619 results about "Counter propagation" patented technology

The invention discloses a base station facility abnormity intelligent monitoring method and system, and the method comprises the steps: employing a multi-scale wavelet fusion pulse neural network to construct a dynamic signal perception topology according to the real-time data of a base station physical layer, and generating a space-time aligned base station full-dimension feature tensor; inputting the full-dimensional feature tensor of the base station into a fault mode confrontation distillation module, reconstructing a normal working condition manifold of the base station based on a physical constraint variational auto-encoder, and outputting an abnormal feature vector with a fault fingerprint identifier; fault propagation graph modeling is carried out on the abnormal feature vectors, and a base station fault root cause topological graph is generated in combination with back propagation credibility verification; and inputting the base station fault root cause topological graph into a toughness self-healing strategy generator, and finally outputting a base station facility self-healing strategy set meeting real-time constraint. By utilizing the embodiment of the invention, the accuracy and the real-time performance of abnormity monitoring can be improved, and the operation reliability and the communication service quality of the base station are improved.

The invention discloses a quantitative training method and system for a deep neural network, and the method comprises the steps: obtaining an original neural network model and a verification data set, and generating a quantitative priority through hierarchical sensitivity evaluation and topology analysis; on the basis of the layer sensitivity matrix, differentiated quantization parameters are configured for each layer, and quantization constraints are established; constructing an error compensation mechanism, and generating an error compensation strategy; executing dual-scale adaptive quantization training, and respectively adopting an independently optimized quantization strategy for forward propagation and back propagation; dynamically adjusting quantization parameters according to the training state and the resource constraint; and evaluating model performance and resource efficiency. According to the method, through multi-dimensional sensitivity evaluation, a dynamic quantification strategy and system error compensation, the precision and efficiency of quantification training are improved, and meanwhile it is guaranteed that deployment resource constraints are met.

The invention discloses a user behavior prediction system and method based on multi-modal data fusion, and particularly relates to the field of user behavior prediction, and the system comprises a multi-modal data collection module, a preprocessing and feature extraction module, a cross-modal fusion module, a user behavior prediction module, and a model optimization and feedback module. According to the system, multi-dimensional original data such as visual sense, auditory sense, text, physiological signals and environment context of a user are acquired in real time through a multi-modal data acquisition module; then, deep networks such as ResNet, VGGish and BERT are adopted to extract high-dimensional feature vectors of all modals, and contribution weights of features of different modals are dynamically learned through an attention mechanism; and finally, based on a time sequence model of Transform and LSTM, analyzing fusion features, and outputting probability distribution of future behavior intentions. And parameter joint optimization and continuous learning are realized through a multi-objective loss function and end-to-end back propagation.

The invention provides a deep learning large model training method and system for heterogeneous equipment, belongs to the technical field of model training, and aims to solve the problem that a heterogeneous GPU cluster cannot be effectively utilized when a traditional scheme is used for training a deep learning large model. Different network layers of a deep learning large model to be trained are divided into a plurality of stages, forward propagation and back propagation calculation of all network layers in each stage is executed by independent virtual equipment, and meanwhile, utilization of GPU resources of different structures is coordinated in combination with a proposed hybrid parallel training strategy, so that efficient model training is realized.

The invention relates to a resource-limited large model heterogeneous training method, computer equipment and a storage medium, and the method comprises the steps: determining a first activation amount according to a dependency relationship between calculated amounts corresponding to the activation amounts and / or the calculated amount and the storage amount of each activation amount in the activation amounts generated when an image processor carries out model forward propagation, the first activation amount is asynchronously transmitted to the central processing unit; loading a first activation amount to the image processor from the central processing unit in a model back propagation process; obtaining the gradient of the model parameter calculated by the image processor based on the first activation amount, and asynchronously transmitting the gradient to the central processing unit; and determining an optimizer obtained based on gradient updating in the central processing unit, obtaining model parameters obtained by adjustment of the updated optimizer, and asynchronously transmitting the model parameters to the image processor. By adopting the method, the problems that a large model with limited video memory resources is difficult to train and the computing efficiency of a video card is low can be solved.

The invention discloses an injection molding process fault diagnosis model training method and system based on a large language model and a fault diagnosis method. The model training method comprises the following steps: collecting and cleaning process parameters under the fault working condition of the injection molding machine, converting the process parameters into a natural language text, combining the natural language text with a fault label to construct a textualized data set, and dividing the textualized data set into a training set and a verification set according to a proportion; and in combination with the text data dimension and the fault category number, loading the pre-trained large language model and configuring a diagnosis model structure in a quantitative mode. And inputting the training set into a model to extract semantic features, processing the semantic features by a feature conversion module to generate a high-order feature vector, and inputting a classification head to output a fault category probability. And back propagation is carried out by using a loss function, and model parameters are efficiently and finely tuned in combination with low-rank adaptation and a layered freezing strategy. And repeating training until the performance reaches the standard, and outputting a final diagnosis model. The method is efficient in training, and can effectively reduce the maintenance and use cost of the model.

The invention discloses a segmentation federal learning model training method based on a heterogeneous system. The system comprises a plurality of clients, a central server and an edge server. The global model segments the client local model and the server local model based on each client device condition and deploys to corresponding clients and central servers, respectively. And in each round of training, the client performs parallel training, forwards propagates local data, outputs crushed data, transmits the crushed data to the server local model of the central server, continuously forwards propagates to obtain a loss value, and backwards propagates a gradient to update parameters of the server local model and the client local model. And each client transmits the updated model to the edge server, and the edge server and the central server complete parameter exchange of a public layer and then perform model gathering to generate a global client model and a global server model. The global client model distributes client local models to the clients according to each client break point. The method can adapt to equipment conditions of heterogeneous equipment, and the model training efficiency is improved.

The embodiment of the invention provides an assembly line optimization method and device for multi-modal large model training, and relates to the technical field of artificial intelligence. According to the method, each model slice of a to-be-trained multi-modal large model is deployed to different training devices, each training batch is divided into a plurality of micro-batches, for each training batch, training sequences corresponding to different training devices are determined according to a parallel scheduling strategy, and the training sequences are used for training the multi-modal large model. The training sequence comprises a forward propagation position, an input back propagation position and a weight back propagation position of each micro-batch, and finally, on each training device, a training process of a corresponding training batch is executed based on the training sequence until training is completed. A back propagation process is divided into back propagation of an input matrix and back propagation of a weight matrix, three calculation stages are jointly formed by the back propagation process and forward propagation, peak shifting calculation can be carried out, bubble time can be effectively filled, idle duration can be reduced, the bubble proportion of an assembly line can be remarkably reduced, and training throughput can be greatly improved.

The invention discloses a VSP sound wave full-waveform inversion method of a double-branch physical driving recurrent neural network, which is applied to the field of seismic data processing and aims to solve the problems of low interpretability, low calculation cost and the like due to the adoption of a complete data driving mode in the existing seismic velocity inversion technology. As the wave equation describes the change of the wave field in time and space, a time stepping method is adopted during numerical simulation, namely, the state of the wave field at the next moment is calculated according to the state at the previous moment. Taking a wave field state at a previous moment as a hidden layer of the RNN, performing finite difference solution on an acoustic wave equation, taking a speed parameter in the equation as a trainable parameter in a physically-driven RNN forward modeling network, and taking a shot gather record obtained by outputting through the physically-driven RNN forward modeling network each time as a predicted value; taking shot gather records obtained through physical driving RNN forward modeling output by setting real speed parameters as observation values; the process of solving the loss between the predicted value and the observed value to carry out back propagation to correct the speed parameter is called as a speed inversion process.

According to the motor anomaly detection model training method and the motor anomaly detection method provided by the invention, a plurality of audio samples and category labels thereof during motor operation are acquired, a plurality of disturbance audios are generated through speed disturbance for each audio sample, the disturbance audios are input into a frequency domain feature extraction sub-model and a time domain feature extraction sub-model, and the frequency domain feature extraction sub-model and the time domain feature extraction sub-model are extracted. Performing linear transformation and weighted summation on the enhanced wavelet time-frequency spectrum and the enhanced time-domain features through a full connection layer to generate fusion enhanced features, performing feature transformation on the fusion enhanced features through a deep neural network, inputting the fusion enhanced features into a classifier to obtain a classification probability, and calculating triple loss according to a category label and the classification probability; and updating parameters of the frequency domain feature extraction sub-model, the time domain feature extraction sub-model, the full connection layer, the deep neural network and the classifier through loss back propagation and a stochastic gradient descent algorithm to obtain a trained motor anomaly detection model. Therefore, the accuracy of motor state recognition of the model in a high-noise environment is improved.

The invention relates to a visual attention mobility anti-attack method based on self-adaptive token fine tuning, which comprises the following steps of: constructing a feature important matrix by utilizing a proxy model middle layer, and generating a semantic-guided sparse mask; performing token-level point multiplication on the sparse mask and the initialized disturbance, and performing linear superposition on the sparse mask and the initialized disturbance and an original image to serve as initial input data; inputting the input data into the agent model for iterative training; in each round of iterative training, sparse masks are continuously updated, the number of discarded tokens is gradually increased, and gradient variance between layers in an agent module is reduced through gradient back propagation by using a gradient penalty factor and a balance factor. Meanwhile, self-adaptive truncation factor sets are designed for different modules of the agent model to weaken the attention mechanism of the model, and through T times of iterative training, a target loss function is maximized to obtain optimal mobility disturbance. Experiments prove that the method has better attack effect and mobility on the attack of the target model.

The invention discloses a classification model training method based on big data distributed computing, and relates to the technical field of big data processing and machine learning, and the method comprises the steps: S1, obtaining communication delay data between distributed computing nodes, and analyzing delay characteristics to generate regulation and control parameters, the method comprises the steps of S1, dynamically determining the batch size of each training batch based on regulation and control parameters, and ensuring the optimization of the synchronization efficiency, S3, distributing the adjusted batch size to each node, and executing the forward and reverse propagation calculation process of the model, and S4, collecting the calculation result of each node to perform parameter aggregation updating, and completing the iterative training of the classification model. According to the classification model training method based on big data distributed computing, the batch size is regulated and controlled according to the communication delay between the nodes so as to solve the problem that the distributed synchronization efficiency is low.

The invention provides a prediction method for the remaining service life of a rolling bearing based on transfer learning, and belongs to the technical field of artificial intelligence and mechanical engineering. Rolling bearing vibration signals are obtained, and a data set is constructed and divided into a source domain and a target domain; constructing a prediction model of the remaining service life of the rolling bearing; the model comprises the following steps: obtaining low-dimensional features and model weights by using a coding layer; the coding layer comprises a multi-head self-attention sub-layer used for obtaining a relationship between features and a model weight; the feedforward mechanism is used for obtaining low-dimensional mapping; predicting the residual life of the bearing by using the feature representation output by the last coding layer through the full connection layer; training the prediction model of the remaining service life of the rolling bearing: calculating the difference between a source domain and a target domain by using the data set, and constructing a loss item; weight parameters are added to the loss item, the weight parameters and the root-mean-square error loss item are added for back propagation, and the model weight is updated. And the generalization ability of predicting the bearing life by the model is improved.

The invention relates to a robot decision control method based on gradient rarefaction and a robot. The method comprises the following steps: acquiring multi-modal sensor data of a robot; based on a preset sparsification strategy, generating a dynamic mask corresponding to the gradient matrix of the multi-modal large model; based on the generated dynamic mask, screening an effective gradient in a back propagation process of the dynamic mask; updating parameters corresponding to the effective gradient in real time, and obtaining the output of the multi-modal large model based on the updated parameters; according to the obtained multi-modal sensor data and the output of the multi-modal large model based on the updated parameters, feature fusion is carried out, and a combined state code including an environment state, a robot body state and historical decision information is generated; and according to the determined joint state code and based on a time sequence model, generating an action sequence, a force control parameter and a path planning dynamic decision instruction of the robot, so that the robot can act based on the generated dynamic decision instruction, thereby realizing decision control of the robot.

The invention provides a method for model training, a host and a storage device. The method includes instructing, by a host device, a graphics processing unit (GPU) to load first intermediate data of a current layer of the model from a dynamic random access memory (DRAM) of a storage device into a memory of the GPU, where the current layer is a layer of the model that is performing computations; and based on the space capacity of the DRAM, notifying, by the host device, the storage device to pre-fetch second intermediate data of the layer to be calculated of the model from the NAND of the storage device to the DRAM of the storage device, the first intermediate data for the current layer is used by the GPU in back propagation of the model to perform computations for the current layer.

The invention discloses a multi-dimensional knowledge distillation method based on Logit cross correction, and the method comprises the steps: inputting a to-be-classified image into a primary feature extraction module of a teacher model and a primary feature extraction module of a student model, and obtaining two primary features; secondly, inputting the two primary features into a category result sensing module to obtain a self-adaptive weighted Logit score, and calculating category result loss; and then inputting the adaptively weighted Logit score and the primary feature into a Logit cross correction module and a category generation perception module, and calculating correction loss and category generation loss. And finally, performing weighted fusion on the category result loss, the correction loss and the category generation loss through variable weights to obtain a final loss value, and minimizing the loss value through back propagation to complete multi-dimensional knowledge distillation. According to the method, feature knowledge and Logit knowledge are combined, so that the problems of poor distillation interpretability and insufficient utilization of local semantic information in a knowledge distillation task are solved.

The invention discloses a digital intelligent integrated platform terminal display operation and maintenance decision-making method and system, and belongs to the field of GIS equipment partial discharge data monitoring and processing, and the method comprises the steps: S100, collecting partial discharge signals, environment data and equipment operation state data in real time; s200, identifying a discharge type through a discharge type identification model, and generating environment or equipment operation state correlation analysis through gradient back propagation and physical rule matching; s300, generating a feature contribution degree report based on SHAP + LIME, verifying a model decision based on a physical rule base, and dynamically adjusting the confidence coefficient; s400, matching an operation and maintenance strategy based on the knowledge graph; s500, displaying a natural language report of the 3D spectrogram, the thermodynamic diagram and the operation and maintenance strategy on a visual interface; and S600, updating model parameters through incremental learning. The operation and maintenance threshold can be reduced.

The invention discloses a deep learning table recognition model evolution-oriented regression defect relieving method, which comprises the following steps of: firstly, screening new features by applying a CONMI evaluation function in combination with specific hyper-parameters in a feature selection stage, and taking a new feature set obtained by combining the new features with an old feature set as model training data to realize contribution degree control-based retraining; on one hand, the feature contribution degree is calculated through the expected gradient, on the other hand, an overall loss function containing cosine similarity and a cross entropy loss function is designed to stabilize the old feature contribution degree and learn new features, and a model is trained through forward propagation and back propagation processes based on a new feature set; and under the condition that the accuracy rate of the table recognition model of the new version meets the condition, constructing a feature evolution scene, realizing a model evolution process according to a regression mitigation strategy, and taking the accuracy rate of the table recognition model of the new version as an evaluation index to obtain an evolution process regression defect mitigation strategy. The method is beneficial to improving the quality and reliability of a deep learning table recognition model.

The invention provides a federated learning posterior inference method and system based on mutual information regularization, and the method is applied to a client, and comprises the steps: receiving an initialized global model or an updated global model; initializing a local model according to the initialized global model or the updated global model, and determining the initialized local model and prior probability distribution of the local model; carrying out model training on the initialized local model by adopting local data, and determining a loss function of the local model; according to the loss function of the local model, performing first updating processing on the local model based on back propagation; performing second updating processing on the local model according to Gaussian noise sampled from preset normal distribution; determining a local model change amount; and sending the local model change quantity to a server side. Through the method and the device, mutual information regularization of the global model and the data is introduced, deviation in posterior estimation is relieved, and generalization ability of the global model is improved.

The invention relates to a spacecraft pose estimation method, in particular to a high-precision spacecraft pose estimation method based on deep learning, and solves the technical problems that a network model of an existing spacecraft pose estimation method is poor in interpretability and generalization ability, or precision is difficult to guarantee. According to the method, the pose estimation task of the spacecraft is decomposed into three-dimensional view reconstruction and key point regression of the spacecraft, the interpretability is high, and the generalization ability is stable; two-dimensional coordinates of key points are predicted through the key point regression initial model, then a predicted pose and a loss function of the spacecraft are calculated in sequence, the gradient of the loss function about model parameters serves as a constraint condition to participate in back propagation of the key point regression initial model, and the pose solving process of the spacecraft participates in updating of the model parameters. The overall integrating degree of the key point regression model obtained through training can be increased, the situation that pose estimation is caught in local optimum is avoided, and the precision of spacecraft pose estimation is improved.

The invention discloses a multivariable time sequence prediction method and system based on an implicit neural network. The method comprises the following steps: 1) collecting data and preprocessing the data; 2) performing window division on the standardized or normalized multivariable time sequence and determining the length of a to-be-predicted window; 3) performing variable correlation coding on the input window to obtain a variable-level feature vector; 4) the implicit neural network based on time attention predicts target parameters by using the variable features in the step 3), and implicit neural representation of the target sequence is modeled through the parameters; 5) taking the output of the implicit nerve representation and the original input window as the input of the multi-head attention predictor, and obtaining a prediction result through cross-sequence cross attention calculation performed in the implicit space and multi-layer perceptron conversion output dimension; and 6) training and optimizing model parameters, calculating a mean square error of a prediction result and a real result, taking the mean square error as a loss function, carrying out back propagation to optimize trainable parameters of the variable correlation coding module, the implicit neural network module multi-head attention predictor and the multi-layer perceptron, and then repeating the steps 3) to 6) to obtain the multi-head attention predictor. Until the preset number of iterations is reached or the error of the model on the verification set meets the requirement of early stop; and 7) performing prediction by using a model of training convergence, and performing reverse normalization on a prediction result to obtain a final prediction result. The method has good generalization, and meanwhile, the interpretability of the attention mechanism is remarkably improved by generating the hidden space characteristics of the trend component and the season component.

The invention relates to a vision and GNSS fusion displacement monitoring method and system based on deep learning. The method comprises the following steps: respectively acquiring visual data and GNSS data, preprocessing the visual data and the GNSS data, and synchronizing the visual data and the GNSS data to obtain synchronized visual data and synchronized GNSS data; performing feature extraction and combination to obtain a modal combination feature sequence; constructing a dynamic weight adaptive fusion network; and training the dynamic weight adaptive fusion network to obtain a displacement monitoring model, and inputting the modal joint feature sequence into the displacement monitoring model to complete displacement monitoring. According to the invention, through a feature extraction network of joint learning, time sequence correlation modeling of vision and GNSS in the same embedding space is realized. And dynamic self-adjustment of the modal weight is realized through a dynamic weight adaptive fusion network. All modules can be micro, and end-to-end back propagation training is supported. And when the visual signal is interfered or the GNSS is interrupted for a short time, the system can carry out self-adaptive compensation, and continuous and stable displacement output is kept.

The present application relates to the technical field of autonomous driving, and discloses a BEV feature decoding method and apparatus, an electronic device, and a storage medium. The method comprises: first, acquiring a BEV feature map corresponding to an image at the current moment; and then, inputting the BEV feature map into a preset multi-dimensional attention decoding model for decoding, to obtain a multi-task decoding result. During the training of the multi-dimensional attention decoding model, the multi-dimensional attention decoding model is configured to comprise N attention mechanism network layers; losses of outputs of the N attention mechanism network layers would be independently calculated, and the losses of the layers are summed at the last attention mechanism network layer as a total loss, so that the back propagation process of each attention mechanism network layer is optimized, making global training convergence faster; in addition, model training is not prone to being trapped in local optima, and a large deviation would hardly occur in a result.

The invention relates to the technical field of metal processing detection, in particular to a copper bar drawing residual stress detection method and system, and the method comprises the steps: collecting production line process state parameters in real time, and mapping the parameters to a predefined multi-dimensional process parameter space to generate a dynamic state vector; adjusting a key coefficient of a material constitutive equation based on the dynamic state vector, and generating a reference stress field; synchronously acquiring multi-physical field data on the surface of the copper bar; constructing a physically constrained machine learning model, and generating a cross-scale fusion stress field; an adjoint optimization equation is constructed based on dynamic process constraints, and model weight parameters are updated through real-time back propagation gradient; and outputting a new cross-scale fusion stress field according to the updated machine learning model, and obtaining related indexes of residual stress detection. According to the invention, the defects of static stiffness and insufficient data fusion of the model in the prior art are effectively overcome, and the real-time detection of the residual stress with adaptive technological parameters is realized.

The invention provides a training method and device for a VLA model, and relates to the technical field of intelligent robots with bodies, and the method comprises the steps that the VLA model outputs a joint angle sequence of a mechanical arm of a robot with a body based on visual input and language input; the differentiable forward kinematics module outputs a real-time pose of an end effector of the mechanical arm in a task space; based on joint space loss formed by the joint angle sequence and the joint angle in the teaching data, task space loss formed by the real-time pose and the tail end pose in the teaching data, and task space constraint loss, a multi-objective loss function is constructed, and total loss is calculated; calculating the gradient of the total loss to the joint angle sequence and the real-time pose through back propagation, and optimizing preset parameters of the VLA model; the above steps are repeatedly executed until the total loss meets the expectation, and a trained target VLA model is obtained; the technical problems that when a VLA model is trained in a joint space, the hardware coupling performance is high, and the generalization ability is insufficient are solved.

The invention discloses a voice model compression method, electronic equipment and a storage medium. The method is specially designed for a large-scale sequence-to-sequence speech recognition model with an encoder-decoder architecture. According to the method, the decoder and the encoder are pruned in sequence, so that heavy back propagation calculation is avoided. According to the method, under the condition of no back propagation or retraining, the parameters of the Whisper-large model can be reduced by about 60%, and the performance of the model on various data sets is hardly influenced. Meanwhile, the method is suitable for a multi-language data set, and the pruned model keeps good robustness and generalization in the aspect of multi-language ability. According to the innovation, the threshold of large-scale model deployment is greatly reduced, and the method is easier to apply in a resource-limited environment.

The invention provides an online video instance segmentation method and system based on mask propagation, and the method comprises the following steps: S1, achieving the cross-frame propagation of a target mask through a mask propagation model, obtaining a prediction mask of a current frame, and achieving the correlation of a target through the calculation of the intersection-union ratio of the prediction mask; and S2, performing back propagation on the target by using the mask propagation model so as to complement the missed target mask and enhance the continuity of the track. Objects between different frames are associated on the basis of a mask propagation mechanism and in combination with the intersection-to-union ratio of masks, and meanwhile, in order to relieve the scene that a segmentation model fails to segment shielded objects, non-significant objects and the like, a reverse mask propagation technology is provided to complement the failed frames. The method aims at performing fine segmentation and continuous tracking on various scenes such as intelligent monitoring, automatic driving, augmented reality and video editing on the target in the video, and has wide research and application prospects.

The invention relates to a data parallel communication method and device in distributed training, a storage medium and a program product. The method comprises the following steps: for any computing device in a computing device cluster participating in distributed training of a target model, obtaining global latest parameters of the target model through global collection operation in a forward propagation process, according to the training data subsets corresponding to the computing devices and the global latest parameters of the target model, forward propagation calculation is carried out, loss values corresponding to the computing devices are obtained, and different computing devices in the computing device cluster carry out forward propagation calculation based on different training data subsets; and for any computing device, calculating a gradient corresponding to the computing device based on the loss value corresponding to the computing device in a back propagation process, and transmitting the gradient corresponding to the computing device to other computing devices in the computing device cluster through reduction and dispersion operation. The communication overhead can be reduced, and the efficiency of large-scale training can be improved.

The invention discloses a low signal-to-noise ratio conditional modulation identification method based on wavelet transform and channel attention. The method comprises the following steps: acquiring a received signal; and inputting the received signal into an identification model of a pre-trained neural network, and outputting a classification identification result and classification accuracy. In the recognition model based on signal reconstruction and the neural network, a wavelet threshold estimation module and a wavelet reconstruction module form a signal reconstruction path, a multi-scale feature extraction module and a prediction classification module form a recognition path, and the two paths are mutually enhanced, so that the combination of the advantages of a digital signal processing technology and the neural network is realized; a wavelet threshold estimation module is introduced to predict a denoising threshold through a neural network, and network parameters of the wavelet threshold estimation module are updated according to back propagation; a signal reconstruction path is combined with a recognition path, the interpretability of the network is enhanced, and the accuracy of modulation recognition in a low signal-to-noise ratio scene is remarkably improved by using multi-scale modulation characteristics.

The invention provides a segmentation federal learning method and system based on aggregation gradient broadcast, and the method comprises the steps: initializing a global model, and segmenting the global model into a server model and a client model according to the capability limitation of a local device; issuing the client model to all local equipment terminals; the multiple local devices execute forward propagation at the same time, and shredded data are obtained through calculation; transmitting the shredded data and the training data label to an edge server; performing forward propagation in parallel according to the shredded data, calculating the loss of each local equipment end in combination with a corresponding training data label, and performing back propagation to obtain a loss function and a gradient of the shredded data; aggregating the gradient of the shredded data and broadcasting to all local equipment; updating the server side model and the client side model, and aggregating the server side model; and the iterative learning loop is repeatedly executed until convergence or the maximum communication round is reached. According to the invention, the communication overhead in segmentation federal learning is saved, and the model training efficiency is effectively improved.