27469 results about "Deep learning" patented technology

An AI-based Cybersecurity System and Method enable real-time detection, analysis, and mitigation of cyber threats within computing networks using adaptive artificial intelligence. The system continuously monitors network traffic, extracts behavioral and contextual attributes, and applies deep learning-based inference to identify anomalous activities indicating security breaches. The method integrates several computational units, including a network monitoring unit, feature extraction unit, artificial intelligence processor, contextual reasoning processor, and decision synthesis unit, to compute a composite risk index quantifying threat likelihood and severity. A classification processor categorizes detected threats into types such as ransomware, phishing, or unauthorized access, while a mitigation control processor initiates automated response actions to isolate compromised nodes and restore network integrity. An adaptive learning processor updates AI models using feedback from confirmed incidents. This provides a scalable, self-evolving cybersecurity framework that minimizes human intervention and enhances resilience against dynamic and zero-day threats.

Systems and methods for protecting and fortifying machine learning engines, artificial intelligence (AI) engines, large language models, deep learning engines, reinforcement learning engines, and AI-based agentic units. An Offline Protection Unit analyzes characteristics of a Protected Engine, and performs offline fortification of the Protected Engine against attacks; by changing operational properties or operational parameters of the Protected Engine to reduce its vulnerability to attacks. An Online Protection Unit performs analysis of at least one of: (i) inputs that are intended to be inputs of the Protected Engine, (ii) outputs that are generated by the Protected Engine; and based on the analysis, dynamically performs online fortification of the Protected Engine against attacks; by dynamically changing operational properties or operational parameters of the Protected Engine to reduce its vulnerability to attacks.

The invention discloses a building ground real-time settlement monitoring device and a use method thereof, and belongs to the field of building structure safety monitoring. The monitoring device comprises a hierarchical sensor network which is used for carrying out multi-time-scale real-time data acquisition and comprehensively obtaining deformation data and related environmental parameters of a building structure; the data processing and analyzing module is used for performing real-time processing and intelligent analysis on the acquired data, and identifying and classifying abnormal deformation characteristics of the building structure in time; the deep learning prediction module is used for quantitatively predicting the probability state and the evolution trend of building settlement by constructing a multi-scale time sequence prediction model; the multi-factor analysis module is used for carrying out coupling modeling and comprehensive analysis on the environmental factors, the structural characteristics and the abnormal evolution process so as to identify key influence factors and action mechanisms thereof; and the risk assessment and early warning module is used for performing grading assessment on the building settlement risk based on the prediction and analysis result and generating corresponding early warning information and decision support schemes.

The invention relates to the technical field of building construction, in particular to a building construction safety intelligent early warning system based on multi-sensor fusion and deep learning. Comprising a multi-source sensing unit; an intelligent fusion unit; a depth analysis unit; and a dynamic response unit. According to the method, through a mixed deep learning model, personnel-equipment-environment space association in a 1m * 1m * 0.5 m space grid is extracted through an improved U-Net network, and a space risk association map is output; modeling data of 10 sampling periods by using a bidirectional LSTM network, and outputting a short-term prediction value; and carrying out weighted fusion through an attention mechanism to form a risk feature vector, and removing invalid anomalies in cooperation with parameter anomaly judgment and cross validation. And then a risk grade evaluation module introduces multiple coefficients to calculate a risk grade index, and a grid diffusion range is delimited according to grades, so that real-time identification, quantitative evaluation and range pre-judgment of construction safety risks are realized, and the problem that risk identification evaluation lacks scenarized accuracy and comprehensiveness is solved.

The invention discloses a defect repair method based on digital twinning and friction stir welding technologies, and relates to the technical field of intelligent manufacturing and digital twinning, and the defect repair method comprises the following steps: synchronously capturing full-dimensional data of a welding area through a multi-mode sensor array integrated by an actuator; secondly, segmenting defect boundaries by adopting a deep learning algorithm, constructing a dynamic twin model in combination with thermal-force field coupling simulation, and accurately mapping defect three-dimensional features; generating a repair track according to the twinborn model, converting the repair track into a robot joint instruction through a curved surface parameterization mapping algorithm, and implanting real-time anti-collision constraint; in the repairing process, based on reinforcement learning control of the material rheological resistance and the temperature gradient, the rotating speed, the advancing speed and the down force of the tool are dynamically adjusted; and after repairing, micro-focus CT scanning is started immediately, actually measured data is compared with twinborn prediction, and when the deviation exceeds a threshold value, a re-repairing process is triggered automatically. The method solves the problems that a traditional method depends on manual intervention and the precision of a sensor is easily interfered by the environment.

The invention discloses an attention mechanism and LSTM fused industrial bearing vibration time sequence signal fault prediction method and system. The method comprises the following steps: collecting a bearing vibration signal and carrying out filtering, noise reduction and normalization preprocessing; constructing a deep learning model combining the bidirectional BiLSTM and a coordinate attention mechanism to extract bidirectional time sequence features and enhance key fault features; carrying out model training by adopting a multi-target composite loss function and an Adam optimizer, and introducing an early stop mechanism to prevent overfitting; performing fault type identification and degree evaluation on the real-time vibration signal by using the trained model, and performing quantitative analysis by fusing multi-scale spectrum kurtosis features and nonlinear kinetic parameters; and finally, outputting a fault diagnosis report, and triggering multi-stage early warning based on an adaptive threshold. The method can realize high-precision and high-reliability bearing fault prediction and health state evaluation, and is suitable for intelligent operation and maintenance of industrial equipment.

A deep learning system for time series prediction comprising a preprocessor that receives time series input sequences, truncates them by removing terminal values, and appends padding values to maintain the original sequence length. An encoder compresses these padded sequences into latent space representations, while a decoder reconstructs predicted sequences matching the original length, specifically trained to reconstruct values matching the removed terminal values in positions corresponding to the padding values. A training system optimizes the encoder and decoder by minimizing differences between original sequences and predicted sequences. The system can process multiple time horizons simultaneously while maintaining statistical properties and providing uncertainty quantification through confidence intervals. This approach enables accurate short-term forecasting while preserving both temporal patterns and statistical relationships in the predicted sequences.

The invention discloses a deep learning-combined power transformer partial discharge signal extraction and diagnosis method. The method comprises the following steps of S1, setting a multi-channel synchronous acquisition system in a power transformer body area to acquire a multi-dimensional original partial discharge data set; s2, preprocessing the acquired multi-dimensional original partial discharge data set; s3, performing time alignment and amplitude matching on the processed signal, and dividing the processed signal into a sliding time window to construct a standard input tensor; s4, constructing an attention enhancement model fused by the convolutional neural network and the bidirectional gating circulation unit; s5, performing supervised training on the attention enhancement model by using the labeled sample; s6, inputting the real-time signal into the training model, and outputting a discharge type label; s7, risk grade evaluation is carried out in combination with statistical characteristics; and S8, generating a structured diagnosis report and uploading the structured diagnosis report to a monitoring platform. According to the invention, multi-source signals and a depth model are fused, and intelligent diagnosis and risk assessment of transformer partial discharge are realized.

The invention discloses a method for analyzing a matching degree between a demand and an output result based on text semantics. The method comprises the following steps: step 1, labeling a data set; step 2, technical document preprocessing; 3, training and predicting a single-parameter model; 4, integrating prediction results of the multi-parameter model; the method has the beneficial effects thatthe method is simple; deep learning and the NLP technology are applied to the field of project association degree calculation of enterprise project management for the first time. Calculating an association matching degree between the two projects according to project requirements and result description; the associated project positioning difficulty is effectively reduced; meanwhile, the demand side can be helped to quickly and efficiently locate high-quality projects adapting to the demand of the demand side; time and resource investment for achievement screening and matching are greatly reduced, the association matching degree between projects is calculated by means of text data of existing project achievement technical documents and project declaration guidelines, and then large enterprises are assisted in screening high-quality projects with the high matching degree in the project bidding and tendering link.

The invention relates to the technical field of reservoir earth and rockfill dam leakage abnormity safety monitoring and early warning, in particular to an earth and rockfill dam leakage abnormity real-time monitoring and early warning system based on deep learning and a medium. The system comprises a data sensing transmission module, a data fusion processing and analysis module, an early warning evaluation module, a system management and maintenance module, a database management module and an emergency response command module. Through a well-ground collaborative full-dimensional electrical method and shallow earth surface and full-section distributed optical fiber sensing, the system collects and transmits multi-source data. And multi-mode fusion and a deep learning algorithm are adopted to realize multi-physical field feature extraction and three-dimensional modeling. The system generates graded early warning information based on dynamic threshold and multi-factor coupling, and realizes automatic real-time monitoring, intelligent early warning and efficient management of leakage abnormity of the earth and rockfill dam in combination with a database, management maintenance and emergency response functions. According to the invention, the accuracy of earth and rockfill dam leakage abnormity identification and the intelligent level of early warning are improved.

The invention provides an engineering construction defect automatic detection and classification method based on deep learning, and the method comprises the steps: obtaining a welding seam surface image through the shooting of an unmanned plane, and carrying out the denoising and illumination normalization processing of the welding seam surface image, and obtaining a standardized image; welding seam surface texture features are extracted from the standardized image, a convolutional neural network is adopted to analyze the spatial distribution characteristics of textures, and vectorization processing is carried out to obtain texture feature vectors; segmenting a weld surface corresponding to abnormal region distribution by adopting a region growing algorithm, and analyzing pore and weld discontinuity in combination with the texture feature vector to obtain a defect candidate region; performing threshold division on the sizes and the numbers of the defects according to the defect types and the feature vectors of the candidate regions to obtain a severity grading result of each type of defects; and severity features are extracted from a grading result, and a Bayesian network is adopted to fuse texture feature vectors and defect type labels to obtain a welding quality evaluation score.

The invention discloses an information security adaptive protection method and system based on artificial intelligence, and relates to the field of security protection, and the method comprises the steps: dynamically collecting multi-dimensional asset data through distributed nodes, carrying out the edge calculation preprocessing, and extracting features through a deep learning model; carrying out threat identification by fusing LSTM time sequence analysis, an isolated forest and a multi-modal AI detection engine of a knowledge graph; outputting a risk level based on an improved analytic hierarchy process and a fuzzy evaluation model; the AI strategy engine combines the risk level and the business scene to generate an optimal protection strategy, and continuous optimization is carried out through reinforcement learning; a standardized instruction is linked with safety equipment to execute protection, and interception effect closed-loop optimization is fed back in real time; a whole process log is stored through a block chain, and an attack evidence chain is generated through an AI traceability model. The method has the advantages that the information security protection capability is comprehensively improved through hierarchical data acquisition, multi-modal threat detection, scientific situation evaluation, dynamic generation of an optimization protection strategy and combination of block chain evidence storage and AI traceability.

The invention relates to the technical field of flood early warning, and discloses an urban flood disaster early warning method and system based on artificial intelligence, and the method comprises the steps: collecting five types of information, i.e., meteorological perception, hydrological monitoring, geographic space, urban operation and social perception in real time, and obtaining multi-source data with precise space-time coordinates; through preprocessing, gridding space-time alignment and key feature screening, rainfall accumulation and confluence evolution related features are extracted; constructing a physically constrained space-time fusion deep learning model, and outputting a future ponding depth prediction result in combination with a multi-head attention mechanism; environmental changes such as urban terrains and drainage facilities are adapted through incremental updating and transfer learning; and fusing the ponding depth, the influence range and the regional vulnerability characteristics to generate multi-level early warning, and synchronously outputting a spatial distribution map, a time evolution trend and affected object evaluation information. According to the invention, urban flood control and disaster reduction decision making and public accurate risk avoiding can be effectively supported.

The invention relates to the technical field of power system scheduling, and discloses a power distribution network simulation scheduling optimization method and system based on artificial intelligence, and the system comprises a data fusion module, a digital twin modeling module, an intelligent prediction module, a strategy optimization module, and a visual scheduling module. The whole scene of the power distribution network is simulated through the digital twin model, the operation state and fault influence of equipment are accurately simulated, a scientific basis is provided for making a maintenance plan, blind maintenance is avoided, and the maintenance and repair cost of the equipment is reduced; meanwhile, by optimizing a load transfer path and distributed power supply output, the network loss rate is reduced, and the utilization efficiency of electric power resources is improved; in addition, the knowledge graph and the LSTM deep learning algorithm are fused, the distribution network topology entity relation network is constructed, and multi-source data are trained, so that the fault prediction accuracy is improved, the power failure risk can be early warned in advance, the conversion from passive first-aid repair to active prevention is realized, and the power failure frequency outside a plan is reduced.

The invention relates to the technical field of power equipment fault diagnosis, in particular to a power equipment fault intelligent diagnosis method and system based on deep learning. The method comprises the following steps: automatically learning high-dimensional space-time correlation features in original time series data through a deep feature extraction network, and generating feature vectors representing potential abnormal modes of equipment; performing adaptive weight distribution on the high-dimensional space-time correlation features by using an attention enhancement mechanism, and marking a fault sensitive area to form enhanced fault features; inputting the enhanced fault features into a multi-level classifier for joint fault mode recognition and severity evaluation, and outputting a diagnosis result tensor containing a fault type and confidence; and an equipment maintenance decision signal is triggered based on the diagnosis result tensor, and the feature extraction network and classifier parameters are iteratively optimized according to feedback data, so that the intelligent level of operation and maintenance of the power equipment can be comprehensively improved.

The invention relates to the technical field of electric power system intelligent monitoring, and discloses an intelligent power supply system state monitoring and fault early warning method and system. According to the system, power grid operation parameters are collected in real time through a heterogeneous sensor array, multi-dimensional features are extracted through wavelet transform, a fault diagnosis model is constructed based on deep learning, precise early warning is achieved in combination with a dynamic threshold optimization algorithm, an optimal disposal scheme is generated based on an expert knowledge base, and remote data transmission is achieved through dual-channel communication. Real-time monitoring, fault early warning and intelligent decision support of the state of the power supply network are realized, and the operation reliability and the operation and maintenance efficiency of the power grid are remarkably improved.

Deep learning tools such as convolutional neural networks (CNNs) and transformers have spurred great advancements in computational biology. However, existing methods are constrained architecturally in context length, computational complexity, and model size. This application introduces a sub-quadratic architecture for modeling, which combines projected gated convolutions and structured state spaces to achieve local and global context with, for example, single-nucleotide resolution. These models outperform CNN-, GPT-, BERT-, and long convolution-based models in many tested genomics tasks without pre-training and with 4×-781× fewer parameters. In the proteomics domain, these models similarly outperform pretrained attention-based models, including ESM-1B and TAPE-BERT, on remote homology prediction without pre-training and while using 3,308×-23,636× fewer parameters.

The invention provides an intelligent drilling speed prediction method based on physical feature guidance and multi-source information fusion, and relates to the technical field of intelligent drilling speed prediction, and the method specifically comprises the following steps: collecting multi-source heterogeneous data from a drilling real-time database, a logging system, a logging system and a geological database; constructing a dual-channel deep learning prediction model, wherein the dual-channel deep learning prediction model comprises a dual-channel convolution feature extraction module, a feature fusion module, a time sequence fusion module, a time sequence modeling module and a full connection layer which are connected in sequence; obtaining a predicted drilling speed by using a dual-channel deep learning prediction model; a joint loss function is constructed by considering a data driving error and a physical constraint error, an error is calculated according to the joint loss function, and network parameters are updated through back propagation; carrying out loop iteration training until convergence; and the trained dual-channel deep learning prediction model is used for drilling speed prediction. According to the technical scheme, the problems that in the prior art, a mechanism model is insufficient in precision, and a data driving model is poor in reliability are solved.

The present invention relates to the technical field of deep learning and computer vision. Disclosed is an unmanned aerial vehicle image-based small object detection method for target areas. The present invention crops images of obvious small objects in certain target areas, and annotates the small objects of different categories to form a raw training and testing dataset, so as to ensure the accuracy of data required in the early stage of the algorithm and further ensure the scientificity of the algorithm; uses the computing capability of an improved YOLOv7 detection model to collect image features of different degrees in the dataset, the improved YOLOv7 detection model using YOLOv7 as a basic model and adding to a neck network an MS-CET module, which is constituted by an improved self-attention mechanism and convolution module SPPCSP, and a BHC-FB module, which is constituted by bidirectional mixed convolution modules NConv and RPConv connected in parallel; and finally fuses different feature layers as a final judgment basis of an unmanned aerial vehicle for small object detection in the target areas, to further check the accuracy of the algorithm and criteria for dataset selection, thereby improving recognition accuracy.

The invention discloses a wetland ecological restoration dynamic monitoring method based on deep learning, and relates to the technical field of ecological restoration, and the method comprises the following steps: obtaining multi-source wetland ecological sensor data and remote sensing image flow in real time, constructing a space-time fusion data cube, and extracting an ecological feature tensor; performing degradation mode analysis on the ecological characteristic tensor, generating an ecological state dynamic topological graph, and calculating an ecological connectivity index; carrying out restoration demand identification based on the ecological connectivity index, positioning a degradation hot spot region through a multi-modal graph convolutional network, and generating a restoration priority region coordinate set; through multi-source data space-time fusion and deep crossing of deep learning and landscape ecology, a whole-process technical system from ecological state dynamic perception to restoration scheme intelligent optimization is constructed. The problems that in traditional wetland restoration, data scales are not matched, degradation area positioning is fuzzy, restoration path ecological adaptability is poor, and multi-target cooperation is difficult are effectively solved.

The invention relates to the field of bridge structure dynamic response analysis, and discloses a windmill bridge coupling response analysis method. According to the method, wind speed, wind direction and vehicle speed data are collected, and a data set is constructed by combining finite element and CFD coupling numerical simulation; a parallel encoder is adopted to fuse Transform feature extraction and LSTM time sequence processing to generate a hybrid prediction response; constructing a physical constraint and composite loss function based on a train-bridge motion equation, and optimizing neural network parameters through a subtraction average strategy; and finally, predicting dynamic response through forward propagation and verifying physical consistency to form a model optimization closed loop. According to the method, a deep learning method and physical equation constraints are fused, the analysis precision and calculation efficiency of windmill bridge coupling response are remarkably improved, and a more reliable dynamic evaluation means is provided for bridge wind resistance design.

The invention belongs to the technical field of intelligent monitoring, and particularly relates to an urban underground pipe network real-time monitoring algorithm and system based on multi-source data fusion, and the method comprises the steps: obtaining multi-source heterogeneous monitoring data; performing multi-source data preprocessing; carrying out multi-source heterogeneous feature coding and fusion; carrying out real-time monitoring and anomaly detection on a pipe network state; fault diagnosis and prediction are carried out; and generating decision support information and early warning. The system comprises a data acquisition module, a data preprocessing module, a multi-source heterogeneous feature coding and fusion module, a pipe network state real-time monitoring and anomaly detection module, a fault diagnosis and prediction module and a decision support and early warning module. According to the scheme, multi-source heterogeneous data are integrated, spatial-temporal feature coding and fusion are carried out through deep learning, accurate sensing, early warning and intelligent fault diagnosis of the operation state of the pipe network are achieved, and the safe operation level and maintenance management efficiency of the urban underground pipe network are improved.

The disclosure belongs to the technical field of network security, and provides a method for constructing a feature knowledge base of mapping behavior based on deep learning, which includes: data acquisition and preprocessing: extracting five-tuple information and behavior features from network traffic. The disclosure automatically extracts the spatio-temporal features through the deep learning model, and enhances the sensitivity to abnormal behaviors by combining the attention mechanism, thus significantly improving the detection accuracy. The explanatory AI technology is used to automatically generate detection rules, the maintenance cost of manual rules is greatly reduced and the efficiency of rule generation is significantly improved. The feature knowledge base supports dynamic updating, may integrate third-party threat information in real time, and ensures the continuous defense ability against new attacks and variant detection means.

The invention belongs to the technical field of computer vision and artificial intelligence, belongs to the cross technical field of target detection, deep learning and image processing, and particularly relates to a YOLOv8 algorithm improvement method based on an unmanned aerial vehicle aerial image small target detection model, which comprises the following steps of: introducing a user-defined feature enhancement module into a YOLOv8 backbone network, a neck part and a detection head part; the self-defined feature enhancement module comprises a context guide self-adaptive fusion module introduced into a backbone network so as to replace part of traditional convolution operation; a space edge sensing feature up-sampling module and a space sensing enhanced convolution module are adopted in the neck fusion network; a fine-grained dynamic pruning detection head is introduced into a detection head detection network. According to the method, the performance of the model in a small target detection scene is effectively enhanced, and the accuracy, robustness and real-time response capability of a detection system are remarkably improved.

Disclosed in the present invention is a non-autoregressive Transformer-based modeling method for a 4-level pulse amplitude modulation high-speed transmitter. The method involves establishing a deep learning model having an encoder-decoder architecture to predict the behavior of a 4-level pulse amplitude modulation transmitter. An encoder processes unordered non-sequential inputs, including an input signal parameter and link parameters, to generate a context vector and then transmit same to a decoder. The decoder uses both the context vector generated by the encoder and a transmitter output signal sequence to generate a categorical probability distribution for each point in the sequence one by one. The model is trained using a random masking strategy, and inference is performed by means of non-autoregressive decoding and filtering, so that the model can perform parallel prediction on an output sequence, and perform a filtering process to predict an output signal. Compared to traditional simulation methods, the present invention achieves a significant acceleration effect, particularly when processing multi-link systems.

The invention relates to the technical field of computer vision, and discloses a real-time video analysis method based on deep learning. The method comprises the following steps: acquiring a real-time video stream through image acquisition equipment, and performing frame segmentation processing to generate a continuous video frame sequence; and extracting features of the video frame sequence by using a pre-trained convolutional neural network to obtain a multi-dimensional feature vector, inputting the multi-dimensional feature vector into the time sequence analysis model to calculate dynamic relevance, and outputting an inter-frame movement track and object behavior features. And constructing a scene understanding map containing a spatial position and a time evolution relationship according to the above-mentioned data, and carrying out abnormal event detection and generating event marking data based on the map. And performing semantic analysis on the event marking data, determining an abnormal event type and a confidence score, triggering a real-time alarm signal according to a result, and updating a historical event database. In the analysis process, the resource occupancy rate of the system is continuously monitored, the calculation precision is dynamically adjusted, a degradation processing mechanism is started when a preset threshold value is exceeded, and key area analysis is preferentially guaranteed.

The invention provides an image restoration and super-resolution reconstruction system and method based on deep learning, and belongs to the technical field of digital image processing. The invention aims to solve the problems of high calculation complexity and resource consumption, limitation of long sequence processing, high training difficulty and texture scene deficiency when a multi-scale residual network based on a Transform architecture is used for image resolution conversion. The reconstruction system comprises: an image preprocessing module performing window division and video memory optimization on an input low-resolution image; the multi-layer fusion network dynamically adjusts the characteristics of the low-resolution image, captures channel information in different scenes, performs interactive fusion, performs comparison supervision, establishes an information communication channel, dynamically adjusts and optimizes parameters through negative feedback, and obtains a super-resolution image. And the loss function module maximizes the similarity of the super-resolution image and the high-resolution image in the segmentation feature space to obtain a final super-resolution image.

The present invention relates to a solar azimuth estimation method and system based on multi-channel feature enhancement and region-aware attention, belonging to the technical field of intelligent navigation for low-altitude economy unmanned systems. Aiming at the problem of decreased accuracy in solar azimuth estimation based on polarization images under complex cloud cover conditions, the present invention proposes a deep learning framework integrating multi-channel features and direction-aware attention. First, based on polarization light field information acquired by a division-of-focal-plane polarization camera, a three-channel composite input feature composed of a polarization intensity map, an adaptive threshold gradient map, and high-frequency residual edge information is constructed. Second, a ResNet backbone network embedded with a squeeze-and-excitation mechanism is adopted, and a direction-aware polarization attention module is introduced to achieve adaptive fusion of multi-scale features through luminance guidance, deep feature enhancement, and a gradient edge branch.

The invention discloses a mineral resource intelligent prediction method and system based on multi-source heterogeneous data fusion and deep learning, and the method comprises the steps: collecting and preprocessing multi-source heterogeneous data, and carrying out the standardization processing to form a structured data set; multi-source heterogeneous data fusion: realizing data layer space registration and feature layer weight dynamic allocation through an attention mechanism multi-modal fusion module, and outputting a high-dimensional metallogenic feature vector; constructing a CNN-LSTM mixed deep learning model and completing initialization training, and outputting an initial mineralization probability graph; and establishing a dynamic updating engine, performing model increment training based on transfer learning, correcting the mineralization probability through positive and negative sample reinforcement learning in combination with a newly added data type, and outputting a time sequence dynamic mineralization probability graph. According to the method, mineralization probability dynamic evaluation and risk quantitative updating are realized, the prediction precision and the model updating efficiency are improved, the method is adaptive to a multi-stage exploration scene, and accurate real-time support is provided for exploration decision making.

The invention discloses a plateau mountain road disaster identification method and system based on multi-source remote sensing image restoration and super-resolution reconstruction. The method comprises the following steps: acquiring and preprocessing a multi-source remote sensing image of a plateau mountain region, and extracting landform measurement parameters based on a digital elevation model; a super-resolution reconstruction network fusing deformable convolution and Transform is constructed, and a low-resolution image is reconstructed by using constraint training of a composite loss function containing geomorphic measurement parameters; performing feature extraction and adaptive weighted fusion on the preprocessed image and the reconstructed high-resolution image; based on the fused image, utilizing a multi-task deep learning model to identify landslide, debris flow and roadbed subsidence disasters along the highway; and carrying out morphological optimization and boundary refinement under GIS constraint on an identification result, and outputting a disaster thematic map. According to the invention, the precision and reliability of road disaster identification in a complex terrain environment are effectively improved.