301 results about "Multi-agent system" patented technology

The invention discloses a hierarchical multi-agent robot cluster control method and system, and aims to solve the problems of partial observability and environment non-stability of a multi-agent system in a complex environment. According to the method, a three-layer layered reinforcement learning architecture is constructed, a high-layer strategy is responsible for global task decomposition and role allocation, a middle-layer strategy converts tactical intention into a cooperative behavior mode, and a low-layer strategy executes accurate motion control; a graph neural network is adopted for cluster modeling, global graph representation and local neighborhood features are extracted in parallel through graph convolution and an attention mechanism, and hierarchical decision making is supported; a centralized graph enhancement evaluation network is designed to be combined with an MAPPO algorithm for collaborative optimization, and dynamic adversarial training is introduced to improve strategy robustness. According to the method, effective decoupling of global planning and local control is realized, and the cluster cooperation efficiency, the strategy interpretability and the adaptive capacity in a dynamic environment are improved.

The invention discloses a visual algorithm self-training method based on multi-agent collaborative optimization, and the method comprises the following steps: constructing a multi-agent system architecture which comprises a user interaction layer, an intelligent scheduling layer, an A2A protocol communication layer and a professional agent cluster layer; the user interaction layer analyzes a user task intention and generates an execution plan; the scheduling agent calls the professional agent to complete data processing, model construction, training, testing and deployment; a task process is coordinated through a standardized communication mechanism, and task execution is supported by combining an MCP tool set, a knowledge base module and a memory system; and when the task fails, automatically executing rescheduling operation, and finally outputting a self-training result. According to the method, the development efficiency, the self-adaptability and the intelligent level are remarkably improved, and the method is suitable for computer vision tasks such as industrial detection, intelligent security and protection and automatic driving.

Provided are a multi-agent construction method and apparatus, a task processing method and apparatus, a computing device, a storage medium, a computer program product, and a chip. The multi-agent construction method comprises: splitting a task into a plurality of sub-tasks; determining, from an agent pool, agents respectively matching the plurality of sub-tasks, wherein the agent pool comprises a plurality of agents, and the agents matching the sub-tasks can process the sub-tasks by calling at least one of tools and other agents which are configured by the agents; and constructing a multi-agent system on the basis of the agents respectively matching the plurality of sub-tasks, wherein the multi-agent system is used for processing the task.

The invention relates to the technical field of intelligent unmanned systems, in particular to a task allocation method of a sea area cross-medium unmanned system based on a graph attention network and deep reinforcement learning, and the method comprises the following steps: S1, constructing a dynamic graph and calculating task priority; s2, screening and selecting schedulable tasks; s3, intelligent agent distribution and state updating; s4, dynamic reordering and cycle control are carried out; according to the method, a space-time coupling dynamic graph structure is constructed, task attributes and agent states are coded into node features, a four-layer graph attention network is designed to extract task priority distribution, and a self-adaptive scheduling decision is realized in combination with a near-end strategy optimization algorithm; a task dependence verification and resource availability check mechanism is established, and approximate optimal agent allocation is realized; a multi-dimensional reward function is included, training stability is guaranteed in combination with an experience playback mechanism and a gradient clipping technology, and task allocation efficiency of a multi-agent system in a complex environment is remarkably improved.

The invention relates to the technical field of multi-agent cooperative control, and discloses a multi-agent autonomous decision-making method based on deep reinforcement learning. The method comprises the steps of synchronously detecting an initial collaborative state of a cluster, performing joint situation assessment, and judging a collaborative operation mode according to a quantitative situation. And analyzing the capability of each agent and the real-time task load, and constructing a distributed task knowledge graph. And utilizing the atlas to drive a deep reinforcement learning network, coupling computing resource allocation and a task path, and generating a preliminary behavior strategy of each agent. And performing cluster-level conflict detection and iterative negotiation adjustment, and finally issuing an executable action instruction sequence. According to the method, integrated optimization of resource allocation and action paths is realized, the situation understanding and negotiation mechanism is enhanced through the knowledge graph to guarantee the collaborative consistency, and the collaborative decision-making efficiency and task execution robustness of a multi-agent system in a dynamic environment are improved.

The invention discloses a heterogeneous agent distributed multi-alliance game control method, device and equipment and a medium, and relates to the field of multi-agent system cooperative control and game theory cross application, and the method comprises the steps: dividing agents in a heterogeneous unmanned cluster system into a plurality of alliances; establishing a high-order heterogeneous linear state dynamical model for the intelligent agent in each alliance; constructing an internal and external double-layer alliance communication topological graph according to an actual communication condition; and on the basis of the model and the topological graph, through a distributed Nash equilibrium search algorithm containing a search layer and an output adjustment layer, performing iterative optimization on an agent decision state to obtain a multi-alliance game strategy, and controlling the agent according to the strategy. According to the method, the cooperative control problem of the heterogeneous agents in a multi-alliance game scene can be effectively solved, the Nash equilibrium point is quickly searched, the decision state is adjusted to be optimal, and the cooperative control performance and task execution efficiency of a multi-agent system are improved.

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.

The invention provides a multi-agent proposition method and system based on collaborative reinforcement learning. The method comprises the following steps: constructing a multi-agent proposition framework comprising a test question generation agent and a quality inspection agent based on a large language model; constructing training data on the basis of a target subject test question set, respectively supervising and adjusting large language models on which a test question generation agent and a quality inspection agent are based, and training a reward model for evaluating the output quality of each agent for the agent; and performing multi-agent collaborative reinforcement learning training on the test question generation agent and the quality inspection agent by using the reward model to obtain a trained agent model weight. And loading the trained agent model weight into a multi-agent collaborative proposition framework, and receiving proposition requirements to generate final test questions and reference answers. A multi-agent cooperative reinforcement learning mechanism is introduced into a multi-agent system, so that the agents can form a stable and efficient cooperation strategy in a real proposition task interaction environment.

The invention relates to the technical field of computers, and discloses a fragmentation block chain federal learning method based on a large language model multi-agent, and the method comprises the steps: S1, initializing a client; s2, dynamic fragmentation scheduling and distribution; s3, generating and uploading local knowledge; s4, intelligent agent collaborative routing and knowledge acquisition; s5, knowledge fusion and model updating; and S6, repeatedly executing the steps S3 to S5 until the model converges or reaches a preset number of iterations. According to the invention, under a decentralized and fragmented federated learning architecture, the complex reasoning ability of a large language model and the autonomous cooperation mechanism of three multi-agent systems, namely a fragmented scheduling agent, a fragmented knowledge state agent and a global knowledge routing agent, are deeply fused; according to the mechanism, dynamic optimization of a bottom layer fragment structure and intelligent routing of high-value knowledge are achieved in an intelligent mode, and therefore the overall efficiency and model performance of a system under the condition of heterogeneous data and heterogeneous equipment are remarkably improved.

The invention discloses an electric vehicle charging station energy storage scheduling method based on a multi-agent system. The method comprises the following steps: obtaining and standardizing operation basic data of a plurality of new energy vehicle charging stations; setting five types of agents, defining observation variables and action space, and constructing a multi-agent system model; constructing a global collaborative scheduling network, and executing strategy evaluation and strategy generation; setting a constraint boundary, and constructing a linear programming scheduling model; constructing a training sample, and performing offline training and updating of a global collaborative scheduling network; solving a local optimal scheduling amount based on the real-time operation basic data, and analyzing to generate a control instruction; and issuing an energy storage control instruction and a computing power unit control instruction, acquiring a cooperative scheduling result to generate a final scheduling result set, and submitting the final scheduling result set to an upper-layer scheduling system. According to the method, a multi-agent collaborative scheduling system is constructed, strategy optimization and linear programming are fused, and efficient, stable and executable global collaborative scheduling of energy storage and computing power tasks of the charging station is achieved.

The invention provides a multi-agent system and a multi-agent dialogue management method. The system comprises a main agent, a dialogue management module and a plurality of sub-agents, and the sub-agents correspond to processing of tasks in different business fields respectively; the main agent is used for calling the dialogue management module under the condition that a user request is received; the dialogue management module is used for acquiring historical information corresponding to the user request, analyzing the historical information and returning an analysis result to the main agent; the main agent is further used for determining corresponding request task data and a target sub-agent in the multiple sub-agents according to the analysis result and the user request, and sending the request task data to the target sub-agent; the sub-agent is used for processing based on the request task data, obtaining a task processing result and returning the task processing result to the main agent; and the main agent is also used for returning a corresponding natural language reply to the user according to the task processing result of the sub-agent.

The invention relates to the technical field of control and information, and particularly discloses a distributed optimization control method for a security constraint uncertain multi-agent system, which comprises the following steps of: constructing a topological graph according to a network structure of the multi-agent system, and determining an adjacent matrix of the topological graph; determining a state equation; determining a target function needing to be optimized and inequality constraints needing to be met; according to the state equation, the target function needing to be optimized and the inequality constraint needing to be met, based on a Lyapunov function control method, an optimal solution search condition is established, and based on a barrier function control method, a system safety maintenance condition is established; determining an input constraint condition according to the multi-agent system; calculating by using a quadratic programming method to obtain optimal control input; and controlling the multi-agent system according to the optimal control input. According to the method, the long-term reliability of the system can be remarkably improved, the communication and calculation overhead is remarkably reduced, and the calculation efficiency is remarkably improved.

The invention provides a multi-agent trajectory prediction method based on space-time causal interaction modeling, and belongs to the field of behavior prediction of a multi-agent system. The problem of low trajectory prediction precision caused by data deviation and false correlation in the existing method is solved. The method comprises the following steps: extracting two-dimensional position coordinates of a lane center line corresponding to driving of each vehicle; calculating the deviation degree between the vehicle position and the center line of the corresponding lane, modeling the spatial dependency relationship between the vehicles, outputting vehicle spatial interaction characteristics, carrying out time sequence modeling, and extracting vehicle time sequence characteristics; feature coding: outputting lane center line features; fusing the time sequence features and the lane center line features to generate vehicle fusion features; constructing a causal discovery network, and outputting a causal probability matrix; based on the vehicle fusion features and the causal probability matrix, space-time causal interaction features between the vehicles are extracted and input into a trajectory decoder, and multiple possible future trajectory sequences of each vehicle are generated. The method is used in the fields of artificial intelligence, robots and intelligent driving.

The invention relates to a motorcade consistency formation control method and device based on a dynamic event triggering mechanism, electronic equipment and a storage medium. The method comprises the steps of generating a communication topological graph of a multi-agent system composed of a preset number of unmanned vehicles according to the theoretical basis of a graph theory, and building a mathematical model of each unmanned vehicle; based on the mathematical model, designing a combined measurement function, a measurement error and a consistency controller of the multi-agent system; distributed event triggering conditions and self-triggering conditions are designed based on Lyapunov parameters; according to a dynamic event triggering condition and a self-triggering condition, a triggering time interval expression of the intelligent agent is obtained through calculation; by constructing a multi-agent system consistency controller and combining distributed event triggering conditions and self-triggering conditions, multi-vehicle formation consistency control is completed. According to the fleet consistency formation control method disclosed by the invention, accurate and efficient control of a fleet formed by multiple unmanned vehicles can be realized.

The invention relates to the technical field of digitization systems, and particularly discloses an intelligent AI-driven archive digitization full-process processing system, which comprises a physical digitization module, an AI agent collaborative network and a digital resource management module which work cooperatively in sequence, and realizes automatic processing from an entity archive to a structured digital knowledge base; the physical digitization module is configured to perform high-fidelity scanning or shooting on the entity archive to generate an original digital image set; the AI agent collaborative network is a multi-agent system dispatched and managed by the central coordinator; according to the system, an end-to-end closed-loop processing flow from an entity file to a structured digital knowledge base is constructed through sequential collaboration of the physical digitization module, the AI agent collaboration network and the digital resource management module, connection of all links does not need to be manually intervened, manual review is only needed in a very few complex abnormal scenes, the labor cost is remarkably reduced, and the efficiency is improved. And the processing efficiency and the flow consistency are improved.

The invention provides a self-adjusting dialogue type multi-agent system and interaction method based on dynamic topology, and the system comprises a scheduling module which is used for receiving user input and routing a task to a corresponding field task agent in a conventional state; the domain task intelligent agents are used for processing the received tasks, evaluating the cognitive states in real time and sending out assistance signals when the cognitive states meet preset conditions; the shared knowledge management module is used for maintaining a dynamically updated distributed semantic knowledge graph; wherein the distributed semantic knowledge graph is used for sharing, associating and persisting structured knowledge entities and context information generated in the session process among all modules in real time; the topology control module is used for dynamically switching the communication control topology of the system from a first topology structure to a second topology structure in response to the received assistance signal; and when the assistance signal is eliminated, the communication control topology is recovered from the second topology structure to the first topology structure.

The invention discloses a GNN-MAPPO task unloading method based on dominant value noise addition, which is characterized in that an MLP is changed into a GNN on the basis of the existing MAPPO framework, a multi-agent system can be directly modeled into a graph structure, an interaction relationship among multiple agents can be better established, Gaussian noise is added on the dominant value, the exploration capability of a model is enhanced, and overfitting is reduced. According to the method, the powerful graph structure learning ability of GNN is combined with an innovative dominant value noise adding mechanism, and the mixed reward function is elaborately designed, so that the MAPPO algorithm can more effectively learn a cooperation strategy between agents and optimize time delay and energy consumption in the aspect of edge computing task unloading, and the efficiency of the MAPPO algorithm is improved. And the exploration capability of the strategy and the avoidance capability of the communication risk can be obviously enhanced, so that a more robust and efficient intelligent task unloading scheme adapting to a dynamic environment can be obtained.

The embodiment of the invention provides a task processing method, device and equipment for a multi-agent system. According to the scheme, the system comprises a planning agent, an execution agent, a context injection module and a memory storage module; wherein when a planning agent needs to perform task planning for a user request, a context acquisition request is sent to the context injection module, and the context acquisition request comprises task description information of the user request; afterwards, the context injection module responds to the context acquisition request and acquires a planning context related to the task planning from a memory storage module based on the task description information, and the memory storage module stores historical data generated when each agent in the multi-agent system executes a historical task; afterwards, the planning agent receives the planning context, and generates a calling instruction for calling the execution agent based on the task description information and the planning context;

The invention discloses a value maximization calculation unloading method and system based on dynamic priority scheduling and reinforcement learning. According to the method, an optimization framework with maximization of the'long-term average task value 'of the system as a core target is constructed, and the task value is defined by introducing an exponential value function, so that the problem of'value neglect' existing in a traditional'average delay or energy consumption optimization 'strategy is solved. According to the value-oriented optimization mechanism, the multi-agent system can autonomously learn a strategy which preferentially ensures high-value task execution when resources are limited in the training process. In addition, the invention further provides a dynamic priority function which can accurately measure the actual emergency level of the task at different moments, so that the defect that a static priority model is difficult to deal with the real-time change of the emergency state is overcome. Particularly, the dynamic priority method is not only used for task selection in a waiting queue, but also innovatively introduced into a resource dynamic allocation mechanism of a running queue.

The invention belongs to the technical field of industrial process control, and particularly relates to a drying device temperature and humidity cooperative control method based on a multi-agent system, and the method comprises the steps: dividing the internal space of a drying device into independent agent regions, and obtaining a denoised temperature observation value and a denoised humidity observation value through an integrated sensor array; based on the dynamic deviation between the observed value and the expected value, intelligent agent node deviation potential energy reflecting the environment unbalance momentum is obtained; establishing a neighborhood topological structure by using the centroid coordinates, and obtaining a collaborative flux compensation amount based on a potential energy difference cumulant between a current area and an agent area in a neighborhood and in combination with a temperature change acceleration; and mapping the collaborative flux compensation quantity into a frequency output value of the heating unit and a rotating speed output value of the moisture removal fan so as to realize synchronous adjustment of an actuator. The problems that a large-volume drying cavity is uneven in room temperature and humidity distribution and extremely prone to oscillation are solved, and the consistency of the material drying quality is guaranteed.

The invention discloses a two-way output consistency control method for a heterogeneous multi-agent system, and the method comprises the following steps: 1, constructing state and output equations of a follower agent and a leader agent, calculating an output tracking error ei (k), and constructing an augmented system state space model and a linear control input ui (k); 2, designing a distributed bipartite observer for each follower agent to enable an output tracking error ei (k) to be zero all the time, and replacing a leader agent state of the augmented system state space model with a state of the distributed bipartite observer; 3, defining a Q function, solving the Q function to obtain an optimal control strategy, and introducing a Q-learning algorithm to obtain an optimal control gain only depending on an input state of the augmented system state space model; 4, introducing a fuzzy logic system approximation Q function to enable a matrix phi i to meet a full-rank condition, and updating a fuzzy weight by minimizing a Bellman residual error to obtain an optimal control gain of the input state of the augmented system state space model; and updating the control gain by adopting a gradient descent method, and calculating linear control input ui (k) by utilizing the updated control gain.

The invention discloses an earthquake and secondary disaster vulnerability assessment method in combination with multiple agents and deep learning, and the method comprises the following steps: (1), collecting and preprocessing data related to an earthquake and an infrasound disaster thereof, and obtaining multi-source static data; key features are extracted from the multi-source static data; step (2), constructing a hierarchical structure index system of vulnerability assessment by utilizing expert knowledge, constructing a judgment matrix by adopting an analytic hierarchy process, and calculating the weight of each index to obtain an AHP weight vector; step (3), multi-agent system construction and disaster propagation dynamic simulation; step (4), designing a GCN + Transform deep learning model, and combining the multi-source static data with the dynamic evolution data to construct a spatial-temporal feature tensor as the input of the GCN + Transform deep learning model; and step (5), outputting a vulnerability evaluation result. According to the method, the problems of the existing earthquake and secondary disaster vulnerability assessment precision and timeliness can be solved.

The invention relates to a credit distribution method in multi-agent cooperation, and the method comprises the following steps: obtaining joint data of a multi-agent system, the joint data comprising observation information and execution actions of each agent; the joint data are input into a discriminator model, and the discriminator model carries out modeling on an interaction dependency relationship among multiple agents based on an interaction dependency relationship modeling module of an attention mechanism; generating an auxiliary reward signal corresponding to each agent through a discriminator model; generating a fused reward signal based on the auxiliary reward signal and a global reward signal from the environment; and training and updating the multi-agent strategy model by using the fused reward signal so as to optimize the cooperation strategy of the multi-agent system. By introducing a credit distribution mechanism based on a discriminator model, automatic decomposition and optimization generation of individual reward signals are realized, so that the learning efficiency and stability of a multi-agent system in a complex cooperative task are remarkably improved.

The invention discloses a shared energy storage-containing electrical integrated energy system optimization scheduling method based on federal reinforcement learning. The method comprises the following steps: constructing an optimal scheduling model of an electrical multi-park integrated energy system containing shared energy storage, wherein the optimal scheduling model comprises optimization targets, model constraint conditions and optimization variables of a plurality of parks; converting the optimal scheduling model into a multi-agent system, wherein the multi-agent system comprises a plurality of park agents; multiple park intelligent agents are trained based on a federal reinforcement learning method, and in the training process, training samples of all park intelligent agents are reserved in all parks; and deploying each trained park intelligent agent to the corresponding park to execute an online optimization scheduling scheme in real time. According to the method, on the premise of realizing efficient scheduling of energy and reducing the operation cost of the park, the main body data privacy of each park can be fully protected, and the enthusiasm of each park to participate in scheduling optimization is fully aroused.

In described embodiments, there is provided a multi-agent system for processing information, comprising a data processing agent configured to ingest and standardize raw data input to produce standardized data, and a standard integration agent configured to integrate the standardized data with the standard integration agent. The standard integration agent is configured to apply a reporting standard to the standardized data to generate an integrated reporting standard. The system also includes a performance alignment agent configured to align performance metrics based on the standardized data and the integrated reporting criteria, and an information synthesis agent configured to process narrative information from the standardized data and the integrated reporting criteria. An orchestration framework is also provided that is configured to manage operation of the data processing agent, the standard integration agent, and the performance alignment agent to generate regulatory reports that comply with regulatory requirements. The orchestration framework may also be executed by a large language model.

The invention discloses a large-model multi-agent task scheduling method with memory and retrieval capabilities, and the method comprises the steps: carrying out the cognitive analysis of a complex task based on task scheduling agents, and carrying out the distribution of subtasks through combining the functional attributes of all task execution agents and an integrated tool; each task execution agent completes execution work of a specific task through an integration tool, a task result is returned to the task scheduling agent for integration, and execution of a next link subtask or completion of the task is determined according to a task condition; maintaining task context information and a task entity information base by adopting a dynamic memory pool; and cross-agent and cross-task node multi-dimensional information sharing is realized by using cross-agent search. According to the method, the problem of state loss of a multi-agent system is solved by introducing a memory enhancement mechanism, and the context sensing capability in the task execution process is remarkably improved; cross-task and cross-agent knowledge reuse is realized through a cross-agent search mechanism, and the decision quality of the system is improved; the method is compatible with multi-source heterogeneous task requirements, breaks through the limitation of a traditional multi-agent system on task complexity, cross-agent collaboration and knowledge reuse capability, and can be widely applied to the field of intelligent scheduling of complex scenes such as emergency rescue, industrial automation and urban public management.

The invention discloses a high-order multi-agent system control method with unknown input time lag and quantization, which comprises the following steps: S1) under the condition of unknown time-varying time lag and input quantization, carrying out system description on an uncertain high-order multi-agent system and introducing a lag uniform quantizer; s2) converting an uncertain high-order multi-agent system tracking control problem with unknown time-varying time-lag and input quantization into a bounded problem of a differential equation solution with time-lag; s3) constructing a dominant expression of the system and feasibility conditions for realizing bounded tracking according to the bounded problem of the time delay differential equation; and S4) performing control design according to a dominant expression of the system and bounded tracking feasibility conditions. The invention designs an adaptive finite time dynamic surface control scheme for a high-order multi-agent system with unknown input delay. Meanwhile, the finite time stability theorem is utilized to prove that all signals in the closed-loop system are semi-globally practical and stable in finite time.

The invention provides an adaptive high-performance consistent control method for a multi-agent system under denial of service (DoS) attack, and a sensing unit comprises a state sensing module carried on each agent, obtains body state information in real time, and shares information with other agents through an adjacent communication network; the information is used for error calculation and local control decision, and meanwhile, communication quality and whether interruption occurs are judged, so that the observability and anti-disturbance capability of the system are enhanced; a distributed control unit controller is deployed in each intelligent body, error mapping and performance constraint are carried out, a time-varying performance boundary is constructed, a control law and a self-adaptive estimation law are designed, a communication execution unit is responsible for transmitting a trigger signal, state estimation or control input generated by the controller among the intelligent bodies, intermittent DoS attacks can be tolerated, and the control law and the self-adaptive estimation law are designed. And an automatic retransmission and timeout judgment mechanism is provided, so that reliable transmission of key data is guaranteed. State estimation, performance recovery and efficient communication can be realized in a DoS attack environment.

The present disclosure provides a system for predicting customer churn and generating retention strategies. The system includes a data ingestion module that collects and normalizes customer interaction data and network telemetry data comprising latency, bandwidth, and packet loss metrics. A generative artificial intelligence (GenAI) labeling agent applies chain-of-thought reasoning to categorize this data based on contextual features and temporal patterns. A machine learning module executes time-series regression models to predict customer churn probabilities using the labeled datasets. Finally, a prescriptive GenAI agent generates actionable customer retention recommendations based on these predictions, which are delivered through an automated engagement system. The system integrates real-time data processing with artificial intelligence (AI)-driven analysis to identify at-risk customers and develop targeted retention strategies.

The invention discloses a multi-agent ecological collaboration method and system based on an MCP protocol, and the method comprises the steps: understanding a composite operation intention in a natural language request of a user through a large model, and dynamically planning a target agent sequence and a collaboration workflow from a plurality of field agents following an MCP protocol standard based on the composite operation intention; standardized tool interfaces of all domain agents are called in sequence through an MCP client side so as to execute corresponding domain service logic, intermediate execution results and state data are transmitted in real time in the process, finally, all output results are gathered and processed through an agent arrangement framework and returned to a user terminal, and a related global knowledge graph is synchronously updated. According to the method, the agent interaction standard is unified through the MCP, and the dynamic arrangement capability of a large model is combined, so that plug-and-play and flexible collaboration of cross-domain agents are realized, and the problems of difficulty in integration, solidification of a collaboration process and difficulty in automatic processing of complex cross-domain tasks caused by interface heterogeneity of a multi-agent system are solved.