1043 results about "Match algorithm" patented technology

The invention relates to a risk management and control method and system based on real-time behavior analysis, and the method comprises the steps: carrying out the structural processing of multi-source behavior data through lightweight protocol decoding and behavior label embedding, and constructing an original behavior data set of a user and an entity; extracting multi-dimensional behavior characteristics by using a sliding window analysis and sparse representation mechanism, and constructing a user behavior graph by combining graph embedding learning; constructing a time-sensitive behavior trend model through streaming modeling and an incremental learning strategy, identifying an abnormal evolution trajectory in real time, and introducing a dynamic risk threshold regulation and control mechanism; adopting a high-throughput flow data processing and fast similarity matching algorithm to construct a fusion discrimination model, giving risk levels to abnormal behaviors and classifying the abnormal behaviors; and finally, performing closed-loop optimization in combination with a historical treatment effect. The system has the advantages of high real-time performance, high calculation efficiency, adaptability to complex network environments and the like, and the network security protection capability can be effectively improved.

The invention provides a multi-target tracking detection method and system based on cascade matching and trajectory confirmation, and relates to the technical field of digital video monitoring and tracking, and the method comprises the steps: obtaining a personnel construction video, and decomposing a video frame into a plurality of images; identifying a target in the current frame of image based on an improved YOLOv5 network, obtaining a target detection frame, and obtaining a prediction trajectory frame of the current frame through a Kalman filtering algorithm based on the trajectory frame of the previous frame; performing multi-target tracking on the target detection frame and the prediction trajectory frame of the current frame by using a DeepSort algorithm, respectively obtaining motion features and appearance features of the target detection frame and the prediction trajectory frame, performing cascade matching on the motion features and the appearance features of the target detection frame and the prediction trajectory frame by using a Hungary algorithm, and performing matching optimization by using an IOU matching algorithm; and carrying out fusion updating on the successfully matched target detection frame and prediction trajectory frame by using a Kalman filtering algorithm, and replacing the original prediction trajectory frame to obtain a tracking result.

The invention discloses an intelligent interactive enterprise management simulation system and a method thereof. The method comprises the following steps: constructing a multi-level state causal graph model with a multi-dimensional feature tag; fusing interaction data of the user, constructing a behavior intention tensor, and identifying a situation transition intention through a multi-modal fusion reasoning algorithm; a personalized interaction strategy is dynamically generated by a context-driven interaction optimization generation algorithm; a context semantic tensor is constructed based on a semantic context dynamic matching algorithm, a semantic compression response is realized in combination with a current intention and a historical information path, and a future strategy plan is actively generated through a causal relationship backstepping inference device; and establishing a situation feedback learning and weight updating mechanism, and dynamically adjusting a state causal graph, an intention tensor and an interaction strategy parameter to realize self-evolution closed-loop optimization of the model. Context changes can be perceived in real time, and the decision intention of the user can be deduced deeply.

The invention provides an intelligent human resource training recommendation method and system, and relates to the technical field of data processing, and the method comprises the steps: obtaining post data, skill data, performance data, training records and development target data of a target, building an employee database, and constructing a knowledge graph; post data, skill levels, performance expressions, training records and individual development targets of the employees are integrated to form a comprehensive portrait; dividing all courses according to difficulty levels, selecting courses with corresponding difficulty according to post requirements and performance data of the employees, and generating a group of preliminary course lists matched with current skill levels and post requirements of the employees; semantic analysis is carried out on skill requirements of employee portraits and recommended course contents, a semantic analysis result is obtained, and according to employee portrait data, a semantic matching algorithm is used to calculate the matching degree between the employees and each training content; and according to the matching degree scores of the employees and the training contents, generating a course list subjected to semantic matching optimization.

The invention discloses a motor fault detection method and system based on voiceprint recognition. According to the method, an annular microphone array is adopted to collect motor sound signals in a non-contact mode, a three-channel time-frequency data set is constructed through empirical mode decomposition (EMD) and a Mel-frequency cepstral coefficient (MFCC), fault diagnosis is carried out in combination with a CNN + ResNet network, and dynamic time warping (DTW) and CNN fusion matching is supported. The system comprises a preprocessing module, a fault template library and a matching algorithm, integrates wavelet denoising and multi-beam acquisition technologies, covers a frequency band of 50Hz-20kHz, can display a fault type and trend analysis in real time, and triggers secondary verification when the confidence coefficient is insufficient. According to the scheme, the anti-interference capability is improved through array signal processing, model parameters are optimized in combination with transfer learning, non-contact detection is achieved, the real-time performance and accuracy of fault diagnosis are remarkably improved, and the method is suitable for industrial motor health monitoring.

The invention discloses an LLM capability enhancement method of a hybrid enhancement strategy, and particularly relates to the technical field of natural language processing. The method comprises the following steps: obtaining corpus data and external literature data of a target application field, carrying out denoising, word segmentation and semantic indexing processing, and establishing a searchable heterogeneous knowledge base; secondly, classifying the corpus data by adopting a topic analysis and word vector clustering method to form a basic corpus set; performing multi-round parameter updating on the large language model by using a domain fine tuning algorithm based on the basic corpus set, and setting a fusion threshold value between a new parameter and an original parameter; and retrieving related literature fragments from the heterogeneous knowledge base through a matching algorithm, screening content conforming to field correlation by utilizing semantic similarity evaluation, fusing the content with the fine-tuned model, processing a fusion result by adopting a context fusion algorithm and an entity linking method, completing syntactic analysis, and generating a precise solution oriented to the target application field.

The invention discloses a three-dimensional stomatognathic model reconstruction system based on multi-modal data fusion. The system comprises a multi-modal data input unit, a template deformation reconstruction unit, a registration fusion unit, a multi-source data integration unit and an output unit. Through fusion processing of a CBCT image, an oral cavity vision measurement model and facial scanning data, a body deformation algorithm is adopted to couple biomechanical characteristics to realize craniojaw template deformation, and a non-rigid ICP algorithm is combined for dynamic regulation and control to realize facial template adaptation. A deep neural network is innovatively constructed to segment CBCT gingival data, the CBCT gingival data is fused with an oral cavity vision measurement model, and high-precision tooth reconstruction is realized by applying a differential geometry multi-scale curvature field segmentation and adversarial edge optimization technology. Through a composite registration strategy combining adaptive rigid registration and non-rigid registration, an occlusal plane constraint mechanism and an orbital curvature extreme point matching algorithm are innovatively introduced, finally, multi-source data high-precision registration fusion is realized, and a three-dimensional oral-jaw system model with anatomical structure integrity and clinical precision can be generated.

The invention discloses an intelligent management system for a service consultation platform, and the system comprises the steps: processing data through a data collection and processing module; using a data fusion unit to construct a feature matrix for the cleaned multi-source data; based on a demand prediction module, generating a prediction result of the user consultation demand; user input is recognized through a semantic analysis and question and answer module; the analyzed semantic information is transmitted to a knowledge management module, matched content is retrieved from a knowledge base based on a semantic similarity matching algorithm, and answers are generated after ranking according to priorities; information in the service process is collected through the service quality dynamic evaluation module for scoring, an optimization scheme is made through the service optimization strategy generation module, and the optimization scheme is fed back to the evaluation module to achieve closed-loop management. According to the method, the prediction capability and the service efficiency of the platform are remarkably improved, and more efficient and more personalized consultation experience is provided for the user.

The invention relates to the field of knowledge graph construction, in particular to a policy knowledge graph construction method and system based on digital human interaction data analysis. The policy knowledge graph construction system based on digital human interaction data analysis comprises a knowledge graph preliminary construction module, a first graph updating module, a second graph updating module and a digital human interaction module. According to the method, the policy source webpage content change is monitored in real time, and the question information in the digital human interaction data is deeply mined, so that the full-life-cycle dynamic maintenance of the policy knowledge graph is realized; on one hand, a webpage policy updating event is accurately captured, and knowledge injection is automatically completed in combination with a semantic unit matching algorithm; and on the other hand, the conflict characteristics questioned by the user in the interaction data are extracted through dialogue semantic analysis, atlas correction is triggered after confidence assessment and multi-stage verification, it is ensured that the end-to-end timeliness from policy release to user perception is controlled within a reasonable period, and the policy response accuracy of the digital human service is remarkably improved.

The invention relates to the technical field of meteorological observation, and provides a ground hail identification method and system based on a hydrogel classification result, and the method comprises the steps: carrying out the time-space correlation of multi-source hail data through a time-space matching algorithm, and obtaining a hail event data set of time-space matching; through a dynamic membership function optimization algorithm, self-adaptive phase state identification is carried out on the dual-polarization radar data, and multi-elevation hail phase state characteristic parameters containing rain-ice mixture categories are obtained; based on the multi-elevation hail phase state characteristic parameters, performing integrated preprocessing on the multi-source meteorological data to obtain standardized multi-dimensional meteorological characteristic data fused with phase state characteristics; performing unsupervised pre-training and supervised fine-tuning training on the DCNN-DBN hybrid neural network through the standardized multi-dimensional meteorological feature data to obtain a ground hail recognition model; and outputting a hail falling area identification result through the ground hail identification model. According to the invention, the distinguishing capability of easily-confused phase states is improved, and the false alarm rate and the missing report rate of hail identification are reduced.

The invention relates to the field of human resource management, and discloses a tobacco enterprise human resource management auxiliary calibration method based on big data, and the method comprises the steps: obtaining multi-source heterogeneous data related to enterprise internal human resources, and constructing a structured human resource data model in combination with a data standardization processing mechanism and an abnormality elimination strategy; post portrait modeling is carried out on the structured human resource data model, a capability dimension nesting analysis method is introduced, key capability factors and weight distribution required by each post are extracted, and a post capability demand graph is constructed; based on the post capability demand map, fusing the staff portraits and the historical job data, and identifying the deviation between posts and the staff through a multi-dimensional feature matching algorithm to form a preliminary calibration suggestion set; and a dynamic service association analysis method is introduced, and key matching parameters in the preliminary calibration suggestion set are dynamically corrected in combination with latest service demand data and real-time task assignment information. The method has the advantage of improving the management efficiency.

The embodiment of the invention provides a multi-modal knowledge graph construction method in cross-media retrieval. The method comprises the steps that extracted multi-modal features are mapped to a multi-modal feature space through a linear transformation layer; in the multi-modal feature space, the intra-modal attention weight of each modal feature is calculated according to a self-attention mechanism, the cross-modal attention weight of different modal features is calculated according to a cross attention mechanism, the two weights are fused to obtain a final fusion weight, each modal feature is weighted and input into a graph attention network, and the multi-modal feature is obtained. Obtaining a multi-modal fusion graph structure; performing semantic analysis on each modal feature, matching with a preset multi-modal semantic knowledge base, determining potential semantic association, performing semantic alignment on the multi-modal fusion graph structure according to a preset graph matching algorithm and the potential semantic association to obtain a multi-modal knowledge graph, performing cross-modal data retrieval according to the multi-modal knowledge graph, and performing cross-modal data retrieval according to the multi-modal knowledge graph. The multi-modal data cross-media retrieval method and device can improve the efficiency and accuracy of multi-modal data cross-media retrieval.

The invention discloses an infrared unmanned aerial vehicle multi-target tracking method, and relates to the field of computer vision. The method comprises the following steps: reading a video of an infrared camera, and detecting a target by using YOLOv8 to obtain information; a camera motion compensation correction position is introduced, and a Kalman filtering algorithm is adopted to predict a track and determine a state; marking a low-matching-degree target through a pre-matching strategy; extracting appearance characteristics of the target by using RepO-LightMBN, calculating a cost matrix by combining an appearance characteristic distance and motion information, and associating a detection frame and a track through cascade matching and a B-IoU + matching algorithm; matching the last observation value and detection value of the track by adopting B-IoU + and OCR matching algorithms according to the mismatched target and track in cascade matching; and finally, updating a matched track state by using Kalman filtering, deleting an unmatched track and outputting a result. The method effectively improves the speed and precision of multi-target tracking of the unmanned aerial vehicle in the infrared mode, is innovative and practical, and can be used in the fields of anti-unmanned aerial vehicle monitoring and the like.

The invention discloses a dynamic load balancing optimization method for AI intelligent computing system server equipment, which relates to the technical field of load balancing optimization, and comprises the following steps: acquiring equipment performance data, and preprocessing the acquired equipment performance data; based on the preprocessed equipment performance data, extracting equipment state features through time sequence analysis and periodic fluctuation detection; predicting the future load change of the equipment based on the state characteristics of the equipment, dividing the priority of the equipment according to the prediction result, and analyzing the resource demand; generating a resource allocation strategy by applying a resource matching algorithm according to the device priority and the resource demand; and executing the resource allocation strategy, receiving feedback information in real time in the execution process, and optimizing the resource allocation strategy according to the feedback information. According to the method, the response speed and the service quality of the server equipment are remarkably improved, and the resource utilization efficiency is maximized.

The invention provides a network defense capability verification method and system based on intrusion attack simulation. According to the method, network dynamics and a photoacoustic effect simulation technology are creatively fused, and network abnormal traffic equivalent to real attacks is dynamically excited by constructing a photoacoustic coupling waveform driven by network topology; reversely analyzing the vulnerability characteristics based on the protocol interaction entropy, and generating an attack instruction with a space-time cooperation characteristic; utilizing a phase matching algorithm to precisely couple the attack behavior and the network dynamic disturbance to form a defense response track capable of being quantitatively analyzed; and finally, through an asymmetric correlation model, analyzing a dynamic relationship between trajectory deformation and a node survival state, and realizing objective quantitative evaluation of defense efficiency. According to the technical scheme provided by the embodiment of the invention, high-precision quantitative verification of the virtual-real combined network security defense capability can be realized, and the real-time performance and credibility of defense strategy evaluation are improved.

The invention relates to the technical field of gesture recognition, in particular to an anti-interference optimized gesture recognition method. Comprising the following steps: acquiring a gesture video stream through a camera, constructing a dynamic background model by using a frame difference method and a Gaussian mixture model, eliminating a static background and interference, and extracting a target area image; performing local brightness histogram analysis on the target region image, and optimizing the image quality by adopting a region adaptive compensation algorithm and a multi-scale edge enhancement technology; positioning a gesture area in real time by using a color histogram and a feature matching algorithm, and dynamically updating a gesture track in combination with Kalman filtering; and extracting gesture shapes, tracks and dynamic mode features through deep learning, comparing the features with a standard model library, and outputting gesture categories and corresponding function instructions. According to the method, a multi-level optimization strategy is adopted for a complex background, a dynamic target and a changeable illumination environment, so that the anti-interference capability and the recognition precision of gesture recognition are improved.

The invention discloses an archive retrieval method and system based on cloud computing, and the method comprises the steps: receiving retrieval request information inputted by a user, and analyzing a retrieval intention according to the retrieval content in the retrieval request information, the historical retrieval behavior of the user and a retrieval field database by using a context perception semantic analysis model, generating a user retrieval semantic vector in combination with the retrieval intention; the method comprises the following steps: constructing an archive data index map for archive data stored in a distributed manner in a cloud storage environment; according to the user retrieval semantic vector, a search domain related to retrieval semantics is dynamically positioned in the archive data index map in a multi-layer projection calculation mode; and in the search domain, screening a candidate archive set according with the query intention by using a matching algorithm of multi-modal semantic fusion, and sorting and displaying the candidate archive set. By utilizing the embodiment of the invention, the accuracy and efficiency of file retrieval and the user experience can be improved.

The invention discloses a multi-agent cooperation enhancement method, system and equipment based on a knowledge graph, and the method comprises the steps: obtaining original data in an external environment, carrying out the preprocessing and feature extraction of the original data, generating a knowledge triple, storing the knowledge triple in a local knowledge graph, and submitting the knowledge triple to a shared knowledge graph for knowledge updating; when a to-be-executed task is received, decomposing the to-be-executed task by utilizing the large language model and querying global knowledge in the shared knowledge graph and local knowledge in the local knowledge graph to obtain a plurality of sub-tasks; a bipartite graph minimum cost matching algorithm is adopted to match a plurality of sub-tasks with the capability and availability of each agent to generate a preliminary task allocation scheme, and a large language model is utilized to optimize the preliminary task allocation scheme to generate an optimal task allocation scheme; and sending each task allocation knowledge fragment in the optimal task allocation scheme to a corresponding agent for collaborative execution through a semantic communication protocol.

The invention relates to the technical field of data processing, and provides a network device discovery method, which can perform iterative retrieval under a target network according to an ARP table, provides a more comprehensive view, and is beneficial to monitoring the health condition and the network load condition of the target network. Legality detection of an IP address is carried out based on a rule base; legality detection of an MAC address is carried out based on a multi-level detection mechanism; uniqueness detection is carried out based on a device fingerprint; subnet suitability detection is carried out based on a subnet mask matching algorithm; a self-adaptive network equipment discovery algorithm combined with multi-dimensional data analysis can reduce redundant data, eliminate invalid information and improve the accuracy and management efficiency of equipment discovery; information generation is carried out based on the initial network equipment data to obtain the network equipment view, so that more accurate network equipment discovery is carried out.

The invention relates to the technical field of rehabilitation training detection, in particular to a rehabilitation training detection method and system based on artificial intelligence, a standard action library is constructed through standard action videos shot at multiple angles, and track and angle features of key joints are extracted for user training comparison; the skeleton key points of the user are extracted in real time through a MoveNet network, and efficient posture recognition in a home scene is achieved; analyzing position difference, angle change and acceleration characteristics by combining a space-time sequence matching algorithm, generating a dynamic matching degree index, and positioning a deviation joint to generate a correction prompt; introducing an attention mechanism model, learning the contribution degree of each joint to cycle recognition, dynamically selecting a dominant joint for action counting, recognizing starting and ending points of an action cycle through an acceleration curve, and finishing effective action statistics in combination with a dynamic threshold value, so that the counting accuracy and the self-adaptive capability are improved; therefore, the training cost is reduced, the evaluation credibility is enhanced, and accurate statistics and analysis of rehabilitation training data are realized.

The invention discloses a computer network security situation awareness system and method, and relates to the technical field of computer network security, and the method comprises the steps: generating a dynamic gene pool through an antigen-antibody matching algorithm based on an initial quantum trust vector, and building a mapping relation table of an antigen feature vector and an antibody defense strategy; triggering a quantum alarm according to an entanglement entropy mutation event in the real-time quantum state flow data, matching a biological antibody strategy corresponding to a current network attack feature based on a mapping relation table, and fusing the quantum alarm and the biological alarm to generate an attack path topological graph; the network security situation is perceived by analyzing the quantum state change of the abnormal node ID and combining an attack path topological graph and a dynamic gene pool. Quantum entanglement pairs are distributed to network nodes through the quantum key distribution center, and initial quantum trust vectors are generated, so that the unknown attack resisting capability of the network is remarkably improved, and efficient and accurate network security situation awareness is realized.

The invention relates to the technical field of wind power equipment monitoring, and discloses a wind power gear box intelligent fault early warning method and system based on machine learning. The method comprises the steps that multi-source monitoring data such as vibration signals, temperature data and oil analysis data of the wind power gear box are acquired, and multi-scale operation characteristics are extracted through time-frequency conjoint analysis; key fault sensitive features are determined through an adaptive feature selection algorithm, and a dynamic fault feature weight matrix is constructed in combination with a historical fault case library; multi-modal data fusion is adopted to generate an enhanced fault feature set, and modal decomposition is carried out on the enhanced fault feature set to obtain a trend component and a fluctuation component; a fault evolution feature space is constructed by using a deep neural network based on two components, then a fault development mode is identified by using a time sequence mode matching algorithm, and finally a graded early warning signal is generated according to a matching degree with a preset mode, so that fault features can be comprehensively captured, and safe operation of a wind power gear box is ensured.

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 time-space clustering-based instant retail intelligent distribution scheduling method, medium and system, and the method comprises the steps: obtaining the geographic information of a hierarchical geographic unit through an electronic fence, collecting the data of a to-be-distributed order, and calculating a distribution time window through a time window prediction model, so as to generate time-space clustering information; according to the method, orders with overlapped delivery time windows in the same geographic unit are aggregated into task packages with the same address, the task packages are dynamically allocated through a matching algorithm based on the real-time state of a rider, and algorithm parameters are updated according to delivery feedback. According to the invention, the accuracy of order aggregation and the rationality of task allocation are obviously improved, and the refined scheduling of transport capacity resources and the optimization and improvement of the overall distribution efficiency are realized.

The embodiment of the invention discloses a multi-sensor fusion anti-degradation SLAM mapping method and system. The method can effectively solve the problem of pose drift of a robot in a mapping process in structure degradation environments such as an indoor long corridor, constructs a globally consistent three-dimensional point cloud map and a robot trajectory, and comprises the following steps: realizing depth coupling of an IMU and a wheel speedometer based on extended Kalman filtering, and generating high-frequency pose prediction; denoising, down-sampling and motion distortion correction are carried out on the 4D laser radar point cloud, and the normal vector and intensity characteristics of the point cloud are extracted; a normal vector and intensity feature enhanced scanning matching algorithm is adopted, and a target function is optimized through a multi-feature weight, so that the matching precision in a degradation scene is improved; loopback detection is realized through candidate key frame screening and geometric registration verification, and a closed-loop constraint is incorporated into a factor graph for global correction; and finally, incrementally updating the global point cloud map and carrying out consistency optimization, and outputting a robust three-dimensional point cloud map and a high-precision robot track.

The invention discloses an automobile body welding seam detection method and system based on machine vision, and particularly relates to the technical field of welding seam detection. The method comprises the following steps: capturing a welding seam image in real time through a high-definition camera, positioning a welding seam by using a template matching algorithm, calculating the width of the welding seam by using a dynamic window scanning technology, identifying a complex form area, extracting curvature change and surface roughness characteristics of the welding seam, and evaluating the adaptability of the algorithm to the complex form; classification processing is carried out according to the adaptability level, and the system automatically judges that a high-adaptability-level area is qualified; generating early warning and storing data in the low-adaptation-level region; the accuracy of a general adaptation level area is improved through a dynamic optimization algorithm, the detection precision is effectively improved, reworking and missing detection are reduced, and the adaptability of the system to various welding seam forms is improved.

The invention belongs to a synchronous localization and mapping (SLAM) method in the field of robots, and discloses a binocular vision SLAM method based on a deep learning feature extraction and matching algorithm. The system comprises three modules: a front-end tracking module, a local mapping module and a loopback detection module. For each frame of input binocular image, firstly, feature points of the image are extracted, and then frame-to-frame matching is used to track a current image frame and determine whether the current frame is set as a key frame. In the local mapping module, matching from a key frame to a local map is used to obtain a more accurate pose and a global map, and in addition, the loopback detection module is used for inhibiting accumulative errors of a large scene. Experiments on a public data set and a data set collected by a robot platform show that robust, accurate and globally consistent pose estimation and mapping are realized by the method, and quick real-time operation can be realized on an embedded platform at a speed exceeding 10 FPS.

The invention relates to the technical field of semiconductor manufacturing, in particular to an accurate detection method and system for a flat-edge sheet wafer placement rotary chuck, and the method comprises the steps: when a wafer is placed on the rotary chuck, scanning the lap joint condition of a wafer edge and a chuck contact area through a laser sensor, and obtaining the real-time distribution data of an edge lap joint sheet; flat edge position information is extracted from the edge lap joint distribution data, an image matching algorithm is adopted to compare a preset orientation reference, and a specific angle value of orientation deviation is determined; according to the orientation deviation angle value and the edge lapping piece distribution data, the rotating speed and the angle of the rotating chuck are adjusted through a cooperative control algorithm, and a final positioning result of the wafer on the chuck is obtained; after a final positioning result is obtained, the in-place state of the wafer is classified and judged through a deep learning model, and whether the residual deviation or wafer lapping phenomenon exists or not is determined; and extracting abnormal data from a classification judgment result, and adjusting collaborative parameters of carrying and placing according to the abnormal data to obtain an optimized process control scheme.

The invention relates to the technical field of crane line fault diagnosis, in particular to a crane line fault diagnosis system and method based on multi-source data fusion, which comprises a data acquisition and processing unit, a mechanical and electrical coupling characteristic unit and a characteristic fusion and fault quantification unit, the three-axis vibration acceleration and the three-phase current waveform of the track are obtained through the data collecting and processing unit, the mechanical and electrical coupling characteristic unit conducts three-dimensional vector synthesis and wavelet packet decomposition on vibration data, and a time-space incidence matrix of harmonic distortion and vibration is constructed. And the feature fusion and fault quantification unit outputs coupling factors by using a bidirectional long-short-term memory network and an attention mechanism, and outputs a fault probability value through a dynamic time warping matching algorithm after time-frequency domain analysis and sample entropy judgment, so that time-space correlation modeling and dynamic fault matching of multi-source data are realized. And the fault positioning precision and the diagnosis accuracy are improved.

The invention discloses a multi-mode driven cross-industry digital twinning universal platform architecture and an implementation method, and relates to the technical field of digital twinning and artificial intelligence. The method comprises the following steps: establishing a multi-modal driven cross-industry digital twinning universal platform, deploying a multi-source heterogeneous data acquisition component in a data access layer to access text, image and time series data, and converting unstructured data into a unified feature space by adopting a Transform-GNN cross-modal encoder in a multi-modal fusion layer; in the large model scheduling layer, feature vectors are analyzed through a multi-modal large model center based on an industry knowledge graph, an algorithm is dynamically matched, and an initial decision strategy is generated; the method comprises the following steps of: establishing a parameterized template library, and supporting security cooperative training of a third-party algorithm scheduling engine on a third-party algorithm, and deploying a lightweight digital twin engine in a twin engine layer: establishing the parameterized template library: pre-defining three templates of geographic space, equipment assets and business processes; deploying the twin model to an edge node by adopting a knowledge distillation method; in the interactive application layer, loading the BIM / GIS model in a lightweight manner through a low-code tool, and completing scene construction through a dragging component; and rendering a twin state in real time through a three-dimensional cockpit, analyzing a natural language instruction and performing corresponding operation.