116 results about "Data imbalance" patented technology

The invention discloses an industrial part defect sample accurate generation method based on a conditional diffusion model, and belongs to the field of image processing and artificial intelligence. The method forms a closed-loop cooperative system by constructing four deep coupling modules of physical constraint noise scheduling, multi-scale feature coupling, double-domain feedback optimization and adaptive weight adjustment; a defect physical forming mechanism is converted into a dynamic noise scheduling strategy, deep interaction between condition information and a feature map is established at multiple levels of a diffusion network, quality closed-loop optimization is achieved through dual evaluation of a pixel domain and a frequency domain, and training weight is dynamically adjusted according to defect scarcity. And multi-scale accurate control is realized, a quality guarantee closed loop is established, the problem of data imbalance is effectively solved, and the performance of an industrial defect detection model is remarkably improved.

The invention discloses a maritime accident prediction method and device based on interpretable integrated machine learning, and relates to the technical field of maritime affair safety risk analysis, and the method comprises the steps: obtaining accident investigation data, carrying out the preprocessing, balancing the data through a ten-fold layered oversampling method, and carrying out the cross verification training, and determining a performance optimal model by using the test set and carrying out interpretable analysis to explain the influence of the characteristics on the accident prediction result. By constructing a closed-loop'data processing-model optimization-explanation output 'process and adopting SMOTE oversampling and ten-fold layered cross validation training and a heterogeneous base model ensemble learning strategy, the processing capacity of the data imbalance problem of accident categories is improved, the data leakage problem of oversampling is avoided, and the possible bias of a single model is overcome. The interpretability analysis of the model prediction result can quantitatively display the contribution degree of each feature to prediction globally and locally, reveal the nonlinear relationship and interaction effect between the features, and provide transparent interpretation of model decision.

The invention belongs to the technical field of rainfall prediction, and discloses a short and temporary rainfall prediction method based on multi-model random scheduling integration, which develops a robust training and pushing framework based on a continuous rolling prediction strategy, and decomposes long-sequence prediction into manageable stages. According to the method, training is carried out through teacher forcing and planned sampling, error propagation is relieved, and the training process is stabilized. The invention further designs asymmetric encoder-decoders (DSE and AFD) that achieve lower FLOPs than competitive baselines under standardized assessment, where DSE selectively compresses significant features and AFD stepwise reconstructs details to mitigate excessive smoothing problems. Finally, an intensity weighted Gaussian KL divergence loss function is designed, and the key problem of data balance is solved by modeling and predicting on a distribution level and endowing a large weight to a meteorological important heavy rainfall event.

The invention discloses a voice and music collaborative generation method and system based on a dynamic mixed attention and expert architecture, terminal equipment and a medium, and relates to the technical field of audio generation. The method comprises the following steps: acquiring multi-modal input containing at least one of audio, text and vision, performing embedding processing on the multi-modal input, and mapping the multi-modal input to a unified space to obtain a fusion sequence; setting a plurality of attention heads, dynamically selecting the attention heads to activate experts through attention head routing gating, and weighting and aggregating calculation results to obtain mixed attention features; generating expert probability distribution through expert set routing gating, dynamically selecting an expert set to activate experts, and calculating task adaptation features; and performing audio generation processing based on the audio language modeling head to obtain a voice or music result. According to the method, collaborative generation of voice and music, dynamic allocation of computing resources, balance of domain-specific and cross-domain general knowledge learning are realized, the problems of task conflict and data imbalance are solved, and the audio generation quality and efficiency are improved.

The invention discloses a semi-supervised prognosis prediction system based on irregular sampling medical data pre-training, and the system comprises a clinical electronic medical record data collection and preprocessing module which automatically collects original clinical electronic medical record EHR data from a medical database; and the pre-training module is used for receiving the patient feature vector sequence output by the clinical electronic medical record data acquisition and preprocessing module and carrying out feature representation learning on the preprocessed clinical time sequence data by utilizing a combined multi-task self-supervised learning mechanism. And the classifier fine tuning and pseudo-label iterative optimization module is used for training the pre-trained model through fine tuning of samples with labels and carrying out iterative optimization through guidance of pseudo-labels to obtain a prediction result. And the application display module is used for displaying and outputting a post-hospital-admission vital sign sequence and a prediction result. According to the method, irregular sampling and missing data are effectively processed, information loss is avoided, and the prediction capability of the model and the performance of the model under the conditions of data imbalance and label scarcity are improved.

The invention relates to the technical field of computers, and discloses a subject classification model construction method and system, electronic equipment and a storage medium, and the method comprises the steps: obtaining academic paper bibliography data based on an academic database, and constructing an initial training data set; identifying minority category subjects of which the sample quantity is lower than a preset threshold value, generating synthetic data containing chapters and keywords, and labeling corresponding subject categories; mixing the synthetic data with real data in the initial training data set, and constructing a balanced mixed training data set; splicing a text based on the chapter and the keyword of each sample in the mixed training data set, and generating a multi-level fusion feature; and taking the multi-level fusion features as input, accessing a full-connection classification layer to construct a model, carrying out end-to-end training based on a mixed training data set, and adjusting and optimizing model hyper-parameters to obtain a final subject classification model. According to the method, data imbalance can be effectively relieved, existing labeling resources are fully utilized, and the model generalization ability is improved.

The invention discloses a thin-wall shell plastic part injection molding process parameter multi-objective optimization method, which is based on an RIME-RF-MOGWO framework, takes a simulation sample as a research object, selects a volume shrinkage rate and a buckling deformation amount as optimization objectives, and firstly adopts SMOTE to process a data imbalance problem; establishing a nonlinear mapping relation between the process parameters and the quality target by using RF; an RIME is introduced to optimize the hyper-parameter of the RF; multi-objective optimization of process parameters is realized in combination with MOGWO, and a Pareto frontier solution set is obtained through non-dominated sorting and a congestion degree control mechanism. A multi-round optimization and simulation verification result shows that the multi-objective optimization method for the injection molding process parameters of the thin-wall shell plastic part can effectively obtain an optimal process parameter combination, the volume shrinkage rate is reduced by 19.02%, the buckling deformation amount is reduced by 50.63%, and the molding quality of the thin-wall plastic part can be remarkably improved.

The invention discloses a metal surface multi-scale defect recognition and classification method, system and device and a medium, and relates to the field of metal detection.The method comprises the steps that metal surface images are collected and preprocessed, and a preprocessed image set is obtained; performing data enhancement on the preprocessed image set by adopting a multi-layer strategy search and gradient matching mechanism to obtain an enhanced image set; based on the enhanced image set, adopting an SPGP-YOLOv11 network to generate a candidate detection frame of the metal defect; based on the candidate detection frame, determining the type of the metal defect by adopting a pre-trained classifier and a pre-trained two-state reinforcement learning algorithm; the classifier and the two-state reinforcement learning algorithm are cooperatively trained. The technical bottlenecks of the existing method in the aspects of multi-scale defect detection precision, small target detection effect, model real-time performance, data imbalance, insufficient robustness and the like can be solved.

The invention provides a threat detection method and device, and the method comprises the steps: constructing a time sequence diagram sequence corresponding to each time window through the preprocessed multi-source log data of a target network; embedding nodes in the time sequence diagram sequence corresponding to each time window by using a relational graph neural network to obtain an embedded sequence matrix; inputting the embedded sequence matrix into a Transform model, and performing autoregressive prediction to obtain a node prediction matrix of a next sub-graph node; constructing an attention score matrix through the predicted node prediction matrix of the next sub-graph node, so as to predict a connection matrix at the next moment; and calculating an error between the connection matrix at the next moment and the real adjacent matrix at the next moment to determine whether a security threat exists at the next moment. According to the scheme, the technical problems of data imbalance and data annotation in the prior art are solved, and efficient identification of low-frequency and hidden attack behaviors is achieved.

The invention discloses an aero-engine vibration signal generation method under extreme imbalance, and belongs to the technical field of aero-engine fault signal generation. The method comprises the following steps: acquiring an original vibration signal at a target position of the aero-engine, and performing preprocessing operation; taking the preprocessed real vibration signal as a training sample, constructing a forward noise adding process, and training the improved one-dimensional diffusion generation network to learn a reverse denoising mapping relation; and inputting random Gaussian noise into the one-dimensional diffusion generation network after training convergence, and generating a target vibration signal matched with a real vibration signal feature through a reverse diffusion denoising process. Through targeted improvement of the diffusion generation network, the problem of data imbalance is effectively relieved, the model deployment cost is reduced, the signal generation capability of the model for minority types of faults is improved, and the method is suitable for fault signal generation scenes of aero-engines under complex working conditions.

The invention provides a sodium ion battery safety early warning method and device based on multi-dimensional feature fusion and a neural network, and a storage medium, and belongs to the technical field of sodium ion battery safety management. The problems of low anomaly detection sensitivity, poor aging adaptability, high false alarm rate and the like in a traditional safety early warning method are solved; according to the method, a TCN-Bi-GRU hybrid neural network is constructed, millisecond-level voltage step characteristics of sodium ions are accurately captured through time sequence convolution, and a long-time temperature rise trend is analyzed in combination with a bidirectional gating unit; aiming at a specific capacity attenuation mode of the sodium battery, designing a three-level dynamic threshold collaborative optimization system based on SOH compensation, and realizing self-adaptive adjustment of an early warning boundary through a health state compensation function and an intelligent learning algorithm; a self-adaptive sample enhancement strategy and a multi-stage training method which are combined with sodium electrochemical characteristics are developed, safety early warning model deviation caused by data imbalance is effectively relieved, and the method can be applied to safety early warning of the sodium ion battery.

The invention relates to the technical field of wind power generation, and discloses a wind turbine generator fault diagnosis data processing method based on a machine learning algorithm, which adopts multi-source data cleaning and working condition self-adaptive slicing to ensure data quality. Automatic discovery and explanation of fault subclasses are realized through multi-algorithm consensus clustering and physical mechanism mapping; an unbalance index comprehensively considering quantity and classification difficulty is innovatively proposed, and a data set is accurately balanced in combination with a physical constraint oversampling technology; and finally, through hierarchical training and dynamic weight optimization, a high-precision and high-robustness interpretable diagnosis model is constructed. According to the method, high-precision traps caused by data imbalance of the model are effectively avoided, the recognition capability of early weak faults is remarkably improved, reliable technical support is provided for predictive maintenance of the wind turbine generator, and the operation and maintenance cost and the fault risk are greatly reduced.

The invention discloses a medical data intelligent identification method and apparatus. The method comprises the steps of obtaining to-be-identified target data; inputting the target data into a pre-trained intelligent recognition model to obtain a recognition result output by the intelligent recognition model, the recognition result at least comprising all sample categories of the target data and statistics of the number of the categories; wherein the intelligent identification model is obtained by training and optimizing a pre-constructed neural network by using a training data set, the training data set trains the neural network to obtain an initial network, and the initial model is optimized by using a preset optimization target to obtain the intelligent identification model. According to the intelligent recognition model based on feature distribution robustness optimization, by optimizing feature distribution, automatically exploring and constructing an optimal and most robust feature space and introducing anti-noise classification loss, the problems of medical data imbalance, annotation noise and generalization in the prior art are solved.

The present application relates to the technical field of data processing, and more particularly to a data privacy protection and compliance use method and system, the present application is provided with data acquisition module, terminal pretreatment module, terminal analysis module and terminal identification module, the access offset tendency parameter of the access terminal is determined through the terminal pretreatment module, the feature access terminal is screened, the data access risk curve is constructed for a single feature access terminal based on the data imbalance tendency parameter through the terminal analysis module, whether the data isolation is carried out to the feature access terminal based on the risk representation coefficient of the feature access terminal through the terminal identification module, and then, the access terminal with abnormal risk is quickly identified according to the actual access characteristics of the access terminal, the data processing mode of the access terminal with abnormal risk is adaptively adjusted, and the processing efficiency and reliability of the data privacy protection and compliance use system are improved.

The application discloses a train axle temperature anomaly recognition method based on a generative adversarial network and ensemble learning, which comprises the following steps: collecting operation data in actual operation of an urban rail train, obtaining a two-class data set with unbalanced categories after preprocessing, and dividing the data set into a training set and a test set; training a constructor and a discriminator of the generative adversarial network by using abnormal data samples in the training set, and realizing automatic network parameter adjustment by using a Bayesian optimization algorithm; synthesizing abnormal samples by using the trained generative adversarial network model, and jointly constructing a training set with balanced categories with the original training set; filtering and screening noise samples by using a cross-committee filtering technology; constructing an axle temperature anomaly recognition classifier by using an AdaBoost method, training the ensemble learning model by using the training set, and inputting the test set to obtain a test result. The application solves the problems of missing of the axle temperature abnormal samples of the urban rail train and data imbalance, and improves the accuracy and correctness of the axle temperature anomaly recognition.

The invention belongs to but is not limited to the technical field of log anomaly detection, and discloses a log relationship anomaly detection system which fuses a large language model (LLM) and a dynamic graph neural network and has interpretable and diagnostic capabilities. The method comprises the following steps: collecting an original log stream from a distributed system, carrying out timestamp alignment, denoising and block preprocessing, carrying out field-level named entity recognition on a log template and parameters by adopting a pre-trained large language model, and generating deep semantic embedding; constructing a continuous time dynamic graph according to the log event, the field instance and the time relationship thereof, and supporting 0-hop, 1-hop and multi-hop relationship modeling; carrying out joint coding on a graph structure and time sequence dependence by fusing GCN and Set-Transform, relieving data imbalance by adopting category-guided Mixup and comparative learning, and outputting an edge-level abnormal score; and organizing the abnormal edge / subgraph and the related context into a structured Prompt, and calling LLM to generate natural language interpretation and root cause suggestions.

The invention discloses an urban residence land price evaluation method considering data imbalance and spatial heterogeneity. The method comprises the steps of collecting historical residence land sample data of a research area and performing spatial position matching; performing hierarchical index evaluation processing on the historical residential land sample data by using a multi-hierarchical index system, and performing fusion arrangement to obtain a residential hierarchical index land price data set; the land price evaluation combination model carries out model training of residence land price prediction by using a residence level index land price data set, and a differential evolution algorithm model DE dynamically searches a hyper-parameter combination of an XGBoost model and carries out optimization processing; and obtaining residential land multi-source data of the research block to obtain indexes of all levels, inputting the indexes into the land price evaluation combination model, and outputting and obtaining a residential land price evaluation prediction result. According to the method, the double problems of unbalanced sample price data and insufficient spatial heterogeneity identification are solved, high-precision urban residential land price evaluation is realized, and the accuracy and automation level of land price evaluation are improved.

The invention discloses a power servo knife rest health state assessment method based on an integrated multi-scale convolution attention network, and belongs to the technical field of power servo knife rest health state assessment, the method adopts a base classifier architecture of the multi-scale convolution attention network, and the base classifier architecture is composed of a multi-scale convolution noise reduction module and an attention enhancement module; the multi-scale convolution noise reduction module extracts rich discrimination features through a multi-scale kernel; the noise is further filtered through a soft threshold function, the attention enhancement module adopts a sparse improved channel attention mechanism to adaptively filter redundant features, important channel information is concerned, and the anti-noise performance and generalization of the model are improved; an interactive joint training strategy is adopted, a basic classifier automatically pays attention to a category with poorer classification through a designed Recall guide loss function, a balance training subset is constructed for each basic classifier, weighted voting is adopted to integrate the trained basic classifiers, and the robustness of an integrated model and the evaluation performance under data imbalance are improved.

This invention discloses a method for identifying lesion regions in gastrointestinal images based on a visual language model. It combines the cross-modal feature alignment capability of the visual language model, a medical semantic guidance mechanism, and a data imbalance handling strategy. By constructing a matching relationship between images and corresponding text categories, it achieves the identification of gastrointestinal lesions. This method introduces a bidirectional contrastive learning loss, enhancing the discriminative ability of different lesion categories while maintaining consistency between image features and text semantics. Furthermore, to address the uneven distribution of lesion categories in the training data, this invention introduces a category weighting mechanism and sampling strategy, allowing minority class samples to obtain higher weights or higher frequencies during training, effectively improving the identification accuracy and model stability of minority class lesions. During the inference stage, classification is completed by calculating the similarity between the image and all categories of text features, achieving the identification and classification of various gastrointestinal endoscopic images without the need for additional labeled data or complex training.

The invention discloses a femoral head necrosis prediction system and method based on Transform, and belongs to the technical field of image processing, the system comprises a data acquisition module, a data processing module, a data balancing module, a feature extraction module, a feature merging module and a necrosis classification module; the method comprises the following steps: acquiring preoperative hip joint CT data, pre-processing to unify specifications, adopting directional data enhancement to solve the problem of class imbalance, extracting features by virtue of Video Swin Transform, merging and modeling a spatial relationship through volume blocks, and finally outputting a necrosis classification result. According to the femoral head necrosis prediction system and method based on Transform provided by the invention, the prediction accuracy and robustness are effectively improved, the problem of model instability caused by strong subjectivity, hysteresis and data imbalance in the prior art is solved, an objective and efficient prediction tool is provided for clinic, and the risk of postoperative complications is reduced.

The invention discloses a power plant auxiliary machine fault early warning system and method based on vibration data imbalance learning. The system comprises an acquisition module, a segmentation module, a feature construction module, a learning module, a drift suppression module, a positioning module and an early warning module which are connected in sequence. The acquisition module acquires multi-axial vibration signals and working condition parameters in a precise clock synchronization mode and a self-adaptive sampling rate. The feature construction module generates two-dimensional image and graph structure features in parallel. And the learning module processes unbalanced data through a dual-channel heterogeneous model, and dynamically weights, fuses and outputs a fault probability. The drifting suppression module monitors data distribution drifting on line, and model self-evolution is achieved by confirming and incrementally updating a closed loop. And the positioning module queries a knowledge graph which can be dynamically updated, and maps the probability into a specific fault part. According to the method, the problems of high model missing report / false report rate and unexplainable early warning information caused by rare fault samples and working condition drifting are effectively solved, and accurate, self-adaptive and positionable early warning of the auxiliary engine fault is realized.

The invention discloses a medical image report generation method, system and device and a storage medium, and relates to the technical field of computer vision and natural language processing, and the method comprises the steps: constructing a causal graph model, taking an image as an input variable, taking a final report as an output variable, and taking a region-level pathological state in the image as an intermediary variable; the data imbalance factor is an unobservable hybrid factor; based on a causal graph model, intervening the intermediary variable by using a front door adjustment strategy, and establishing a causal path from visual evidence to report text; based on the intervened intermediary variable, executing a report generation process: a, identifying an abnormal region in the image by using a focus detection model and outputting a corresponding pathological discovery description; and b, inputting the intervened pathological discovery description and the original image into a visual language model to generate a complete clinical report by taking the intervened pathological discovery description and the original image as conditions. And the sensitivity of the model to pathological changes and the clinical reliability of report generation are improved.

The application discloses a digital power grid security situation awareness method and system based on a selective convolution network, relates to the technical field of asset security management and control, and comprises the following steps: collecting multi-element heterogeneous data of digital power grid operation by using a sensor and performing preprocessing; adopting a selective convolution network to perform multi-scale feature extraction on the preprocessed data; inputting the extracted multi-scale features into a secondary classification model to perform fault risk judgment and classification; and combining a time domain convolution network to perform time sequence modeling on the classification results and the multi-scale features, and predicting future operation situation and potential risks of the digital power grid. The application improves the selective convolution network and the selective time domain convolution network, solves the problems of insufficient multi-source heterogeneous data feature extraction capability, low classification precision caused by data imbalance and limited time sequence modeling capability, and achieves the effects of enhancing feature extraction precision, improving minority class sample recognition capability, optimizing complex time sequence feature modeling and situation prediction precision.

The invention relates to a data imbalance fault diagnosis method based on an improved GAN in the technical field of industrial equipment fault diagnosis. The method comprises the following steps: S1, data preparation and model improvement; s2, constructing a fault diagnosis model; and S3, experimental simulation verification. According to the method, original data distribution can be adaptively learned, new samples are generated to increase minority classes, and then an enhanced data set is applied to network training of a support vector machine, a multi-layer perceptron, a convolutional neural network, a residual neural network, a sparse auto-encoder and the like so as to carry out subsequent fault diagnosis.

The application relates to the technical field of data retrieval and fraud detection, and discloses a vehicle insurance data optimization retrieval method for a digital management platform, which comprises the following steps: acquiring vehicle insurance data, performing multi-view feature extraction, and constructing a unified feature space representation; generating high-quality fraud samples by using a conditional generative adversarial network to enhance model training; constructing a deep reconstruction network to amplify abnormal feature signals through reconstruction error; constructing a difference-sensitive hash index structure based on the features of the reconstruction error; comprehensively evaluating the retrieved suspected fraud samples by using a multi-view consistency verification method to output final fraud detection results; and generating high-quality fraud samples by using the conditional generative adversarial network, so that the problem of data imbalance caused by the scarcity of fraud samples is effectively solved, and the model generalization capability is improved.

The application relates to the technical field of data processing, and provides a hybrid internal threat detection method based on a DACGAN-Transformer, which solves the problems of data imbalance and lack of fine-grained analysis in internal threat detection. A generative adversarial network (GAN) is used to generate samples similar to normal data distribution but having abnormal characteristics, data set is enhanced, and abnormalities are preliminarily judged. A Transformer model is used for hierarchical feature extraction of log data. Abnormality detection includes single-log abnormality detection and context abnormality detection, and the fine granularity and accuracy of detection are improved. Finally, the overall abnormality score of the GAN and the hierarchical abnormality score of the Transformer are combined, a multilayer perceptron is used for comprehensive evaluation, and whether a log entry is abnormal is determined. The application effectively improves the precision of internal threat detection and the security of a system.

The invention discloses a model self-lifting method, system and equipment based on data weight balance and a medium, the method comprises the following steps: under each round of iteration, sampling a batch of queries for multiple times by using a current model to generate multiple pieces of reasoning trajectory data of each query, then screening out a correct trajectory from the multiple pieces of reasoning trajectory data, and carrying out self-lifting on the correct trajectory. The number of correct tracks of each query is obtained, and then the head and tail imbalance phenomenon is recognized based on the number of the correct tracks of each query; and when the head-tail imbalance phenomenon is identified, adjusting the data by adopting a weight balance strategy to obtain the data after weight balance processing, and finally carrying out self-lifting training on the model by adopting the data after weight balance processing as training data. By adopting the method, the data imbalance phenomenon of the visual reasoning model in self-lifting iteration can be relieved, the data quality and the utilization efficiency are improved, and the optimization of the self-lifting effect of the model is realized.

This disclosure provides a method, apparatus, network device, medium, and program product for predicting network element anomalies, relating to the field of wireless communication technology. The method includes: dividing collected network element operational data in the core network into normal indicator data and raw anomaly indicator data based on different indicator types; performing time-series-based forward noise addition processing on the raw anomaly indicator data to construct a noisy indicator sequence; fusing the corresponding normal indicator data and the noisy indicator sequence based on the time sequence to obtain a fused sequence; performing the inverse operation of forward noise addition processing on the fused sequence to obtain diffused anomaly indicator data; and constructing network element time-series data based on the normal indicator data and the diffused anomaly indicator data to train an anomaly prediction model. This technical solution effectively alleviates the network element data imbalance problem and improves the prediction model's ability to learn anomaly indicators and predict network element anomalies.

The invention relates to a confocal laser endoscope video redundancy removing and filtering method, device and system, and relates to the technical field of computers, and the method comprises the following steps: receiving an input confocal laser endoscope CLE video clip; a video clip is processed through a parallel multi-path feature coding architecture, wherein the architecture comprises a microscopic feature coding path, a macroscopic space-time coding path and a time sequence stability coding path; dynamically integrating the feature vectors output by the three paths to generate a fused feature vector; on the basis of the fusion feature vector, a weighted ordinal regression classifier is used for generating classification output, the classifier considers the sequence relation between diagnostic value levels and allocates weights for different categories to deal with the problem of data imbalance, and the classification result accurately corresponds to a predefined operator cognitive intention stage. According to the method, the technical problem that key diagnosis fragments in confocal laser endoscope videos cannot be accurately and efficiently screened due to the design of'literal blindness' and'single integrality 'in the prior art is solved.

The application discloses a ship navigation risk early warning method based on unbalanced offshore meteorological data enhancement, which firstly determines the ship navigation risk grade, and divides the unbalanced data set of target sea area meteorological disaster-causing elements corresponding thereto. Secondly, an adversarial learning model composed of a deep neural network generator and an evidence reasoning discriminator is designed to balance the unbalanced data set under different risk grades, and a Gaussian distribution model is established to describe the feature distribution of meteorological disaster-causing elements under different risk grades. Then, the risk grade reliability distribution of meteorological disaster-causing elements is calculated through the Gaussian distribution model. Finally, the weighted average method is adopted to fuse the risk grade reliability distribution, and the risk mode with the highest reliability after fusion is selected as the navigation risk grade of the current target sea area. The application can generate a small number of meteorological data conforming to the real distribution, effectively solve the data imbalance problem, and improve the extreme weather risk warning capability.