712 results about "Topological graph" patented technology

The invention belongs to the technical field of computers, and particularly relates to an Internet of Things security data real-time monitoring and protection method and system, and the method comprises the steps: collecting equipment communication and state data through an edge agent, and analyzing and extracting standardized metadata; constructing an equipment behavior contour vector based on a sliding window, and dynamically maintaining a global equipment topological graph; triggering a primary alarm in combination with behavior deviation detection and topology abnormity; outputting a threat score and an attack intention through rule matching and Bayesian network double-engine collaborative reasoning; and executing automatic response according to grading, and feeding back and correcting a behavior baseline to realize closed-loop optimization. The system comprises a data acquisition module, a protocol analysis module, a behavior modeling module, a topology maintenance module, an anomaly detection module, a collaborative reasoning module, an automatic response module and a baseline correction module. Through full-link real-time modeling and cross-device collaborative analysis, the attack detection rate is significantly increased to 98% or above, the false alarm rate is lower than 2%, the response delay is controlled within 800 milliseconds, and the security and adaptive ability of the Internet of Things system are enhanced.

The invention relates to the technical field of industrial automation control, and discloses a change gear assembly processing technological parameter intelligent optimization system, which comprises a multi-dimensional data synchronous acquisition unit, an angular domain static map construction unit, a phase lead constraint control unit and an angle trigger execution unit, according to the method, a static angle-load topological graph with a main shaft angle as an index is established, a phase lead angle is calculated by combining inherent physical response lag time of a servo system, and a parameter adjustment instruction sequence is directly injected into a servo current loop at a preset angle window before physical load impact occurs; according to the feed-forward control mechanism based on angular domain reconstruction and phase lead constraint, the problem of physical lag of traditional time domain feedback control in response to high-frequency intermittent cutting is avoided, and zero time difference of periodic load impact and even pre-judgment torque compensation are achieved.

The invention discloses an earth and rockfill dam seepage-deformation early warning method and system based on time-space combined anomaly, and belongs to the field of dam body safety data research. The method comprises the following steps: constructing a spatio-temporal topological graph based on an engineering coordinate system, integrating multi-dimensional data by nodes, and constructing a dynamic adjacency matrix according to spatial distance and seepage relevance; extracting features by using a space-time diagram convolutional network, a self-loop mechanism and cross-layer attention; and executing dual-drive early warning through standard threshold preliminary screening, multi-scale LSTM prediction and a time decay evidence theory. The system comprises a sensor network and an intelligent computing module, and the intelligent computing module has adaptive modeling and visualization functions. According to the scheme, seepage-deformation space-time correlation quantitative analysis is achieved, the hysteresis effect is captured, the threshold value is dynamically corrected, multi-source evidences are fused, the early warning timeliness and accuracy are improved, and the risk of false alarm and missing alarm is reduced.

The invention provides a marine equipment drawing recognition method and system based on a large model, and is applied to the field of intelligent analysis and knowledge management of ship engineering. The method comprises the following steps: receiving a marine equipment engineering drawing image, extracting global features through character and line detection after preprocessing so as to identify a drawing type, and combining symbol classification and topological graph construction to determine an equipment connection relationship, performing multi-source information reasoning on the target component by fusing a rule engine and a large language model, and outputting a high-confidence identification result; according to the scheme, the accuracy and the automation level of recognition of the equipment parts in the complex marine drawing can be remarkably improved, and the technical bottlenecks of a traditional method in the aspects of insufficient cross-modal information fusion, limited semantic understanding depth, poor heterogeneous drawing adaptability and the like are effectively solved.

The invention discloses a ring main unit inspection robot autonomous navigation method and system based on SLAM, particularly relates to the technical field of robot autonomous navigation and intelligent inspection, and is used for solving the problem of positioning drift caused by repeated features of an existing ring main unit scene. Semantic feature analysis and topological constraints are introduced into an SLAM processing flow, acquired image data and point cloud data are processed through a deep learning model, objects such as an electrical cabinet, a corridor channel and a cable trench are identified, and a semantic feature set with category labels and spatial position information is generated; and constructing a topological graph containing node spacing, connectivity and directivity constraints based on the semantic features, adding the topological graph as a constraint factor into SLAM back-end optimization, and performing joint optimization in combination with vision, a laser odometer and inertial prior information, thereby avoiding only depending on repeated geometric feature positioning, and improving the positioning accuracy. The problems of loopback misjudgment and drifting caused by feature confusion are reduced, and the pose resolving stability in the ring main unit environment is improved.

The invention provides a server cluster operation and maintenance method based on multi-source heterogeneous data fusion and a dynamic knowledge graph, and the method comprises the following steps: collecting a performance index, a log text and topological structure data of a server cluster, splicing the performance data and the log data based on a unified time window, and generating a multi-modal feature sequence; and analyzing the sequence by using an unsupervised deep learning model, constructing a dynamic health baseline, and generating a health degree portrait through the deviation with real-time data. When an exception is detected, mapping an exception event into a dynamic topological graph constructed based on a topological structure; analyzing a fault propagation probability between nodes by using a graph neural network algorithm, positioning a root cause node, and generating a disposal strategy to execute disposal operation; and collecting the processed recovery data as a feedback signal, and updating the deep learning model by using incremental learning. The method has the beneficial effects that the fault discovery accuracy is improved, the alarm storm is effectively inhibited, the root cause is directly positioned, and the model self-iteration adaptability is higher.

The invention provides a multi-modal characterization molecular property prediction method based on hierarchical bidirectional cross attention, and relates to the technical field of machine learning assisted organic chemistry, and the method comprises the following steps: S10, generating same-molecule multiple sequences for data enhancement; s20, coding the sequence features through a pre-trained molecular language model MolBERT; s30, performing multi-modal feature fusion through a layered bidirectional cross attention mechanism; s40, establishing a prediction head; s50, in the reasoning stage, only the feature extraction and fusion steps are executed, and a molecular property prediction result is output through the trained prediction head. According to the method, the molecular sequence, the topological graph structure and the fingerprint features are effectively integrated, so that the prediction precision of the model on a plurality of MoleculeNet (molecular network benchmark) public data sets is superior to that of an existing method.

The invention relates to the fields of computer graphic processing, industrial software technology and the like, discloses a Cocos engine-oriented pipeline loop perception linear decomposition method, and aims to solve the problem that a complex topological graph which cannot be effectively processed and comprises a high-density nested loop in the prior art. The structure is completely and accurately decomposed into a linear drawing instruction sequence which can be accepted by a Cocos engine, and lossless conversion of original topological information is ensured; comprising the steps that after undirected topological graph data are input, a ring detection algorithm is called to recognize and record all independent ring structures in an undirected topological graph and nodes and edges contained in the independent ring structures; judging whether at least one ring is detected in the previous step, and if the at least one ring exists, assigning a determined traversal direction for each detected ring according to a preset ring direction rule; and if the ring does not exist, skipping, and directly performing depth-first search traversal on the undirected topological graph data.

The invention relates to the technical field of artificial intelligence in the education industry, in particular to an intelligent composition quality evaluation method and system based on a large language model, and the method comprises the steps: carrying out the text normalization and semantic unit segmentation of a composition, extracting a semantic vector through a first large language model in combination with a context enhancement strategy, and positioning a semantic fracture risk position; recognizing composition core elements through a second large language model, and mapping the composition core elements back to the semantic unit sequence; constructing a demonstration logic diagram, extracting a core demonstration path and abstracting the core demonstration path into a logic role topological graph; in combination with a pre-constructed writing specification knowledge graph, comparing structural compliance, connection strength and an expected support relationship, identifying and demonstrating logic defects, and generating a global deduction item list; semantic clustering is carried out on illegal items to form an error label set, comprehensive weight is calculated in combination with historical data of students, and core weak items are positioned; according to the application, the logic analysis depth of intelligent evaluation of the argument is remarkably improved, and the pertinence and practicability of teaching feedback are improved.

The invention belongs to the technical field of electronic equipment thermal management, and discloses an electronic equipment thermal field rapid prediction method for multi-physical field strong coupling. According to the method, a layered heat source intensity distribution model is constructed, a grid mapping relation topological graph technology and a boundary node energy conservation compensation mechanism are developed, a multi-time scale coupling transfer function is designed, and a dynamic adjustment strategy based on phase deviation analysis is introduced. According to the method, the non-uniform heat source distribution and thermal diffusion dynamic characteristics under the high-frequency condition are accurately captured, the energy consistency of multi-physical field coupling is ensured, the thermal field prediction precision is improved, particularly, the method has outstanding advantages in the aspect of phase and amplitude prediction of transient thermal response, and meanwhile calculation resource consumption is greatly reduced.

The invention discloses a graph neural network-based train path collaborative scheduling method, which relates to the technical field of rail transit transportation scheduling, and comprises the following steps: S1, constructing a train path topological graph; s2, extracting a node embedding feature vector; s3, extracting context feature vectors of the computational nodes; s4, extracting a conflict node pair set; s5, introducing a fitness sharing mechanism and an elitist strategy, and adopting an improved binary whale optimization algorithm to generate an optimized multi-train collaborative path scheduling scheme; and S6, performing feedback and iterative optimization. The method overcomes the limitations of strong subjectivity of manual decision, slow response, difficulty in coping with complex path conflict problems and difficulty in accurately capturing path dynamic change rules in a traditional class path scheduling method, and provides an intelligent, efficient and accurate solution for real-time collaborative scheduling of class paths.

The invention relates to the technical field of natural language processing, and discloses a workflow calling method based on a large language model. The method comprises the steps of receiving an initial task description text of a user, and decomposing the initial task description text into a discrete intention unit set through a semantic analysis engine; inputting a pre-trained large language model to carry out context association analysis, and generating a task node topological graph containing a hierarchical relationship; detecting a data transmission dependency relationship between nodes, and marking a strong association cluster with bidirectional data streams; according to cluster dynamic load parameters, automatically dividing parallel execution domains and distributing independent data transmission channels; and monitoring channel throughput fluctuation in real time, and triggering a channel switching protocol when the channel throughput is blocked. According to the method, the complex task execution logic and the data flow path are straightened out, the problems of dependency conflicts and resource allocation are solved, the orderliness and stability of workflow execution are guaranteed, and the automatic task scheduling requirements under various complex scenes are met.

The invention belongs to the technical field of artificial intelligence, and particularly relates to a complex table intelligent analysis method and system based on multi-modal fusion and semantic analysis. The method comprises the following steps: S1, performing preliminary analysis on a document based on a multi-modal fusion technology, identifying position information of a table area, a text and an image, and outputting the position information of the table area; s2, reconstructing the table structure based on the topological graph structure and the geometrical relationship of the table to obtain a reconstructed table; s3, identifying the content of the reconstructed table by utilizing machine vision, and correcting the identified content of the table and the position information of the table area in combination with semantics to obtain all the content of table analysis; and S4, outputting the analyzed table content according to a required format. According to the method, the complex table can be analyzed and corrected.

The invention discloses a multi-terminal collaborative modular power operation and maintenance method and system based on digital twinning, and the method comprises the following steps: constructing a global power topological graph of a power energy site, mapping power equipment, sensors and connecting lines into graph nodes and graph edges, and binding the static attributes of the equipment with the topological structure; and acquiring real-time operation data of the power equipment, and distributing a unified time label for the multi-source heterogeneous data. According to the method, a unified twinborn model of cross-voltage class, cross-region and cross-equipment type is established in a digital twinborn platform, and operation data of different equipment such as photovoltaic equipment, battery energy storage equipment, an inverter, a protection device, an electric energy meter and temperature control equipment are expressed in a unified data semantic mode; according to the invention, the system can still automatically establish a consistent device portrait under the conditions of a large number of multi-terminal devices and diversified communication protocols, and the multi-terminal cooperative computing capability is significantly improved.

The invention relates to the technical field of intelligent control of heavy equipment, in particular to a hydraulic synchronous intelligent control system for segmented turnover of an overweight steel structure, and discloses the hydraulic synchronous intelligent control system for segmented turnover of the overweight steel structure. According to the system, full-field strain data of a structure surface is acquired by deploying a flexible grid sensor array, and a deformation gradient topological graph is constructed to identify an instability risk area. And a dynamic fluid network model of the hydraulic system is established, fluid-solid coupling simulation is carried out in combination with deformation characteristics, and pressure pulsation transmission paths under different control instructions are predicted. And the system dynamically optimizes a data sampling strategy and network model parameters according to a prediction path, generates a hydraulic cylinder coordination action instruction subjected to pressure balance verification, and finally drives an execution mechanism to complete turnover operation. According to the scheme, full-field real-time sensing of structural deformation and dynamic coupling prediction control of hydraulic fluid are achieved, and the safety and control precision of the overweight component in the turnover process are improved.

The invention provides a video monitoring abnormal behavior identification and tracking linkage method based on artificial intelligence, which relates to the technical field of artificial intelligence, and comprises the following steps: carrying out space-time registration on a multi-camera video stream, and establishing a unified coordinate system; in the system, static objects are detected, and suspected remnants are marked; constructing a time sequence backtracking window to determine the association between the article and the person in charge; establishing a topological graph model containing a camera switching probability and a spatial adjacency relation; and predicting a motion track of an uncovered area according to the current motion state, dynamically distributing a tracking weight and generating an alarm. According to the invention, the remnant tracking efficiency and accuracy are improved.

The invention provides an automatic data exception root cause positioning and playback repair method and system and related equipment. The method comprises the following steps: constructing a dynamic heterogeneous topological graph containing data logic nodes and physical resource nodes in real time, and establishing real-time directed dependency connection between the nodes; in response to a monitored abnormal signal, generating an anti-fact intervention set assuming that an upstream node is in a reference state by using a Do operator based on the dynamic heterogeneous topological graph; the anti-fact intervention set is substituted into a causal reasoning model for simulation, and the abnormal maintenance probability of the abnormal signal still existing under the condition that the anti-fact intervention set takes effect is obtained; and calculating a causal contribution degree according to the exception maintenance probability to lock a root cause node, and transmitting state data of the root cause node to a repair module to trigger playback repair. According to the invention, the accuracy and stability of abnormal root cause positioning are improved.

The invention discloses a mining equipment state prediction method based on digital twinning and multi-modal fusion, and relates to the technical field of intelligent operation and maintenance, and the method comprises the steps: inputting a multi-modal alignment working condition window sequence into a digital twinning mechanism link, carrying out the same-window ideal response deduction, outputting an ideal multi-modal response, and constructing a twinning dynamic residual error; meanwhile, segmenting a residual structure event to generate a residual event token set; positioning a multi-modal data fragment based on the residual event token set, executing cross-modal attention alignment, and performing topology propagation aggregation in combination with a mechanical topology observation mapping table to generate a topology constraint fusion table set; and inputting the topological constraint fusion table set into the graph neural network, carrying out message passing in combination with a mechanical topological graph, outputting a component state and a complete machine state, and packaging the component state and the complete machine state into a mining equipment state prediction set. According to the method, structured analysis of the twinborn dynamic residual error is realized, and the method is used for accurately positioning an abnormal event and improving the sensitivity and timeliness of state prediction.

The invention relates to the technical field of unmanned aerial vehicle autonomous navigation, in particular to an unmanned aerial vehicle real-time path planning method based on dynamic topological graph construction, and the method comprises the steps: constructing a lightweight dynamic topological graph through environment change detection and influence domain calculation; and executing global path planning based on the topological graph. According to the method, memory and calculation overhead are remarkably reduced, real-time incremental updating is supported, dynamic obstacles are effectively processed, path planning efficiency and robustness are improved, and the method is suitable for autonomous flight of the unmanned aerial vehicle in a complex environment.

The invention discloses a three-dimensional geographic environment real-time intelligent deduction method based on a multi-modal large model, and relates to the technical field of computer vision. The method is used for solving the technical problem of unified modeling and real-time deduction of a dynamic object and a static environment in a three-dimensional geographical environment. The method comprises the following steps: firstly, resolving a camera pose through a motion recovery structure algorithm to generate a sparse point cloud, and separating a dynamic foreground object in a monitoring video to extract motion features; thirdly, initializing a three-dimensional Gaussian distribution set based on the sparse point cloud, extracting semantic features through a visual encoder, and mapping the semantic features to corresponding Gaussian distribution; thirdly, a topological graph structure of Gaussian distribution is constructed, motion features are used as initial excitation, and coordinate offset and appearance variation of each distribution are iteratively updated through message passing calculation; finally, Gaussian distribution attributes are dynamically updated, a continuous deduction image sequence is synthesized through micro-rasterization rendering, and high-reality real-time simulation of dynamic evolution of the three-dimensional geographical environment is achieved.

The invention provides a line loss reason analysis and positioning method and system based on artificial intelligence and a medium, and relates to the technical field of power system management.The method comprises the steps that when the bus loss rate of a target station area exceeds a preset line loss threshold value, an excitation sequence is issued to a general meter, a circuit breaker and a user electricity meter of the target station area, respectively obtaining corresponding transient response data, and further constructing a dynamic topological graph of the target transformer area; and a topological structure is optimized by combining a graph neural network and an attention mechanism, and abnormal connection points are detected. And determining downstream associated user electric meters, and calculating the power utilization abnormity score based on the load data. And injecting a steep front traveling wave signal into the electric meter with the highest score to obtain a reflection characteristic parameter. And performing iterative analysis by using a Double DQN reinforcement learning algorithm, determining a fault point, a line loss reason type and confidence, and realizing efficient and accurate line loss reason positioning and analysis. According to the invention, efficient and accurate troubleshooting of line loss reasons is realized.

The invention discloses a formation riding danger information sharing method and system for intelligent riding helmets, and relates to the technical field of information sharing, and the method comprises the steps: carrying out the deep fusion of the adjacent beacons of all intelligent helmets, the state information of a vehicle, and the multi-source heterogeneous data of an external sensor, vehicle-road cooperation and the like; and constructing and dynamically maintaining a topological graph reflecting the space-time relationship among the formation members in real time. On the basis, intelligent source end propagation strategy decision is carried out on perceived semantic danger information, and topology-based directional relay and propagation are carried out. And finally, the decided propagable information is combined with the state of the rider, so that a highly personalized early warning instruction is generated. In this way, undifferentiated global information broadcast can be effectively converted into accurate risk announcement based on individual context, and the efficiency of dangerous information sharing in formation riding and the cooperative safety capability of the whole system are remarkably improved.

The invention provides a building information model compliance processing method and device based on artificial intelligence, electronic equipment and a storage medium, and the method comprises the steps: analyzing a standard document through a natural language processing model, and constructing a structured compliance knowledge graph containing a forced parameter, a naming rule, a geometric constraint and a data mapping relation; when the components are loaded, geometric feature vectors of the components are extracted, a hierarchical topological graph is modeled and nested, and a digital twin file containing geometric attributes, a parameter list and risk scores is generated; and matching and comparing the archive with the knowledge graph, dynamically generating a processing strategy sequence, and scheduling a geometric optimization and data encapsulation module to execute adaptive processing. Geometric optimization adopts a deep learning driven non-uniform grid simplification algorithm, key region details are reserved, and topological defects are repaired; and the data packaging realizes intelligent matching and binding from the custom parameters to the standard attribute set through semantic mapping. Through the method and the device, the efficiency, the accuracy and the automation level of cross-platform compliance conversion of the building information model can be remarkably improved.

The invention relates to the technical field of medical instruments, and discloses a breast cancer sentinel lymph node positioning system and method, and the system comprises a data collection subsystem, a space positioning subsystem and a central processing subsystem. The method comprises the following steps: acquiring an anatomical structure image, a radioactivity counting rate and fluorescence intensity after performing primary fluorescence, radioactivity and secondary pulse type fluorescence tracer injection in sequence; establishing a global coordinate system and generating an anatomical region of interest; constructing a weighted directed topological graph based on the initial fluorescence data, and obtaining a baseline flow velocity; extracting radionuclide dynamic characteristics based on the radioactive data; a functional flow rate attenuation coefficient is calculated based on the second pulsed fluorescence data. And a multi-factor scoring model is applied, topological information, dynamic characteristics and functional flow velocity attenuation coefficients are fused, and a comprehensive score is calculated to identify the sentinel lymph node. According to the method, the lymphatic flow topological structure, nuclide dynamics and functional flow velocity information are combined, and the positioning accuracy and reliability are improved.

The invention discloses a GCN-LSTM-based tailing dam multi-point settlement deformation prediction method. The method comprises the steps of collecting and preprocessing original settlement monitoring data of monitoring points in a research area; constructing a graph structure for settlement data between all monitoring point pairs, setting a threshold value, connecting node pairs with significant correlation coefficient relationships by using edges, constructing a weighted undirected graph, and converting the weighted undirected graph into a normalized adjacent matrix as the input of a graph convolutional network GCN; extracting the spatial topology of each monitoring point by using a GCN; capturing long-term time dependence in the settlement process by using a gating mechanism of the LSTM network; and fusing the GCN and the LSTM network, and finally outputting a predicted value through a full connection layer. According to the method, the spatial topological graph among the monitoring points of the tailing dam is constructed, and the GCN and LSTM networks are fused, so that the spatial correlation among the monitoring points and the time dynamic characteristics of the settlement data are effectively captured, and high-precision tailing dam multipoint settlement prediction is realized.

The invention relates to an infantile autism classification method based on a double-branch functional topological graph neural network. The infantile autism classification method can realize the classification of the infantile autism by using functional magnetic resonance imaging data. According to the provided autism classification network, long-distance connection and short-distance connection are divided based on the shortest path between brain intervals, then an exponential decay mask is introduced through a functional topological graph Transform branch to adjust attention weight and accurately extract long-distance dependency features, a graph isomorphic network in the other branch is subjected to multiple neighborhood aggregation operations, short-distance dependency features are captured, and the short-distance dependency features are extracted. According to the method, multi-scale dependence of the brain network is extracted in parallel through a double-branch structure, information redundancy is reduced by means of a topology perception attention mechanism, and the adaptive ability of the model to the heterogeneous brain network is improved by using the adaptive fusion module, so that multi-scale dependence of the heterogeneous brain network is balanced in a self-adaptive manner. The classification accuracy is remarkably superior to that of an existing mainstream method, objective and efficient technical support is provided for autism diagnosis, and high interpretability is achieved.

The invention discloses a transformer area topological structure estimation method, system, equipment and medium based on multi-dimensional power utilization characteristics, and belongs to the technical field of power distribution transformer area topologies, and the method comprises the steps: collecting multi-source data, carrying out dynamic weight distribution and abnormal value correction, carrying out the characteristic extraction according to the collected multi-source data, and generating a high-dimensional characteristic vector; clustering user nodes, dividing cluster labels, performing topological modeling according to a cluster division result, generating a topological graph, and performing anomaly verification through multi-dimensional anomaly scoring and abnormal power utilization detection; and performing incremental model parameter correction and multi-objective optimization according to anomaly verification feedback, and generating dynamic topological graph rendering and multi-dimensional decision suggestions by integrating topological modeling, anomaly verification and optimization results. According to the method, accurate estimation of a topological structure is realized through dynamic clustering and hidden node recognition, real-time diagnosis of abnormal nodes and self-correction of a model are realized by means of a multi-dimensional abnormal scoring and self-adaptive optimization mechanism, and the accuracy and operation and maintenance efficiency of transformer area management are improved.

The invention provides an airborne point cloud building contour point extraction method based on a constraint triangulation network and semantic ring analysis, and belongs to the field of airborne laser radar data processing, and the method comprises the steps: obtaining an airborne laser radar point cloud data set of a to-be-processed region; performing classification processing by using a filtering algorithm to obtain a surface point set and a non-surface point set; building candidate seed points are extracted, and building point clouds are extracted; a Delaunay triangulation network is constructed based on the building point clouds, and constraint is carried out based on the distance between the point clouds; constructing a concurrent triangle set, and extracting contour points and contour connecting edges; and constructing a topological graph, performing traversal search on the topological graph, determining the minimum inclusion rectangle of the closed loop, and judging the contour point type corresponding to the closed loop according to the geometrical shape parameter and the spatial distance parameter of the minimum inclusion rectangle. According to the method, the triangulation network is constructed by using the disordered contour points, and the sequence relationship and semantic information between the points are considered, so that accurate extraction of the semantic contour points is realized.

The invention discloses a GNN-PINN fusion dynamic error enhancement current transformer error prediction method, and the method comprises the following steps: firstly, building a sliding window steady-state recognition method based on a kurtosis-entropy collaborative criterion, and achieving the precise segmentation of current features under a complex working condition through multi-dimensional statistic fusion; secondly, a dynamic error simulation injection mechanism is designed, a current data enhancement strategy guided by a physical rule is constructed, and the working condition coverage of training data is effectively improved; on the basis, a GNN-PINN-based current transformer error prediction model is provided, and deep coupling of an error mechanism and data characteristics is realized through embedding a physical connection relation of equipment through a topological graph and combining partial differential equation constraints, so that a current transformer error is obtained. According to the current transformer error prediction method provided by the invention, the key problems of difficulty in steady-state feature extraction, scarcity of data samples, lack of physical constraints and the like in current transformer error prediction during online calibration of the transformer substation current transformer can be solved.

The invention discloses a fusion graph recognition and symbolic expression-based resin-based composite material automatic native modeling and reverse design method and system, belongs to the field of composite material modeling and design, and particularly relates to a graph neural network and symbolic regression fusion-based composite material native modeling and structure reverse optimization method. The method comprises six steps of microcosmic image structure extraction, topological graph construction and graph embedding, constitutive relation symbol modeling, graph structure homogenization, performance-oriented reverse design and multi-modal performance prediction, and can realize an automatic process from microcosmic image to macroscopic performance prediction to structure optimization design. The problems that an existing method is low in efficiency, poor in interpretability and difficult in reverse design are solved, and the modeling efficiency and the design intelligence level of the composite material under multiple scales and multiple targets are improved.