateur graphiques [GUI] fondées sur des propriétés spécifiques de l’objet d’interaction affiché ou sur un environnement basé sur les métaphores, p. ex. interaction avec des éléments du bureau telles les fenêtres ou les icônes, ou avec l’aide d’un curseur changeant de comportement ou d’aspect
09 - Appareils et instruments scientifiques et électriques
35 - Publicité; Affaires commerciales
36 - Services financiers, assurances et affaires immobilières
42 - Services scientifiques, technologiques et industriels, recherche et conception
Produits et services
Computer software; downloadable computer software for use in personal and business finance, financial planning and management, financial and business transaction processing, accounting, bookkeeping, tax preparation, planning, and filing; payment processing software; downloadable computer software for creating, customizing, and managing invoices, recording payments, and issuing receipts; downloadable computer software for electronic invoicing and payment processing; downloadable computer software for facilitating payments; downloadable computer software for processing electronic transactions; downloadable computer software for electronic funds transfer; downloadable computer software that enables communication between business and financial professionals and their clients; downloadable computer software to automate creation of invoices; downloadable computer software to create, customize, print, export, and e-mail purchase orders, invoices, receipts, documents, and reports; downloadable software for sending, receiving and recording monetary transactions; downloadable software for use in organizing, servicing and tracking sales, collections, and receivables data; downloadable software that provides financial data for use by small businesses; downloadable computer software for controlling access to financial and business information, data, and documents; downloadable computer software to track sales, expenses, and payments; downloadable computer software for enabling consumers to make, and merchants to accept, payments using cryptocurrency, digital currency, electronic cash, and virtual currency; downloadable computer software for managing online bank accounts; downloadable computer software for tracking income, expenses, sales, and profitability by business location, department, type of business, or other user set field; downloadable computer software for use in transaction processing, accounting, customer relationship management, inventory management, business operations and operations management; downloadable computer software that enables users to capture, upload, download, store, organize, view, create, edit, encrypt, send and share documents, information, data, images, photographs, and electronic messages; downloadable computer software to import contacts and business data from other electronic services and software. Business invoicing services; online accounting and bookkeeping services; online bill payment services. Banking services; online banking services; bank account management services; bill payment services; electronic bill presentment for others; electronic commerce payment services; electronic money transfer services; electronic payment processing services; electronic payment services; electronic processing and transmission of bill payment data for others; financial management services via global computer networks; financial services; financial transaction services; payment processing services; providing electronic cash, credit card, and debit card transaction services via computer and communication networks; provision of financial information; transaction processing services for consumers and businesses. Providing non-downloadable computer software; Providing non-downloadable financial management software; Providing non-downloadable software for personal and business finance, accounting, bookkeeping, financial and business transaction processing management, financial and business transaction management, tax preparation, tax planning, and tax filing, business process management, and financial planning; Providing non-downloadable payment processing software; Providing non-downloadable payment software; Providing non-downloadable electronic payment processing software; Providing non-downloadable computer software for facilitating payments; Providing non-downloadable software for creating, customizing, and managing invoices, recording payments, and issuing receipts; Providing non-downloadable software for electronic funds transfer; Providing non-downloadable software for electronic invoicing and payment processing; Providing non-downloadable software to automate creation of invoices; Providing non-downloadable software to create, customize, print, export, and e-mail purchase orders, invoices, receipts, documents, and reports; Providing non-downloadable software for executing, processing, and recording financial transactions; Providing non-downloadable software for sending, receiving and recording monetary transactions; non-downloadable computer software that enables communication between business and financial professionals and their clients; Providing non-downloadable business management software; Providing non-downloadable computer software for enabling consumers to make, and merchants to accept, payments using cryptocurrency, digital currency, electronic cash, and virtual currency; Providing non-downloadable computer software for managing online bank accounts; Providing non-downloadable software for controlling access to financial and business information, data, and documents; Providing non-downloadable software for tracking income, expenses, sales, and profitability by business location, department, type of business, or other user set fields; Providing non-downloadable software for use in organizing, servicing and tracking sales, collections, and receivables data; Providing non-downloadable software for use in transaction processing, accounting, customer relationship management, inventory management, and operations management; Providing non-downloadable software that enables users to capture, upload, download, store, organize, view, create, edit, encrypt, send and share documents, information, data, images, photographs, and electronic messages; Providing non-downloadable software that provides financial data for use by small businesses; Providing non-downloadable software to import contacts and business data from other electronic services and software; Providing non-downloadable software to track sales, expenses, and payments; software as a service (SaaS) featuring cloud computing capabilities for accounting, bookkeeping, financial and business transaction processing management, financial and business transaction management, tax preparation and tax planning, business process management, and financial planning; software as a service (SaaS) services.
57.
LARGE LANGUAGE MODEL AND DETERMINISTIC CALCULATOR SYSTEMS AND METHODS
At least one large language model (LLM) may be instructed to request data from a user while being prevented from performing calculations using the data. A user-generated response to the request for data, including at least a portion of the data, may be received. The user-generated response may be translated into a machine-readable response in a format configured for processing by a calculation engine. The calculation engine may process the machine-readable response, thereby generating a calculation engine output.
A method for detecting fraudulent financial transactions in information technology networks involves obtaining a multitude of features associated with a financial transaction conducted over an information technology network by an unknown transaction party. The multitude of features includes clickstream data obtained from the unknown transaction party. The clickstream data is associated with data of the financial transaction being entered by the unknown transaction party. The method further involves obtaining a first fraud indicator using a machine learning classifier operating on the multitude of features, obtaining a second fraud indicator using a rule-based classifier operating on the multitude of features, obtaining a fraud prediction for the financial transaction, using the first fraud indicator and the second fraud indicator, and taking an action, in response to the fraud prediction.
G06Q 20/40 - Autorisation, p. ex. identification du payeur ou du bénéficiaire, vérification des références du client ou du magasinExamen et approbation des payeurs, p. ex. contrôle des lignes de crédit ou des listes négatives
G06F 18/243 - Techniques de classification relatives au nombre de classes
G06F 21/52 - Contrôle des utilisateurs, des programmes ou des dispositifs de préservation de l’intégrité des plates-formes, p. ex. des processeurs, des micrologiciels ou des systèmes d’exploitation au stade de l’exécution du programme, p. ex. intégrité de la pile, débordement de tampon ou prévention d'effacement involontaire de données
At least one processor may receive a query response generated by a query machine learning (ML) model, wherein the query response is generated in response to a query from a client device. The at least one processor may generate an evaluated likelihood of the query response being found in a training data set comprising known valid data, wherein the generating is performed using an evaluation ML model. The at least one processor may determine that the evaluated likelihood indicates the query response is likely to include valid data. In response to the determining, the at least one processor may return the query response to the client device.
A method includes obtaining matches between target records in a target dataset and a reference records in a reference dataset, each match of the matches comprising a corresponding confidence level of the match, categorizing the target records into review level categories according to the corresponding confidence level, and presenting a graphical user interface (GUI). The GUI includes a first section for a first review level category showing a first subset of the target records assigned to the first review level category, the first subset comprising target records related, in the GUI, to at least one matching reference record. The GUI includes a second section for a second review level category, wherein the second section shows a second subset of the target records assigned to the second review level category, the second subset comprising target records related, in the GUI, to at least one matching reference record.
Systems and methods for enriching raw user text with a database to identify relevant context, wherein generated prompts provide responses to user queries is provided. A method includes receiving a query, wherein the query comprises the raw text, creating a first embedding based on the query, retrieving a plurality of other embeddings, wherein the plurality of other embeddings are complementary to the first embedding, creating a contextual prompt including context from at least one of the plurality of other embeddings, processing the contextual prompt using a trained machine learning model, thereby generating a response to the query, and causing the response to be displayed by a display device.
Certain aspects of the disclosure provide a method of providing an interactive user support interface, the method comprising receiving a communication with a support request for an application. The method further comprising determining, based on the communication, an account associated with the application and determining, based on the account, that the user is an active session in to the application. The method further comprising determining support content responsive to the support request and causing the support content to be displayed within the application based on the determination that the user is an active session in to the application.
A method classifies feedback from transcripts. The method includes receiving an utterance from a transcript from a communication session and processing the utterance with a classifier model to identify a topic label for the utterance. The classifier model is trained to identify topic labels for training utterances. The topic labels correspond to topics of clusters of the training utterances. The training utterances are selected using attention values for the training utterances and clustered using encoder values for the utterances. The method further includes routing the communication session using the topic label for the utterance.
G06F 40/131 - Fragmentation de fichiers textes, p. ex. création de blocs de texte réutilisablesLiaison aux fragments, p. ex. par utilisation de XIncludeEspaces de nommage
G06F 40/289 - Analyse syntagmatique, p. ex. techniques d’états finis ou regroupement
67.
Methods and systems for implementing large language models and smart caching with zero shot
A Large Language Model (LLM) for classifying documents by identifying indicators within the documents. A smart caching mechanism stores document classifications and associated indicators output from the LLM. The database contains document details, classifications, and associated indicators. A classification module classifies a new document by analyzing it for indicators, checking the cache for a match, and querying the database for the indicators if no match is found. The module applies a majority vote based on the classifications associated with the indicators.
G06F 12/0875 - Adressage d’un niveau de mémoire dans lequel l’accès aux données ou aux blocs de données désirés nécessite des moyens d’adressage associatif, p. ex. mémoires cache avec mémoire cache dédiée, p. ex. instruction ou pile
Certain aspects of the present disclosure provide techniques and systems for automatically detecting, tracking, and processing certain information content, based on voice input from a user. A voice enabled content tracking system receives natural language content corresponding to audio input from a user. A determination is made as to whether the natural language content includes a first type of information, based on evaluating the natural language content with a first machine learning model. In response to determining the natural language content comprises the first type of information, a temporal association of the first type of information is determined, based on evaluating the natural language content with a second machine learning model, and a message including an indication of the temporal association of the first type of information is transmitted to the user.
G06F 3/0484 - Techniques d’interaction fondées sur les interfaces utilisateur graphiques [GUI] pour la commande de fonctions ou d’opérations spécifiques, p. ex. sélection ou transformation d’un objet, d’une image ou d’un élément de texte affiché, détermination d’une valeur de paramètre ou sélection d’une plage de valeurs
A transaction model of a general model generates a target transaction vector for a target transaction record. The general model also generates account vectors for accounts. A match score is generated between the account vectors and the transaction vector. The general model selects a first account identifier of an account using the match score. The transaction model also generates historical transaction vectors for historical transaction records. Further, a comparison score is generated between the historical transaction vectors and the target transaction vector. A second account identifier of an historical transaction is selected according to the comparison score. One of the first account identifier and the second account identifier is selected as the account identifier for the transaction record, and the transaction record is stored with the account identifier.
The present disclosure provides techniques for schema-based machine learning model monitoring. One example method includes receiving input data to and output data related to a machine learning model, wherein the input data and the output data conform to a data schema, retrieving, based on the data schema, a set of fields associated with the input data and the output data, performing statistical analysis for the machine learning model based on the set of fields retrieved, and predicting one or more attributes of the machine learning model based on the statistical analysis, wherein the one or more attributes of the machine learning model indicate a result of monitoring of the machine learning model, explainability information related to the machine learning model, or health of the machine learning model.
Systems and methods for matching received product information with stored product information. Incoming product information has multiple attributes, which may be fuzzy matched with corresponding attributes of stored product information to generate corresponding fuzzy matching scores. Each of the fuzzy matching scores is associated with a weighting factor, which is used to indicate a contribution of the corresponding fuzzy matched attribute to a match between the entire product information. A matching coefficient is initialized and progressively updated by using the weighted fuzzy matching scores. When a desired number of fuzzy matchings between the corresponding attributes is reached and the matching coefficient is finalized, the matching coefficient is compared to a threshold. If the matching coefficient is above the threshold, a recommendation is generated indicating a match between the received product information and the stored product information.
A method including receiving a user input from a user device. The method also includes generating test inputs including the user input and modified inputs. The user input is processed with a rephrasing model to form the modified inputs. The method also includes executing a test model to generate test outputs, including an original test output and modified test outputs, from processing the test inputs. The method also includes generating similarity scores by performing similarity comparisons among the test outputs. The method also includes determining a model confidence from the similarity scores. The method also includes routing the user input responsive to the model confidence satisfying or failing to satisfy a confidence threshold.
Certain aspects of the disclosure provide a method for training a machine learning model to predict text containing sensitive information. The method includes extracting one or more features from a historical data set. The method further includes anonymizing the historical data set, including determining, for each feature of the extracted one or more features, tokens containing personally identifiable information (sensitive information); assigning a category placeholder to each of the tokens containing sensitive information; and generating a new data set where each token containing sensitive information is replaced with the assigned category placeholder. The method further includes determining a probability associated with each token containing sensitive information; and training a generalized model to predict anonymized text given the one or more features.
A computer-implemented method includes receiving data comprising a plurality of application programming interface (API) requests from a plurality of client devices. The method includes generating a plurality of API sessions based on the data, wherein each of the API sessions is associated with a corresponding client device of the plurality of client devices and includes a sequence of API requests originating from the corresponding client device. The method includes determining one or more API sessions of the plurality of API sessions generated based on the data are abnormal. Finally, the method includes performing one or more actions based on determining the one or more API sessions are abnormal.
Certain aspects of the present disclosure provide techniques for executing a function in a software application through a conversational user interface based on a knowledge graph associated with the function. An example method generally includes receiving a request to execute a function in a software application through a conversational user interface. A graph definition of the function is retrieved from a knowledge engine. Input is iteratively requested through the conversational user interface for each parameter of the parameters identified in the graph definition of the function based on a traversal of the graph definition of the function. Based on a completeness graph associated with the function, it is determined that the requested inputs corresponding to the parameters identified in the graph definition of the function have been provided through the conversational user interface. The function is executed using the requested inputs as parameters for executing the function.
G06F 16/901 - IndexationStructures de données à cet effetStructures de stockage
G06N 5/02 - Représentation de la connaissanceReprésentation symbolique
G10L 15/22 - Procédures utilisées pendant le processus de reconnaissance de la parole, p. ex. dialogue homme-machine
H04L 51/02 - Messagerie d'utilisateur à utilisateur dans des réseaux à commutation de paquets, transmise selon des protocoles de stockage et de retransmission ou en temps réel, p. ex. courriel en utilisant des réactions automatiques ou la délégation par l’utilisateur, p. ex. des réponses automatiques ou des messages générés par un agent conversationnel
76.
Contextual bandit for multiple machine learning models for content delivery
A processor may receive user information for a request payload from an external device and data describing a plurality of user interface (UI) elements configured to be presented in a UI of the external device. The processor may select a machine learning (ML) model from a plurality of ML models using a contextual bandit ML model that is trained based on the user information. The processor determines at least one recommended user interface (UI) element with a selected ML model, based on the user information and the data describing the plurality of UI elements. The at least one recommended UI element may be presented in the UI of the external device. The processor may receive event data indicating a user interaction with the at least one recommended UI element in the UI of the external device. The contextual bandit ML model may be re-trained based on the event data.
G06Q 30/02 - MarketingEstimation ou détermination des prixCollecte de fonds
G06N 3/006 - Vie artificielle, c.-à-d. agencements informatiques simulant la vie fondés sur des formes de vie individuelles ou collectives simulées et virtuelles, p. ex. simulations sociales ou optimisation par essaims particulaires [PSO]
G06N 3/082 - Méthodes d'apprentissage modifiant l’architecture, p. ex. par ajout, suppression ou mise sous silence de nœuds ou de connexions
G06N 5/04 - Modèles d’inférence ou de raisonnement
Certain aspects of the disclosure pertain to predicting a candidate entity match for a transaction with a machine learning model. A description of a transaction comprising encoded transaction data associated with an organization is received as input. In response, at least one machine learning model can be invoked to infer a transaction embedding based on the description, a first score that captures similarity between the transaction embedding entity embeddings associated with a global list of entities and organizations, a second score that captures a probability of interaction between the first organization and the entities based on organization and entity embeddings that capture profile data associated with the organization and the entities, and at least one candidate entity based on the first score and the second score. Finally, the inferred candidate entity can be output for use by an automated data entry or other process or system.
A method including identifying first and second training data having first and second subsets of click-through information for a dataset. Identifying includes associating the first and second subsets first and second applications executing on first and second domains having divergent first and second ontologically defined groupings of entities. The method also includes storing, as first and second vector data structures, the first and second training data. The method also includes training, on the first and second vector data structures, first and second ARIMA machine learning models. The first trained ARIMA machine learning model is trained on the first domain and the second trained ARIMA machine learning model is trained on the second domain. The method also includes deploying the first and second trained ARIMA machine learning models.
09 - Appareils et instruments scientifiques et électriques
41 - Éducation, divertissements, activités sportives et culturelles
Produits et services
(1) Downloadable electronic newsletters delivered via email in the fields of accounting, bookkeeping, personal and business finance, financial and business transaction management, tax preparation and tax planning, business process management, and financial planning (1) Providing online newsletters via email in the fields of accounting, bookkeeping, personal and business finance, financial and business transaction management, tax preparation and tax planning, business process management, and financial planning
81.
Display device with graphical user interface having a strategy card
The present disclosure provides techniques for friendship-based automated recommender system. One example method includes receiving electronic record data indicating interactions between a plurality of users and a plurality of providers, constructing a bipartite graph based on the interactions, identifying, for each user of the plurality of users, a set of other users in the plurality of users, adding to the bipartite graph, for each user of the plurality of users, intra-user edges between the user and the set of other users, computing, for each respective intra-user edge of the intra-user edges, a weight of the respective intra-user edge, computing, for each respective user of the plurality of users, a popularity score, computing, for each respective provider of the plurality of providers, a reputation score, and training a recommender system using the reputation scores of the plurality of providers, wherein the recommender system is used to automatically determine a provider recommendation.
In a pipeline, data events generated by a producer application are temporally grouped by using a group identification tag. For each data event, data points are generated and uploaded to a storage and cache at each point of production and consumption. The storage allows a matching of data events between the production point and the consumption point, thereby ensuring that streaming parity is maintained. In cases of mismatch, the cache allows for detecting missing data events, i.e., identifying data events that were generated by an upstream producer application, but not consumed by a downstream consumer. While being agnostic to the transformations applied by the various applications in the pipeline, the embodiments disclosed herein keep track of the output data events and input data events and precisely identify the missing data events.
Aspects of the present disclosure provide techniques for active multifidelity machine learning. Embodiments include selecting, based on one or more criteria, a first subset of unlabeled training data for manual review and a second subset of unlabeled training data for providing to a pre-trained machine learning model for automated labeling. Embodiments include receiving manual label data for the first subset of unlabeled training data. Embodiments include providing inputs to the pre-trained machine learning model based on a subset of the manual label data and the second subset of training data. Embodiments include receiving, as outputs from the pre-trained machine learning model, automated label data for the second subset of unlabeled training data. Embodiments include generating a training data set for a target machine learning model based on the set of unlabeled training data, the manual label data, and the automated label data.
A method for operating a stateful advice system includes determining, based on configuration data, whether a selected mode for the stateful advice system corresponds to a first mode in which a domain model is directly modified to implement one or more of a plurality of different strategies or a second mode in which the domain model is indirectly modified via a model schema of the domain model. The method includes providing a prompt to a generative artificial intelligence (AI) model configured to determine applicability of each of the plurality of different strategies to the domain model. The prompt includes the domain model when the selected mode corresponds to the first mode or the model schema when the selected mode corresponds to the second mode. The method includes receiving one or more recommendations from the generative AI model.
A method for generating stateful advice includes obtaining configuration data associated with configuring a stateful advice system to provide stateful advice within a domain. The method includes obtaining data indicative of an attribute for a strategy that is associated with the domain. The method includes providing the configuration data and the data indicative of the attribute to a generative artificial intelligence (AI) model configured to automatically author content for an advice artifact for the strategy. The content includes a series of prompts associated with providing stateful advice regarding the strategy. The method includes determining the strategy is applicable to a domain model associated with the domain based, at least in part, on the content automatically authored by the generative AI model. The method includes generating a recommendation to apply the strategy to the domain model in response to determining the strategy is applicable to the domain model.
Certain aspects of the disclosure provide a method of constructing a report incorporating data stored in a plurality of database tables. The method generally includes receiving, via an interactive user interface (UI), a selection of a first database table, generating a visualization of data associated with the first database table organized in rows and columns, wherein each column includes data for a data field in the first database table, displaying, via the interactive UI, shared data fields associated with other related database tables and shared among all of the other database tables, receiving, via the interactive UI, a selection of a first shared data field, and displaying, via the interactive UI, data for the first shared data field from all the other database tables in a first new column added to the visualization, wherein each row in the first new column includes data from one of the other database table.
Certain aspects of the disclosure provide a method for transferring an achievement token, comprising: receiving a request to transfer an achievement token to a user; querying a smart contract to obtain a requirement associated with the achievement token; verifying, via a blockchain, the user completed the requirement, including retrieving user evidence associated with the requirement from the blockchain; and storing user evidence with a transaction history associated with the transfer of the achievement token to the user; and transferring, via the blockchain, the achievement token to the user.
A method includes receiving a user input including natural language text. The method also includes generating modified inputs from the user input. The method also includes executing a machine learning model on the modified inputs to generate model outputs. The method also includes sampling the model outputs using a statistical sampling strategy to generate sampled model outputs. The method also includes clustering the sampled model outputs into clusters. The method also includes generating a confidence metric of the clusters. The method also includes routing, automatically in a computing system, the user input based on whether the confidence metric satisfies a threshold value.
41 - Éducation, divertissements, activités sportives et culturelles
Produits et services
matching lenders with borrowers in the fields of consumer lending and commercial lending; providing information in the nature of business and marketing advice, news, and opinions for professionals in the fields of accounting, finance, financial planning, small business management, tax preparation, tax filing and tax planning; Accounting and bookkeeping services; association and membership services, namely promoting the interests of, and providing business referral, marketing, and business management services to member professionals in the fields of accounting, finance, financial planning, small business management, tax preparation, tax filing, and tax planning; business information and accounting advisory services; business management in the field of bookkeeping and accounting; member benefits program, namely, customer loyalty services for commercial, promotional and/or advertising purposes that provides a variety of amenities to member accounting professionals, computer consultants, tax professionals, and business consultants educational services, namely, conducting classes, seminars, conferences, workshops and webcasts in the fields of computer software, computer hardware, software as a service (SaaS) technology, cloud computing, and mobile computing, and distributing course materials in connection therewith; providing training of accountants, bookkeepers, and business managers for certification in the fields of accounting, business and computer software; educational services, namely, conducting classes, seminars, conferences, workshops and webcasts in the fields of accounting, tax, finance, business, and productivity and distributing course materials in connection therewith; Providing training and educational services in the fields of accounting, tax, finance, business, and computer software; educational services, namely, conducting classes, seminars, conferences, workshops and webcasts in the fields of business development and business management, and distributing course materials in connection therewith
91.
TRANSACTION ENTITY PREDICTION THROUGH LEARNED EMBEDDINGS
Certain aspects of the disclosure pertain to inferring a candidate entity associated with a transaction with a machine learning model. An organization identifier and description associated with a transaction can be received as input. In response, an entity embedding, comprising a vector for each entity of an organization based on the organization identifier, can be retrieved from storage. A machine learning model can be invoked with the entity embedding and description. The machine learning model can be trained to infer a transaction embedding from the description and compute a similarity score between the transaction embedding and each vector of the entity embedding. A candidate entity with a similarity score satisfying a threshold can be identified and returned. The candidate entity with the highest similarity score can be identified in certain aspects.
A method and system are provided for generating a combined prediction using an ensemble machine learning system. The prediction may be used in risk assessment for payroll processing. A data point is received as input to a multitude of trained models. Each model is trained from a respective data subset of a disparate data. A model prediction this generated by each of a multitude of machine learning models. For each respective trained model, a trust score is generated based on a data sparseness metric of the data point and a feature importance vector of the respective model. The model predictions and trust scores are received as input to a meta-model that was trained from the trust score and the model prediction of the multitude of trained models over the respective data subset of the disparate data. A combined prediction is generated using the trained meta-model.
Customizable template-based user interfaces for digital CRM tools. For instance, the CRM tools are pre-loaded with customizable templates, which are rendered as interactive user interfaces that allow customization of the templates based on user needs. This customization therefore allows a user to rapidly, visually, and easily define a customer engagement pipeline and customer segments without any specialized programming knowledge. The user interfaces may dynamically show the flow of customers between different phases and provide recommended actions to further drive customer engagement. Additionally, the CRM tools are integrated with other on-line platforms such as social media sites and e-commerce sites.
G06Q 30/01 - Services de relation avec la clientèle
G06Q 50/00 - Technologies de l’information et de la communication [TIC] spécialement adaptées à la mise en œuvre des procédés d’affaires d’un secteur particulier d’activité économique, p. ex. aux services d’utilité publique ou au tourisme
94.
Automated user experience orchestration using natural language based machine learning techniques
Certain aspects of the present disclosure provide techniques for orchestrating a user experience using natural language input. A user experience is orchestrated within an ecosystem of features for which a plurality of corresponding tokens is defined. Natural language describing a desired user experience result is received by a user experience orchestrator. A sequence of tokens corresponding to operations belonging to an ecosystem of features which produce a correct result for the natural language input can be identified by a trained large language model and executed by the user experience orchestrator using a token operator. The output operations determined by the model to produce or be likely to produce the correct result based on the natural language input can be disambiguated, confirmed, and/or executed.
A system and method that leverage a hybrid bi-directional user experience system that bi-directionally transfers an application session between a first application and a migrated application based on the availability of application features in the migrated application stack.
A method includes receiving a set of execution paths for a directed acyclic graph. The directed acyclic graph includes multiple nodes and multiple edges. The nodes include sets of executable code. The edges represent an operational relationship between at least two nodes. The execution paths include a subset of the nodes connected by a sequence of edges. The method further includes setting a current training level to a maximum training level. The method further includes constructing a transition probability set for the current training level and adding the transition probability set to a transition probability dictionary. The method further includes storing the transition probability dictionary as a final transition probability dictionary.
A system is configured to train a machine learning tree network using path based features, such as leaf nodes or connections between nodes. A first machine learning tree network model, for example, may be trained using a first set of training data, and used to generate predictions for a second set of training data. The path based features are determined from the first machine learning tree network model when generating the predictions for the second set of training data. The path based features may then be used to train a second machine learning tree network model, e.g., using logistic regression.
Augmented Denoising Diffusion Implicit Models (“DDIMs”) using a latent trajectory optimization process can be used for image generation and manipulation using text input and one or more source images to create an output image. Noise bias and textual bias inherent in the model representing the image and text input is corrected by correcting trajectories previously determined by the model at each step of a diffusion inversion process by iterating multiple starts the trajectories to find determine augmented trajectories that minimizes loss at each step. The trajectories can be used to determine an augmented noise vector, enabling use of an augmented DDIM and resulting in more accurate, stable, and responsive text-based image manipulation.
This disclosure relates to systems and methods for providing user content on a social network. In some aspects, the social network receives, over a communications network from a first computing device associated with a first user of the social network, a transmission including a post to be published on the social network. The social network detects, in the post, goods or services sought or inquired about by the first user, and determines a proximity of the first user. The social network identifies one or more other users of the social network located within a geographical area or the proximity associated with the first user, and presents the post only to the one or more identified users of the social network.
H04L 51/222 - Surveillance ou traitement des messages en utilisant des informations de localisation géographique, p. ex. des messages transmis ou reçus à proximité d'un certain lieu ou d'une certaine zone
H04L 51/52 - Messagerie d'utilisateur à utilisateur dans des réseaux à commutation de paquets, transmise selon des protocoles de stockage et de retransmission ou en temps réel, p. ex. courriel pour la prise en charge des services des réseaux sociaux
A system and method implementing K-anonymity processing of a data record to protect sensitive information, while still revealing useful information. The system and method performing K-anonymity processing of categories in the data record, and choosing to mask the data of the category that produces the highest anonymity score. The system and method repeats the process until a K-value of the data record is achieved.
