7113 results about "Learning methods" patented technology

The invention provides an intelligent task alarm rule self-learning method and system based on support priority, and relates to the technical field of intellectualization, and the method comprises the steps: constructing a bidirectional feature extraction network to collect task operation data, and combining historical alarm data to generate a task exception association model; and carrying out migration mapping on the model and a business scene knowledge base by utilizing a migration learning algorithm, generating a task priority quantitative index, and constructing a self-adaptive priority scoring system. And training an alarm rule generator based on the model and a scoring system, generating a multi-level alarm strategy tree, and realizing differential alarm. And the incremental learning engine monitors a task state in real time, dynamically adjusts an alarm response strategy and feeds back data to optimize a rule. A federal learning mechanism is adopted to cooperatively train a model, and the generalization ability and adaptability of alarm rules are improved, so that more accurate and efficient task alarm is realized, the false alarm rate is reduced, and the operation and maintenance efficiency is improved.

An agent policy learning method with privacy protection in mobile edge computing, which belongs to the technical field of mobile communications. The method comprises: establishing an edge collaborative computing unloading model which comprises a service caching model, a task unloading model and a system cost model; on the basis of the edge collaborative computing unloading model, using the minimization of the processing cost of a task as a target to establish an optimization problem of joint task unloading, service caching, computing power resource allocation and transmission power control; abstracting an optimal problem into a partially observable Markov decision process; and on the basis of the Markov decision process, using a multi-agent deep reinforcement learning algorithm based on a federated learning method to autonomously learn a task unloading, service caching, computing power resource allocation and transmission power control policy. In the present invention, an edge collaborative computing unloading model is established, such that an agent network protects privacy security of data and sensitive information of users by means of training based on federated learning.

The invention provides a micro-grid energy-saving scheme generation method and system based on energy storage optimization scheduling, and relates to the technical field of energy storage optimization scheduling, and the method comprises the steps: collecting historical operation data, real-time operation data and external environment data of a micro-grid system, and carrying out the multi-scene prediction through a Monte Carlo simulation method, and generating a multi-scene prediction result; according to a multi-scene prediction result, a fuzzy decision theory and an analytic hierarchy process are adopted, and an optimal microgrid energy-saving scheme is screened out from the solution set; and converting the optimal energy storage scheduling scheme into an intelligent energy-saving operation instruction set, recording a microgrid operation state, an energy storage scheduling result and energy transaction information by using a block chain, calculating a comprehensive performance index based on data recorded by the block chain, and performing distributed evaluation by using a federated learning method according to the comprehensive performance index. And continuously optimizing the micro-grid energy-saving scheme according to the evaluation result of the comprehensive performance index.

The invention provides an intelligent auxiliary diagnosis and maintenance method and system based on multi-path recall, and relates to the technical field of fault processing, and the method comprises the steps: collecting equipment operation data, extracting and enhancing time sequence features after preprocessing, constructing a feature dependency graph, and generating a state feature vector. And carrying out fault feature recall by using the multi-path recall diagnosis network, fusing to generate a fault propagation map, and further generating a fault diagnosis result. And finally, generating a preliminary maintenance scheme based on a fault diagnosis result and the equipment state transition probability matrix, and optimizing the maintenance scheme by adopting a hierarchical reinforcement learning method in combination with a historical case and a fault propagation map to generate an optimal maintenance scheme. According to the invention, the accuracy of fault diagnosis and the effectiveness of a maintenance scheme can be improved, and the equipment maintenance cost is reduced.

The invention discloses a fine-grained multi-modal prompt learning method based on a visual language pre-training model, and relates to the technical field of visual language pre-training models.The method comprises the steps that a multi-modal prompt learning vector used for learning visual features and text features is constructed, and a fine-grained multi-modal prompt learning model is constructed based on the fine-grained multi-modal prompt learning model; global differences, subtle distinguishing visual features and category difference text features among different visual categories are generated, and a multi-modal prompt learning vector is optimized based on a cosine similarity loss function. According to the invention, through combination of dual-granularity visual prompt and text prompt, the problems that in an existing prompt learning tuning method, cooperative reasoning cannot be carried out in a dual-mode prompt representation space, and fine distinguishing features are difficult to capture are effectively solved; and superior migration generalization ability and few-sample learning ability are verified on a plurality of main image identification reference data sets, and the performance is remarkably improved in downstream tasks.

The invention discloses a vacuum dry pump bearing fault diagnosis method based on domain confrontation and attention transfer learning, and aims to solve the problem of performance reduction caused by data distribution difference of dry vacuum pump bearing faults in cross-domain fault diagnosis of a deep learning method. Domain adversarial training is carried out by introducing a gradient inversion layer, and feature weights are dynamically adjusted in combination with an attention mechanism. According to the method, the distribution difference between the bearing fault data source domain and the target domain can be effectively reduced, and the fault diagnosis precision of the model on the target domain is improved. The method specifically comprises the steps of constructing a deep transfer learning model combining a convolutional neural network, an attention mechanism and domain adversarial training, performing feature extraction and classification training on data of a source domain and a target domain, and optimizing the model by adopting cross entropy loss, domain adversarial loss and maximum mean difference loss. The method shows high diagnosis accuracy and good generalization ability under different working conditions, and is suitable for cross-domain fault detection and diagnosis.

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.

A method is provided for improving image classification accuracy in few-shot learning scenarios, where only a limited number of training examples are available. The method combines the use of Gabor filters and convolutional neural networks (CNNs) to extract detailed texture and orientation features from images. These features are then enhanced through global average pooling, aggregated into comprehensive feature vectors, and refined using an attention mechanism that identifies and emphasizes the most relevant features for classification. Masks generated from this attention process selectively enhance critical features, which, after optional re-encoding, are used to train a classifier via a metric learning approach. This method aims to increase feature separability and classification performance, facilitating more accurate classification of new images with minimal training data.

The invention provides an intelligent temperature adjusting method and system for an injection molding mold. The method comprises the steps that real-time multi-source sensor data flow is generated by collecting temperature data and pressure data of all areas of the injection molding mold; performing feature extraction on the real-time multi-source sensor data flow to obtain temperature field distribution features; a temperature field distribution prediction model is obtained through training based on the temperature field distribution characteristics and a differential private Bayesian optimization algorithm, and then a mold temperature prediction result is output through the model; performing feature fusion on the mold temperature prediction result and the pressure data, constructing input features of a neural network controller, training based on the input features and a positive definite curvature learning method to obtain the neural network controller, and generating a power control signal of a heater and a flow control instruction of a water cooling system through the neural network controller, and based on the control signal and the instruction, the temperature field of the mold is dynamically controlled through the adjustable clearance compensation mechanism. According to the invention, the precision and response speed of temperature adjustment are improved.

The invention relates to the technical field of engineering data monitoring, in particular to a hydraulic engineering data intelligent monitoring method and system based on digital twinning, and the method comprises the following steps: collecting real-time operation data through physical sensors disposed at different nodes of a hydraulic engineering; a self-adaptive digital twinborn model capable of being automatically adjusted is generated through a meta-learning method, and the self-adaptive digital twinborn model dynamically adjusts the internal structure of the self-adaptive digital twinborn model according to the change of real-time data; and on the basis of the adaptive digital twinborn model, constructing a simulation module of a plurality of target scenes, and performing decision simulation in a virtual environment in real time. According to the method, the accuracy and the stability of the digital twinborn model in a complex environment are improved, the model can quickly adapt to real-time changes in the operation process of a water conservancy project through the self-adaptive mechanism, and the prediction precision and the response of the model in a dynamic complex scene are improved.

A generative adversarial multi-headed attention neural network self-learning method for aero-engine data reconstruction belongs to the field of end-to-end self-learning of aero-engine missing data. First, the samples are pre-processed, and the machine learning algorithm is used to pre-fill the normalized data first, and the pre-filled information is involved in the network training as part of the training information. Second, a generative adversarial multi-headed attention network model is constructed and the trained sample set is used to train the generative adversarial multi-headed attention network model. Finally, the samples are generated using the trained sample generator G. The method uses the generative adversarial network to better learn the distribution information of the data, and uses parallel convolution and multi-headed attention mechanism to fully exploit the spatial and temporal information among the aero-engine data.

The invention discloses an unmanned aerial vehicle battery dynamic management reinforcement learning method for adaptive path planning, and relates to the technical field of unmanned aerial vehicles, and the method comprises the steps: activating the multi-modal sensing of an unmanned aerial vehicle at a ground control station, collecting the multi-modal sensing data of the unmanned aerial vehicle, and carrying out the preprocessing; carrying out fusion analysis on the preprocessed multi-modal data by utilizing a deep learning model, generating an environment perception graph, carrying out adaptive path planning by adopting a reinforcement learning algorithm based on the environment perception graph, and dynamically generating an optimal flight path and a battery management strategy deep learning model through the state and environment conditions of the unmanned aerial vehicle; and after the flight task is completed, collecting flight data, environment sensing data and decision records, feeding back to the ground control station, and carrying out iterative training. According to the method, multi-modal perception and deep learning are fused, the path and battery management are optimized through reinforcement learning, and the task efficiency and safety are iteratively improved through group intelligent collaboration.

High-level synthesis (HLS) is a complex design flow that exploits the benefit of modern language features such as loops, inheritance, templates, etc. for rapid prototyping of hardware designs. Hardware engineers explore various design space parameters in a time-consuming trial-and-error approach to meet a target design specification. This invention provides a framework where machine learning methods are integrated with Bayesian optimization (BO) to accelerate hardware design in HLS. This tool is built around the context of HLS pragma exploration and kernel transformation. It can produce best set of pragma installments to determine parameters by optimizing on multi-objective functions, such as reduction of digital signal processor, flip-flop, look-up table, power consumption, and latency. The method uses classical deep neural network and quantum neural network for reinforcement meta learning to predict the synthesis characteristics and synthesizability under a given time budget. A large language model can also assist transpilation to modify the original codes so that the best tradeoff between hardware complexity, latency, and power consumption is realized.

The invention relates to the technical field of computers, and discloses a carbon emission calculation method based on deep learning, which comprises the following steps: S1, collecting multi-source data through a sensor, satellite remote sensing, an intelligent electric meter and a monitoring system, carrying out cleaning, denoising and missing value filling on the collected data, and in addition, carrying out data processing on the collected data; the structured data and the unstructured data are integrated through a multi-source data fusion technology; s2, performing feature extraction on the original data by adopting a deep feature learning model, and screening out key features contributing to carbon emission prediction; and S3, performing real-time decomposition and anomaly detection on the data by combining an autoregressive integral moving average model and an online learning algorithm. By combining an autoregressive integral moving average model and an online Bayesian learning method, carbon emission calculation can dynamically adjust parameters according to real-time data to adapt to environmental changes, seasonal fluctuations and emergencies, so that the flexibility and real-time performance of a prediction model are remarkably improved.

The invention provides a wafer factory-level real-time scheduling method in semiconductor manufacturing based on deep reinforcement learning, which relates to the technical field of semiconductors, and comprises the following steps: constructing a state space vector by collecting equipment state, batch information and process flow information based on deep reinforcement learning, inputting a pre-trained deep reinforcement learning network model, and constructing a state space vector; the model includes a value assessment network and a policy network. The model generates matching probability distribution of batches and devices, a hierarchical reinforcement learning method is adopted to decompose the distribution into two sub-tasks of batch selection and device allocation, and a plurality of candidate matching schemes are generated. And then evaluating the candidate schemes by applying a multi-target reward and punishment function, selecting an optimal scheduling scheme in combination with a Monte Carlo tree search algorithm, and issuing a processing instruction. And real-time processing data is collected in the working procedure processing process to update the state space vector, so that real-time scheduling is realized.

The invention relates to a traffic flow prediction optimization method based on an intelligent optimization algorithm, which is applied to the technical field of traffic flow prediction. The system comprises a multi-modal data acquisition and fusion module, a hybrid deep learning prediction module, an intelligent parameter optimization module, an integrated learning module, a multi-scale error correction module, a prediction result analysis and visualization module, a distributed learning and privacy protection module and the like. Wherein the hybrid deep learning prediction module adopts an attention mechanism to fuse models such as CNN, Transform and LSTM, and introduces an adaptive error correction mechanism, so that the prediction precision is remarkably improved; the intelligent parameter optimization module accelerates the model search efficiency by using technologies such as quantum computing and swarm intelligence optimization; the integrated learning module and the adversarial training strategy enhance the robustness and generalization of the model; and the multi-scale error correction module adopts a time sequence decomposition and self-adaptive online learning method to improve the accuracy of long-term and short-term prediction.

The invention discloses an adaptive differential privacy federal learning method, a client, a server, a storage medium and a product, and the method is applied to the client, and comprises the steps: determining a gradient cutting threshold based on a current training round and a cutting threshold adjustment strategy, the cutting threshold adjustment strategy is constructed according to the data distribution similarity and the gradient change rate corresponding to each training round; cutting the gradient of each sample to obtain a target gradient of each sample; adding noise disturbance to the target gradient of each sample according to an adaptive differential privacy algorithm and the target privacy budget to obtain adaptive noise; and performing model updating in combination with the target data set and the global loss function to obtain local model parameters, sending the local model parameters to a server, and updating the parameters by the server according to the local model parameters to obtain a global model. Through the above mode, the robustness of the model to noise and attack is enhanced, and the capability of protecting data privacy, the accuracy of the model and the generalization capability of the model of the client are improved.

The invention provides a physiological signal self-supervision representation learning method and system based on time-frequency reconstruction, and belongs to the technical field of signal processing and mode recognition. Comprising the following steps: acquiring original multi-channel physiological signal data and converting the data into a time-frequency diagram; carrying out segmentation / blocking, random masking and feature conversion on the physiological signal and the time-frequency diagram thereof to obtain a primary time domain representation and a primary frequency domain representation; coding and fusing the preliminary time domain representation and the frequency domain representation in a time dimension and a channel dimension to obtain a time-frequency mixed representation; pre-training an encoder by adopting a reconstruction learning method based on the time-frequency mixed representation; a pre-trained encoder is used for obtaining multi-channel time-frequency representation of to-be-processed original multi-channel physiological signal data, the multi-channel time-frequency representation is mixed to obtain time-frequency mixed representation, and the time-frequency mixed representation serves as learned physiological signal self-supervision representation and is used for a physiological disease classification task. The method has higher generalization ability and adaptability, and an effective solution is provided for a physiological signal classification task.

The invention provides a smart agriculture fusion system based on Internet of Things and digital twinning, and relates to the technical field of data acquisition, and the system comprises an Internet of Things sensing network which is used for collecting data of soil humidity, soil oxygen, environmental parameters, meteorological information and crop growth states; the big data processing unit is used for receiving the data acquired by the sensor and feeding back the processed data to the digital twinborn model; establishing a digital twinborn model, and constructing the digital twinborn model of the farmland by using the real-time data and historical data of the farmland through a computer learning method and a deep learning algorithm; the control and decision-making unit is used for making farmland management strategies and decisions based on the analysis and prediction results of the digital twinborn model; a user remotely monitors and manages the operation state of the farmland through a terminal, and through the Internet of Things and the digital twinning technology, informatization and intelligentization of the whole chain of agricultural production are achieved, and the efficiency and quality of agricultural production are improved.

The invention discloses an integer programming automatic modeling method based on a large language model, and the method comprises the steps: obtaining an integer programming problem data set, carrying out the processing through employing a data enhancement and dynamic complexity balance method, and obtaining a balance data set of multi-modal representation; processing by adopting a model architecture search and combinatorial optimization method to obtain an optimized neural network model structure; processing by adopting a dynamic sparse training and self-adaptive difficulty course learning method to obtain a model subjected to first-stage training; processing by adopting hierarchical reinforcement learning and a multi-target Pareto frontier exploration method to obtain a final model subjected to second-stage training; processing by adopting a dynamic neural symbol inference method to obtain an integer programming model with enhanced logic consistency; and processing by adopting a self-adaptive antagonism test generation method to obtain a comprehensive evaluation result. According to the method, the modeling efficiency, accuracy and adaptability of the integer programming problem are improved.

The invention belongs to the technical field of smart home control, and particularly relates to a smart home generation strategy optimization system based on adaptive learning, and the system comprises the steps: collecting the operation history, sensor data and equipment use modes of a user in a smart home system, and determining an evaluation standard and an optimization direction; extracting features according to user behaviors, environment changes and equipment states, and constructing a feature matrix; selecting a reinforcement learning method for modeling according to an optimization problem, designing an adaptive learning mechanism, and enabling the model to be continuously adjusted according to real-time data in an operation process; according to the method, historical data is used for training the model, a reward mechanism in reinforcement learning is used for guiding the implementation of an optimization target, a control strategy adapting to the current environment and demand is generated based on model prediction, and the method has the effects of better meeting the use demand of a user for the smart home and improving the intelligent level of the system and the user experience.

The invention relates to a multi-modal data generalization learning method and system based on causal invariant transformation. The method comprises the following steps: acquiring multi-modal data to construct a causal graph; designing causal invariant transformation to simulate a causal relationship, keeping causal features in the causal relationship unchanged, changing non-causal features, and generating a new training sample; fusing information of different modes; and constructing a self-supervised learning framework, predicting labels of the node pairs as pre-training tasks, and learning feature representation and causal structures of the multi-modal data. A causal graph is constructed and analyzed, causal invariant transformation is designed to simulate a causal relationship and generate a new training sample, and the model can learn feature representation consistent with a causal structure, so that stable performance is kept on different distributed data; according to the method, a self-supervised learning framework is constructed, extra labeling information is not needed, data representation and causal structures are learned by predicting labels of node pairs as pre-training tasks, and the generalization ability of the model can be effectively improved.

The invention discloses an image label noise learning method based on granular ball calculation and contrast learning, and the method comprises the steps: obtaining image data, carrying out the preprocessing of the image data, inputting the preprocessed image data into a trained image label noise learning model, and obtaining an image classification result. The training process of the image label noise learning network comprises the following steps: acquiring an image training data set, and performing preprocessing and data enhancement on the image training data set; respectively extracting feature representations of the strong data enhancement sample and the weak data enhancement sample by adopting a contrast learning framework SimSiam, inputting the feature representation of the weak data enhancement sample into a granular ball calculation layer, inputting a feature matrix of the granular ball sample and a label thereof into a classifier after clustering to obtain an image classification result p, and calculating classification loss; predicting the feature representation of the strong data enhancement sample through a prediction layer, and calculating comparison loss by taking an image classification result p as an indicator function; and the network is optimized through back propagation of the comparison loss and the classification loss. According to the invention, the network performance can be obviously improved.

The invention relates to the related technical field of digital data processing, in particular to a personalized federated learning method and system for a heterogeneous multi-source industrial internet, and the method comprises the steps: connecting a client, evaluating a load, time delay and modal similarity to generate a dynamic association table, deploying a hierarchical encryption protocol, and constructing a priority queue; a cache mechanism is set to coordinate distributed iterative optimization, so that the technical problem that network oscillation and computing resource waste are aggravated due to overhigh load of part of nodes caused by frequent access and exit of equipment and data volume difference in the industrial internet and repeated migration of clients and nodes is caused is solved, cross-equipment shared knowledge base vectors are extracted, and the computing efficiency is improved. The technical effects of reducing the influence of model isomerism on aggregation, dynamically scheduling high-frequency parameter local aggregation and low-frequency parameter cloud synchronization, optimizing the association weight of a client and a fog node in real time, realizing privacy protection and efficient personalized federated learning, and ensuring the privacy and security of user data in the training process are achieved.

The invention provides a student adaptive auxiliary learning method and system based on artificial intelligence, and the method comprises the steps: constructing a subject knowledge graph, and carrying out the correlation and structuralization of knowledge points; the knowledge points are associated with learning resources and test questions in the subject knowledge graph; collecting learning behavior data of students, and constructing student portraits; the student portrait comprises three dimensions of learning style, knowledge level and hobbies and interests; wherein the knowledge level is a mastering probability of each knowledge point acquired according to the subject knowledge graph; personalized learning paths, learning resources and learning strategies are recommended to the students according to the student portraits and the subject knowledge maps; and learning results of the students are automatically evaluated and fed back. According to the characteristics and requirements of each student, a personalized learning scheme is provided, the learning efficiency is improved, the limitation of time and space is broken through, and the students can obtain high-quality learning resources which are more personalized for themselves anytime and anywhere.

The invention provides a hybrid representation learning-based omni-directional motion control method for a quadruped robot in a three-dimensional environment, aiming at solving the problem that an existing motion control method for the quadruped robot is limited by a narrow forward view angle and external perception noise of the robot, so that the omni-directional motion capability in the three-dimensional environment is difficult to obtain. Comprising the steps of designing various input and output contents of a first-stage end-to-end neural network learning framework, designing a training process including mixed representation learning based on a reinforcement learning framework, constructing a specific neural network model of each module, and constructing a quadruped robot simulation motion control training environment. The method has the advantages that network input and output content beneficial to efficiently learning the relation between actual observation of the robot and the environment truth value is provided, and a mixed representation learning method including supervised learning and comparative learning is introduced, so that the robot can effectively deduce environment information beyond the visual field range of the robot in the training process.

The embodiment of the invention provides a cross-chip platform instruction conversion method, which comprises the following steps: collecting instruction set information of a source chip platform and a target chip platform, establishing an instruction feature analysis model, and calculating a semantic similarity matrix between instructions in a feature vector space by adopting a kernel function; training a multilayer graph attention neural network based on the semantic similarity matrix, mapping feature vectors of a source platform instruction and a target platform instruction to a shared embedding space, and performing iterative optimization on a mapping relation graph by applying a reinforcement learning method to obtain an instruction equivalent conversion rule; the instruction equivalent conversion rule is loaded in the instruction conversion engine, the input source platform instruction is decoded and analyzed, and a converted target platform instruction sequence is output to an instruction execution unit of a target chip platform; the resource overhead in the conversion process can be optimized, and the overall efficiency of the system is improved on the basis of ensuring the conversion correctness.

The invention relates to the field of photovoltaic technology, and discloses a photovoltaic power generation-oriented big data analysis method, which comprises the steps of obtaining performance monitoring data and environment monitoring data of a photovoltaic panel; constructing a local model at each local node by adopting a distributed federated learning method, and constructing a federated model at the central server; performing data expansion on the performance monitoring data and the environment monitoring data of the photovoltaic panel by using the local model and adopting a quantum feature fusion-based generative adversarial network, performing feature extraction on the expanded data, then classifying extracted feature maps, and uploading model parameters of the local model to a central server; performing parameter aggregation and updating on the model parameters uploaded by each local model by using the federal model; and performing analysis processing on the performance monitoring data and the environment monitoring data of the photovoltaic panel to be analyzed by using the trained federal model to obtain a photovoltaic power generation category. According to the method, distributed model training and data mining of the multi-node joint model are realized, and the data security is effectively ensured.

The invention belongs to the technical field of federated learning, and particularly relates to a self-adaptive bilateral distillation personalized federated learning method based on a diffusion model. According to the method, a guidance mechanism is designed, so that mutual distillation is carried out between a global model and a local model, efficient transmission of knowledge is realized, and the adaptability of a personalized model to specific data distribution of a client is enhanced. Meanwhile, a conditional diffusion model is introduced to generate high-quality pseudo data, and the aggregated global model is finely adjusted by using the pseudo data. The process not only effectively makes up global information possibly lost in the local-global mutual distillation process, but also further optimizes the performance of the global model. By combining the mutual distillation and conditional diffusion fine tuning technology, the data privacy is protected, meanwhile, the balance between the personalized performance and the global generalization ability is achieved, and the method is suitable for a multi-client cooperation scene in a non-independent identically-distributed non-IID data environment.

The invention relates to the technical field of federated learning, and discloses a federated learning method and system based on multiple agents and knowledge distillation, and a medium, and the method comprises the steps: S1, training a local model; s2, knowledge distillation based on decoupling; s3, decentralized knowledge sharing based on a block chain: packaging the standardized distillation knowledge fragments extracted in S2 and metadata thereof into block chain transactions, submitting the block chain transactions to a block chain network, verifying the legality of the transactions, and writing the transactions into a block chain account book to realize decentralized distribution; s4, performing multi-agent collaborative knowledge management based on a large language model, and updating a student model; and S5, repeatedly executing the steps S1 to S4 until a training termination condition is met. According to the method, personalized selection, adaptive filtering and efficient sharing of knowledge in the federated learning process are realized, the client drift phenomenon caused by data non-independent identical distribution characteristics is effectively relieved, the convergence speed, the overall performance and the personalized level of the model in a heterogeneous data environment are remarkably improved, and the communication overhead between clients is optimized.