55 results about "Multiple edges" patented technology

The invention relates to the technical field of computer vision and image recognition, in particular to an image recognition method based on edge computing, which comprises the following steps: dynamically capturing an original image through a plurality of edge nodes, rejecting redundant regions through a multi-modal perception triggering mechanism, and establishing a cooperative processing group. Illumination equalization, noise filtering and resolution self-adaptive compression tasks are distributed according to dynamic role election, a standardized preprocessed image is generated, a lightweight convolutional neural network is operated in parallel to extract a dual-channel feature vector, and after entropy coding lossless compression and equipment identity tag and time sequence stamp attachment, the dual-channel feature vector is transmitted to a cloud end by adopting a lightweight encryption protocol. The cloud end analyzes the data packet, reconstructs a feature topological graph based on space-time relevance, loads a depth residual error recognition model to execute feature fusion and classification decision, feeds back and updates the weight of an edge node model, solves the problems of low collaborative efficiency and feature distortion, and improves the efficiency and precision of image recognition.

The invention relates to the technical field of edge computing, in particular to an edge node collaborative optimization method and system of a computing power network. Comprising the steps of collecting resource state information and historical behavior data of a plurality of edge nodes to form a resource state data set; constructing a computing power network topological graph based on the resource state data set, and extracting node feature representation of each node through a graph neural network; calculating the comprehensive credibility of each edge node based on the historical behavior data, and integrating the comprehensive credibility into the node feature representation; collecting energy consumption state data of each edge node, and calculating an energy consumption efficiency index of each edge node; and a coupling linkage mechanism of credibility and energy consumption perception is established. Through a coupling linkage mechanism of credibility and energy consumption perception, high resource utilization rate, low task delay, strong system robustness and green energy conservation of computing power network edge node scheduling are realized.

The invention discloses a photoetching mask optimization method and device, a computer storage medium and a program product, and relates to the technical field of semiconductors. The photoetching mask optimization method comprises the steps that edge breaking is carried out on an initial mask plate graph, multiple broken edges are obtained, and the multiple edges comprise irregular edges; determining n horizontal segments and n vertical segments corresponding to the irregular edge according to the horizontal width and the vertical width of the irregular edge; combining the n horizontal segments and the n vertical segments, and converting to obtain a regular edge corresponding to the irregular edge and a reticle graph containing the regular edge; and performing mask optimization on the intermediate mask plate graph based on the initial mask plate graph to obtain a target mask plate graph. According to the embodiment of the invention, the photoetching mask optimization of the irregular layout can be effectively realized, so that the overall photoetching mask optimization efficiency and precision can be effectively improved.

This article relates to the field of communication technology, and in particular to a device access authentication method, apparatus, and system. The method includes: in response to receiving an access authentication request, determining transmission parameters corresponding to each CPE, wherein the access authentication request is sent by the requesting CPE among multiple CPEs; based on the transmission parameters, performing edge connectivity judgment and processing on a pre-constructed CPE topology graph to obtain a target CPE topology graph, the CPE topology graph including multiple nodes and multiple edges, the edges being used to connect nodes to represent connectivity with two CPEs corresponding to two connected nodes; determining an index value for each edge in the target CPE topology graph based on the transmission parameters and the weights corresponding to the transmission parameters; and based on the index values, determining a target path in the target CPE topology graph, starting from the requesting node corresponding to the requesting CPE and ending at the target node corresponding to the target CPE, as the device access authentication path.

The present application discloses a method and device for predicting network risks, a processor and an electronic device. The method comprises: obtaining a network directed graph, wherein the network directed graph comprises at least a plurality of nodes and a plurality of edges, each node is used to represent each device in the target network, and each edge is used to represent the access relationship between multiple devices in the target network; obtaining a risk matrix corresponding to the network directed graph, a weight value corresponding to each node in the network directed graph and a weight value corresponding to each edge in the network directed graph; inputting the risk matrix corresponding to the network directed graph, the weight value corresponding to each node in the network directed graph and the weight value corresponding to each edge in the network directed graph into a graph neural network, and outputting the risk value corresponding to each device in the target network; and predicting the security risk of the target network according to the risk value corresponding to each device in the target network. Through the present application, the problem of low accuracy in predicting whether a network has security risks in the related art is solved.

Systems and methods for estimating a graph edit distance (GED) between compounds are provided. A first graph representing a first compound includes a plurality of nodes and a plurality of edges. An atom of the first compound is represented by the node of the first graph, and a bond of the first compound is represented by the edge of the first graph. A second graph representing a second compound also includes a plurality of nodes and a plurality of edges. Atoms of the second compound are represented by the nodes of the second graph, and bonds of the second compound are represented by edges of the second graph. The first graph is input into a model to generate a first potential embedding. The second graph is input into the model to generate a second potential embedding. An estimated value (GED) between the two compounds is determined from a difference between the two potential embeddings.

The invention discloses a multi-dimensional data intelligent processing and analysis method, which relates to the technical field of data processing, and comprises the following steps of: performing static dependency analysis on a parallel task set, and constructing a directed resource dependency graph containing a semaphore occupancy relationship, a calling hierarchy and a recursive path; depth-first loop detection is performed based on the directed resource dependency graph, a potential deadlock closed loop is identified and divided into a plurality of edge loop-free sub-graphs, and a sequenced execution plan is generated for each sub-graph. According to the method, by introducing static dependency analysis, resource dependency graph construction, a token lease mechanism and a multi-level semaphore pool, active avoidance of task deadlock risks and automatic recovery of resource anomalies in the engineering machinery multi-dimensional data processing process are achieved. Through sequential scheduling, adaptive regulation and control and self-healing monitoring strategies, the task scheduling stability and the resource utilization efficiency in a high-concurrency scene are effectively improved, and closed-loop optimization of task scheduling is realized in cooperation with process traceability and evolutionary knowledge base feedback.

The invention provides a network attack model training and detection method and device, electronic equipment and a medium, and relates to the technical field of network security. According to the specific implementation scheme, based on a preset causal relationship mechanism, a connection relationship between two nodes which are the same as any relationship in the causal relationship mechanism is searched in log data of a target network, and a plurality of connection relationships are obtained; based on the multiple connection relations, a first causal relation graph is constructed, and the first causal relation graph comprises multiple nodes and multiple edges formed by connecting every two nodes; deleting nodes and edges related to the non-attack chain in the first causal relationship graph to obtain a second causal relationship graph; based on the second causal relationship graph, multiple attack sequences are determined, the attack sequences comprise triple events arranged according to the time sequence, and each triple event comprises a source node, an edge and a destination node; and training to obtain a target network attack model based on the plurality of attack sequences.

The invention discloses an open set identification decision-making method based on an extreme value Copula joint model. The method comprises the following implementation steps: firstly, extracting training sample features through a deep neural network, forming a known category compact cluster and determining a center; calculating the distance from each training sample to the center of each cluster, and fitting generalized extreme value distribution for each known category as edge distribution; secondly, introducing an extreme value Copula function, constructing a multivariate joint extreme value distribution model in combination with a plurality of edge distributions, and depicting an extreme value distance dependent structure between clusters; and finally, calculating a new sample joint extremum probability based on the model, and setting a threshold to judge whether the new sample joint extremum probability is a known or open set unknown category. According to the method, the multi-edge distribution and cluster dependency relationship is unified, the traditional'tail independence 'constraint is broken through, the feature space geometrical relationship is quantified, and the accuracy, interpretability and robustness of open set recognition are remarkably improved.

In some examples, a method of determining a shortest path between two locations includes: a first device receiving a first graph representing a graph network including a plurality of regions, each region including a plurality of vertices and a plurality of edges; identifying each of the plurality of regions and sending the first map to a mobile device; the first device partitions the first map based on the identified plurality of regions, thereby generating a set of partition maps, each region of the identified plurality of regions corresponding to a respective partition map of the set of partition maps; generating, by the first device, a second graph defining information including the set of partitioned graphs and defining connectivity between the set of partitioned graphs, and transmitting the second graph to a mobile device; traversing, by the mobile device, the second graph to determine an advanced path including a plurality of shortcuts representing a side of the plurality of sides of the first graph that connects a first vertex and a second vertex; the mobile device determines a shortest path between the first vertex and the second vertex, the shortest path being determined based on the advanced path, the shortest path comprising an edge connecting the first vertex and the second vertex in the plurality of edges of the first graph; and the mobile device outputs the shortest path.

The invention provides a data partitioning and distributed query method, which comprises the following steps of: traversing a plurality of attributes of a resource description framework (RDF) data graph, extracting an edge induction sub-graph corresponding to each attribute, and constructing a maximized local connectable attribute set by applying a greedy algorithm based on partitioning information input by a user; coarsening weak connected components of the edge induction sub-graphs corresponding to the attributes to obtain a coarsened graph, and dividing the coarsened graph into a plurality of edge-disjoint data partitions based on a vertex disjoint division algorithm; obtaining a query statement input by a user, and determining an attribute type of the query statement; and sending the query statement to the data partition corresponding to the attribute type to obtain a query result corresponding to the query statement. According to the method, the processing efficiency and performance of the complex SPARQL query can be improved.

The present disclosure relates to a vein determination method, apparatus, electronic device, and storage medium. The method includes: determining unique edges in triangular faces by using vertex coordinates of a plurality of triangular faces constituting a leaf model to obtain multiple edge edges of the leaf model, determining an edge vertex sequence based on the multiple edge edges, determining vein feature points based on the edge vertex sequence, and finally determining the shortest path between the vein feature points and the petiole point as the vein of the leaf model, so that it is possible to determine the vein in the leaf model corresponding to a radially shaped leaf based on the vertex coordinates of the multiple triangular faces of the leaf model.

This application discloses a lightweight preprocessing method for geometric components in 3D scene rendering, relating to the field of 3D rendering. The method includes: when there are multiple edge points in a triangular mesh model, performing component edge shape detection based on the position information of the multiple edge points to determine whether the component to be processed is a cylindrical component; when the component to be processed is determined to be a cylindrical component, performing circular fullness detection on the bottom surface to determine whether the cylindrical component is a cylindrical pipeline; converting the geometric features of each cylindrical pipeline into an instantiated reuse matrix; combining the view frustum parameters of the current viewpoint and the instantiated reuse matrix to perform view frustum culling and occlusion judgment to determine whether each cylindrical pipeline is visible; for cylindrical pipelines, collaborative optimization is achieved in three stages: recognition efficiency, lightweight transmission, and rendering visibility screening. Through the preprocessing mechanism in the early stage of rendering, the overall efficiency of subsequent rendering is effectively improved.

The application discloses a retrieval enhancement generation method and related products, which comprises the following steps: obtaining a query vector; matching the query vector with a multi-dimensional feature graph to determine a target node; the multi-dimensional feature graph comprises multiple nodes and multiple edges; the node represents a node vector; the edge represents a relationship vector; there is an index relationship between the node vector and the relationship vector; the multiple nodes comprise the target node; performing feature extraction on the query vector to obtain a relationship feature corresponding to the query vector; performing dynamic graph walking in the multi-dimensional feature graph based on the target node and the relationship feature to obtain one or more effective paths; and obtaining a final answer based on the one or more effective paths. The application effectively avoids the "illusion" risk of a large model, ensures that the output content is compliant, reliable and auditable, improves the accuracy of the retrieval result in retrieval enhancement generation, and effectively breaks through the inherent limitations in semantic integrity, multi-hop reasoning capability and relationship intention understanding.

The present invention provides a power consumption data processing method for multiple user types, which relates to the technical field of power grids. The method includes constructing a heterogeneous power grid of a target area based on multiple node types, node attributes, multiple edge types, and edge attributes; applying heterogeneous graph convolution on the heterogeneous power grid, introducing a time dimension on the basis of heterogeneous graph convolution to construct a spatio-temporal heterogeneous graph convolution model, applying one-dimensional convolution in the time dimension to extract multi-scale spatio-temporal dependence patterns, and obtaining spatio-temporal heterogeneous features corresponding to the heterogeneous power grid; using the fuzzy C-means clustering algorithm to cluster users for the spatio-temporal heterogeneous features, obtaining a membership matrix of users for each cluster by optimizing the objective function, determining the optimal number of clusters according to the clustering validity index, and obtaining the user clustering result; by converting the power consumption load curve into a symbol sequence and applying a community discovery algorithm to identify the behavior clusters within the user group, obtaining typical power consumption behavior patterns.

This application discloses an image processing method, apparatus, device, and storage medium. The method includes: acquiring input data, which includes data of multiple modalities, and the input data is used to generate a three-dimensional scene; generating a mixed modality graph based on the input data, the mixed modality graph including multiple nodes and multiple edges between the nodes, each node representing an object, and each edge representing the relationship between two nodes corresponding to each edge; generating a three-dimensional scene based on the mixed modality graph, the content of the three-dimensional scene including the geometric shape information of the object corresponding to each node and the spatial position information of the object corresponding to each node in the three-dimensional scene. This allows for flexible processing of data of different modalities, improves the adaptability to input data, significantly enhances the support for complex user-inputted data, and enables the generation of three-dimensional scenes with high spatial consistency and geometric detail.

Generating transportation network solutions using graph neural networks, includes: generating, based on input data describing a product transportation network, a graph neural network representing the product transportation network, wherein the graph neural network comprises multiple edges, multiple source nodes, multiple destination nodes, and multiple intermediary nodes; performing a graph neural network prediction based on the graph neural network, wherein performing the graph neural network prediction comprises predicting inclusion in the transportation network solution for each edge and intermediary node; and generating a transportation network solution by performing a model optimization using an initial state based on the graph neural network prediction.

The application discloses an industrial internet remote monitoring operation and maintenance management system and method, and belongs to the technical field of industrial internet. The method comprises the following steps: in response to access requests of multiple edge nodes, collecting real-time running state parameters of each edge node and performing heterogeneous data graph construction to obtain a dynamic attribute graph structure; performing federated transfer learning on the multiple edge nodes based on the dynamic attribute graph structure to obtain a cross-domain joint inference model; constructing a dynamic reconfigurable digital twin corresponding to each edge node, and performing closed-loop dynamic reconfiguration on the digital twin by using real-time feedback data; performing multi-step simulation deduction based on the reconfigured digital twin to generate an adaptive operation and maintenance strategy; and decomposing the adaptive operation and maintenance strategy into an atomic control instruction sequence, and delivering the atomic control instruction sequence to an execution unit through an asynchronous message queue to realize remote collaborative control.

The present invention relates to the technical field of data processing, and discloses a multi-source heterogeneous data semantic alignment method, apparatus and computer device. Among them, the method includes: collecting multi-source heterogeneous spatio-temporal data through a central data node and multiple edge nodes, and performing spatial attribute feature extraction and inter-unit spatial correlation calculation to obtain an urban data semantic association degree feature matrix; inputting the urban data semantic association degree feature matrix into a multi-layer graph attention network for feature extraction to obtain a node feature vector matrix and a task association degree adjacency matrix; generating a distributed scheduling scheme for data processing tasks according to the node feature vector matrix and the task association degree adjacency matrix; allocating data processing tasks to computing nodes according to the distributed scheduling scheme, and performing alternating iterative optimization based on the urban data semantic association degree feature matrix to obtain a semantic mapping relationship set. This method realizes the intelligent scheduling of data processing tasks and efficient semantic alignment in a distributed environment.

The present disclosure is about a triangular mesh reconstruction method based on regional expansion. The method includes: constructing a tree structure to manage the point cloud data set; selecting seed points in the point cloud data set and constructing seed triangles; mapping the point cloud data set to a two-dimensional plane, taking one of the three sides of the seed triangle as the reference side in turn, and determining the candidate point set of the reference side from the point cloud data set according to the two vertices of the reference side; mapping the candidate point set back to three-dimensional space, selecting the optimal point from the candidate point set as the expansion point through the candidate point evaluation function to expand and obtain a mesh area; mapping the point cloud data set to a two-dimensional plane, taking one of the multiple sides of the mesh area as the reference side in turn, selecting the optimal point as the expansion point for regional expansion, until all points in the point cloud data set are constructed and the mesh reconstruction is completed.

The invention discloses an abnormal object recognition method and device, electronic equipment, a medium and a program product, and relates to the technical field of computers.The method comprises the steps that a graph model is constructed based on a graph structure corresponding to at least one time dimension, the graph structure comprises a plurality of nodes and a plurality of edges, the plurality of nodes comprise a user node, a device node, a website node and an application APP node; determining a plurality of first target nodes from the graph structure corresponding to the at least one target time dimension, wherein the first target nodes are device nodes in the graph structure corresponding to the target time dimension in the at least one time dimension; inputting the multiple pieces of first feature information into a preset decision tree model to determine at least one second target node; constructing a target graph structure based on the plurality of first target nodes, the at least one second target node and the user node associated with each first target node; and identifying abnormal user nodes in the target graph structure. According to the invention, the accuracy of abnormal object recognition can be effectively improved.

Embodiments of the present disclosure relate to parallel mask rule checking on evolving mask shapes in optical proximity correction (OPC) flows for integrated circuit designs. Systems and methods are disclosed that perform mask (manufacturing) rule checks (MRC) in parallel, sharing information to maintain symmetry when violations are corrected. In an embodiment the shared information is also used to minimize changes to the geometric area of proposed mask shapes resulting from the OPC. In contrast to conventional systems, MRC is performed for multiple edges in parallel, sharing information between the different edges to encourage symmetry. In an embodiment, all edges may be adjusted in parallel to reduce mask-edge traversal bias.

In some examples, a method of determining a shortest path between two locations comprises receiving, by a first device, a first graph representing a graph network comprising multiple regions, wherein each region comprising multiple vertices and multiple edges, identifying each of the multiple regions, and transmitting the first graph to a mobile device, partitioning, by the first device, the first graph based on the identified multiple regions to thereby generate a set of partitioned graphs, wherein each of the identified multiple regions corresponds to a respective partitioned graph from the set of partitioned graphs, generating, by the first device, a second graph, wherein the second graph defines comprises the set of partitioned graphs and information defining connectivity among the set of partitioned graphs, and transmitting the second graph to a mobile device, traversing, by the mobile device, the second graph to determine a high-level path comprising multiple shortcuts representing the edges of the multiple edges of the first graph that connect a first vertex and a second vertex, determining, by the mobile device, a shortest path between the first vertex and the second vertex, wherein the shortest path is determined based on the high-level path, wherein the shortest path comprises the edges of the multiple edges of the first graph that connect the first vertex and the second vertex, and outputting, by the mobile device, the shortest path.

The application discloses a network abnormal traffic detection method and system based on federated learning and drift detection. Through data preprocessing and spatio-temporal feature extraction on multiple edge nodes, feature data is generated. Each edge node independently detects whether the traffic has concept drift. If drift is detected, incremental learning is started and only the changed data is updated. The updated local model parameters are uploaded to the central server, aggregated and a global model is generated. After evaluation, it is distributed to the edge nodes for real-time traffic detection. This method combines federated learning and drift detection technology, not only protects data privacy, but also improves the accuracy and real-time performance of network traffic detection, suitable for traffic monitoring and anomaly detection in large-scale distributed networks. Graph neural networks and bidirectional long short-term memory networks are used to improve feature extraction and model training accuracy, ensuring stability and reliability in complex network environments.

The present invention provides a link prediction method and apparatus for resisting edge type interference in a heterogeneous social network. The method includes: constructing an initial heterogeneous social network link prediction model, where the initial heterogeneous social network link prediction model includes an edge feature extraction sub-model and multiple types of expert prediction sub-models; obtaining a data set in the heterogeneous social network and generating a heterogeneous social network graph according to the data set, where the data set includes multiple nodes, multiple edge samples, and multiple edge types; extracting edge features of each edge sample in the heterogeneous social network graph based on the edge feature extraction sub-model to generate an edge feature set; training the multiple types of expert prediction sub-models based on the edge feature set and a preset loss function to obtain a trained and complete target heterogeneous social network link prediction model; predicting a to-be-predicted edge link based on the target heterogeneous social network link prediction model. The present invention can predict multiple link types and new link types.

The invention provides a risk score calculation method and device and related equipment, and relates to the technical field of virtualization and communication, and the method comprises the steps: obtaining attack difficulty information among a plurality of network nodes through calculation according to the obtained historical utilization frequency of the plurality of network nodes, a time window needed by an attack, and an environment impact factor; an attack graph is constructed according to the obtained node information and attack difficulty information of the multiple network nodes, the attack graph comprises multiple elements, multiple edges and multiple weights, the weights correspond to the edges, the elements are used for representing the network nodes, the edges are used for connecting any two elements in the multiple elements, and the edges are used for corresponding to attack paths between the network nodes; the weight is used for representing attack difficulty information between two network nodes of corresponding edge connection; and inputting the attack graph into the graph attention network for scoring, and outputting a first risk score of the target node. In this way, the accuracy of the obtained first risk score of the target node can be further improved.

Methods, systems, and devices for wireless communications are described. A transmitting device may perform a lifting procedure on a base graph including multiple variable nodes and multiple check nodes to obtain a lifted graph. The lifting procedure may include replacing each edge between multiple variable nodes and multiple check nodes of the base graph with a respective identity matrices with respective circular shift values. The base graph may include a punctured variable node which corresponds to each of one or more check nodes of the plurality of check nodes via multiple edges. The transmitting device may encode multiple information nodes and multiple parity nodes according to the lifted graph. The transmitting device may transmit a signal including multiple information bits and multiple parity bits based on encoding the multiple information nodes and the multiple parity nodes.

The invention provides a graph neural network processor simulation framework-oriented acceleration method, which comprises the following steps of: decomposing a calculation task of a special GNN processor into a plurality of nodes by constructing a GPU (Graphics Processing Unit)-based simulation framework, and enabling each node to correspond to a calculation unit of the GPU; operators of the graph neural network are rearranged and optimized, so that vertex feature transformation operators are executed preferentially in the simulation framework, and edge data distribution operators are executed later; adopting a kernel fusion strategy to merge a plurality of GPU kernels into a single kernel; on the basis of a GNAS programming model, a workload is divided into thread blocks with edges as centers, each thread block processes calculation tasks of multiple edges in parallel, and results are accumulated to a target vertex through reduction and atomicAdd function operation. The invention further provides an acceleration system for the graph neural network processor simulation framework, a storage medium and electronic equipment. Therefore, redundant calculation and memory transmission can be reduced, and the simulation efficiency of the special GNN processor is effectively improved.

Generating transportation network solutions using graph neural networks, includes: generating, based on input data describing a product transportation network, a graph neural network representing the product transportation network, wherein the graph neural network comprises multiple edges, multiple source nodes, multiple destination nodes, and multiple intermediary nodes; performing a graph neural network prediction based on the graph neural network, wherein performing the graph neural network prediction comprises predicting inclusion in the transportation network solution for each edge and intermediary node; and generating a transportation network solution by performing a model optimization using an initial state based on the graph neural network prediction.