113 results about "Decision agent" patented technology

The invention discloses a financial network security defense method and system based on multiple Agents and a dynamic large model. A detection Agent is deployed in an edge layer, financial network node flow data and system logs are collected in real time, time sequence features are extracted through a lightweight convolutional network, and a preliminary anomaly score is generated. And the cloud layer constructs a decision Agent, receives the feature abstract transmitted by the edge node in an encrypted manner, inputs the feature abstract into a dynamic large model for multi-modal feature fusion, and outputs defense action probability distribution. And the intelligence Agent constructs a cross-institution federated learning network. And constructing a dynamic game engine, constructing a revenue matrix based on the attack cost and the defense revenue, solving a Nash equilibrium strategy, and generating an optimal defense instruction set. And dynamically allocating detection tasks according to the threat level and the edge computing power state. According to the method, efficient acquisition and analysis are realized, the abnormal behavior recognition capability is improved, support is provided for making a defense strategy, the defense strategy is optimized, and the intelligent, automatic and efficient levels of defense are improved.

The invention provides an agent construction method and system based on a large language model, a medium and equipment, and relates to the technical field of decision agent construction. According to the method, an appropriate large language model is selected, a series of prompt project texts are established for the large language model, target codes are generated as required by utilizing the large language model and prompt projects, and class library functions of a network model library, a reinforcement learning algorithm and a simulation training environment can be correspondingly called by running the codes. Finally, auxiliary construction and training of the decision-making agent are realized, and the problems in the existing decision-making agent construction and training process are solved.

The invention relates to a construction method of a cooperative combat decision-making agent for ground unmanned equipment, and aims to solve the problem of space dimension disaster of a complex cooperative combat task. The DRL solution space is effectively compressed, the exploration efficiency is improved, and meanwhile intelligent decision making of tasks with different granularities in the whole combat process is achieved; aiming at the problem of generating a'task layer 'combat command action strategy, a cooperative combat decision-making agent network model is constructed to realize the unified coordination control from the effective representation of complex state input to the combat action; by constructing a distributed training framework, the sampling and training efficiency is improved, and high-throughput asynchronous parallel training of a cooperative combat decision-making agent network model is realized; by establishing a combat decision agent learning algorithm based on deep reinforcement learning and solving the combat decision agent learning algorithm, the learning efficiency and final performance of an agent network model are effectively improved.

The invention relates to an app automatic execution and test system based on multi-agent collaborative perception decision, and the system comprises three agents and an upper computer which is used for collecting information and carrying out interactive execution: an execution decision agent receives the output of a planning strategy recommendation agent and a perception agent, serves as input information, generates an instruction to control the upper computer, and carries out the execution of the decision. And interacting with the to-be-tested system to complete the execution task of the to-be-tested system. The three agents are an execution decision agent, a planning strategy recommendation agent and a perception agent, and the three agents jointly form a decision system of the app automatic execution system. After a task target is given, the system can interact with a system to be tested, text recognition, icon recognition, keyboard recognition, layout recognition and anomaly recognition are carried out on a UI page where the system is located through a sensing agent, and meanwhile, system information is stored in a knowledge base after a planning strategy recommendation agent carries out offline exploration; and the execution decision-making agent autonomously reasones out an execution action according to information input of the perception agent and the planning strategy recommendation agent so as to complete execution of a task target. According to the method, multiple agents with different capabilities are combined to work cooperatively while the reasoning capability of the large model is utilized, so that the accuracy and the stability of the model are greatly improved.

The invention relates to a multi-agent medical diagnosis and treatment system which comprises a plurality of agents. The plurality of agents comprise: a task planning agent analyzes input content and generates a corresponding task process, and the task planning agent sequentially issues task instructions to a data management agent, a tool use agent and a medical decision agent according to the task process; the task instructions comprise a data task instruction, a tool task instruction and a decision task instruction; the data management agent extracts patient data from the database and sends the patient data to the task planning agent according to a data task instruction issued by the task planning agent; the tool using agent performs feature extraction processing on the patient data according to the patient data and the tool task instruction issued by the task planning agent so as to obtain key features and send the key features to the task planning agent; and the medical decision-making agent carries out diagnosis and treatment reasoning according to the key features and the decision-making task instruction issued by the task planning agent, and a diagnosis report is obtained and displayed.

The invention relates to the technical field of artificial intelligence, can be applied to business system platforms of financial science and technology, medical treatment and health and the like, and discloses a task processing method, device and equipment based on multi-agent cooperation and a medium. And constructing a sub-task dependency graph, sequentially scheduling and executing the sub-tasks, and performing parameter completion to obtain the completed sub-tasks. And tracking the execution progress and the historical record of the completion subtask through a preset progress agent, and generating an executable operation decision by using a preset decision agent. If the task execution does not reach the expected effect, feeding back difference information and a correction suggestion, adjusting an operation decision and generating an updating operation; if the task achieves the expected effect, task completion information is sent to the progress agent, and the state is updated to be task completion. According to the method, the perception accuracy is improved, a task dependence tracking and feedback correction mechanism is provided, and a cross-application automatic task is successfully realized.

The invention relates to the technical field of artificial intelligence, can be applied to business scenes such as financial science and technology and medical health, and discloses an anomaly analysis method, device and equipment based on multi-agent collaboration and a medium. The method comprises the following steps: generating fusion data through processing of a data fusion agent, extracting abnormal feature information through a data analysis agent, generating an abnormal analysis result and a decision instruction through a decision agent, collecting decision feedback through a feedback optimization agent, and analyzing and generating an optimization instruction for optimizing the data analysis agent and the decision agent. According to the method, closed-loop processing of data acquisition, fusion, analysis, decision and feedback optimization is realized through cooperation of multiple agents, so that multi-source heterogeneous data is efficiently integrated and deeply analyzed, the accuracy and adaptability of analysis and decision are continuously improved in combination with feedback optimization, and the timeliness and reliability of anomaly recognition and response are improved.

The invention discloses a cluster-oriented multi-agent cooperative task planning method, which comprises the steps of constructing a cruise simulation interaction scene, and determining data input to a reinforcement learning network model, the reinforcement learning network model being used for outputting a time sequence of a plurality of sub-tasks, an agent type corresponding to each sub-task and an agent number; converting output data of the reinforcement learning network model into cruise constraint conditions; and performing branch and bound search of an optimal combination scheme according to cruise constraint conditions, planning the action starting time and ending time of each agent, and completing agent sub-task planning. According to the method, a task allocation combination problem and a task execution optimization problem are decoupled, and rapid multi-agent task planning is realized. In the training stage, a task formation is generated, a task allocation decision agent is constructed, and a plan containing the type and number of agents required by each sub-task is generated through a reinforcement learning algorithm; and generating an agent task execution scheme including agent task allocation and execution time in the task.

The invention discloses a large model material formula design and evaluation method and system based on multi-agent collaboration and a storage medium, and relates to the technical field of artificial intelligence auxiliary material research and development and multi-agent systems. Comprising the steps of receiving target material performance parameters and constraint conditions input by a user through a computer interaction interface; according to the method, a plurality of initial formulas are output by setting a generation agent, and formulas which do not meet environmental protection standards are removed in combination with a mechanism agent, so that the problems of frequent violation of a rubber vulcanization ratio, low manual screening efficiency, coating forbidden solvent omission and the like in an existing monomer model and a manual post-treatment scheme are effectively solved; and the evaluation agent can synchronously estimate the rationality of the formula, and the decision-making agent outputs the optimal formula based on the comprehensive score, so that the experimental verification link of the invalid formula is reduced, and the final formula is ensured to meet the use and production requirements.

The invention provides a multi-Agent-based workshop management system and a cross-workshop migration method and system. The multi-Agent-based workshop management system comprises a sensing layer, an intelligent layer, an execution layer and a communication layer, a data acquisition module of the sensing layer is used for acquiring sensing data in a physical scene, and a sensing Agent of the sensing layer generates a corresponding virtual mirror image platform according to the sensing data and outputs an analysis result; the intelligent layer comprises a decision-making Agent and a coordination Agent, the decision-making Agent dynamically generates a global or local decision-making result according to an analysis result, and the coordination Agent monitors and evaluates the decision-making result through a preset mechanism and outputs an optimization strategy; the intelligent layer transmits the decision result and the optimization strategy to the execution layer; an execution Agent of the execution layer deploys a lightweight model through an edge calculation module, and analyzes a decision result and an optimization strategy into an equipment control signal to control equipment operation; and the communication layer provides an information interaction channel for the Agent of each layer. The limitation of a traditional layered architecture is broken through, and a self-organized, self-adaptive and self-optimized distributed intelligent ecological architecture is constructed.

The invention provides a hybrid flow shop dynamic scheduling optimization method under demand disturbance. Firstly, a Markov decision process (MDP) model is constructed, a state set of the model is composed of a workpiece state and a machine state, and a two-dimensional action set and a specific reward function are designed so as to guide production to be efficiently delivered on time. Secondly, constructing a state feature extraction network of the decision-making agent by adopting a bidirectional long-short term memory network (Bi-LSTM), and processing time sequence dependence; afterwards, in the training process, a near-end strategy optimization algorithm (PPO) is combined with a potential function-based reward shaping method, so that the training stability and efficiency are improved. And finally, in the scheduling process, demand disturbance is continuously monitored, real-time adjustment is performed by using the trained intelligent agent, and smooth and efficient production is ensured. According to the method, the production efficiency is remarkably improved, the resource utilization is optimized, the production flexibility is enhanced, the production cost is reduced, the product quality and customer satisfaction are improved, the intelligent management of the production process is realized, and the market competitiveness and adaptability of enterprises are enhanced.

The invention provides a nuclear power safety analysis report examination method and an applicable system and a readable medium thereof, and relates to the technical field of nuclear power. The review method comprises the following steps: converting each design file into document fragment data through a knowledge maintenance agent, and storing the document fragment data into a knowledge base; converting the nuclear power safety analysis report into a plurality of to-be-examined text blocks through a document analysis agent; extracting at least one technical expression statement and a corresponding retrieval problem and a matched knowledge fragment from each to-be-examined text block through a retrieval composite agent; performing consistency judgment on each technical expression statement, and a retrieval problem and a matched knowledge fragment corresponding to the technical expression statement through a technical review agent to obtain initial review data; and obtaining a final examination decision agent and a historical examination database, and generating corresponding final examination data through the final examination decision agent according to the historical examination database and the initial examination data.

The technology described herein relates to systems, methods, and computer storage media, among other things, for determining whether an electronic transmission (e.g., associated with an electronic payment transaction) should be blocked (e.g., based on being a fraudulent transaction). In embodiments, a policy-based reinforcement learning risk decision agent is used to make these determinations for a plurality of stages associated with the electronic payment transaction (e.g., a pre-authorization stage, a post-authorization stage, and a delay-captured stage). The policy-based reinforcement learning risk decision agent can be trained using previous electronic payment transaction data for previous electronic payment transactions. For example, this particular agent can be trained using pre-authorization electronic payment transaction data, post-authorization electronic payment transaction data, and delay-captured electronic payment transaction data for each of the previous electronic payment transactions.

The present application relates to an integrated customer service method and system based on multiple agents, wherein the method includes: processing consulting questions raised by active incoming users through a dialogue management agent, obtaining multi-dimensional data information and generating dialogue responses to the consulting questions; based on the feedback of the active incoming users after the dialogue response, obtaining the consulting intention of the active incoming users through analysis by an intention recognition agent; based on the consulting intention and recent activity records of the active incoming users, determining the outgoing call operation to be performed through an outgoing decision agent; and then executing the outgoing call operation through an outgoing execution agent. Through the present application, integrated customer service of multiple agents is realized, and the collaborative division of labor of multiple different agents is achieved, each focusing on its specific business process, thereby providing better services to customers. It is also possible to proactively contact customers by analyzing customer data, track customer issues or conduct proactive marketing, and effectively improve customer satisfaction.

The invention belongs to the technical field of medical auxiliary diagnosis, and particularly relates to an AI-based LoRA fine-tuning medical decision Agent system and an implementation method. The multi-modal data acquisition module is used for acquiring vital sign data, medical image data, laboratory inspection data and electronic medical record text data of a patient in real time; the dynamic weight adjustment LoRA fine adjustment module is used for carrying out low-rank adaptive fine adjustment on a pre-trained medical decision model by introducing a time attenuation factor, a data importance weight and a modal emergency degree coefficient based on the multi-modal data so as to generate a personalized decision model for the current patient; the multi-modal risk assessment module is used for fusing feature vectors output by the fine-tuned personalized decision-making model, constructing a comprehensive assessment function in combination with an attention mechanism and a feature interaction coefficient, and realizing dynamic quantitative assessment of the illness state risk of the patient; according to the method, the timeliness, the importance and the scene emergency degree of the multi-modal data can be dynamically balanced.

The invention belongs to the technical field of hydraulic engineering supervision, and particularly relates to a hydraulic engineering supervision system based on big data. Comprising a data acquisition and preprocessing module used for collecting and processing a multi-source heterogeneous data set; the multi-modal feature extraction and alignment module is used for generating a node feature matrix; the space-time degradation modeling and fusion module is used for predicting and generating an evolution trajectory of the key performance indexes of the water conservancy project; the health trajectory prediction and risk decision module is used for calculating the future failure probability of the structure and determining whether to start intervention or not by adopting a reinforcement learning decision agent; the active intervention strategy optimization module is used for generating a group of optimal maintenance strategies; the parameterization maintenance instruction generation module is used for converting the operation instruction into a standardized operation instruction; and the digital twin visualization and execution feedback module is used for feeding back and updating the time-space diagram attention network model. According to the method, the accuracy and the reliability of predicting the long-term evolution trend of the key performance index are remarkably improved.

The invention provides a disease consumable recommendation method and system based on multi-agent cooperation, electronic equipment and a medium, and relates to the technical field of medical consumable recommendation. According to the technology of the invention, the related data of disease consumables are obtained based on the data sensing agent, and feature extraction is carried out on the related data of the disease consumables; constructing a consumable knowledge base based on the consumable related data; based on the extracted features, matching the AI decision agent in a consumable knowledge base, and outputting a plurality of intelligent recommendation results; the multiple intelligent recommendation results are fused, a medical consumable recommendation scheme is generated, and the service execution agent executes related services based on the medical consumable recommendation scheme. The disease type consumable recommendation technology can realize full-process intelligent management from disease type identification to consumable recommendation, has strong learning ability, reasoning ability and decision-making ability, and can provide accurate and personalized consumable recommendation services for different disease types.

The invention discloses a vehicle-road cooperation signal control method based on a large model Agent, relates to the technical field of intelligent traffic control, and aims to solve the problems of signal control response lag and insufficient V2X scheme prediction capability in the prior art. The method comprises the following steps: S1, constructing a V2X collaborative architecture driven by a large model Agent, wherein the V2X collaborative architecture comprises a sensing Agent, a decision Agent, an execution Agent and a communication Agent; s2, constructing a knowledge graph database containing various traffic event coping strategies to realize event-strategy-influence dynamic association; s3, deploying a lightweight model to a roadside edge calculation unit, and generating a signal phase scheme through the lightweight model; and S4, polling traffic flow sudden change indexes, and performing decision impact evaluation to formulate a dynamic response mechanism. By constructing a V2X collaborative architecture driven by a large model Agent, dynamic traffic flow millisecond-level decision, multi-target global optimization and emergency scene adaptive control are realized, and the traffic efficiency of an intersection and the system robustness are improved.

The invention discloses an alarm studying and judging system and method based on multi-agent cooperation. Comprising an alarm access module, a multi-agent collaborative research and judgment engine and a result output module, the alarm access module is used for acquiring original alarm data and generating a structured alarm object after preprocessing; the multi-agent collaborative research and judgment engine comprises a plurality of special agents and a task orchestrator; the plurality of special agents comprise an entity extraction agent, a problem generation agent, a tool calling agent and a research and judgment decision agent; the entity extraction agent extracts and marks an entity list; the question generation agent generates a study and judgment question list; the tool calls the intelligent agent to obtain and integrate query results; the research and judgment decision agent generates a research and judgment result; and the result output module is used for writing the research and judgment result and the original alarm data back to the security information and event management platform. According to the invention, through multi-agent division cooperation and hybrid reasoning, the problems of low research and judgment efficiency and poor accuracy in an alarm scene are solved.

The invention relates to a non-signalized intersection traffic decision-making method based on a large model enabling reinforcement learning decision-making framework, and belongs to the technical field of automatic driving. The method comprises the following steps: firstly, acquiring an environment map and a vehicle state, providing coarse-grained reference actions based on a navigation reference model of classical path planning and trajectory tracking, and then generating a reward function through a large model by adopting a chain reasoning structure based on designer-suggestor-optimizer; based on the reference action and the reward function, the vehicle decision-making agent learns a driving strategy based on a reinforcement learning framework; and finally, establishing a rule-based interaction field, and finely adjusting the driving strategy output by the reinforcement learning framework to obtain a final control strategy. The reward design of the invention gets rid of excessive dependence on expert knowledge, and the design of the reference action can significantly reduce the exploration dimension and accelerate strategy learning.

The invention provides a long video understanding method and system based on sparse sampling in the technical field of computer vision, and the method comprises the steps: S1, dividing each long video, decoding each sub-video into frames, and carrying out the uniform sampling of each frame; s2, extracting global features of each long video, fragment-level features of the sub-videos and frame-level features of the frames, and constructing a multi-granularity video database based on each sub-video, the global features, the fragment-level features and the frame-level features; s3, analyzing the long video query request to obtain a target object and a clue object; s4, the planning decision Agent plans a retrieval strategy based on the target object and the clue object; s5, the interactive Agent performs retrieval operation on the multi-granularity video database based on the retrieval strategy; and S6, verifying the retrieval result to obtain a verification result, and iterating the retrieval strategy based on the verification result, or outputting the retrieval result. The method has the advantage that the accuracy and efficiency of long video understanding are greatly improved.

The invention provides a meteorological decision intelligent processing method and device based on an intelligent agent and electronic equipment, and relates to the field of data processing, and the method comprises the steps: collecting original meteorological data from meteorological observation equipment, satellite data and a numerical prediction model; in response to the detected user instruction, constructing a user demand model according to a user query request corresponding to the user instruction, user preference setting and user historical behaviors; initializing a meteorological early warning decision-making agent according to the user demand model, and configuring a sensing module, a reasoning module and a learning module for the meteorological early warning decision-making agent; performing logical reasoning based on the space-time tensor meteorological data and the user demand model through a meteorological early warning decision agent by using a reasoning module, generating meteorological decision suggestion data, and displaying the meteorological decision suggestion data in a graphical user interface; through the method, the meteorological early warning decision-making efficiency can be improved.

The invention provides a question and answer method and device, and relates to the technical field of artificial intelligence, in particular to the technical field of natural language processing, deep learning and large language models. A specific embodiment of the method comprises the following steps: inputting a current question input by a user into a decision agent, and outputting a task agent chain; selecting a task agent corresponding to the task agent chain from the task agent set; and executing the selected task agents according to the sequence of the task agent chain to obtain an answer of the current question.

This invention discloses a method for generating honeypot deployment strategies based on reinforcement learning in an intranet environment. The method includes: randomly generating multiple nodes to construct an intranet environment; constructing attack agents, which interact with the intranet environment in stages to pre-train the attack agents; assigning pre-trained attack agents with different attack intentions to each honeypot agent, and pre-training the honeypot agents in the intranet environment; initializing the pre-trained honeypot agents and constructing the honeypot environment using them; in the honeypot environment, the pre-trained attack agents interact with the pre-trained honeypot agents to pre-train decision agents; training all agents using the MADDPG algorithm, constructing a hierarchical defense agent using the pre-trained honeypot agents and the pre-trained decision agents, and updating the policy network and value network of each agent. This invention improves the adaptability of the honeypot system and enhances the security protection level of the intranet environment through dynamic deployment strategies.

The invention provides a data generation method and device, electronic equipment, a storage medium and a program product, and the method comprises the steps: obtaining to-be-generalized first text data, and determining first semantic information of the first text data; generalizing the first text data based on the first semantic information by utilizing a generation agent to obtain second text data; determining second semantic information of the second text data by using a quality inspection agent, and determining a first evaluation result of the second text data based on the first semantic information and the second semantic information; wherein the first evaluation result is used for representing the relationship between the similarity of the first semantic information and the second semantic information and a preset similarity threshold; and determining whether the second text data is target text data or not at least based on the first evaluation result of the quality inspection agent by using a decision agent. Through the method, the accuracy of the determined target text data can be improved.

A system capable of reasoning, learning, and imagination. The system includes an input / output module, a reasoning and decision agent, and a knowledge management module including a deliberation agent and a semantic knowledge space. This system uses prior knowledge stored in memory for reasoning and decision-making. It learns new domain knowledge and user behavior throughout operation, making it an evolving system that adapts to the user's needs. The system reinforces knowledge stored in its semantic memory without user intervention and imagines new relationships between existing concepts to search for novel ideas until it reaches an epiphany. Several embodiments of the disclosed system can interact in a collaborative environment for cross-domain reasoning and brainstorming new ideas.

This disclosure provides a question-answering method and apparatus, relating to the fields of artificial intelligence technology, particularly natural language processing, deep learning, and large language models. A specific implementation of this method includes: inputting a current question from a user into a decision agent, outputting a task agent chain; selecting a task agent corresponding to the task agent chain from a set of task agents; and executing the selected task agent in the order of the task agent chain to obtain an answer to the current question.

The invention discloses a broadband satellite communication verification system and method, relates to the technical field of broadband satellite communication, and remarkably improves the response efficiency and stability of the broadband satellite communication verification system through a distributed asynchronous Q learning framework and a dynamic coordination mechanism. In a high dynamic environment of a satellite-ground fusion network, a local decision agent operates independently, a resource allocation decision is quickly generated based on a real-time channel state and a user demand, and a calculation bottleneck brought by centralized optimization is avoided; according to the distributed architecture, communication overhead among nodes is reduced, decision delay is reduced, and therefore the jitter phenomenon caused by multi-user competition is effectively restrained; a penalty function mechanism integrates the conflict rate, the interference degree and other multi-dimensional costs into a learning process, so that the nodes autonomously avoid high-competition actions, and the fairness of resource allocation is enhanced; meanwhile, the coordination module adaptively adjusts the updating period through topological change measurement, and the response interval is shortened when the satellite rapidly moves.

The invention discloses a semiconductor valve fluid simulation method based on deep reinforcement learning fusion, and relates to the technical field of semiconductor equipment manufacturing, and the method comprises the steps: collecting real-time working condition data, and dynamically calibrating the helium detection inner leakage rate, the flow coefficient CV and the adaptive threshold of the inner surface roughness in combination with the service degradation characteristics of a valve; a perception-decision double deep reinforcement learning agent architecture is established, a perception agent extracts multi-physics field high-dimensional features through a convolutional neural network and performs noise reduction, and a decision agent drives a simulation model to adaptively adjust structural parameters by adopting an improved double-strategy reinforcement learning algorithm; starting multi-physics field simulation and double-agent closed-loop iteration until a simulation result meets a self-adaptive threshold value requirement; and introducing a multi-target degradation compensation mechanism based on an iteration result, reversely correcting valve service degradation characteristic related parameters, and outputting a valve simulation optimization scheme. According to the invention, the problem of low simulation precision in the prior art is solved, and intelligent and accurate optimization of the semiconductor valve structure is realized.

A computer-implemented method for processing a natural language question related to maritime vessel tracking is described. The method includes receiving, from a user device, a user query, the user query comprising the natural language question related to maritime vessel tracking, selecting, at a processor in communication with the network device, using a decision-making agent configured to use a large language model, a data retrieval function from a plurality of data retrieval functions based on the maritime question type, generating, at the processor, using the decision-making agent, the data retrieval function, and the one or more maritime identifiers, one or more relevant output data related to the maritime question type and the one or more maritime attributes, and sending, at the network device, to the user device, a user response based on the one or more relevant output data, wherein the user response comprises an answer to the natural language question.