155results about How to "Efficient fusion" patented technology

The invention provides a satellite-borne multi-band synthetic aperture radar signal processing optimization method and system, and relates to the technical field of signal processing, and the method comprises the steps: obtaining original echo data of a satellite-borne multi-band synthetic aperture radar, carrying out Doppler center frequency estimation, carrying out two-dimensional matrix product operation, and obtaining compensation echo data; distance direction position information and scattering intensity information are obtained based on a distance direction matching filtering algorithm of sub-band decomposition; determining spatial distribution density, performing adaptive block processing, and performing phase error modeling in each block to generate a continuous phase correction function; performing wavelet domain convolution operation to obtain corrected echo data, obtaining a multi-band two-dimensional image, extracting a multi-dimensional feature vector through a deep neural network, performing weight learning, performing nonlinear weighted fusion, and performing adaptive histogram equalization enhancement to determine a synthetic aperture radar imaging result.

The invention discloses a coal mine industry multi-dimensional data real-time monitoring and abnormity positioning method and system, and the method comprises the steps: collecting real-time data in coal mine operation, and carrying out the preprocessing; and carrying out dimension construction on the preprocessed data, and fusing the data of different dimensions to form multi-dimensional data. And inputting the multi-dimensional data into the anomaly detection model, and carrying out backtracking analysis on the abnormal data. And performing exception handling and response according to the detected exception and backtracking analysis. According to the coal mining industry multi-dimensional data real-time monitoring and anomaly positioning method and system provided by the invention, correlation analysis and fusion are performed on different-dimensional data, key features are extracted by using principal component analysis, and efficient fusion of the multi-dimensional data is ensured in combination with nonlinear transformation. The main information is reserved, and the accuracy of anomaly detection is improved by enhancing the representativeness of the features. The abnormal response time is shortened, and the emergency processing accuracy is improved.

The invention relates to the technical field of intelligent equipment evaluation and fault prediction, and discloses a dynamic equipment quality evaluation method based on multi-agent collaborative reinforcement learning, and the method comprises the steps: obtaining original data from equipment and a sensor, and carrying out the preprocessing; analyzing the preprocessed data, and identifying key factors influencing the quality of the equipment; constructing a plurality of expert models, and predicting and evaluating an analysis result; fusing the weight of each expert model to obtain a comprehensive evaluation result; and performing risk assessment on the comprehensive assessment result, extracting key influence factors and decision rules, and generating an assessment result. Efficient fusion of multi-source data and automatic identification of key factors are realized, and the accuracy and reliability of equipment quality evaluation are remarkably improved; a model fusion result is optimized through dynamic weight distribution, so that the prediction performance is improved; the problems that in the prior art, data fusion is difficult, key factor identification depends on experience, and the interpretability of an evaluation result is insufficient are solved.

The invention discloses an industrial visual detection system based on multi-modal fusion, which belongs to the technical field of industrial data acquisition, processing and processing, and comprises a multi-modal data acquisition and calibration module, a scene image capture module, a visual information synthesis module, an algorithm optimization and training module and a multi-modal image output module, the multiple modules are integrated into the industrial visual detection system for multi-modal data acquisition, processing and fusion, high-quality original data are provided for subsequent image analysis, images of industrial scenes can be automatically captured under different illumination conditions, an original image database containing various illumination and scene conditions is constructed, and the visual detection system has the advantages of being simple in structure, convenient to operate and high in practicability. The system can operate stably, high-precision analysis and processing of the image data set in the industrial scene are realized, the corresponding fusion image is generated, the industrial visual inspection report is generated based on the fusion image, and the adaptability and reliability of the industrial visual inspection system are improved.

The invention provides a petrochemical pipeline full-life-cycle detection and evaluation method and equipment. The method comprises the following steps: constructing a pipeline detection digital twin model comprising a geometric model and material attributes; collecting detection data of the pipeline through the deployed multi-source sensor network; inputting the detection data into the pipeline detection digital twin model to perform feature extraction and analysis of the pipeline state; constructing a heterogeneous tree network and executing hierarchical evaluation; optimizing the maintenance plan based on the evaluation result; and predicting the residual life of the pipeline. Through the digital twinning technology and multi-source detection data fusion, full-life-cycle accurate evaluation of the petrochemical pipeline is realized.

The invention relates to the field of remote sensing image processing, and discloses a high-quality HRHS image generation method based on a double-subnetwork structure, and the method comprises the following steps: receiving an input low-resolution hyperspectral image and a panchromatic image, which are respectively used for providing spectral information and spatial information; performing noise filtering on the low-resolution hyperspectral image through an anti-noise pre-fusion sub-network, and generating a pre-fused hyperspectral image by using the correlation between the high spatial resolution information of the panchromatic image and the spectral characteristics of the low-resolution hyperspectral image; performing high-frequency detail reconstruction and enhancement on the pre-fused image based on a conditional diffusion model through a high-frequency enhancement sub-network; and fusing the low-frequency information of the pre-fused image and the high-frequency detail information generated by the high-frequency enhancement sub-network through wavelet inverse transformation, and outputting a final high-resolution hyperspectral image. According to the method, spectrum and space information can be effectively fused in various noise environments, and a high-resolution hyperspectral image with hyperspectral fidelity and space details is generated.

The invention discloses a shallow-layer and deep-layer multispectral point cloud generation method based on multispectral image data and laser radar point cloud data, and relates to the field of remote sensing data processing, and the method comprises the steps: obtaining a multispectral image and laser radar point cloud data of a target region; the method comprises the following steps: calculating a shallow multispectral feature map through ENVI software, constructing a three-dimensional multispectral point cloud fusion model, inputting a shallow / deep multispectral feature map and point cloud data into the three-dimensional multispectral point cloud fusion model, and realizing spatial registration of a multispectral image grid coordinate system and a point cloud plane coordinate system through affine transformation. And respectively generating shallow multi-spectral point cloud data and deep multi-spectral point cloud data. According to the invention, shallow and deep multispectral feature maps are respectively extracted, efficient fusion of the multispectral image and the laser radar point cloud is realized based on the constructed three-dimensional multispectral point cloud fusion model, and the defects that the point cloud data lacks spectral information and the hyperspectral point cloud data is high in cost are overcome.

The invention provides a multi-modal network rumor detection method based on big language model feature enhancement, and belongs to the technical field of language processing. Comprising the following steps: acquiring text modal data and image modal data; performing enhancement processing on the text modal data and the image modal data; combining the enhanced text with a predefined prompt template to obtain an input prompt enhanced text; converting the image modal data into visual feature representation; obtaining emotion-enhanced text feature representation, fused visual feature representation and fused text feature representation based on the enhanced text; optimizing the fused visual feature representation and text feature representation, and generating a visual integrated feature vector and a text integrated feature vector; weighting the visual integration feature vector and the text integration feature vector to generate a visual cross-modal feature and a text cross-modal feature; and inputting the visual cross-modal features, the text cross-modal features, and the text information and the visual information with balanced adjustable weight coefficients into a full connection layer, and outputting a prediction result.

The invention discloses an intelligent command decision-making system, and the system comprises an intelligent decision-making software unit which is used for achieving the intelligent planning and decision-making of a combat mission based on real-time battlefield situation data and simulated online training learning; the command terminal software unit is used for acquiring battlefield situation, equipment data and battlefield environment information based on a geographic information platform, collecting, processing and analyzing battlefield target and environment data, and quickly making, revising and reporting a combat action plan; calling a vehicle-mounted communication service to combat with superior and neighbors; the guarantee unit can establish voice, message and data communication; action plans and instructions issued by a superior are received in time, and integrated plan management and monitoring are carried out; combating and guaranteeing vehicles and providing battlefield action navigation; and the information service software unit is used for providing tactical information services of geographic information, comprehensive situation and battlefield environment for the vehicle-mounted command terminal through a communication network. The invention further discloses a corresponding intelligent command decision-making method.

The invention provides a laser radar and gamma camera integrated detection system based on a shared SiPM array, and belongs to the field of detector equipment. The system comprises a laser emission module, a gamma camera, an optical module, an SiPM array detection module, a signal processing module and a control module. Wherein the optical module controls high-frequency pulse laser of the laser emission module to scan a target scene, respectively guides a reflected laser beam and a scintillation light signal emitted by the gamma camera to the SIPM array detection module for photoelectric conversion to generate an electric signal, and performs gain and time gate adjustment according to a sensor working mode to obtain a first electric signal; the signal processing module receives the first electric signal and carries out laser radar ranging calculation and gamma camera imaging processing to obtain three-dimensional point cloud data and a radioactivity distribution image of the target scene. According to the invention, efficient fusion of functions of the laser radar and the gamma camera is realized, the size and weight of the system are greatly reduced, and the manufacturing and maintenance cost is also reduced.

The invention provides an ink quality online monitoring method and system based on multi-sensor fusion, and relates to the technical field of printers, and the method comprises the steps: obtaining the temperature, humidity, pH value, viscosity, particle thickness, flow velocity and other data collected by a plurality of sensors in the production process of water-based ink, and employing a multi-sensor data fusion algorithm of adaptive weight, calculating a sensing weight corresponding to the sensor data, and combining the sensor data to obtain fused water-based ink quality characteristic data; establishing a water-based ink quality prediction model by adopting a support vector machine algorithm, and inputting the fused water-based ink quality feature data into the trained water-based ink quality prediction model to obtain a water-based ink quality prediction result; and if the water-based ink quality prediction result does not meet the preset condition, judging that the water-based ink quality is unqualified, sending a feedback signal in a preset format to water-based ink production equipment, and adjusting water-based ink production parameters through a PID controller of the water-based ink production equipment. According to the method, the related parameters of the ink can be monitored and reflected in real time, and the possible problem of artificial false description is solved.

The invention discloses a steel rail surface defect detection method based on LAH-YOLO. The detection precision of the YOLOv5-s algorithm on a steel rail surface defect data set still needs to be improved. The method comprises the following steps: acquiring a steel rail surface image, and inputting the steel rail surface image into a constructed LAH-YOLO defect detection network; the LAH-YOLO defect detection network comprises a backbone network, a feature fusion network and a detection head; the backbone network comprises a GRF-C3 module, and the feature fusion network is an AFPN feature fusion network. The method is suitable for small target and small sample data sets, the detection precision is remarkably improved while the parameter quantity is reduced, and the method has better detection performance on the steel rail surface defect data set.

The invention discloses a dual-light camera image registration fusion method, system and device based on binocular distance measurement and a storage medium, which are applied to the technical field of image processing, and the method comprises the steps: carrying out the distortion correction of a dual-light image, obtaining the internal and external parameters of a dual-light camera, and carrying out the stereo correction and mapping transformation of the dual-light image based on the internal and external parameters; performing parallax estimation calculation on the corrected image by using an SGBM stereo matching method, calculating a distance from a target to the dual-light camera according to a value in a center range in the image, and extracting corresponding preliminary registration parameters and an affine transformation homography matrix according to a registration parameter index table to perform image registration; and performing pixel value proportion conversion on the dual-light image after image registration, extracting high-frequency information and low-frequency information of the infrared image, and performing fusion of the infrared image and the visible light image based on the high-frequency information and the low-frequency information. According to the method, the real-time performance and practicability of image registration fusion are effectively improved, and the image registration fusion precision is further improved.

The invention relates to a spacecraft pose estimation method, in particular to a lightweight spacecraft pose estimation method based on a high-resolution network, and solves the technical problem that in an existing spacecraft pose estimation method, key point regression is difficult to meet precision and efficiency requirements at the same time. According to the method, the key point regression model is based on a high-resolution network, depth separable convolution is adopted in the feature extraction process, the parameter quantity and the calculation quantity are greatly reduced, meanwhile, a mixed attention mechanism is combined, the high expression ability is reserved in feature extraction, the lightweight degree is further improved, and the method is suitable for large-scale popularization and application. The balance of precision and efficiency is realized; in the feature fusion process, cavity convolution is adopted to enlarge a receptive field, global information in an image can be captured, the pixel position of an occluded key point can be more accurately deduced, then key local and global features are focused in combination with a mixed attention mechanism, the effectiveness of feature representation is further improved, and the regression precision of the key point is improved.

The invention discloses a low-illumination image enhancement algorithm based on deep convolution, which is suitable for the field of image processing, and the core of the algorithm lies in an efficient noise reduction process and accurate decomposition of an illumination image and a reflection image. Comprising the following steps that firstly, a channel noise reduction module works cooperatively through multiple noise reduction strategies, noise in an image is effectively removed, and a foundation is laid for follow-up processing; then, the illumination image decomposition network and the reflection image decomposition network accurately separate the brightness information, texture and color information of the image based on a deep learning structure. And finally, by ingeniously fusing the illumination image and the reflection image, reconstructing a high-quality enhanced image, remarkably improving the brightness, contrast and details of the image, and meanwhile, retaining the natural color of the image. The algorithm has the advantages of being high in noise reduction capacity, accurate in illumination image decomposition, efficient in reflection image decomposition, good in enhancement effect and the like, and an effective and practical solution is provided for image enhancement under the low-illumination condition.

The invention belongs to but not limited to the technical field of animal husbandry statistics, and particularly relates to an alpine meadow yak number calculation method and system based on an unmanned aerial vehicle image, and the method comprises the steps: S1, employing an unmanned aerial vehicle to shoot an orthoimage of a sample plot, and carrying out the statistics of the yak number; s2, splicing the shot images by using Pix4D software, screening a proper sample plot, and respectively counting the quantity of wet cow dung and the quantity of dry cow dung in a visual interpretation mode; and S3, carrying out linear fitting on the obtained data by using Origin 2024b, so as to obtain three relation curves. According to the method for estimating the number of the yaks through statistics of the number of the cow dung in the unmanned aerial vehicle image, the workload of data collection is greatly reduced, and the limitation that the number of the yaks cannot be obtained when the yaks are not grazed in the grassland is avoided. According to the invention, the data acquisition frequency of experimenters is effectively reduced, and the research cost is reduced.

The invention belongs to the technical field of emotion recognition, and provides a multi-modal data fusion driver emotion recognition method and device, and the method comprises the steps: obtaining a multi-modal data set from a collected original data set of driver eyes, an original data set of a vehicle, and an original data set of an environment; performing feature extraction on the data in the multi-modal data set to obtain audio features, text features and visual features; performing feature alignment on the audio features, the text features and the visual features to obtain modal alignment features; performing feature fusion on the modal alignment features by using a mixed attention mechanism to obtain modal fusion features; and performing emotion recognition processing on the modal fusion features to obtain an emotion recognition result. According to the method, efficient fusion of the multi-modal data in the feature layer is realized, and the accuracy of driver emotion recognition is improved.

The invention discloses a digital integrated system of an LNG receiving station. Wherein the data fusion module comprises a multi-source heterogeneous data fusion engine and is used for collecting, storing and preprocessing data of an LNG receiving station; the model building module comprises a self-adaptive digital twinning modeling framework and is used for building digital twinning models of the LNG receiving station, and the models comprise a physical model, a machine learning model and a 3D visual model; the service module comprises an intelligent scene engine and a decision support subsystem driven by a knowledge graph; and the application module comprises an application development framework of a micro-service architecture and is used for developing an application oriented to a terminal user. Thus, efficient fusion and processing of multi-source heterogeneous data are realized through fusion of a multi-layer module architecture design and an advanced technology, and the data utilization rate and the real-time performance are greatly improved. And meanwhile, the intelligent decision-making capability of the system is remarkably enhanced, and various complex operation scenes and emergency situations can be effectively handled.

The invention relates to a motion function rehabilitation state detection method based on multi-modal information, and the method comprises the steps: collecting a wrist electromyographic signal when a target person executes an action, carrying out the preprocessing and dimension reduction of the electromyographic signal, and extracting the features of the electromyographic signal; collecting a video when the target person executes the action, and performing preprocessing and recognition based on the collected video to obtain an action classification result as an action recognition feature; detection data of a wearable dynamic sensor worn on the body of the target person when the target person executes the action are collected, and kinematic characteristics are extracted and obtained, and the kinematic characteristics comprise acceleration, angular velocity and force information; splicing the electromyographic signal features, the action recognition features and the kinematics features under the same time window to obtain a detection feature vector, and calculating the Euclidean distance between the detection feature vector and the standard feature vector to obtain a rehabilitation state detection result. Compared with the prior art, the method has the advantages of high detection accuracy and the like.

The invention discloses an insurance intelligent risk control system, and relates to the technical field of risk control, and the system comprises a data collection module which is used for collecting corresponding vehicle operation data and external environment data in the driving process of a target vehicle; the data analysis module is used for analyzing the vehicle operation data corresponding to the target vehicle in the driving process, generating a driving behavior evaluation coefficient corresponding to the target vehicle based on an analysis result, and processing the external environment data corresponding to the target vehicle to obtain a driving behavior evaluation result; determining an environment risk assessment coefficient corresponding to the target vehicle according to the processing result; the insurance adjustment module is used for generating a comprehensive risk assessment coefficient according to the driving behavior assessment coefficient and the environmental risk assessment coefficient, and determining a rate adjustment strategy in combination with a pricing model preset by an insurance company; and the strategy execution module is used for responding to the rate adjustment strategy and dynamically adjusting the rate corresponding to the insurance of the target vehicle. The method and the device have the effect of improving the risk assessment accuracy.

The invention discloses a zero-sample food image detection method based on visual semantic bidirectional guidance, which belongs to the technical field of image data processing and generation, takes DETR based on Transform as a detection framework, and fuses a food semantic enhancement network and a cross-modal bidirectional guidance module. Firstly, an image is input to an image backbone network branch to extract visual features, a category label is input to a food semantic enhancement network branch to extract semantic features, then the two obtained features are sent to a cross-modal two-way guide fusion module, the module comprises a two-way guide encoder, a two-way guide query vector and a two-way guide decoder, and the cross-modal two-way guide fusion module comprises a two-way guide query vector and a two-way guide decoder. Visual and semantic features are aligned and fused through coding and decoding processes, and finally, regression and classification tasks of zero sample food image detection are completed in a full connection layer. According to the method, detailed food attributes and visual features can be captured in the detection process, effective interaction of visual semantic modals is achieved, and therefore the detection precision of unseen food categories is improved.

The invention relates to the technical field of intelligent teaching, and particularly provides an interpretable exercise recommendation method and system based on relation attributes, and the method specifically comprises the following steps: processing the interaction data between a user and an exercise in an existing data set, building a user-exercise knowledge graph according to the relation between the data, and carrying out the initialization; inputting the initialized user-exercise knowledge graph instances into a TransE model for training to obtain embedded vectors of trained entities and relationships; and performing user exercise recommendation on the user-exercise knowledge graph, formalizing the user exercise recommendation into a Markov decision process, and performing multi-step path reasoning on the user-exercise knowledge graph by constructing a reinforcement learning system to realize user exercise recommendation. According to the method, a more accurate user portrait is realized, the accuracy of the recommendation system is improved, and meanwhile, the path between the recommendation question and the question practiced by the student is extracted from the knowledge graph to generate interpretable recommendation.

The invention relates to the technical field of flood disaster simulation, in particular to a watershed flood dynamic simulation system based on multi-source data fusion, which comprises a multi-source data preprocessing module, a multi-source data fusion module, a digital twin watershed modeling module, a flood dynamic simulation module, a flood risk assessment module and a visualization module. According to the scheme, a space-time cross-modal interaction fusion method is put forward to fuse multi-source data, a cross-modal interaction mechanism is introduced to capture dependency in a modal, high-dimensional interaction tensors are efficiently fused by means of low-rank decomposition, complementarity of space topology, time dynamic and multi-source heterogeneous data is considered, and multi-source data fusion efficiency is improved. The precision and robustness of hydrological process modeling are effectively improved; by constructing a distributed hydrological-hydrodynamic coupling model, whole-process dynamic simulation from runoff production to river channel-flood area flood routing is realized.

The invention relates to the field of computer vision, deep learning and multi-modal behavior analysis, in particular to a multi-modal action recognition method and system based on fine-grained analysis and knowledge distillation, and the method comprises the steps: carrying out the frame extraction of an input video, and obtaining an image sequence; carrying out body part segmentation on the image and inputting the image into a CLIP model in combination with text description to obtain multi-modal features of each part; integrating the feature information through a part level fusion network; a student model is constructed in combination with learnable prompts, and knowledge distillation is carried out; and carrying out optimization training on the model and outputting an action recognition result. According to the method, fine-grained visual features and semantic information are well fused, and key modes in actions are effectively mined, so that the accuracy of action recognition is improved.

The invention discloses a millimeter wave radar and monocular camera fused information acquisition device and method, and relates to the technical field of target detection. The device comprises a millimeter wave radar, a monocular camera and an adjusting bracket, wherein the adjusting bracket can adjust the positions and angles of the radar and the camera. And the data fusion module performs time synchronization and space alignment on the radar information and the image information, and obtains a target recognition result through a preset target recognition model. The acquisition method comprises the steps of timestamp matching, time compensation, joint calibration, coordinate transformation, image distortion correction and the like. Further, radar physical features are extracted by using a CFAR algorithm, image features are extracted by using a deep learning model, and effective features are obtained through PCA dimension reduction. And finally, an accurate target recognition result is obtained through feature splicing and optimization by using a support vector machine (SVM). According to the method, efficient fusion and target identification of millimeter wave radar and monocular camera information are realized, and the method has a wide application prospect.

The invention discloses a power equipment test data acquisition method and device based on multi-source data fusion. The method comprises the steps that each sensor acquires operation data of power equipment in real time; evaluating the operation data based on the abnormal condition and the equipment state to generate a multi-source data fusion parameter; generating a compression strategy parameter based on the multi-source data fusion parameter; based on multi-source data fusion parameters, fusing the operation data of the power equipment collected by the sensors in real time to obtain fused multi-source operation data; performing data compression on the fused multi-source operation data according to the compression strategy parameters; and transmitting the compressed fused multi-source operation data to a central processing unit. According to the invention, the real-time monitoring capability and the fault early warning level of the power equipment data acquisition system are improved, and the data transmission and storage cost is reduced.

The invention relates to the technical field of automatic driving, and discloses an end-to-end automatic driving multi-modal data fusion method and system, and the method comprises the steps: obtaining multiple pieces of sensor data, GPS data and vehicle body data of an automatic driving vehicle, and the multiple pieces of sensor data comprise laser radar data, camera data and millimeter wave radar data; performing pre-fusion processing on the laser radar data and the camera data to obtain a pre-fusion result; and performing post-fusion processing on the pre-fusion result, the millimeter wave radar data, the GPS data and the vehicle body data to obtain a post-fusion result so as to realize multi-modal data fusion, and further realizing automatic driving decision through a large model technology based on the pre-fusion result and the post-fusion result. According to the invention, efficient fusion of multi-modal data in a complex driving environment is realized, the accuracy and reliability of automatic driving decision making are improved, and the stability and safety of an automatic driving system in a dynamic environment are also improved.

The invention discloses a lightweight image super-resolution reconstruction system and method for underground mobile equipment, and belongs to the technical field of image reconstruction. Comprising a shallow feature extraction module, a deep feature extraction module, a feature aggregation module and an image reconstruction module. The deep feature extraction module comprises a high-frequency enhanced distillation block, and the high-frequency enhanced distillation block comprises a feature refining module, a multi-scale information distillation module and an information fusion module; and the feature refining module comprises three high-frequency enhanced residual blocks which are connected in series. According to the method, an information distillation architecture is adopted, a two-way branch structure is adopted in a feature extraction trunk, channel segmentation is carried out on input features, the calculation amount is reduced, the capturing capacity of a network on detail information is improved by utilizing global feature extraction and high-frequency enhancement branches, and deep information is efficiently extracted; and adopting a multi-scale information distillation method to perform multi-scale high-frequency information distillation on the features after feature extraction trunk refinement, and fusing the distilled multi-scale high-frequency information by using a mixed feature enhancement block.

The invention relates to a prompt learning and SAR data-assisted optical image external parameter autonomous calibration method. Compared with the prior art, dependence of ground control points is eliminated, multi-source information is fused, and an optical image external parameter compensation model is constructed. The method comprises the following steps of prompting preparation work of the learning and SAR-assisted optical image external parameter autonomous calibration method; converting the SAR satellite image into a pseudo optical image; building an optical image external parameter autonomous calibration model based on prompt learning; training an optical image external parameter autonomous calibration model based on prompt learning; and application of the optical image external parameter autonomous calibration model. According to the method, the SAR image and prompt learning technology is introduced, so that the external parameter calibration performance is particularly outstanding in areas which cannot be covered by a traditional calibration method, such as polar regions, deserts and mountain forest areas.

The invention relates to a knowledge graph entity alignment method based on multi-scale neighbor aggregation, which is suitable for the fields of natural language processing, knowledge graphs, data integration and analysis and the like. At present, an entity alignment method based on representation learning makes a significant progress in the field of knowledge maps, but the accuracy still needs to be improved when facing a large-scale knowledge map with more long-tail entities and higher graph structure heterogeneity, so that the existing method cannot be applied in an actual scene. According to the invention, on the basis of a Dual-AMN model, in combination with a multi-scale neighbor aggregation mechanism, a Dual-AMN with long-tail enhancement (Dual-LTE) graph encoder is provided, so that the performance of the model in a long-tail entity alignment task is enhanced. By expanding the neighbor entity information aggregation range of the long-tail entity, the graph structure information capturing capability of the model is improved, so that the entity alignment accuracy is effectively improved. The method has important significance for solving the long-tail entity problem in knowledge graph entity alignment, and powerful support can be provided for research in related fields and landing application of actual scenes.