496results about How to "Improve learning efficiency" patented technology

The invention discloses a decision-making method and model for off-line reinforcement learning and continuous on-line fine tuning, and the method comprises the steps: obtaining original text-image pair data and historical track data, and obtaining an enhanced state sequence through feature matching verification and standardization processing; performing sequence prediction by using a multi-level attention mechanism, and obtaining pre-training model parameters through knowledge distillation and task adaptability enhancement; on the basis of stability evaluation and plasticity control, online knowledge migration is carried out on the model, and optimized model parameters are obtained by combining experience playback optimization; and finally, performing multi-dimensional performance evaluation and resource optimization. According to the method, through multi-modal feature fusion, dynamic knowledge migration and an adaptive optimization mechanism, the problems of insufficient feature representation, disastrous forgetting, low optimization efficiency and the like are effectively solved, and the learning efficiency and generalization ability of the model are improved.

The invention provides a digital factory operation virtual simulation teaching method and system, and relates to the technical field of smart factories, and the method comprises the steps: collecting factory operation data, carrying out the standardization processing and correlation analysis, constructing a multi-dimensional data model, carrying out the feature extraction and semantic mining of the hierarchical data of each dimension, and constructing a multi-level digital twin factory model. Carrying out dynamic modeling, constructing a personalized knowledge graph, generating a learning demand list, matching the learning demand list with a digital twin factory model, and generating a multi-dimensional simulation environment; in the multi-dimensional simulation environment, performing analysis and intention recognition on an operation instruction of the learner, converting the operation instruction into a virtual operation, calculating a normative score of the virtual operation, generating corresponding feedback information based on the normative score and the personalized knowledge graph, updating model parameters based on a response of the learner to the feedback information, and performing simulation on the learner according to the updated model parameters. And completing iteration of the model.

The invention provides a riverbed evolution prediction method based on multi-source data fusion, and belongs to the technical field of hydrological resource monitoring. The method comprises the following steps: acquiring and fusing multi-source data by using different devices, performing data preprocessing to form unified three-dimensional grid data, and then generating a multi-scale feature map based on a designed feature extraction network; based on the designed multi-channel convolutional neural network, learning and extracting features on multiple channels at the same time, and performing hierarchical expression and fusion on different information sources; and finally, based on the designed time sequence regression network, extracting a complex dependency relationship in the time sequence through a double-layer LSTM structure, learning residual error information through an adaptive residual error correction module to improve prediction precision, and obtaining a final prediction result. The method shows relatively high applicability and robustness in a complex river channel environment, and can cope with various river bed form changes caused by natural factors and human activities through multi-source data fusion and an innovative feature extraction and regression method.

The invention belongs to the technical field of learner cognitive state interpretation, and particularly discloses a brain-language-vision large model-based cognitive state interpretable method, which comprises the following steps of performing multi-modal data collection for the cognitive state of a learner; performing learner cognitive state characterization based on a multi-scale map convolutional network; brain-vision-language mixed multi-modal time sequence feature fusion based on hierarchical mutual information maximization is carried out; embedding knowledge graph nodes for enhancing the complex task understanding ability of the multi-modal large model; training a brain-vision-language multi-modal large model guided by knowledge; recognizing a learner cognitive state based on a multi-modal large model; the cognitive state of the learner can be explained and analyzed under the support of multi-mode owned reasoning. According to the cognitive state interpretable method based on the brain-language-vision large model, the input multi-modal fusion features are converted into high-quality prompts so as to guide the large language model to extract implicit knowledge, and important support is provided for reasoning generation.

The invention discloses a knowledge graph-based learning path design system, and belongs to the technical field of learning path design, and the knowledge graph-based learning path design system comprises a knowledge graph construction module which is used for collecting, sorting and representing knowledge in different fields from various sources, and constructing a knowledge graph model; the system comprises a learning module which is used for integrating knowledge levels, interests, preferences and learning style information of users into a coherent knowledge system, a user modeling module which is used for understanding and representing the knowledge levels, interests, preferences and learning style information of the users, and a learning path planning module which is used for generating personalized learning paths according to the information provided by the user modeling module. According to the method, multiple aspects of knowledge graph construction, user modeling, learning path planning, learning resource management, learning monitoring and the like are covered, and through cooperative work of the modules, the system can provide efficient, personalized and comprehensive learning path design, so that the experience and learning effect of learners are remarkably improved.

The invention relates to the field of enterprise process automation, in particular to a multi-mode Action Transform model and an intelligent task execution method thereof. The technical problems that in an existing Web page operation automation technology, flexibility and adaptability are insufficient, generalization ability is weak, context understanding ability is limited, multi-modal information integration is insufficient, and data utilization efficiency is low are solved. According to the technical scheme, the multi-modal Action Transform model and the intelligent task execution method thereof comprise a multi-modal input processing module, a multi-modal fusion module, a Transform encoder and an operation prediction module; according to the method, various inputs such as images, texts and DOM structures are processed at the same time, the fault-tolerant ability and adaptability to page changes are improved, the long-range dependency relationship in the operation sequence can be effectively captured and utilized through the attention mechanism, and deep fusion of various modal information such as the images, the texts and the DOM structures is achieved through the attention mechanism and the feature fusion layer.

The invention provides an automatic task allocation method and system for an elevator emergency rescue platform, and relates to the technical field of artificial intelligence, and the method comprises the steps: obtaining elevator operation state data and environment information data, constructing an emergency task model, and obtaining classified emergency tasks; inputting the classified emergency tasks into a deep reinforcement learning model to generate a task allocation scheme; the deep reinforcement learning model is formed by combining a deep Q network structure with a priority scanning algorithm, and a priority experience playback mechanism is introduced; and constructing a multi-objective optimization module comprising a time constraint, a space constraint and a resource constraint, and optimizing the task allocation scheme by the multi-objective optimization module based on an improved particle swarm algorithm to obtain an optimal task allocation scheme.

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

The invention relates to the technical field of artificial intelligence, and discloses an artificial intelligence-assisted adaptive sickbed control system and method, and the method comprises the steps: carrying out the noise reduction and normalization preprocessing of original physiological data collected by a multi-modal sensor, and obtaining standardized multi-modal data; performing time sequence fusion and dimension reduction to obtain low-dimensional fusion features; performing feature extraction through a multi-branch convolutional neural network to obtain generalization feature representation; the optimal posture demand of the patient is predicted through a long-short term memory network model with an attention mechanism, and an optimal posture demand prediction result is obtained; a layered sickbed adjustment strategy is generated through a double-time-scale reinforcement learning network comprising a priority experience playback mechanism; according to the intelligent sickbed control method and system, the multi-mode sensing data can be comprehensively utilized, the adaptive learning ability is achieved, the intelligent sickbed can be accurately controlled, and the performance and the application effect of the intelligent sickbed are improved.

The invention discloses a course learning planning system based on a computer, and relates to the technical field of course learning planning, and the course learning planning system comprises a learning data acquisition module, a knowledge graph construction module, a learning index scoring module, a multi-index comprehensive evaluation module, a learning plan making module and a real-time progress feedback module. Wherein the modules are connected through electric signals; the learning data acquisition module is used for collecting learning data of students and determining evaluation indexes of the learning data. According to the course learning planning system based on the computer, by monitoring the learning progress and achievement of students, instant learning feedback is provided for the students, so that the students can quickly know the learning state of themselves, related learning resources and exercises are intelligently recommended according to the learning conditions of the students, the students are helped to consolidate knowledge and make up for deficiencies, and the learning efficiency is improved. Students can achieve a higher learning effect in a shorter time, and the learning efficiency is improved.

The invention, which relates to the technical field of artificial intelligence and skill training examination, discloses a multi-crowd adaptive training evaluation system comprising the following components: a user data management module, an RAG module, an answer processing module, a score analysis module, an intensive training module and a question bank updating module. According to the method, comprehensive and accurate assessment of the user ability is realized by constructing a multi-crowd adaptive training assessment system, the system constructs the user ability portrait by collecting historical data and real-time performance of the user in multiple dimensions and utilizing advanced data processing and analysis technologies, and dynamically adjusts the training content and difficulty, so that the user ability assessment efficiency is improved. According to the method and the system, the ability level and the learning requirement of different users are adapted, the personalized training mode not only improves the participation degree and the learning efficiency of the users, but also helps the users to quickly and accurately identify the ability weakness of the users, and powerful support is provided for subsequent improvement.

The invention discloses a target detection tracking method and system based on automatic detection, and relates to the technical field of target detection tracking, and the method comprises the following steps: carrying out the target position and category labeling of an image through a labeling tool based on an image data set of a typical target, and obtaining a training data set with a label, establishing a target detection model according to a YOLO architecture, and introducing a dynamic weighted loss function; according to the training data set, a training batch is generated by using a hierarchical sampling strategy, an optimized training sample is obtained through an online difficult case mining mechanism, and iterative training is performed on the target detection model based on the generated training batch and the optimized sample; and performing target detection on the real-time video stream by using the trained target detection model to obtain the tracking position and category information of each frame. According to the method, the problem of class imbalance can be effectively solved, the detection capability of rare targets is improved, and meanwhile, the overall performance of the model is improved through difficult case mining.

The invention relates to the technical field of optimization methods, in particular to an action type model optimization method based on reward feedback, which comprises the following steps of: SI, constructing a multi-level reward function; s2, starting and initializing; s3, observing a current web environment state; s4, executing the action; s5, environment feedback; s6, constructing a Reward model reward signal processing module; s7, reward signal processing; s8, constructing an action evaluation network; s9, action evaluation; s10, updating the strategy; s11, judging whether the task is completed or a termination condition is reached; according to the method, a more comprehensive action feedback mechanism is established, the final reward is considered, the effect of the intermediate action is fully utilized, the action of the intelligent agent is evaluated and fed back more meticulously, the intelligent agent is guided to explore and utilize the environment more reasonably, and the user experience is improved. And an action feedback mechanism encourages the intelligent agent to try more actions which may contribute to realizing the target, and meanwhile, invalid or harmful actions are avoided, so that the exploration of the intelligent agent in the web environment is more efficient.

The invention relates to the technical field of intelligent teaching, in particular to an intelligent teaching system for traditional Chinese medicine clinical skill cultivation. The system comprises a virtual reality simulation module, an operation interaction module, an operation data analysis module, an adaptive learning feedback module and a teaching evaluation module. The virtual reality simulation module constructs a vivid traditional Chinese medicine skill training scene through three-dimensional modeling, ray tracing and physical simulation technologies, and the vivid traditional Chinese medicine skill training scene covers pulse feeling, acupuncture and moxibustion, massage and other operations. The operation interaction module collects user operation data and extracts features in combination with a variational auto-encoder. The operation data analysis module analyzes user operation deviation by using a graph neural network and a generative adversarial network, the adaptive learning feedback module generates a personalized learning strategy, and the teaching evaluation module evaluates a learning effect through fuzzy evaluation and analytic hierarchy process. According to the invention, intelligence, individuation and high efficiency of traditional Chinese medicine clinical skill cultivation are realized, the fidelity of teaching and the accuracy of feedback are improved, and the skill level and the training effect of learners are also improved.

The invention discloses a comprehensive management system for an intelligent digital campus, and relates to the technical field of digitization, and the system comprises the steps: collecting the learning behavior data of students in real time, and forming a preliminary data set of the students; the learning behaviors of the students in the preliminary data set are analyzed, and a personalized learning portrait of each student is generated; based on the personalized learning portrait, determining a learning demand and a resource demand feature of the student; pushing a personalized learning path and dynamically adjusting a teaching resource allocation scheme according to the learning demand characteristics and the resource demand characteristics of the students; and collecting energy consumption data of each region, and automatically optimizing an energy consumption use strategy in combination with a resource allocation result and the energy consumption data of each region to obtain an optimized learning environment. According to the resource scheduling strategy based on personalized demands, the learning efficiency of students can be improved, and full utilization of resources can be ensured.

The invention discloses a multi-modal federation active learning-based network anomaly detection method, which comprises the following steps of: fusing data of a plurality of modals through multi-modal feature aggregation to generate uniform feature representation; an active learning mechanism is introduced into the federated learning framework, and distributed nodes are allowed to autonomously select learning strategies according to characteristics and distribution conditions of own data; the node isomerism in the distributed environment is dealt with through an adaptive learning optimization strategy; the communication efficiency is optimized and the global synchronization frequency is reduced through a progressive federated synchronization mechanism; according to the method, multi-modal data fusion and federated active learning are combined, so that the precision and efficiency of network anomaly detection are improved on the premise of protecting data privacy.

The invention provides an automatic expansion and contraction method and system for a Kubernetes container based on double agents in the technical field of cloud computing resource management, and the method comprises the steps: S1, building an expansion and contraction model based on a double-agent module, a state space layering module and an attention experience playback module, and setting a reward function of the expansion and contraction model; s2, acquiring a large amount of historical workload data of the Kubernetes containers to construct a data set; s3, dividing the data set into a training set, a verification set and a test set based on a preset proportion, training the telescopic model through the training set, continuously optimizing the telescopic model through a reward function in the training process, verifying the trained telescopic model through the verification set, and testing the telescopic model passing the verification through the test set; and S4, the cloud computing resources of the Kubernetes container are scheduled through the telescopic model which passes the test. The method has the advantages that the resource utilization rate, efficiency and reliability of cloud computing resource scheduling of the Kubernetes container are greatly improved.

The invention discloses a personalized homework generation method based on an artificial intelligence algorithm. The personalized homework generation method comprises the following steps: S1, collecting multi-dimensional learning behavior data of a learner; s2, constructing a knowledge point mastering model of the learner based on the knowledge graph; s3, generating a behavior feature vector set of the learner; s4, constructing a cognitive load model of the learner according to the behavior feature vector set and the knowledge point mastering model in combination with the knowledge point relevance; s5, generating and dynamically adjusting a personalized job; s6, adjusting relevance weights of recommendation contents and knowledge points of the personalized homework; s7, updating the generation strategy of the personalized operation in real time; s8, enabling the learner to complete proper exercise content at a proper time; and S9, providing a personalized homework generation scheme for the learner according to the updated behavior feature vector set, the knowledge point mastering model and the cognitive load model. According to the method and the device, the homework generation and pushing dynamically adaptive to the requirements of the learner are realized, and the accuracy and the adaptability of personalized homework generation are improved.

The invention relates to the technical field of intelligent fault diagnosis systems, in particular to an intelligent fault diagnosis system and method for multi-sensor data fusion, and the system comprises an online diagnosis module and an offline training module, the online diagnosis module comprises a self-adaptive balance sub-module and a prototype network sub-module, and is used for processing sensor data in real time and carrying out fault diagnosis; the offline training module comprises a data preprocessing sub-module, a data fusion sub-module, a fault diagnosis sub-module, a data balance sub-module and a data interpretation sub-module, and is used for optimizing a diagnosis model; the data interpretation sub-module comprises an SHAP value extraction unit which is used for interpreting a diagnosis result; an online diagnosis module and an offline training module of the system form a closed-loop optimization mechanism, so that the diagnosis model can continuously learn and adapt to a new fault mode. The design ingeniously balances the requirement of real-time diagnosis and the requirement of continuous optimization of the model, and the long-term effectiveness of the system is greatly improved.

The invention provides an electroencephalogram signal recognition method of a domain decoupling electroencephalogram representation learning model based on hybrid experts, and the method comprises the steps: carrying out the spatial domain coding of sample electroencephalogram data, and obtaining spatial domain feature electroencephalogram data; performing frequency domain coding on the spatial domain feature electroencephalogram data to obtain sample electroencephalogram feature data; performing multi-head self-attention calculation on the sample electroencephalogram feature data to obtain sample electroencephalogram attention feature data; performing hybrid expert domain decoupling processing on the sample electroencephalogram attention feature data to obtain sample electroencephalogram reconstruction data; and according to the sample electroencephalogram reconstruction data and the sample electroencephalogram feature data, performing parameter adjustment on the electroencephalogram representation learning model to obtain a trained electroencephalogram representation learning model.

The invention provides an auxiliary hierarchical reinforcement learning training method and system based on a large language model. The method comprises the steps that a teacher agent and a student agent receive the same environment observation information; the teacher intelligent agent adopts a large language model and gives a guidance strategy according to the received environment observation information, and the guidance strategy is introduced into the training module; the student agent gives a high-level strategy according to environment observation information, and when the high-level strategy is transmitted into a corresponding low-level strategy option pi omega, the pi omega generates a series of actions according to a high-level strategy target and the environment until a termination condition is reached or the maximum task step number is exceeded; meanwhile, each action output by the low-level strategy interacts with the environment and obtains an environment reward, and the environment reward accumulation sum is regarded as a reward obtained by the current high-level action, and the environment reward accumulation sum is sent to the training module for the student intelligent agent to learn towards the environment; and the training module is used for updating the high-level strategy network of the student intelligent agent by using the loss function.

The invention belongs to the technical field of healthy lighting, solves the problem that the lighting environment in a classroom cannot be dynamically adjusted in the prior art, and provides a healthy lighting control method, device and equipment for dynamically adjusting the lighting environment in the classroom. The method comprises the steps of obtaining a corresponding time schedule with a target illumination space as a classroom; querying the time schedule according to the current time to obtain teaching activity information corresponding to the current time; obtaining a parameter adjustment coefficient of an illumination adjustment parameter according to the teaching activity type; for each teaching activity type, adjusting an illumination control parameter by using an adjustment coefficient to obtain a target illumination parameter; according to the target illumination parameter, the historical illumination adjustment parameter and the teaching activity type and time period, obtaining an illumination adjustment rate; and controlling the light source to illuminate according to the target illumination parameter and the illumination adjustment rate. The illumination environment in the classroom can be dynamically adjusted, and the healthy illumination requirement of a user is met.

The invention discloses an improved YOLOv8 fish image recognition method based on transfer learning, and the method comprises the following steps: collecting a fish image data set, and carrying out the preprocessing of the data set; correspondingly marking category names on the fish image data set according to fish categories, and dividing the fish image data set into a training set, a verification set and a test set in proportion; a standard YOLOv8 model is improved; all fish images in the ImageNet data set are adopted to pre-train the improved YOLOv8 model, and obtained weight parameters are migrated to the model; performing optimization parameter training on the improved YOLOv8 model after transfer learning by using the training set and the verification set; and performing target detection on the test set through the optimized improved YOLOv8 model, and outputting a fish identification result. According to the method, the feature extraction and recognition precision is effectively improved, the computing resource demand is reduced, and the robustness and adaptability of the model are enhanced; according to the method, the learning efficiency and the recognition precision of the model are remarkably improved, data dependence is reduced, and the model has high generalization ability.

The invention discloses a fine-grained knowledge point mastering analysis method based on local graph convolution, and the method comprises the steps: S1, collecting the learning behavior data of students, and constructing an initial knowledge graph based on the learning behavior data; s2, establishing a local graph convolution model based on the initial knowledge graph; s3, updating and generating a knowledge graph with personalized features; s4, based on the personalized knowledge graph, generating a knowledge point mastering condition table by calculating a mastering degree index of each knowledge point; s5, performing clustering analysis on the knowledge points of which the mastering degree indexes are lower than a preset threshold value in the knowledge point mastering condition table; s6, generating knowledge blind spot group feature vectors; and S7, generating a learning strategy for each knowledge blind spot group according to the feature vectors of the knowledge blind spot groups. According to the invention, refined evaluation and real-time dynamic tracking of knowledge point mastering are realized.

The invention relates to the field of electronic component workshop AGV logistics scheduling, and discloses an improved PPO scheduling method and system in an electronic component workshop AGV composite operation mode, a medium and equipment, and the method comprises the steps: carrying out the rasterization of a workshop environment map through grid modeling, enabling the AGV to carry out an A * search algorithm in a grid map through a plurality of task orders, obtaining batch sample data, and carrying out the calculation of the A * search algorithm in the grid map; pre-training is completed according to model parameters of the sample pre-training strategy network; according to the new task order, the AGV interacts with the environment, an observation state, an action space and a reward value are obtained, after matrix processing is carried out on the observation state, the observation state serves as input data of a PPO algorithm, a strategy network loss value and a value network loss value of the PPO algorithm are calculated, network model parameters are updated through a gradient descent method, and PPO training is completed; and generating a real-time task order on line, and guiding the AGV to complete path planning and scheduling tasks through the decision network models trained in the first two stages. According to the method, the electronic component workshop AGV scheduling strategy can be obtained through rapid learning, the learning efficiency is remarkably improved, and stability is achieved.

The invention relates to the field of gas leakage detection, and discloses a gridding directional laser methane detection system, which comprises the following steps of: acquiring area information which comprises a methane absorption signal, environmental data, background gas, an area image and historical leakage data; generating first two-dimensional structure data from the collected regional information, wherein the first two-dimensional structure data comprises a data matrix and a relation matrix; first one-dimensional structure data is obtained based on sorting of the first two-dimensional structure data, wherein the first one-dimensional structure data comprises n data items sorted according to time; and inputting the first two-dimensional structure data into the detection model, and outputting a methane leakage processing strategy. According to the invention, detection and treatment strategies of methane in fuel gas can be realized, and a distribution strategy of the methane laser detection device can be further given.

The invention discloses a self-adaptive wafer defect identification method and system in a semi-supervised field. The method comprises the following steps: acquiring a data set of a wafer defect source domain and a wafer defect target domain; the data set is preprocessed; constructing a cross alignment network, and respectively extracting image features of a source domain and a target domain of the preprocessed data set by using a feature extractor and an encoder; for the extracted image features, using a classifier to obtain an output probability, for unmarked data, determining and updating a false label threshold value of each category through a dynamic threshold value strategy, then using a sample-by-sample cross alignment method, a category-by-category cross alignment method and a consistency regularization method to calculate a loss function, and performing training; obtaining a trained cross alignment network; and the trained cross alignment network is used as a prediction model, and the wafer defect category for identifying the unmarked data of the target domain is output. According to the method, knowledge migration among different data sets can be effectively realized, and relatively high recognition accuracy is realized under the condition that the target domain data set only has a very small number of labels, for example, each category only has one label.

The invention relates to an amphibious vehicle path planning method and system based on fuzzy logic rules and reinforcement learning. The planning method comprises the following steps: collecting scene parameters by using a sensor according to an application scene of the amphibious vehicle, and taking the scene parameters as input parameters; performing fuzzification processing on the input parameters, performing reasoning by using a fuzzy rule base to obtain fuzzy output, and performing output defuzzification on the fuzzy output by using a gravity center method; defining a state space and an action space, resetting an environment, executing an action and calculating a reward, and finishing the step when a turn ending condition is met; an Actor-Critic neural network is initialized, and stable learning of a strategy is realized through experience playback and an updating mechanism of a target network; and training and optimizing the Actor-Critic neural network to obtain an optimal path planning strategy. According to the amphibious vehicle path planning method based on the fuzzy logic rule in combination with reinforcement learning, efficient solution of a path planning problem in a complex environment is realized through combination of a fuzzy logic system and a reinforcement learning algorithm, and the amphibious vehicle path planning method has a wide application prospect.

The invention discloses a user learning behavior analysis system and method based on a knowledge graph, and relates to the technical field of data analysis, the system comprises an evaluation test question labeling module, a knowledge graph construction module, a user investigation evaluation unit and a learning recommendation module; the evaluation test question labeling module is used for performing knowledge point division on all evaluation test questions and labeling the investigation proportion of each knowledge point in the evaluation test questions; the knowledge graph construction module is used for screening all knowledge points involved in user learning contents, constructing a knowledge graph and analyzing a pre-repair relationship between the knowledge points; the user investigation and evaluation unit is used for investigating and evaluating the mastering degree of a user on each knowledge point in the knowledge graph; and the learning recommendation module is used for screening recommended learning knowledge points according to the mastery degree of the user on each knowledge point in the knowledge graph, calculating and analyzing the recommendation priority of each recommended learning knowledge point and the adaptation degree of each evaluation test question, and synchronously recommending the knowledge points and the evaluation test questions to the user.

The invention provides an active load shedding optimization control method, system and device of a wind power plant and a storage medium, and belongs to the technical field of active power control of the wind power plant, and the method comprises the steps: constructing and training an SAC intelligent agent through an SAC algorithm; acquiring a wind power plant state quantity; inputting the state quantity of the wind power plant into the SAC intelligent agent to obtain a vector # imgabs0 # composed of active power initial reference values of all wind turbine generators; inputting the # imgabs 1 # into a constraint controller for secondary calculation to obtain a vector # imgabs 2 # composed of active power optimization reference values of the wind turbine generators; the wind power plant executes # imgabs3 #; and repeating the steps, and adjusting the active power of each wind turbine generator in real time. The model is high in generalization, stability, reliability and learning efficiency, real-time online calculation of the equivalent fatigue load can be achieved, reasonable distribution of the active power of the wind power plant can be achieved under the condition that the active power constraint of the wind power plant is met, the equivalent fatigue load of the whole wind power plant can be reduced, and the maintenance cost can be reduced.