2837 results about "Decision process" patented technology

The invention relates to a dynamic data pipeline construction method based on artificial intelligence and multi-modal data processing, and belongs to the technical field of data fusion treatment and artificial intelligence. According to the method, a multi-modal deep learning model is adopted, semantic analysis is performed on business documents, user requirements and function specification instructions, and key indexes, data requirements and logic constraints are extracted; constructing a multi-modal knowledge graph, performing unified representation and feature extraction on structured and unstructured data resources, and performing embedded learning by using a graph neural network; based on a deep semantic matching model and a hybrid recommendation system, realizing accurate matching of business requirements and data resources; modeling generation of a data processing flow into a Markov decision process by adopting a reinforcement learning strategy, and automatically generating an optimized data processing workflow; the adaptability of the model to new business requirements is improved by utilizing a meta-learning algorithm; and dynamic scheduling and execution of tasks are realized through a workflow engine. According to the invention, the data processing efficiency can be improved.

The invention discloses an AI agent design platform decision optimization method based on big data, and particularly relates to the field of artificial intelligence, comprising multi-modal data sensing layer construction, a streaming feature calculation engine, a dynamic index fusion center and an adaptive decision matrix. According to the method, accurate synchronous monitoring of the utilization rate of hardware resources and dynamic collaborative optimization of heterogeneous computing units are achieved, and the resource scheduling efficiency in a complex computing scene is remarkably improved; knowledge system degradation caused by long-term learning is effectively prevented, and the continuous reliability of a cognitive system is ensured. The provided multi-dimensional decision credibility verification system is fused with interpretability penetration analysis, environment coupling modeling and logic drift detection technologies, the limitation of a traditional single credibility index is broken through, the risk prediction and fault-tolerant capability of the decision process is remarkably enhanced, and a full-dimensional safety decision guarantee system is constructed for an intelligent agent.

The invention discloses a method and a system for collecting decision data by an intelligent agent driven by a multi-modal large model. The method comprises the following steps: collecting original data of a predetermined sensor, calculating information entropy and a normalized mass score, and generating a fusion feature vector through self-adaptive multi-modal information fusion; time sequence sensitive multi-mode alignment processing is carried out on the image, and time sequence alignment features are obtained by combining timestamp embedding and a self-attention mechanism; based on this, decision distribution is generated by using a Bayesian neural network, uncertainty is evaluated, and a final decision and index set is generated; evaluating a task score in combination with task description, and making an execution plan according to a resource state; initializing the model, generating synthetic data, optimizing the model and storing experience. According to the invention, the efficient decision-making process of the intelligent trolley is realized, and the execution capability and task completion precision of the intelligent trolley are improved.

The invention discloses a predictive maintenance method for an optical storage and charging integrated power station based on deep learning, and the method comprises the steps: constructing an efficient equipment state evaluation and prediction model based on multi-source data fusion, an intelligent prediction algorithm and a closed-loop optimization feedback mechanism, collecting multi-source data, and carrying out the fusion processing, an improved Attention-LSTM model is utilized to evaluate and predict the state of equipment, a transfer learning method is adopted to improve generalization ability, Bayesian optimization and an adaptive sliding window technology are combined at the same time, dynamic threshold adjustment is performed, a deep reinforcement learning algorithm based on a Markov decision process is adopted to optimize a maintenance strategy, and the maintenance efficiency is improved. Weibull distribution is introduced for failure probability modeling, the maintenance cost and the fault risk are balanced, continuous optimization and dynamic adaptive adjustment of a predictive maintenance scheme are realized through a closed-loop feedback mechanism, the prediction accuracy and the intelligent level of maintenance decision are remarkably improved, planned maintenance and sudden fault maintenance are reduced, and the maintenance efficiency is improved. And the reliability of the charging station is improved.

The invention provides a decision generation and execution method and system based on an AI agent, and the method comprises the steps: analyzing a user demand document through a natural language processing technology, and extracting key information to construct a structured cue word; then inputting the cue word into a private domain AI agent based on a large model, and generating a preliminary decision scheme in combination with a professional domain database; automatically generating adversarial introspection probe cues, and guiding an AI agent to carry out consistency, risk and constraint conformity evaluation on the preliminary scheme; the system collects feedback response of the AI intelligent agent, analyzes the feedback through a pre-trained graph neural network, and calculates a confidence score of a decision scheme; when the confidence reaches a preset threshold value, automatically generating an execution script according to the decision scheme; and the execution script automatically operates the target system through the preset API and generates an execution document. The whole process realizes a closed-loop intelligent decision-making process from demand understanding, scheme generation, self-verification and automatic execution, and the decision-making efficiency and reliability are remarkably improved.

The invention provides an optical storage charging and discharging station aggregation control and optimization method based on a virtual power plant, and aims to solve the problems of multi-target collaborative optimization, dynamic resource response and uncertainty robustness. By introducing a Markov decision process and an adaptive clustering algorithm, the system can dynamically aggregate photovoltaic, energy storage and charging pile resources according to equipment characteristics, and power dispatching is optimized. A multi-objective optimization model is adopted, economical, technical and environmental objectives are combined, a dynamic weight factor is introduced, and optimal scheduling is generated in combination with a fuzzy decision theory. And real-time compensation is carried out by adopting a rolling time domain control framework and deep reinforcement learning, so that the scheduling precision and the response speed are improved. The edge computing and cloud collaboration mechanism reduces the communication load through a lightweight federated learning model, and improves the scheduling response efficiency. According to the invention, the scheduling efficiency of the optical storage charging station can be obviously improved, the operation cost is reduced, the system stability is improved, and the system has good adaptability and expandability.

The invention provides a marketing strategy optimization method based on big language model analysis and evaluation driving, and the method comprises the steps: obtaining historical data including user behavior data, label data and statistical data, carrying out the analysis, and constructing a basic marketing strategy; user content data are collected in real time through Kafka, deep analysis is conducted on user content through a large language model, and a personalized marketing scheme is matched from a knowledge base based on the deep analysis result of the large language model and basic rule matching; through a feedback circulation mechanism, feedback of the user to marketing activities is collected, and a feedback result is stored in a knowledge base and used for optimizing a marketing strategy and a large language model; meanwhile, the decision-making process is logged, textualized and vectorized and is stored in a vector library, and the decision-making process and the marketing scheme are optimized in combination with a continuously optimized large language model, so that dynamic adjustment and matching are realized. According to the invention, the accuracy and effect of the marketing strategy are improved by using the large language model.

The invention relates to the technical field of information retrieval, and discloses a multi-modal fusion and reinforcement learning collaborative retrieval enhancement generation method and system. The method comprises the following steps: receiving an original query input by a user, and generating a sub-query based on a large language model in combination with a multi-modal context of a current iteration step; forming a current state in combination with the sub-query and the multi-modal context, modeling a retrieval enhancement generation task as a Markov decision process, and adaptively selecting an optimal action from a predefined action set in the current state by utilizing a large language model according to a decision strategy; executing a corresponding multi-modal retrieval operation according to the optimal action, fusing the obtained multi-modal information, generating an intermediate answer or a final answer of the sub-query, and updating a multi-modal context by using the intermediate answer; off-line training optimization is carried out on the large language model through imitation learning and a calibration chain, and decision strategies and sub-queries are inferred online through the model after fine adjustment. According to the invention, more efficient and accurate complex query processing is realized.

The invention discloses a city updating intelligent expert system architecture and method based on a large language model, and relates to the technical field of city planning and construction. The knowledge base management module supports efficient retrieval and application of professional domain knowledge; the expert agent group comprises a user-defined core expert and a system dynamic supplement expert; the expert team collaborative decision-making module is used for executing multiple rounds of hierarchical collaborative decision-making processes; the meta-agent module is responsible for project feature analysis and expert team dynamic configuration; the auxiliary agent module comprises a host agent which is responsible for guiding the decision making process; the recorder agent generates a decision summary report; the verification agent is responsible for verifying and evaluating the professional ability of the expert agent; and the scoring agent evaluates the decision quality. According to the method, the problems of dispersed professional knowledge, low cross-domain expert cooperation efficiency, high decision-making cost and the like in the existing city updating decision-making process are solved, and the decision-making efficiency and quality of city updating early-stage planning are comprehensively improved.

The invention discloses an agricultural pest question-answering method based on knowledge graph adaptive hybrid retrieval enhancement. The method comprises the following steps: 1) data acquisition and arrangement; 2) construction of a knowledge graph and a vector library; 3) constructing a question and answer pre-classification system; 4) building and training a question type automatic classification model: automatically identifying and classifying the questions input by the user by using a small classification model to form a self-adaptive retrieval classifier; 5) self-adaptive knowledge retrieval based on question types: according to the queried question types, self-adaptively and dynamically selecting different retrieval methods of the knowledge graph and the vector library; 6) selecting a corresponding thinking chain reasoning method according to retrieval results of the knowledge graph and the vector library, and constructing a Prompt cue word with high pertinence; according to the method, the knowledge graph and vector library retrieval are fused, so that the answering precision and accuracy are improved, and by integrating a thinking chain (CoT) reasoning framework, the decision-making process of disease and insect pest problem analysis and answering has a clear logic chain.

The invention discloses an intelligent low-code development method and system based on deep learning model optimization, and relates to the technical field of deep learning. A multi-dimensional domain knowledge graph is constructed, a three-dimensional space-time fusion training sample set is constructed based on the domain knowledge graph, and cross-modal feature alignment is performed on the training sample set, so that the multi-dimensional domain knowledge graph is constructed; the method comprises the following steps: generating an executable logic flow template, encoding the executable logic flow template into a Markov decision process, and performing joint strategy optimization on an optimization target of logic flow by integrating a feature importance index generated by a gradient back propagation path and a multi-target reinforcement learning framework of a Pareto leading edge analysis module. Extracting a strategy parameterization sequence after joint strategy optimization, injecting the strategy parameterization sequence into a dynamic verification sandbox environment, and performing abnormal mode detection and feedback type parameter distillation iteration on an execution track through an online variational auto-encoder to complete dynamic adjustment of the strategy; and the elasticity, the stability and the expandability of the low-code platform are improved.

The invention provides a DCS system autonomous controllable upgrading and system fault prediction method and system, and relates to the technical field of fault prediction, and the method comprises the steps: obtaining historical operation data and real-time operation data of a DCS system, carrying out the preprocessing, and generating an autonomous controllable upgrading scheme through a deep reinforcement learning algorithm; the method comprises the following steps of: setting specified time for upgrading time, carrying out consistent backup on the state of the DCS, executing software updating, hardware configuration adjustment and system parameter optimization according to upgrading steps, analyzing indexes of the DCS in real time in the process of executing the autonomous controllable upgrading scheme, and recovering the DCS to the state before upgrading when an abnormal condition is detected. And verifying and optimizing the real-time fault prediction result based on a knowledge graph, and generating an explanatory report including a fault prediction and upgrade decision process according to the optimized fault prediction result and the autonomous controllable upgrade scheme.

The invention relates to the technical field of fault analysis, and particularly provides a monitoring fault analysis method fused with a multi-modal knowledge base, which comprises the following steps: collecting original data of a monitoring fault log, and preprocessing and storing the original data; performing data cleaning and feature extraction on the obtained original data of the monitoring fault log; constructing a searchable knowledge base based on the cleaned data; when the system triggers an alarm, mixed retrieval is executed through a dynamic routing mechanism; aggregating the plurality of retrieval results to generate an executable repair scheme; iteratively optimizing the decision process through manual feedback; and continuously optimizing the knowledge base and the diagnosis model to form a closed loop iteration mechanism. According to the scheme, the accuracy and response efficiency of fault diagnosis are improved.

The invention discloses an intelligent flow arrangement method based on fusion expert network and deep reinforcement learning, which comprises the following steps: collecting network node and link state data in real time, and constructing a time sequence input vector and a topological graph structure; a time sequence neural network and a graph neural network are used for extracting traffic spatial-temporal features and node topological features respectively, future traffic is predicted through a classification network after fusion, and coarse-grained arrangement of network slices of different service levels is completed; modeling resource scheduling into a multi-agent Markov decision process, and designing a state space, an action space and a reward function; a deep reinforcement learning agent is initialized, and training is carried out through interaction experience; fusing a pre-trained expert strategy network, and constructing a total loss function to optimize network parameters; and finally generating an intelligent strategy capable of dynamically optimizing the flow path and resource allocation according to the real-time state. According to the invention, efficient resource scheduling under multi-service differentiation service quality requirements can be realized.

The present invention discloses a method and system for smart grid fault self-healing based on generative artificial intelligence, which relates to the field of smart grid fault self-healing. The method includes: obtaining and preprocessing multi-source heterogeneous data; generating a pre-trained language model and performing domain adaptability fine-tuning, adding a task-specific output layer; performing feature fusion using a multimodal data fusion method, and using annotated historical fault data sets for supervised training to obtain fault diagnosis results. Fault self-healing is modeled as a Markov decision process, and a deep reinforcement learning algorithm is used to interactively learn the optimal decision-making strategy with a power grid simulation environment, and an optimal fault self-healing plan is generated and converted into specific operation instructions. The present invention integrates multi-source heterogeneous data, performs accurate positioning and description generation, improves the reliability and self-healing ability of the smart grid, and ensures rapid recovery of normal operation when a power grid fails.

The invention discloses a multi-modal data processing method and system, computer equipment and a readable storage medium, which can realize deep association and complementarity mining of multi-modal information and improve the accuracy and robustness of multi-modal understanding. The method comprises the following steps: an environment sensing module adjusts an environment sensing strategy according to feedback information transmitted by a self-adaptive decision module, and acquires multi-modal data according to the environment sensing strategy; the multi-modal encoding module encodes the multi-modal data into multi-modal feature vectors of the same dimension; a cross-modal fusion module fuses the multi-modal feature vectors to obtain fusion features; the self-adaptive decision-making module selects a decision-making network matched with the task type from a predefined network library according to the task type of the current decision-making task, inputs the fusion features into the decision-making network, and generates feedback information according to the decision-making process of the decision-making network; and the meta-learning controller evaluates the system performance of the current multi-modal data processing system and adjusts system parameters according to an evaluation result.

The invention discloses a precast beam field production scheduling analysis management method and system based on a large model, and the method comprises the steps: combing precast beam production technological processes, constructing a beam field Internet of Things sensing network, and collecting production information in real time; defining a general engineering data format, establishing a unified standardized beam field production knowledge base, and performing multi-modal data fusion on production elements; analyzing feasibility constraint rule conditions, describing a precast beam production scheduling problem, and establishing a beam field self-organizing scheduling decision mechanism; defining production state characteristics, establishing a beam field scheduling decision process model, and training a large scheduling model based on a PPO algorithm; and developing a beam field scheduling analysis management platform, automatically generating a production scheduling scheme in combination with a real-time production state, and realizing dynamic management of beam field production scheduling. The problems that in the prior art, the resource utilization efficiency is low, scheduling decision making depends on artificial experience, and continuous learning and self-optimization capacity is lacked are solved, and the intelligent level and the management effect of the precast beam field are improved.

The invention discloses a multi-aircraft cooperative formation flight path planning method based on a leader and follower model, and relates to the technical field of environment perception and unmanned aerial vehicle cluster cooperation. The method comprises the following steps of: firstly, designing a multi-agent double delay depth deterministic strategy gradient (LFMATD3) based on a leader-follower model, and converting an optimization problem model into a Markov decision process model by introducing an artificial potential field model and a reward function; and secondly, constructing an independent agent for each unmanned aerial vehicle, optimizing a behavior strategy of the unmanned aerial vehicle by combining a reward function based on an algorithm framework of deep reinforcement learning, and performing flight path planning and realizing dynamic formation control. The method provided by the invention can effectively improve the formation stability and collaboration of the unmanned aerial vehicles in a complex environment.

The invention belongs to the technical field of power distribution network fault recovery, and provides a power distribution network fault recovery method and system based on multi-agent reinforcement learning, and the method comprises the steps: taking a recovered load as a target function based on the load priority of a power distribution network, and taking the operation limitation of each node line in the power distribution network as a constraint condition; constructing a power distribution network fault recovery problem model; based on the power distribution network fault recovery problem model, constructing a multi-agent reinforcement learning agent set, and converting the power distribution network fault recovery problem into a Markov decision process; and a multi-agent reinforcement learning framework is constructed based on the agent set of multi-agent reinforcement learning, multi-agent training is carried out, each agent generates a decision according to respective observation information, and a fault recovery strategy is obtained. The objective function and the constraint condition constructed based on the load priority of the power distribution network and the node line operation limitation can ensure the accuracy and the feasibility of the recovery strategy. And the strategy generation time is shortened through the multi-agent parallel decision-making process.

The invention relates to the technical field of artificial intelligence and insurance, and discloses an intelligent insurance decision core system based on a dynamic dialogue strategy. The system comprises a user interaction module which collects user risk attribute data through voice and text multi-mode input; the insurance product database is used for storing multi-source insurance product structured data; and the intelligent decision-making module is used for generating personalized insurance suggestions by applying a random forest, a gradient boosting tree and other multi-model fusion technologies. A dynamic dialogue strategy engine is further arranged, and a dynamic interaction sequence is generated based on context-aware reinforcement learning. The data synchronization method of the system can obtain latest insurance product data, the multi-model fusion technology improves the decision accuracy, the dynamic dialogue strategy realizes intelligent interaction, the problems of incomplete information collection, inaccurate decision, inflexible interaction and the like in the traditional insurance decision process can be effectively solved, and more efficient and personalized insurance decision service is provided for users.

The decision process of a first machine learning (ML) model may be explained based on a second ML model implemented on an apparatus. The apparatus may obtain a prediction about an image made based on the first ML model. The apparatus may further determine visual concepts associated with the image that may have been used by the first ML model to make the prediction, and determine respective contributions of the visual concepts to the prediction made by the first ML model. The apparatus may then generate, based on the second ML model, a textual description that explains the respective contributions of the visual concepts to the prediction made by the first ML model. The second ML model may determine respective image features associated with the visual concepts, map the determined image features to corresponding text features, and generate the textual description based at least on the text features.

The invention provides a network slice resource allocation method oriented to an industrial internet and related equipment. Comprising the following steps: designing an SDN-based network slice resource allocation management and control architecture which comprises a control plane and a data plane; an intelligent agent is deployed for each switch node in the control plane, and each switch node is provided with an IT slice queue and an OT slice queue; designing a path planning and network slice resource allocation algorithm; modeling joint path planning and network slice resource allocation as a multi-agent Markov decision process; defining a state space and an action space; designing a reward function; constructing and training a multi-agent deep reinforcement learning model; and inputting a network global view collected in the SDN-based network slice resource allocation management and control architecture and demand information of each slice into the deep reinforcement learning agent obtained by training, and outputting a traffic forwarding path and a network slice resource allocation scheme. And the bearable flow quantity of the network can be improved to the maximum extent.

The invention relates to the technical field of natural language processing, in particular to a model distillation method and system based on a teacher model and situational reasoning. By using a multi-teacher learning framework, the student model can draw knowledge from a plurality of large teacher models, and diversified learning paths are provided for the student model; due to the introduction of a context awareness and example generation mechanism, the understanding and reasoning ability of a student model to a complex situation is enhanced by considering context information of input data and an input example; the reasoning chain strategy can ensure that the student model can generate an accurate and deep reasoning process, and the decision process of the teacher model is simulated; a parameter fine adjustment technology is adopted, only key parameters in the student model are adjusted, efficient migration of teacher model knowledge is achieved, and the number of parameters needing to be adjusted in the distillation process of the student model is reduced; the resource consumption in the model deployment and updating process is remarkably reduced, so that the trained model keeps the performance similar to that of the model.

The invention relates to an energy consumption optimization method and device for a server, equipment and a storage medium, and aims to reduce the energy consumption of the server in operation and improve the energy efficiency management level. According to the method, energy consumption of a server in different load states is monitored through a super-resolution data acquisition technology, and load feature embedded representation is generated in combination with a contrast learning network. And based on the embedded representations, performing energy consumption prediction by using a generative adversarial network, and generating a hardware operation parameter adjustment scheme through a Markov decision process and a particle swarm optimization algorithm. And finally, iterative optimization is performed on the scheduling strategy through distributed reinforcement learning, adaptive regulation and control are realized, a target energy consumption optimization scheme is generated, and the accuracy and dynamic response capability of server energy consumption management are remarkably improved.

The invention belongs to the field of reservoir optimization intelligent scheduling, and particularly provides a reservoir multi-objective optimization intelligent scheduling method based on deep reinforcement learning and a deterministic strategy gradient algorithm, which comprises the following steps: collecting original hydrological data and reservoir characteristic curves of a target reservoir; establishing a multi-objective optimization scheduling model including an objective function and constraint conditions; mapping the multi-objective optimization scheduling model into a Markov decision process, and establishing a corresponding reinforcement learning environment; a deep reinforcement learning deterministic strategy gradient algorithm is selected to perform interactive training with the environment, and a reservoir multi-objective optimization intelligent scheduling model is established; and performing multi-target optimization intelligent scheduling on the reservoir through the reservoir multi-target optimization intelligent scheduling model. The method solves the problems that in the prior art, a deep reinforcement learning method generally adopts a fixed weight to design an excitation function, so that the flexibility of a learned scheduling strategy is insufficient, and real-time dynamic coordination optimization of each reservoir scheduling target is difficult to realize according to an environment state.

The invention discloses an information scanning and penetration test path planning method in a Windows domain based on reinforcement learning. The method comprises the following steps: carrying out information detection on a target Windows domain environment, surveying and mapping a network topology of the target Windows domain environment, establishing connection with a target machine by utilizing protocols such as LDAP (Lightweight Directory Access Point) and the like, and collecting related information in the domain; the method comprises the following steps of: collecting, sorting and abstracting detected related information, solving a multi-stage sequence decision problem by utilizing a Markov decision process, realizing environment simulation, constructing a reinforcement learning agent, generating a penetration test path by performing interactive training with a simulation environment, and performing adjustment according to a reward strategy so as to obtain a penetration test result. And searching an optimal penetration test path by accumulating rewards, constructing a Windows domain penetration test model, and finally generating the optimal penetration test path. According to the method, collection of information in the Windows domain and planning of the penetration test path are realized, and finally, the environmental safety of the Windows domain is evaluated and maintained.

The invention belongs to the technical field of mobile communication, and particularly relates to a task unloading and resource allocation method for edge computing. According to the method, a three-layer network structure is established, a distributed decision framework is constructed through reinforcement learning, the task emergency degree is dynamically evaluated, and computing resources are distributed in a differentiated mode; and task unloading and resource allocation are optimized in combination with an edge-cloud collaborative architecture, so that calculation load balancing is realized. According to the method, aiming at a cloud edge-end collaborative edge calculation model, the total cost of a system is defined as a joint optimization problem of task unloading time delay and energy consumption, the problem model is converted into a Markov decision process, and multi-agent and multi-user oriented deep reinforcement learning algorithm agent near-end strategy optimization (MAPPO) is designed; and obtaining an optimal unloading decision through mutual learning among multiple agents. According to the method, the total cost of the system can be effectively reduced, the rationality of edge computing task unloading and resource allocation decision is realized, and meanwhile, the use experience of a user can be improved.

The invention belongs to the technical field of integrated energy system planning optimization, and provides an integrated energy system planning optimization method and system based on deep reinforcement learning in order to solve the problems of difficult solution, long time consumption and the like in integrated energy system planning. Determining an objective function and constraint conditions of the integrated energy system, and forming an initial dynamic programming optimization problem; converting an initial dynamic programming optimization problem into a Markov decision process; performing off-line learning on historical operation data of the integrated energy system by using a DDPG algorithm and a prediction network; and applying the optimization parameters of offline learning to an Online-DDPG algorithm, and solving an initial dynamic planning optimization problem to obtain an optimal planning scheme of the integrated energy system. The problem of solving the model caused by curse of dimensionality and information loss is effectively solved, and meanwhile, the anti-interference capability to load and renewable energy fluctuation is improved.

The invention relates to the technical field of power system fault recovery, in particular to a power distribution network fault transfer optimization method fusing a knowledge base under the participation of a virtual power plant, and the method comprises the steps: firstly modeling a power distribution network fault transfer process into a Markov decision process to construct a power grid environment model, and then extracting power grid topological features through a graph neural network; the method comprises the following steps: extracting and fusing time sequence features in combination with a Transform structure, then introducing expert knowledge to carry out imitation learning, providing an initial strategy for an intelligent agent, then adopting PPO and DQN cooperative training to optimize an intelligent agent strategy, finally aggregating distributed energy with the help of a virtual power plant, realizing resource coordination and fault load transfer, and dynamically correcting the strategy through closed-loop feedback. Therefore, dynamic adaptability, resource cooperation efficiency and strategy reliability of power distribution network fault recovery are improved, power supply recovery time is shortened, and safe and stable operation of a power grid is guaranteed.

The invention belongs to the technical field of power system security, discloses a load frequency control system attack detection method based on reinforcement learning, and aims to improve the recognition and defense capability of a power system on complex network attacks and overcome the defects of a traditional detection method in the aspects of attack sample generation, unknown attack recognition and system adaptability. According to the method, an attack agent based on a Markov decision process is constructed, and an improved reinforcement learning algorithm is adopted to generate a high-concealment confrontation sample; designing a bimodal detection architecture fusing LSTM supervised learning and auto-encoder unsupervised learning, and introducing an adaptive weight fusion mechanism to realize attack type identification and anomaly detection; and incremental learning and a parameter dynamic adjustment mechanism are combined, so that the detection model has continuous learning and evolution capabilities. The method can be applied to a power grid dispatching center or an intelligent micro-grid, real-time monitoring and attack defense of a load frequency control system are achieved, and the operation safety and robustness of a power system are remarkably improved.