Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

933 results about "Multi-agent system" patented technology

A multi-agent system (MAS or "self-organized system") is a computerized system composed of multiple interacting intelligent agents. Multi-agent systems can solve problems that are difficult or impossible for an individual agent or a monolithic system to solve. Intelligence may include methodic, functional, procedural approaches, algorithmic search or reinforcement learning.

Robot agent reinforcement learning training method and system in complex scene

The invention discloses a robot agent reinforcement learning training method in a complex scene, and the method comprises the steps: constructing a reinforcement learning algorithm environment and a state transition model which comprise a barrier, a dynamic target, environment constraints and other complex scenes and are suitable for a multi-agent system; an independent neural network is constructed for each robot agent by adopting a reinforcement learning algorithm; taking vectors of a given state, time sequence information and historical state information of the intelligent agent as input of the state transition model, and outputting a state transition probability and reward information of a prediction state; the action strategy and the action value output by the neural network are executed in the state transition model, and a new prediction state and reward information are generated; through adjusting hyper-parameters of the neural network, a large-scale distributed training architecture is used to carry out cooperative training on the decision network and the evaluation network, parallel learning and cooperative decision of multiple agents are realized, and performance and generalization ability of the agents in a complex scene are improved.
Owner:XIAMEN YUANTING INFORMATION TECH CO LTD

Dynamic load balancing method and system of AI model intelligent machine

The invention discloses a dynamic load balancing method and system for an AI model intelligent machine, and relates to the technical field of computer science, and the method comprises the steps: constructing an agent behavior strategy model through combining deep reinforcement learning and a multi-agent system MAS; constructing an intelligent scheduling model based on user request data and resource data, inputting the data into the model, performing resource demand prediction and task characteristic analysis, and outputting an optimal resource allocation scheme; constructing a dynamic load balancing function based on the optimal resource allocation scheme, and automatically adjusting the dynamic load balancing function when the network topology and the load mode change; collecting user feedback data, and performing deep analysis on the user feedback data to obtain a user satisfaction score and a service quality score as a basis for constructing a user feedback evaluation function; constructing a resource scheduling optimization model based on the intelligent scheduling model, the dynamic load balancing function and the user feedback evaluation function, and predicting a user experience strategy; and according to a prediction result, carrying out strategy adjustment and resource redistribution decision making.
Owner:SUZHOU JITIAN INFORMATION TECHNOLOGY CO LTD

Coal mining intelligent scheduling method based on artificial intelligence platform

ActiveCN119090243AAccurately reflect real-time statusStrong real-timeForecastingArtificial lifeData setEngineering
The invention discloses a coal mining intelligent scheduling method based on an artificial intelligence platform. The method comprises the following steps: S1, constructing a data set; s2, preprocessing the data set; s3, analyzing the preprocessed data set to generate an analysis result; s4, based on an analysis result, constructing and training a prediction model by adopting a variational auto-encoder and a graph neural network; s5, multi-agent deep reinforcement learning is adopted, a hybrid expert model and a distributed depth deterministic strategy gradient are combined, and an optimization model is constructed and trained; s6, predicting the fault of the equipment by using the prediction model, generating a prediction result, performing early warning in advance, and taking measures; s7, dynamically adjusting a production plan by using the optimization model according to the prediction result and the real-time data, performing resource scheduling, and optimizing resource allocation; and S8, establishing a feedback mechanism, collecting feedback information, and optimizing and improving a resource scheduling strategy. According to the invention, efficient intelligent scheduling is realized by using big data analysis, deep learning and a multi-agent system.
Owner:SHENHUA HOLLYSYS INFORMATION TECH CO LTD

Intelligent target distribution method and system based on deep reinforcement learning

The invention discloses an intelligent target allocation method and system based on deep reinforcement learning, particularly relates to the field of multi-agent systems, and is used for solving the real-time decision problem under multi-dimensional constraints in a dynamic confrontation simulation scene. Time, space and resource constraints are decomposed into independent models, and the decision complexity of a multi-agent system in a dynamic confrontation scene is reduced; by means of adaptive Monte Carlo sampling, prediction perception path planning and dynamic threshold value resource allocation, diversified high-quality candidate schemes are quickly generated; when the environment changes, the multi-layer influence propagation network and the spatial topological relation graph are used for positioning an affected agent, and scheme fragments are generated through local adjustment, so that global re-calculation is avoided, the overhead is reduced, and real-time response is ensured; meanwhile, an efficient and reliable optimal solution is screened out through resource delay coupling and path efficiency comprehensive evaluation in combination with multi-objective optimization and task consistency verification.
Owner:NO 15 INST OF CHINA ELECTRONICS TECH GRP

Task complexity driven graph semantic multi-agent collaborative decision-making method and system

The invention belongs to the field of natural language processing, and provides a task complexity driven graph semantic multi-agent collaborative decision-making method and system.The task complexity driven graph semantic multi-agent collaborative decision-making method comprises the steps that a task text is obtained and subjected to semantic coding to obtain a task semantic vector, evaluation is conducted based on the task semantic vector to obtain a complexity vector, and a task complexity score of the complexity vector is calculated; the task semantic vector and the complexity vector are fused to obtain a task representation vector, an agent capability relation graph is constructed, the participation probability of each agent node is obtained according to the task representation vector and the agent capability relation graph, and a dynamic agent combination scheme is formed; and performing task decomposition according to the agent combination scheme, constructing a sub-task dependency graph, scheduling the execution sequence of the sub-tasks through topological sorting, realizing cooperative execution of the agents, and generating a task result. According to the method, precise matching and efficient cooperation of the agent combination are realized, and the capability of processing complex tasks and the resource utilization efficiency of the multi-agent system are remarkably improved.
Owner:QILU UNIVERSITY OF TECHNOLOGY (SHANDONG ACADEMY OF SCIENCES) +3

Supply chain management system and method based on operation data

The invention relates to the technical field of supply chain management, in particular to a supply chain management system and method based on operation data, and the system comprises the steps: collecting market demands, production efficiency, logistics states and other multi-dimensional data through a data collection module, and generating prediction data through a multi-task learning model and quantum Bayesian deduction; based on the prediction data, the distributed collaborative decision-making module optimizes resource allocation of each node of the supply chain by using a multi-agent system and a self-organizing criticality algorithm to generate a final scheduling scheme; through resource pooling and virtualization technical means, the system realizes unified allocation of cross-regional resources, and performs dynamic self-correction through a feedback mechanism; according to the invention, the scheduling efficiency of the supply chain is improved, the inventory overstock risk is reduced, and the capability of dealing with market fluctuation is enhanced.
Owner:JIWU (CHONGQING) SUPPLY CHAIN CO LTD

Secure multi-agent system for privacy-preserving distributed computation

The present disclosure provides a system for secure compute using artificial intelligence agents. The system includes a hardware execution environment with one or more computerized processors and electronic storage media. The processors are configured to establish a secure agent comprising a secure state management module, an encrypted state transition management module, a threshold cryptography implementation, and a digital signature verification module. The system also includes a plurality of atomic agents, each configured to perform a composite task and comprising a task-specific execution module, a state management interface, and a communication module. An orchestrator agent coordinates secure execution of the atomic agents and includes a task distribution module, a result aggregation module, a workflow management module, and a security policy enforcement module. The orchestrator agent integrates encrypted outputs from the atomic agents to perform composite tasks while maintaining data integrity and security through the secure state management module.
Owner:K2 NETWORK LABS INC

Multi-agent system-based information processing method and multi-agent system

The present disclosure provides a multi-agent system-based information processing method and a multi-agent system. The multi-agent system comprises multiple agents. The method is applied to a target agent, and the target agent is any agent among the multiple agents. The method comprises: determining information to be processed corresponding to a target agent; on the basis of an information processing model, when said information does not match a function corresponding to the target agent, determining an agent to which a function matching said information corresponds; and sending said information to the matching agent for processing. In the present disclosure, information to be processed can be quickly and accurately transferred between agents by utilizing the analytical capability of an information processing model, and is processed by a suitable agent, thereby effectively improving the processing effect of tasks.
Owner:ALIBABA (CHINA) CO LTD

Logistics scheduling method and system

The invention relates to the field of logistics information processing, in particular to a logistics scheduling method and system.The method comprises the steps that multi-source data such as traffic flow, weather, orders and logistics network states are collected in real time, and dynamic logistics state data are generated through a data fusion model; on the basis of the data, performing fine-grained modeling of path fragments by using distributed simulation nodes, performing simulation of the state of the path fragments in combination with a cellular automaton model, and performing adaptive adjustment by using a reinforcement learning algorithm to generate optimized path decision data; global state modeling and resource scheduling optimization of a multi-layer feedback interaction mechanism are carried out through a multi-agent system, and finally dynamic prediction and automatic adjustment of a global logistics state are realized through model prediction control and a multi-layer self-correction mechanism. According to the invention, the flexibility and response speed of logistics scheduling are effectively improved, and efficient execution of logistics tasks is ensured.
Owner:BAODING HONGYUAN SHUNDA LOGISTICS CO LTD

Multi-agent collaboration method based on large language model

The invention discloses a multi-agent cooperation method based on a large language model, and relates to the field of agent cooperation control, and the method comprises the steps: constructing a multi-agent system; establishing a multi-agent coordination resource allocation model; a task allocation problem in the resource allocation model is converted into a multi-objective optimization problem, and optimization objectives comprise the minimum task completion time and the optimal resource utilization rate; and solving a multi-objective optimization problem by using an improved particle swarm optimization (PSO) to obtain an optimal cooperation scheme among the master control agent, the task creation agent, the intention arrangement agent and the at least one professional agent. The improved particle swarm optimization (PSO) evaluates the uncertainty of each candidate solution through multiple times of random sampling, and when the uncertainty exceeds a threshold value, cross validation is performed through a multi-agent voting mechanism. For uncertainty accumulation of a multi-agent system under a complex cognitive task, the efficiency and stability of collaborative decision and task scheduling of the multi-agent system are improved.
Owner:北京长河数智科技有限责任公司 +1

Text generation system and method based on multi-agent cooperation mechanism MOPAR

The invention provides a text generation system and method based on a multi-agent cooperation mechanism MOPAR, and the system comprises a matching agent which is connected with a field multi-agent system, and is used for obtaining the writing demands of a user, generating a matching prompt word according to the writing demands, and transmitting the matching prompt word to the field multi-agent system, performing field matching with the field multi-agent system through the matching prompt word, and performing optimization according to feedback information of an reflection agent in the field multi-agent system; and the field multi-agent system comprises a plurality of multi-agents in different fields, is connected with the matched agent and is used for receiving the matched cue word, acquiring the multi-agent in the corresponding field according to the matched cue word and generating text content required by a user through the multi-agent in the corresponding field on the basis of a multi-agent coordination mechanism MOPAR. According to the method, a cooperation mechanism among multiple agents is introduced, so that a more efficient, professional and creative text generation service is provided for the user.
Owner:数字郑州科技有限公司

Coordination control method for smart power grid

The invention relates to the technical field of power grid coordination control, and provides a coordination control method for a smart power grid, which comprises the following steps: S1, collecting voltage, current, frequency and load data in real time by deploying sensors and monitoring equipment, S2, processing the data by using a big data analysis technology, extracting load trend and fault early warning information, and carrying out early warning on the load trend and the fault early warning information. Real-time data collection is realized by deploying sensors and monitoring equipment, data analysis and load prediction are performed by using big data and a machine learning technology, an optimized objective function is constructed, fine coordination and a global optimal solution are realized by using a multi-agent system and a distributed optimization algorithm, and meanwhile, energy privacy is protected. The reliability of the power grid is improved through intelligent fault detection and a quick response mechanism; according to the technical scheme, interaction between the power grid and users is enhanced, demand side management is achieved, an efficient safety monitoring system is established, multi-level protection measures are taken, safe and stable operation of the power grid is ensured, and the problem that optimization and coordination are not comprehensive in the prior art is solved.
Owner:SHANGHAI HUADIAN ELECTRIC POWER DEV CO LTD

Robot cluster control method and system based on hierarchical multi-agent

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.
Owner:WUHAN UNIV

Data-based predefined time heterogeneous multi-agent formation collision avoidance method

The invention discloses a data-based predefined time heterogeneous multi-agent formation collision avoidance method. The method comprises the following steps: establishing a nonlinear heterogeneous multi-agent system; designing a bimodal artificial potential field function to perform dynamic obstacle avoidance and prevent regional escape; establishing a self-adaptive robust controller used for generating an obstacle avoidance safety motion trail of the root leader; designing a self-adaptive formation zooming mechanism of the leader, and constructing a predefined time affine observer of the follower based on the self-adaptive formation zooming mechanism; designing a unified obstacle function; constructing a virtual control law for processing tracking errors based on the unified obstacle function; designing a neural network estimator; designing controllers of the leader and the follower according to the virtual control law; and forming a collision avoidance decision of the heterogeneous multi-agent formation based on a self-adaptive robust controller, a predefined time affine observer, a neural network estimator and controllers of the leader and the follower. According to the method, safe, efficient and robust cooperative control of the formation in a complex environment is realized, and the safety and task execution efficiency of the heterogeneous multi-agent formation in a limited and unknown environment are remarkably improved.
Owner:DALIAN MARITIME UNIVERSITY

Visual algorithm self-training method based on multi-agent collaborative optimization

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.
Owner:ANHUI HEQING INTELLIGENT ROBOT CO LTD

Multi-agent robust specified time state estimation method based on discrete continuous mixing

The invention discloses a multi-agent robust specified time state estimation method based on discrete continuous mixing, and belongs to the field of distributed state estimation of an agent system, and the method comprises the following steps: S1, analyzing the uncertainty of a multi-agent system and a measurement noise model, and building a system dynamic equation; s2, designing a transformation matrix based on a null space and a system dynamic equation, and constructing a multi-agent system consistency error; s3, constructing a state space equation of the state observer based on the consistency error of the multi-agent system; and S4, based on the state space equation of the state observer, realizing specified time convergence of the estimation error through the power return-to-zero characteristic of the power zero matrix. According to the multi-agent robust specified time state estimation method based on discrete continuous mixing, state estimation is carried out only by using relative output information between neighbors without depending on relative input information between the neighbors, use of communication channels is avoided, and the method has the characteristic of network attack immunity.
Owner:BEIJING INST OF TECH

Cooperative transportation robust control method of flexible constraint multi-agent system

A collaborative transportation robust control method for a flexible constraint multi-agent system comprises the following steps: establishing the multi-agent system, and taking tether tension generated by a load on each agent as an uncertain nonlinear term of the multi-agent system; an RBF neural network is constructed, and approximation prediction is carried out on the uncertain nonlinear term through the RBF neural network; constructing a test data set by using a multi-agent system to obtain an ideal tether tension value as a data label value; according to the data label value, updating parameters in the RBF neural network through a gradient descent method, and deploying the parameters into an uncertain nonlinear term; and designing a non-singular terminal sliding mode adaptive controller based on RBF neural network prediction of supervised learning, and performing control compensation on the uncertain nonlinear term. According to the method, stable transportation of the tethered multi-agent can be ensured, and model calculation is simple.
Owner:NORTHWESTERN POLYTECHNICAL UNIV

Multi-agent unmanned aerial vehicle search task energy optimization method based on entropy maximization strategy

The invention discloses a multi-agent unmanned aerial vehicle search task energy optimization method based on an entropy maximization strategy, and belongs to the field of unmanned aerial vehicle search task energy optimization. The implementation method comprises the following steps: modeling a multi-region search task of the multi-agent unmanned aerial vehicle, constructing an energy consumption model of the unmanned aerial vehicle, taking the minimum energy consumption of a multi-agent system as a priority target, adopting a reinforcement learning algorithm with maximized multi-agent entropy, making a decision on the action of each unmanned aerial vehicle, and obtaining a multi-region search task of the multi-agent unmanned aerial vehicle. According to the method, the randomness of strategy implementation of each agent is enhanced, premature falling into a suboptimal solution is avoided, real-time adjustment is performed on the next action decision of each unmanned aerial vehicle according to the environment and energy consumption observed by other unmanned aerial vehicles based on a method of centralized training in distributed execution, and when the unmanned aerial vehicle arrives at a target area, the unmanned aerial vehicle is subjected to real-time control. And carrying out full-path search on the target area to ensure the optimality of solving sub-problems, namely, realizing energy optimization of a multi-unmanned aerial vehicle search task based on an entropy maximization strategy.
Owner:BEIJING INST OF TECH

Data braiding system implementation method and device based on dialogue and multi-agent collaboration

The invention provides a dialogue and multi-agent collaboration-based data knitting system implementation method, which comprises the following steps that: a main agent performs user intention recognition, splits and distributes a data processing task according to the user intention, and issues a data retrieval task to a data retrieval agent in a domain agent; the data retrieval agent executes a data retrieval task on the managed data domain to obtain a retrieval result, the main agent issues a data calculation task to the data calculation agent in the domain agent, and the data calculation agent executes the data calculation task to obtain a result data set; and the main agent executes a data fusion task on the retrieval result and / or the result data set, and returns the fused data set to the user. According to the invention, through the precise division and efficient cooperation mechanism of the main agent and the domain agent in the multi-agent system, the implementation process of the data knitting system is simplified, the system is easy to expand, and the high efficiency and intelligence of the enterprise-level data knitting process are realized.
Owner:HANGZHOU EASTCOM SOFTWARE TECH

Consistency control method and system for second-order nonlinear multi-agent system

The invention relates to the field of multi-agent system control, and particularly provides a second-order nonlinear multi-agent system consistency control method and system, and the method comprises the steps: building a second-order nonlinear multi-agent dynamic system model with a plurality of same agents; establishing a leader following finite time consistency sufficient condition; establishing a distributed sliding mode surface based on a second-order nonlinear multi-agent dynamic system model; obtaining a control protocol by combining a preset dynamic event triggering condition, a preset adaptive law and a distributed sliding mode surface, and introducing the control protocol into a distributed time triggering controller to obtain a novel controller; and verifying the novel controller by utilizing a condition that the leader follows the finite time consistency is sufficient, obtaining a stable expected trajectory of the multi-agent, and completing the control of the consistency of the second-order nonlinear multi-agent system. According to the invention, trajectory tracking and consistency control of the leader following intelligent agent system are realized, and external disturbance can be effectively inhibited.
Owner:GUANGDONG UNIV OF PETROCHEMICAL TECH

Multi-agent path planning method, device and equipment

The invention discloses a multi-agent path planning method, device and equipment, and the method comprises the steps: dividing a map according to first grids of a preset size, carrying out the global planning of all agents on the map, and generating a global path, the global path being a road section passing through a plurality of first grids from a starting point to a target point; on the basis of each path section of the global path, local planning is conducted on all agents, a local path is generated, and each path section is a road section formed by the center points of every two adjacent first grids; real-time data are obtained by monitoring changes of dynamic obstacles and dynamic targets in a map in real time, and the local path and / or the local path are / is updated and planned according to the real-time data to obtain an updated path. Potential collision risks can be quickly found, obstacle avoidance measures can be taken in time, and the safety of a multi-agent system and the smooth completion rate of tasks are improved.
Owner:XIAMEN YUANTING INFORMATION TECH CO LTD

Distributed formation control method driven by recursive balance network under communication attack

The invention provides a distributed formation control method driven by a recursive balance network under a communication attack, and relates to the technical field of cooperative control of a multi-agent system, and the method comprises the steps: constructing a distributed multi-agent system model, and constructing an RBN controller heterogeneous communication network architecture and a DoS attack model; the RBN controller design is optimized, the distributed RBN controller architecture is realized, the stability of the RBN controller is analyzed based on the shrinkage mapping theory, and the exponential convergence of the system state difference is proved by constructing a Lyapunov function; training the optimized RBN controller by adopting a difficulty priority confrontation training strategy, designing a multi-objective loss function, and dynamically adjusting the training weight of each difficulty level; and simulating the distributed multi-agent system optimized by the above steps, testing the robustness of the distributed multi-agent system under incremental DoS attack intensity, and performing comparative analysis of heterogeneous and isomorphic communication network configuration and comprehensive performance comparison of an RBN controller and a traditional MPC method.
Owner:CHANGCHUN UNIV OF SCI & TECH

Multi-agent reinforcement learning task planning and control method under space-time task driving

The invention provides a multi-agent reinforcement learning task planning and control method under space-time task driving. The method comprises the following steps: S1, establishing a reinforcement learning controller training architecture of a signal sequential logic task under a multi-agent system; s2, establishing a self-attention action compensation mechanism among the multi-agent systems; s3, constructing a robust value filtering baseline corresponding to the signal sequential logic task according to the task framework; s4, according to the environment information, soft constraints are generated for intelligent agent actions; s5, constructing a conflict detection and task replanning mechanism of the multi-target task according to the compensation action degree; and S6, based on the constraint conditions, iteratively training controller parameters so as to provide a control law online to meet the STL task requirements. According to the method, the controller parameters are learned in a reinforcement learning mode, the method adapts to the online solution control law in a complex environment, the given control law better conforms to the actual conditions of the external environment and the internal dynamic system, and the burden of the online calculation control law is greatly reduced.
Owner:SHANGHAI JIAOTONG UNIV

Multi-agent construction method and apparatus, task processing method and apparatus, computing device, storage medium, computer program product, and chip

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.
Owner:HUAWEI TECH CO LTD

Automatic medical record writing system and method based on multi-modal input and multi-agent driving

The invention relates to the technical field of medical information, in particular to a method and a system for processing medical record documents by utilizing artificial intelligence, and particularly relates to a method and a system which can receive and process multi-modal input information including images, videos and voices, can work cooperatively through a multi-agent system and can process the medical record documents. The invention discloses a system for automatically generating, controlling quality and safely inputting medical records in combination with a medical knowledge base and an implementation method thereof. The invention relates to an automatic medical record writing system based on multi-modal input and multi-agent driving. The automatic medical record writing system comprises a multi-modal input module, a multi-agent processing platform and a safety intranet input module. According to the method, establishment of the data channel between the medical intranet and the external AI system is proposed for the first time, the problem of medical intranet isolation is solved, industrial pain points are solved in a breakthrough mode, and a new medical AI landing path is developed.
Owner:YANBIAN UNIV

Multi-agent communication strategy learning method based on human feedback

The invention provides a multi-agent communication strategy learning method based on human feedback. The method comprises the steps that S1, a multi-agent reinforcement learning model is constructed, modeling is conducted on a multi-agent system, a dynamic communication topological structure in the multi-agent system is constructed, and the overall calculation process of the model is determined; s2, an offline pre-training process of the multi-agent system is carried out, training is carried out only through historical trajectory data in the process, interaction is not participated, and a suboptimal behavior strategy is rapidly learned; s3, collecting human feedback reward data and historical training data of the multi-agent system based on the specific task scene model; and S4, dynamically adjusting a communication strategy, carrying out auxiliary online training according to reward data fed back by human beings, helping the multi-agent system to better carry out communication decision making, and improving learning efficiency. Human feedback data is applied to multi-agent system training, and the limitation of a traditional multi-agent reinforcement learning method is effectively improved.
Owner:UNIV OF ELECTRONICS SCI & TECH OF CHINA

Sea area cross-medium unmanned system task allocation method based on graph attention network and deep reinforcement learning, and electronic equipment

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.
Owner:SHANGHAI UNIV

Resource elastic scaling method and system based on average consistency of multi-agent system

The invention belongs to the technical field of computers, and discloses a resource elastic scaling method and system based on the average consistency of a multi-agent system, and the method comprises the steps: obtaining the state information of a current server, and estimating user input based on the state information and a scaling decision at the last moment; an event trigger is designed, and if the event trigger based on the edge is triggered, the server sends own state information to the neighbor and receives the state information of the neighbor; if the event trigger based on the node is triggered, the server records the state of the load observer of the server and the information of the self-adaptive variable; and forming a scaling decision according to the state information of the server at the last triggering moment, the state information of the neighbor server and the state information of the load observer, executing the scaling decision and updating the state information of the server. According to the method, on the premise that global information of communication topology is not used, the security resources of the server cluster under DSS attack are elastically expanded and contracted, and the server cannot be misguided by tampered information.
Owner:SHANDONG COMP SCI CENTNAT SUPERCOMP CENT IN JINAN +1

Multi-agent system distributed consistency optimization method considering unbalanced directed communication graph

The invention relates to a multi-agent system distributed consistency optimization method considering an unbalanced directed communication graph, and belongs to the field of multi-agent system coordination control. The method comprises the following steps: S1, establishing a first-order dynamic model of a multi-agent system; s2, constructing an unbalanced directed communication topology network of the multi-agent system, and describing a communication relationship between agents through an adjacent matrix; s3, defining a global optimization target to minimize the sum of local cost functions of all agents; s4, constructing a distance-based adaptive precise penalty function, and converting a set constraint optimization problem into a set-free constraint optimization problem; s5, designing an adaptive coupling gain to solve a distributed optimization problem, and designing an auxiliary variable to estimate a left eigenvector corresponding to a zero eigenvalue of the Laplacian matrix; and then updating the state variable and the auxiliary variable of the intelligent agent according to the estimated value, and solving the problem of consistency optimization of the multi-intelligent-agent system of which the cost function cannot be differentiated.
Owner:CHONGQING JIAOTONG UNIV

Country land space carbon emission assessment method

The invention relates to the technical field of environmental science and information, in particular to a rural land space carbon emission assessment method, which collects real-time data through a distributed sensor network and an unmanned aerial vehicle remote sensing technology, analyzes and extracts key features by using an adaptive variational auto-encoder and topological data, and effectively identifies a land utilization mode. The graph neural network and the Bayesian optimization generative adversarial network are combined to dynamically evaluate and predict carbon emission, and uncertainty quantitative data are generated; a multi-objective genetic algorithm and a game theory model are used for optimizing land utilization layout, an optimization scheme is executed on a block chain through an intelligent contract and a multi-agent system, and automatic management and dynamic adjustment are achieved; according to the method, the accuracy and the real-time performance of rural land carbon emission evaluation are remarkably improved, and a scientific basis is provided for low-carbon sustainable development.
Owner:NINGXIA UNIVERSITY