616 results about "Feature description" patented technology

The invention provides a civil engineering structure apparent damage diagnosis method based on a multi-modal large model. The method comprises the steps of structure apparent damage multi-modal data unified representation and alignment fusion, a structure damage identification reasoning method based on a multi-modal thinking chain, multi-modal data set construction and large model fine adjustment, and civil engineering structure damage identification and feature description. According to the method, vector coding of a structure damage image is completed by using a multi-modal large model, the structure damage image is aligned with text coding features, a damage semantic segmentation map is generated by calling a computer vision model to serve as a visual thinking chain, and a language thinking chain is formed by constructing a fine tuning data set; and reasoning of multi-modal information coding and generation of structural damage diagnosis are completed by the pre-trained large language model. According to the method, a multi-modal large model is used as a base, and a multi-modal thinking chain reasoning method is fused, so that the model can perform man-machine interaction through a natural language, various structural damages are efficiently diagnosed, and the generalization ability and accuracy of the structural damage diagnosis model are improved.

The invention relates to the technical field of big data, and discloses a space-time big data abnormal event detection method and device and a storage medium. The method comprises the following steps: performing timestamp unification and space coordinate standardization processing on urban space-time big data to obtain a standardized space-time data set; feature vector cosine similarity between each data point in the standardized spatio-temporal data set and other data points is calculated to obtain a target similarity value, and an initial neighborhood data set is selected; performing space-time density distribution calculation on the initial neighborhood data set to obtain a core neighborhood data set; performing time sequence feature and spatial distribution feature extraction on the core neighborhood data set to obtain a fusion feature weight matrix; and inputting the fusion feature weight matrix into a support vector machine classifier to perform abnormal event recognition to obtain an abnormal event detection result, thereby improving the classification capability of high-dimensional nonlinear features, and simultaneously realizing all-directional feature description and detection of abnormal events.

The invention relates to an intelligent vacuum coating quality monitoring method based on artificial intelligence, which comprises the following steps: collecting process parameters in real time through a coating equipment sensor, dynamically monitoring vacuum degree change, deposition rate deviation and temperature gradient, and standardizing data flow to obtain a quantitative trend curve of process parameter fluctuation; combining the defect microcosmic feature description set with gas flow fluctuation and power supply voltage jitter to obtain a correlation analysis result of process parameters and defect forms, and calibrating defect types according to a defect feature library to obtain an updated defect classification basis; and inputting real-time new surface image data through the updated defect classification basis, performing defect detection for illumination reflection differences and stripe deflection angles, obtaining a preliminary defect classification result, and adjusting classification weight parameters.

The invention relates to the technical field of visual identification, and discloses a belt tearing detection method, device and equipment based on visual identification, and the method comprises the steps: carrying out the dual-channel image collection and preprocessing of the surface of a conveying belt, and obtaining a multi-channel preprocessing image; extracting a thermal difference feature and a texture structure feature of the multi-channel preprocessed image through a double-flow feature network, and inputting the thermal difference feature and the texture structure feature into a quaternion material deformation analysis model for deformation gradient tensor and invariant parameter calculation to obtain a tear feature description vector; performing hierarchical progressive identification and three-dimensional reconstruction analysis to obtain target tearing feature data; and risk assessment is carried out based on the target tear feature data to obtain a tear grade classification result, the interference of ambient temperature drift and non-uniform illumination is effectively eliminated, the calculation efficiency and accuracy of tear detection are improved, and false alarms and missing alarms are reduced.

The invention belongs to the technical field of three-dimensional measurement, and discloses a 3D laser line scanning system based on a point cloud positioning algorithm and a control method. The method comprises the following steps: acquiring environment initial point cloud data and scanning target information; carrying out feature extraction, constructing an environment feature description model, carrying out three-dimensional space partitioning processing, carrying out regional reflectivity feature analysis, and constructing a space reflection feature model; adaptive optimization configuration is carried out on the laser scanning parameters, and a scanning strategy is generated; scanning path dynamic planning is carried out on the scanning target information, scanning density distribution calculation is carried out, and a scanning path is generated; performing laser line scanning control by using the scanning path and the scanning strategy, and performing scanning data quality real-time monitoring to obtain scanning quality evaluation data; scanning parameter iterative optimization is carried out on the scanning quality evaluation data, point cloud data real-time fusion reconstruction is carried out, a high-precision three-dimensional model is generated, the modeling precision is improved, and meanwhile the system resource utilization efficiency is optimized.

The invention relates to the technical field of model construction, in particular to a method and a system for establishing a parameterized tunnel model based on cloud computing. The method comprises the following steps: acquiring a tunnel section type, and extracting structural semantics to obtain a section feature description set; constructing a parameter dictionary of the tunnel section based on the section feature description set to obtain a dynamic parameter dictionary data set; and modeling a tunnel section geometric structure based on the dynamic parameter dictionary data set to obtain an initial three-dimensional tunnel geometric model. Through dynamic parameter management, a self-correction mechanism and a Latin hypercube sampling technology, efficient automatic modeling and precise simulation optimization of the tunnel section three-dimensional geometric model are achieved, meanwhile, through unified packaging and authority control, safe and efficient management and collaborative sharing of cloud model resources are achieved, and the method is suitable for large-scale popularization and application. And the intelligent level and the engineering efficiency of tunnel model construction and application are comprehensively improved.

The invention relates to the technical field of intelligent detection, and discloses an intelligent detection method, device and equipment for a plastic container, and the method comprises the following steps: carrying out multi-angle image acquisition on preforming, blank forming, multi-layer co-extrusion and final blowing forming stages of a plastic container blow molding process to obtain an original image data set; performing targeted preprocessing on the images in each forming stage to obtain an enhanced image data set, and performing feature calculation to obtain multilayer forming feature description data; establishing a feature mapping relationship among different forming stages to obtain defect position and type data; according to the blow molding equipment control system and method, full-process monitoring of the whole blow molding process is achieved, closed-loop control over defect detection and production parameter adjustment is achieved, and the production efficiency is improved. The technical problem that interface defects of all layers in the multi-layer forming process cannot be monitored in real time through a traditional detection method is solved, and the qualification rate of plastic containers is increased.

The invention relates to an audio feature extraction method and device based on a neural network. The method comprises the following steps: performing framing processing and fast Fourier transform on an original audio signal acquired by a vehicle-mounted microphone to obtain a frequency domain feature sequence; extracting short-time energy, a zero-crossing rate, a frequency spectrum centroid and a Mel-frequency cepstrum coefficient from the frequency domain feature sequence, and combining first-order difference and second-order difference features of each feature to obtain a multi-dimensional acoustic feature point sequence; performing time sequence arrangement on the multi-dimensional acoustic feature point sequence, constructing an original feature matrix, and performing principal component analysis on the original feature matrix to obtain a feature description matrix; inputting the feature description matrix into a dynamic time feature extraction network for deep time-frequency feature analysis to obtain vehicle-mounted voice deep time-frequency features; and performing voice detection classification based on the vehicle-mounted voice deep time-frequency features, and outputting a vehicle-mounted voice detection result. According to the invention, various noise interferences in a vehicle-mounted environment are effectively suppressed, and the anti-noise capability of the system is enhanced.

The invention relates to the technical field of wood detection, and particularly discloses a wood furniture material rapid detection system, which utilizes a portable spectrum scanner to collect spectrum scanning images of a wood furniture material to be detected from a plurality of positions, and introduces a spectrum image processing technology based on deep learning. Spectral feature extraction, correlation analysis of spectral features of all the positions and complementary information enhanced polymerization processing are performed on the spectral scanning images of the multiple positions, so that global spectral feature description of the to-be-detected wooden furniture material is constructed; based on matching analysis between the spectral characteristics of the wooden furniture material to be detected and the spectral characteristics of the known wood type, rapid and accurate detection of the wooden furniture material is realized. In this way, the limitation of a traditional wood identification method and the defects of an existing spectrum detection method can be effectively overcome, and the accuracy and efficiency of wood furniture material detection are improved.

The invention provides a visible light and infrared fusion-based river channel fish banning ship monitoring method and system, and relates to the technical field of computer vision, and the method comprises the steps: firstly obtaining a visible light image sequence and an infrared image sequence of a river channel monitoring region; ship visual feature extraction and thermal feature extraction are carried out on the visible light image sequence and the infrared image sequence respectively to obtain a visible light ship feature set and an infrared ship feature set, and cross-source feature fusion processing is carried out on the two feature sets to generate a cross-source fusion feature set; and calling a pre-trained fish forbidding ship identification model to analyze the cross-source fusion feature set, generating a ship monitoring result including the ship type, the position change track and the suspected fish forbidding behavior identifier, and finally generating fish forbidding early warning information including the real-time position and behavior feature description of the suspected fish forbidding ship based on the ship monitoring result. And measures can be quickly taken to stop the fishing forbidding behavior.

The invention relates to the technical field of data analysis, provides an intelligent factory automatic monitoring method and system based on knowledge base enhancement, and realizes more accurate anomaly analysis and more effective process adjustment of an intelligent factory. The method comprises the steps of performing knowledge enhancement fusion processing on an obtained real-time monitoring data set of an intelligent factory through a pre-constructed process knowledge base and a pre-constructed monitoring rule base, and generating a process knowledge graph; performing abnormal mode recognition processing on the process knowledge graph based on a semantic matching strategy, extracting feature description of an abnormal event and a semantic association path with a historical monitoring text, and generating an abnormal mode analysis result containing abnormal root cause inference; according to the abnormal mode analysis result and the dynamic incidence relation in the process knowledge graph, an automatic monitoring report containing root cause priority ranking and optimization operation guidance is generated, and the automatic monitoring report is fed back to the intelligent factory control terminal to trigger process adjustment operation.

The invention relates to an underwater topographic measurement method based on laser radar and visual fusion, which comprises the following steps: synchronously acquiring underwater point cloud, images and physical environment sensing data, and endowing a unified space-time label to realize the space-time consistency of multi-source data; according to the method, the data quality of different modes is improved by means of preprocessing, denoising, scale normalization, feature enhancement and the like, an environment interference weight matrix is constructed in combination with an environment sensing model, feature extraction and matching algorithm parameters are adaptively adjusted according to different environment states, and multi-scale feature description, spatial consistency and physical constraint criteria are established, so that the multi-modal data quality is improved. According to the scheme, high-reliability feature matching between the point cloud and the image is achieved, finally, through environment-driven iterative optimization and fusion, the robustness and precision of space registration are improved, high-precision multi-modal data automatic registration can be stably achieved in the underwater dynamic environment, adaptability is high, and environment perception and space measurement quality is effectively improved.

The invention discloses a two-stage infrared and visible light image registration method, system and device. The method comprises the following steps of image preprocessing, contour extraction, angular point detection, feature description and matching, affine transformation estimation, multi-scale optical flow estimation, optical flow constraint and loss function, reverse resampling and fusion and error evaluation. According to the invention, rough registration is carried out by using contour angular point features, so that a preliminary alignment result can be quickly obtained; refined alignment is carried out in combination with an unsupervised optical flow network, and sub-pixel-level registration precision is achieved. The contour angular points are based on shape information of an image target, are natural and are not influenced by spectral differences, and the matching stability is enhanced through main direction and angle features. The unsupervised depth optical flow model estimates a pixel displacement field by learning consistency characteristics of an input image, and does not need to depend on annotation data. The combination can effectively eliminate the difference between infrared light and visible light, and improves the robustness and adaptability of registration.

The invention relates to the technical field of logistics automation, in particular to a full-automatic stacking method and system based on machine vision and path planning, and the method comprises the following steps: based on three-dimensional point cloud data of goods, extracting point cloud coordinates, normal vectors and curvature values of the surface of the goods, calculating the geometric segmentation range of point cloud edge features, and calculating the geometric segmentation range of the point cloud edge features; and calculating a fitting relationship between the boundary size and curvature distribution. According to the method, the surface point cloud coordinates, the normal vector and the curvature value are extracted based on the three-dimensional point cloud data, the accuracy of geometric feature description of the complex cargo surface is enhanced, the geometric center and the variance range are reasonably determined through spatial distribution analysis and feature set classification, the accuracy and stability of shape classification are improved, and the accuracy and stability of shape classification are improved through gravity center and size deviation calculation. The position and pressure distribution of the contact point are optimized, the space priority analysis of the grabbing point and the obstacle point is combined, the path planning and obstacle point elimination strategy is optimized, the path conflict is reduced, and the flexibility and efficiency of logistics operation are improved.

The invention relates to a point cloud registration method based on improved ISS-TOLDI features in combination with ICP, and belongs to the technical field of laser point cloud application. The method comprises the steps of obtaining a source point cloud and a target point cloud, and performing preprocessing; extracting feature points from the point cloud data by using an internal shape descriptor ISS algorithm; performing feature description on the extracted feature point set by using an improved TOLDI algorithm; performing coarse registration on the point cloud by using a sampling consistency initial registration algorithm; and performing fine registration on the coarsely registered point cloud data by using an iterative closest point ICP algorithm to complete point cloud registration. According to the method, the TOLDI algorithm is improved, so that the calculation complexity is reduced, the feature integrity is ensured, and the point cloud registration precision is higher.

The invention relates to the field of intelligent remote control, in particular to a digitization-based intelligent remote control method and a digitization-based intelligent remote control system for a drilling machine. The system monitors and collects drilling parameter data in real time through a sensor network, and transmits the drilling parameter data to a remote control server through a wireless communication network. In a remote control server, a data processing and analysis algorithm based on artificial intelligence and deep learning is used to carry out time sequence analysis and collaborative association feature description on the drilling parameter data, so as to capture context semantics among time sequence features of each drilling parameter. The bit pressure time sequence semantics are used as query features to query and match the optimal bit pressure recommendation decoding value from the other drilling parameter time sequence collaborative association features, and the bit pressure recommendation decoding value is compared with the bit pressure value at the current time point to generate a bit pressure remote regulation and control instruction, so that the bit pressure remote regulation and control instruction is quickly adapted to the change of geological conditions in the drilling process; and remote intelligent control of the drilling machine is realized.

The invention discloses a test method of a server system, a storage medium, electronic equipment and a program product, and relates to the technical field of computers, and the method comprises the following steps: firstly, obtaining an equipment feature vector of a to-be-tested server system; performing fuzzy matching on the equipment feature vector and a feature description vector capable of performing server system testing in a driver library; if the matching is successful, collecting hardware characteristic parameters of the server system to be tested, and dynamically determining a test threshold value of the hardware state of the server system to be tested according to the environment parameters monitored in real time; and then testing the hardware state of the to-be-tested server system based on the hardware characteristic parameters and the dynamically determined test threshold. Compared with the prior art, automatic identification and adaptation of multi-manufacturer hardware equipment are realized, the time of manual intervention and the complexity of drive configuration are remarkably reduced, the test cost is further reduced, the test efficiency is improved, and meanwhile, the test accuracy and flexibility are also improved.

The invention relates to the technical field of reservoir storage capacity measurement, in particular to a reservoir storage capacity measurement method and system based on remote sensing and point cloud data, and the method comprises the following steps: extracting a terrain surface point set based on input remote sensing image data and point cloud data, and calculating a three-dimensional coordinate value, a curvature value and a point density value of each point; and comparing and classifying curvature and density data in combination with the change of the reservoir boundary. According to the method, through comprehensive application of remote sensing image data and point cloud data, three-dimensional coordinates, curvature values and point density values are adopted to accurately extract topographic features, scientific division and feature description of sub-regions are achieved, refined three-dimensional grid parameters are generated through fitting and interpolation calculation, and the accuracy of the three-dimensional grid parameters is improved. The terrain modeling precision and the space geometry description capability of a complex area are improved, boundary node coordinates and normal vectors are dynamically adjusted, the grid continuity is optimized, the integrity of a boundary transition area is ensured, and the boundary complex volume is accurately described by adopting unit volume subdivision and boundary correction.

Provided are a multimodal image matching method and system, terminal device, and storage medium. The method includes: performing self-supervised feature extraction on an optical image and a synthetic aperture radar (SAR) image to obtain a repetitive feature point between the optical image and the SAR image; segmenting the optical image and the SAR image into a first image block sequence based on the repetitive feature point, and performing feature extraction on the first image block sequence through a dual-branch network to obtain feature description vectors of the optical image and the SAR image respectively, where the dual-branch network includes a first branch network for extracting a global feature and a second branch network for extracting a local feature; and performing feature matching on the optical image and the SAR image based on the feature description vectors to obtain a matching point pair between the optical image and the SAR image.

The invention relates to the technical field of image extraction, and provides a remote sensing image processing system, which comprises a server, an unmanned aerial vehicle, a data acquisition module, a feature extraction module, an image fusion module, an evaluation module and a result output module, the image fusion module preprocesses the satellite image and the image data to generate a multispectral image and a high-resolution image respectively, and performs fusion processing on the multispectral image and the high-resolution image to form a fused image, and the feature extraction module extracts spectral features, texture features and shape features from the fused image; the evaluation module evaluates the abnormal position according to the multi-dimensional feature description data to form an evaluation result, and the result output module generates an early warning prompt according to the evaluation result.

The invention relates to the technical field of unmanned aerial vehicle geological survey, and discloses a path planning method and system for unmanned aerial vehicle geological survey, and the method comprises the steps: obtaining the image, spectrum and topographic data of a remote mountainous area through a multispectral sensor and a laser radar, and recognizing potential vein abnormal points through data fusion and geological feature analysis; and constructing a geological interestingness weight map and planning a flight path. Dense sampling flights are performed in a high interestingness region, high resolution data are processed in real-time to identify key reconnaissance targets, a weight map is updated, and a flight trajectory is dynamically adjusted. Through the closed-loop self-adaptive exploration process, accurate positioning and feature description of the hidden vein are realized, the mineral exploration efficiency is improved, the labor cost and the safety risk are reduced, and an innovative solution is provided for mineral resource exploration in remote areas.

The invention relates to the technical field of augmented reality application, and discloses an augmented reality system and method for immersive experience. The method comprises the following steps: collecting dynamic spatial data of a physical environment in real time, and synchronously obtaining an interactive behavior data stream of a user terminal; performing environment semantic modeling on the dynamic spatial data to generate multi-level feature description of a physical environment, and determining a rendering priority sequence of virtual-real superposition content according to the multi-level feature description; extracting behavior pattern characteristics in historical interaction data of the user, performing immersion correlation analysis on the behavior pattern characteristics to obtain environment cognitive preference parameters of the current user, and generating a virtual-real interaction event sequence in combination with the environment cognitive preference parameters and the interaction behavior data flow; and dynamically compensating the virtual-real synchronization error in the immersive experience process according to the rendering priority sequence and the virtual-real interaction event sequence. According to the method, the accuracy and naturalness of virtual-real fusion can be improved, the personalized requirements of the user are met, and the overall immersive experience effect is enhanced.

The invention relates to a method and a system for realizing personalized recommendation based on multi-feature fusion face recognition, and aims to provide real-time, efficient and accurate recommendation service, the method comprises the following steps: collecting a face image of a target audience in real time through a camera device, and preprocessing the image to extract a face region; running a face recognition algorithm in the edge computing device, and extracting multi-modal features including age, gender, appearance and style features; a comprehensive feature vector is generated by using a Transform model through a feature fusion module, and style classification and appearance classification are realized; according to the method, user feature vectors and a content database are matched on the basis of cosine similarity, personalized recommendation content is generated, the weight of a classification model is dynamically optimized in combination with user feedback, and dynamic behaviors and appearance features of a user are accurately captured through a time sequence analysis module, a dynamic style analysis module and a deep appearance analysis module; and comprehensively generating user feature description by combining vision, voice and character multi-mode information.

The invention discloses a multi-modal remote sensing image matching method, particularly relates to the technical field of remote sensing image processing, and is used for solving the problem of multi-modal image matching. The method mainly comprises the following steps of: 1, improving a phase consistency model, and constructing a phase-moment weighted joint direction feature in combination with a maximum moment and a minimum moment to replace the feature expression of the traditional image gradient; 2, implementing a point product fusion strategy on the phase-amplitude characteristics extracted by the phase consistency model and the maximum moment, and constructing phase-moment weighted joint amplitude characteristics; and 3, on the basis of the steps 1 and 2, identifying the direction of the feature points and screening local peak values to determine the main direction. Three values adjacent to a peak value are selected, and the peak value position is interpolated through parabola fitting so as to improve the matching precision; and step 4, constructing a logarithm polar coordinate descriptor based on regularization non-uniform partition to generate a feature description vector. Through the mode, high-precision and high-efficiency matching of the multi-mode remote sensing image can be realized.

The invention discloses a cultural heritage digital reconstruction system based on deep learning, and the system comprises a data collection module, a data preprocessing module, a feature description module, a modeling module, and a model optimization module. The feature description module is used for acquiring data processed by the data preprocessing module, feature extraction is performed on point cloud data through a point cloud processing network in deep learning, the data preprocessing module is used for data preprocessing, the data preprocessing comprises correction, denoising, color correction and cutting, and the modeling module is used for modeling the point cloud data according to the extracted features. Three-dimensional reconstruction of the cultural heritage is carried out, and a model optimization module is used for smoothing a generated cultural heritage model, filling the deficiency and eliminating noise; the cultural heritage digital reconstruction method has the advantages that the digital system has rich details and sense of reality, people can conveniently visit and learn, and the efficiency and precision of cultural heritage digital reconstruction are improved.

The invention discloses a user-defined cataloguing template generation method and system, and the method comprises the steps: obtaining a program feature description, obtaining a business demand description, and carrying out the program feature description and semantic coding of the program feature description through employing a natural language processing and analysis technology based on deep learning, thereby obtaining a user-defined cataloguing template. Therefore, the definition coding template is intelligently generated according to the dynamic memory interaction representation between the program characteristic description semantic features and the business requirement description semantic features. Through the mode, the most suitable cataloguing template can be automatically generated according to the specific demand and demand feedback of each user, and personalized services are provided. And user feedback can be considered in real time, and the cataloguing template is automatically updated according to latest data and changed contents, so that the cataloguing template is ensured to always fit an actual service scene.

The invention provides a task unloading method for an emergency rescue scene under a space-air-ground integrated network, and relates to the technical field of calculation unloading, and the method comprises the steps: unifying the feature description of task unloading; establishing a joint optimization problem model by taking minimization of unloading time delay and power consumption as an optimization target; determining a task unloading priority based on a firefly algorithm; constructing a reward mechanism of a deep reinforcement learning model according to the task unloading priority, and solving the joint optimization problem model by using a deep reinforcement learning algorithm to obtain a plurality of task unloading schemes; performing simulation verification based on the task unloading scheme to obtain evaluation data; parameters of the joint optimization problem model are corrected according to the evaluation data, and a task unloading optimal model is obtained; and solving the optimal task unloading model to obtain a final task unloading scheme. Reasonable and effective resource allocation is carried out on a large number of tasks which emerge in an emergency rescue scene and need to be processed in real time, and the scheduling efficiency is improved.

The invention belongs to the technical field of intelligent clothing pattern making, and relates to a text-driven intelligent clothing pattern generation method, which specifically comprises the following steps of: inputting a user-defined clothing pattern feature description text into a trained intelligent clothing pattern generation model to generate clothing pattern data; jointly inputting the generated garment template data and a user-defined action feature description text into a trained learning-based three-dimensional virtual fitting model, and setting parameters of the inelastic fabric to obtain garment template data of the inelastic fabric; the real elastic fabric parameters are adopted to optimize the garment template data of the inelastic fabric, and garment template data of the real elastic fabric are generated; and finely adjusting and storing the garment template data of the real elastic fabric according to individual requirements. According to the method, the generation efficiency and quality of the garment template are remarkably improved, the fitness and comfort of the garment in a dynamic scene are effectively improved, and an innovative solution is provided for intelligent garment pattern making.

The invention discloses a hunting camera imaging quality optimization method and system based on multimode data fusion, and relates to the related field of image processing, and the method comprises the steps: obtaining the data source features of multimode data, and building a multimode data feature description library; analyzing the imaging composition factors, and performing hierarchical decomposition on the imaging composition factors to obtain imaging hierarchies; performing imaging quality dimension correlation analysis on the imaging hierarchy to obtain a forward quality factor and a reverse quality factor of the imaging hierarchy; establishing a compensation effect relationship between each data feature in the multimode data feature description library and the forward quality factor and the reverse quality factor; and based on the compensation effect relationship, performing imaging compensation optimization on each data feature in the multimode data feature description library. The technical problems that the optimization effect of the imaging quality of an existing hunting camera is limited, and the robustness and accuracy of the imaging quality are insufficient are solved, and the technical effects of improving the optimization effect of the imaging quality and improving the robustness and accuracy of the imaging quality are achieved.

The invention provides a satellite fault diagnosis method and system based on multi-source information fusion. The satellite fault diagnosis method comprises the steps that firstly, a multi-source monitoring data set of platform system state data, load system working data and measurement and control link interaction data is generated in the satellite testing process based on an emergency fast response satellite testing system; then performing multi-source information association extraction processing on the multi-source monitoring data set to generate an association feature set reflecting a coupling relationship between systems; then inputting the associated feature set into a pre-trained satellite fault diagnosis model for fault mode analysis processing to obtain a fault feature description containing a fault trigger node and an influence link; a preset fault knowledge base is matched based on the fault feature description, and a fault diagnosis result containing a fault type identifier and a propagation path is generated; and finally, generating a satellite fault handling strategy according to a fault diagnosis result. The method can comprehensively and accurately diagnose the satellite fault and improve the satellite reliability.