279 results about "Model aggregation" patented technology

The invention discloses a multi-modal data real-time identification and cooperative processing system based on edge computing and federated learning. The multi-modal data real-time identification and cooperative processing system comprises a cloud center coordination node, a plurality of edge computing nodes, a cross-modal encryption engine, a federated learning controller and a model updating verification module. The cloud center coordination node executes federated learning model aggregation and dynamic task allocation, and generates a cross-modal encryption strategy; and the edge computing node is configured with a multi-modal data acquisition module, a local model training unit and a co-processing gateway to realize multi-modal data acquisition and local processing. The system encrypts vision, acoustics and text data by using differentiated algorithms such as spatial confusion, frequency domain permutation and homomorphic encryption; the federated learning controller carries out multi-modal feature fusion, hierarchical encryption and dynamic networking at the edge node; and the model updating verification module performs aggregation updating after ensuring parameter consistency by using secure multi-party calculation. According to the method, real-time processing and privacy protection of multi-modal data are realized, and the data co-processing efficiency is improved.

The invention relates to the technical field of agricultural information management, and particularly discloses an agricultural information management system and method based on a big data platform, and the method comprises the steps: firstly deploying a multi-source data collection module at an edge calculation node, and obtaining and standardizing the soil moisture content, meteorological environment and equipment operation data in real time; secondly, constructing a local dynamic irrigation strategy model, and realizing multi-objective optimization through a reinforcement learning algorithm; establishing a federated learning framework at the cloud, dynamically distributing node weights by adopting an attention mechanism, and realizing model aggregation of privacy protection in combination with secure multi-party computing; an optimal irrigation instruction is generated through a multi-source data fusion engine, and a three-level response exception handling mechanism is established; and finally, a closed-loop feedback system containing short-term incremental learning and long-term architecture optimization is formed. The corresponding management system comprises six functional modules, namely a data acquisition module, a local modeling module, a federated learning module, a real-time decision-making module, an abnormal monitoring module and a closed-loop optimization module.

The invention discloses a privacy protection system based on federated learning, and relates to the technical field of privacy protection. The system comprises a distributed participating node cluster, wherein each participating node is configured with a local model training unit and a privacy protection module; the coordination server is connected with each participating node through a secure communication layer and comprises a model aggregation module and a dynamic trust evaluation module; the global model distribution channel is used for broadcasting the encrypted global model parameters to participating nodes; and the privacy protection module is integrated in a local participating node and comprises a homomorphic encryption engine and a local differential privacy injector. According to the method, privacy protection strength improvement, model utility optimization, system efficiency breakthrough and security boundary expansion are synchronously achieved under a federated learning framework, and an industrial-grade solution is provided for cross-domain data collaborative learning.

The invention relates to the technical field of distributed learning, in particular to a large model pre-training system based on distributed parallel processing. In the system, a data distribution layer collects a node resource state through a fragmentation module and generates a dynamic scheduling strategy; a computing resource layer configuration model initialization module and a strategy switching module support flexible switching of multiple modes such as tensor parallelism, data parallelism and assembly line parallelism; the network communication management layer is combined with topology perception and gradient compression technologies, so that the communication efficiency is improved; and the model aggregation layer realizes global parameter updating and training tuning under privacy protection through a security aggregation and optimization control mechanism. All layers of the system operate cooperatively, the calculation efficiency, the communication performance and the data security of large model pre-training can be effectively improved, and the method is suitable for model development and deployment in a large-scale heterogeneous calculation environment.

The invention discloses a multi-source threat intelligence privacy fusion processing method and system, and relates to the technical field of network security threat intelligence analysis and processing, and the method comprises the steps: collecting threat intelligence, and carrying out the cleaning, standardization and desensitization; establishing a threat index semantic model and aligning cross-modal features; the central coordination module completes model aggregation after organization node local training; and based on the aggregation model fusion intelligence, semantic association and attack link reconstruction are established, and a result is generated and fed back for optimization. The technical problems that in cross-organization fusion processing of multi-source heterogeneous threat intelligence, data formats are not uniform, and privacy protection and intelligence collaborative analysis contradictions exist, so that threat detection is not comprehensive and inaccurate, and accurate evaluation and effective management and control requirements are difficult to meet are solved. The technical effects that the multi-source heterogeneous threat intelligence is effectively fused on the premise of privacy protection, the comprehensiveness and accuracy of threat detection are improved, and the requirements for accurate assessment and effective management and control of threats in a cross-organization scene are met are achieved.

The invention belongs to the technical field of federated learning dual optimization, and discloses a federated learning dual optimization method and system based on cluster knowledge distillation and adaptive local differential privacy, and the method comprises the steps: carrying out the data statistical feature extraction of a client; clustering the clients; local training of the client is carried out; applying an adaptive local differential privacy mechanism (ALDP); carrying out model aggregation FedAvg in the cluster; distilling structural knowledge; updating the global model; and evaluating model performance and privacy protection capability. The invention provides a federated learning optimization method which combines client clustering, structural knowledge distillation and a self-adaptive local differential privacy mechanism aiming at the problems of client data heterogeneity, unstable model distillation and difficulty in considering privacy protection and performance in the existing federated learning method. According to the method, client data statistical feature clustering and structural relationship knowledge distillation are combined, and a disturbance mechanism with a dynamic adjustment capability is introduced, so that efficient protection of privacy information is realized while the model performance is improved.

The invention belongs to the technical field of block chains and federated learning, and particularly discloses a dynamic incentive federated learning method based on a trusted execution environment and a block chain. The method comprises the following steps: firstly, constructing a core computing security area by utilizing TEE, and executing key links such as model aggregation, client screening and contribution measurement in a hardware isolated trusted environment; and then, a block chain and an intelligent contract technology are adopted as a decentralized trust root to realize effective management of identities of participants, tamper-proof records of key certificates and automatic distribution of economic incentives. Secondly, establishing a set of dynamic excitation and reputation mechanism executed in the TEE, and performing credible quantification and automatic reward on the contribution of the client based on multi-dimensional indexes such as model quality, historical reputation, asset pledge, participation stability and the like; and finally, end-to-end data encryption is realized through a session key mechanism in the TEE, so that the data privacy of the client is effectively protected.

The invention discloses a non-independent identically distributed data asynchronous federal learning method based on an improved aggregation algorithm. The method comprises the steps that a server initializes a global model and issues the global model to all clients; and the client performs local training on the received global model by using local data, and uploads the model and model parameters to the server after training is completed. Then, the server adjusts a model lag degree based on a client data volume proportion, calculates model difference consistency, client historical contribution stability, old degree penalty of the client model and cosine similarity of the client model and the global model based on parameters of the client model and the current global model, and generates an asynchronous federal aggregation factor accordingly; and updating the global model parameters to generate a new global model. And finally, testing the global model by the server, and judging whether the learning process is stopped or not. According to the method, fair and effective model aggregation can be realized, and the model convergence stability and the final model detection precision are improved.

The invention discloses an MEC federated learning model aggregation optimization method based on non-independent identically distributed data, and relates to the technical field of edge computing, and the method comprises the following steps: a distributed mobile terminal collects local data, records performance parameters, carries out power law distribution classification after preprocessing, sets a dynamic threshold value, and optimizes local training by using a dynamic sampling algorithm; the asynchronous transmission global model is fused with weight optimization updating and timestamp monitoring technologies to provide heterogeneous network state feedback, and efficient federated learning model aggregation is achieved. According to the method, the efficiency and precision of MEC federated learning under non-independent identically distributed data are remarkably improved, resource allocation is effectively balanced through dynamic threshold adjustment and sampling optimization, the communication overhead is reduced, the model generalization ability is enhanced through asynchronous model updating and weight fusion strategies, real-time feedback of the network state is ensured through the timestamp monitoring technology, and the method has the advantages of being high in reliability and high in reliability. And an efficient and reliable solution is provided for federated learning in the field of edge computing.

The invention discloses a violation snapshot method based on image recognition, which relates to the related technical field of traffic video monitoring and comprises the steps of environment perception, scene analysis, scene feature library establishment, multi-modal data acquisition, server model aggregation, model issuing and fine adjustment and violation behavior recognition. The invention further discloses a violation snapshot system based on image recognition. The violation snapshot system comprises an environment sensing module, a data acquisition module, a data processing center, a violation behavior recognition module and a snapshot and recording module. Different from a fixed snapshot strategy of a traditional method, the system can dynamically adjust the snapshot strategy according to real-time understanding of a traffic scene, the system can automatically improve the snapshot frame rate when detecting a high-risk scene in which a traffic accident is about to occur, and the snapshot frame rate can be automatically increased in a road section in which the traffic flow is small and the scene is simple. Snapshot resource consumption can be properly reduced; therefore, a complex and changeable traffic environment can be better dealt with, and the snapshot effectiveness and the resource utilization efficiency are improved.

The invention provides a personalized federal learning method suitable for an edge network, which is characterized in that a collaborative training network topology between clients is constructed based on a graph, and local models of the clients and aggregation relationships thereof are described as points and edges of the graph. Secondly, a personalized model aggregation mode based on group dynamics is established, a personalized aggregation matrix is obtained according to the adjacency matrix and the aggregation weight matrix, and finally, the personalized aggregation matrix is used for weighting personalized model parameters uploaded by all clients to obtain a personalized aggregation model; the adjacency matrix is used for controlling the personalized model of the client to move towards the personalized models of other clients aggregated by the client in the state space; the aggregation weight matrix is used for controlling the moving degree of the personalized model; therefore, the personalized model aggregation is rapidly realized in the edge server, and the personalized model automatically completes clustering in the convergence movement in the state space along with the continuous proceeding of training and aggregation, so that the collaborative training of the personalized model between clients is realized.

The invention discloses an underwater edge privacy protection task unloading method based on differential federated learning. Firstly, sensor nodes are arranged in a target water area, a network architecture is constructed, a state space, an action space and a reward function are defined respectively, and the sensor nodes execute local model training after sensing environment data. Then, each sensor node uploads local model parameters to a sea surface buoy for model aggregation, and differential disturbance is introduced in the uploading process to protect privacy; and after model aggregation is completed, the sea surface buoy issues a global model to each sensor node, and the node generates a task unloading strategy according to the global model. And finally, the sensor node encrypts the task data through homomorphic encryption, and safely unloads the encrypted calculation task to the corresponding sea surface buoy or low orbit satellite for execution. According to the method, privacy leakage in an underwater task unloading process is effectively reduced, and the security of data transmission in an underwater network is improved.

The invention discloses a heterogeneous data financial intelligent model collaborative construction device and method and related equipment, and relates to the technical field of model processing, and an institution grouping device of a public control unit clusters and groups financial institutions participating in model construction by using clustering, data distribution speculation and other related technologies. The mechanisms of the same type in the grouping result have similar data distribution characteristics, and the mechanisms in the same group have data with complementary distribution characteristics, that is, missing data knowledge is mutually compensated, and finally good training data with the same distribution are formed on the whole. The grouping result is input into a first model scheduler to schedule mechanism selection of local training of the federal model, the model is guided to complete training and learn complete data knowledge in different grouped mechanisms, and a financial intelligent model meeting result expectation is output through multiple rounds of local model training, correct model scheduling and model aggregation. The method solves the influence of heterogeneous data, and constructs a financial intelligent model with high accuracy.

The present invention belongs to the technical field of communication networks. Disclosed is an adaptive split federated learning method for a distributed AI training service in a 6G computing power network. The method comprises: establishing a 6G computing power network model, and constructing an adaptive split federated learning model for a distributed AI training service; analyzing the delays of each intelligent terminal in a model training stage and a model aggregation stage; constructing a total service delay minimization optimization problem; and using a shortest-path search algorithm to perform joint optimization on model segmentation modes, cooperative node selection modes and multi-domain resource scheduling modes in the model training stage and the model aggregation stage. In the present invention, by means of joint optimization of a model segmentation mode, node selection and multi-dimensional resource allocation in a multi-base-station scenario, the problem of network congestion caused by a single-base-station learning framework processing the aggregation of a large number of intelligent terminal models is alleviated, and the present invention adapts to the heterogeneous computing power of intelligent terminals and the differentiated channel quality in an actual network, thereby improving the efficiency and generalization capability of model training.

The invention relates to the technical field of network security, in particular to an encrypted network abnormal traffic detection method, system and device and a medium. According to the invention, by combining edge calculation and federated learning, the efficiency and precision of encrypted network traffic anomaly detection are improved. The edge device independently trains a local model and uploads the local model to the central server, and the central server aggregates model parameters through federal learning to generate a global detection model. The method can be closer to a data source for real-time analysis, and delay and bandwidth consumption caused by data transmission are reduced. Meanwhile, by means of local training and model aggregation, concentrated storage and transmission of sensitive data are avoided, and data privacy is effectively guaranteed. The global model is optimized for multiple rounds, abnormal behaviors in encrypted traffic can be accurately identified, the network security protection capability is improved, and an efficient and accurate network security solution with privacy protection is provided.

The invention provides a data space construction method and system based on dynamic ontology modeling and privacy calculation, and belongs to the technical field of data processing. The method comprises the following steps: respectively constructing a structured semantic network and a vector space of multi-modal data based on the multi-modal data, aligning nodes of the semantic network with the vector space by using an attention mechanism to generate a joint knowledge representation, compressing the joint knowledge representation into a low-dimensional knowledge representation, and constructing a low-dimensional index, modeling by adopting a federated learning improved algorithm combined with differential privacy to obtain an original model; distributing the initial model and the initial model parameters to each participant for federated learning training, and performing model aggregation by using the trained encrypted model parameters to obtain a global model; and finally, distributing model parameters of the global model to each participant for model deployment to form a three-level collaborative data space. According to the invention, the risk of privacy disclosure is reduced, and the storage overhead of the data space is reduced.

The invention discloses a personalized federal learning method based on homomorphic encryption, which comprises the following steps of: firstly, introducing constraint between a global model and a personalized model through a regularization method, adopting a separated updating strategy, performing multi-round updating on the personalized model by a client by utilizing local data, and performing multi-round updating on the personalized model by utilizing local data; and the personalized model parameters are uploaded to a server. Meanwhile, an optimization strategy is provided, namely, the strategy of dynamically adjusting the aggregation weight by utilizing the precision and frequency of each client on the public verification set is used, so that the global aggregation weight is dynamically adjusted, and the global model is updated more fairly and accurately. Besides, a model pool is introduced to realize preferential updating of a local model of the client, dynamic weight adjustment and model pool selection are both lightweight operations, a fully homomorphic encryption technology is adopted to realize ciphertext model aggregation, original precision / frequency data and model parameters of the client are ensured to be encrypted in the whole process in transmission and calculation, and gradient inversion attacks can be effectively defended.

The invention discloses a federated learning client scheduling method, device and system with contribution perception, and the method comprises the steps: quantizing the marginal contribution of a client into an information entropy change amount caused after a model parameter is updated and added into a client alliance based on an information entropy theory and a Shapley Value contribution evaluation method; according to the client selection method based on the dobby machine theory, under the constraint of availability and fairness, the utilization of known high-contribution clients and the exploration of unknown clients are balanced. The system comprises a server unit responsible for contribution evaluation, client selection and model aggregation; and the client unit is responsible for local model training. The method, the device and the system can be used for federal learning scenes with heterogeneous clients, and performance of a final global model is improved while participation fairness of the clients is guaranteed.

The invention provides a small signal frequency domain impedance automatic construction method compatible with a network tracking type system and a network constructing type system. For a complex system connected with a network-following type or network-constructing type converter, a uniform state-space equation is used for representing the characteristics of the converter, and an impedance calculation framework based on mapping between a time-frequency domain and a continuous discrete domain is established. The implementation process comprises the following steps: firstly, deducing a state-space equation of a single element, performing linear approximation and time domain discretization at a stable equilibrium point to form an equivalent Norton model, then dividing the whole network into two subsystems, hiding internal electrical parameters of the subsystems through model aggregation, and finally obtaining an equivalent Norton model; and automatic conversion from a small-signal time domain state space model of a single element to a system frequency domain model is realized. In the method, the system impedance model can be automatically constructed only according to branch and node information, the operation is simple, the expansibility is high, and the method is suitable for a large-scale power grid with a complex structure.

The invention discloses an air-space asynchronous federated edge learning-based general computing resource management method, which comprises the following steps of: 1, establishing an air-space asynchronous federated edge learning system model assisted by a low-orbit satellite, and designing a layered federated model aggregation mechanism; 2, describing a communication-sensing-computing resource management problem with optimal global model convergence, and considering terminal equipment energy consumption and training time delay constraints; step 3, decoupling the problem into three sub-problems by adopting alternative optimization, namely satellite receiving denoising factor optimization, terminal transmitting power control and sensing data batch size design; and step 4, solving the three sub-problems based on mathematical optimization methods such as quadratic constraint quadratic programming and fractional programming, and obtaining an optimization result of general inductance computing resource management through iteration. According to the method, an aggregation mechanism of asynchronous federated learning is reasonably designed to balance contributions of different terminals to model convergence, and meanwhile, an efficient problem decoupling and optimization method is provided to realize joint allocation of multi-domain resources of the general inductance calculation, so that the federated learning performance is improved.

The invention provides a construction method of a network intrusion model based on meta learning, comprising the following steps: a global server constructs a plurality of client nodes based on a federated learning framework, and constructs a node detection model in each client node; a client node collects local multivariate heterogeneous data at a fixed time interval, generates a simulated attack sample by using a GAN network, and then forms training data by using the simulated attack sample and a normal sample; performing iterative training on the node detection model by using the training data; performing meta-optimization on the trained node detection model by using an irrelevant meta-algorithm; and the global server dynamically allocates aggregation weights for each client node, and performs model aggregation in a weighted average manner to generate a global detection model. According to the method, the problems that the detection capability of a detection model on minority class attacks is insufficient and the detection model is difficult to quickly adapt to newly occurring novel network attacks due to the fact that the classes of model training samples are unbalanced in the prior art are solved.

The invention discloses a robust efficient physical layer key generation method based on edge federated learning. The method comprises the steps that an edge server prepares a channel state information data set; the edge server divides the local beta-VAE model into a shared part and a private part, and cooperates with the base station to perform personalized federated learning to complete training of the local beta-VAE model; the edge server stores an encoder part of the trained personalized local beta-VAE model; the communication party carries out channel estimation to obtain channel state information; the communication party and the base station perform feature extraction and quantification on the channel state information by using a local encoder; and the communication party and the base station carry out information negotiation, and the bit mismatching rate is recorded. And if the bit mismatching rate is greater than a threshold value, carrying out privacy protection model aggregation and key generation model switching, otherwise, carrying out privacy amplification on key bits, and obtaining a consistent final key of the two parties. According to the invention, through a lightweight pre-training and fine tuning mode, the key generation cost is greatly reduced.

The invention relates to a multi-party trusted cooperation method and system based on a DAG block chain and federal learning. According to the method, a task publisher publishes a global initial model and task metadata in a DAG block chain, and starts a collaborative training task; a task training party dynamically selects Tip nodes from a DAG block chain cooperation module based on freshness, accessibility and data distribution similarity, aggregates models according to a set Tip selection rule-based model aggregation strategy to obtain a local training model, and trains the local training model; after the model is aggregated, a model aggregation path is uploaded to a DAG block chain cooperation module to generate a corresponding Hash commitment; after model training is completed, model parameters and model updating metadata are encrypted and then uploaded to a DAG block chain cooperation module; after the DAG block chain cooperation module confirms that no tampering exists, Tip node updating is executed by utilizing the updating data; and the task issuer issues a training termination command to terminate training according to a preset global training termination condition.

The invention discloses a federal learning model leakage traceability method based on model structure confusion, and the method comprises an initialization step: S1, a server copies an initial model for subsequent structure comparison, and generates a unique binary user identity (UID) for each client; a UID embedding step S2, before each round of training is started, independently executing structure confusion for each client model by the server, embedding a client UID into a model structure, and then issuing the model to the client; a model structure recovery step S3, when one round of training is finished, the server executes structure recovery on each client model, and then executes model aggregation; and S4, when a model ownership owner doubts that a model with an unknown source comes from leakage in a training process, the structure of the model is detected, and a suspicious UID is extracted through structure comparison with an initial model so as to find a leakage person. The method has the characteristics of no negative influence on the performance of the original model, low embedding time overhead, high robustness and the like.

The invention discloses a privacy protection federal basic model continuous learning method for a new energy main body power system. Comprising an initialization stage, a stage of communication reliability evaluation and dynamic selection of a new energy main client, a privacy protection processing stage and a model aggregation updating stage, intelligent node screening is realized through communication reliability scoring and data stability analysis, and the problem of unstable communication between virtual power plants is effectively overcome. Label distribution alignment optimization and differential privacy protection are innovatively combined, and privacy security of new energy main body client communication is ensured through adaptive noise injection and gradient level privacy budget distribution.

The embodiment of the invention provides a data generation method, a model optimization method and related equipment, the data generation method comprises a data generation method based on illusion enhancement, and the method generates paragraph description including diversified illusion by enhancing the illusion of paragraph-level description of a video. The model is optimized based on a paragraph description including diverse halluses to reduce the number of halluses in a paragraph-level description of the video generated by the model. The data generation method comprises a hallusion optimization-based data generation method, and according to the method, an initial video level description is optimized to reduce video level hallusion so as to obtain an optimized video level description. The model is optimized based on the optimized video level description to reduce hallucination accumulation formed in the model aggregation paragraph level description process. According to the embodiment of the invention, the number of illusions in the video description text output by the model can be reduced based on the generated data optimization model, and the accuracy of the video description text output by the model is improved.

The invention provides a universal model heterogeneous federated learning privacy protection method, which comprises the following steps that: a cloud server randomly selects an online client, and obtains a model generation parameter union set of the client through a privacy protection union set protocol; generating heterogeneous models with different sizes and architectures according to the union set, and distributing the models to edge nodes for storage; the client downloads the local model from the corresponding edge node, and disturbs and encrypts the trained model parameters; the edge node receives the encryption model parameters uploaded by the client, and performs secure aggregation through a threshold vector aggregation protocol to obtain an aggregation model meeting the differential privacy requirement; and the cloud server receives the aggregation models from all the edge nodes, and globally updates the aggregation models by adopting a heterogeneous model aggregation method to obtain a new global model. Through an innovative privacy protection protocol and system architecture, the privacy protection problem in a model heterogeneous federated learning scene is effectively solved, and the practicability and security of federated learning are improved.

The invention provides a dynamic threshold adjustment method based on a self-adaptive alarm rule engine, and belongs to the field of intelligent power grids, and the method comprises the steps: collecting equipment operation data in real time by an edge node, and building a personalized threshold model; the central server initiates a model aggregation request according to a preset period, each edge node uploads a personalized threshold model parameter increment, calculates an aggregated global model parameter, adds noise to the aggregated global model parameter to obtain the global model parameter, and establishes a global model; inputting the standardized feature vector into a global model to obtain a prediction probability, and calculating a basic threshold according to the prediction probability; if the prediction probability exceeds a basic threshold value, generating a weight vector for the feature vector after standardization processing to obtain a weighted feature; calculating an anomaly degree, calculating a smoothness anomaly degree, calculating an adjustment factor, and adjusting the basic threshold value to obtain a dynamic threshold value; the invention further provides a dynamic threshold adjusting system. The problem that a traditional fixed threshold value cannot cope with equipment parameter volatility enhancement is solved.

The invention relates to the technical field of project management informatization, and discloses a project supervision cost consultation integrated management system, which comprises a dynamic risk modeling module, a risk probability distribution and gradient matrix generated by fusing multi-source data through a dynamic Bayesian network, and a federal collaborative learning module, the system comprises a model aggregation module, a multi-target optimization module, a block chain auditing module, a closed-loop feedback module, a block chain auditing module, a block chain auditing module, a block chain auditing module and a block chain auditing module, wherein the model aggregation under multi-party privacy protection is realized based on a timestamp-driven algorithm and gradient confusion encryption; the multi-target optimization module is used for performing cost, construction period, quality and risk tolerance four-dimensional optimization by using an improved NSGA-III algorithm; and dynamically correcting system parameters according to an audit result to form a closed loop. The reliability and the intelligent level of the consultation management system are improved by fusing the multi-source data quantification risk through the dynamic Bayesian network, combining federal collaborative learning with gradient encryption, risk gradient optimization decision and closed-loop mechanism dynamic correction.

The invention discloses a federated learning dynamic aggregation method, system and device, a medium and a product. According to the method, a twinborn layer is constructed on a central server, model aggregation deduction is performed in advance in a virtual environment by establishing a digital twinborn model of a client, and then an optimal aggregation strategy is screened out; in each round of iteration, the client maps self state information and local model parameters to a twinborn layer, the twinborn layer clusters the client by using a K-means dynamic clustering algorithm, the aggregation effect of different cluster combinations is evaluated, and an optimal aggregation strategy is selected for pre-aggregation; therefore, the server globally aggregates the client model according to the strategy provided by the twinborn layer. According to the embodiment of the invention, the model convergence speed and precision of federal learning can be remarkably improved, the communication delay and energy consumption are reduced, the method effectively adapts to the isomerism of clients, and an efficient and flexible solution is provided for distributed machine learning.