253 results about "Hypergraph" patented technology

The invention discloses a hypergraph-based financial question and answer retrieval enhancement generation method and system, and the generation method comprises the steps: carrying out the blocking processing of a document stored in a corpus in advance, and obtaining text blocks; performing entity relationship extraction on the text blocks to obtain nodes and edges, and obtaining a node set and an edge set according to the nodes and the edges; constructing a hypergraph through a community clustering detection algorithm based on the node set and the edge set, and generating a corresponding abstract by using a large language model; constructing a knowledge graph according to the text block, the node set, the edge set, the hypergraph and the abstract; and performing node and hyperedge retrieval on the constructed knowledge graph to generate a final answer. According to the method, a retrieval enhancement generation method is used for answering complex financial questions, the illusion phenomenon of a large language model is reduced, and the answering reliability is improved; retaining a topological structure of the source text content; the hyperedge has abstract representation on the knowledge graph at different levels, and provides multi-dimensional selection for the context of the large language model.

The invention provides a tunnel construction safety monitoring and early warning method and system based on multi-dimensional data fusion, and relates to the technical field of construction safety early warning, and the method comprises the steps: obtaining first information which comprises tunnel construction parameters and image information; performing space-time fusion processing and redundancy reduction processing on the first information to generate a four-dimensional hypergraph tensor space of tunnel construction; performing cross-scale analysis and topology extraction on the four-dimensional hypergraph tensor space, and constructing a dynamic heterogeneous graph network; performing space-time diagram convolution processing on the dynamic heterogeneous graph network, and generating a composite risk manifold based on a result obtained by processing and a multi-head attention mechanism; coupling processing is carried out according to the composite risk manifold, stability analysis and critical state judgment are carried out based on the risk phase change hypersurface obtained through processing, and real-time early warning is carried out based on a dynamic early warning boundary of tunnel construction obtained through judgment. According to the invention, the risk identification accuracy and the early warning response timeliness in the tunnel construction environment are improved.

The invention discloses a fault diagnosis method and system based on a multi-scale adaptive hypergraph convolutional neural network, and belongs to the technical field of fault diagnosis. The method comprises the following steps: acquiring original vibration data of mechanical equipment, and carrying out data preprocessing; constructing a fault diagnosis model based on the multi-scale adaptive hypergraph convolutional neural network; and inputting the vibration data after data preprocessing into the constructed fault diagnosis model, and outputting a fault diagnosis result. According to the method, a vibration signal is decomposed into different frequency bands, features under various scales are extracted respectively, prior knowledge is fused, local topological graphs are constructed through various weighting measures, and a plurality of local topological graphs jointly form a spatial hypergraph to serve as input of a model; a dual-channel graph convolutional network is introduced to extract features, weights of different channels are adaptively distributed through an attention mechanism, and deep fusion of the features is realized. Experiments on two reference data sets show that the method can effectively improve the fault diagnosis accuracy, and has good stability and generalization.

The invention discloses a traffic flow prediction method based on adaptive dynamic multi-scale space-time hypergraph convolution. The method comprises the following steps: S1, collecting traffic data; s2, forming space-time enhancement data from the traffic data; s3, a multi-scale adaptive causal convolution module extracts multi-scale traffic flow change features; s4, constructing a dynamic hypergraph structure, defining a hypergraph incidence matrix, and generating a self-adaptive hypergraph by adopting an attention enhancement matrix decomposition method; s5, fusing the time features in the S3 and the hypergraph structure in the S4, designing a multi-scale fusion homogeneous convolution module, and realizing fusion of multiple different-scale spatio-temporal features; s6, extracting topological node features through a graph convolutional network and a hypergraph convolutional network by using the multi-scale spatial-temporal features, and performing adaptive weighted fusion through a gating feature fusion unit; s7, performing multi-scale feature integration by a residual feature aggregation module; s8, generating traffic flow prediction results of a plurality of time steps in the future; the method has the advantages of extracting the traffic space-time dependency relationship, improving the prediction precision and generalization ability, and being more suitable for dynamic traffic.

The invention relates to the technical field of data monitoring, and discloses an intelligent data monitoring method and a monitoring platform, and the intelligent data monitoring method comprises the steps: constructing a dynamic heterogeneous hypergraph model, and representing the complex relation and time sequence evolution characteristics among multi-source data nodes; based on a dynamic heterogeneous hypergraph model, realizing high-order relationship representation and calculation, and obtaining embedded representation of nodes and relationships; performing heterogeneous graph information transmission and aggregation by utilizing embedded representation of nodes and relationships, and capturing complex interaction characteristics among multiple nodes; according to the complex interaction characteristics, an abnormal propagation rate model is established, and accurate prediction of an abnormal diffusion path is realized; based on the abnormal propagation rate model and the abnormal diffusion path, multi-level collaborative anomaly detection is implemented, and collaborative faults across subsystems are identified; according to the invention, the abnormal propagation path can be predicted in advance, the abnormal prediction accuracy is improved, and the system fault response time is advanced.

The invention discloses a course session recommendation method and device, equipment, a storage medium and a program product, and the method comprises the steps: carrying out the channel splicing of a semantic embedding matrix of course text description data and a user behavior feature matrix, and generating a multi-dimensional feature matrix; constructing an adjacent graph and a hypergraph between courses according to the multi-dimensional feature matrix, performing graph convolution operation based on the adjacent graph and the hypergraph, and generating a target embedded representation vector of each course node; generating an attention weight of each course node, performing weighted aggregation on the target embedded representation vector based on the attention weight, and performing course session recommendation based on the target embedded representation vector after weighted aggregation; according to the method, the curriculum semantic features and the user behavior features are fused, so that the feature expression ability of curriculum nodes is effectively improved, local neighborhood features between curriculums and global features in a hypergraph structure are captured, dynamic changes of user interests are accurately captured, and accurate curriculum session recommendation is achieved.

The invention discloses an adaptive learning path recommendation method based on a hypergraph neural network and knowledge tracking, and relates to the field of learning path recommendation, and the method comprises the steps: determining an incidence relation between learning resources, and enabling the incidence relation to serve as an edge of a learning resource undirected graph; the features of the learning resources serve as embedded feature vectors of all nodes of the learning resource undirected graph; updating the embedded feature vector by using a graph neural network to obtain a resource embedded vector, and taking the resource embedded vector as a node feature of a learner hypergraph structure; performing iterative aggregation on the learner hypergraph structure by using a hypergraph neural network to obtain a dynamic resource embedding and learner behavior sequence, generating an initial recommendation list, further generating a candidate learning path set, and generating a Pareto frontier solution set by using a non-dominated sorting genetic algorithm II; and calculating a comprehensive score of each path in the solution set based on a dynamic weight distribution strategy and a comprehensive utility function, and determining an optimal learning path. According to the invention, the accuracy and effectiveness of learning path recommendation are improved.

The invention provides a traffic flow prediction method based on a dual hypergraph neural network. The method comprises the following steps: preprocessing traffic data collected by a sensor in a traffic road network in a certain time period; forming a data set by the preprocessed traffic data, and dividing the data set into a training set, a test set and a verification set; respectively constructing a traffic flow graph and a dual hypergraph according to the topological graph of the traffic network; constructing a traffic flow prediction model based on the space-time dual hypergraph convolution layer, wherein the traffic flow prediction model comprises an input layer, the space-time dual hypergraph convolution layer and an output layer which are connected in sequence; inputting the preprocessed traffic data in the training set into a traffic flow prediction model for training; testing the trained traffic flow prediction model by using the preprocessed traffic data in the test set to obtain a final traffic flow prediction model; and inputting the traffic data preprocessed in the verification set into the final traffic flow prediction model to obtain the predicted traffic flow. According to the method, multi-source data are fused and external knowledge is utilized, so that the spatial-temporal correlation in the data can be better understood and utilized, and the accuracy of a traffic prediction model is improved.

The invention relates to the technical field of natural language processing, in particular to a hypergraph neural network-based multi-modal entity relationship extraction method, which comprises the following steps of: acquiring a text-image pair and inputting the text-image pair into a preset hypergraph construction model, acquiring node characteristics and a multi-modal hypergraph structure of the text-image pair, the hypergraph structure comprises a group of hyperedge sets, each hyperedge in the hyperedge sets can be connected with a plurality of nodes at the same time, and the number of the nodes connected with the hyperedges is not limited; the node features and the multi-modal hypergraph structure are input into a preset hypergraph neural network model, the multi-modal entity relation in the text-image pair is output, and the hypergraph neural network model is used for analyzing hypergraph node information propagation from the semantic and contextual relation and giving corresponding weights to semantic information between modals in combination with an attention mechanism. According to the method, the multi-modal information can be effectively fused, and the entity category and the entity relationship of the multi-modal information can be identified.

Hypergraph matching algorithms have better matching accuracy at the cost of exponentially increased computation resources. Recent kd-tree-based approximate nearest neighbor (ANN) methods represent the compatibility between two hypergraphs as a sparse tensor, which still requires exhaustive calculation for large-scale graph matching problems. To decrease the computation for the large-scale hypergraph matching problem, this work proposes a CUR-based cascaded framework to generate the sparse compatibility tensor by decreasing the calculated compatibility between two graphs. The framework includes a CUR-based second-order graph matching algorithm, a fiber CUR-based tensor generation method, and a PRL-based hypergraph matching algorithm that is specifically suitable for sparse tensors. The experiment results show that the proposed cascaded framework requires much fewer computation resources and can effectively deal with larger-scale graph-matching problems. The PRL-based hypergraph matching algorithm can achieve a higher matching accuracy with a sparser tensor than existing methods.

The invention relates to the technical field of distributed data storage, and discloses a data index construction method for distributed data storage, comprising the following steps: constructing a hypergraph model of a distributed storage system through a high-order graph theory, the hypergraph model comprising a plurality of storage nodes, a plurality of data blocks and a plurality of query requests, the method comprises the following steps: performing load balancing optimization on storage nodes and a query request on the basis of a minimum cut theorem in a high-order graph model, mapping data blocks and the storage nodes to a consistent hash ring according to a consistent hash algorithm, reducing data migration through a virtual node mechanism, storing the data blocks on a plurality of storage nodes in a redundant manner by adopting a redundant coding method, and storing the data blocks on the storage nodes in a redundant manner. And a load distribution strategy of the storage nodes is adjusted through a game theory model, and load adjustment is optimized by adopting an optimal control method. The method can ensure high availability, expansibility and reliability of the system while improving the efficiency of the data storage system, and is suitable for a large-scale distributed data storage system.

Provided are techniques for performing a search using a hypergraph. Entities are identified. A knowledge graph using the entities is generated, wherein nodes of the knowledge graph represent the entities and edges between the nodes represent pair-wise relationships, and wherein each of the edges carries an edge score that quantifies a degree of coherence between a pair of the entities. A hypergraph using the knowledge graph is generated, wherein nodes of the hypergraph represent the entities and hyperedges represent relationships between multiple entities, and wherein each of the hyperedges carries a hyperedge score that quantifies a degree of coherence between the multiple entities. A search request is received. A search result is generated using the hypergraph, wherein the search result comprises a set of coherently related entities. The search result is returned.

The invention discloses a hypergraph feature representation method, system and device based on fuzzy logic and a medium, and the method comprises the steps: obtaining original data, and constructing a hypergraph structure containing vertexes and hyperedges according to the original data; the hypergraph structure is initialized, and an initialized hypergraph structure is obtained; and inputting the initialized hypergraph structure into a preset hypergraph convolutional fuzzy network model for feature representation processing to obtain a hypergraph structure after feature representation processing. According to the hypergraph convolutional fuzzy network model, fuzzy representation and the hypergraph technology are deeply fused, the membership core concept of fuzzy logic is introduced, the hard coding association limitation of an existing hypergraph representation learning method that no black is white is broken through, the technical problems that a traditional hypergraph model cannot capture association gradients and fuzzy semantics are lost are effectively solved, and the learning efficiency is improved. Therefore, the flexibility and accuracy of the model are effectively improved, and stable prediction is provided in an uncertain data environment.

The invention relates to the technical field of computer vision, in particular to a human body behavior recognition method and system. According to the method, a multi-head space hypergraph convolution module is arranged before each time graph convolution of an ST-GCN model, and a human body behavior recognition model is constructed; the multi-head space hypergraph convolution module constructs a non-uniform hypergraph to represent the topological relation of the human skeleton through the maximum number, which can be contained by hyperedges, of each node, and generates the output of the module in combination with a physical adjacency matrix reflecting the relation of each joint; virtual connection is also added, virtual features which are the same as the input channel dimension and the time dimension of the multi-head space hypergraph convolution module are constructed, and the virtual features and modal data features are spliced along the joint dimension and then serve as module input again, so that global semantic information of real nodes is enriched, generalization information of human body behavior modes is supplemented, and the real-time performance of the multi-head space hypergraph convolution module is improved. And stage dense connection is introduced between different layers to smooth the change degree of the features, so that the human behavior recognition precision is improved.

The invention discloses a multivariable time sequence prediction method based on a collaborative graph, and belongs to the technical field of time sequence analysis. The method mainly comprises the following steps that firstly, a multivariate time sequence is processed through a multi-scale feature extraction network, and feature representation matrixes under different scales are generated; secondly, capturing a multi-level relation mode between variables by utilizing a collaborative graph structure and a hypergraph structure, and generating an adjacent matrix and an incidence matrix which represent a multi-scale graph structure and the hypergraph structure; and then, learning a dependency relationship in space and time through the graph convolutional network and the hypergraph convolutional network to obtain multi-scale space-time dependency. And finally, fusing the feature dependence matrixes under each scale, and generating a final prediction result through a multi-layer perceptron and a convolutional neural network. According to the method, the multi-scale spatial relationship and the space-time dependency relationship are effectively combined, the multivariate time series can be predicted more accurately, and the prediction precision is improved.

The invention provides a storage resource optimization method and system based on a time sequence dependence hypergraph neural network, and belongs to the field of artificial intelligence computing. Based on medical health big data and computing resources, constructing and fusing data and computing resource dependency matrixes to obtain a static dependency relationship matrix; the method comprises the following steps: collecting a computing resource multi-source operation log, generating dynamic characteristics of each moment according to a fixed interval, introducing time sequence position coding and self-attention mechanism weighting in a sliding time window to obtain attention optimization characteristics, and generating a dynamic dependency weight matrix by combining a modeling historical hidden state and the dynamic characteristics; the static and dynamic dependency weight matrixes are fused to obtain a comprehensive dependency matrix, attention optimization features are used as nodes, hyperedges are constructed in combination with the comprehensive dependency matrix, and hypergraph association and other matrixes are generated; and inputting the matrix into a graph neural network, learning node representation in combination with a time sequence attention network, classifying nodes and mapping the nodes into scheduling actions, and realizing self-adaptive allocation of storage resources in combination with target function optimization of medical scene constraints.

The invention discloses a multi-modal recommendation method based on hypergraph edge diffusion, which comprises the following steps: firstly, collecting user-project interaction and multi-modal features, constructing a multi-source relation graph and generating a modal perception hyperedge; then, optimizing a hypergraph structure through forward diffusion and reverse denoising; performing feature learning in combination with local graph convolution and a global hypergraph attention network; then, cross-modal contrast enhancement is introduced to improve feature consistency; and finally, sorting recommendation is realized through joint optimization of recommendation loss, diffusion loss and comparison loss. According to the multi-modal recommendation method based on hypergraph edge diffusion, a modal perception hypergraph structure and a diffusion generation mechanism are introduced, so that the problem of recommendation performance reduction caused by sparse user-project interaction can be effectively relieved, and modal information and a high-order user-project relationship can be fully mined; and the recommendation accuracy and the model robustness in a data sparse environment are improved.

The invention discloses an electricity consumption anomaly detection method based on a graph structure, and relates to the technical field of electricity consumption anomaly detection, and the method comprises the steps: obtaining historical electricity consumption data, environment variable data and power grid physical topology information of a power grid region, and carrying out the standardization processing of the historical electricity consumption data, the environment variable data and the power grid physical topology information, a standardized time sequence-environment data set is obtained; based on the standardized time sequence-environment data set, identifying a causal association relationship between electricity consumption and environment variables through a causal discovery algorithm, and constructing a causal perception heterogeneous graph containing region nodes and environment factor nodes; based on a causal perception heterogeneous graph, introducing a plurality of region nodes of which hyperedge connection is influenced by the same environmental event to form a dynamic hypergraph structure for representing a many-to-many environment-region coupling relationship; based on the dynamic hypergraph structure, a graph comparison learning task is constructed, positive and negative sample pairs are generated by applying disturbance to node features and the graph structure, and unsupervised pre-training is completed;

The invention relates to an unsupervised region representation learning method and system for learning urban region embedding, and belongs to the technical field of urban calculation and intelligent systems. The method specifically comprises the following steps: S1, constructing a regional mixed graph network, and capturing pairing and grouping relationships among regions by using multi-modal data; s2, graph and hypergraph comparative learning is executed, and discriminative representation of region nodes and a high-order relation between regions are learned from graph and hypergraph structures through a parallel comparative learning module; s3, cross-module comparative learning is carried out, information exchange between graph and hypergraph node representation is promoted through a controller assembly, and the learning ability of the model is enhanced; and S4, optimizing model parameters, and generating more effective region embedding through joint optimization of graph loss, hypergraph loss and cross-module loss so as to support various downstream tasks. According to the technical scheme provided by the invention, the accuracy and efficiency of urban area analysis are improved, and the capturing capability of the model on complex interaction between the areas is enhanced.

The invention discloses a drug-microorganism association prediction method based on a multi-view variational graph automatic encoder and multi-scale hypergraph convolution, and the method comprises the steps: constructing a first drug-microorganism isomerism graph and a second drug-microorganism isomerism graph, and building local neighbor enhanced attribute embedding; learning attribute distribution of nodes by combining a multi-view variational graph automatic encoder; an enhanced hyperedge attribute is established in combination with cross attention; constructing a dynamically evolved hypergraph topology; establishing a multi-scale hypergraph convolution framework, and adaptively fusing multi-scale node attributes to obtain dynamic hypergraph attribute representation of nodes; through comparative learning of a plurality of graphs, the consistency of features of the same node in the plurality of graphs is enhanced. The prediction method can deduce the correlation tendency between the drugs and the microorganisms obtained in real time. In conclusion, the multi-view node attribute distribution and the multi-scale neighbor topology can be learned, the relation between the multiple nodes of the hypergraph can be dynamically coded, the node representation consistency is enhanced, and the performance of drug-related microorganism candidate prediction is improved.

The invention discloses a multi-modal data drawing logical relationship analysis method, electronic equipment and a medium, and the method comprises the steps: generating a node set based on drawing image data and text data; generating a cross-modal hyperedge set based on the spatial proximity relationship, the visual feature similarity and the semantic correlation between the node sets; generating a hypergraph embedding input representation based on the node set and the cross-modal hyperedge set; the hypergraph is embedded into the input representation input improved hypergraph self-attention network model, and a hyperedge logic relation type and a corresponding hyperedge confidence coefficient are generated; generating a graph structure result based on the hyperedge logic relationship type and the node set, wherein the graph structure result meets the structure legality requirement; and performing hyper-parameter automatic adjustment and convergence control on the atlas structure result based on hyper-edge confidence, and generating an optimal atlas analysis model and a structured output result. According to the method, the reliability and the quality of analysis of component nodes, logic edge relationships and semantic structures in the drawing are improved.

A hypergraph workload manager in a server is configured for failure tolerant and explainable state machine driven hypergraph execution. The hypergraph executor comprises a query optimizer, a hypergraph enlister, a pipeline analyzer, and a state machine generator. The query optimizer translates a user query into a query operator graph. The hypergraph enlister enlists the query operator graph into a hypergraph containing a set of query operator graphs representative of already submitted user queries. The enlistment is configured to join query operator graphs where it makes sense to optimize query executions. Updates to the hypergraph based on the enlistment results in a set of disconnected graphs. The pipeline analyzer performs an analysis of all operators of all queries in the hypergraph to find an optimal sequencing of execution. The state machine generator is configured to generate a hierarchical state machine for all operators of a disconnected graph of the hypergraph.

The invention relates to a hypergraph neural network inference method and system. The method comprises the following steps: extracting topological information with a vertex with the highest degree from compressed hypergraph topological representation; identifying the common vertex with the highest degree and the hyperedge connected with the common vertex and sending the common vertex and the hyperedge to a task queue; triggering hyperedge aggregation operation on each hyperedge in parallel based on common vertexes from the common vertex table in the task queue; hyperedge aggregation operation is executed, generated hyperedge aggregation intermediate results are temporarily stored in an intermediate result buffer area of an on-chip cache unit, and in the process of executing hyperedge aggregation operation of hyperedges in sequence based on the hyperedge storage sequence in the hypergraph topology, the hyperedge aggregation intermediate results from common vertexes of a common vertex table are reused, and the hyperedge aggregation intermediate results from the common vertexes of the common vertex table are reused. And thus, a final hyperedge aggregation result of each hyperedge is obtained. According to the method, calculation tasks are executed more compactly, meanwhile, a large amount of unnecessary memory access and communication are avoided through cache reuse, and the calculation efficiency of hypergraph neural network reasoning is improved.

The invention discloses an e-commerce advertisement accurate recommendation system based on deep learning, and relates to the technical field of e-commerce, and the system comprises the following modules: an entity index module used for constructing a node registry; the hypergraph construction module is used for continuously monitoring an event stream and constructing a dynamic hypergraph; the initial embedding module is used for extracting a node embedding tensor and a hyperedge embedding tensor; the graph representation learning module is used for extracting a final node embedding representation tensor and a final hyperedge embedding representation tensor by improving a GraphTransform model; the click rate estimation module is used for outputting the predicted click rate of each candidate advertisement; and the sorting decision module is used for screening a candidate advertisement list. According to the method, the limitation that a traditional recommendation method depends on simple characteristics and neglects high-order association and dynamic evolution information is overcome, and a powerful solution is provided for realizing efficient, accurate and personalized e-commerce advertisement recommendation.

The invention provides an interest point recommendation method and device for heterogeneous multi-graph representation learning, equipment and a medium, and the method comprises the steps: obtaining a set of users and POIs containing multi-dimensional situation information in a location social network, building a user-POI interaction graph, and extracting feature vector representation of the users and the POIs in an interaction space by adopting a neighborhood similarity measurement method; based on user sign-in time information and text description information, calculating a semantic information similarity distance and a time pattern similarity distance, constructing a user-user perception graph, and learning feature vector representation of the user in a social space; constructing a distance hypergraph by utilizing POI position information, and obtaining feature vector representation of the POI in a position space after dimension reduction clustering processing; and fusing each feature vector representation in the social space and the interaction space as well as the position space and the interaction space, extracting a user representation vector and a POI representation vector, and predicting user preferences by using a neural network model to realize POI recommendation.

The invention belongs to the technical field of hypergraph segmentation, and particularly relates to a hypergraph segmentation method based on self-supervised learning, so as to provide a solution of a hypergraph segmentation problem with fewer cut edges and better balance in industrial application scenes such as integrated circuit design. According to the method, only the hypergraph structure and the number of the sub-blocks needing to be segmented are needed to serve as input, the hypergraph segmentation problem is trained and automatically solved through the end-to-end self-supervised neural network model, and due to the fact that operation included in the adopted loss function is matrix operation such as PyTorch supported by a current deep learning framework, the method has high operation efficiency, and the method is easy to implement. A traditional heuristic graph segmentation algorithm represented by multi-layer hypergraph segmentation needs to use heuristic information, so that local optimum is easy to fall into, and compared with the traditional heuristic graph segmentation algorithm, a result closer to a globally optimal solution can be obtained under some conditions; compared with a traditional method, the method has a certain advantage in the aspect of reducing the number of cut edges while ensuring the balance of each block obtained by hypergraph segmentation.

The invention provides a modeling method of a whole-brain space-time multi-layer functional connection network, which comprises the following steps: preprocessing resting state functional magnetic resonance imaging data, and extracting a blood oxygen level dependent signal of a region of interest; dividing the blood oxygen level dependent signal into a plurality of overlapped time windows by adopting a time window sliding method; based on a Pearson correlation method and an L1 sparse linear regression algorithm, estimating edges and hyperedges between the brain regions; based on a graph theory and a hypergraph theory, modeling the edge and the hyperedge into a graph and a hypergraph respectively, and constructing a spatial multi-layer function connection network; and constructing a spatial multi-layer function connection network in each time window so as to construct a whole-brain space-time multi-layer function connection network. According to the method, comprehensive description of space and time multi-layer dynamic features of the brain FCN can be realized, and the characterization capability of the brain FCN on brain dynamic information is improved.

The invention provides an equivalent hypergraph construction method for traffic flow prediction. The equivalent hypergraph construction method comprises the following steps: S1, data collection: collecting traffic flow data of each region through a sensor of an intelligent traffic system; s2, data processing: carrying out preprocessing and normalization processing on the collected traffic flow data, and constructing a graph structure of a traffic system and a training graph neural network model; s3, constructing a graph neural network: selecting a GCN as a framework of the graph neural network; s4, client node construction: performing feature fusion on the graph constructed for the local jurisdiction by each client through an attention mechanism; and S5, constructing an equivalent hypergraph: for n clients formed by traffic flow information of n regions, repeating the step S4 to obtain n client nodes, adding edges and weights according to a region adjacency principle to obtain an initial equivalent hypergraph, and continuously training and comparing based on the initial equivalent hypergraph to finally obtain the equivalent hypergraph. The risk of privacy disclosure is reduced, the efficiency of model training is improved, and the prediction precision of the model is improved.

The invention relates to the field of deep learning, and discloses a multi-agent collaborative task state embedding method based on a multi-scale hypergraph and multi-dimensional aggregation. In order to solve the problems that an existing graph neural network is difficult to capture a high-order interaction relation, poor in dynamic environment adaptability and limited in communication, the method comprises the steps of constructing a state observation graph; calculating an adjacent matrix according to explicit states such as position and speed; generating a latent layer feature adjacency matrix through nonlinear conversion and similarity calculation of a graph convolutional network, and fusing the latent layer feature adjacency matrix with the Hadamard product of the interactive graph; constructing a multi-scale hypergraph (containing S scales) according to the latent layer matrix, and searching a high-density sub-matrix to form hyperedges; building a two-stage information aggregation model: integrating multi-dimensional features and calculating association degree and interaction types in a hyperedge aggregation stage, and updating node features by using a graph attention network GAT in a node aggregation stage; a multi-agent soft behavior-commentator algorithm MASAC is fused, a behavior and reward function is designed, and an MHGNN-MASAC model is formed; the method is applied to cooperative control task decision.

The invention relates to the technical field of field programmable gate array physical optimization, and discloses a field programmable gate array multi-resource division method, device and equipment, the method comprises the following steps: generating a hypergraph comprising vertexes and hyperedges based on a netlist, the hypergraph comprising one or more types of resources; carrying out first partition division on the hypergraph, and carrying out multi-level vertex combination; partitioning the hypergraph of the maximum merging hierarchy, dividing vertexes in the maximum merging hierarchy to each partition, and carrying out the following processing on the hypergraph of each hierarchy from the maximum merging hierarchy to the minimum merging hierarchy: moving a first vertex between the partitions in the target merging hierarchy, and meeting the multi-resource constraint of the partitions in the moving process; splitting the vertexes in the target merging hierarchy into the vertexes of the previous hierarchy of the target merging hierarchy; until a first hypergraph is obtained; moving a first vertex in the first hypergraph to obtain a first partitioning result; and carrying out partition division again until the position of each functional module is determined.