207 results about "Data registration" patented technology

The invention discloses a concrete crack depth detection method and system based on multi-modal data fusion. The method comprises the following steps: synchronously obtaining a visible light image sequence and a thermal imaging image sequence of a concrete crack; the thermal imaging image sequence is obtained based on adjustable thermal excitation; and through a preset multi-modal data registration algorithm, according to the visible light image, predicting a registration displacement vector field to generate a pseudo-infrared image corresponding to the enhanced visible light image, and migrating a temperature field of the thermal imaging image at the same moment and under the same picture to the pseudo-infrared image to generate a fusion modal image, obtaining a fusion modal image sequence; and through a preset heat conduction inversion model and a temperature attenuation characteristic curve generated based on the fusion modal image sequence, obtaining crack depth data and generating a three-dimensional crack map so as to visually present concrete crack depth detection data. According to the invention, the universality and accuracy of concrete crack depth detection can be improved.

The invention relates to the technical field of data processing, can be applied to business scenes of financial science and technology, medical health and the like, and discloses a data processing and analysis method, device, equipment and medium, and the method comprises the steps: obtaining a data source set, and registering a source label and field mapping relation; executing extraction, cleaning, conversion and loading in the data processing assembly line based on the data source set, the source label and the field mapping relation to generate a processing table set; performing quality verification and exception handling on the processing table set to generate a verified processing table set; generating an index cloud based on the verified processing table set and the configuration strategy; the index cloud is pushed to the analysis tool set through the interface transmission channel, and the analysis tool set generates analysis output according to the index cloud. According to the method, through unified data registration, standardized processing and quality verification, the index cloud is generated in combination with the configuration strategy and pushed to the analysis tool set, the analysis result is generated and transmitted, the data consistency is ensured, and the real-time performance is improved.

The invention discloses a brain multi-modal multi-sequence data registration method and device based on deep learning. The method comprises the steps of performing first iteration processing on a target image and a first moving image to obtain a first deformation field, wherein the first iteration processing comprises image alignment constraint processing of the target image, smooth constraint processing of the first deformation field, and area alignment constraint processing of a tumor area in the image; registering the first moving image to the target image based on the first deformation field to obtain a second moving image; performing second iteration processing on the target image and the second moving image to obtain a second deformation field; and registering the second moving image to the target image based on the second deformation field to obtain a registered moving image. In the process of performing unsupervised training on the deep learning model, after multiple times of iterative processing, model parameters are updated based on image alignment constraint loss with a target image, deformation field smooth constraint loss and region alignment constraint loss of a tumor region in the image.

The invention discloses a smart city planning three-dimensional scene reconstruction optimization system combined with semantic segmentation, and belongs to the technical field of three-dimensional scene reconstruction optimization. The system comprises a data sensing module which collects aerial images and laser point clouds, and complements a sheltered area to obtain city modeling data; the preprocessing module performs denoising, data registration and data fusion on the city modeling data to generate texture point cloud data; the semantic understanding module realizes multi-modal semantic segmentation of the texture point cloud data through a fine-tuned SAM network and an improved RandLA-Net, and semantic tag data is obtained through restoration and optimization; the reconstruction optimization module constructs an initial three-dimensional grid model based on the texture point cloud data, and optimizes a ground feature boundary and a missing region of the model in combination with a semantic tag; and the output application module converts the optimized model into a standard format and outputs the model. Through deep coupling of semantic segmentation and reconstruction optimization, the precision of the three-dimensional scene model is improved, and reliable support is provided for smart city planning.

The invention provides a Yangtze river export deep and far sea environment data association analysis method based on multi-modal fusion, belongs to the technical field of far sea environment analysis, and achieves accurate data registration by establishing a multi-source data space-time standardization model and adopting an adaptive space-time Kriging interpolation algorithm. A sparse coding ocean signal separation algorithm is utilized to construct an over-complete dictionary separation mixed signal to extract pure features, a feature extraction network is constructed based on an attention mechanism to automatically learn deep feature representation of physicochemical biological parameters, and a matrix rank loss detection algorithm is adopted to automatically supplement feature compensation vectors to ensure feature integrity. A cross-scale attention mechanism is constructed based on wavelet transform to fuse multi-scale features, a Shapley value interpretability evaluation system is established to quantify correlation feature importance, and the technical problem that correlation feature extraction is inaccurate in the multi-source heterogeneous marine environment data fusion process is solved.

The invention discloses an image three-dimensional reconstruction method and system for orthopedic postoperative monitoring, and relates to the technical field related to image processing, and the method comprises the steps: positioning an operation region pixel mask of a user, and collecting reference three-dimensional image data; performing candidate base point analysis on the reference three-dimensional image data to obtain a candidate base point set; performing stability scoring on the candidate base point set, identifying an anchoring base point set greater than a preset stability scoring threshold based on a stability scoring result, and selecting at least one reconstructed anchoring base point; and obtaining at least one follow-up visit three-dimensional image data, and performing three-dimensional reconstruction on the at least one follow-up visit three-dimensional image data to obtain a three-dimensional image reconstruction result. The technical problems that in the prior art, image three-dimensional reconstruction dynamic change analysis is difficult, and feature point stability and data registration precision are insufficient are solved, and the technical effects that multi-temporal three-dimensional image high-precision registration is achieved, and the consistency of three-dimensional reconstruction results at different follow-up visit time points and three-dimensional reconstruction precision are improved are achieved.

Systems, methods, and computer readable media for routing inputs on a extended reality (XR) wearable device where the methods performed on an apparatus of a system include receiving, at an input framework service, an input data registration request from a client component, the input data registration request comprising an indication of a callback component and an indication of input data having a type, and verifying, at the input framework service, the client component is authorized to access the input data having the type. The method may further include registering, at the input framework service, the callback component with an input service associated with the input data having the type, receiving, at the input service, input data having the type, and invoking, at the input service, the callback component.

The invention discloses an identification-based industrial map data registration method and system. The method comprises the following steps: 1) an industrial map data registration system distributes a unique user id for each registered user; then generating a character string according to the feature value of the to-be-registered graph data filled by the user and the user id; the feature value comprises a picture name, a picture path, a storage server ip, a superior node id and a child node id; 2) encrypting the character string to generate a ciphertext as an identifier of the graph data; 3) receiving a data source access permission set by a user for the graph data; when duplicate checking judgment is carried out on the graph data, an identifier of the graph data is analyzed, and according to a picture storage path of the analyzed graph data, the storage server ip obtains an absolute path of a storage position of the graph data and accesses the data for comparison duplicate checking; and 4) updating the registered knowledge graph of the user by identifying the superior node id and the child node id of the analyzed graph data.

The invention discloses a focus intelligent detection and diagnosis system based on multi-modal medical image fusion, and relates to the technical field of medical image processing. A molybdenum target image, an ultrasonic image and a magnetic resonance image of the mammary gland of the patient are acquired through the data acquisition module; a data registration module is used for carrying out partition affine and local refinement registration on the multi-modal image by taking the molybdenum target image as a geometric anchor point and combining parameters such as compression force; extracting registered fusion feature data through a data fusion module; generating a candidate focus set by a focus detection module; finally, the risk assessment module calculates a comprehensive risk score through weighting, correction and consistency verification processes based on a plurality of interpretable feature indexes. And the output module generates a visual diagnosis result. According to the invention, intelligent detection and risk assessment of rechecking of breast lesions are realized, and the diagnosis accuracy and clinical reliability are effectively improved.

The invention discloses a power distribution network inspection robot system and method, and relates to the technical field of intelligent inspection, and the system comprises a data collection module, a data registration module, an anomaly detection module, a space verification module, a time sequence analysis module and a comprehensive judgment module. The data acquisition module controls the robot to acquire multi-modal data and record space-time positioning information; the data registration module registers the multi-modal data to an equipment coordinate system; the anomaly detection module extracts anomaly features and calculates confidence; the space verification module carries out space consistency verification and physical logic consistency verification according to the physical rule base and evaluates the abnormal level; the time sequence analysis module evaluates a defect evolution state; and the comprehensive judgment module performs defect judgment and generates a processing strategy. According to the method, single-mode false detection and environmental interference are effectively eliminated through a dual verification mechanism, comprehensive evaluation of the current state and the development trend of the defect is realized in combination with time sequence evolution analysis, and the accuracy and the reliability of defect detection are remarkably improved.

The invention relates to the technical field of electric data processing, and provides a fault diagnosis method and device for an AGV battery management system, and the method comprises the steps: collecting the monomer voltage sequence data of a battery monomer group, and carrying out the data registration, and obtaining a drift curve parameter and a stability evaluation index; performing difference fitting calculation on the drift curve parameters to obtain inflection point characteristic data, performing two-dimensional space superposition on stability evaluation indexes by using the inflection point characteristic data to obtain a temperature correlation group and average efficiency data of each charging and discharging type, and performing dynamic thermal attenuation mapping processing on all the average efficiency data by using the temperature correlation group to obtain a stability evaluation result. And obtaining fault evaluation result data. The attenuation law of the battery in a temperature change environment is effectively revealed by utilizing dynamic thermal attenuation mapping, and the problems that when early faults occur in the battery, the faults are difficult to capture, and potential faults or performance degradation of the battery cannot be predicted in time are solved.

The invention relates to the technical field of point cloud registration, in particular to a multi-view point cloud data registration method and system. The method comprises the following steps: acquiring single-view point cloud data to perform adjacent field configuration construction to obtain local structure chart data; performing resonance mode analysis on the local structure diagram data to obtain diagram embedded data; performing geometric potential energy mapping according to the graph embedded data to obtain morphological stability distribution graph data; performing spectral domain supporting point family extraction according to the morphological stability distribution diagram data to obtain a skeleton topology node set; constructing cross-view structure chart data according to the skeleton topology node set corresponding to the multiple pieces of single-view point cloud data; performing semantic perception fingerprint generation on the cross-vision-field structure chart data to obtain structure recognition cluster data; obtaining different-source structure coupling graph data according to the structure identification cluster data; and performing low-degree-of-freedom rigid body calculation according to the heterogeneous structure coupling graph data to obtain point cloud registration data. According to the invention, the stability and precision of multi-view point cloud registration are improved.

The invention relates to the technical field of agricultural intelligent equipment, in particular to intelligent monitoring and weeding equipment for gramineous weeds in a winter wheat field, and aims to solve the technical problem of high missing detection rate and false detection rate of a traditional visual identification method caused by similar forms of winter wheat and gramineous weeds in a seedling stage. The equipment comprises an autonomous mobile platform, a multi-mode sensing assembly, a data processing and decision-making unit and a targeted clearing execution mechanism. The multi-mode sensing assembly integrates a hyperspectral imaging module, a three-dimensional shape measurement module and a polarization characteristic analysis module, and pixel-level data registration is achieved in combination with the cooperative illumination system. The data processing unit performs high-confidence classification decision on the multi-source features through a hierarchical Bayesian fusion model; and the targeted clearing mechanism adopts a laser galvanometer system to carry out non-contact precise clearing on the identified weed growing points. Intelligent identification and efficient physical weeding of weeds in the winter wheat field are achieved, and the method has the advantages of being free of chemical residues and high in operation continuity.

The invention belongs to the technical field of building engineering intelligent detection, and particularly relates to an unmanned aerial vehicle-based fabricated building defect automatic identification system, which comprises a data acquisition module, a data registration module, a sleeve positioning module, a feature extraction module, a defect identification module and a report output module. A sequential three-dimensional data field is constructed, environmental interference influences are eliminated through preprocessing, visible light image features, infrared thermal imaging features and three-dimensional point cloud geometric features are extracted in parallel, internal and external comprehensive diagnosis of the grouting full state is achieved, grouting insufficient cavities, later-stage contractile cavities and grouting vertical depth deficiency defects are accurately recognized, and the grouting quality is improved. Dynamic tracking, accurate quantification and traceability are synchronously carried out, the problems of single dimension, poor space-time continuity, weak environmental adaptability, difficulty in accurate quantification and traceability of defects and the like of existing prefabricated building sleeve grouting fullness state detection are effectively solved, and the intelligent reliability of quality control is improved.

The invention discloses a gallium oxide substrate surface grinding morphology prediction method and system, and relates to the technical field of nondestructive testing, and the method comprises the steps: collecting a surface fluorescence distribution image, matching the surface fluorescence distribution image with a pre-constructed fluorescence-crack mapping database, and generating a two-dimensional crack depth distribution cloud picture; marking a risk area coordinate set in the two-dimensional crack depth distribution cloud picture based on a preset crack depth threshold value; inputting the risk area coordinate set into a Bessel beam chromatography scanner for multi-angle transmission type scanning, synchronously collecting scattering images generated by scanning, and fusing the scattering images to generate a subsurface damage three-dimensional model; and performing data registration and weight superposition on the two-dimensional crack depth distribution cloud picture and the subsurface damage three-dimensional model, and outputting a morphology prediction report and grinding process optimization parameters. The subsurface damage three-dimensional model is constructed through the Bessel beam tomography scanning and multi-angle scattering image fusion technology, and high-resolution visual reconstruction of microcracks and damage distribution in the gallium oxide substrate is achieved.

The invention discloses a power transmission line three-dimensional full-attribute reconstruction method, system and device and a storage medium, and relates to the field of power transmission line monitoring, and the method comprises the steps: obtaining the visible light data of a power transmission line, and generating a time-aligned original data set; performing low-illumination enhancement on the original data set to obtain an enhanced image and an illumination distribution diagram, and performing multi-modal data registration based on the enhanced image and the illumination distribution diagram to form a multi-source data cube under a unified coordinate system; carrying out multi-scale feature expression and cross-domain mapping on the cube, deeply fusing features to construct a three-dimensional model, evaluating and detecting the model, and starting local super-resolution reconstruction on a defective region to realize dynamic updating of the model; according to the method, the accuracy, integrity and real-time performance of the three-dimensional model of the power transmission line can be effectively improved, potential defects in the power transmission line can be found in time, a powerful guarantee is provided for safe and stable operation of the power transmission line, and the method has important application value and practical significance in operation, maintenance and management of a power system.

The invention relates to a forest fire sensing and predicting method based on a deep space-time hyperspectral fusion network, and belongs to the field of forestry artificial intelligence. The method comprises the following steps: obtaining a high-resolution and hyperspectral forest image, constructing a data set, and dividing a training set and a test set; data registration and preprocessing are carried out on the training set images, a forest fire perception and prediction model based on a deep space-time hyperspectral fusion network is constructed, and the model covers an image feature extraction module, a time sequence attention guiding module, a time sequence feature extraction module, a hyperspectral feature extraction module, a thermal anomaly enhancement module, a variable receptive field fusion module and a fire risk prediction module; preprocessing the data training model by using the training set, constructing a loss function based on the difference between the predicted fire risk level and the real fire risk level, and iteratively updating the parameters by using an optimizer until the training is completed; and finally, inputting a test set preprocessing image into the trained model to obtain a predicted fire risk level. According to the invention, the timeliness and accuracy of early fire prediction can be improved.

The invention provides tunnel lining disease AI detection and positioning equipment, which relates to the technical field of tunnel engineering detection and comprises a data acquisition module, an edge calculation module and a cloud analysis module. According to the invention, the appearance image data, the three-dimensional point cloud data and the thermal imaging data of the tunnel lining are synchronously acquired through the multi-sensor array carried on the mobile carrier, unmanned continuous automatic detection can be realized, manual processing of subsequent mass data is avoided, then an end-side-cloud collaborative architecture is introduced, and the real-time performance of the tunnel lining is improved. The edge calculation module is responsible for real-time identification and preliminary positioning to ensure the detection efficiency, and the cloud analysis module maps two-dimensional disease information to a three-dimensional space through a multi-source data registration and fusion algorithm to accurately calculate the geometric dimension and absolute coordinates of the disease information. Meanwhile, in combination with thermal imaging data analysis, recessive diseases which cannot be found by a traditional method are effectively identified. According to the method, human eye interpretation is replaced by the artificial intelligence model, so that the objectivity and consistency of results are ensured.

The invention relates to the technical field of robot control, and discloses an ultrasonic image guided robot operation method, device and equipment and a medium, and the method comprises the steps: obtaining real-time ultrasonic image data, executing non-rigid image registration based on the real-time ultrasonic image data and reference image data to determine current deformation data, and based on the current deformation data and the historical deformation data, using a recursive least square method with a forgetting factor to predict future deformation path data, based on the future deformation path data and the target path data, generating a robot navigation instruction, and according to the robot navigation instruction, controlling a robot end effector to move so as to track the future deformation path data. According to the method, a real-time ultrasonic image data registration result is integrated with a prediction algorithm and a navigation control algorithm, and a closed-loop process of data perception, deformation prediction and robot end motion control is established, so that a robot end effector can adapt to a dynamic deformation environment and continuously and accurately track a target path, and the operation precision is effectively improved.

The invention belongs to the technical field of intelligent cleaning, and discloses an intelligent cleaning system for a passenger cabin. Comprising a stereoscopic vision positioning module used for acquiring a stereoscopic vision image in a passenger cabin; extracting three-dimensional information of the stain area; the image enhancement sub-module based on the generative adversarial network is used for preprocessing the stereoscopic vision image; the laser scanning and positioning module is used for shooting the whole environment of the passenger cabin and constructing a first point cloud map; the data fusion positioning module is used for receiving the three-dimensional information of the blotted area, performing data registration with the first point cloud map and outputting accurate three-dimensional coordinates of the blotted area; and the cleaning execution module is connected with the data fusion positioning module and is used for receiving the accurate three-dimensional coordinates of the dirty area and controlling a cleaning execution mechanism to clean point by point according to the three-dimensional coordinates so as to adapt to a complex environment, and the efficiency and the quality of passenger cabin cleaning are greatly improved.

Systems, methods, and computer readable media for routing inputs on a extended reality (XR) wearable device where the methods performed on an apparatus of a system include receiving, at an input framework service, an input data registration request from a client component, the input data registration request comprising an indication of a callback component and an indication of input data having a type, and verifying, at the input framework service, the client component is authorized to access the input data having the type. The method may further include registering, at the input framework service, the callback component with an input service associated with the input data having the type, receiving, at the input service, input data having the type, and invoking, at the input service, the callback component.

The invention relates to the technical field of marine geological survey, in particular to a shallow sea sediment classification method and system based on multi-scale and multi-direction feature fusion, and the method comprises the steps: obtaining the multi-source acoustic data of a shallow sea sediment, and carrying out the preprocessing of the obtained multi-source acoustic data, constructing a spatial correlation model based on the preprocessed multi-source acoustic data, performing submarine topographic feature extraction according to a water depth value of MBES data, performing multi-scale and multi-direction texture feature extraction by using an SSS image output by the spatial correlation model, performing feature optimization on the obtained topographic features and texture features, and taking a core feature set as an input to perform feature extraction on the obtained topographic features and texture features; according to the method, the echo intensity image is taken as a core, the problem of poor space consistency in traditional multi-source data registration is solved, classification errors caused by feature space dislocation are avoided, and the accuracy of the multi-source data registration is improved. And classification reliability is improved.

A data registration apparatus (200) processes original data saved in a data source and registers the processed data. A data verification apparatus (300) computes a digest value of reference combined data which is generated based on a digest value of the original data and a digest value of the processed data as a reference digest value. The data verification apparatus computes a digest value of the registered processed data as a provisional digest value, retrieves digest value saved in the data source as a provisional digest value, computes a digest value of verification combined data which is generated based on the provisional digest value of the original data and the provisional digest value of the processed data as a verification digest value, and compares the verification digest value with the reference digest value.

This application provides a method, apparatus, device, and medium for determining joint calibration parameters. In this method, a calibration board is placed in different poses. For each pose, based on the edge line of the calibration board in the image acquired by the camera at that pose, the first coordinates of a preset position on the calibration board in the image are determined. Then, the point cloud data at that pose is processed using a plane fitting algorithm to obtain a first plane corresponding to the calibration board in the point cloud data acquired by the LiDAR. Based on the laser point located on the edge line of the calibration board and the determined first plane, the second coordinates of the target laser point at the preset position on the calibration board are determined. Based on the determined first and second coordinates of each pose and a preset data registration algorithm, the parameters for joint calibration of the camera and LiDAR are comprehensively determined, mitigating the problem of low accuracy in determining calibration parameters caused by error accumulation.

The invention discloses a human body scanning data registration method and device, equipment and a medium, and relates to the technical field of computer vision. The method comprises the following steps: acquiring a full-head 3D scanning point cloud, a side face 3D scanning point cloud and an in-ear 3D scanning point cloud; human ear 3D scanning point clouds are extracted from the full-head 3D scanning point clouds and the side face 3D scanning point clouds, and first human ear 3D scanning point clouds in the full-head 3D scanning point clouds and second human ear 3D scanning point clouds in the side face 3D scanning point clouds are obtained; determining a first spatial conversion relation and a second spatial conversion relation according to the in-ear 3D scanning point cloud, the first human ear 3D scanning point cloud and the second human ear 3D scanning point cloud; wherein the first space conversion relation is a coordinate conversion relation between the full-head 3D scanning point cloud and the side face 3D scanning point cloud, and the second space conversion relation is a coordinate conversion relation between the in-ear 3D scanning point cloud and the side face 3D scanning point cloud. The method provides a new human body scanning data registration method.

The application belongs to the technical field of intelligent detection of building engineering, and particularly relates to an automatic defect identification system for fabricated buildings based on an unmanned aerial vehicle, which comprises a data acquisition module, a data registration module, a sleeve positioning module, a feature extraction module, a defect identification module and a report output module. The system collects multi-source heterogeneous data through the unmanned aerial vehicle, constructs a time-sequenced three-dimensional data field, eliminates the influence of environmental interference through pretreatment, extracts visible light image features, infrared thermal imaging features and three-dimensional point cloud geometric features in parallel, realizes comprehensive diagnosis of the internal and external filling state of grouting, accurately identifies insufficient hollows of grouting, late shrinkage hollows and defects of insufficient vertical depth of grouting, simultaneously carries out dynamic tracking, accurate quantification and tracing, effectively solves the problems that the existing detection of the filling state of sleeve grouting of fabricated buildings is single in dimension, poor in space-time continuity, weak in environmental adaptability and difficult to accurately quantify and trace defects, and improves the intelligent reliability of quality control.

The invention discloses a tunnel face integrity evaluation method based on deep learning, and the method comprises the steps: firstly scanning a tunnel face through a laser radar carried on an unmanned plane, obtaining a point cloud file of the tunnel face, and carrying out the data registration, data noise reduction, data simplification and three-dimensional modeling of the point cloud file through a data processing technology; the method comprises the following steps: performing tunnel face image extraction and image preprocessing on a three-dimensional model obtained after data processing, performing crack identification through a YOLOv5 convolutional neural network, and performing enhancement and structure optimization on crack image features through operations such as image segmentation, image noise reduction, crack skeleton extraction, edge detection, crack skeleton line splicing and the like. And information such as crack width and crack length is obtained through the processed image. The face fracture density and the ratio of open, micro-open and closed fractures are calculated through the information, the face fracture density is used for distinguishing the completeness and local stability of the tunnel face rock mass, and the completeness and local stability of the tunnel face are evaluated more comprehensively through the ratio of the three fractures.

In accordance with one aspect of the inventive concepts, provided is an autonomous mobile robot (AMR), comprising: a carriage actuation and feedback system configured to robotically control a carriage to control a height of a pair of forks; at least one sensor configured to acquire sensor data over multiple planes in a direction of the forks during actuation of the carriage that raises and lowers the forks; an infrastructure localization system configured to combine the sensor data from the multiple planes into dense point cloud data and identify an infrastructure from the dense point cloud data. A method of localizing infrastructure using dense point cloud data is also provided.

The application relates to the computer technical field and discloses a tooth three-dimensional precision correction method and system for multi-source oral data fusion, aiming to solve the problems of low multi-modal oral data registration precision, serious geometric distortion and lack of function-oriented optimization in the prior art. The method comprises the following steps: synchronously acquiring intraoral scanning, CBCT and facial three-dimensional point cloud data; performing format conversion, denoising and grid simplification preprocessing; extracting tooth surface morphology, root canal anatomy and soft tissue contour features and encoding them into a unified feature tensor; and realizing multi-modal data space alignment through phased rigid and non-rigid registration. Through the above scheme, the multi-source data fusion precision and tooth morphology restoration accuracy are significantly improved, full-process automatic and efficient processing is realized, and the clinical real-time and high-precision diagnosis and treatment requirements are met.

The invention provides a magnetocardiogram data current source feature extraction method, system and device and a medium. The method comprises the steps of obtaining target data; the target data comprises magnetocardiogram data and heart model data; performing data registration according to the magnetocardiogram data and the heart model data to obtain fusion data; performing inverse problem solving on the fusion data according to a point source reduction algorithm to obtain a comprehensive current source of the heart model; and extracting characteristic parameters according to the comprehensive current source to obtain target characteristic parameters. According to the method, data registration is carried out on the magnetocardiogram data and the three-dimensional heart model data to obtain the fusion data, inverse problem solving is carried out on the fusion data through a point source reduction algorithm, the current source on the heart model corresponding to the magnetogram at the moment is solved, distinguishable index parameters are further mined according to the current source, and therefore the accuracy of the heart model is improved. The indexes start from the angle of a current source instead of a magnetic graph or a waveform, so that the mining angle is more comprehensive, and the analysis result is more accurate.