401 results about "System usage" patented technology

A computer system implements a unified framework integrating an adaptive elastic funnel (AEF) with a convergent intelligence fabric (CIF) for multi-agent AI collaboration. The system provides a universal multi-modal key-value subsystem for sharing partial computations, implements hybrid placement strategies for dynamic memory management, and incorporates quantum-resistant secure enclaves. The architecture integrates hardware acceleration through GPU-FPGA hybrid caching and neuromorphic processors, applies adaptive energy and thermal management across hardware generations, and implements autonomous flash resource orchestration with multi-dimensional wear management. The system orchestrates tensor workflows using hierarchical scheduling, enables cross-agent collaboration with privacy preservation, and supports continuous learning without catastrophic forgetting. This integration delivers unprecedented computational efficiency and security in high-dimensional decision-making environments while supporting incremental adoption through modular interfaces.

The present invention discloses a system and method for secure artificial intelligence-based financial technology governance and risk management, designed to provide real-time, autonomous, and verifiable compliance assurance within digital financial ecosystems. The invention integrates a secure artificial intelligence processing unit, a governance control processor, a cryptographically anchored storage unit, a federated learning coordination processor, and a quantum-resistant communication interface enclosed within a tamper-proof hardware structure. The system performs encrypted machine learning computations on financial transaction data using homomorphic encryption and trusted execution environments to preserve confidentiality during analysis. It computes a governance risk index based on probabilistic inference and anomaly detection to identify regulatory deviations, applies adaptive compliance reasoning across multi-jurisdictional frameworks, and automatically enforces governance actions through secure decision logic.

Systems and methods disclosed herein automatically authorize, audit, and manage usage of protected digital content via agentic artificial intelligence (AI) models. A data access / usage request is received (e.g., from a graphical user interface) that is associated with digital assets licensed from third parties. The system uses a first AI agent set to identify the digital content and retrieve corresponding access policies from a distributed database. The system uses a second AI agent set (same as or different from the first AI agent set) to evaluate the request against the retrieved policy to generate a permission set and / or settlement instructions. The system uses a third AI agent set (same as or different from the first and / or second AI agent sets) to embed digital watermarks and / or cryptographic signatures into the accessed content, and to record an audit trail of access, authorization, and / or settlement events in a distributed ledger or database.

A device may provide a prompt to a first machine learning model. The prompt may include at least one instruction to cause the first machine learning model to use at least first natural language input associated with a use of a conversational search system to rank data sources, generate a first search query and reasoning, and use the first search query and the reasoning to generate a second search query. The first search query may include data obtained from at least one of the ranked data sources. The reasoning may include an explanation of how the first machine learning model generated the first search query. A second machine learning model may synthesize a response determined via execution of the second search query. The synthesized response may be provided for presentation via the conversational search system.

Systems and methods disclosed herein automatically register, monitor, and authenticate distributed artificial intelligence (AI) agents and their operational contexts using a distributed or federated ledger-based agent knowledge registry. The system obtains a registration or query request (e.g., from an AI agent, orchestrator, or user interface) to identify or store operational context linked to each AI-based agent. The system determines a feature set of agent metadata and operational parameters using a first AI model set, and dynamically generates a cryptographically verifiable registry record set using a second AI model set (same as or different from the first AI model set) based on the operational feature set, to be stored in a distributed ledger database. The system automatically executes registry updating, agent selection, or operational verification workflows using a third AI model set (same as or different from the first and / or second AI model sets) to maintain records that trace inter-agent interactions.

Systems and methods for interfacing with data profilers using a machine learning model. In some aspects, the system receives a data profiler configured to create and interface with a plurality of data profiles. The system trains a profile query model to generate responses to user queries relating to data profiles. The system receives a user query concerning data profiles associated with the data profiler. Using an interpretation model, the system pre-processes the user query and data profile attributes to determine an activation pattern for the profile query model. The system uses the profile query model to process the user query and the data profile attributes of the data profiler and generate a preliminary response. The system post-processes the preliminary response to generate a verified response by applying a corrective program. The system then transmits the verified response in a conversational program related to the user query.

The present disclosure relates to systems, non-transitory computer-readable media, and methods for generating modifications to an LLM based artificial intelligence assistant based on classifying the severity of errors and focusing the modifications on resolving high-severity errors. In particular, the disclosed systems receive prompts via an artificial intelligence assistant graphical user interface and generate responses to the prompts using the LLM based artificial intelligence assistant. Further, the disclosed systems determine errors in the responses using an annotation tool to generate annotated errors and an error analysis mechanism to generate indications of the errors based on the annotated errors. Additionally, the disclosed systems classify the errors as one of high-severity, mid-severity, or low-severity. Moreover, the disclosed systems generate modifications to components of the LLM based artificial intelligence assistant based on the high-severity errors.

Disclosed embodiments provide techniques for computerized moderation, authorship recording, and distribution of social media content. Moderator-supplied tags are associated with content and supplied to a machine learning system as training data. Using blockchain, authorship is authenticated and can be converted from anonymous to non-anonymous. Collaboration among authors on content is supported with authorship lists that can contain a mix of anonymous and non-anonymous authors. Contribution limits are established to determine royalty payments for sale and rent of content.

Disclosed herein are systems and methods for cross-domain training of sensing-system-model instances. In an embodiment, a system receives, via a first application programming interface (API), an input-dataset selection identifying an input dataset, which includes a plurality of dataframes that are in a first dataframe format and that have annotations corresponding to one or more sensing tasks performed with respect to the dataframes. The system executes a plurality of dataframe-transformation functions to convert the plurality of dataframes of the input dataset into a predetermined dataframe format. The system trains an instance of a first machine-learning model using the converted dataframes of the input dataset to perform at least a subset of the one or more sensing tasks. The system outputs, via the first API, one or more model-validation metrics pertaining to the training of the instance of the first machine-learning model.

The invention provides a lightweight configurable cue word labeling method and system for a Web system, and relates to the technical field of Web front-end development and man-machine interaction, and the system comprises a front-end labeling plug-in module, a cue word content service module, a cue word management module and an intelligent recommendation module. The front-end labeling plug-in captures text content selected by the user by monitoring a global shortcut key, and allows the user to add prompt words of a text, a rich text or a link type; the prompt word content service module provides an API (Application Program Interface) to realize persistent storage of data; the prompt word management module provides a unified management interface for an administrator; and the intelligent recommendation module automatically judges the prompt word display priority through a candidate recall and sorting algorithm based on the user click behavior data, and continuously optimizes the recommendation result by using an online learning mechanism. The method is integrated to an existing Web system in a non-intrusive mode, business core codes do not need to be modified, the use threshold of the system is remarkably lowered, and precipitation and sharing of business knowledge are promoted.

In accordance with the described techniques, a system receives a plurality of facets describing language-agnostic aspects of language translation, a translation document describing language-specific rules for translating from a source language to a target language, and a source text in the source language. Using one or more machine learning models, a plurality of guidelines are extracted from the translation document and assigned to respective facets of the plurality of facets. The system translates the source text to a translated text in the target language using one or more machine learning models conditioned on the plurality of guidelines assigned to the respective facets.

A system generates data modification operators that reduce bias or distortions in artificial intelligence (AI) models. The system uses a first artificial intelligence (AI) model to generate outputs based on a set of corresponding inputs to the first AI model. First measurement values of one or more model output metrics in the outputs generated by the first AI model are received. Based on the first measurement values, the system generates a set of data modification operators that specifies one or more operations for modifying inputs to a second AI model. Inputs to the second AI model can be modified using the set of data modification operators to generate a modified set of corresponding inputs. The second AI model can then be applied to the modified set of corresponding inputs to the second AI model.

A system and method for generating structured software application specifications through multi-phase conversational dialogue is disclosed. The system implements multiple specialized AI agents including a framework generation agent, an interactive coaching agent, specialized capsule agents for analyzing different concern categories, and a specification coaching agent. During Phase 1, the system conducts exploratory dialogue using a tailored question framework while detecting and storing user concerns in structured capsule entries. Concern injection into the dialogue is strategically timed based on algorithmic evaluation of cooldown periods and user sentiment analysis. During Phase 2, the system conducts comprehensive concern resolution dialogue and generates a final specification in structured JSON format with explicit traceability linking requirements to source conversations and concern resolutions. The system solves technical problems of preserving concern context across conversation phases, optimizing injection timing to avoid overwhelming users, and generating machine-readable specifications suitable for automated downstream processing.

An artificial intelligence-based system and method facilitate enhanced interaction between users and mechanical devices such as vehicles. One system uses an application equipped with AI algorithms to process user inputs concerning specific vehicle information and issues, providing tailored recommendations and feedback. This includes automated troubleshooting, parts recommendations, and maintenance advice, aiming to improve user experience and vehicle upkeep efficiency.

A system and method are disclosed for interfacing with one or more databases using natural-language queries. The system translates a natural-language input into an intermediate formal representation, such as a Concept Query Language (CQL), which references domain concepts rather than database-specific structures. A data access subsystem maps these domain concepts to database-specific queries using a domain dictionary, enabling seamless translation across heterogeneous databases and database management systems (DBMSs). The system supports distributed data retrieval, error recovery, and dynamic query planning. A presentation subsystem formats the results into user-friendly outputs such as charts or tables. The architecture allows for modular grammar and dictionary configuration, enabling rapid adaptation to new domains, schemas, or user roles without procedural code changes. This approach improves accessibility, maintainability, and scalability of database interactions by abstracting technical complexity from end users.

In some embodiments, a system transforms an initial user query into a first rewritten query using a first query rewriting algorithm, executes a search of a data repository using the first rewritten query to generate a set of results, executes a chunking process on the set of results to generate chunks of data, transforms the initial user query into a second rewritten query using a second query rewriting algorithm, generates corresponding embeddings for the second rewritten query and the chunks of data using a reranking model, selects a subset of the chunks of data based on a comparison of the embeddings for the chunks of data and the embedding for the initial user query, generates a prompt based on the initial user query and the subset of the chunks of data, submits the prompt to a Large Language Model (LLM) to generate a response to the initial user query.

Techniques for a knowledge-graph system to use large language models (LLMs) to build knowledge graphs to answer queries submitted to a chatbot by users. The knowledge-graph system builds the knowledge graph using answers produced by an LLM for novel queries. The chatbot will continue to use the LLM to answer novel queries, but the chatbot may harness the knowledge graph to answer repeat questions to gain various efficiencies over LLM-backed chatbots. For example, the knowledge-graph system may easily debug or otherwise improve the answers in knowledge graphs, store provenance information in knowledge graphs, and augment the knowledge graphs using other data sources. Thus, the reliability and correctness of chatbots will be improved as the bugs and inaccuracies in answers provided by the LLM will be corrected in the knowledge graphs, but the chatbots can still harness the abilities of LLMs to provide answers across various subject-matter domains.

An XR system is provided that enhances user interaction within an extended reality environment by capturing tracking data of a user's hands using one or more sensors. The XR system uses this data to generate a system control user interface that includes interactive virtual objects positioned on a first hand of the user, which the user can interact with using a digit of a second hand. The system control user interface is displayed directly to the user. Upon detecting a system control input from the user, the XR system generates and displays a system function user interface that includes further interactive virtual objects for accessing various system functions. These interfaces are displayed simultaneously yet separately within the user's field of view.

Systems, methods, and devices that relate to generation of responses to query sets are disclosed. In one example aspect, the system uses multiple models to retrieve data relevant to queries and appropriate for the requesting user and to output the data in a certain style. In particular, the system uses a first model to determine a type of user submitting a query, a second model to retrieve data relevant to the query, subject to constraints based on the type of user, and a third model to formulate a response to the query, based on the retrieved data, using a consistent style. In some implementations, another model enables certain users to validate the outputs from one or more of the first, second, and third models. The system can output a compilation of the responses to the queries in a particular manner, style, or presentation that is consistent across all outputs.

Techniques for assessing security risk at scale for a computing environment are disclosed. In an example method, a computing system accesses a risk model specified for a computing environment including at least a set of individual risk factors, a set of composite risk factors, and a final composite function for computing an overall risk score. The computing system receives a set of one or more inputs. The computing system computes an individual risk score for each individual risk factor using at least one input. The computing system computes a composite risk score for each composite risk factor. The computing system computes the overall risk score using the final composite function using at least two composite risk scores and outputs the overall risk score.

An online concierge system uses a model to predict a user's interaction with an item, based on a user embedding for the user and an item embedding for the item. For the model to account for more recent interactions by users with items without retraining the model, the online concierge system generates updated item embeddings and updated user embeddings that account for the recent interactions by users with items. The online concierge system compares performance of the model using the updated item embeddings and the updated user embeddings relative to performance of the model using the existing item embeddings and user embeddings. If the performance of the model decreases, the online concierge system adjusts the updated user embeddings and the updated item embeddings based on the change in performance of the model. The adjusted updated user embeddings and adjusted updated item embeddings are stored for use by the model.

The present disclosure relates to a multidimensional adaptive sensing system and method for event detection with improved accuracy. The system dynamically adjusts, using baseline and compound models, a triggering conditional threshold of each event based on real-time variations in environmental parameters and sensor health. The adaptive system allows for fine-tuning of sensitivity to environmental changes, seasonal variations, and sensor decay, thereby reducing false positives and negatives. Installation flexibility is achieved by selecting and deploying a subset of models tailored to available data at the sensor's location, ensuring optimal operation regardless of specific environmental conditions or sensor configurations. The adaptive sensing system is used in environmental control systems for dynamic routine management, sensor health management, a triage system for complex event analysis, and multifaceted compliance assurance solution. Further, the adaptive sensing system is used for automated configuration, model deployment, and maintenance by leveraging edge computing units and a central control unit.

Systems and methods disclosed herein automatically authorize, audit, and manage usage of protected digital content via agentic artificial intelligence (AI) models. A data access / usage request is received (e.g., from a graphical user interface) that is associated with digital assets licensed from third parties. The system uses a first AI agent set to identify the digital content and retrieve corresponding access policies from a distributed database. The system uses a second AI agent set (same as or different from the first AI agent set) to evaluate the request against the retrieved policy to generate a permission set and / or settlement instructions. The system uses a third AI agent set (same as or different from the first and / or second AI agent sets) to embed digital watermarks and / or cryptographic signatures into the accessed content, and to record an audit trail of access, authorization, and / or settlement events in a distributed ledger or database.

A system may be configured to train an artificial intelligence model (AI model). For example, the system, using a training framework with both a teacher layer and a student layer provides target outputs from the teacher layer, while the student layer learns to approximate these outputs. The system may obtain input data and, using the training framework, train the AI model using the input data. For example, the training framework defines a quantizer with clipping and rounding functions to convert full-precision data to quantized data. The framework calculates a first output distribution from the teacher layer and a second output distribution from the student layer. A training loss is computed between these distributions, and parameters of the quantized network are adjusted to minimize discretization error and prediction discrepancy. The trained quantized network is then used to generate new predictive outputs from the AI model.

Systems and methods for bias testing and remediation are disclosed. Decentralized Web Application Testing Systems use a Holochain framework to distribute testing workloads across Full Nodes and Lightning Nodes. A Holochain Node Management Application for configuring nodes, a UI Application creates test cases, and a Version Management System tracks changes. Test results are stored and analyzed in a Test Result Store, with a Bias Intelligence module detecting biases and generating additional test cases. A Consensus Algorithm validates test cases through decentralized nomination. An AI-Driven Defect Remediation System automates defect detection, root cause analysis, and remediation using AI modules. Machine learning algorithms identify patterns and anomalies, while NLP techniques generate code fixes. Predictive maintenance monitors application performance to preemptively address issues. A feedback loop mechanism continuously improves AI models through reinforcement learning. Together, these systems provide a holistic approach to web application testing and maintenance.

Embodiments of the present disclosure provide a system for automatically generating design rule checking (DRC) code for a design rule. The DRC code is generated using a first large-language model (LLM) agent and a second LLM agent. The first LLM agent generates a plurality of design rule conditions based on a multi-modal description of the design rule. The second LLM agent generates executable DRC code based on the plurality of design rule conditions. The executable DRC code is executed on example layouts to generate corresponding outputs. The executable DRC code is evaluated by comparing the outputs with corresponding reference outputs. The executable DRC code is iteratively regenerated based on the evaluation, where the evaluation includes providing a performance report to the first LLM agent and / or to the second LLM agent.

An intelligent router for generative artificial intelligence (GAI) model instances optimizes request routing to reduce latency. The system predicts output lengths using a trained response-length predictor and assesses the state of multiple GAI instances, including prompt and decode distributions. It estimates the workload mixing impact of routing requests to each instance and determines selection probabilities using a machine-learning routing model. The router either assigns the request to the most suitable instance or delays routing if conditions are suboptimal. This approach improves end-to-end latency, Time-To-First-Token (TTFT), and Time-Between-Tokens (TBT) by considering the distinct characteristics of GAI workload phases.

The present disclosure relates to systems, methods, and non-transitory computer-readable media that modify digital files in accordance with user requests. For instance, in some cases, the disclosed systems receive, from a client device, a user request for modifying a digital file. The disclosed systems generate, using a language machine learning model, a task plan having formatted code indicating one or more application programming interface calls to execute to modify the digital file. Further, the disclosed systems generate, via one or more code verifications on the formatted code, an error log that identifies one or more errors in the task plan. The disclosed systems generate, from the error log and using the language machine learning model, a corrected task plan that corrects the one or more errors. Additionally, the disclosed systems provide, for display, a modified digital file generated through execution of the corrected task plan.

Methods, systems, and apparatus, including computer-readable media, for artificial intelligence techniques to create or update data models. In some implementations, the system stores records describing each of a plurality of different functions that can be performed in a data processing system. The system receives a user prompt that indicates a type of data object to be created. The system selects records for a subset of the functions based on the user prompt. The system sends a request to be processed by one or more artificial intelligence and / or machine learning (AI / ML) models. The system receives output of the one or more AI / ML models that defines an additional data object. The system uses the output of the one or more AI / ML models to cause a user interface to be updated or to update a data model.

A system for automated account interaction receives historical information associated with an account corresponding to a user. The historical information identifies a transaction involving the account. The system uses one or more trained machine learning models to identify an intent for the transaction at least in part by inputting the historical information to the trained machine learning models. The system uses the trained machine learning models to generate a recommended transaction at least in part by inputting the intent for the transaction to the trained machine learning models. The system outputs the recommended transaction and receives a confirmation regarding the recommended transaction.