34 results about "Adaptive agents" patented technology

A multimodal intelligent agent system for dynamic environmental monitoring and user-centered support, consisting of: a multimodal sensor module configured to continuously acquire environmental and behavioral data from multiple input modalities, including at least one visual sensor, at least one acoustic sensor, at least one environmental conditions sensor, and at least one proximity or motion detection sensor, each generating modality-specific data streams representing visual images, audio waveforms, physical environmental parameters, and motion signatures within a monitored environment; a data preprocessing and fusion subsystem that is operationally coupled with the multimodal sensor module and configured to normalize, temporally align, and transform the modality-specific data streams into high-dimensional feature embeddings using a variety of encoders, wherein the visual encoder uses convolutional or vision transformer architectures, the audio encoder uses a spectral-temporal feature extractor, and the sensor encoder transforms raw analog data into context vectors suitable for multimodal alignment; a multimodal processing unit consisting of a transformer-based large language model (LLM) trained on paired multimodal datasets and configured to perform semantic fusion, context abstraction, and inference across the aforementioned aligned multimodal feature embeddings to generate a contextual understanding of environmental and behavioral states; an adaptive agent controller coupled to the multimodal inference processing unit and configured to instantiate, manage, and terminate a variety of task-specific intelligent agents, each agent being a software unit configured to perform a specialized function selected from meeting summarization, behavioral analysis, misplaced object detection, or environmental anomaly identification, with the agents dynamically interacting with the inference engine to retrieve contextually relevant multimodal embeddings for task execution; a personalization and adaptive learning subsystem consisting of a user preference database and a neural memory structure configured to update and refine model parameters based on user-specific interaction history, thereby enabling personalized output generation, prioritization of recommendations, and long-term behavioral adaptation; and An output generation interface is operationally connected to the adaptive agent controller and configured to produce multimodal output in textual, visual, and auditory form. The interface is capable of displaying human-readable summaries, notifications, and visual reconstructions of identified entities or environmental states.

The invention provides an airfoil profile adaptive design and optimization method based on reinforcement learning and a conditional generative adversarial network, and belongs to the field of airfoil profile optimization design. The method aims at achieving the two core functions of self-adaptive optimal airfoil generation and rapid optimization. According to the first function, through interaction of a reinforcement learning agent and a conditional generative adversarial network generator, generation strategies for generating optimal airfoil profile potential variables under different design conditions are continuously learned, so that the airfoil profile with the optimal aerodynamic performance is adaptively generated, intelligent and adaptive design of the airfoil profile is achieved, and the optimization period is remarkably shortened. Secondly, a self-adaptive agent model based on meta-learning is introduced, the model not only establishes a mapping relation among design conditions, aerodynamic performance and potential variables and directly predicts the optimal potential variables of a specific airfoil profile, but also can quickly adapt to an updated database through simple adjustment; the agent model predicts the optimal potential variable corresponding to the specific airfoil profile for the self-adaptive generation framework, so that the agent can quickly optimize the specific airfoil profile under the condition of fine adjustment.

The invention relates to a question and answer method and system fusing a multi-granularity knowledge graph and a self-adaptive agent. The question and answer method comprises the steps of knowledge governance and extraction, knowledge generation and expansion, knowledge retrieval and management, and knowledge rule mining and self-adaptive retrieval. Through cooperation of the multi-granularity knowledge graph and the self-adaptive agent, questions of the user can be more comprehensively understood, and more relevant knowledge can be retrieved from the knowledge base, so that the question and answer accuracy is remarkably improved, and wrong answers are reduced. Meanwhile, the multi-granularity knowledge graph can support more complex knowledge application requirements such as reasoning and prediction, so that the application capability of the question and answer system is enhanced, and the question and answer system can process more complex question and answer tasks such as multi-round dialogues and multi-task question and answer.

The invention discloses an offshore wind turbine foundation scouring full-period intelligent monitoring method and system based on multi-source data fusion and a dynamic coupling model, and relates to the technical field of intelligent monitoring, and the method comprises the steps: deploying a multi-source monitoring module, and constructing a finite element model; carrying out load calculation and parameter inversion; and training full-cycle dynamic updating of the washout failure function model. According to the method, a self-adaptive Kriging-Bayesian method is adopted, a Bayesian inversion framework and a self-adaptive agent model are fused to solve optimal soil body parameters, full-period model dynamic updating based on dynamic monitoring data is achieved, a multi-fidelity deep kernel learning model is adopted, three types of data are fused into a training set, full-period intelligent monitoring of offshore wind turbine foundation scouring is achieved, and the method has the advantages of being simple in structure, convenient to operate and high in practicability. The dynamic identification of soil parameters is realized by combining a self-adaptive inversion framework with a displacement error closed-loop optimization mechanism, and the technical problem that a traditional static model cannot adapt to the spatial-temporal variability of seabed geology is solved.

The invention discloses a heterogeneous computing network resource collaborative scheduling optimization method based on self-adaptive multi-agent, and aims to solve the scheduling problem caused by resource heterogeneity, load dynamics and task high concurrency in a heterogeneous computing network system. According to the method, cross-domain resource collaboration is realized by constructing three sub-domain adaptive agents of a computing resource domain, a network resource domain and a storage resource domain and a global collaboration layer. According to the method, a deep reinforcement learning algorithm and an 'LSTM + GNN' fusion model are integrated, and multi-target adaptive optimization of resource utilization rate, task time delay, service quality and energy consumption is achieved through closed-loop optimization of state perception, strategy generation, value evaluation and strategy updating. The heterogeneous computing network resource fine-grained sensing, cross-domain cooperative scheduling and multi-target dynamic optimization are realized, the resource utilization rate and the task completion rate are high, the service quality and the energy consumption performance are good, and the dynamic response capability and the overall performance of the heterogeneous computing network system are improved.

The invention discloses a tree health state assessment method based on a proxy model, which comprises the following steps: establishing a three-dimensional finite element model of trees by collecting geometrical shape data and material attribute data of different types of trees, and performing finite element analysis. And according to the analysis result and the geometric data, constructing an adaptive agent model by using a neural network, training the adaptive agent model, and generating a prediction model of the tree health state. Characteristic data such as stress, strain and damage factor distribution of a tree to be evaluated are collected in real time through a sensor and an unmanned aerial vehicle and input into the trained adaptive agent model for dynamic analysis, and data optimization model parameters are fed back in real time. And according to an evaluation result, windproof reinforcement countermeasures for trees with different health state levels are automatically generated, and the scientificity and the accuracy of the reinforcement measures are improved. According to the method, the accuracy of tree health state evaluation is improved, real-time monitoring and dynamic early warning are realized, timely identification and feedback can be realized at the initial stage of tree damage, a corresponding windproof reinforcement countermeasure is given, and delayed processing is avoided.

The invention relates to a self-adaptive agent decision framework training method with dynamic environment perception capability, which comprises the following steps of: 1, collecting multi-modal sensor data in parallel, and carrying out hardware-level preprocessing on the collected data; step 2, based on the data preprocessed in the step 1, performing dynamic security boundary driven real-time feature extraction to obtain security boundary coordinates; 3, based on the safety boundary coordinates obtained in the step 2, generating an execution action strategy in a decision period; and 4, based on the action strategy generated in the step 3, constructing a feedback closed loop of the distributed execution framework, and realizing real-time closed loop optimization. According to the method, the core requirements of scenes such as mobile robot navigation and intelligent industrial control on autonomous decision-making safety and real-time performance are met.

The invention discloses an emotional diary intelligent glasses system driven by a multi-modal agent. The emotional diary intelligent glasses system comprises a multi-modal perception layer, a unified vector space processing layer and an agent collaborative decision-making layer. The multi-modal sensing layer constructs a full-dimensional sensing network by integrating a camera, a microphone array and an eye movement tracker, and collects image, sound and eye movement information; the unified vector space processing layer realizes cross-modal information unified representation by using a multi-modal large model; the agent collaborative decision-making layer comprises an emotion perception agent, a scene understanding agent, a diary generation agent and a personalized adaptive agent. According to the method, deep understanding of the emotional state and the environment scene of the user is realized through a multi-modal fusion perception and agent cooperation mechanism, the personalized emotional diary is generated in combination with chain thinking and reflection, and the content insight and the user experience are effectively improved.

The invention relates to the technical field of smart home, in particular to a smart home collaborative decision and adaptive agent construction method based on LLM. The method comprises the steps of receiving a user instruction to generate a family situation model, decomposing an abstract instruction into a sub-task sequence, identifying conflicts and negotiating consensus, calling a database interaction sub-agent to complete data operation, and injecting a query result to support subsequent task execution and full-link redisk to optimize system performance. Through context sensing, conflict pre-judgment and safety controllable database interaction modules, the problems of fuzzy instruction understanding, dynamic environment adaptation and data safety are solved, the intelligent level and the user satisfaction degree of the system are improved, and meanwhile the sustainable evolution capacity of the system is achieved.

Embodiments described herein systems and methods for dynamically guiding a generative artificial intelligence model through structured, goal-oriented interactions using machine- generated rubrics for instructing operations of the generative Al model. The system selects, for each conversational turn, a first rubric defining response structure and a second rubric defining evaluation criteria. A generative model formulates prompts based on these rubrics and receives participant responses. An assessment module evaluates the responses against the second rubric to update the interaction context. A rubric orchestration module uses the updated context to select new rubrics for subsequent turns. This iterative process transforms a stateless generative model into a persistent, adaptive agent capable of conducting multi-turn interactions aligned with defined objectives.

The invention particularly relates to a medical artificial intelligence system and method based on situation intelligence and multi-agent cooperation, and relates to the technical field of medical artificial intelligence. Performing context analysis and task planning; selecting and scheduling an expert agent; and performing collaborative execution and result convergence. According to the invention, multiple modules cooperate to greatly optimize the clinical working process, and the diagnosis and treatment efficiency and decision accuracy are improved; the unified context bus can aggregate multi-source heterogeneous data such as patient diagnosis information, allergy history and examination results in real time, and automatically standardizes the data into structured context objects, so that the tedious operation of manually arranging and dispersing data by medical staff is avoided, and a large amount of data preprocessing time is saved; the context awareness and intelligent orchestration engine accurately schedules an adaptive agent by means of the logic reasoning ability of a large language model, and avoids the logic vulnerability of artificial task decomposition.

The application discloses a multi-agent distributed situation interaction device and method based on a multi-modal large model, and relates to the technical field of computer model application. The device comprises the following steps: constructing a double-layer distributed interaction network; setting an environment monitoring time window according to a preset feedback adjustment period, collecting the number of node survival, the available communication bandwidth value and the task urgency level as the environment state parameters; inputting the environment state parameters into a pre-constructed interaction strategy adjustment model to output the adaptive local node interaction strategy and the adaptive agent node interaction strategy in the next feedback adjustment period; and inputting the adaptive local node interaction strategy and the adaptive agent node interaction strategy into the double-layer distributed interaction network in the next feedback adjustment period to control the local consensus node and the agent node to respectively perform distributed situation interaction and output a unified task situation cognition benchmark. The application realizes high reliability, low delay and consistency guarantee of the distributed situation interaction of the unmanned cluster in a complex battlefield or dynamic environment.

The application discloses a service processing method, device, equipment and medium, the method comprises the following steps: in response to a service instruction, determining a target instruction intention; based on the target instruction intention, determining a corresponding task path; based on the task path, determining a target agent, and an execution algorithm and a computing power configuration of the target agent; based on the execution algorithm, the computing power configuration and the task path, calling the target agent for service processing. The method dynamically constructs a task path by identifying an instruction intention, thereby scheduling an adaptive agent and computing power, algorithm resources in real time according to the task path, realizing flexible execution of the service instruction, avoiding resource waste, and improving service processing efficiency and response real-time performance.

The invention relates to an intelligent call routing method and system based on panoramic awareness, and belongs to the field of intelligent routing. The method comprises the following steps: capturing a multi-modal original data stream, performing panoramic perception based on the multi-modal original data stream, and constructing a multi-dimensional emotion field; constructing a field coupling degree model based on the multi-dimensional emotional field and the emotional resonance spectrum, and outputting an optimal matching seat; establishing a user-seat dialogue pair based on the optimal matching seat, and constructing a strategy utility function for outputting an optimal strategy sequence; based on the multi-dimensional emotion field and the optimal strategy sequence, resonance spectrum adjustment amount is obtained through resonance spectrum dynamic tuning, and a seat behavior fine tuning instruction is output; and constructing a strategy scene package and forming a strategy gene pool, and updating the emotional resonance spectrum based on the strategy gene pool. According to the method, real-time perception of user emotions, seat adaptive matching and strategy dynamic optimization are realized through multi-mode emotional field construction, emotional resonance spectrum matching and strategy gene pool evolution.

The invention relates to a reliability analysis method based on a self-adaptive agent model and importance sampling, belongs to the technical field of interventional medical stents, solves the problem of low reliability analysis efficiency of medical stents in the prior art, and is used for reliability analysis of mechanical thrombectomy stents. Comprising the following steps: quantifying random parameter probability distribution of a mechanical thrombectomy stent, and initializing algorithm parameters; generating a random sample, and obtaining a training sample set and a candidate sample set; constructing and training a Kriging agent model of the finite element model of the mechanical thrombectomy stent, and establishing an updated hypersphere; carrying out convergence judgment on the updated hypersphere radius; performing cross validation on the precision of the trained Kriging agent model by using a leave-one-out method; calculating a failure probability; and calculating a failure probability variable coefficient and carrying out convergence judgment, and when a convergence ending program is judged, applying the failure probability to safety evaluation and optimization design of the mechanical thrombectomy stent, otherwise, expanding the size of the candidate sample set and returning to regenerate a random sample.

The present invention discloses a valve performance simulation and optimization method and system based on hybrid deep learning, including: S1. performing finite element simulation analysis on the valve and using multi-physics field thermal-solid coupling solution to obtain the stress, deformation and temperature distribution data of the valve under different working conditions and the maximum thermal stress and maximum displacement of thermal deformation of key components of the valve; S2. after data processing, using the stress, deformation and temperature distribution data of the valve under different working conditions as input parameters and the maximum thermal stress and maximum displacement of thermal deformation as output parameters, training a neural network model and establishing a thermal-structural performance prediction model; S3. based on the prediction results, using a non-dominated genetic algorithm based on a reference point, combined with reference point generation and an adaptive agent model, to perform multi-objective optimization and output the optimal parameter combination to adjust the valve design; the present invention uses a neural network to perform deep learning and multi-objective optimization on the finite element simulation results, thereby improving the valve performance prediction accuracy and optimization efficiency.

The application belongs to the technical field of automatic driving control, and proposes a trajectory tracking method for unmanned trucks based on dynamic correction of MPC through reinforcement learning, which obtains real-time running state and expected reference trajectory of the unmanned truck through a vehicle-mounted sensor, constructs a current vehicle state vector and a tracking error; the current vehicle state vector is input into an adaptive agent based on deep reinforcement learning, the expected reference trajectory and the current vehicle state vector are input into an MPC controller, a prediction residual is generated and input into the adaptive agent; a comprehensive state vector is constructed based on the tracking error, the current vehicle state vector and the prediction residual, the adaptive agent generates a correction gain based on the comprehensive state vector and inputs the correction gain into the MPC controller; the MPC controller generates a current control instruction; the current control instruction is input into a physical system of the unmanned truck to implement vehicle control, and high-precision trajectory tracking control of the unmanned truck under complex working conditions is realized.

This invention discloses a multidisciplinary collaborative design optimization method for connectors based on an adaptive surrogate model. The method includes constructing an initial Kriging surrogate model, introducing an EI function to upgrade the Kriging surrogate model to an adaptive surrogate model, applying the adaptive surrogate model to multidisciplinary collaborative design optimization, constructing a multidisciplinary collaborative design optimization method based on the adaptive surrogate model, performing uncertainty analysis and design optimization modeling under the coupled state of multi-physics mechanical properties of connectors for special-purpose lifting slewing platforms, and finally performing design optimization. This invention, by combining uncertainty theory, surrogate model theory, and collaborative optimization theory, solves the problem that traditional design methods struggle to qualitatively and quantitatively construct optimization problem performance functions or constraints for complex engineering models, thus limiting the widespread application of collaborative design optimization methods in practical engineering fields. This allows the invention to meet the lightweight target requirements of connectors for special-purpose lifting slewing platforms.

The space-time analysis-oriented application has become a main technical means for solving the operation security digital intelligence, and the general method is to establish a sensing system by an artificial intelligence method, convert various sensor data into analyzable structured information, and combine with a preset analysis rule to realize the multi-source information comprehensive analysis of a specific space-time scene. According to the method, a sensing system and analysis rules need to be updated according to changes of scenes and demands, so that the applicability is limited. The self-adaptive agent technology is a technology which combines spatio-temporal data processing and agent self-adaption and generates perception analysis ability, through the technology, the perception ability and analysis rules can be automatically adjusted according to a target of a user, rapid landing and iteration of intelligent application are achieved, and a sustainable development solution is provided for digital intelligent construction.

The invention discloses a distributed security resource intelligent arrangement and adaptation method. Distributed heterogeneous security resources are efficiently and automatically arranged in combination with capability tagging abstraction, a plug-in type adaptation agent architecture and an efficiency comprehensive optimization algorithm. For distributed security resources, lightweight adaptive agents are deployed at nodes, resource functions are split into standardized capability tags and reported to a registration center, and an arrangement decision module generates an optimal security service chain based on resource capabilities, real-time operation indexes and a multi-objective optimization algorithm according to user requirements analyzed by a strategy management module. And the scheduling distribution module serializes the scheme and issues the scheme to each adaptive agent to call a manufacturer interface to execute configuration, so that efficient, automatic and safe resource arrangement is realized. According to the method, unified management and dynamic arrangement of cross-manufacturer, cross-cloud and cross-network are realized, the method has the advantages of pluggable expansion, efficient automation, real-time online self-adaption and the like, and the arrangement efficiency and protection flexibility of distributed security resources are remarkably improved.

The invention discloses a method, system, equipment and medium for optimizing injection and production parameters of a water-drive oil reservoir, and specifically relates to the field of oil reservoir engineering technology. The technical key points are as follows: inputting basic sample points into at least one high-precision simulation model for calculation to obtain the net present value corresponding to the basic sample points, and using the basic sample points and the corresponding net present value to construct a high-fidelity training sample data set; inputting non-basic sample points into at least one low-precision simulation model for calculation to obtain the net present value corresponding to the non-basic sample points, and using the non-basic sample points and the corresponding net present value to construct a low-fidelity training sample data set; based on the high-fidelity training sample data set and the low-fidelity training sample data set, a variable credibility adaptive proxy model for the optimization problem of injection and production parameters of oil and water wells is constructed; using a differential evolution hybrid particle swarm algorithm in combination with the variable credibility adaptive proxy model to optimize design variables, and obtaining a maximum net present value and a corresponding injection and production plan.

The invention relates to the field of intelligent agent platforms, in particular to a self-adaptive intelligent agent service platform for intelligent analysis of unstructured data. Wherein the preprocessing module is used for extracting semantic tags of features in an image sample and describing keywords in an event, the construction module constructs the association degree between the semantic tags based on the semantic tags and the keywords and provides a basis for association analysis of the features, and the association acquisition module determines anchoring main features and association identification coefficients in image data and sends the anchoring main features and the association identification coefficients to the processing module. And the image processing module processes the image data according to the association identification label, and the presentation of the image data is optimized through operations such as construction of an association feature set, screening of isolated features and fuzzy processing, so that the analysis precision of the platform and the user experience are improved.

The invention discloses an agent model training and calling method for system simulation, which is characterized in that under the condition that given training set data is unchanged, an agent model can be efficiently constructed by applying the self-adaptive agent model training method provided by the invention, and the agent model is ensured to have high accuracy and good generalization ability; meanwhile, the method can be adapted to a current mainstream system simulation tool. According to the method, a general format capable of being called by each mainstream simulation tool can be generated, and the constructed proxy model can be published to other simulation tools for use in a standard general format. The whole agent model training process does not depend on manual operation, so that the method has the advantages of high efficiency and high accuracy, and reference significance is provided for the RBF agent model and the agent model training process in other forms.

The application discloses a logic defect intelligent detection method and system based on business semantic enhancement, which comprises the following steps: constructing a historical business defect knowledge base by using multi-dimensional information of historical defects; extracting business domain, language, file path and business rules from the code to be detected; generating a code semantic vector according to the code to be detected; performing multi-modal representation learning on the code to be detected, using a multi-modal fusion mechanism to fuse the embedded representations of abstract syntax tree, control flow graph, program dependency graph and business semantic graph, and generating a code graph structure; adopting a hierarchical retrieval strategy to filter similar historical defects from the historical business defect knowledge base; inputting the code to be detected and the similar historical defects into an adaptive Agent reasoning engine, performing static and dynamic analysis on the code to be detected through a natural language instruction driven tool, and comprehensively generating a defect detection result; and verifying the result according to the confidence output by the adaptive Agent reasoning engine and generating a defect report.

The application belongs to the field of digital government service system modeling, and provides a self-adaptive intelligent agent modeling method, system and product for digital government service, and the technical scheme is: obtaining business processing data of intelligent agents of various government departments; based on the business processing data of the intelligent agents of various government departments, a digital government service model is constructed; according to different response variables, the modeling characteristics corresponding to the digital government service model are matched, and according to the correlation between the response variables and the corresponding modeling characteristics, events leading to significant changes in the response variables are determined. This framework captures and models the micro individual characteristics and emergence mechanism in the digital government service system, which not only helps to standardize the modeling process, but also eliminates the gap between the complex characteristics modeling of the intelligent agents and the system of the government departments and the application of AI technology.

The invention discloses a multi-graph feature combined code similarity detection method based on reinforcement learning, and the method comprises the following steps: carrying out the preprocessing of a to-be-detected code, and generating an AST (abstract syntax tree) and a PDG (program dependency graph); extracting a sequence feature matrix of AST by adopting Transform, and extracting a graph feature matrix of PDG by adopting a GATv2 + model; constructing a three-layer reinforcement learning agent optimization detection parameter based on a PPO algorithm, including constructing a feature weight adaptive agent, a cross-language structure alignment agent and a local-global matching collaborative agent; and based on the optimal weight, in combination with the alignment list and the optimization matrix, calculating the similarity through a weighting formula and outputting the similarity. The invention provides a code similarity detection method based on reinforcement learning by combining multi-graph features, which realizes an integrated architecture of scene-divided similarity calculation, realizes accurate detection of different types of codes, does not need to manually preset fixed parameters, and remarkably improves the detection precision and scene adaptability.

The invention provides a contract review-oriented LLM multi-agent adaptive dynamic collaborative design method, which comprises the following steps of: firstly, constructing a specialized agent library containing multiple types of universal bases, special contracts and the like, and covering the professional review capability of multiple fields; secondly, establishing a semantic ontology dynamic communication protocol between intelligent agents, and ensuring that information transmission is accurate and efficient; constructing a workflow adaptive engine through the contract feature vector, and dynamically generating an adjustment review path; after a to-be-examined contract is preprocessed, selecting an adaptive agent to establish a collaboration group and triggering a workflow; the intelligent agent executes review according to the process, a multi-element collaborative decision-making mechanism is adopted to process cross-domain clause conflicts, and a staged structured result is generated; and finally, fusing all node results, and outputting a standardized review report. The method solves the problem that the prior art is difficult to meet the core requirements of complex contract review on specialized division of labor, cross-domain collaboration and whole-process controllability.

The invention discloses a Symbolic Kernel for Neuroadaptive Wearables (SKNW), a real-time embedded operating system enabling symbolic cognition, ethical reasoning, and adaptive agent modulation in wearable AI devices. The system interprets biometric signals including EEG, GSR, HRV, and facial microexpressions, converting them into symbolic cognitive primitives that guide AGI behavior. It comprises a Biometric-Symbolic Compiler, Wearable Arbitration Engine, AGI Intent Modulator, and Neurofeedback Override Channel to establish a closed-loop symbolic feedback pathway allowing users to influence, pause, or override AGI actions based on emotional or ethical states. The kernel provides explainable, consent-aware arbitration and ethical co-regulation between human and agent, ensuring real-time alignment with user volition. Implemented as a POSIX-compliant, RTOS-capable kernel for edge and wearable platforms, the SKNW supports Bluetooth-based data acquisition and on-device symbolic execution, enabling interpretable, ethically responsive, and emotionally adaptive interaction between humans and neuroadaptive AGI assistants.

The invention discloses an intelligent agent graphical representation dynamic display method and device based on driving situation self-adaption, and the method comprises the steps: firstly obtaining vehicle parameters and environment parameters uploaded by a multi-source sensor, and carrying out the data preprocessing of the vehicle parameters and the environment parameters; secondly, performing feature extraction on each parameter to obtain a multi-dimensional feature vector; and outputting the current driving scene category by taking the multi-dimensional feature vector as input through a rule detection algorithm or a machine learning model. And finally, mapping the current driving scene category into agent graphical representation rendering, and generating a visual interface frame sequence for dynamic display. According to the method, the intelligent agent graphical representation serves as an interface core, multi-dimensional state information is visually borne, a user can instantly understand energy consumption, safety and the vehicle body condition through the posture and the dynamic special effect of the intelligent agent, and the understanding burden of the user is reduced. Meanwhile, the driving environment is analyzed in combination with various types of vehicle data such as environment, electricity, posture and operation, real-time prompting can be achieved in a high-risk scene, and safety information is improved.

The present invention proposes a method and system for power system load forecasting based on intelligent agent simulation, which relates to the field of power systems. Based on real environmental information and a large language model, individual intelligent agents are constructed, and group categories are divided by clustering; the typical characteristics and behavior patterns of the group categories are input into the large language model to generate group electricity consumption behavior characteristics and patterns in different scenarios; the behavior probability distribution of each group category in different scenarios is estimated, and the probability distribution is sampled to obtain individual electricity consumption behavior; based on the individual electricity consumption behavior, the power system load forecast result is obtained through analysis. The present invention integrates LLMs into ABM, constructs millions of adaptive agents, simulates the diversity of user behavior and group effects, and combines environmental interactions to perform power load forecasting. While maintaining computational efficiency, it balances the complexity of agent behavior, so that detailed agent electricity consumption or charging behavior analysis can be achieved in large-scale simulations, providing support for power grid planning and management.