51 results about "Agent behavior" patented technology

The invention relates to the technical field of computer application, and particularly discloses a chemical industry park safety risk assessment method based on an agent model. The method comprises the following steps: constructing a multi-agent collaborative perception framework, and fusing multi-source heterogeneous data of equipment, environment, materials and personnel to form a park panoramic view under a unified space-time reference; establishing an agent behavior model library embedded with the chemical process mechanism and the safety interlocking logic; an intelligent agent decision strategy is optimized through deep reinforcement learning, and multi-target training is carried out by taking a safety index as a reward function; executing dynamic risk deduction and accident chain simulation in a digital twin environment, and quantifying risk probability and consequences in combination with Monte Carlo sampling; and finally, a visual thermodynamic diagram and an interpretable risk assessment report are generated, weak links are identified, and intervention suggestions are provided. According to the technical scheme, dynamic, accurate and prospective evaluation of the safety risk of the chemical industry park can be realized, and the early warning timeliness and the evaluation reliability are remarkably improved.

A computing platform can generate a virtual world and a set of virtual agents that have agent traits (attributes). A trait distribution for a set of agents Y can be generated by processing seed data to generate trait values T and a trait distribution algorithm. The algorithm assigns a particular trait value T′ to an agent Y′, conforming to the trait distribution algorithm applied to the set of agents Y. The platform uses the agents in a simulation session, prompting an AI model with the particular trait value T′ to generate an output set. The output set can be displayed and navigated to provide further information about the trait value T′, which enables analysis of agent behaviors and outputs based on agent traits.

The invention discloses a method and equipment for detecting the compliance of an access protocol of a power internet of things terminal based on multi-agent dynamic evolution. According to the method, a directed acyclic graph plan logic, a cue word template and an agent registry are coded into a multi-dimensional constraint space, a rigid rule framework of task decomposition, agent behaviors and data streams is constructed, and on the basis, the task decomposition, the agent behaviors and the data streams are analyzed through a verification module and a node-level error back propagation and path-level weight aggregation feedback mechanism of a positioning agent. Closed-loop cooperative tuning of static template parameters and dynamic execution logic is achieved, the manual intervention requirement is remarkably reduced while the rigidity of protocol detection specifications is ensured, and a self-consistent closed loop of detection task decomposition and agent set management and control is formed. According to the method, the power grid terminal access control efficiency and compliance guarantee strength can be remarkably improved, and a core technical support is provided for large-scale deployment of the power internet of things.

The invention discloses a social group simulation method and device based on multi-agent driving. The method comprises the following steps: performing user attribute sampling processing on a real e-commerce user data set, and constructing agent basic attributes based on user attributes in combination with a large language model to obtain agent basic attribute features; performing construction processing on the agent basic behaviors based on a preset memory mechanism in combination with the agent basic attribute features; according to the agent basic attribute features and the agent basic behavior features, performing construction processing on agent interaction behaviors in combination with a large language model; performing relation network construction processing based on a small-world network model on the plurality of agents; and performing simulation processing based on execution agent behaviors on the agent social group model to obtain a multi-user behavior simulation result. By constructing a multi-agent simulation system in an e-commerce scene and combining the multi-agent simulation system with a large language model, social group simulation in a complex e-commerce interaction scene is realized, and the accuracy of social group simulation in the e-commerce scene is improved.

The invention relates to the technical field of knowledge graph construction, and discloses a knowledge graph-based agent behavior description method, which comprises the following steps of: firstly, analyzing an unstructured agent operation log data stream through a processor, and mapping the unstructured agent operation log data stream into a discretized module access sequence by utilizing a topological structure of a code knowledge graph so as to remove text redundancy; performing multi-dimensional time sequence analysis on the sequence, and calculating resident distribution data representing operation continuity, frequency domain fluctuation data representing switching rhythm and multi-scale coverage extension data representing a traversal range; and then aggregating the data into a fixed-length multi-dimensional index vector, constructing an index node associated with a session entity in a graph database, and writing the vector as a binary structured attribute into a storage field. According to the method, massive unstructured logs are converted into compact graph structured indexes, and quick positioning and direct retrieval of a complex agent operation mode are supported while the storage space is remarkably saved.

The invention provides a dynamic permission allocation method and system for a large-scale agent, and relates to the technical field of artificial intelligence security, and the method comprises the steps: collecting the multi-dimensional access feature information of a historical service user group of a target agent in real time; and mapping the multi-dimensional and high-dimensional access features to a preset vector space, identifying a core resource access feature domain of the intelligent agent by calculating an affiliation relationship between a feature vector and each Voronoi cell, and outputting a dominant feature vector representing service features of the intelligent agent. According to the method, the precise permission strategy is dynamically generated by fusing agent behavior characteristics and real-time context, credible mutual recognition and self-adaptive evolution of the cross-domain strategy are realized based on the geometric topology network, and finally, the safety, flexibility and system efficiency of cross-domain collaboration are improved under the principle of ensuring the minimum permission.

The invention discloses a lightweight cross-domain recommendation method and system based on user alignment Agent driving. The method comprises the following steps: firstly, acquiring historical behavior data of a user in multiple fields, fusing multi-modal contents such as texts and images, generating a fine-grained interest prototype through a cross-domain semantic encoder, and constructing a personalized Agent to simulate the intention of the user; then, in a multi-field collaborative environment, an Agent behavior strategy is optimized by utilizing reinforcement learning and a mixed reward mechanism, general preference and field specific preference are modeled through a hierarchical strategy network, and knowledge fusion is realized through a gating mechanism; and then, in combination with a preference distillation technology, extracting transferable characterization from Agent behaviors, and constructing a lightweight cross-domain knowledge graph. Finally, behavior track compression and cross-domain preference mapping are adopted, and efficient and low-consumption personalized recommendation is achieved. According to the method, the problems of cross-domain data sparsity and model complexity are effectively relieved, recommendation accuracy and system response efficiency are improved, and the method is suitable for real-time recommendation service of multiple scenes.

The invention discloses an agent training method, a data processing method and a related device, and relates to the field of artificial intelligence. In an agent training process, key information in target interaction data generated by interaction between an initial agent and a target user is automatically extracted to generate a structured memory; and a context basis for supporting training can be constructed without manually annotating data, so that the training cost of the intelligent agent is reduced. Traceable historical context support is provided for the intelligent agent by processing the target interaction data and updating the target database based on the processing result; a comprehensive basis is provided for agent behavior evaluation by acquiring whole-process trajectory data generated when an initial agent executes a task in a target task environment; the scoring model constructed by the user for the feedback information of the full interaction trajectory scores the trajectory data, and the initial agent parameters are updated, so that the agent can continuously optimize the strategy, and the accuracy of the agent is effectively improved.

Embodiments described herein provide an optimization framework to control LLM agent behavior using dynamically optimized principles as part of the generation context. Specifically, a principle may take a form of a set of logic, parameters or text that describe the conditions for using that action. An LLM agent may generate a next step action conditioned on a set of principles corresponding to a set of available actions, and an execution trajectory. A reflector model (such as an LLM) may then generate a reward score based on the generated trajectory and the set of principles. Based on the reward scores, an optimizer (such as an LLM) may revise the set of principles to better align with observed conditions.

The invention discloses a puzzle solution game adaptive design method and system based on ecological balance, and the method specifically comprises the steps: receiving ecological scene data selected by a player, carrying out the evaluation processing of the capability level of the player through combining with a player capability evaluation model, and generating an evaluation result; dynamically generating hierarchical ecological problems according to an evaluation result, and synchronously activating Agent behavior tree loaders of corresponding hierarchies to form an Agent modeling system; simulating a biological interaction network through an Agent modeling system, inputting real-time operation data of the biological interaction network into an LSTM double-time-sequence prediction engine for prediction processing, and generating an ecological evolution graph; and generating a dynamic visual interface according to the ecological evolution map, and triggering a difficulty regulator when detecting that the ecological imbalance index exceeds a difficulty threshold value of the current player. Complex characteristics of an ecological system are effectively simulated, more challenging and interesting puzzle solving game experience is provided for players, and meanwhile understanding and protection awareness of the players to the ecological system can be improved.

Techniques are discussed herein for executing simulations with parameterized object controllers to control smart agents, to evaluate the agent realism of the smart agents and to validate the efficacy of the simulations. A simulation system may analyze log data captured by a vehicle operating in a physical environment, to determine observable and non-observable behavior characteristics of the agents in the environment. The simulation system may execute simulations using object controllers to control simulated objects (e.g., “smart agents”) based on parameters associated with scenarios, object types, and / or scenario locations. Log data associated with smart agent behaviors may be aggregated and compared to the behavior characteristics of agents in physical environments, to determine metrics for agent realism and simulation efficacy. Based on such metrics, simulation results may be validated and / or object controller parameters may be modified.

The invention relates to the field of artificial intelligence, the technical scheme can be applied to the field of industrial automation, the field of intelligent transportation and the field of intelligent power grids, and discloses an abnormal behavior recognition method, device and equipment of a multi-agent system and a medium. Meanwhile, the abnormal behavior score is calculated in parallel by the abnormal detection module; and after abnormity is judged through a dynamic threshold value, a closed-loop correction mechanism is triggered, and a reward function and an experience sampling weight of a strategy module are adjusted in real time, so that online compensation and optimization are performed on the behaviors of the intelligent agent. According to the method, the anomaly recognition accuracy, the real-time response capability and the overall system robustness of the multi-agent system in a complex dynamic environment are remarkably improved.

The application relates to the technical field of agent testing, and particularly provides an agent dynamic behavior safety testing method and system based on a risk transmission quantitative model, which comprises the following steps: collecting agent behavior data, containing a plurality of risk operation information and risk correlation relations; constructing a behavior risk correlation graph taking risk operations as nodes and correlation relations as edges, marking risk attributes and time limit factors on the nodes, and marking risk transmission strength on the edges; constructing a risk rule library based on the risk marking results and a preset risk judgment logic; inputting the behavior data, the behavior risk correlation graph and the rule library into a trained quantitative model to calculate risk transmission probability, influence range and critical nodes; real-time monitoring of behavior trajectories, task suspension, backtracking reasoning chain and intervention record generation when a multi-dimensional risk threshold is triggered; and test report generation by fusing multi-dimensional data. The application solves the problems of missed judgment and response lag in traditional testing, and improves the pertinence and reliability of safety testing.

The invention provides an output lexical element prediction method oriented to a multi-agent large language model application. Comprising a multi-agent behavior acquisition module for executing light intrusion behavior acquisition, a feature construction module for executing feature construction, a single-agent high-quantile output length prediction module for executing single-agent high-quantile output length prediction, a model online self-adaptive adjustment and optimization module for executing online self-adaptive updating, and a model online self-adaptive adjustment and optimization module for executing online self-adaptive updating. The multi-agent execution portrait construction module is used for executing the application-level execution portrait; a two-stage hybrid prediction architecture (intention classification + quantile regression) adopted by the method can effectively adapt to behavior differences of different roles (such as translation, writing and reasoning) in a multi-agent system. Meanwhile, the prediction overhead is extremely low, and the low-delay requirement of a real-time scheduling system is met.

This application provides a method, system, device, and storage medium for dynamic evaluation of agent behavior consistency, belonging to the field of agent technology. The method includes: testing the agent using a multi-turn dialogue state machine based on an adversarial evaluation dataset to obtain interaction behavior data; scoring the interaction behavior data using multiple reviewer models to obtain multi-source reviewer scoring data; calculating the scoring divergence degree based on the multi-source reviewer scoring data; if the scoring divergence degree is greater than an empirical threshold, obtaining the structured evidence chain output by each reviewer model; obtaining the divergence logic attribution result based on each structured evidence chain through a meta-reviewer model; adjusting the weights of each reviewer model based on the divergence logic attribution result and an evaluation priority matrix; and weighting the multi-source reviewer scoring data based on the adjusted weights of each reviewer model to obtain a weighted comprehensive score. This application can improve the accuracy and reliability of agent evaluation results.

This invention belongs to the field of artificial intelligence and computer simulation technology, and discloses a knowledge-driven multi-agent strategic game deduction method. Existing strategic game deduction methods generally suffer from insufficient agent consistency and stability, inadequate representation of knowledge differences, and a lack of interpretability in strategy generation. The knowledge-driven multi-agent strategic game intelligent deduction method and system proposed in this invention constructs a knowledge base for each agent, sets the game environment and context for each agent, conducts multiple rounds of game deduction based on the context of each agent, the knowledge base, and the game environment, and finally outputs a complete set of game deduction states based on the state of each round of game deduction. This invention effectively solves the problems of unstable agent behavior and convergent role characteristics by embedding the agent's domain knowledge into its decision loop in a structured manner. It can generate logically consistent, distinctive, and traceable strategy sequences, improving the reliability and analytical value of strategic game deduction.

The invention relates to an agent learning training method and device, computer equipment and a storage medium, and the method comprises the steps: converting a high-level intention into an executable code through employing an LLM model, obtaining a clone data set, constructing an intelligent driving scene into a Markov decision process, and constructing an instruction space; constructing an intelligent agent strategy model; a training target is decoupled into a behavior cloning and reinforcement learning target and weighted summation is carried out, the intelligent agent is trained according to the final training target, sampling is carried out from a cloning data set, intelligent agent strategy model parameters are updated, then sampling is carried out from an environment interaction track, and the intelligent agent strategy model parameters are updated in a PPO mode. Due to the fact that a high-level intention-instruction-strategy link is closer to a decision-making level which can be understood by human beings, intelligent agent behaviors can be debugged, audited and backtracked conveniently, maintainability is improved from the perspective of engineering landing, and a clearer interface is provided for follow-up safety fence access, formalized constraint or rule verification.

The invention provides a fault detection method and device for a multi-agent system influenced by channel fading, and relates to the technical field of multi-agent control. The method comprises the steps that the multi-agent system is modeled into a linear variable parameter system, external disturbance and fault signals are fully considered, a foundation is laid for subsequent operation, a fault detection observer and a consistency controller are constructed, and the fault detection accuracy is improved. The former monitors faults, the latter unifies agent behaviors, introduces an event trigger mechanism to reduce resource consumption, improves system collaboration and operation efficiency, calculates and detects observer gain and consistency controller gain according to specific conditions, updates control input based on the gain, calculates residual signals, and provides a basis for fault judgment; the fault is judged by using the residual error evaluation function and the threshold value, the method is intuitive and efficient, an alarm can be given in time, the system performance, safety and reliability are guaranteed, and the stability and fault detection capability of the multi-agent system in a channel fading environment are improved.

The application discloses a multi-agent behavior decision-making method and system based on an interactive dynamic influence graph, and particularly relates to the technical field of artificial intelligence, and the scheme comprises the following steps: acquiring observation environment information and action information of each agent in an agent cluster, and utilizing the observation environment information and / or the action information to form a behavior sequence of a corresponding agent; performing evolution calculation on the behavior sequence to obtain a strategy tree, and controlling the behavior of each agent according to the strategy tree. According to the scheme, the evolution calculation is utilized to iteratively output a more diverse behavior model according to the mutual influence relationship of each agent in the interactive dynamic influence graph, and the obtained behavior model is embedded into the interactive dynamic influence graph model, so that more effective and rich environment information is provided for the main agent to optimize its own decision-making, and the main agent and other agents can make more optimal decisions.

A system and method dynamically manages the operational boundaries of an autonomous system or agent in a configurable and adaptable manner. Traditional approaches rely on static or fixed boundaries to constrain an agent's operation, which can be highly restrictive and inefficient. To address these issues, a virtual anchor state is established to provide a dynamic reference entity that represents a focal point based on factors such as proximity to objectives, environmental conditions, or system priorities. The agent state provides real-time information such as the agent's position, status, and behavior, while environmental data includes external factors like obstacles, nearby objects, or mission-specific variables. By combining these inputs, the system continuously updates the anchor state to reflect the most relevant context and uses it to calculate boundary conditions, which define permissible operational areas or constraints. These boundaries adapt dynamically to changing contexts, such as shifts in the environment or agent behavior.

The invention discloses an agent behavior compliance constraint method based on a multi-source data traceability chain. The method comprises the following steps: forming a multi-source data set; generating corresponding signature information; constructing a multi-source data tracing chain; agent behavior event data are received, and a behavior data association record set is formed; establishing an agent behavior compliance constraint model by using an improved CMAN algorithm; performing real-time verification on the agent behavior event data to generate a compliance verification result; and a traceable compliance audit chain is generated, so that fusion of a multi-source data traceability chain and an intelligent compliance algorithm is realized, and transparency, compliance and traceability of agent behaviors can be effectively improved.

A single policy may be trained to cope with user selection of parameters across a predetermined range for each component of an artificial intelligence agent within a domain. The agent may be trained across multiple weights within a desired range for each component. These weights determine how many reward portions for each component should be considered by the agent during training. Therefore, for a UVFA-like target based on a compositional reward function parameterized by the weights of its components, an improved formulated expression can be achieved. Further, for the field of autonomous racing games, a set of reward components is determined that, when combined with an improved UVFA formulation expression, allows training of a single racing agent that is generalized in multiple dimensions in continuous behavior. This can be used by a game designer to adjust the skill and personality of the trained agent.

The invention discloses an intelligent agent cooperative behavior control method and system based on a state-driven architecture. The method comprises the following steps: defining a multi-dimensional state vector model of a business object; defining a circulation rule based on a state vector; compiling the rule into an optimized discrimination network; during running, executing according to a state matching driving rule, and setting a non-bypassing multi-stage safety judgment process in an execution link; chained circulation is realized through automatic conduction of state change. According to the system, heterogeneous intelligent agent collaboration is realized by adopting a distributed architecture. According to the invention, the state is taken as a core driving force, the business logic is decoupled from a code into a configurable rule, the safe controllability of the behavior of the high-autonomy intelligent agent is ensured through a built-in safety decision, and the flexible, safe and explainable intelligent agent collaborative management is realized.

This invention belongs to the field of vehicular edge computing and discloses a distributed service migration method for vehicular edge computing environments. This method, based on contrastive role representation and multi-agent deep reinforcement learning, optimizes service migration decisions by constructing a three-layer heterogeneous vehicular edge network model, including a cloud center layer, an edge layer, and a user layer. This invention proposes a multi-agent deep reinforcement learning method based on an improved QMIX. It constructs agent behavior state trajectory embeddings for local Q-networks and hybrid networks based on agent historical trajectory information, capturing time-related behavioral patterns and solving some observability problems. Furthermore, it uses a contrastive learning-based role encoder to extract unique behavioral patterns of different agents to generate role representations, capturing long-term features of agent behavior. A multi-head attention mechanism is introduced into the hybrid network to dynamically allocate attention weights. This method exhibits superior performance.

Safety reinforcement learning is widely applied to the fields of games, robot control and the like. However, the traditional method often causes efficiency and stability problems due to limitation of an optimization strategy and a projection technology. In order to solve the problems, the invention provides a new algorithm which is named as an OSAPS (One-step Anticipative Policy Selector), and the new algorithm is an OSAPS (One-step Anticipative Policy Selector). The OSAPS improves the efficiency and safety of agent behaviors through integrating strategy selection, single-step planning and a self-adaptive safety threshold mechanism. The core of policy selection is a conditional dual-path policy network architecture, which comprises a vertex policy network and a basic policy network. In addition, a single-step planning mechanism of the OSAPS enables the intelligent agent to perform prospective action adjustment in a safe range, and simulates a human decision process. The self-adaptive safety threshold mechanism further improves the balance and safety between exploration and utilization. A robot simulation experiment shows that the OSAPS improves the time efficiency by 18.52% in a Pendula environment; the performance is improved by 7.67% in a Hovertrap environment, and meanwhile, the stability and the safety are kept.

The invention discloses a BDI-based ground unmanned system multi-agent simulation behavior model construction method, and relates to the technical field of unmanned system simulation, and the method comprises the following steps: S1, constructing an internal BDI cognitive layer of an agent; s2, setting an intention-behavior converter; s3, constructing a Couzin model layer; and S4, establishing a sensing feedback loop. According to the method, the motion naturalness is remarkably improved while the task efficiency is guaranteed through a bidirectional coupling architecture, the trust and controllability of people to an unmanned cluster are enhanced by quantifying a mapping chain and establishing a transparent bridge from a human instruction to a cluster behavior, and the problem of disjunction of cognition and behaviors in a traditional model is effectively solved; according to the method, the intelligent agent cluster shows smooth and natural self-organizing motion characteristics during task execution, the established task target can be efficiently completed, the sense of reality of a simulation scene and the natural coordination of intelligent agent behaviors are remarkably improved, and a simulation result is closer to the operation performance of an actual ground unmanned cluster.

An embodiment includes non-deterministic agent state transition behavior specification, monitoring, and correction. An embodiment establishes an agent, wherein the agent is configured to output text in response to input text. The embodiment defines an agent behavior specification for the agent. The embodiment inputs a text input to the agent and monitors the text output of the agent to detect an incorrect state transition, wherein the incorrect state transition comprises a state transition that deviates from the agent behavior specification. The embodiment applies a correction to the output text to create a corrected output text upon detecting the incorrect state transition. The embodiment reverts the agent to a previous state, the previous state preceding the state corresponding to the incorrect state transition detected. The embodiment inputs the corrected output text to the agent in the previous state to cause future behavior of the agent to align with the agent behavior specification.

The present application relates to the technical field of computer and artificial intelligence, and particularly relates to a kind of Agent generation, interfacing, integration and control method, device, computer equipment, storage medium and computer program product.The certain Agent generation, interfacing, adjustment and control method described in the present application comprises the following steps: generating ActionAgent model through integrated and split type, optimizing Agent behavior based on dynamic adjustment factor relationship, reducing energy consumption by optimizing data transmission mechanism, enhancing system security by introducing multiple control points, and verifying system performance by simulating fault detection.The present application can standardize the generation and interfacing process of ActionAgent, reduce repeated operation and data transmission, improve the efficiency of multi-ActionAgent collaboration, and enhance the stability and security of the system through factor parameter value sharing and fault detection technology, and is suitable for multi-Action Agent generation, interfacing, collaboration and self-feedback continuous operation requirements in medical, household, industrial, autonomous driving and other scenarios.

The invention discloses an AI agent behavior prediction method based on multi-modal data, and particularly relates to the field of multi-modal data processing, and the method comprises the steps: S1, determining an agent data collection region, S2, obtaining agent multi-modal data, S3, processing the multi-modal data, S4, coding the multi-modal data, S5, fusing the multi-modal data, and S6, predicting the agent behavior. According to the method, multi-modal data such as vision, acceleration and voice are fused, the limitation of single data in description of agent behaviors is overcome, information is acquired from multiple dimensions, the behavior prediction accuracy is greatly improved, the potential relationship among different modal data is deeply mined through cooperative work of an attention mechanism and the graph convolutional network, and the behavior prediction accuracy is improved. According to the method, multi-modal data is subjected to multi-modal analysis, internal relations in the multi-modal data are accurately grasped, more powerful support is provided for prediction, in addition, targeted preprocessing is performed on the multi-modal data, the adaptability of the model to complex scenes is enhanced, and then the stability of prediction in different scenes is guaranteed.