171results about How to "Improve feature extraction" patented technology

The invention discloses a lightweight semantic segmentation network and method for power grid inspection, and the method comprises the steps: employing an encoder-decoder architecture, inputting original data into a lightweight MobileNet v2 backbone network for feature extraction at an encoder part, inputting an obtained feature map into a lightweight large-scale ASPP module, and carrying out the feature extraction; further performing multi-scale feature extraction on the high-dimensional feature map; and in the decoder part, high-dimensional features and low-dimensional features obtained by the backbone network are respectively input into a cross attention wavelet fusion module, after an obtained feature map is fused with the output of a decoder, the feature map is recovered to the size of original data through down-sampling operation by a full-dimensional dynamic convolution post-processing module, and a final prediction mask is obtained. According to the invention, by optimizing a coding and decoding structure, the receptive field of the model and the modeling capability of a narrow and long target are improved, the balance between the precision and the complexity can be effectively realized, and the method is suitable for an unmanned aerial vehicle inspection system with limited resources.

The invention discloses a brain tumor MRI image segmentation model and method based on an improved Swin UNETR network, and belongs to the technical field of image segmentation. The brain tumor MRI image segmentation model is obtained by improving a Swin UNETR as a baseline model and comprises an encoder, a jump connection and a decoder, the decoder comprises a plurality of convolution fusion modules and an attention mechanism module, feature information of different levels is fused in the decoder by using the plurality of convolution fusion modules, and the attention mechanism module is used for identifying the feature information of the different levels of the feature information of the different levels of the feature information of the different levels of the feature information of the different levels of the feature information of the different levels of the convolution fusion modules. And the attention mechanism module is used to focus the feature information obtained by the plurality of convolutions. By adopting the scheme of the invention, the problem that the existing medical image segmentation technology based on deep learning is insufficient in brain tumor MRI image segmentation precision and is difficult to realize accurate segmentation especially in the face of different types of tumors and variability can be effectively solved, the calculation amount is small, and the image segmentation efficiency can be effectively improved.

The invention discloses a 6D pose estimation method and system based on an RGBD camera, and relates to the technical field of computer vision processing. Calibrating camera parameters based on the calibrated camera imaging; reconstructing a three-dimensional model and constructing a data set; segmenting the target object and calculating the actual size based on the three-dimensional model and the data set; establishing a 6D pose estimation network model based on the three-dimensional model and the data set; and performing pose estimation based on the actual size. The method has the advantages that the accuracy of 6D pose estimation is remarkably improved by combining the RGB image, the depth image and the point cloud data, object region segmentation is performed by using the SAM model, the actual size of the object is visually calculated by combining the depth information and the point cloud data, the precision of size estimation is improved, and the method is suitable for popularization and application. The introduction of depth information enables the pose estimation system to have better adaptability to objects with different sizes, shapes and surface features, and improves the robustness and accuracy of the system.

The invention provides a high-resolution remote sensing image semantic segmentation method based on multi-scale depth supervision, and the method comprises the following steps: 1, obtaining an ISPRS Potsdam data set and a Vaihingen data set; 2, building a multi-scale deep supervision network MDSNet, wherein the multi-scale deep supervision network MDSNet comprises a spatial branch network, a semantic branch network and a multi-scale feature aggregation part; each of the spatial branch, the semantic branch network and the multi-scale feature aggregation part is of a four-layer structure; step 3, inputting the training set into a multi-scale deep supervised network MDSNet for training, calculating a loss function and performing back propagation, updating network parameters, and obtaining a trained parameter model; and step 4, inputting the test set into the trained parameter model, and outputting a segmentation image of the target image. According to the method provided by the invention, the feature extraction capability is improved, and meanwhile, the semantic segmentation accuracy, the training efficiency and the stability are improved.

The invention provides a time sequence prediction method and system for a KAN enabling graph attention parallel loop network, and relates to the technical field of time sequence prediction, and the method comprises the steps: obtaining time sequence input data; inputting the time sequence input data into a feature extraction layer based on fast Fourier transform and discrete wavelet transform, and preprocessing the time sequence input data by the feature extraction layer to obtain spliced feature extraction data; inputting the spliced feature extraction data into a feature aggregation layer of graph attention based on KAN, and preprocessing the spliced feature extraction data by the feature aggregation layer to obtain feature aggregation data; and inputting the feature aggregation data into a time sequence prediction model of the parallel gating circulation unit network based on KAN and attention, and outputting time sequence prediction data by the time sequence prediction model. According to the method, the calculation complexity of time sequence prediction is reduced, and the time sequence prediction efficiency and accuracy are improved.

The invention relates to the technical field of light source control, and discloses a multispectral LED detection light source synchronous control method, device and equipment and a storage medium. The method comprises the following steps: carrying out double-interlaced spectral data sampling on a light source, and carrying out baseline extraction and compensation correction on preset three-dimensional spectral parameters; mapping of multi-dimensional mixed domain time sequence characteristics and decomposition of working characteristic tensors are carried out on the corrected calibration spectrum data, and modulation of recursive phases and group delay compensation calculation are carried out; performing crosstalk compensation of a multi-stage LED light source channel and suppression reconstruction of a multi-harmonic component on the light source phase compensation vector subjected to compensation calculation to generate light source correction control data; and performing light source driving signal synthesis on the light source correction control data to obtain a light source driving waveform sequence, and performing light source channel distribution and synchronous adjustment on the light source driving waveform sequence to generate a light source synchronous control result of the target multispectral LED detection light source. According to the invention, high-precision synchronous control of the multispectral LED detection light source is realized.

The invention discloses a rainy day target detection method based on paired image data generation and knowledge distillation, and belongs to the technical field of automatic driving target detection. The method comprises the following steps: acquiring a real image of a road scene and a semantic segmentation mask; inputting the semantic segmentation mask and the weather condition text information into a trained improved diffusion model to obtain a road scene generation image under a rainy day condition; introducing a CoT module and an ODConv module into the target detection model for optimization, and then improving the target detection model by adopting a dynamic weighted aggregation loss function to obtain an optimized target detection model; performing knowledge distillation to obtain a rainy day target detection enhancement model; and performing target detection by using the rainy day target detection enhancement model. The method provided by the invention is excellent in performance in a rainy day scene, has good generalization ability, can provide higher-precision target detection in various complex scenes, and effectively improves the detection accuracy and stability.

The invention belongs to the technical field of medical image processing, and particularly relates to a double-encoder semi-supervised heart MRI double-ventricle segmentation method based on improved SAM. A teacher model and a student model which are used both comprise double encoders, prompt encoders and mask decoders, each double encoder comprises a ViT branch and a CNN-Mama branch which are parallel, parameter fine tuning of the ViT branch is realized through a position adapter and a feature adapter, the CNN-Mama branch mainly comprises a convolution fusion Mama block and a second-order dimension attention block, and the CNN-Mama branch is used for realizing fine tuning of parameters of the CNN-Mama block. The convolution fusion Mama block introduces an enhanced convolution block on the basis of a VSS block, and the second-order dimension attention block uses a covariance matrix to mine second-order statistical information of data; carrying out weighted summation on the output features of the ViT branch and the CNN-Mama branch to obtain the output features of the double encoders; the output features of the double-encoder and the prompt encoder are input into a mask decoder to be decoded, and a segmentation result is obtained; and performing joint training on the teacher model and the student model based on interpolation consistency regularization semi-supervision, and using the trained student model as a segmentation model for double-ventricle segmentation of heart MRI. The segmentation model has strong feature extraction capability, can effectively extract the edge information of the ventricles and the boundary information of the double-ventricle connection region, and improves the segmentation precision.

The invention relates to the technical field of American ginseng quality evaluation, and discloses an American ginseng quality evaluation method based on multi-task deep learning, a computer readable storage medium and a computer program product. The method comprises the following steps: collecting near infrared spectrum data of each American ginseng sample; determining the ginsenoside content of each American ginseng sample to obtain label data of each American ginseng sample; according to the collected near infrared spectrum data and the obtained label data, constructing and training an American ginseng quality detection model; according to the constructed American ginseng quality detection model, producing area tracing and ginsenoside content prediction are carried out on American ginseng to be evaluated. According to the method, the improved multi-task deep neural network is constructed, so that the feature extraction capability is improved, nondestructive origin traceability and total ginsenoside content prediction of American ginseng can be realized at the same time, the detection accuracy and efficiency are improved, and the defects of a traditional method in the aspects of real-time performance and nondestructive detection are overcome.

The invention relates to the technical field of composite material damage detection, and particularly discloses a composite material damage intelligent detection and modeling method based on ultrasonic point cloud and deep learning, and the method comprises the steps: S1, data collection, S2, ultrasonic data processing, S3, simulation model construction, S4, PVT-RCNN model processing, S5, RI CP processing, and S6, damage model generation. According to the method, an ultrasonic point cloud data acquisition platform and a data processing method are designed, a sufficient composite laminate ultrasonic point cloud data set with obvious features is constructed, a PVT-RCNN model which is based on PV-RCNN and is improved by Swi n Transformer is designed, the feature extraction capability of the model on point cloud is improved, three-dimensional space information of damage is intelligently obtained, and the accuracy of the damage is improved. An RI CP registration algorithm and a damage model generation method are designed, a finite element model with damage is directly generated according to damage point cloud, and the material performance can be obtained through calculation.

The invention discloses a credible medical image segmentation method and equipment based on evidence uncertainty progressive guidance. The method comprises the following steps: S1, obtaining a training sample and a corresponding label; s2, training a credible medical image segmentation model according to the training samples and the corresponding labels; s3, acquiring a test sample; s4, inputting a test sample into the trained credible medical image segmentation model for prediction, calculating parameters of Dirichlet distribution, and calculating an expected tensor of the Dirichlet distribution; s5, calculating a segmentation evidence uncertainty matrix; s6, enabling the category with the maximum category probability to be a prediction category, and enabling a prediction segmentation result output by the credible medical image segmentation model based on the test sample to be predictioni = argmax pi; and S7, the prediction segmentation result of the test sample and the segmentation evidence uncertainty matrix are visualized. According to the method, the segmentation precision is improved, the calculation cost is greatly reduced, and more accurate uncertainty estimation is provided.

The invention provides a double-path medical image segmentation method and device based on multistage comprehensive attention, and relates to the technical field of medical images. The method comprises the following steps: acquiring to-be-segmented medical image data, and inputting the to-be-segmented medical image data into a constructed comprehensive attention converter to obtain a medical image segmentation result; the comprehensive attention converter comprises a dual-path encoder, a first mixed attention converter module and a decoder; the encoder comprises a plurality of layers; the decoder comprises a multi-scale feature fusion decoder and a multi-scale aggregation module; the multi-scale feature fusion decoder comprises a channel-based efficient feature fusion module and a comprehensive attention module; the channel-based efficient feature fusion module comprises a multi-channel connectivity extraction module and a channel-level feature fusion module; the comprehensive attention module comprises an enhanced converter module, a channel attention module, a space attention module and a convolution block; the multi-scale aggregation module includes a second hybrid attention converter module and a multi-layer prediction link. And the feature extraction performance is improved.

The invention discloses a wafer detection model training method, a wafer detection method, a wafer detection system, wafer detection equipment and a medium, and the method comprises the steps: obtaining a wafer surface defect image set, carrying out the category marking of the wafer surface defect image set, constructing a wafer defect detection data set, constructing an improved RT-DETR model, and carrying out the training of the improved RT-DETR model according to the wafer defect detection data set. Training the to-be-detected image of the wafer until the training is finished to obtain a wafer detection model, inputting the to-be-detected image of the wafer into a pre-trained wafer detection model, outputting a detection result of the to-be-detected image of the wafer, outputting a defect probability and a mark of the to-be-detected image of the wafer, and obtaining the defect probability of the to-be-detected image of the wafer through an improved RT-DERT model. The detection performance on small particles, slender scratches and the like is effectively improved.

The invention discloses a remote sensing image target recognition method and system based on a visual language model, and relates to the technical field of image recognition. The method comprises the following steps: constructing an initial image detection model based on a real-time open vocabulary detector YOLO-World and a remote sensing visual language basic model RemoteCLIP; adding a double-attention fusion encoder and a multi-level text guide fusion decoder on the initial image detection model to obtain a target image detection model; performing knowledge self-adaptive adjustment and optimization on the basis of the pre-training weight of the target image detection model to obtain a final image target recognition model; and performing target identification on the remote sensing image based on the image target identification model. According to the method, a powerful visual language model is introduced, and an image feature extraction and target classification strategy is optimized, so that the accuracy and efficiency of target recognition in the remote sensing image are improved.

The invention discloses a power equipment detection method and system, and relates to the technical field of power equipment detection, and the method comprises the steps: inputting a power equipment image into a trained enhanced target detection model; the trained enhanced target detection model comprises a backbone network, a neck network and a head network; performing multi-level feature extraction enhancement on the power equipment image through the backbone network to generate a low-level feature, a middle-level feature and a high-level feature; inputting the low-layer features, the middle-layer features and the high-layer features into a neck network for feature pyramid fusion, and outputting a plurality of fusion features; and respectively detecting each fusion feature by using a head network, adding elements one by one, and determining a detection result of the power equipment. The electrical equipment image is detected through the enhanced target detection model with an improved structure, so that the feature extraction capability is enhanced, the interaction of multi-scale information is realized, the accuracy and robustness of target detection are improved, and the detection reliability of the electrical equipment is improved.

The invention provides a transformer substation secondary circuit intelligent identification method based on multi-scale large-kernel attention YOLOV8, aiming at the requirements of the transformer substation secondary circuit intelligent identification field on identification accuracy and model lightweight in a small sample environment, and the transformer substation secondary circuit intelligent identification method comprises the following steps: carrying out data enhancement and label labeling on original drawing data; a YOLOV8 based on transfer learning is adopted as a backbone network of a model, pre-training and fine tuning are carried out on a large-scale data set, MAB is introduced, an MLKA module is designed based on a large kernel structure and a multi-scale gating mechanism, the gating mechanism and space attention are combined to propose a GSAU, a training set is input into an MLKA-YOLO network model for training learning, and an MLKA-YOLO network model is constructed. After training is completed, a test set is input to carry out secondary circuit terminal strip identification, based on a Paddle OCR framework, line name identification of the terminal strip is realized by using a cyclic convolutional neural network, and a line information comparison library is constructed by using the identified line content.

The invention provides a point cloud semantic segmentation method for improving a RandLA-Net network. The method comprises the following steps: step 1, carrying out data preprocessing grid downsampling; step 2, calculating a point cloud normal vector by a local curved surface fitting method; thirdly, local multi-dimensional feature fusion is carried out, and local geometric information is captured; fourthly, important features are automatically learned and aggregated through a self-attention module and attention pooling; 5, cascading an up-sampling result with the intermediate feature of the coding layer through jump connection; and 6, predicting the semantic tag by using a full connection layer. According to the invention, high-precision and high-efficiency automatic point cloud semantic segmentation in a large-scale outdoor scene is realized.

The invention relates to a machine tool thermal error modeling method based on a time convolution network and transfer learning, which comprises the following steps: data acquisition: providing a network based on an encoder-decoder architecture based on the time convolution network, inputting the acquired data of source (sufficient) and target (few) machine tools into an encoder, and carrying out data processing on the encoder; the method comprises the following steps of: coding and decoding to output a reconstruction sequence, and adding a reconstruction loss function which is calculated by the reconstruction sequence output by a decoder on a loss function with only one predicted value, so that deep features in thermal error data can be extracted through the architecture, and the prediction precision is improved; in order to achieve enough prediction precision on another target machine tool, transfer learning is used to obtain a loss function adapted to a field, the loss functions are summarized, iterative updating is repeated until deep learning regression algorithm training is completed, and accurate prediction of the thermal error value on the target machine tool is realized.

The invention discloses a water quality prediction method based on double decomposition and a hybrid model and a related device, and relates to the technical field of water quality monitoring, and the method comprises the following steps: preprocessing obtained original water quality time sequence data; determining to-be-processed data based on a Pearson's correlation coefficient method and the preprocessed data; performing complete ensemble empirical mode decomposition on the to-be-processed data to obtain a plurality of intrinsic mode functions; k-means clustering is carried out on the plurality of intrinsic mode functions; the clustered intrinsic mode function comprises a high-frequency mode, an intermediate-frequency mode and a low-frequency mode; variational mode decomposition is carried out on a high-frequency mode in the clustered intrinsic mode function, and a plurality of high-frequency sub-modes are obtained; and respectively inputting the plurality of high-frequency sub-modes, the plurality of intermediate-frequency modes and the plurality of low-frequency modes into the Parallel Transform-LSTM model to obtain a final prediction result. The precision and stability of water quality parameter prediction can be improved.

The invention discloses a gas outburst monitoring and early warning method and system based on an improved ConvLSTM model, and relates to the technical field of gas monitoring, and the key points of the technical scheme are that the method comprises the following steps: constructing a mine gas data set; cleaning the gas data set, converting unstructured data into structured data, and performing data cleaning, denoising and standardization on the structured data; performing high-order derived feature extraction on the preprocessed gas data set; an improved ConvLSTM model is constructed; using a historical gas data set to train the improved ConvLSTM model; identifying a potential gas high-risk area; based on an analysis result of the improved ConvLSTM model, identifying a potential gas outburst ignition risk area; and constructing a monitoring platform. By improving the ConvLSTM model, efficient collection and processing of gas data are achieved, monitoring accuracy and real-time performance are improved, and powerful support is provided for mine safety management.

The invention discloses a lane line detection method based on a learnable line anchor and a KAN network detection head. Firstly, a trunk image feature extraction model is used for carrying out multi-stage feature extraction on an input lane line image; in the first several stages, focusing on line anchor learning and adjustment, performing line anchor pooling on a feature map output by the main image feature extraction model by using a predefined line anchor, generating a preliminary prediction result of a lane line by using a detection head based on a KAN network, and adjusting the position of the line anchor so as to perform line anchor pooling on the feature map in the next stage; and the pooling result of the previous stage is used as global information for fusion. And after repeating for multiple times, carrying out line anchor pooling on the feature map of the last stage by utilizing the adjusted line anchor, and outputting a final lane line prediction result. And in the training process of the model, the segmented intersection-union ratio is put forward as a part of loss calculation, so that model learning is more effectively supervised. The method can improve the speed and precision of lane line detection.

The invention provides an infrared weak and small target detection method and system, electronic equipment and a storage medium, and belongs to the technical field of target detection, and the method comprises the steps: improving a YOLOv8 model for the features of an infrared weak and small target image; and performing target detection on the infrared weak and small target image by using the improved YOLOv8 model. According to the invention, a stronger infrared weak and small target detection capability is provided for the YOLOv8 model, and the problem of target detection precision bottleneck of a traditional model in a complex scene is effectively solved.

The invention provides a multifunctional self-assembly peptide recognition method and system, and relates to the technical field of biological peptide recognition. The method comprises the following steps: firstly, obtaining peptide sequences of a self-assembled peptide and a plurality of biological functional peptides, and inputting the peptide sequences into an embedded layer of a polypeptide function prediction model for 21-dimensional vectorization; and learning combination modes and sequence features of amino acids through an amino acid association feature extraction layer of the LSTM network. Then, acquiring direct contact information among different amino acids on the basis of a fine-grained feature learning layer of a multi-head self-attention mechanism; and finally, designing a Transform multi-task classifier which comprises five sub-task classifiers which are used for respectively predicting the self-assembly function, the anti-cancer function, the anti-inflammatory function, the antibacterial function and the antioxidant function. According to the method, a multi-layer structure is adopted to carry out layer-by-layer deep learning and optimization on polypeptide sequence features, efficient recognition and classification of multifunctional biological peptides are achieved, and finally the model performance is comprehensively evaluated through the accuracy rate, the precision rate, the recall rate and the F1 value.

The invention discloses a medicine bottle defect detection method and system based on machine vision and deep learning, belongs to the technical field of defect detection, and solves the problems that a twin defect classification network is sensitive to a highlight area caused by light reflection in appearance image information and the defect detection accuracy of the twin defect classification network is interfered in the existing method. The method comprises the following steps: constructing a defect detection model based on deep learning in combination with a YOLOV5 model, carrying out conjoint analysis detection on a time sequence image set by the defect detection model in combination with a medicine bottle simulation model, carrying out defect identification on the time sequence image set by the defect detection model, positioning a medicine bottle defect area, and carrying out defect detection on the medicine bottle. Classifying and marking defect types of the defect areas of the medicine bottles in a short circuit and random vector machine combined mode; according to the invention, the mean filter is introduced into the defect detection model, so that background filtering can be carried out on the image acquired under machine vision under the condition of light reflection of the medicine bottle, effective information of a small-size target image is effectively reserved, and the defect classification and recognition accuracy is ensured.

The invention belongs to the technical field of image processing, and provides a small-target lightweight substation equipment defect detection method and system, and the method comprises the steps: obtaining a substation equipment image; according to the acquired image and a preset small target lightweight defect detection model, completing defect detection of the substation equipment; wherein the preset small target lightweight defect detection model adopts a YOLOv8 target detection network which adopts an Officient Former V2 and a separation convolution attention mechanism as a backbone network, adopts scale time sequence feature fusion as a neck network and adopts a prediction head network of a shared convolution lightweight detection head, and image features are extracted based on the backbone network; obtaining feature maps of different scales; the neck network performs feature fusion on the feature maps with different scales to obtain a multi-scale feature map; and detecting the multi-scale feature map through the shared convolutional lightweight detection head, and performing defect positioning of the equipment image to complete defect detection of the substation equipment.

The invention discloses a lightweight water ship target detection method in a complex navigation environment, and the method comprises the following steps: obtaining a picture of a to-be-detected water ship, and forming a data set; dividing the data set into a training set and a test set; based on the improved YOLOv8 network, an enhanced and lightweight ship detection model is constructed; based on the training set data, training the enhanced and lightweight ship detection model to obtain a trained enhanced and lightweight ship detection model; according to the method, data of a test set is input into a trained enhanced and lightweight ship detection model, detection of a water ship target in a complex navigation environment is realized, a GELAN module is combined with an original PANet network, a more efficient and lightweight neck network is designed, and more efficient feature fusion is realized. In addition, an MPDIOU loss function is used to optimize a model gradient gain distribution strategy, so that the network can be converged more quickly.

The invention discloses a COD (Chemical Oxygen Demand) prediction method based on a two-channel convolution time sequence mechanism, which comprises the following steps of: acquiring COD original data for preprocessing to obtain COD input characteristics; constructing a prediction model, and importing data into a dual-channel convolution module; importing the first double-channel convolution output feature vector and the second double-channel convolution output feature vector into a double attention memory network to obtain a time sequence dependence feature; the time sequence dependence characteristics are imported into an output module, and predicted COD output is obtained; training the model, and in the training process, optimizing hyper-parameters of the model based on an improved pelican algorithm; and importing real-time COD original data into the trained model, and obtaining real-time COD output. According to the method, a high-efficiency effluent COD content prediction model of the sewage treatment plant is constructed by creatively fusing the two-channel convolution and the double-attention memory network.

The invention discloses a cardiac ultrasound image segmentation method based on a UCT-UNet model, and relates to the technical field of image segmentation, a Transform module is fused on a unit layer of an encoder, and detail information is captured by using global characteristics of Transform and local characteristic advantages of convolution. In the decoder stage, a Transform block (UCTBlock) is guided through uncertainty to focus on uncertainty estimation to guide a model to pay attention to an area which is difficult to accurately segment by the CNN, so that a global dependency relationship is established, and functional overlapping of local features and global information is reduced. The method effectively avoids the wrong segmentation of the complex structure by the model, improves the feature fusion, and improves the segmentation accuracy. Besides, by adding a feature extraction module FEM in each jump connection, the feature extraction capability is enhanced, the output quality of the model is further improved, and finally the segmentation performance of the cardiac ultrasound image is improved.

The invention discloses a digital power grid security situation awareness method and system based on a selective convolutional network, and relates to the technical field of asset security management and control, and the method comprises the steps: collecting the multivariate heterogeneous data of the operation of a digital power grid through a sensor, and carrying out the preprocessing; performing multi-scale feature extraction on the preprocessed data by adopting a selective convolutional network; inputting the extracted multi-scale features into a secondary classification model for fault risk judgment and classification; and performing time sequence modeling on the classification result and the multi-scale features in combination with a time domain convolutional network, and predicting the future operation situation and potential risk of the digital power grid. According to the method, the selective convolutional network and the selective time domain convolutional network are improved, so that the problems of low classification precision and limited time sequence modeling capability caused by insufficient multi-source heterogeneous data feature extraction capability and data imbalance are technically solved; the method achieves the effects of enhancing the feature extraction precision, improving the minority class sample recognition capability, and optimizing the complex time sequence feature modeling and situation prediction precision.

The invention discloses a judicial case judgment and prediction method and system and a medium. Relates to the technical field of natural language processing. According to the scheme, the method is improved on the basis of the traditional prediction technology, the fact description feature representation model for extracting the fact description part is obtained based on the judicial judgment document and the content, the content and structural integrity of the judicial judgment document is guaranteed to the maximum extent, the text length is reduced, and the prediction efficiency is improved. On the other hand, a fact description feature representation model fitting a real case judgment scene is constructed based on an xsBert model and a BiGRU model, and the fact description feature representation is mapped to criminal names and law articles by a full connection layer, so that the judgment prediction problem of a plurality of criminal names and law articles is solved.