649 results about "Graph computation" patented technology

The invention discloses a digital twin three-dimensional scene modeling method based on a webGPU, and relates to the technical field of three-dimensional scene modeling and graphic computing, multi-source sensing data are asynchronously sampled from sparse point cloud, a video texture sequence, a scene semantic tag graph and a structure boundary tuple, and a six-dimensional structure unit group is generated through a normalization operator; constructing a structural unit atlas with nodes representing component entities and edges representing constraint relations, and introducing a tension balance mechanism and multi-scale constraints to generate a modeling path prior model; constructing a graph calculation and graph rendering dual-channel assembly line in the WebGPU, and executing parallel texture mapping and boundary fitting operation; a dynamic sensing module is used for capturing scene disturbance and driving atlas response, and incremental reconstruction of the model is achieved; and finally, mapping the model to a Web terminal, and supporting microscopic semantic query and multi-layer data linkage. According to the method, the response speed, semantic consistency and structural adaptability of three-dimensional modeling in a complex environment are improved.

The invention relates to the field of financial science and technology, and discloses a financial risk dynamic assessment system and method based on artificial intelligence. The system comprises a multi-source heterogeneous data acquisition module which acquires transaction data, public opinion texts and association maps in real time; the adaptive feature engineering module dynamically screens key risk factors; the dynamic risk map construction module calculates a risk conduction coefficient through a map neural network; the multi-modal AI analysis engine cooperatively runs a time sequence prediction model, a text mining model and a graph calculation model; a risk conduction simulator quantifies a systematic risk path. The problems of data splitting processing, model static solidification and correlation risk quantification deficiency in the prior art are solved, the false alarm rate is reduced to 12%, the response speed reaches 90 seconds, the prediction deviation is reduced to 22%, and an interpretable supervision report is generated.

The invention discloses an electric power capital construction site operation environment data monitoring and safety management method, which belongs to the field of intelligent decision technology and electric power safety management, and comprises the following steps: constructing a semantic network framework according to a construction plan; collecting and calibrating multi-source environment data to generate a trusted data set; generating a real-time risk network graph based on the semantic framework and the trusted data set; calculating a robust risk index and performing sensitivity deconstruction; generating a closed-loop intervention instruction when the risk indicator exceeds a safety threshold; and finally, collecting, feeding back, iteratively optimizing the whole system, and generating a cross-project multiplexing intelligent template library. According to the method, a comprehensive technical path of semantic modeling, causal inference and closed-loop adaptive optimization is adopted, the operation situation can be deeply analyzed, potential risks can be quantified and attributed prospectively, the optimal intervention strategy is intelligently generated, and the intelligence, precision and prospective level of safety management of the electric power capital construction site is remarkably improved.

The invention relates to the field of power system dispatching control, in particular to a virtual power plant collaborative optimization dispatching method, system and device based on multiple spatial-temporal scales and a storage medium. The method comprises the following steps: acquiring real-time supply and demand data of a multi-energy data source, constructing a dynamic operation data set by adopting distributed data acquisition, and performing time sequence analysis on the data set to extract a multi-energy fluctuation feature set; the fluctuation feature set constructs a network topology model in a spatial dimension, and a resource allocation weight of each energy node is determined through graph calculation to generate a resource allocation optimization scheme; when the real-time demand fluctuation exceeds a threshold value, a reinforcement learning algorithm is adopted to carry out optimization adjustment to obtain a real-time scheduling instruction set; in combination with real-time data of the electricity market, an optimized economic signal set is obtained through multi-objective optimization, and an equipment control instruction set is generated by adopting distributed control; and performing real-time monitoring by utilizing edge calculation according to the equipment control instruction set, and dynamically updating the scheduling instruction set through adaptive adjustment based on the system operation deviation to obtain a final resource optimization configuration scheme.

The invention relates to the technical field of knowledge graph construction, in particular to a node attenuation and edge similarity weight fused knowledge graph construction method and system, and the method comprises the steps: collecting multi-source heterogeneous data, and carrying out the preprocessing of the multi-source heterogeneous data; identifying entities in the preprocessed multi-source heterogeneous data, and extracting a relationship between the entities; establishing an initial graph structure based on the entities and the relationship between the entities, and determining the representation mode of nodes and edges in the graph; fusing time decay and space correlation factors to correct representation of nodes and edges in the constructed graph structure, and fusing semantic similarity on the basis of node and edge weight correction to further adjust an edge connection relation; after the graph structure is corrected and optimized, final knowledge graph data representation is organized and generated, and unified storage and graph calculation structured packaging are completed. According to the method, the defect that an existing map construction scheme only depends on time attenuation and neglects space factors can be effectively overcome.

The invention discloses a machine vision-based intelligent detection method for steel galvanized surface defects, which comprises the following steps: S1, acquiring and preprocessing a steel galvanized surface image to obtain a standardized image; s2, constructing a specular reflection probability graph according to the brightness distribution and the gradient magnitude, and calculating a reflection intensity value; s3, calculating a structure tensor matrix, determining a main direction angle and an anisotropic consistency coefficient, and generating a direction feature matrix; s4, establishing a multi-scale direction adaptive phase kernel function, and performing phase modulation in a frequency domain by adopting an improved phase stretching transformation algorithm; s5, inverse Fourier transform is executed, and a phase response matrix is extracted; s6, performing weighted fusion to obtain a comprehensive phase response diagram; and S7, setting a threshold value according to the noise variance and the statistical characteristics, executing binarization and morphological processing, and outputting a defect region and boundary coordinates. According to the invention, high-precision identification and boundary positioning of steel galvanized surface defects are realized.

The invention discloses an electronic material life cycle quality tracing method based on digital twinning, and relates to the technical field of industrial Internet of Things, the digital twinning of an electronic material is constructed, a material constitutive equation, a process parameter threshold library and historical quality data are integrated, and a multi-dimensional virtual model is formed; a production line real-time data stream including an equipment state, environmental parameters and material attributes is collected. According to the method, the virtual model containing the material constitutive equation and the process parameter threshold library is constructed, the real-time data flow dynamic evolution is combined, and the graph calculation and the causal reasoning algorithm are applied, so that the interaction effect of the equipment state, the environmental parameters and the material attributes can be associated, the core influence factor chain of the quality abnormality can be positioned, the single-point alarm limitation is broken through, and the quality abnormality can be accurately detected. The quality problem is deeply analyzed from the angle of multi-factor coupling, a comprehensive and systematic analysis framework is provided for accurate attribution, the source of the quality problem can be quickly and accurately found, and the efficiency and accuracy of quality tracing are improved.

The invention discloses an electricity larceny identification method based on graph calculation, and particularly relates to the technical field of electricity utilization anomaly detection of an electric power system. Historical power consumption data and a power supply topological relation of power consumers are collected, and a multi-dimensional behavior graph model fusing behavior characteristics and structural information is constructed; performing structure disturbance analysis on each node in the graph, calculating information entropy change before and after node removal, performing attention fusion on a time sequence behavior feature of the node and a structure disturbance vector, constructing a joint feature vector, and enhancing feature expression through spectral clustering and linear reconstruction; a behavior propagation field and a disturbance adjustment mechanism are introduced into the graph to form a disturbance response graph, and an abnormal gathering area is identified through path energy analysis and focusing area fitting; calculating confidence scores of the nodes and outputting a suspicious user list; the method can realize efficient identification of electricity stealing behaviors with strong concealment and complex transmissibility, and has the advantages of high precision, strong interpretability and wide application scene adaptability.

The invention discloses a code fingerprint-based open source component identification and vulnerability detection method, which comprises the following steps of: receiving a local or remote code, extracting a difference file, generating an AST and constructing a code attribute graph; sHA-256 Hash fingerprints and GNN semantic fingerprints are calculated for the function level sub-graphs to form mixed fingerprints, accurate matching is conducted through a Bloom filter, semantic matching is completed through nearest neighbor, and a component version is determined through a distribution difference algorithm. The method comprises the steps that firstly, a component identifier is mapped into a PURL or an SWID, an OSV / NVD library is inquired to obtain a CVE, comprehensive risks are calculated in combination with CVSS, EPSS and dependency depth, and an SBOM and a vulnerability report conforming to CycloneDX or SPDX are output. The method is high in speed and high in accuracy, and the open source risk can be automatically treated in continuous integration.

The invention relates to the technical field of computer vision, and particularly discloses a corn ear harvester harvesting loss prediction method and system based on deep learning, and the method comprises the steps: collecting an ear image in an ear collection box of a corn harvester in real time, and cutting the ear image into a plurality of sub-images with preset sizes; pixel-level classification is carried out on the sub-images based on a pre-trained pixel-level classification model, and a three-channel label graph of each sub-image is generated; splicing the plurality of three-channel label graphs to form an integral label graph consistent with the original image in size; calculating the pixel proportion of the damaged corn ear based on the overall label graph; when the ear collection box is full, outputting a predicted value of corn ear harvesting loss quality based on a pre-trained harvesting loss prediction model; the method based on deep learning can more accurately detect the corn damage proportion during harvesting of the corn harvester under different illumination conditions, and solves the problem of low identification of damaged pixels by a model due to few damaged ear pixel samples at the same time.

The invention discloses a construction emergency early warning method and system, and the method comprises the following steps: collecting the three-dimensional coordinates of a constructor, combining a sliding time window with a wavelet packet energy entropy and other indexes, and generating a multi-scale movement disorder index through principal component analysis and fusion; continuously unstable persons are recognized according to the disorder index, after the trajectory of the persons is segmented, a weighted graph is constructed in combination with hidden Markov and building information model environment parameters, and the cognitive mismatch degree is calculated; mapping the cognitive mismatch degree to a space grid, calculating a local Moran index, fusing a density gradient and a mechanical operation sequence resonance result, and constructing a propagation weight matrix; constructing a heterogeneous graph based on weight matrix guidance, calculating risk influence propagation potential energy, combining historical disorder sequence analysis and relative entropy, and coupling to obtain a group-level instability pre-judgment value; and outputting a comprehensive critical level for the pre-judgment value over-limit individuals through motion trend prediction, spatial intersection and shortest path algorithms. The safety during building construction operation is improved.

The invention provides a full-text retrieval method and system fusing various types of documents, and relates to the technical field of information retrieval, and the method comprises the following steps: obtaining document representation through document content extraction and structure recognition, generating a cross-modal semantic vector by using word embedding and nonlinear transformation, constructing a hierarchical index and a cross-document association graph, and obtaining a full-text retrieval result; the basic correlation score is calculated after the query request is received, and the comprehensive score of the candidate content segments is calculated based on the association graph to determine the optimal retrieval result, so that unified representation and retrieval of heterogeneous documents are realized, the cross-document retrieval precision and relevance are improved, and the processing capability of a retrieval system on complex queries is enhanced.

The invention relates to the technical field of language information processing, and provides a large language model-based structured information retrieval method, which comprises the following steps of: deploying an adapter, accessing operation and maintenance data, carrying out timestamp synchronization on an original entry and identifying a source, mapping equipment, parts and personnel based on an asset directory and recording mapping confidence, extracting structural elements from the records; injecting three types of metadata into candidate evidences, establishing corresponding nodes and edges in a graph database, analyzing query into a structured retrieval intention, expanding a candidate evidence set along three chains to form candidate sub-graphs, and calculating comprehensive scores for sorting; the candidate evidences should be verified and constrained, meanwhile, LLM is called for inference, feasibility inference confidence is output, actual measurement results, the inference confidence and source confidence are fused according to preset weights, feasibility scores of the candidate evidences are obtained, and for the candidate evidences passing feasibility verification, accurate anchor points are calibrated for each evidence along a source chain; and generating a structured answer.

The invention relates to the technical field of artificial intelligence and industrial visual inspection, and discloses a Dinov3 and SAM-based few-sample industrial defect target detection method and system, and the method comprises the steps: building a reference feature library: extracting the features of a few defect reference images through a Dinov3 model, and generating a category prototype through weighted aggregation; generating a similarity response diagram: calculating the pixel-by-pixel similarity of the image to be detected and the reference prototype, and performing context enhancement filtering; generating a segmentation prompt: screening a salient region in combination with a space attention mechanism, and generating a geometric prompt required by the SAM model; fine segmentation is executed; an accurate mask of the defect instance is generated by using an SAM model; and confidence evaluation: multi-dimensional scoring is carried out, and a dynamic threshold value is adopted to screen results. Rapid deployment can be realized without fine adjustment of the model, the problem of data shortage in the initial stage is effectively solved, data is continuously accumulated through automatic detection, a foundation is laid for training a better special model, and the method is suitable for scenes such as new product import or new defect discovery.

The invention belongs to the technical field of vehicle fault prediction, and discloses a vehicle fault evolution law modeling method and system based on digital twinning. According to the method, vehicle running state data are obtained and mapped to a digital twin virtual state space, a fault feature evolution sequence is extracted in combination with historical fault records, a state transition topological graph is constructed, the spatial distance between a real-time state and a feature vector group is calculated to match an evolution path, and the state transition topological graph is obtained. And a fault evolution prediction result is determined based on the corresponding timestamp information, and a preventive maintenance strategy is generated. According to the invention, accurate modeling of the vehicle fault evolution rule is realized, and the fault prediction accuracy and the maintenance efficiency are improved.

The invention relates to the technical field of boxing path planning, and discloses a deep learning-based boxing path planning method and system, and the method comprises the steps: collecting the data of an object to be boxed, and constructing a three-dimensional coordinate parameter; performing spatial topology modeling by using the graph convolutional network to generate a geometric topological graph, and calculating a path density coefficient; carrying out graph Laplacian matrix spectrum decomposition on the path density coefficient to extract a spatial principal component vector, and generating a path planning weight through a genetic algorithm; and dynamically updating the reference path node based on the weight to generate an optimized path, and controlling the motion trail of the mechanical arm. The system comprises a three-dimensional data acquisition module, a topology modeling module, a density coefficient calculation module, a spectral decomposition module, a weight optimization module, a path generation module and a motion control module. According to the method, through combination of deep learning and an intelligent algorithm, complex geometric feature modeling and path optimization are realized, the boxing efficiency, accuracy and system adaptability are improved, and the method is suitable for boxing scenes such as logistics and warehousing.

The invention relates to an identification method for matching scene behaviors by using multi-modal features, and belongs to the technical field of scene behavior matching. The method comprises the following steps: acquiring multi-modal scene behavior data, and carrying out noise self-adaptive purification processing on the multi-modal scene behavior data to obtain a preprocessed scene image, scene audio data and a scene label text; secondly, performing feature collaborative extraction on the preprocessed data to obtain visual features, audio features and text features, inputting the cooperatively extracted features into a scene behavior matching network, and performing scene feature fusion and behavior feature fusion respectively to obtain a scene feature vector and a behavior feature vector; and constructing a bipartite graph according to the scene feature vector and the behavior feature vector, calculating the semantic similarity between nodes of the bipartite graph, dynamically updating the edge weight of the bipartite graph according to the semantic similarity between the nodes, and normalizing the updated bipartite graph to obtain a scene behavior matching result. According to the method, the association degree of the scene and the behavior can be accurately quantified, and the accuracy of a matching result is greatly improved.

The embodiment of the invention discloses a multi-core heterogeneous processor-oriented computing pool event-driven scheduling method and device. One specific embodiment of the method comprises the following steps: performing task node decoupling on an original task flow chart to obtain a virtual operator subset and a subtask information set; determining a candidate processor corresponding to each virtual operator according to mapping configuration representing an execution relationship between the operator and an execution processor; determining operator execution sequence information corresponding to each virtual operator according to a task node dependency relationship corresponding to the sub-task information set; for each virtual operator in the virtual operator set, executing a heterogeneous resource allocation step to serve as a virtual operator execution carrier; and through an event-driven mechanism and the operator execution sequence information, scheduling a virtual operator execution carrier to perform sequential execution of each sub-task to obtain a task execution result. According to the embodiment, the parallel efficiency when the multi-core heterogeneous processor processes the graph calculation task is improved, and the scheduling delay is reduced.

The invention relates to an intelligent driving control method of a vehicle and the vehicle, and belongs to the technical field of intelligent driving, and the method comprises the following steps: obtaining an original data stream of a vehicle sensor network, and carrying out feature extraction on a dynamic feature vector; state vectors of the traffic participants are extracted according to the dynamic feature vectors, edges between the two traffic participants are constructed, a traffic participant interaction graph is constructed, and an asymmetric factor matrix is calculated; acquiring a historical scene data set of the vehicle, calculating correction similarity, and calculating a weight coefficient; performing weighted fusion on the weight coefficient and the historical scene data set to obtain an enhanced data set; and performing updating training on the pre-trained intelligent driving decision model according to the enhanced data set to obtain an updated intelligent driving decision model, generating an intelligent driving decision, and controlling vehicle operation, thereby realizing more accurate characterization of a dynamic game relationship in a complex traffic scene, and improving the accuracy of the dynamic game relationship. And the intelligent driving decision model can continuously adapt to an asymmetric interaction mode effect in a real scene.

The invention provides an intelligent data consanguinity tracking and visualization method based on graph calculation, and the method comprises the steps: carrying out the data structure analysis and metadata extraction of original data assets, so as to generate a standardized data asset package; performing graph node attribute definition on the data entities in the standardized data asset package, and performing graph edge attribute definition on the association relationship between the data entities to generate a first data blood relationship model; performing blood relationship path mining on graph nodes and graph edges in the first data blood relationship graph model to obtain a basic blood relationship path set, and performing quantitative calculation and feature labeling on path association strength in the basic blood relationship path set to generate a second data blood relationship graph model; and performing visual rule mapping on graph node attributes and graph edge attributes in the second data blood relationship graph model to construct a standardized visual data set and generate a data blood relationship visual interaction interface according to the standardized visual data set.

The invention relates to the technical field of recording and broadcasting teaching, and discloses a recording and broadcasting teaching course quality evaluation method based on cloud computing. The method comprises five steps of data item collection, data preprocessing, evaluation model construction, evaluation strategy optimization and quality optimization. Wherein the evaluation model construction adopts a dynamic heterogeneous improved graph calculation method, and evaluation reference data is obtained through the steps of construction of an evaluation heterogeneous graph, dynamic updating of a graph structure, construction of a three-layer layering weight mechanism and the like; the evaluation strategy optimization adopts a multi-objective guide improved multi-layer strategy optimization method, and optimal strategy reference data is obtained through the steps of improving a state parameter space, modeling a multi-layer strategy network and the like; and finally obtaining a course quality comprehensive optimization reference scheme. According to the method, multi-modal dynamic data can be comprehensively processed, correlation of each factor is deeply mined, multi-objective optimization is balanced, evaluation accuracy and effectiveness are improved, and specific guidance is provided for quality improvement of recording and broadcasting courses.

The invention discloses a self-service vending machine commodity identification method based on AI image identification, and the method comprises the following steps: 1, employing PSConv convolution, and improving the detection precision of small commodities under the condition of guaranteeing the small transformation of parameter quantities; step 2, establishing a high-order semantic relationship and enhancing semantic information capability by using an adaptive dynamic threshold hypergraph calculation module (ADT-HGC), and further improving the detection precision of the model; step 3, using a semantic collection-refining-mapping trinity semantic architecture to significantly enhance the detection precision of the model; compared with the prior art, the method has the advantages that multi-scale features are dynamically captured through the windmill convolution module to enhance the small commodity detection capability, and the self-adaptive dynamic threshold hypergraph calculation module is constructed to establish high-order semantic association among commodities; and collaborative optimization of local details and global context is realized in combination with cross-layer feature fusion and a reverse mapping mechanism, and finally, 91% of mAP detection precision is achieved under the condition that the parameter quantity is only increased by 0.28 M.

The invention discloses a graph calculation-driven complex publication derivative resource content layout planning system, which belongs to the technical field of digital publication and intelligent media, and comprises a multi-modal data analysis module for analyzing heterogeneous data such as texts, images, tables and the like in publications into structured node features; a feature fusion module; a content relationship modeling module; a graph calculation driving layout optimization module; performing layout constraint modeling: converting a layout problem into a graph constraint optimization problem; a modeling optimization module; a multi-terminal adaptive rendering module; the layout generation engine is used for converting a graph calculation result into a visual layout scheme; and the interactive feedback module is used for feeding back user operation to the graph in real time to trigger layout reconstruction. According to the method, advanced technologies such as graph calculation, multi-modal fusion and constraint solution are deeply fused, the limitation that a traditional typesetting tool depends on a fixed template is broken through, and a content-driven one-stop solution is provided for scenes such as academic periodicals, electronic textbooks and digital reports.

The invention provides a network security test coverage evaluation method and system based on deep learning, and relates to the technical field of network security testing, and the method comprises the steps: extracting a multi-dimensional feature vector through constructing a feature fusion network, calculating the similarity based on a test execution path diagram, carrying out the clustering, and removing redundant branches, traversing the optimized path set to obtain a key node sequence, evaluating the contribution degree, and establishing a mapping relation between the contribution degree and the test effect to determine the test coverage rate.

Disclosed are systems and techniques for image processing. For example, a computing device can process, using an encoder, an image to generate a feature map representing the image. The computing device can use the encoder to determine, based on the feature map, mask embeddings, negative mask embeddings, textual embeddings, and textual prompts for semantic segmentation of the image. The computing device can use a semantic segmentation model to determine, based on the feature map, mask proposals and a negative mask for the image and to determine a similarity map between total mask embeddings (including the mask embeddings and the negative mask embeddings) and total textual embeddings (including the textual embeddings and the textual prompts). The computing device can determine, using the semantic segmentation model, final semantic predictions for the image based on the similarity map and total mask proposals (including the mask proposals and the negative mask).

The invention belongs to the related technical field of graph calculation and streaming data processing, and particularly relates to a streaming graph-oriented random walk acceleration method, which comprises the following steps of: storing vertex information by adopting a hierarchical graph storage architecture consisting of a base layer, a dynamic extension layer and a chain storage layer, enabling neighbor ID (Identity) intervals stored in each layer to be different, and according to the degree change of a target vertex, carrying out random walk acceleration on the target vertex; dispersing and storing neighbors in different layers through a cross-layer migration mechanism; dividing neighbor information of the target vertex into a plurality of independent partitions, and independently constructing an alias table for each partition; a DPST is constructed for each target vertex, and one node maintains one partition to accumulate and add all neighbor weight values; when the neighbor weight of the target vertex changes, modifying the alias table of the changed partition, and updating the DPST; resampling is started from the position where the target vertex appears for the first time in all the migration sequences, and a sampling mode is selected according to the size relation between the weight skew factor of the target vertex and the threshold value. According to the invention, the random walk speed can be improved.

The invention discloses a customer portrait analysis method and system based on a knowledge graph, and the method comprises the steps: S1, collecting a user behavior event flow and an external environment event flow, and generating a dynamic event signal carrying a timestamp based on a heterogeneous data source; s2, responding to a dynamic event signal, and analyzing an event type to trigger incremental updating operation; s3, in response to the real-time graph updating signal, updating the feature vector of the user node through an incremental graph calculation algorithm to generate a portrait updating signal; s4, generating a graph updating instruction and a portrait recalculation instruction to form a cooperative control signal; and S5, feeding back a graph updating instruction in the cooperative control signal to an incremental updating operation step, and feeding back a portrait recalculation instruction to a feature vector updating step to drive a real-time cooperative closed loop. According to the air quality intelligent monitoring method and system based on sensing data feedback, the problems of client portrait hysteresis quality and low map-portrait cooperation efficiency can be solved.

The invention discloses an FTU-based power distribution network fault positioning method and system, and belongs to the technical field of power distribution automation, and the method comprises the steps: constructing a space-time correlation feature matrix according to a transient current sequence and a voltage drop sequence during a fault period, and extracting the convolution features of a graph to obtain a fault feature graph containing the fault correlation degree between nodes; according to a static topological structure in the power distribution information model, virtual impedance is calculated based on the fault feature graph, and network equivalent topology is dynamically identified to obtain a dynamic virtual topological structure graph; and based on the dynamic virtual topological structure diagram structure and the fault feature diagram, performing fault section confidence competing decision through the intelligent agent unit corresponding to each FTU based on an incomplete information game, and outputting a fault section positioning result. The power distribution network fault positioning method solves the problems that a traditional power distribution network fault positioning method is insufficient in positioning accuracy and poor in fault tolerance and excessively depends on centralized processing and global information synchronization when information is incomplete, fault features are complex and network topology dynamically changes.

The invention relates to a dynamic scheduling method and device for a power grid network frame topological structure based on graph calculation and a medium, and relates to the technical field of power grids, and the method comprises the steps: S1, collecting the multi-source data of a power grid, and constructing an initial power grid topological graph; s2, performing hierarchical processing on the power grid topological graph to obtain a plurality of sub-topological graph layers, establishing independent asynchronous calculation units, and monitoring state changes of power grid equipment in a jurisdiction area of the corresponding sub-topological graph layer by each calculation unit to generate update information; s3, predicting the change trend of the power grid topological structure in different time scales and space ranges based on the update information of each calculation unit, and generating a space-time prediction topological model; and S4, inputting the space-time prediction topology model into a decision generation module based on Monte Carlo tree search, generating a scheduling instruction, feeding back the scheduling instruction to the power grid topological graph, and performing verification and optimization until a target effect is met. Compared with the prior art, the method has the advantages of improving the corresponding scheduling speed and the like.

The invention discloses a communication network fault rapid positioning and recovery method based on self-supervised learning. The method comprises the following steps: S1, collecting and preprocessing communication network operation data; s2, constructing a communication network topological graph, and mapping the preprocessed data into node and edge attributes; s3, executing feature mask and structure disturbance, and constructing positive and negative comparison samples; s4, constructing a graph neural network model and pre-training by using positive and negative comparison samples; s5, calculating reconstruction errors of the nodes and the edges, and marking elements higher than a threshold value as abnormal candidate areas; s6, performing graph segmentation to extract continuous abnormal sub-graphs, and calculating sub-graph embedding and historical feature center similarity; and S7, matching an instruction sequence according to a positioning result, executing link scheduling, node reconfiguration and topology updating, and iteratively training the model. According to the method, high-precision rapid positioning and automatic recovery of communication network faults are realized under the condition of lack of a large number of labeled samples, and the method has a continuous optimization capability.