252 results about "Relational graph" patented technology

The invention relates to a water quality prediction method and system based on gating residual enhancement and feature fusion, and belongs to the technical field of water environment intelligent analysis and deep learning. Taking each water quality index as a node of the graph, and constructing two complementary variable relation graph structures by utilizing a Pearson's correlation coefficient and mutual information; respectively inputting the two graph structures into a graph convolutional network, extracting deep dependency features among indexes, and splicing and fusing the deep dependency features. A multi-head attention mechanism is used as a trunk to extract global time dependence, a GRU network is introduced to extract local time sequence features, GRU output is used as an adjustable residual term to be injected into the attention trunk through a residual gating mechanism, self-adaptive enhancement of local dynamic features is achieved, and finally a self-adaptive fusion mechanism is introduced to generate comprehensive representation. According to the method, the complex dependency relationship between the water quality indexes and the time dynamic evolution process can be modeled in a collaborative manner, the response capability to key local change and sudden change events is remarkably enhanced, and the accuracy and robustness of water quality prediction are improved.

The invention discloses an agent inference system based on multiple maps, and relates to the technical field of artificial intelligence, and the system comprises the steps: based on industry report, academic literature and business manual multi-source data, extracting entity-relationship-attribute, and constructing a knowledge map; dynamically capturing cooperation, report and task allocation relationships among entities, and constructing a production relationship graph; constructing a decision graph based on a field expert heuristic rule; based on the thinking engineering theory, human thinking modes and emotional states are analyzed, and a thinking map is constructed; integrating a knowledge graph, a production relation graph, a decision graph and a thinking graph, performing entity and mode alignment, mapping multi-source nodes and edges into the same vector space, introducing conflict resolution, and constructing a unified multi-mode heterogeneous knowledge graph; and guiding a large language model to generate a reasoning direction through path cue word injection, querying a constraint reasoning boundary, outputting an optimal reasoning result, and realizing agent reasoning of multiple maps. The method has the beneficial effect that the reasoning accuracy is improved.

The invention discloses a multi-priori knowledge fused cerebral apoplexy rehabilitation map convolutional network evaluation method, and belongs to the technical field of cerebral apoplexy rehabilitation evaluation. Firstly, a high-precision prior information matrix is automatically generated through a collaborative and causal relationship automatic reasoning method based on Riemannian manifold geometry and transfer entropy, the problem that in the prior art, engineering depends on artificial features is effectively solved, and interpretable physical prior guidance is provided for a model. Then, through a multi-relation graph construction and attention weighting multi-modal adaptive fusion method, spatio-temporal features and priori knowledge are adaptively fused, an optimized graph structure is constructed, and the representation ability and interpretability of the model to complex joint interaction are improved. And finally, through a space-time diagram convolutional network guided by prior information and a comparative learning collaborative optimization method, the generalization ability and evaluation precision of the model in a small sample scene are remarkably improved through data enhancement and loss function optimization.

The invention relates to the technical field of knowledge maps, and discloses a knowledge map completion method based on semantic-structure multi-level fusion. According to the technical scheme, for a training set positive example triple, a structured rationality score and a semantic correlation score are fused to screen high-quality training samples; in order to complement a query search relation path, screening a guiding path through a uniqueness index; integrating the query text, the entity description, the neighbor facts and the guide path to construct an enhanced input prompt; dynamic structure embedding is generated by using a relational graph convolutional network, the dynamic structure is mapped by an adapter module and then injected into a large language model, and completion prediction is completed by combining a fusion input fine tuning model. According to the method, through multi-level fusion of semantics and structural information, intelligent sample screening, prompt enhancement construction and structural information dynamic injection are achieved, the accuracy, reasoning ability and training efficiency of a large language model in a knowledge graph completion task are effectively improved, and the method is especially excellent in performance in complex relation reasoning and inductive completion scenes.

The invention discloses an operation and maintenance workflow cooperation system and method, and relates to the technical field of business process.The method comprises the steps that after a natural language operation and maintenance requirement is received, a subtask set containing task attributes is extracted through a semantic model built based on a pre-training operation and maintenance field language model; inputting the sub-tasks into a causal mining model, capturing an implicit dependency relationship between the tasks through an attention mechanism which takes task types and resource demands as weight regulation factors, and generating an operation and maintenance relationship graph which contains dependency confidence coefficients and dependency types and does not have cyclic conflicts; splitting the atlas into a task chain set and a free task point set by adopting a causal-oriented greedy pruning algorithm based on a directed edge association subtask maximum aggregation and task chain set scale minimization principle; task chains are distributed through a weighted matching algorithm in combination with the chain overlap ratio and the to-be-handled task amount of the intelligent agent, remaining free task points are distributed according to the balance principle, and accurate disassembly and efficient cooperation of operation and maintenance tasks are achieved.

The invention relates to the technical field of data intelligent traceability, and discloses a whole-process business data intelligent traceability method and system. The method comprises the following steps: collecting first data of a preset business link and creating a semantic tag to form a semantic tag data set; the semantic tag data set is stored in a Merkle tree structure, and a service block chain is constructed; extracting second data of each business link from the business block chain, and generating a fusion data set based on the second data; and establishing a relation graph according to the fused data set, after receiving a traceability query request, starting to search a traceability path from a starting service point in the relation graph, and outputting a traceability result, thereby ensuring the reliability of the traceability result, and solving the problems of serious data island, missing association relationship and low traceability precision of the traditional traceability technology.

The invention discloses a financial knowledge graph construction method and system based on artificial intelligence, and relates to the field of artificial intelligence data processing. The method comprises the following steps: performing multi-dimensional semantic analysis on a heterogeneous financial data source, and extracting a structured semantic fragment; constructing a financial entity perception unit, identifying a multi-granularity entity and generating a unique code; generating a preliminary relation graph based on the event cascade relation and the attachment structure, and injecting a semantic translation label; normalizing the atlas relationship through semantic separation and a label reconstruction mechanism to form a financial relationship network with consistent semantics; executing evolution increment iteration in combination with the newly added corpus, and dynamically updating nodes and edge sets; and performing semantic consistency and structural integrity evaluation on an iteration result, and outputting a stable financial knowledge graph structural body. By introducing a multi-factor semantic analysis model, a causal relationship modeling mechanism and a graph evolution iteration strategy, systematic improvement of the financial knowledge graph in the aspects of structural expression precision, semantic reasoning ability and dynamic adaptability is achieved.

The invention discloses a scientific and technological achievement analysis and prediction method and system based on big data, and relates to the technical field of machine learning and big data analysis, and the method comprises the steps: collecting and preprocessing multi-source scientific and technological achievement semantic data, and constructing a scientific and technological concept relation graph; the method comprises the following steps: performing training by taking a time sequence diagram convolutional network as a basic framework and taking a scientific and technological concept relation graph as a training sample, constructing a dynamic knowledge flow semantic model, performing evolution feature extraction on the scientific and technological concept relation graph by utilizing the dynamic knowledge flow semantic model, and outputting a knowledge flow feature vector; and inputting the causal enhanced space-time diagram into a space-time diagram neural network, aggregating semantic association and causal relationships among the scientific and technological achievements in a space dimension, capturing a dynamic change mode of scientific and technological achievement characteristics in a time dimension, and outputting a scientific and technological concept time sequence predicted value sequence. According to the method, the causal enhancement space-time diagram is constructed, so that trend deduction and causal traceability analysis are carried out for the time dimension, and the accuracy of scientific and technological achievement development trend prediction is improved.

The invention discloses an intelligent manufacturing feeding method and system fusing three-dimensional vision and robot cooperation, and belongs to the technical field of robot automation control. Three-dimensional point cloud data in a feeding area is acquired, and a workpiece space topological relation graph is constructed through adaptive clustering and boundary extraction; generating a task association tensor in combination with the physical attribute of the workpiece and a scheduling rule; the method comprises the following steps: collecting operation state information of a plurality of industrial robots, and constructing an action capability tensor; based on the task association tensor and the action capability tensor, an optimal task allocation matrix is generated through a multi-target collaborative optimization algorithm, and dynamic matching between the robot and the workpiece is achieved; in combination with real-time point cloud feedback, the initial path is corrected and the tail end is adjusted, and the robot is driven to accurately execute a grabbing task; the intelligent feeding system has the advantages of being high in environment adaptability, high in dispatching intelligence degree, excellent in path control precision and the like, and is suitable for high-dynamic complex manufacturing scenes.

The invention discloses an industrial design-oriented drawing semantic analysis and structured conversion method and system. The method comprises the following steps: acquiring an input image, carrying out different-scale coding on image features through an image coding backbone network, selecting a specific layer to extract a multi-scale feature map, and fusing to generate multi-scale features; inputting the multi-scale features into a geometric primitive detection network and an other element detection network, respectively identifying geometric primitives and non-geometric primitives, and carrying out positioning and classification; analyzing mutual relations between geometric elements and other elements contained in the graph through an element relation graph network, and generating formalized language description based on a matching rule; a Prompt template is constructed, geometric information is supplemented by using a multi-modal large model, the rationality of the supplemented information is verified through a geometric attribute relationship verifier, and complete formalized language description is obtained. According to the method, the industrial drawing image containing the complex constraint relation can be efficiently and accurately converted into machine-readable structured data.

The invention provides a product recommendation method and device, electronic equipment, a medium and a program product, and can be applied to the technical field of artificial intelligence, the technical field of big data, the technical field of block chains and the technical field of privacy computing. The method comprises the following steps: acquiring structured data and unstructured data of a target user; extracting preference features based on the unstructured data, and obtaining a time sequence preference portrait by using a time sequence attention model; obtaining a target user portrait based on the time sequence preference portrait and the structured data; obtaining a multi-dimensional sequential relation graph, and reasoning the multi-dimensional sequential relation graph by using a graph neural network to obtain relation representation; executing collaborative filtering scoring based on the target user portrait and the relationship representation, and generating an intermediate product score; taking the generated intermediate product score as an input, and outputting a candidate product score based on a recommendation optimization function containing a space-time weight; and performing product recommendation based on the candidate product scores.

The invention relates to the technical field of price monitoring, in particular to a building material multi-source price anomaly detection method, which comprises the following steps: firstly, uniformly metering and pricing calibers, learning a conversion coefficient, and constructing a replaceable relation graph; multi-source distribution is aligned through optimal transmission, residual errors and shadow prices are obtained based on structure invariants and variational inequality, and abnormal evidences are formed through hypergraph propagation and persistent coherence; generating a valence band reference in combination with a convex hull method and distribution robust optimization under the equilibrium clearing of graph regularization; a feasible set is defined by price bands and constraints, a weighted maximum satisfactory model is constructed to position a minimum default set, a minimum correction suggestion is generated by using vector optimal transmission and packet sparsity, and an executable closed loop is realized through satisfactory model theory verification.

The invention discloses an Internet of Things terminal anomaly clustering method based on a graph neural network. The Internet of Things terminal anomaly clustering method comprises the following steps that data are collected and preprocessed to form time series data; constructing an Internet of Things terminal relation graph, and representing time sequence correlation, spatial proximity and protocol layer interaction characteristics by using a multi-scale edge weight factor; weighting by using a feature attention mechanism to generate an abnormal sensitive input vector; performing time modeling by adopting phase-aligned expansion causal time sequence convolution to obtain time channel representation; an edge-time double-attention coupling mechanism is introduced into the improved ST-GNN model, edge attention and time attention are calculated, and an embedded vector is generated; executing density clustering and correcting isolated nodes and small-scale clusters through semi-supervised label propagation to obtain a correction result; and carrying out dynamic evolution analysis, identifying growing, merging and disappearing abnormal clusters, and feeding back to optimize modeling. According to the invention, the precision and robustness of Internet of Things anomaly detection are improved, and the method is suitable for large-scale Internet of Things safety monitoring.

The invention discloses a joint object attitude generation method based on physical perception and graph diffusion, and relates to the field of computer vision. The method comprises the following steps: firstly, reconstructing componentized geometric and physical attributes of an object from an image through a double-branch neural implicit network, and initializing a component connection relationship; then, a component relation graph is refined through kinematics fitting and time sequence consistency test, and attitude prior distribution of the component on the SE (3) manifold is inferred by utilizing a physically enhanced graph diffusion process; and finally, constructing a conditional diffusion model on the SE (3) manifold under the condition of prior and reconstruction information, and performing reverse sampling through a physically guided two-step reverse sampling framework to generate a group of diversified and physically reasonable joint object attitude hypothesis sets. According to the method, efficient generation of diversified and high-physical-rationality postures of a joint object is realized through tight coupling of physical rules and data driving generation.

The invention discloses a zero-sample composite fault diagnosis method based on semantic graph embedding and multi-stage fusion, and the method comprises the following steps: firstly, generating an initial semantic descriptor through manual definition or statistical features according to known fault types, and constructing a fault relation structure diagram to represent the association between types; combining reconstruction, semantic comparison and propagation loss by using a graph convolutional network, and fusing the initial semantics and the relation graph to generate enhanced semantic features; meanwhile, a multi-modal model is constructed to extract vibration, temperature, acoustics and other signal features, and after multi-stage fusion of input-stage cross-modal attention, feature-stage Transform and output-stage semantic alignment, a semantic feature supervision training network is jointly enhanced; and finally, extracting unseen fault features in a zero sample scene and carrying out classified diagnosis. According to the method, through a multi-modal fusion and semantic enhancement strategy, the precision and generalization ability of zero-sample composite fault diagnosis are remarkably improved.

The invention discloses a multi-platform log anomaly recognition and analysis method based on self-supervised learning, which comprises the following steps: collecting and preprocessing multi-platform data, constructing a call chain relation graph, and generating a standardized log sequence; carrying out conversational splicing to generate a conversational log sequence; inputting the conversational log sequence into an extended LogBERT model, and generating a multi-granularity log representation vector; cross-platform domain alignment processing is carried out through adversarial training based on gradient inversion and cross-platform comparison alignment, and cross-platform log representation in the unified embedding space is generated; an abnormal detection result is determined by adopting a one-class classification detection method and confidence interval calibration; generating a root cause analysis result by utilizing a graph attention mechanism and time sequence correlation analysis; and generating an exception report according to an exception detection result and a root cause analysis result. According to the method, the accuracy of multi-platform log anomaly detection and the precision of root cause analysis are improved, and the method is suitable for cross-platform operation and maintenance and monitoring scenes.

The invention discloses an event entity prediction method based on perceptual contrast learning, which comprises the following steps: obtaining a time sequence knowledge graph of all events, each event being represented by a subject, a relationship, an object and a time tetrad; performing reverse operation on the tetrad to obtain a reverse tetrad, and respectively constructing a global historical graph and a local historical graph for all events in any day; then constructing an event entity prediction model, and inputting the global historical graph and the local historical graph into the event entity prediction model to train the model; and finally, predicting the event entity by using the trained event entity prediction model. According to the method, the accuracy of event entity prediction is improved through multi-tense dynamic embedding and relational graph comparative learning, the influence of time on event evolution can be more accurately captured by adopting the multi-tense dynamic embedding, and a dynamic context is provided for local historical node feature updating; the problem that the flexibility is insufficient due to the fact that event prediction excessively depends on recent events is solved.

The invention belongs to the technical field of computer big data, and discloses a relation graph construction and layout method, device and system based on spectral clustering and a storage medium, a clustering center is initialized through a genetic algorithm, the clustering center serves as genetic information and is coded into a character string, the operation time can be shortened, and the classification precision can be improved; furthermore, a weighted Euclidean distance is constructed as a distance function of a K-means algorithm, mutual relation weighting between the features can be reflected, features of different weights are counted into the distance, the classification precision can be effectively improved, the loss is reduced, and the classification efficiency is improved. According to the method, an initial similarity matrix, obtained through a traditional similarity calculation method, between XML documents is corrected through an affinity propagation algorithm, the similarity between the hidden similar XML documents can be reflected, on the basis, the correct clustering number and the correct clustering result are obtained by applying a multi-path spectral clustering method NJW, the method is irrelevant to the sequence of the XML documents, and the method has the advantages of being high in practicability and easy to popularize. The method is suitable for clustering the retrieval results of the XML documents arranged in any sequence.

The invention relates to the technical field of computers, and discloses a visual operation and maintenance supervision platform based on a digital twinning technology, and the platform comprises a data preprocessing module which is used for preprocessing a multi-source heterogeneous monitoring data flow; the data fusion module is used for constructing an equipment topological relation graph, extracting an initial feature vector set of equipment nodes and carrying out space-time fusion; the digital twin modeling module is used for performing parametric modeling and semantic annotation; the real-time synchronization module is used for extracting a model updating instruction set and carrying out asynchronous message transmission and parallel updating; the anomaly detection module is used for training an anomaly detection model and analyzing anomaly types and anomaly reasons; the root cause tracing module is used for constructing an associated sub-graph of abnormal equipment, predicting a root cause candidate equipment list and carrying out hybrid reasoning and evidence fusion; the visual presentation module is used for visualizing a fault influence range, dynamically displaying network traffic and performing multi-view roaming and information drilling; according to the invention, the fault positioning efficiency and the operation and maintenance management level are improved.

A graph-forming process generates a graph having nodes that represent a plurality of previously captured screenshots. The graph-forming process relies on a plurality of machine-trained models to identify edges between pairs of the nodes. The edges represent relationships among the screenshots. The graph-forming process then trains a graph neural network (GNN) based on the graph. The training produces a plurality of target embeddings associated with respective nodes in the graph. A retrieval process retrieves a previously captured screenshot using the plurality of target embeddings. The retrieval process involves adding a new node to the graph that represents the query and using the GNN to produce a query embedding associated with the new node. The retrieval process then finds at least one target embedding that matches the query embedding and retrieves a screenshot associated with the matching target embedding.

The invention relates to the technical field of data processing, in particular to an enterprise associated person identity recognition and relation graph construction method and system. The method comprises the following steps: accessing entity data of a person to be identified and enterprise data associated with the entity data from a heterogeneous data source; through a multi-channel candidate recall engine, a candidate person and object entity set with the same name as the to-be-recognized person is retrieved from the relation graph; for each candidate person, calculating a comprehensive similarity score between the candidate person and the person to be identified by using a multi-dimensional evidence weighting and similarity calculation model; according to a comparison result of the comprehensive similarity score and a preset threshold value, judging whether the to-be-recognized person and the candidate person are the same entity or not; if it is judged that the to-be-recognized persons are the same entity, a graph database node merging operation is triggered, the relation associated with the to-be-recognized persons is migrated to existing candidate person nodes, redundant nodes are deleted, and a relation graph is updated; therefore, the problem of figure identity disambiguation can be automatically and intelligently solved with high precision.

The invention provides a graph neural network fraud detection method and system based on an attention mechanism, and the method comprises the steps: calculating the semantic similarity between a center node of a specific relation sub-graph in a multi-relation graph and a neighbor node of the center node based on a label perception mechanism; a reinforcement learning mechanism is utilized to adaptively adjust a selection filtering threshold value of a neighbor node; selecting neighbor node information, and aggregating the selected neighbor node information to form a first node representation of each specific relation sub-graph in the multi-relation graph; utilizing an attention mechanism to dynamically evaluate the importance of each specific relation sub-graph in the multi-relation graph to a center node, and distributing corresponding weights to form a comprehensive second node representation; fusing the first node representation, the second node representation and the node representation of the previous layer of the GNN to form a final embedded representation; and inputting the final embedded representation into a classifier for identifying and judging fraudulent behaviors. According to the method, efficient detection is realized through a sparse gating attention and reinforcement learning neighbor selection mechanism.

A method for managing an event includes: obtaining a dependency graph including a plurality of nodes representing operational elements of the event and a plurality of edges representing relationships between the operational elements; generating, for each of the plurality of nodes, a risk vector and a readiness vector based on an analytic routine; and performing a graph updating routine, wherein the graph updating routine includes: applying a modification to a first set of nodes of the plurality of nodes; identifying a subgraph of the dependency graph based on the modification, wherein the subgraph includes a second set of nodes of the plurality of nodes; generating a modified dependency graph by updating, for each node of the second set of nodes, the risk vector and the readiness vector; and displaying the modified dependency graph.

The invention belongs to the technical field of intelligent education and personalized learning, and provides a personalized learning path recommendation method based on a course knowledge point sequence. The method aims at solving the problems that existing learning path recommendation logic association is insufficient, the personalized matching degree is low, and the optimization efficiency is not high. The method comprises the following steps: constructing a knowledge point sequence model by adopting a topological sorting algorithm on the basis of a curriculum knowledge point pre-modification and post-modification relationship, a difficulty level and dependence intensity, and generating a structured knowledge relationship graph; a learner feature model and a knowledge resource model are established, learner features are described from the dimensions of learning targets, cognitive levels, learning styles and the like, and the matching degree with knowledge points is calculated; and constructing an optimization model taking learning cost minimization, mastering degree maximization and path continuity optimization as targets, performing iterative optimization by using an improved intelligent optimization algorithm, and generating a learning path with logic rationality and personalized adaptability. According to the method, the scientificity and learning efficiency of learning path recommendation can be effectively improved.

The invention provides a container capacity expansion method, system and device, belongs to the technical field of data processing, and aims to achieve container dynamic resource management.The method comprises the steps that running state data of all containers in a target container cluster are collected in real time; constructing a service calling relation graph according to the running state data; wherein the service calling relation graph is a directed acyclic graph, each node in the graph represents a micro-service, each edge in the graph represents a calling relation from the current node to the next node, and the weight of each edge represents service processing time delay; when a preset capacity expansion condition is met, executing a critical path algorithm according to the service calling relation graph, identifying to obtain a critical path, calculating the priority of each node in the critical path, and determining a to-be-expanded container according to the priority; determining an expansion strategy according to the state of the container to be expanded; and according to the capacity expansion strategy, carrying out capacity expansion on the container to be subjected to capacity expansion.

The invention discloses an aluminum veneer punching path optimization method based on artificial intelligence, and the method comprises the following steps: collecting hole site distribution information in an aluminum veneer design drawing, and generating standardized hole group data; constructing a hole group topological relation graph, and generating a hole group topological entropy feature vector; constructing a path state vector, and generating a plurality of groups of candidate punching path sequences through an OfficientZero reinforcement learning model; performing residual stress field prediction on the candidate punching path sequence to generate a corresponding stress stability index set; a comprehensive cost function is constructed, and iterative training is carried out on the OfficientZero model; and selecting the path sequence with the minimum comprehensive cost function value as an aluminum veneer punching path optimization scheme. According to the method, EfficitZero reinforcement learning and stress field prediction are adopted, intelligent optimization of the punching path of the aluminum veneer is achieved, and the method has the advantages of being high in efficiency, low in energy consumption and good in stability.

The invention relates to the technical field of pre-training models, and discloses an LLM-based industry graph multi-modal report generation system, which comprises a multi-source data fusion module, a triple extraction module, a knowledge graph construction module and a multi-modal output module. According to the method, comprehensive coverage of multi-source heterogeneous news text data is realized in combination with a large language model and a traditional crawler technology; calling a large language model to generate a structured industry report based on the industry relation graph node features and the relation weights; complementing the key data through a networking data complementing tool, and automatically generating a dynamic chart in linkage with a visual tool format; meanwhile, an interactive industry knowledge graph is rendered, user exploration entity association is achieved, and multi-dimensional output of texts, charts and graphs is achieved; high automation from data acquisition and processing to report generation is realized, flexible arrangement of a networking data completion tool workflow is combined, the manual intervention cost is remarkably reduced, and the system response efficiency is improved.

The invention provides a method and device for improving an RAG recall effect, and belongs to the technical field of computers, and the method comprises the following steps: file input and typesetting structure analysis: identifying a typesetting unit for an input file, extracting text content in the typesetting unit, and generating associated data of typesetting and content; constructing a two-dimensional relation graph: performing semantic segmentation based on the typesetting units, and extracting a logic relation of the typesetting units; constructing a two-dimensional relation graph of the semantic relation and the typesetting relation; and multi-dimensional information fusion recall: receiving user query and performing semantic analysis, recalling similar semantic slices from a semantic community and a typesetting community, executing double-graph cross validation, dynamically adjusting weights, and calculating and obtaining a final recall result. According to the method, the knowledge base construction mode of the RAG is optimized from the perspective of typesetting, the multi-dimensional relation between text semantics and typesetting logic is fused, information association in the knowledge base is more comprehensive, and the retrieval recall can be based on the semantic similarity and the typesetting logic at the same time, so that the recall effect is remarkably improved.

Methods, systems, and computer-readable media are used in graph-based machine learning of analog integrated circuits (ICs). In a first aspect, functional device pairs in transistor-level circuits are detected and classified using a hybrid approach combining a subgraph isomorphism algorithm, such as VF2, with a trained relational-graph convolutional network (RGCN). The VF2 algorithm identifies candidate pairs and initial categories, while the RGCN filters false positives using link prediction scores, preserving category labels for validated pairs. In a second aspect, a relational GraphSAGE model performs multi-class link prediction on a heterogeneous graph with netlist and functional relation edge types, labeling device pairs into analog primitive categories without technology-dependent features and merging overlapping pairs into larger functional groups. In a third aspect, circuit performance is predicted using a hierarchy-aware graph neural network comprising an edge-conditioned convolution (ECC) layer and multiple Circuit graph isomorphism network layers corresponding to hierarchy levels of device groupings.

The application discloses a graphite ore grade identification method and device, equipment and medium, and relates to the technical field of graphite ore grade identification. The application introduces Laplacian wavelet convolution instead of a traditional ordinary convolution kernel, realizes parallel extraction of multi-scale features, combines a multi-head attention mechanism to capture scale features of the ore under a global view, constructs a sparse sample relation graph based on an enhanced feature matrix, and uses a Chebyshev graph convolution network to perform multi-order neighborhood information propagation and aggregation on a graph structure to realize grade identification. The process reconstructs the grade identification problem from'single sample independent judgment' to'sample relation learning' under a small sample on the basis of global multi-scale feature extraction, so that the final prediction of each sample node depends not only on its own features, but also on similar feature information of all neighbor samples, thereby realizing high-precision identification of the grade of the graphite ore under a small sample.