717 results about "Semi-supervised learning" patented technology

The invention relates to dialect speech synthesis, in particular to a semi-supervised dialect emotion speech synthesis system based on hybrid experts, which comprises a text analysis module for preprocessing an input dialect text and generating a text representation vector through feature extraction and feature fusion; the mixed expert module is used for acquiring dialect acoustic features, rhythm features, emotional features and general acoustic features; the dynamic routing module is used for realizing intelligent cooperation among experts through a task-aware soft routing algorithm; the semi-supervised learning module is used for training supervised learning by using the marked dialect emotion voice data and training self-supervised learning by using the unmarked dialect emotion voice data; the acoustic parameter generation module is used for integrating the output of each expert to generate a complete acoustic parameter set; the neural vocoder is used for converting the acoustic parameter set into final dialect emotion voice; the method can effectively overcome the defect that the dialect emotional voice is difficult to accurately synthesize under the condition of lack of sample resources.

The invention discloses a high-resolution remote sensing image accurate classification system and method based on deep learning multi-modal fusion, and the method comprises the steps: S1, carrying out the preprocessing and fusion optimization of multi-modal data; S1.1, carrying out the standardization and normalization: carrying out the standardization and normalization of remote sensing data of different modals, and eliminating the influence caused by the difference between the different modals, the difference between the resolution, the spectral range and the like; for optical images, contrast may be enhanced by histogram equalization. The method aims at solving the problems of data heterogeneity, calculation efficiency, over-fitting, difficulty in labeling, real-time performance, interpretability and the like in an existing method by adopting multi-modal data optimization preprocessing, deep fusion model design, automatic labeling and semi-supervised learning, a lightweight model and hardware acceleration technology and a strategy for enhancing interpretability. Through the optimization, the system can maintain high classification precision, improve the calculation efficiency, reduce manual intervention, enhance the transparency and generalization ability of the model, and meet the actual application requirements.

Disclosed is a method for establishing a 3D medical image segmentation model based on masked modeling and application thereof includes: establishing a semi-supervised learning network, wherein a student network includes an encoding module for extracting latent features and a segmentation decoder that predicts segmentation results, a teacher network includes an encoding module and a segmentation decoder that are structurally consistent with the student network; training the semi-supervised learning network, wherein during training, two random masking operations are performed on each image, and the image is input to the two networks respectively; optimizing and updating the weight of the student network, and transferring the updated weight to the teacher network, wherein the training loss function includes prototype representation loss, which is used to characterize the difference between the prototypes extracted and generated by the two networks; the student network may further include a reconstruction decoder and an auxiliary segmentation decoder.

The invention provides a cross-domain target detection method and system based on semi-supervised learning in extreme weather, and the method comprises the steps: enabling a student model to learn bounding box regression knowledge of a trained teacher model through distillation, so as to achieve the regression capability in extreme weather; performing instance-level feature adversarial training on a pre-training detection model which is obtained in a distillation stage and has a regression capability in extreme weather by using an intermediate-state image which is generated by a diffusion model and is closer to a target domain and has smaller noise, and determining a new teacher model and a new student model based on the detection model after the adversarial training; in the fine tuning stage, a dynamic category pseudo label screening strategy is utilized to screen pseudo labels generated by a new teacher model, and a screened target domain pseudo label is utilized to train a new student model to obtain a target detection model used for detecting a to-be-detected image in extreme weather. The phenomena of leak detection and error detection in extreme weather scenes in the prior art can be reduced, and the original reasoning speed is kept.

The invention relates to the technical field of printed circuit board assembly quality detection, and discloses a PCBA anomaly detection method and system based on three-dimensional modeling and AI fusion, and a medium. The method comprises the following steps: acquiring three-dimensional point cloud data of a PCBA board to be detected; generating a reference three-dimensional digital twin model according to a standard PCBA design drawing; carrying out spatial registration on the three-dimensional point cloud data and the reference three-dimensional digital twin model, obtaining the three-dimensional point cloud data, carrying out hierarchical processing on the obtained three-dimensional point cloud data, extracting geometric features of a welding spot region, contour features of an element region and surface features of a substrate region, and carrying out fusion to generate a feature vector group; constructing a generative adversarial model based on a preset semi-supervised learning framework and the normal PCBA sample vector group; and inputting the feature vector group into a generative adversarial model, and examining the abnormal vectors, the corresponding three-dimensional coordinates and the abnormal types in the feature vector group by the generative adversarial model to complete the abnormal detection of the PCBA board. The method is suitable for quality control of a high-density and miniaturized PCBA.

The invention discloses an industrial machine vision recognition and analysis system, relates to the technical field of machine vision recognition, and is used to solve the problem of poor industrial machine vision recognition. The invention combines total variation denoising, contrast-limited adaptive histogram equalization, random geometric transformation and other technologies to enhance image diversity, improve the system's generalization ability for images in different environments, extract image texture and edge features, provide high-quality data for subsequent analysis, use unsupervised learning to extract image potential features and patterns, and locate abnormal areas through template matching, so as to adaptively discover defects in the production process, dynamically update the model based on a small amount of labeled data, optimize feature representation in real time, and adapt to environmental changes. Finally, semi-supervised learning and pseudo-label generation technology are used to expand the training set, improve the generalization ability of the model, maintain efficient learning when labeled data is limited, reduce manual labeling costs, and improve the accuracy of automated quality inspection.

The invention discloses an industrial equipment intelligent control method and system, and the method comprises the following steps: S1, collecting and preprocessing equipment operation data, and constructing a state data set; s2, establishing a trend prediction model by adopting Gaussian process regression, and outputting a state prediction value; s3, constructing a graph structure representation model, and combining a graph convolutional network and a semi-supervised learning method to carry out joint training and identify a working condition category and an operation level; s4, based on the equipment operation data, calculating a fuzzy membership degree and a fuzzy entropy index, and generating an entropy distribution curve; s5, fusing the state prediction value, the working condition category, the operation grade and the fuzzy entropy index to generate a state evaluation result; s6, adjusting control strategy parameters according to a state evaluation result, and issuing a control instruction to an equipment control system; and S7, collecting feedback data, updating the state data set, and realizing closed-loop iterative optimization. The method has the advantages of accurate prediction, stable identification, flexible evaluation, fast control, self-learning and the like, and is suitable for complex and changeable industrial application scenes.

The invention discloses a semi-supervised medical image segmentation method based on uncertainty-driven dynamic correction and multi-scale consistency learning, and the method comprises the steps: carrying out the preprocessing of a medical image data set, and dividing the medical image data set into a training set and a test set; constructing a semi-supervised segmentation model of dynamic correction and multi-scale consistency learning based on uncertainty driving; inputting the training set into a semi-supervised segmentation model, and performing iterative training and parameter optimization to obtain a trained semi-supervised segmentation model; inputting the test set into the trained semi-supervised segmentation model to obtain a medical image segmentation result; wherein the semi-supervised segmentation model adopts a mean teacher model of a V-Net network, a prediction block is added behind each up-sampling block of a V-Net decoder, and a dropout layer is added; according to the method, the problems that the existing semi-supervised learning method is difficult to adapt to the complexity of annotated data and unannotated data distribution, so that effective information is lost; meanwhile, a traditional uncertainty estimation method needs multiple times of forward transmission, and the calculation cost is high.

The invention relates to a lithium ion battery health state estimation method based on semi-supervised learning, and the method comprises the steps: obtaining health factors in an original IC curve, and carrying out the preprocessing; constructing a data set based on the preprocessed health factors; wherein the data set comprises a marked sample data set and an unmarked sample data set; using the data set to train a semi-supervised Transform model, and obtaining a battery SOH prediction model; and performing lithium ion battery SOH estimation by using the battery SOH prediction model. According to the method, the effective information of the marked sample is fully mined by utilizing the advantages of the self-attention mechanism in the feature extraction of the time sequence data and the long-range dependence modeling method, the marking and utilization of the unmarked sample are realized through self iteration, and the precise prediction of the SOH of the lithium ion battery is realized.

The invention provides a semi-supervised image semantic segmentation method and system based on a visual basic model, and the method comprises the steps: constructing a multi-task model which comprises a visual basic model and a depth estimation basic model, and the visual basic model is connected with a task solution head, an adapter parameter efficient fine tuning module and a multi-modal cross fusion module; the task solution head comprises a semantic segmentation head and a depth estimation head; extracting semantic hierarchy features and a depth feature map of the RGB image, performing cross attention fusion on the semantic hierarchy features and the depth feature map, and inputting obtained fusion features into a semantic segmentation head and a depth estimation head respectively; semi-supervised learning is adopted to train a multi-task model, only parameters in the adapter parameter efficient fine tuning module and the multi-modal cross fusion module are trained, and a multi-task loss function is adopted. The image semantic segmentation model obtained through training can improve semantic segmentation performance, reduce training cost and is suitable for different tasks.

The invention discloses a tensor depth semi-supervised learning method for high-dimensional small sample data classification. The tensor depth semi-supervised learning method comprises the steps of preprocessing original high-dimensional small sample data; constructing a deep neural network comprising a feature extraction module and a classifier module; constructing a second-order similarity matrix and a third-order similarity tensor based on the low-dimensional embedding representation obtained by pre-training; combining the second-order similarity matrix and the third-order similarity tensor to construct an objective function containing multi-order smooth constraints; then, taking the low-dimensional embedded representation obtained by pre-training as input, performing iterative optimization on the target function by adopting a gradient descent algorithm through a label propagation network formed by a full connection layer, and generating a pseudo label; and inputting the original high-dimensional small sample data, the low-dimensional embedded features and the pseudo labels into the deep neural network, iteratively updating the network in a semi-supervised mode until convergence, and outputting a final prediction result. According to the method, more accurate label propagation is realized, and the semi-supervised classification precision is improved.

The invention discloses a learning achievement prediction method based on learning behavior data mining and a computer device. The method comprises the steps of collecting multi-dimensional learning behavior data of students, performing preprocessing and feature extraction, constructing a structured learning behavior feature set, then constructing a target machine learning model suitable for different prediction tasks, inputting structured learning behavior features of the students to be predicted into the model, and obtaining a continuous cumulative risk prediction curve; converting the cumulative risk prediction curve into discrete classification labels, and generating a classification prediction result with reserved time sequence characteristics; and expanding the structured learning behavior feature set by adopting a pseudo-label semi-supervised learning algorithm, iteratively training a target machine learning model, inputting the structured learning behavior features of a to-be-predicted student into the trained model to obtain a comprehensive prediction result, and generating a visual learning achievement prediction scheme according to a classification prediction result. The method can provide a comprehensive and accurate prediction result.

The invention discloses an ultra-high resolution remote sensing image semi-supervised change detection method based on pseudo label boundary quality improvement. The change detection aims to explore a change region of an image at a later moment compared with an image at a previous moment in a dual-time image; according to the method, semi-supervised learning guidance is enhanced through a high-quality pseudo tag, and the method comprises the following steps: 1, preparing a semi-supervised learning training data set; 2, building a teacher model and a student model; 3, starting training, reasoning data of the training data set by the student model, and generating corresponding rough and false labels by utilizing the teacher model; 4, refining the rough and false labels by using a boundary optimization method, and calculating the consistency loss of the labels and the reasoning result loss of the student model; 5, calculating the total loss, and updating the parameters of the student model and the teacher model; 6, finishing training, and performing change detection on the remote sensing double-time image by the student model; according to the method, the semi-supervised change detection performance which is limited by rough false label boundaries and cannot be further improved is improved.

The invention relates to the field of semantic tag generation, and discloses a semantic tag generation method based on semi-supervised learning, which comprises the following steps: collecting supervised data with tags and unlabeled data without tags, and extracting features generated by semantic tags from original data; training a supervised learning model by using the labeled data, and predicting the unlabeled data by using the trained model to generate a preliminary label; taking a preliminary label generated by the model as a pseudo label, adding the pseudo label into the unlabeled data, and jointly training the model by using the labeled data and the unlabeled data with the pseudo label; in each round of iteration, the labeled data and the unlabeled data with the high-confidence-coefficient false labels are trained together, the labels with the high confidence coefficient are used for label updating, and the false labels with the low confidence coefficient are removed; and predicting all data through the trained semi-supervised learning model to generate a final semantic tag. The method has the advantage of improving the accuracy of tag generation.

The invention provides a semi-supervised target detection method for a visible light-infrared multi-mode fusion scene. The method comprises the following steps: constructing a semi-supervised visible light-infrared multi-modal image data set based on an LLVIP data set; on the basis of a YOLOv11 model architecture, constructing a target detection model oriented to multi-modal image feature fusion, and training the target detection model by using a semi-supervised visible light-infrared multi-modal image data set in a deep learning end-to-end mode to obtain a trained target detection model; and inputting a to-be-detected multi-modal image into the trained target detection model, and outputting a target detection result of the to-be-detected multi-modal image by the trained target detection model. The method is based on a semi-supervised learning normal form, so that the precision and robustness of target detection in a multi-modal fusion scene are improved, and the requirements for high efficiency and reliability of target recognition in practical application scenes such as intelligent traffic and intelligent security and protection are met.

The invention relates to the technical field of industrial magnesium smelting intelligent control, and provides a semi-supervised learning and free threshold value-based electric smelting furnace working condition identification method, which comprises the following steps of: acquiring historical working conditions and video picture sample data of an electric smelting furnace, and dividing the historical working conditions and the video picture sample data into labeled data xa and unlabeled data xb; performing feature enhancement extraction on the preprocessed picture data by adopting a ViT feature extraction network based on a global channel space attention module; performing CNN model training of a time sequence-based dual-time fusion mechanism on the labeled feature extraction picture Xaout to obtain an initial model; sending the unlabeled image data Xbout into the initial model to predict the category probability, and generating a qualified pseudo-label data set by adopting a free threshold mechanism; and updating the training data set, carrying out model training again, calculating training loss, and carrying out iterative training continuously until the model performance meets a preset requirement. According to the method, the manual marking cost can be greatly reduced, and the working condition of the electric smelting magnesia furnace can be efficiently and accurately identified.

The invention relates to a power system network security threat monitoring and early warning method and device, power equipment, a computer readable storage medium and a program product, and belongs to the field of power system network security. The method comprises the following steps: acquiring historical data and real-time data; obtaining first network feature data based on historical data, performing unsupervised learning training on the initial detection model, and taking abnormal data as second network feature data; marking the second network feature data as third network feature data; marking the first network feature data to obtain fourth network feature data to perform self-supervised learning training on the model, and obtaining first network attack features to construct a network attack feature library; performing semi-supervised learning training on the model based on the first network feature data and the third network feature data to obtain a detection model, and updating a network attack feature library; and detecting real-time data based on the detection model and the network attack feature library. The method can improve the accuracy of power system network security threat monitoring and early warning.

The invention discloses a multi-stage loss optimization OCTA (Optical Coherence Tomography Angiography) image diagnosis method based on semi-supervised learning and knowledge distillation. The method comprises the following steps: (1) constructing a teacher-student model framework in combination with semi-supervised learning; (2) data set processing: randomly removing part of sample labels of the training set as label-free data; (3) training a teacher model by using the labeled data, then generating a pseudo label of non-labeled data through the teacher model, and only retaining a high-quality pseudo label meeting a confidence threshold; and (4) training a student model by using a multi-stage loss function, wherein the student model comprises supervision loss of label data, supervision loss of pseudo-label data and knowledge distillation loss. Dependence on annotation data is reduced through semi-supervised learning, the performance of the lightweight student model is improved through knowledge distillation, and the method is suitable for scenes with limited clinical resources.

The invention relates to the technical field of network space security, and provides a DoH malicious tunnel traffic detection method and system based on feature fusion, and the method comprises the steps: carrying out the preprocessing of obtained to-be-detected DoH traffic data, carrying out the sequence segmentation processing, obtaining a Token sequence, and extracting features based on a byte sequence feature extractor; statistical features are extracted and standardized, features are extracted through a statistical feature extraction sub-network, and statistical feature vectors are obtained; fusing the byte sequence feature vector with the statistical feature vector to obtain a classification result; the byte sequence feature extractor and the statistical feature extraction sub-network extract features, and training is carried out by adopting a semi-supervised learning framework of dynamic pseudo-tag screening for non-tag training samples. According to the method, multi-modal features are fused, a semi-supervised learning mechanism is introduced, malicious DoH traffic generated by multiple DNS tunnel tools is effectively identified under a limited annotation data set, and the detection precision and generalization ability are improved.

The invention belongs to but is not limited to the technical field of gearbox residual service life prediction, and discloses a gearbox residual service life prediction method based on multi-task semi-supervised learning, which comprises the following steps of: firstly, decomposing and reconstructing a preprocessed vibration signal by using an empirical mode decomposition technology, extracting sensitive features, and calculating the residual service life of a gearbox; and then carrying out dimensionality reduction on the sensitive features by using a kernel principal component analysis technology, taking a dimensionality reduction result as a gearbox health index, and then dividing a degradation stage of the gearbox based on a hidden Markov model and a dimensionality bit algorithm. And obtaining a residual service life prediction model training set by using the full-life-cycle gearbox data. And a multi-task semi-supervised residual service life prediction model is constructed and trained, and finally the residual service life of the gearbox is predicted through multiple times of iterative prediction. According to the method, multi-task learning and semi-supervised learning are fused and applied to prediction of the remaining service life of the gearbox, and higher prediction precision can be obtained.

The invention discloses a winter wheat LAI and SPAD estimation method based on a lightweight semi-supervised model, and relates to the technical field of agricultural remote sensing monitoring, and the method comprises the steps: obtaining multispectral image data of a winter wheat key growth period, and carrying out the preprocessing of the multispectral image data to generate a standardized multichannel vegetation index image; the method comprises the following steps: constructing a lightweight semi-supervised model MCVI-SANet, and carrying out self-supervised training on the MCVI-SANet by adopting a semi-supervised training strategy driven by VICReg; and inputting the multi-channel vegetation index image into the trained MCVI-SANet, and outputting quantitative estimation results of the LAI and SPAD of the winter wheat. Through combination of a saturation perception mechanism and semi-supervised learning, estimation deviation caused by dense canopy vegetation index saturation and data noise is effectively eliminated, and the estimation precision and generalization ability in a complex agricultural scene are improved while the lightweight deployment characteristic of the model is ensured.

The invention belongs to the field of geotechnical engineering, and provides a geotechnical engineering investigation data analysis method and system based on machine learning, and the method comprises the steps: obtaining geotechnical engineering investigation data; taking the sampling points as nodes of the rock-soil data graph; according to the spatial proximity relation and the geological similarity, determining edges of the rock-soil data graph, and endowing the edges with weights, so that nodes with similar spaces and similar geological characteristics are connected; carrying out sparse processing on the rock and soil data graph; performing weighted fusion according to the spatial distance weight and the geological similarity weight to form a final rock-soil data graph; a graph convolutional neural network is adopted, and the initial features and the adjacency relation of the nodes are used for information propagation; neighbor information of each node is aggregated through multi-layer graph convolution calculation, and node features are updated step by step; a semi-supervised learning or supervised learning method is adopted to train a GNN model, and prediction error minimization is taken as a target; and deducing rock and soil parameters of an unknown area through the trained GNN.

A dynamic adaptive learning method for mineral prediction includes: collecting a dataset including geological data and labels of the geological data; extracting features from the geological data, initializing parameters of a training model and optimizing the parameters to obtain training parameters; performing an associative training on the training model based on the training parameters and the labels in a dynamic adaptive learning framework to obtain a mineral prediction model, algorithms of the associative training including a variational expectation algorithm and a variational maximization algorithm, and the variational expectation algorithm including an unsupervised learning mode, a semi-supervised learning mode, and a fully supervised learning mode; and predicting, by using the mineral prediction model, a mineral to obtain a mineral prediction result. The method can break through limitations of the traditional machine learning technology, offering a more efficient, universal, and stable strategy for geophysical data analysis and mineral resource assessment.

The invention relates to an electric power inspection key target identification and tracking method comprising the following steps: S1, collecting an unmanned aerial vehicle inspection image of a distribution line, using SimCLR to carry out self-supervised feature learning, forming a basic feature platform, using a semi-supervised learning method to generate a pseudo tag, then carrying out artificial fine tuning, and carrying out tracking on the pseudo tag; s2, carrying out preprocessing on the labeled image data, wherein the preprocessing comprises image enhancement and denoising; s3, constructing a target recognition model based on Swin Transform, training based on the preprocessed image data, introducing multi-task learning, and optimizing target detection and mask branching at the same time; and S4, carrying the trained target detection and identification model on the unmanned aerial vehicle, detecting the target, and tracking the detected and identified key target based on the target tracking model. According to the invention, the processing capability of complex target identification and tracking tasks in electric power inspection is effectively improved.

The invention discloses a human body tumble detection method and device, and belongs to the technical field of human body tumble detection, and the method comprises the steps: obtaining a radar point cloud time sequence which comprises continuous frame point clouds of all parts of a human body within a set time; performing relative coordinate coding on each frame of point cloud in the radar point cloud time sequence to obtain a spliced feature vector time sequence; and inputting the spliced feature vector time sequence into a trained human body tumble detection model to obtain a human body tumble detection result, and training is semi-supervised learning training based on a dynamic threshold. Relative coordinate coding is realized through construction of a local coordinate system and coordinate conversion of the point cloud, dynamic enhancement of four-limb micro-motion features in the falling process is realized, a better classification effect is shown, and thus the detection accuracy is improved; through semi-supervised learning training based on a dynamic threshold value, the labeling requirement is greatly reduced, and high detection precision in a small amount of training data scene is also realized.

The invention discloses a combined entity relationship extraction method based on semi-supervised learning and a large language model. The system comprises three modules, namely a data enhancement module, a semi-supervised joint extraction module and a large-scale language model fine adjustment updating module. The data enhancement module (1) is used for implementing a double enhancement strategy on unmarked data, weak enhancement retains syntactic structures and topological features of entities and relationships, and strong enhancement adopts a large language model which is finely adjusted in advance to generate semantic equivalent disturbance; (2) a semi-supervised joint extraction module which obtains a preliminary extraction model through training of marked data, and then generates prediction on unmarked data based on the preliminary extraction model; (3) a large-scale language model fine-tuning updating module which realizes parameter-efficient large-scale language model fine-tuning by using low-rank self-adaption and dynamically adjusts through a semi-supervised extraction result; and (4) fusing prediction results of the three modules to obtain a final joint extraction model. According to the method, semi-supervised learning, a large language model and joint entity relation extraction are creatively combined, the problem of scarcity of artificial label data in the professional field of an existing joint entity relation extraction method is solved, more efficient information extraction is provided, and therefore the overall performance of a joint extraction model is improved.

The invention discloses a semi-supervised learning method based on a self-adaptive threshold value, belongs to the field of radio communication, and aims to extract general semantic features of signals through comparative learning so as to improve generalization of downstream modulation identification tasks. A self-adaptive threshold mechanism is introduced to generate a high-quality pseudo tag, and confirmation deviation is reduced through additional category information, so that the robustness of the model is improved; besides, a hierarchical encoder capable of learning Fourier filtering is designed to capture multi-scale semantic features of large-scale long-sequence signals, improve the calculation efficiency of a model and research and verify an algorithm based on a plurality of large-scale data sets, so that the accuracy of automatic modulation recognition is remarkably improved, and particularly, under the condition of less label data, the accuracy of automatic modulation recognition is greatly improved. Compared with a mainstream method, the method has higher generalization ability and robustness, and can effectively cope with signal diversity and noise interference in a real communication environment.

The invention relates to the technical field of medicine, and particularly discloses a semi-supervised medical image segmentation method based on an improved Transform, which designs a sphere embedded improved Transform module, constructs a boundary enhancement module based on morphological difference, and aims to improve the medical image segmentation performance. According to the method, a semi-supervised learning framework is adopted, and the dependence on a large-scale annotated data set is reduced by effectively utilizing limited annotated data and rich unannotated data, so that the accurate segmentation of the medical image is realized under the condition of limited resources. The method is expected to reduce the cost and time of data annotation while improving the segmentation precision, and brings a new breakthrough to the field of medical image segmentation.

The invention belongs to but is not limited to the technical field of industrial equipment anomaly detection, and discloses an equipment anomaly detection method based on a semi-supervised multi-scale convolutional auto-encoder and a generative adversarial network, which comprises the following steps of: performing model training by using part of marked data and a large amount of unmarked data, performing deep feature extraction by using a multi-scale convolutional neural network, and performing feature extraction by using the multi-scale convolutional neural network; meanwhile, as an encoder, an auto-encoder and a generative adversarial network are fused, the ability of the encoder to learn data features is indirectly improved through adversarial training of a decoder and a discriminator, and then fine adjustment is performed on a newly added classification layer of the encoder by using limited label information, so that the ability of the encoder to extract input data features is improved; and the model can better understand the classification boundary of the data, so that more accurate anomaly detection is realized. The whole model training adopts a two-stage training strategy of unsupervised pre-training and supervised fine tuning in semi-supervised learning, and finally an encoder is used as a classifier for equipment anomaly detection.

The invention relates to the technical field of remote sensing image processing, in particular to an intelligent landslide identification method based on deep learning of a multi-source remote sensing image, which comprises the following steps of: firstly, acquiring high-resolution optical and radar data of the multi-source remote sensing image by adopting a spatio-temporal data expansion method; the problem that an existing landslide identification method is insufficient in data type and data quantity is effectively solved, more comprehensive and accurate landslide data are provided, the generalization ability of the model is enhanced, then a deep learning model with semi-supervised learning and adaptive convolution multi-scale feature fusion is adopted, the size of a convolution kernel can be dynamically adjusted, and the robustness of the landslide identification method is improved. Landslide features of different scales are accurately captured, understanding of landslide morphology and structure is enhanced, robustness of the model in a complex terrain is improved, finally, a landslide boundary and morphology are corrected through a positioning correction method, inaccurate or discontinuous boundaries caused by prediction errors are eliminated, and stability of the model in a complex environment is further improved.