161 results about "Context management" patented technology

The disclosure presents a multi-agent AI system utilizing specialized Large Language Models (LLMs) to automate and enhance software development workflows. This system integrates a memory-augmented generative pre-trained transformer (MemGPT) agent for dynamic context management, a Critic Agent for semi-adversarial quality feedback, and other specialized agents for task delegation and execution. The MemGPT agent interacts with an embedding storage to manage extended contextual information, enabling the system to handle complex software projects with enhanced accuracy and efficiency. This innovative approach significantly reduces manual intervention, streamlines the development process, and improves software quality, offering a robust solution to the challenges of modern software development environments.

A distributed generative artificial intelligence (AI) reasoning and action platform that utilizes a cloud-based computing architecture for neuro-symbolic reasoning. The platform comprises systems for distributed computation, curation, marketplace integration, and context management. A distributed computational graph (DCG) orchestrates complex workflows for building and deploying generative AI models, incorporating expert judgment and external data sources. A context computing system aggregates contextual data, while a curation system provides curated responses from trained models. Marketplaces offer data, algorithms, and expert judgment for purchase or integration. The platform enables enterprises to construct user-defined workflows and incorporate trained models into their business processes, leveraging enterprise-specific knowledge. The platform facilitates flexible and scalable integration of machine learning models into software applications, supported by a dynamic and adaptive DCG architecture.

The invention discloses a network data intelligent tool system and method based on a model context protocol MCP, and relates to the technical field of computer networks. The system comprises an AI analysis main body, an MCP Pcap tool engine, context management, a Pcap data source, various MCP Pcap tools, a Pcap tool gateway interface, a Pcap tool interface and a data packet interface. The invention provides an interaction mechanism of direct embedding and bypass data forwarding in tool calling. According to the method, direct embedded transmission of small-size data in tool calling is supported, separation of data transmission and instruction calling is achieved, the technical bottleneck that large-size Pcap data cannot be efficiently exchanged through a text channel is effectively overcome, efficient processing of the AI model on network packet capture data is achieved, and the data transmission efficiency is improved. And the efficiency and the automation degree of large-scale network traffic analysis are improved.

The invention discloses a method for supporting fast switching of multiple models by NPU (Network Processing Unit) firmware. According to the invention, the system real-time performance and the resource utilization rate in a multi-task scene are obviously improved. Through a dynamic hierarchical caching strategy and a priority scheduling mechanism, the system can intelligently allocate cache resources and preferentially guarantee rapid loading of a high-frequency and high-urgency model, for example, in an automatic driving scene, switching delay of a path planning model can be reduced to a millisecond level, and non-perceptual switching of key tasks is guaranteed. The incremental parameter loading technology and firmware-level context management are deeply fused, only model difference data are transmitted, and hardware is utilized to accelerate and recover a calculation state, so that bandwidth waste caused by traditional full-amount loading is greatly reduced, the model switching efficiency of edge computing equipment is improved by more than 10 times when multiple tasks such as voice recognition and image processing are carried out in parallel, and the efficiency of the edge computing equipment is improved. And meanwhile, the calculation precision is kept lossless.

An auditory operating system designed to facilitate context-aware, audio-based user interactions, particularly with artificial intelligence agents or applications. An auditory operating system shell serves as the primary interface, managing and coordinating multiple specialized agents that handle specific domains like music streaming, scheduling, or home automation. Using natural language processing, the auditory operating system shell identifies the appropriate agent or application for a user's command or query and ensures task execution and context preservation across interactions. The auditory operating system shell enforces privacy and stability by controlling agents' and applications' access to data and system privileges. The auditory operating system shell also supports dynamic context management, enabling seamless handoffs between agents when user requests span multiple domains. This auditory operating system shell may reduce the need for users to memorize specific wake words or commands, as the auditory operating system shell may determine the user's intent from speech or contextual cues.

The invention discloses a customer voice analysis system based on a large model, and the system comprises a voice data collection and preprocessing module which is used for collecting and preprocessing customer voice data; the voice recognition module is used for recognizing the preprocessed customer voice data; the feature fusion module is used for extracting semantic features of the text data and fusing customer voice data features to generate voice text representation; the large model fine tuning module is used for performing fine tuning on the pre-trained starry fire cognition large model; the semantic analysis and emotion recognition module is used for processing the voice text representation, extracting semantic information, recognizing an emotion state and generating an analysis result; and the dialogue context management module is used for associating customer historical voice data, establishing dialogue context information and updating a voice analysis result. According to the method, the stellate fire cognitive large model and the improved quantitative low-rank adaptation are utilized, and the method has the advantages of high precision, low calculation cost and high intelligent adaptability.

The invention relates to the technical field of databases, can be applied to the field of science and technology finance / digital medical treatment, and discloses a database migration method and device, electronic equipment and a storage medium. The method comprises the steps that database structured query language identifiers are defined, strategy classes corresponding to all databases are packaged, and a strategy context management container is created; receiving a target database type, dynamically loading a strategy type instance according to the type, and generating an executable query strategy chain according to the strategy type instance; when a database query request is received, matching a corresponding strategy type instance, and processing an original database query statement to generate a target database executable instruction; controlling a query strategy chain to execute a single-path or double-write-path mode through a common switch, and transmitting the instruction to a strategy type instance for execution; and analyzing a return result of the target database, performing conversion adaptation through the strategy type instance, and returning a conversion adaptation result. The method realizes automatic migration, reduces cost and risk, and improves system performance.

The invention relates to the field of intelligent interaction, and discloses an intelligent hardware dynamic interaction system based on voice semantic fusion and multi-modal perception, which comprises the following steps of: constructing a context model of continuous operation by collecting continuous voice instructions, gesture actions and expression information of a user; semantic analysis and feature fusion are carried out on currently collected voice, gesture and expression features, meanwhile, credibility indexes of all modes are calculated through a weighting or deep learning model, weighting correction is carried out on a fusion result, a real-time feedback algorithm is adopted for weight adjustment for continuous optimization, the next operation intention of a user is predicted through deep learning, and the user experience is improved. And in combination with historical interaction data, online feedback and prediction errors, context management, modal weight and intention prediction strategies are adaptively optimized, and the updated strategies are used for next-round context acquisition and multi-modal fusion. The method has the advantage of improving the recognition accuracy in the continuous interaction scene.

The invention discloses a self-adaptive NL2SQL method and system based on a large language model and retrieval enhancement. The method comprises four key steps of mode linking, example enhancement and SQL generation, multi-path thinking chain fusion reasoning and multi-round self-correction. The system comprises the following modules: a knowledge base management module, an input analysis and preprocessing module, a mode link module, an example enhancement module, an SQL (Structured Query Language) generation module, an SQL fusion and optimization module, an SQL execution and feedback module, a multi-round self-correction module, a Prompt construction and context management module, a system interface module and a content generation module. The method has the advantages that multiple large models are supported, a data source is quickly accessed, a user-defined prompt structure is configured, good engineering maintainability and scene adaptability are achieved, and SQL generation accuracy, performability and universality are improved.

The invention provides a context compression method based on multi-round dialogue intention graph construction, which comprises the following steps: S1, dialogue data acquisition and preprocessing: carrying out natural language processing on each dialogue unit; s2, intention atlas construction is achieved through node design and edge design, and each node comprises original text content and structured semantic information; s3, carrying out context compression and graph structure cutting, and only retaining sub-graphs forming a core semantic link; s4, dynamic context management and topic jump processing: in a multi-topic dialogue, when a user jumps or switches to a new topic, a system records a sub-graph of a current active topic, and contextual nodes of an inactive topic are frozen; s5, context sequence generation and model input: linearizing node contents in the cut sub-graph according to a dependent link sequence to generate a compressed context sequence, and transmitting the context sequence and current user input to a large language model for reasoning; and S6, continuous updating and feedback optimization are carried out.

The invention discloses a protocol method for realizing intelligent connection of a PLC (Programmable Logic Controller) with an AI (Artificial Intelligence) large model, which relates to the technical field of industrial automation, and comprises the following steps: in a PLC system, configuring an MCP client module by defining basic parameters of an MCP, and embedding a context management module in the MCP, the basic parameters comprising a data format, a communication protocol and a security mechanism; and establishing a bidirectional communication channel between the PLC and the AI system based on the configured MCP client module. According to the protocol method for intelligently connecting the PLC with the AI large model, seamless connection between the PLC and the AI system is achieved by defining a unified data format, a communication protocol and a security mechanism, the complexity and the error rate of data transmission are reduced, the overall data transmission efficiency is improved, and the method is suitable for popularization and application. The context management module embedded in the MCP can store and manage historical data, so that the AI system can make intelligent decisions based on comprehensive data, and the accuracy is improved.

The invention provides a background authority management system and method for adaptive risk control. Comprising a data acquisition module used for acquiring behavior data and environment data associated with an account and converting the data into an event stream; the context management module is used for associating the context attribute set with the event flow; the feature construction module is used for generating a multi-dimensional feature vector based on the event stream and the context attribute set; the adaptive risk assessment module is used for calling at least two heterogeneous models to perform parallel reasoning on the multi-dimensional feature vectors; the decision engine module is used for mapping the risk weight into an access control instruction and an audit instruction; the auditing module is used for recording auditing data according to the auditing instruction; and the authority management module is used for calculating an authority weight according to the attenuation parameter and judging and generating an authority recovery instruction or a maintenance instruction according to a threshold value. According to the method, event stream unification and context binding, real-time risk assessment and strategy linkage and permission adaptive recovery closed loop can be realized.

The invention discloses a voice dialogue system based on a large model, and relates to the technical field of voice interaction, and the system comprises an intelligent scheduling module which determines a task type according to a to-be-recognized text, and dynamically adapts to a fast and slow thinking module according to the task type; the fast and slow thinking module dynamically adapts to the calculation unit according to the task type and outputs a feedback result; the voice interaction module generates a to-be-recognized text according to the voice characteristics of the user and generates a voice instruction based on a feedback result; the context management module stores the interaction log to a corresponding storage unit according to the index key value; the interaction log comprises a task type belonging to the same data flow, an adaptive path and a feedback result; and the data centralized control module determines a parameter adjustment strategy according to the performance index factors in the interaction logs, and the parameter adjustment strategy acts on the intelligent scheduling module or / and the fast and slow thinking module to optimize corresponding parameters. The intelligent balance of quick response and deep reasoning of the dialogue system under a single architecture is realized, and the real-time performance and accuracy of interaction are remarkably improved.

The embodiment of the invention provides a question and answer management method and device based on a large model, a storage medium and a program product. In the scheme, a'short-term first and long-term 'progressive recall strategy is introduced, that is, in a storage stage, session abstracts are generated in a segmented manner under the condition that whether the collection frequency of a preset round and the topic category are changed or not, the session abstracts are sequentially written into a short-term memory storage area and sink to a long-term memory storage area after the preset storage duration is reached, and a subsequent recall path is pre-buried; in the acquisition stage, the latest abstract closest to the current round is recalled from the short-term region, and if the abstract is missing, the cross-session or cross-round historical session abstract continues to be complemented from the long-term region. According to the mechanism, session context management of'instant light and thin 'and'long-term consistent' is considered under the condition that the computing power and the bandwidth cost are not remarkably increased, accurate contexts are provided for complex session scenes with long-period, multi-topic and multi-file cooperation, and a large question and answer model can make more accurate and more consistent questions and answers based on complete and related context information.

Techniques for correcting data drift of a language model are disclosed. A model is built, and this model is designed to solve a same task for which the language model has been trained. The model is applied to new input data. This application results in generation of a prediction comprising predicted label data. Context is stored in a context management structure (CMS). The context includes a prompt template, a prediction, and labeled input data used to train the language model. The data drift is determined to have occurred. This determination is performed by determining that the context is within a threshold level of similarity to a previously stored context. In response to determining that the data drift has occurred, an operation is performed to correct the data drift.

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 provides a system for intelligent interaction of a software as a service platform. The system comprises a large language model LLM module, a voice processing module, a model context protocol MCP communication layer and a context management module. According to the system, function operation of the SaaS platform is directly driven through natural language interaction, combination of a menu or button control of a traditional graphical user interface (GUI), an LLM module and historical data of a context management module is not needed, the intention recognition accuracy is larger than or equal to 92%, and repeated correction of a user is reduced.

The invention relates to a battery database access system and method based on Dify and a large model question and answer mechanism, and the system comprises a front end interaction module which is responsible for carrying out information interaction with a user, receiving a natural language question of the user, and transmitting the question to a rear end for processing; the Dify agent management module is responsible for task distribution and user intention recognition; the Prompt generation and scheduling module is responsible for converting the user problem into a query request which can be understood and processed by the system; the database interface module is responsible for being connected with a new energy battery database; the large model generation module is used for generating natural language answers of the user questions through a large language model; and the context management module is responsible for storing and managing context information in multiple rounds of conversations. A user can intelligently interact with the new energy battery database through a natural language, and can easily and efficiently access information in the real-time database.

The embodiment of the invention provides a context information management method and device based on hierarchical memory, equipment and a medium, and the method comprises the steps: analyzing a task request to generate a sub-task node sequence containing a target description and acceptance function, and arranging a plurality of agents to cooperatively execute a task, and after the audit is passed, a complete execution context is stored in a long-term memory, and a structured abstract is generated and stored in a short-term memory, so that the problem that the context management mechanism of the existing multi-agent system is single is effectively solved, stable maintenance of cross-session cognitive continuity is realized, and the efficiency of the multi-agent system is improved. The method improves the execution reliability of a complex long-process task, optimizes the information storage and retrieval efficiency through hierarchical memory, reduces the risk of semantic deviation accumulation and amplification, clarifies the task target and acceptance standard of each stage, enhances the multi-agent cooperation consistency, and improves the efficiency of task execution. And the execution efficiency and the task completion quality of the intelligent agent system in a complex application scene are comprehensively improved.

Provided are a context-aware model generating method, an important event determining method, and an in-game context management server for performing the same methods. The context-aware model generating method includes generating a context-aware model which determines whether an important event of a video game occurs by using in-game data, utterance data, and chat data collected from the video game capable of being broadcasted as a sports game video. The important event determining method includes combining candidate events predictable from each of the in-game data, the utterance data, and the chat data based on the context-aware model, and determining, as an important event, a candidate event including a duplicate game content among candidate events.

The embodiment of the invention relates to the technical field of natural language processing, and discloses a multi-task agent execution method and device based on a large language model, electronic equipment and a storage medium, and the method comprises the following steps: receiving natural language target task description and constraint conditions input by a user; generating a task tree with a hierarchical structure and a dependency relationship; calculating an initial priority for each task node based on a preset priority scoring model, and dynamically adjusting the real-time priority of the task node according to the execution feedback of the task node to form a scheduling queue; asynchronously executing each task node in the task tree according to the scheduling queue, and calling a large language model to complete the generation of subtask contents corresponding to each node; and integrating the execution results of the task nodes, and generating a final output result oriented to the target task. According to the method, the intelligent agent system with self-adaptive dynamic scheduling, hierarchical task decomposition and stable long-range context management capabilities is constructed, so that efficient, reliable and user-controllable multi-task automation is realized.

The invention relates to the technical field of natural language generation, in particular to a retrieval enhancement dialogue generation system and method applied to digital human shopping guide, and the system comprises an input module, a semantic analysis module, a multi-strategy memory module, a context management module, a retrieval module, a generation module and a privacy and security control module. The method has the beneficial effects that through the multi-strategy memory module and dynamic user portrait construction, personalized demands and preferences of users can be deeply understood and captured, and accurate product recommendation and customized purchase suggestions are realized. The shopping satisfaction degree of the user is improved, and the stickiness and loyalty of the user are enhanced.

The invention provides a context management method and device of a large language model, a medium, equipment and a product, and relates to the technical field of machine learning, and the method comprises the steps: determining unique identifiers of messages related to cue words through a first agent according to the received cue words, assembling the determined unique identifiers into an array through the first agent, and storing the array into a database; the method comprises the following steps: acquiring an array, sending the array to a second agent, acquiring a message corresponding to a unique identifier according to the unique identifier included in the array through the second agent, determining a target context of a large language model based on the acquired message, and acquiring an output result of the large language model according to the target context through the large language model included in the second agent, according to the method, the context related to the cue word can be selected, the unrelated context can be filtered out, it is guaranteed that the context can be highly related to the task, the context is transmitted in the multi-AI Agent through the unique identifier, and interference of unrelated information on a large language model can be reduced.

The invention discloses a real-time voice stream dialogue interaction method and system based on a large language model, and belongs to the technical field of voice recognition, natural language processing and human-computer interaction. The method comprises the following steps: S1, segmenting a voice signal according to a 320 millisecond time window; s2, through double-channel parallel processing, generating a preliminary text hypothesis locally and uploading a frame to a server side to accurately reconstruct a text; s3, fusing to generate a final text with a confidence label; s4, inputting the text into a large language model with a context management mechanism to generate a natural language response; s5, performing speech synthesis output of rhythm perception; s6, updating a dialogue cache and synchronizing a language model state; s7, predicting the semantic trend in advance by adopting a delayed slow release mechanism; and S8, introducing round-level intonation / rhythm parameters for semantic adjustment. The method has the beneficial effects that the response delay is reduced, the recognition accuracy is improved by fusing the confidence label, and meanwhile, the continuity and naturalness of multi-round interaction are enhanced through context and intonation modeling.

The invention relates to the technical field of process orchestration, and discloses an automatic orchestration system and implementation method based on event driving and context management, and the system comprises a model orchestration module which receives an external request through an OpenAPI, carries out the model packaging based on namespace attributes, and abstracts the workflow execution capability into a configurable model entity; the workflow engine module is used for providing a dynamic arrangement and execution mechanism based on a directed graph structure and carrying out unified context management; the parameter configuration module is used for constructing a global data constraint and management mechanism of a parameter-result double-layer model, and establishing a data mapping relation between an execution layer and a display layer of the process; and the data source management module uniformly manages and configures the external service capability units which can be called by the nodes in the workflow. According to the method, asynchronous, self-driven and distributed parallel execution of the workflow nodes can be realized, the operation efficiency in a high-concurrency scene is improved, and organic unification of performance, stability and expansibility is realized.

The embodiment of the invention provides a memory information processing method of a large language model and a computer program product, and relates to the technical field of large language models. The method comprises the steps of obtaining interaction request information of a target object, extracting at least one piece of memory information needing to be memorized from the interaction request information based on a large language model, performing classification and importance evaluation on each piece of memory information to obtain category information and an importance score of each piece of memory information, and according to each piece of category information, determining the importance score of each piece of memory information. And determining the expiration duration of each piece of memory information, and storing each piece of memory information, the corresponding category information, the corresponding expiration duration and the corresponding importance score into an active memory pool of the target object. Context management can be carried out by using the memory information, and the context management accuracy of a large language model in a cross-session scene is remarkably improved.

The invention relates to the technical field of artificial intelligence, and discloses an intelligent interaction system and method based on legal consultation, and the system comprises a front-end user interface which supports text input, voice input and image input and has a multi-language switching function; the middle layer processing module comprises an emotion analysis module, an information integration module, a context management module and a response generation module and can dynamically adjust a processing strategy; and the rear-end legal knowledge base is used for storing laws and regulations, case analysis and common legal question answers and supporting real-time updating, version management and efficient retrieval. Through combination of a deep learning model and fine tuning of a special data set in the legal field, the system can accurately identify emotion features in user input, the accuracy not only improves the ability to understand legal terms, but also enhances the ability to process complex emotion expression, so that legal consultation is more humanized, and the efficiency is improved. The emotion change of the user can be responded in time, so that the satisfaction degree and the trust feeling of the user are improved.

The invention discloses an agent context management system and device based on importance sampling, and belongs to the technical field of artificial intelligence and agents, the agent context management system and device based on importance sampling comprise a global context manager used for maintaining and managing eight types of context information; the task stack manager is used for receiving a new request and performing task splitting; and the recursive execution engine is used for executing the task in a recursive mode and controlling the recursive depth. Eight types of context information are maintained through a global context manager, splitting and storage of complex tasks are achieved through a task stack manager, a recursive execution engine provides an efficient task execution mechanism and controls the recursive depth, an importance sampler selects related contexts based on a joint probability model, and the task execution efficiency is improved. And the context compressor combines the sampling fragments into a final context, and the task scheduler coordinates the working process of each component, so that a complete agent collaborative context management system is constructed.

The invention discloses an automatic code debugging and optimizing system and method based on an AI agent, and relates to the technical field of artificial intelligence and automatic programming, the system comprises a coordinator module, a plan generation module, a code generation module, a test verification module, a deployment operation module, a project summary module, a language model module and a context management module; the coordinator module supports to select and call an Agent for specific task execution according to the current task process, and the plan generation module is configured to automatically generate a development task plan according to the requirements of a user and transmit a task list to the code generation module. Through the exception retry mechanism and the task backtracking mechanism, the system can automatically detect errors in the code generation process and repair the errors, and the tedious process of traditional manual debugging is avoided. The system optimizes the code generation process by backtracking the historical task and adjusting the generation strategy, and the quality of the final code is ensured.

The invention provides an interaction system and method based on artificial intelligence, and relates to the technical field of artificial intelligence. The interaction system based on artificial intelligence comprises a multi-modal data acquisition module, a data preprocessing module, an intention understanding module, a context management module, a knowledge graph module, a dynamic decision module, a reply generation module, a multi-modal output module and a feedback optimization module. According to the invention, through multi-modal data acquisition and fusion processing, the intention of the user can be more comprehensively and accurately understood, and the limitation of single-modal interaction is made up; the context management module is arranged, so that the system can keep coherent understanding of the intention of the user in multiple rounds of dialogues, and more intelligent and smoother interaction experience is realized; and secondly, through introduction of the knowledge graph module, rich knowledge support is provided for the system, so that the system can perform reasoning and information supplementation based on knowledge, the answer is more accurate and comprehensive, and the intelligence and practicability of the interaction system are enhanced.