414results about How to "Easy to train" patented technology

The invention provides an unstructured text data calculation method and system, and relates to the technical field of natural language processing, and the method comprises the steps: carrying out the multi-level processing of input unstructured text data, dynamically adjusting the word segmentation granularity according to the word frequency distribution, constructing a part-of-speech co-occurrence matrix in combination with context semantic information, and extracting entity information. And fusing the part-of-speech co-occurrence matrix and the entity information to generate a hierarchical semantic tag sequence. Feature extraction units with different convolution kernel sizes are adopted to extract feature representation, and cosine similarity between different semantic hierarchies is calculated to establish an association weight matrix. A semantic enhancement vector is constructed based on entity information, and adversarial training is carried out to obtain a multi-modal semantic feature matrix. And calculating the semantic similarity between the fusion feature vectors for clustering, setting difficulty weight sorting according to the complexity, consistency and ambiguity of class clusters, then inputting the class clusters into a classifier, and iteratively optimizing a classification result to obtain a calculation result.

The invention discloses a PPY-YOLO-based steel surface defect detection method and a PPY-YOLO-based steel surface defect detection system. The PPY-YOLO-based steel surface defect detection method comprises the following steps: step 1, preprocessing a steel surface defect image; 2, a neck structure Faster-Neck, a deep learning module C3K2Faster and a spatial pyramid pooling module SPPFSim are introduced into the YOLOv11 network, and a PPY-YOLO target detection model is obtained; step 3, training a PPY-YOLO target detection model; and 4, acquiring a steel image, and inputting the steel image into the trained PPY-YOLO target detection model to obtain the category and positioning information of the steel surface defects. A new model is constructed, the backbone network and the neck network are improved, the backbone network is formed by connecting the input end of the C2PSA module with the output end of the SPPFSim module, and an up-sampling group and a down-sampling group are added to the neck network, so that the model has a relatively good detection effect.

The invention relates to the technical field of chemical engineering and machine learning, and provides a method for predicting the solubility of carbon dioxide in a deep-eutectic solvent based on a machine learning model, and the method comprises the steps: collecting CO2 solubility data, carrying out the coding and feature descriptor conversion of a deep-eutectic solvent molecular structure through an open-source chemoinformatics software package RDKit, and constructing a data set. Four algorithms of XGBoost, random forest, a deep neural network and a convolutional neural network are adopted to construct a model, and hyper-parameters are optimized through grid search and k-fold cross validation. After the model is trained, the prediction performance is evaluated, and the optimal model is selected for CO2 solubility prediction. The method improves prediction efficiency and accuracy, has strong adaptability and generalization ability, and provides an effective tool for formula optimization of the eutectic solvent and improvement of CO2 capture efficiency.

The invention relates to a gradient aggregation federated learning method based on combination of zero knowledge proof and a block chain technology, and belongs to the field of distributed machine learning. Through combination of zero knowledge proof (zk-SNARK) and an extensible block chain technology, limitations of a traditional method in aspects of data privacy protection and model verification are broken through. According to the method, the correctness of a global model is verified by using zero-knowledge proof, the transparency and data privacy of an aggregation process are ensured, the Chinese remainder theorem is introduced to compress the proof, and the storage burden of block chain nodes is reduced. And the hash value updated by the encryption model is recorded through the block chain, verification is carried out based on a block chain consensus node, and the data integrity and the system transparency are further improved. Besides, a dynamic client selection mechanism is introduced in the method, participants are optimized based on training performance scores, and the training efficiency and the model quality are improved. As a whole, the invention provides a safe, efficient and transparent distributed learning solution.

The invention discloses a remote physiological signal estimation method and system based on a diffusion model, and relates to the technical field of non-contact physiological signal detection. The training process of the diffusion model is as follows: forward diffusion is performed on an original rPPG signal to obtain a noise rPPG signal; performing feature extraction on the face video to obtain a multi-scale space-time diagram; the noise rPPG signal and the multi-scale space-time diagram are fused; carrying out backward diffusion on the fused data to obtain de-noised data; outputting a predicted rPPG signal according to the denoised data; performing model training by minimizing the difference between the predicted rPPG signal and the original rPPG signal; and performing remote physiological signal estimation by using the trained diffusion model. According to the invention, the accuracy of rPPG signal estimation is improved.

The invention discloses an underwater multi-degraded image enhancement and target recognition joint optimization method based on a genetic algorithm, and relates to the field of underwater image enhancement and underwater target recognition, and the method comprises the steps: building an underwater robot target recognition system, obtaining underwater event camera data, and processing the underwater event camera data to obtain a sample data set; initializing by adopting a genetic algorithm to obtain a primary population, namely an initial enhancement parameter; performing initial enhancement on the environment information by adopting the initial enhancement parameter to obtain an initial enhanced image data set; taking YOLOv5 as a basic framework, constructing an underwater target recognition algorithm model, and obtaining underwater target detection average precision mAP; the underwater target detection average precision mAP is used as a genetic algorithm fitness value, a genetic algorithm is adopted to optimize enhancement parameters of an underwater multi-degraded image enhancement module, then target enhancement parameters are obtained to enhance environment information to obtain a target enhanced image, and the purposes of image enhancement and effective recognition are achieved at the same time.

The invention discloses a T-S fuzzy and TD3-based slow dynamic unknown coal-fired power generation system coordination control method, which comprises the following steps: firstly, decomposing a coal-fired power generation system into a fast subsystem and a slow subsystem by using a singular perturbation theory, and decomposing an original control task into a stabilization task of the fast subsystem and a tracking task of the slow subsystem; for the fast subsystem, a fuzzy set is selected on a definition domain of the fast subsystem by using the slow variation characteristic of steam pressure, and a T-S fuzzy model is constructed; a fast subsystem controller is obtained by solving algebraic Riccati equations corresponding to a plurality of linear systems. For a slow subsystem, a double-Q network is adopted to reduce overestimation of a Q value, a dynamic learning rate and a batch size adjustment mechanism are introduced to accelerate training convergence, and learning is carried out under a TD3 algorithm framework to obtain control input of the slow subsystem. The fast subsystem and the slow subsystem control inputs to be combined and then act on the original system to obtain state information at the next moment, and the intelligent agent interacts with the original system to complete collaborative optimization.

The invention relates to the field of data supervision and detection, and provides an industrial internet anomaly detection method based on a deep generative adversarial network, which is characterized by comprising the following steps: S10, preprocessing an intrusion detection data set based on a numerical value type to obtain a real sample; s20, a DeepGAN sampling model is trained; and S30, outputting a sampling result and carrying out anomaly detection on the sampling result based on the detection model. According to the oversampling method based on the deep generative adversarial network, the problem that the performance of a detector is reduced due to data class imbalance is solved, an existing oversampling method is utilized, the oversampling method based on the deep generative adversarial network is designed, the model training process is improved, and the quality of generated samples is improved. And finally, the detection performance of the detection model is effectively improved.

The invention provides a multi-modal knowledge graph privacy protection embedding method for diagnosis and treatment data, and relates to the technical field of data processing, and the method comprises the steps: carrying out the initialization embedding processing of text information and numerical information based on the diagnosis and treatment data, and carrying out the initialization embedding processing of visual information based on medical image visual data; obtaining a multi-modal attention coefficient of a neighbor entity by using a multi-modal diagram self-attention layer; fusing the structured information of the multi-modal knowledge graph by stacking a plurality of encoder layers; and the multi-modal knowledge graph privacy protection embedding is scored by using the convolution embedding model. According to the method, efficient embedding and deep fusion of multi-modal information are effectively achieved, the processing capacity of heterogeneous data is enhanced, sensitive information is prevented from being leaked through the embedding process, an end-to-end privacy protection mechanism is provided, and the safety and reliability of diagnosis and treatment data in the analysis and reasoning process are ensured.

The invention discloses a home scene image generation method based on Stable Diffusion. The method comprises the following steps: firstly collecting a multi-style home scene image-text data set for a home scene generation task; then, on the basis of the data set, a Stable Diffusion model of the text graph is trained by adopting a LoRA training strategy; meanwhile, the content structure of the generated home scene image is controlled in combination with a ControlNet network, so that a Stable Diffusion model which effectively meets a home scene image generation task is obtained; the method comprises the following steps: combining a Stable Diffusion model network with a home scene generation problem, taking a multi-style home scene graph as initial noise, and taking a design constraint as a condition for generating a structural scene graph; according to the invention, a small sample training set is adopted, so that various home scene designs can be generated; meanwhile, the skill requirement for model training of the user is low, and common users can also be well trained and applied.

The invention discloses a power grid abnormal situation awareness method and system. The method comprises the following steps: acquiring power grid data in real time and calculating different power grid situation evaluation indexes; weighting each power grid situation assessment index, correcting the weight of an abnormal index, and then performing linear weighting on all the power grid situation assessment indexes to obtain a situation assessment value; constructing a prediction model with a double-layer gating recurrent neural network, an attention layer and an output layer cascade, inputting historical data of a power grid situation assessment index, and outputting a future situation assessment prediction value; and inputting new historical data of the power grid situation assessment index into the trained prediction model to obtain a corresponding future situation assessment prediction value, and matching the future situation assessment prediction value with a pre-divided security level to determine whether an abnormality occurs. According to the method, a deep learning framework is utilized, the model for predicting the power grid operation situation of the double-layer gating recurrent neural network based on the attention mechanism is constructed, and a better prediction effect and higher accuracy are achieved.

The invention provides a Chinese herbal medicine indication discovery method and system based on hypergraph convolution. The method is mainly based on two hypergraph convolutions, and makes full use of biological knowledge features of effective components and target spots, high-dimensional Chinese herbal medicine-effective component association and target spot-indication association including molecular fingerprints of the effective components, sequence information of the target spots and high-order features in hypergraphs. The method is low in model complexity and low in power consumption; the association relationship between the Chinese herbal medicine and the indications in the network can be accurately predicted, and reliable technical support is provided for finding the indications of the Chinese herbal medicine.

The invention discloses a multifunctional peoriae paenibacillus and application thereof, and relates to the technical field of microorganisms, and the key point of the technical scheme is as follows: Paenibacillus peoriae S6330 is separated from rhizosphere soil; the peoriae paenibacillus has a good inhibition effect on pathogenic bacteria, pathogenic fungi and oomycetes; meanwhile, the peoriae paenibacillus has the functions of dissolving potassium, producing protease, producing amylase, producing cellulase, producing siderophore and the like, has a growth promoting effect on various crops such as wheat, corn, watermelons, small oilseed rapes, tobaccos and the like, and can remarkably improve indexes such as chlorophyll content, plant height, fresh weight, overground part weight, underground part weight and the like of plants; in addition, the peoriae paenibacillus can be used for effectively inhibiting the tobacco bacterial wilt; the peoriae paenibacillus has no environmental pollution problem, is simple in culture condition, and has wide disease prevention and growth promotion application prospects in agricultural production.

The invention particularly provides a control method and device for self-cleaning of a water tank. The method comprises the steps of monitoring water quality data and cleaning data of each water tank in real time, selectively obtaining environment data of the water tanks according to the water quality data and the cleaning data of each water tank, and substituting the water quality data, the cleaning data and the environment data of the water tanks into a cleaning analysis and evaluation model when the environment data is obtained, obtaining a self-cleaning treatment scheme corresponding to the water tank, executing the self-cleaning treatment scheme on the water tank, obtaining cleaning water quality data of the water tank, and substituting the cleaning water quality data into the cleaning analysis and evaluation model again to obtain a self-cleaning evaluation result of the water tank. And feeding back the self-cleaning treatment scheme and the self-cleaning evaluation result to a user terminal corresponding to the water tank, and selectively cutting off water supply of the water tank based on the self-cleaning evaluation result of the water tank. And through real-time monitoring and timely self-cleaning treatment, water quality pollution is effectively prevented, and the safety of domestic water of a user is guaranteed.

The invention relates to the technical field of data processing, in particular to a geological environment situation analysis method based on multi-scale observation and a three-dimensional field model. Comprising the steps of S1, collecting geological data of a target area; s2, constructing a three-dimensional model of the target area based on the remote sensing image, and fusing the basic geographic data and the geological environment data to obtain a dynamic three-dimensional field model; s3, constructing a geological environment database, and obtaining element data influencing each geological event; s4, creating a geological event prediction model, and training the geological event prediction model through the historical element data and the corresponding geological events; and S5, predicting the occurrence of the geological event after the predetermined time period based on the trained geological event prediction model and the element data before the predetermined time period. According to the method, the problems of poor geological environment observation dynamics and inaccurate situation analysis are solved, multi-scale and dynamic observation of the geological environment is realized, and the accuracy of situation analysis is improved.

The invention discloses a cloud-side collaborative transformer area intelligent electric meter fault diagnosis and positioning method and system, and the method comprises the steps: constructing an intelligent electric meter fault historical data fault library in a master station, completing the training of an intelligent electric meter DBN-DNN-STLSTM fault prediction model, and downloading the trained model into an intelligent electric meter fault diagnosis instrument; on the concentrator side, the intelligent electric meter fault diagnosis instrument acquires real-time operation data of all intelligent electric meters in the transformer area in an unvarnished transmission and on-site manner through the concentrator, and inputs the real-time operation data into the DBN-DNN-STLSTM fault prediction model, so that fault diagnosis is completed, and the fault electric meters in the transformer area are positioned; and according to comparison between the diagnosis fault and the actual fault, abnormal fault information is fed back to the master station, the fault information base is expanded, training of the DBN-DNN-STLSTM fault prediction model is completed again, and the diagnosis model in the intelligent electric meter fault diagnosis instrument is updated. Through cooperation of the main station, the site and the laboratory, the fault diagnosis and positioning precision of the intelligent electric meter is continuously improved.

The invention discloses an uncertainty perception semi-supervised target detection method in an automatic driving environment, and the method comprises the steps: S1, obtaining a teacher model with the uncertainty prediction capability through the supervised learning of labeled data through data enhancement and an uncertainty loss function; s2, the teacher model generates a fuzzy pseudo-label by utilizing label-free data reasoning; and S3, quantizing the similarity of the uncertainty output of the teacher model and the student model by taking the fuzzy pseudo tag as a learning target of the student model. The problem that an uncertainty mechanism is not introduced in an existing semi-supervised target detection task to deal with the problem that the algorithm detection performance is reduced due to label deficiency is solved.

The invention provides a model training method, an industrial internet anomaly detection method and a related device, and relates to the field of industrial internet. The model training method comprises the following steps: acquiring a training sample comprising a plurality of time sequence data samples; inputting the training sample into a domain projection module to perform feature extraction of a unified dimension to obtain a plurality of target features of a target dimension; inputting the plurality of target features into a feature mixing enhancement module for feature mixing enhancement processing to obtain positive features and negative features of a plurality of target dimensions; inputting the target features, the positive features and the negative features into an anomaly detection module for anomaly detection processing to obtain inter-block characterization and intra-block characterization corresponding to each feature, and characterization loss between the inter-block characterization and the intra-block characterization; and adjusting parameters of the anomaly detection model based on a first alignment loss among the plurality of target features, a second alignment loss among the plurality of in-block representations and a target loss determined by the representation loss, and obtaining the anomaly detection model with relatively good generalization ability.

The invention provides a wind turbine generator fault diagnosis system and method, and the system comprises a data generation module which is used for calculating corresponding simulation data according to the fault mechanism of equipment through employing an aerodynamic system model, a transmission system model and a variable pitch system model, learning a distribution mode reflecting fault categories through a data training generation model together with historical faults, and generating virtual fault data; and the fault diagnosis module is used for performing fault diagnosis on the input operation data of the wind turbine generator by using the trained probabilistic neural network. The method has the advantages that enough training data can be generated according to training requirements, meanwhile, the distribution range of the training data is wider than that of mechanism simulation data, the training data is closer to real operation data, and the precision of a fault diagnosis model is greatly improved; compared with a single probabilistic neural network algorithm, the fault diagnosis module has the advantages that the training process of the probabilistic neural network is optimized by utilizing the genetic algorithm, and the training speed is increased.

The invention relates to an X-ray-based defect identification method, belongs to the technical field of X-ray nondestructive testing, and solves the problems of low accuracy and efficiency of casting defect identification in the prior art. The method comprises the following steps: acquiring an X-ray image of a sample casting, and preprocessing the X-ray image to acquire an edge image of the sample casting; marking whether the contour has defects and defect types according to the area and defect features of each contour in the edge image of the sample casting; training a defect identification model by adopting the marked edge image of the sample casting; obtaining an X-ray image of a target casting, and preprocessing the X-ray image to obtain an edge image of the target casting; and inputting the edge image of the target casting into the trained defect identification model so as to identify whether the target casting has a defect and identify the type of the defect. According to the method, through combination of an X-ray imaging technology, an image processing technology and a machine learning technology, rapid and accurate identification of the internal defects of the casting is realized.

The invention discloses a multi-modal data enhancement method and system based on an AI training platform, and belongs to the technical field of multi-modal data processing.The method comprises the steps that firstly, a multi-modal data fusion pipeline is developed on the AI training platform, and data of different modals are collected through a data collection module for preprocessing; in the preprocessing stage, a multi-modal data fusion pipeline is used for carrying out feature extraction on data from different modals, and joint modeling is carried out at a specific level; then, automatically generating high-quality synthetic data by adopting a data enhancement pipeline; and finally, developing a multi-modal deep learning pipeline to fully learn and understand deep features of different modal data. According to the method, the problem of model learning bias caused by single-modal data in the prior art is solved, the generalization ability and the data processing efficiency of the model are improved, meanwhile, the processing difficulty of a multi-modal data task is simplified for an AI training platform user, and the method has important application value.

The present invention discloses a heterotrophic nitrifying Brevundimonas DB‑4 and its application, belonging to the field of microbial technology. The heterotrophic nitrifying Brevundimonas (Brevundimonas) DB‑4 was deposited in the General Microbiological Center of the China Microbiological Culture Collection Administration Committee on December 11, 2023, with a deposit number of CGMCC No.29279. The Brevundimonas DB‑4 provided by the present invention is derived from the decomposed matter of the mixed compost of bean cake and vegetable cypress, has a strong heterotrophic nitrification ability, can promote the conversion of ammonium nitrogen in the rhizosphere soil to nitrate nitrogen, and can effectively colonize in the soil, increase the nitrate nitrogen content in the soil and plants; at the same time, it has the ability to depotassium, thereby increasing the content of available potassium in the rhizosphere soil, can promote the improvement of crop quality, and can be widely used in the preparation of microbial fertilizers to improve the nitrogen conversion efficiency of fertilizers and reduce the application of chemical fertilizers.

The invention provides an aviation trajectory prediction method based on multi-flight training and transposition input, a medium, a device and a program product. The method comprises the steps of collecting a flight data set and performing data preprocessing; constructing a Transform model based on transpose input, and training the model by using the preprocessed data; the trained Transform model is utilized to carry out trajectory prediction; and the trajectory prediction result is visualized. According to the method, multi-flight input is realized through data preprocessing for training, only effective flight data is utilized, the data volume is greatly reduced, and convenience is provided for subsequent training; and meanwhile, the Transform model based on transpose input can better capture dependency among data during trajectory prediction, so that the problem of complex dependency in time sequence data is solved, mutual influence among different variables can be identified under the condition of multiple variables, and the prediction accuracy and the generalization ability of the model are improved.

The invention relates to the technical field of training instrument research, in particular to a double-foot balance feedback training device which comprises a training table used for standing of two feet and a supporting pipe connected with the middle of the front end of the training table and switched between a vertical state and a horizontal state, and a locking handle moving in the axial direction of the supporting pipe is arranged at the top of the supporting pipe in a radial penetrating mode. A toe training device is arranged at the front end of the top face of the training table, and a pelvis training mechanism is arranged in the middle of the training table. The training platform is used for installing and fixing the toe training device, the toe pressing mechanism and the pelvic bone training mechanism, so that a patient can carry out toe training and pelvic bone training by standing on the training platform, a limited space is conveniently utilized for training, and the balance force of double-foot supporting is effectively improved; the foldable supporting pipe is arranged at the front end of the training table, supporting training of a patient is facilitated, meanwhile, the folded supporting pipe and the training table can vertically lean on the wall side or the bedside, storage is convenient, space is not occupied, and practical value is achieved.

The invention provides a drying control method and device of a washing machine and a drying management system, and the method comprises the steps: obtaining an image of to-be-dried clothes and the clothes quality of the to-be-dried clothes under the condition that the washing machine is in a drying stage, the image of the to-be-dried clothes comprises the images of all the to-be-dried clothes, and the image of the to-be-dried clothes comprises the images of all the to-be-dried clothes; the mass of the clothes is the sum of the mass of all the to-be-dried clothes; an identification step: carrying out image identification on the to-be-dried clothes image to obtain a forward stacking height value, an expansion area and a distribution state parameter of the to-be-dried clothes; the clothes mass, the forward stacking height value, the unfolding area and the distribution state are input into a drying parameter control model, a drying parameter set is obtained, and the drying parameter set comprises the inner barrel rotating speed, the fan rotating speed and the heating time; and controlling the washing machine to dry according to the drying parameter group. The problem of poor drying quality of the washing machine in the prior art is solved.

The invention relates to a brain image generation method and system based on multilevel structure constraint, and a medium. The generation method comprises the following steps: preprocessing brain MRI image data; generating a high-fidelity cross-modal brain image through decoupling content features and attribute features by using a generative adversarial network framework of decoupling and comparative learning; pixel-level granularity discrimination: discriminating pixel-level features by using a brain memory library to enhance discrimination ability and optimize a memory space; and structure-level granularity discrimination: constraining different brain structures by dynamically adjusting a weight strategy so as to improve the learning effect of samples difficult to recognize. Compared with the prior art, the hierarchical granularity discrimination method provided by the invention aims to solve the problem of neglecting spatial coherence of structural hierarchical representation and anatomical consistency of content in a model training process by utilizing multi-level semantic information in a medical image.

The invention discloses a fluorescent quantitative PCR (polymerase chain reaction) detection method and a detection kit for detecting differentiation potential of induced pluripotent stem cells. The detection method comprises the following steps: S1, preparing an embryoid body by utilizing iPSC (induced pluripotent stem cells); s2, extracting RNA (Ribonucleic Acid) of the iPSC and the embryoid body; s3, respectively carrying out reverse transcription on the iPSC and RNA of an embryoid body to obtain cDNA; s4, establishing a fluorescent quantitative PCR reaction system by adopting the primer composition in claim 1; s5, carrying out fluorescent quantitative PCR (Polymerase Chain Reaction) detection on the cDNA in S3; and S6, analyzing a result. The detection kit disclosed by the invention can be used for rapidly and accurately evaluating the differentiation potential of the induced pluripotent stem cells, and is suitable for large-scale cell differentiation research and clinical application.

The invention belongs to the technical field of medical diagnosis, and discloses an MRI lumbar sagittal view disease image diagnosis method based on a YOLOv8s algorithm, and the method comprises the following steps: S1, screening collected MRI lumbar sagittal view image data, self-building a VOC2007 data set, and marking the data set; s2, performing data enhancement and other processing on the existing data set; s3, establishing a YOLOv8s deep learning neural network detection model; dividing the data set into a training set, a verification set and a test set according to a proportion of 8: 1: 1, training the YOLOv8s network until convergence, and obtaining a lumbar disease image detection model based on the YOLOv8s network and a weight file; and S4, testing the randomly extracted MRI lumbar vertebra sagittal view image of the patient by using the trained YOLOv8s detection model, outputting a detection result, and evaluating the detection result. According to the invention, the diagnosis of the MRI lumbar sagittal view disease can be realized, the detection precision and efficiency are greatly improved, and the diagnosis accuracy is improved.

The invention relates to the technical field of intelligent sports data analysis, in particular to an intelligent sports data analysis method and system based on the Internet of Things and a medium. The method comprises the following steps: acquiring real-time state data of physical exercise of an athlete through an intelligent bracelet worn by the athlete; based on an electronic video recording device, motion posture data mapping is carried out according to the real-time state data of the athletes in physical exercise, and motion posture mapping data is obtained; performing instantaneous explosive power evaluation on the motion attitude mapping data, performing abnormal load limit coupling processing, and performing motion risk level evaluation to obtain motion risk level data; making an intelligent motion feedback strategy based on the motion risk level data to obtain the intelligent motion feedback strategy; and sending the intelligent motion feedback strategy to the intelligent bracelet to execute sports data analysis. The intelligent sports data analysis technology is optimized, so that the intelligent sports data analysis technology is more perfect.

The invention discloses a human body lower limb posture monitoring system based on a flexible sensor. The human body lower limb posture monitoring system comprises an array type flexible piezoresistive sensor module, a data acquisition and processing module, a feature selection module, a pressure data color mapping module, a wavelet neural network module and a joint bending angle result output module. An array type flexible piezoresistive sensor used for obtaining initial plantar pressure distribution data is designed, a method based on gait intervals is adopted to select data points, key feature points most related to joint angle changes are screened out based on time sequence information of gait events, the dimensionality of input data is reduced, and the accuracy of the input data is improved. And the structure and the training process of the network are optimized, and high-precision prediction of the lower limb joint angle is realized.