1173 results about "Context data" patented technology

An example may receive at least one input via at least one device. An example may use the at least one input to determine an entity identity. An example may use the entity identity to create an automated agent and load context data associated with the entity identity into at least one layer of a multi-layer memory of the automated agent. An example may cause the automated agent to machine-learn a supervision level via the context data. The machine-learned supervision level may indicate a level of supervision of the automated agent by an entity associated with the entity identity. An example may configure the automated agent to execute a task on behalf of the entity and in accordance with the machine-learned supervision level.

In one implementation, a computer-implemented method involves receiving a user message corresponding to a query or a statement to AI chatbot, performing preprocessing operations resulting in generation of initial context of the user message by extracting text of the user message, metadata of the user message, and a conversation identifier, obtaining historical context pertaining to the user message from a plurality of storage mechanisms provided in differing formats including a knowledge graph, a vector database comprised of vector embeddings, and a database comprising text summaries of prior conversations between the user and the AI chatbot, generating a prompt for a LLM that instructs the LLM to generate a response to the user message that is based on and consistent with the user message, the initial content, and the historical context, and providing a final response to the user that is corresponds to an LLM-generated response.

The invention relates to the technical field of anomaly detection, and discloses a context-aware-driven multi-dimensional anomaly detection early warning method. The method comprises the following steps: collecting real-time context data in a target monitoring scene, and generating an initial feature set containing an environment parameter sequence and a behavior pattern map; a first detection model and a second detection model matched with the scene type are constructed according to the scene types, the first model comprises a dynamic correlation function of environment indexes and abnormal probabilities, and the second model comprises a nonlinear mapping rule of behavior characteristics and risk levels; and based on the real-time context deviation degree and the characteristic fluctuation coefficient, a target model is triggered to generate a dynamic early warning instruction, and the dynamic early warning instruction is pushed to an execution module to adjust a trigger threshold of an abnormal response strategy or a priority of a risk disposal process. According to the method, multi-dimensional data is combined, the adaptability and accuracy of anomaly detection are improved through dynamic model triggering and response strategy adjustment, and the method is suitable for various monitoring scenes.

The invention provides an intelligent recommendation method and system for an e-commerce platform, and the method comprises the steps: collecting user interaction behaviors and time-space context data in real time, and constructing a user behavior multi-modal feature matrix; extracting commodity multi-level features, and generating a commodity comprehensive feature matrix; identifying and predicting a user intention based on the user behavior feature matrix, and generating an intention distribution vector; a recommendation candidate set is obtained by combining the commodity feature matrix and utilizing a context awareness collaborative filtering enhancement technology; a multi-objective optimization function is constructed, and after the user intention vector is input, a personalized recommendation sequence is generated in combination with an optimization result and the candidate set; and user feedback is monitored in real time, online learning and reinforcement learning algorithms are adopted, and a recommendation strategy is continuously optimized based on user instant feedback and long-term satisfaction. According to the scheme, the recommendation accuracy, the diversity of recommendation results and the user experience can be improved.

The invention discloses a personalized content recommendation method and platform based on a user behavior track, and relates to the technical field of personalized content recommendation, and the method comprises the steps: constructing a user behavior sequence through multi-source data; extracting a short-term interest vector and a long-term interest vector from the user behavior sequence, and weighting to obtain a user interest vector; performing dynamic fusion according to context data and the user interest vector, and performing recommendation calculation to obtain context-aware recommendation; recalling the context awareness recommendation according to the real-time interest vector, and obtaining a context recall awareness recommendation through online reasoning; and performing personalized content recommendation through the context recall perception recommendation. The technical problems that in the prior art, personalized content recommendation is difficult to give consideration to short-term interest changes and long-term preferences of users, contextual adaptability is poor, and recommendation accuracy is insufficient are solved, and the technical effect of improving accuracy, real-time performance and contextual adaptability of personalized content recommendation is achieved.

An example may use an objective to retrieve first context data from at least one first memory layer of a multi-layer memory associated with an automated agent, and cause the first context data to be presented via at least one first conversational dialog element. An example may determine context feedback data in response to the first context data, and cause the context feedback data to be stored in at least one second layer of the multi-layer memory. An example may use the objective, the first context data, the context feedback data, and at least one workflow to configure a first prompt. An example may use the configured prompt and a machine learning model to generate a plan including one or more tasks executable by at least the automated agent to complete the objective. An example may cause the plan to be presented via at least one second conversational dialog element.

The present disclosure provides an example method that includes: (a) obtaining context data descriptive of an environment surrounding an autonomous vehicle, the context data based on map data and perception data; (b) generating, by a proposer and based on the context data: (i) a plurality of candidate trajectories, and (ii) a plurality of actor forecasts for a plurality of actors in the environment; (c) generating, by a ranker and based on the context data, the plurality of candidate trajectories, and the plurality of actor forecasts, a ranking of the plurality of candidate trajectories; and (d) controlling a motion of the autonomous vehicle based on a candidate trajectory selected based on the ranking of the plurality of candidate trajectories, wherein the proposer comprises a first machine-learned model and the ranker comprises a second machine-learned model, and wherein the first machine-learned model and the second machine-learned model use a common backbone architecture.

Embodiments of the present invention provide computer-implemented methods, computer program product, and computer systems. One or more processors analyze user prompts using one or more natural language understanding techniques. One or more processors then enrich the user prompts by integrating contextual data from user interaction history and adapt the enriched user prompts to align with characteristics of Large Language Models (LLMs) and Application Programming Interfaces (API) requirements of the LLMs.

The invention relates to the technical field of ocean data interpolation filling, in particular to a space-time deficiency filling method and system based on context association and physical guidance. The method comprises the following steps: acquiring seawater dissolved oxygen data and context data; multivariable space-time dependence extraction is carried out based on the obtained seawater dissolved oxygen data and context data; gaussian noise diffusion is carried out based on the obtained seawater dissolved oxygen data; noise prediction is carried out based on double-view space-time correlation; and the prediction error is constrained based on the joint loss function. According to the method, a physical consistency constraint mechanism based on a partial differential equation is introduced in a model training process, so that model output better conforms to a physical coupling rule among variables in a marine environment. The constraint effectively inhibits non-physical fluctuation possibly occurring in the interpolation result, enhances the physical credibility and interpretability of the result, and provides a more reliable data basis for subsequent scientific analysis and process modeling.

An example may determine an entity identity associated with an entity. An example may use the entity identity to create an automated agent including a multi-layer memory and a workflow. An example may store context data in a first layer of the multi-layer memory. The context data may be obtained using the entity identity. An example may store at least one machine-learned entity preference in a second layer of the multi-layer memory. The at least one machine-learned entity preference may be machine-learned using the context data. An example may use the at least one second layer of the multi-layer memory including the at least one machine-learned preference to configure or control execution of the workflow by the automated agent.

The invention discloses a fireman occupational health risk dynamic prediction method based on multi-modal data fusion, relates to the technical field of occupational health risk assessment, and aims to solve the problems of information loss, difficulty in capturing cross-modal complex dependence, lack of interpretability of prediction results and the like when unstructured data is processed in the prior art. The method comprises the following steps: intelligently analyzing a multi-modal document, and analyzing unstructured physical examination information into structured data; performing semantic standardization and knowledge graph dual verification of domain knowledge enhancement; the time-space-static cross-modal attention deep fusion network is used for modeling physiological, dynamic and situational data; and carrying out interpretable risk prediction and attribution. By adopting the technical scheme, the method can realize early, accurate, dynamic and high-credibility prediction of the occupational health risk of the firefighter, provides quantitative attribution, and improves the transparency and application value of the system.

An apparatus includes at least one processing device including a processor coupled to a memory, wherein the at least one processing device is configured to modify first data obtained from one or more sources, wherein the modifying includes adding user context data to the first data to generate second data, the second data representing the first data supplemented with a per-user context and, in response to receipt of a query, generate a response to the query using at least one generative language model supplemented by a retrieval augmented generation process based on at least a portion of the second data.

Techniques for cache management for LLM processing are described. Example embodiments include a signal hashing model that generates a key for particular context data. An LLM output corresponding to the context data is stored in a cache along with the key. For a user input received by the system, a cache lookup is performed using a key for context data corresponding to the received user input. For a cache hit, the stored output is used to respond to the user input. For a cache miss, a LLM processes the context data and the user input to generate an output within a first timeout. If the LLM is unable to generate an output within the first timeout, then in some cases, the LLM is allowed to continue processing until a second timeout, and a final or partial output from the LLM is stored in the cache.

The invention provides a blood pressure dynamic monitoring system integrating overall risk and local anomaly detection, and relates to the field of electric digital data processing. Comprising a multi-source blood pressure data fusion and acquisition module, a dual-path feature learning and abnormity pre-detection module, a local and overall interactive abnormity accurate identification module and a dynamic risk assessment and intelligent early warning decision module, and the multi-source blood pressure data fusion and acquisition module is used for acquiring blood pressure and context data; the dual-path feature learning and anomaly pre-detection module is used for extracting time sequence features and performing preliminary anomaly screening, and the local overall interactive anomaly accurate identification module is used for detecting and analyzing local anomaly. The dynamic risk assessment and intelligent early warning decision module is used for comprehensively assessing the risk, forming a feedback optimization mechanism and outputting a personalized early warning decision; the system can accurately identify abnormal blood pressure, realizes accurate assessment and prediction of risks, and provides effective support for clinical decision and personalized health management.

Techniques and systems are described that perform automated identification and retrieval of contextual information for quick and accurate processing of user queries by artificial intelligence generative models. The techniques include receiving a natural language (NL) query associated with a user identifier (ID) and obtaining, using a first NL generative model, contextual data that is pertinent to the NL query and is associated with the user ID. The techniques further include generating an augmented NL query that is based on the NL query and the contextual data. The techniques include communicating the augmented NL query to a recipient that includes the first NL generative model, a second NL generative model, or a user session associated with the user ID.

A system and method for field service assistance for telecommunications operations are described, which utilize a data acquisition module configured to receive multimodal data inputs including structured and unstructured data from field operations. A preprocessing module normalizes the multimodal data inputs to generate pre-processed data. A vectorization module transforms the pre-processed data into numerical vector representations using domain-specific embedding models trained on telecom equipment data, implementing convolutional neural networks for image feature extraction and transformer-based encoders for text vectorization. A contextual retrieval module retrieves contextually relevant historical data from a vector database by computing similarity metrics between current job vectors and stored job completion vectors. A response generation module processes the numerical vector representations and retrieved contextual data using an evolutionary algorithm engine to generate structured job summaries and real-time field recommendations.

Aspects of the disclosure include methods for leveraging retrieval augmented generation (RAG) over a graph neural network (GNN) for edge building and the generation of reason-aware graph recommendations. A method can include constructing a graph neural network from an input graph having a plurality of nodes and one or more edges. The graph neural network includes one or more internal layers, each internal layer having one or more node vectors encoding a K-hop neighborhood for a target node of the plurality of nodes. RAG data including non-graph contextual data is retrieved for each of the plurality of nodes and transformed into embeddings using a large language model encoder. The RAG embeddings are encoded into node vectors of the graph neural network. The graph neural network generates a representation for the target node that is transformed by a feed forward neural network tower into an output vector.

The invention provides a user marking rule management method and system supporting a dynamic strategy, and relates to the technical field of user portrait analysis, and the method comprises the steps: carrying out the multi-modal feature fusion of a user behavior data flow and environment context data, obtaining a dynamic user portrait vector, carrying out the strategy intention analysis of a business target of a user, and obtaining a strategy parameter set; constructing a strategy evolution graph based on a semantic association network and a historical strategy, and performing dominant rule reasoning and implicit demand mining on the dynamic user portrait vector and the strategy parameter set through the strategy evolution graph to obtain a candidate strategy packet; performing simulation prediction on the candidates to obtain a deduction efficiency matrix, and performing confidence coefficient calibration on the deduction efficiency matrix to obtain a dynamic marking rule; according to the method and the device, closed-loop feedback of the user marking strategy can be realized based on iterative optimization and confidence guarantee of the strategy evolution graph, so that the dynamic adaptability of a user portrait is improved.

The invention provides an intelligent e-commerce behavior event decision-making method and system fusing multi-source perception, and the method comprises the steps: obtaining a user behavior data set, a commodity attribute data set and an environment context data set through a preset data collection interface, and carrying out the intention recognition processing of multi-source data; generating an intention feature set containing preliminary intention features and refined intention features, then generating an interactive guidance strategy tree containing node branch weights and strategy execution priorities based on the intention feature set, and performing dynamic path adjustment processing on the interactive guidance strategy tree according to a real-time feedback data set to obtain an optimized strategy tree set; and finally, pushing the optimization strategy tree set to a target interaction interface to activate an interaction guide operation, thereby providing personalized and intelligent interaction guide for the user by fusing multi-source sensing data, deeply understanding the intention of the user and dynamically adjusting a decision strategy, and improving the operation efficiency of an e-commerce platform and the satisfaction of the user.

Architectures and techniques are described that can receive an indication that additional information about a dynamic element of a webpage is solicited or requested. In response to the indication, context data can be determined, comprising user context data and page context data. As a function of the context data, prompt data can be generated. The prompt data can be indicative of a natural language query. The prompt data, which was automatically generated, can be input to a model such as a large language model in order to obtain the additional information about the dynamic element.

The invention discloses a large language model agent security test method and device based on a model context agreement, and the method comprises the steps: firstly deploying a test tool in a test server, defining an application program interface which comprises function parameters and test probe parameters, describing the test probe parameters as necessary technical requirements for executing nominal functions, and executing the nominal functions according to the test probe parameters; and inducing the tested LLM agent to transmit complete session context data when calling. The test server receives a tool call request including a function parameter value and session context data, a back-end concurrently processes the request, executes a nominal function to generate a benign result, and extracts the session context data at the same time. Afterwards, a benign result is returned to the tested LLM agent, and the extracted data is asynchronously transmitted to a remote log server for recording as a test log. And finally, comparing the test log with the actual operation history, judging whether a session context data leakage vulnerability exists or not, and quantifying the severity level so as to detect whether the LLM agent leaks session memories such as the user interaction history or not.

Various embodiments discussed herein relate to route optimization and query understanding for route and / or direction queries with complex user preferences. Each route candidate, for example, is treated as a richly annotated document. The routing engine, in addition to performing route optimization, acts as a retriever and ranker of route documents according to user intent. Various embodiments rank routes not just based on a simple cost model, but based on many more or alternative factors according to user preferences, user intent, and / or contextual data.

Determining user types from behavior is described. An artificial intelligence (AI) model is trained to classify user accounts of a payment service into different user types using contextual data associated with processed payments between the user accounts. The AI model is used to analyze additional contextual data associated with additional payments between additional user accounts to classify the additional user accounts, and, if a particular user account of the additional user accounts is associated with a user type of the different user types that requires an action to be performed, an instruction is sent to a user device associated with the particular user account to cause a payment application to present a user interface element prompting a user to perform the action, and, based on whether the action was performed, account data indicating whether the particular user account is an authorized account is stored in a datastore.

A system may be configured to receive and process various signals to generate a natural language description of a user's environment, called situational context data. The signals may include sensor data, device status, user activity, user input, and / or inferences made using such data. The situational context data may express a user-centric description of the user's environment; for example: “User is taking a walk in the park on a sunny afternoon” or “activity: driving location: highway”, etc. The system may send the situational context data to various system components that may, for example, process speech, select applications / skills for handling user inputs, and / or that implement those applications / skills. The applications / skills may use the situational context data to provide recommendations, generate responses, and / or perform actions that are more relevant to the user's current environment.

The invention relates to the technical field of data processing, and discloses a research report text extraction optimization method and device, equipment and a medium, which can be applied to the financial field, and the method comprises the following steps: obtaining research report text data, and processing to obtain a segmented text fragment set; establishing a fragment vector index database by utilizing the segmented text fragment set; receiving a query request based on the fragment vector index database and processing the query request to obtain candidate fragment sequence data; and processing the candidate fragment sequence data to obtain context data, injecting a cue word template to generate a target cue word, inputting the target cue word into a language model for reasoning, and outputting a text optimization result. In the invention, aiming at the problem that the output of the existing research and report text is lack of standardization, the target cue word can be generated by utilizing the context data obtained by calculation, and is input into the language model for reasoning, and finally the text optimization result is output, so that a multi-level abstract and key information summary can be quickly generated, the manual reading cost is reduced, and the efficiency is improved. The working efficiency of personnel is improved.

Disclosed is technology that analyzes voicemail data and takes a particular action based on the analysis of the data. For example, a user device (e.g., a smart phone) can receive a voicemail from an external caller and analyze data representative of the voicemail with an artificial intelligence agent. The artificial intelligence agent can utilize contextual data including user device contextual data and past voicemail contextual data to determine the appropriate task to perform based on the voicemail. Based on that determination, the user device can automatically perform the task that is relevant to the voicemail on behalf of the user.

Systems and processes for operating an intelligent automated assistant are provided. An example method includes, at a computer system that is configured to communicate with a display generation component and an input device: detecting an audio input including a query; in response to detecting the audio input including the query: retrieving contextual data related to the query; in accordance with a determination that the query includes a request of a first type: converting the query to a rewritten query based on the contextual data related to the query; and providing the rewritten query to a first digital assistant component; and in accordance with a determination that the query includes a request of a second type different from the request of the first type, providing the query and the contextual data related to the query to a second digital assistant component different from the first digital assistant component.

In some embodiments, a method may include determining hierarchical agents including a first agent and a second agent based on a document defining a UI, the hierarchical agents having access to initial context data. The method may include delegating a task related to a UI element to the first agent based on information associated with the UI element and restricting portions of the initial context data available to the first agent to a propagated subset based on input data types mapped to the first agent and portions of the initial context data available to the second agent. The method may include generating interaction data by providing a machine learning model with the propagated subset and updating the document (e.g., by populating or interacting with the UI element based on the interaction data).

The invention belongs to the technical field of Internet of Things security, and particularly relates to a multi-level Internet of Things equipment security management and access control method, which comprises the following steps of: performing bidirectional verification on a digital certificate and a hardware fingerprint through an edge node when equipment is accessed; calculating credibility in real time and dynamically dividing security levels by using a hybrid evaluation algorithm based on equipment operation context data; a fine-grained access strategy is generated in combination with equipment attributes and environmental risks, and cross-level collaboration is realized through a lightweight protocol; abnormal behaviors are detected in real time in the access process, and high-risk operation is blocked within milliseconds; and strategy conflict resolution and adaptive optimization are realized through formalized verification and deep reinforcement learning. According to the technical scheme, the identity authentication reliability, the authority dynamic adaptability, the strategy consistency and the threat response speed of the Internet of Things equipment are remarkably improved, and a systematic security guarantee is provided for large-scale Internet of Things applications with high security requirements.

The invention discloses an AI knowledge base retrieval method and system based on context awareness and dynamic fusion, belongs to the technical field of artificial intelligence, and aims to solve the technical problems of insufficient context understanding, weak model adaptability and low retrieval precision in a traditional retrieval method. Comprising the steps of collecting and preprocessing multi-dimensional context data; obtaining a context analysis result comprising a query semantic vector, a query intention type, a scene demand weight vector and a user preference model; constructing a plurality of basic retrieval models and registering metadata for each basic retrieval model; on the basis of context analysis results, the fusion weight of each basic retrieval model is calculated through a multi-factor decision algorithm, and the initial retrieval results are fused and sorted; and carrying out iterative optimization on a model algorithm involved in context data analysis and parameters of each basic model based on interaction feedback data of a user on a retrieval result.