35 results about "Complete graph" patented technology

The invention relates to the technical field of artificial influence weather, and discloses an artificial influence weather knowledge graph construction method and system based on a large model. The method comprises the steps that multi-source meteorological data are collected and preprocessed to generate a standardized data set; extracting a meteorological feature set by using the pre-trained large model; detecting a data dynamic change frequency, and starting a dynamic strategy to switch and mark an abnormal data segment when the data dynamic change frequency exceeds a threshold value; in combination with a similarity matching result of the historical knowledge graph and the current features, decomposing the feature set of the non-abnormal data segments to generate knowledge feature subsets; correcting the knowledge feature subset based on the coupling relationship between the meteorological kinetic parameters and the environmental parameters; and reversely backtracking the key influence factors along the weather influence propagation map, and constructing the knowledge map. According to the method, multi-source data are integrated through standardized processing, abnormal data are dynamically identified, historical knowledge and physical mechanism are combined to correct features, key factors are finally backtracked to complete graph construction, and the method is suitable for knowledge integration and analysis in the field of artificial influence weather.

The invention discloses a multi-unmanned aerial vehicle cooperative regional patrol path planning method based on hierarchical optimization, and the method comprises the steps: firstly, abstracting a task space containing a base station and a plurality of target points into a weighted undirected complete graph, and building a mathematical model with a target of minimizing the total completion time of a system and the standard deviation of task time; then solving is carried out through a hierarchical strategy; firstly, k-means clustering is adopted to carry out initial task allocation; solving a traveling salesman problem for each task cluster by using a simulated annealing algorithm, generating an initial path, and performing local optimization by using a 2-OPT algorithm; and finally, carrying out global collaborative optimization by adopting adaptive large-scale neighborhood search, dynamically adjusting task allocation and paths through a cross-unmanned aerial vehicle damage and repair operator, and carrying out iterative optimization according to a composite acceptance criterion and an adaptive mechanism to generate a near-optimal scheme. According to the method, through tight coupling of task allocation and path planning, the defect that a traditional method is prone to local optimization is effectively overcome, and joint optimization of completion time and load balancing is achieved.

This invention relates to a user interface layout generation method based on a latent diffusion model, belonging to the field of image generation. This invention extracts components and constraints from interface requirement description text using the BERT model, utilizes a graph convolutional network module to predict complete constraint relationships and borders to generate a complete graph, and generates the user interface layout based on the latent diffusion model. On one hand, introducing a latent diffusion model into user interface generation can meticulously capture the complex relationships and details between UI elements, thereby generating a more accurate user interface that conforms to interaction specifications. On the other hand, introducing a graph convolutional network into user interface generation can effectively predict complete constraint relationships between components, effectively capturing and modeling the complex dependencies and interactions between user interface elements; through graph structures, multi-dimensional constraints such as the position, alignment, and function of elements are applied, generating a more coordinated layout that conforms to design specifications; improving the aesthetics and usability of the generated interface, and enhancing the user experience.

The application discloses an airport crowd route guidance scheme optimization method and device and a storage medium, and the method comprises the following steps: acquiring layout information of an airport, and abstracting an airport scene into a complete graph according to the layout information; screening edges in the complete graph according to a preset screening condition, so as to delete edges that do not meet the condition; abstracting an airport crowd route guidance scheme optimization problem into a combination optimization problem according to the screened complete graph; and using a discrete differential evolution algorithm to optimize the combination optimization problem, so as to obtain a final optimization result. The application performs mathematical modeling on an airport departure layer scene, and automatically generates and optimizes an airport crowd route guidance scheme by using a discrete differential evolution algorithm, so that a high-quality solution can be obtained, and the guidance of the crowd route in the airport can be effectively assisted. The application can be widely applied to the fields of intelligent transportation and evolutionary calculation.

The invention relates to the technical field of neural network acceleration, and relates to a CPU-FPGA-oriented graph neural network training acceleration method and system. The method comprises the steps that a CPU stores complete graph feature data and distributes different feature data to storage modules of different FPGAs through data channels according to a load balancing algorithm; partitioning the GNN network model by the CPU, and matching a partitioned model operator with a corresponding FPGA (Field Programmable Gate Array); the CPU completes issuing and sampling of a partition model according to a sampler algorithm, and sends the partition model to the FPGA; reading feature data after the FPGA is started, completing a calculation task by a load execution module, and writing a result back to a CPU memory; the CPU completes data updating and weight updating; and resending the updated weight data to the corresponding FPGA, and carrying out iterative training. According to the invention, operation of the graph neural network on a CPU-FPGA platform is successfully realized, and the overall acceleration effect is excellent.

The invention discloses a power distribution network load flow calculation method based on graph synchronization parallel and forward-backward substitution, and the method comprises the steps: building a graph model in a graph database based on a power network, and enabling the graph model to be divided into a plurality of sub-graph models; setting an initial state for nodes in the sub-graph model, traversing the sub-graph model in a graph node parallel computing mode, and recording a node layer number and a node path of the sub-graph model; and in combination with the sub-graph model, completing graph calculation through forward tracking current calculation and backward tracking voltage calculation in sequence by utilizing a forward-backward substitution method, and judging whether an absolute value of a voltage difference value of nodes in the sub-graph model is smaller than the maximum iteration convergence precision or not. According to the method provided by the invention, the graph model is established, and graph calculation is carried out in a graph parallel mode in combination with a forward-backward substitution method, so that the calculation speed can be obviously improved.

The application discloses a water body saliency target detection method based on multi-graph learning, relates to the technical field of saliency target detection, and comprises the following steps: step one: data acquisition: water body information is acquired through unmanned aerial vehicle images or remote sensing images; step two: data preprocessing: an adjacency matrix is generated based on SLIC superpixel segmentation of the acquired images, and a complete graph is constructed; step three: multi-feature extraction: (1) color feature map extraction; (2) contrast feature map extraction; step four: saliency detection by a manifold ordering method; step five: combination of multiple saliency maps; step six: saliency optimization: the images are processed through a saliency optimization framework, and a new saliency effect drawing is obtained; the color feature map, the contrast feature map and the saliency detection map obtained by the manifold ordering method are weighted and fused with different weights, a new saliency map is obtained, and finally saliency optimization is performed, so that a new saliency target detection method based on a multi-graph learning model is realized.

This invention discloses an adaptive graph clustering method based on feature adversarial and graph Transformer, belonging to the field of image processing technology. The original graph is optimized by a feature adversarial autoencoder module to match prior distributions of representation features, obtaining attribute-level features. The feature adversarial autoencoder module includes an autoencoder and a feature adversarial module. The original graph is then processed by a graph Transformer autoencoder module to perform the convergence and fusion of local features and global structure, and information propagation, obtaining structural-level features. Adaptive fusion of attribute-level and structural-level dual-source features from the feature adversarial autoencoder module and the graph Transformer autoencoder module completes graph clustering. The training of the feature adversarial autoencoder module and the graph Transformer autoencoder module employs a self-supervised learning approach. A joint optimization loss function guides the joint optimization of graph representation learning and cluster assignment. The joint optimization loss function includes a feature adversarial loss function, an optimization loss function, and a self-supervised learning loss function. The feature adversarial loss function includes the feature reconstruction loss function of the autoencoder and the minimum cross-entropy loss optimization function of the feature adversarial module.

The invention is suitable for the technical field of electric power Internet of Things, and relates to a power grid real-time topology identification method and system, a medium and a terminal, and the method comprises the steps: S10, taking all measurement points in a power grid as nodes, constructing a virtual edge between any two nodes, and obtaining a virtual complete graph; s20, constructing a node feature vector based on the electrical measurement data of each measurement point, and constructing an edge feature vector corresponding to a virtual edge based on a space-time correlation feature and an instantaneous difference / ratio feature between the measurement data of the paired measurement points; s30, reasoning the virtual complete graph through a pre-trained physical information fusion graph neural network model, and outputting the probability that each virtual edge is a real physical connection; and S40, judging the real topological structure of the power grid according to the probability. The method is simple in process and convenient to operate, high-precision identification of the power grid topological structure is achieved, and reliability and safety of an identification result are guaranteed.

The application discloses a high-speed railway station crowd dispersing route optimization method, system and device and a medium, wherein the method comprises the following steps: acquiring layout information of a high-speed railway station, representing a high-speed railway station scene as a complete graph according to the layout information; screening edges in the complete graph according to a preset screening condition; according to the screened complete graph, representing a high-speed railway station crowd dispersing facility layout design problem as an optimization problem of solving a multi-dimensional binary coding vector; acquiring historical passenger flow data of the high-speed railway station, constructing a simulation model of the high-speed railway station scene according to the historical passenger flow data and the optimization problem, optimizing the simulation model through a discrete competitive particle swarm algorithm, and obtaining a final crowd dispersing route. The application abstractly simplifies the crowd flow guiding facility design into an optimization problem for solving, and adopts the competitive particle swarm algorithm for optimization, so that the high-speed railway station crowd dispersing facility layout optimization problem can be better solved, and the application can be widely applied to the fields of system simulation and intelligent calculation.

This invention relates to the field of data processing and resource management technology, specifically disclosing a method and system for calculating the offset of succession trajectory in degraded forest habitats. The invention acquires multi-period three-dimensional laser point cloud data, generates a set of static physical anchor points through morphological elevation filtering and density clustering for noise reduction, calculates spatial affine transformation parameters using singular value decomposition based on the initial phase, and performs inverse rigid body transformation on the point cloud to generate aligned data. It extracts the centroid of vegetation trunks to construct an undirected complete graph, runs a minimum spanning tree algorithm to obtain the total length of the current habitat structure, and compares it with the baseline value to generate the topological offset. Then, it orthogonally decouples this data with soil sensor data to generate three-dimensional deviation vectors for water deficit, nutrient loss, and increased plant spacing. Finally, it solves for the projection coefficients using a system of linear equations to generate a precise allocation list for irrigation water, compound fertilizer, and seedlings, and schedules automated terminals to execute this list, achieving closed-loop intelligent management.

The application provides a kind of based on betweenness centrality and geometric consistency graph contrast learning method and device, it is related to graph classification technical field.The method includes: according to the betweenness centrality of graph data node and edge, enhanced graph data is constructed to delete probability;Get the node feature of graph data and enhanced graph data, obtain graph representation by aggregating node feature based on Gaussian kernel reading method;According to the topological structure and node feature of graph data, construct multi-scale geometric consistency loss, construct normalized temperature scale cross-entropy loss according to graph representation, and then construct total loss to realize graph classification.The application introduces graph betweenness centrality into graph contrast learning, so as to retain important structural information of graph in graph enhancement process;Introducing multi-scale geometric consistency loss makes the structure information of graph can better guide the generation of graph feature;Optimize aggregated node feature based on Gaussian kernel reading method to obtain complete graph representation, to obtain more discriminative graph-level features.

The application discloses a kind of knowledge graph and sliding bearing surface damage degree evaluation method of big model linkage, belong to mechanical condition monitoring technical field.The application collects sliding bearing fault unstructured text and field damage data, combined with big model and FMEA framework, constructs four tuple initial knowledge graph;Through subgraph decomposition, value pruning and semantic anchor fusion, complete graph topology optimization.Damage information is standardized entity alignment, and optimized knowledge subgraph is obtained by constraint screening;Adopt nonlinear function quantification single damage failure risk, introduce coupling gain coefficient to establish multi-damage coupling evaluation system, and calculate comprehensive failure risk.Relying on hierarchical prompt template constraint big model reasoning, generate interpretable damage assessment report.The application solves the problems that traditional evaluation relies on artificial, hard threshold value determination has poor stability, multi-coupling risk is easily underestimated, and intelligent diagnosis lacks machine interpretation.The evaluation precision is high, and it is suitable for heavy machinery sliding bearing intelligent operation and maintenance scene.

The invention discloses a vector retrieval method and device for a balanced graph topological structure, and relates to the field of vector retrieve.The method comprises the steps that firstly, a graph is initialized into a minimum directed complete graph with any vector meeting the target in-out degree, a gradual vector adding mode is adopted, a forward optimization multi-level edge selection strategy and an edge refining mode are combined, and the minimum directed complete graph with the target in-out degree is obtained; and finally, constructing a neighbor graph of a balanced graph topological structure, and then performing greedy approximate nearest neighbor retrieval on the neighbor graph for the query vector to obtain a query result. According to the method, the balance of the topological structure of the neighbor graph is realized, the problem of deflection of the topological structure of the neighbor graph caused by unbalanced vector distribution is eliminated, and the accuracy and efficiency of vector retrieval are effectively improved. Compared with a current mainstream neighbor graph composition method, the composition method does not depend on reverse edge adding operation to update neighbors for existing vectors in the graph, and composition complexity and time expenditure are reduced.

The application discloses a subway station crowd transfer route optimization method and device and a storage medium, wherein the method comprises the following steps: acquiring layout information of a subway station, and abstracting a subway station scene into a complete graph according to the layout information; screening edges in the complete graph according to a preset screening condition, so as to delete edges that do not meet the condition; constructing a mathematical model according to the screened complete graph, and determining an optimization target of the model; and according to the optimization target, optimizing the model by using an ant colony algorithm, so as to obtain a final transfer route scheme. The ant colony algorithm is applied to the subway station crowd transfer route optimization scheme, a real subway station scene simulation model is established by coding entity facility nodes in the subway station scene, a corresponding crowd transfer route facility design is abstracted into a path planning optimization problem to be solved, and an effective crowd transfer route design scheme can be better provided. The application can be widely applied to urban subway traffic and intelligent computing fields.

This invention discloses an automated migration method and system for graph database metadata, belonging to the field of graph database data migration technology. The method includes: acquiring metadata from a source graph database, including structural definitions of vertex and edge types; performing full sampling analysis on vertex and edge data in the source graph database to construct a distribution mapping relationship from vertices to types and a connection mapping relationship from edges to vertex types; generating graph structure definition statements for the target graph database based on the metadata, distribution mapping relationship, and connection mapping relationship, combined with a preset migration strategy; and sending the graph structure definition statements to the target graph database for execution to complete graph structure modeling. This application can meet the migration needs between different versions of graph databases and ensure data consistency and integrity, thus having broad application prospects.

The application relates to a kind of distributed topology time-varying formation control method and system, and relates to the field of agent formation control, method includes: according to the communication relationship of each node in multi-agent formation, construct initial undirected complete graph;Each node is agent;Based on the initial undirected complete graph, according to distributed algorithm, generate global optimal rigid communication topology;Based on the global optimal rigid communication topology, according to the communication relationship of each node, the corresponding edge of each node is directed, and the in-degree of each node is less than or equal to 3, obtain optimal persistent communication topology;The optimal persistent communication topology is used to carry out communication control to multi-agent formation.The application reduces the complexity of multi-agent communication.

The disclosure provides a link prediction method, a training method and device of a link prediction model, relates to the field of artificial intelligence, specifically relates to the field of graph neural networks and deep learning technologies, and can be applied to scenarios such as smart cities and intelligent transportation. The specific implementation scheme of the link prediction method is as follows: determining implicit information for a historical moment according to first graph information of a complete graph for a target object at the historical moment; the implicit information represents time-dependent information of the complete graph for the target object; determining posterior distribution information of first embedding information of a plurality of first objects belonging to the target object at a current moment according to the implicit information and second graph information of a reference graph for the target object at the current moment; and determining first complete link information between the plurality of first objects according to the posterior distribution information and the second graph information.

The application discloses a method and system for quickly adapting different knowledge graphs. The method comprises the following steps: 1) using an intention recognition module to process a natural language query sentence input by a user to obtain a named entity and a part of speech, and simultaneously outputting a user intention and a slot of the current query sentence; 2) a graph query sentence configuration module configures a graph query sentence template of different answers according to the user intention; 3) for each graph query sentence template, a specified graph is determined according to the graph query sentence template; a knowledge graph entity analysis module filters out a query entity slot field in the graph query sentence template, replaces the query entity slot field with an input or selected query word, forms a complete graph query sentence, and queries a corresponding result object from the specified graph according to the graph query sentence. The application can intelligently connect different field knowledge graphs and quickly analyze data.

The invention discloses a knowledge graph-based cross-border e-commerce product semantic association method and system, and relates to the technical field of artificial intelligence. The method comprises the following steps: receiving an input instruction of a target user, and obtaining e-commerce product data from a target database according to the input instruction; the e-commerce product data comprises a sample number and an entity number, and the sample number and the entity number are respectively used as rows and columns to construct a target product matrix; determining the number of entities as the number of nodes, and constructing an initial undirected complete graph according to the number of nodes; performing search optimization on the initial undirected complete graph to obtain a causal graph; performing path optimization on the causal graph to obtain a target knowledge graph; after querying the target knowledge graph according to an input instruction of a target user, obtaining cross-border e-commerce product information of the target user; according to the method, the search time is shortened, the query efficiency of the system is improved, and the user is helped to efficiently obtain cross-border e-commerce product information.

This application discloses a complete graph counting method based on a hybrid storage architecture, relating to the field of data processing technology. The method includes: obtaining a set of objects, each object having a pointing relationship; obtaining a first set corresponding to a first object in the object set, the first set including all second objects pointed to by the first object; obtaining a second set corresponding to the second object, the second set including all objects pointed to by the second object; obtaining the intersection of the first set with each second set; generating a matrix corresponding to the first object based on all intersections; and obtaining the first number of subsets in the object set that satisfy a preset condition based on the matrices corresponding to each of the first objects. The preset condition is that the number of objects in the subset is a preset number, and any two objects in the subset have a pointing relationship, thus improving processing efficiency.

The application discloses a photolithography hotspot detection method based on edge level positioning. First, an integrated circuit layout is constructed as a graph structure, wherein each node corresponds to an edge of a polygon in the integrated circuit layout, and the edge corresponds to the connection relationship between the nodes; an edge type is introduced, the edge type includes an adjacent edge, a graphic edge and a space edge; edge features and node features are extracted, a complete graph structure is constructed, and the complete graph structure is input into a pre-trained machine learning model to output a hotspot prediction result of each node. The method discloses discarding the method of rasterizing the layout into an image or cutting into a rectangle, directly using the most basic geometric elements constituting the layout to construct the nodes of the graph, and further realizing high-precision positioning and non-Manhattan layout support, and providing the possibility of accurately mapping hotspots to specific problem edges.

The application provides a large-scale layout graph drawing method, an electronic device and a storage medium. The method comprises the following steps: taking an intersection area of an outer frame of a layout and a display window of a user view as a drawing area, and uniformly dividing the drawing area into a plurality of subblocks; for each subblock, extracting graph data of all layers of the layout falling within the range of the subblock, and defining a combination of each subblock and each layer as a drawing task unit; creating an independent thread working instance for each drawing task unit, and allocating an independent drawing context; submitting all thread working instances to a thread pool for scheduling and execution, so that each thread working instance completes graph drawing of the corresponding subblock and layer in the independent drawing context; and merging and displaying the drawing results of the thread working instances according to the subblock positions and layer sequences.

This invention relates to a knowledge graph completion method in the field of enterprise credit, belonging to the field of artificial intelligence technology. It includes the following steps: S1: data preprocessing and graph structure construction; S2: construction of an efficient multi-relation graph convolutional neural network; S3: dynamic boundary conditions and loss optimization; S4: multi-constraint optimization; S5: training and prediction. This invention significantly improves the completion accuracy of multi-relation knowledge graphs through innovative methods such as multi-relation modeling, dynamic similarity adjustment, and boundary adaptive optimization, resulting in a complete graph structure. It enables the model to maintain high prediction accuracy even with scarce data and low-frequency relationships. Through feature smoothing and cluster consistency regularization, it possesses temporal and dynamic semantic modeling capabilities. It also has the ability to model the "equity chain—supply chain—risk chain" characteristics of the enterprise credit field.

The application relates to a blockchain smart contract multi-vulnerability detection method and system based on an improved graph convolution network, which comprises the following steps: S1, constructing a smart contract vulnerability sample dataset; S2, modeling the source code semantics in the smart contract, generating nodes and edges, and forming complete graph structure features; S3, processing the graph structure features to obtain multi-dimensional feature vector outputs; S4, calculating the feature vectors of various vulnerability samples to obtain a multi-vulnerability graph convolution classification model with optimal parameters; and S5, inputting a smart contract to be detected into the multi-label classification model, and outputting the vulnerability detection result of the smart contract by the model. The application realizes accurate and efficient detection of multiple vulnerabilities of a smart contract, and enhances the security of the smart contract.

The invention discloses an optimal test strategy generation method for a complex communication system, and the method comprises the steps: firstly constructing a fault test model of a to-be-tested system, then generating an optimal complete graph in combination with the fault test model, and reducing the optimal complete graph into a binary tree which serves as an optimal test strategy, thereby solving a problem that a space structure is difficult to solve when the space structure is complex; in the process of generating the optimal complete graph, an intelligent search algorithm is selected, and a complete graph solution set is continuously iterated and updated according to an accelerated convergence rule to fit an optimal test strategy.

The application discloses the following technical solutions, first, the graph structure and abstract syntax tree structure are extracted from the source code; then the word vector sequence is obtained by encoding the abstract syntax tree information as the input of the bidirectional recurrent neural network to learn the semantic features of the source code, and the obtained semantic features and the traditional static features are combined to be used as the state vector representation of the graph node; then the teacher integrated network model is pre-trained by using the complete graph representation of the source code; finally, the knowledge is extracted from the teacher integrated network model pre-trained previously and injected into the student integrated network model by the knowledge distillation technology. With the advancement of the graph neural network and the idea of the knowledge distillation technology, compared with the prior art, the generated student integrated network model can realize a higher software defect detection rate, and the design of the integrated network guarantees the robustness and the robustness of the model.

The invention relates to the technical field of video abstraction labeling, and discloses an unsupervised video abstraction method based on structure entropy optimization. According to the method, shot segmentation is optimized so as to ensure semantic integrity, then shot is constructed into a complete graph, global association is described by means of semantic similarity, structural entropy is introduced innovatively, loss is constructed according to the structural entropy difference between an original video and an abstract graph, and the retention degree of global information is quantified. The method plays a guiding role in screening of key shots, and is provided with a dual-path reconstructor to restrain the reconstruction capability from the aspects of content and dependency relationship. The long-distance association can be captured without manual labeling, the retention of the abstract on the core semantics and the logic structure is enhanced, and the performance of the unsupervised video abstract is improved.

The invention discloses an automatic migration method and system for graph database metadata, and belongs to the technical field of graph database data migration. The method comprises the steps that metadata of a source graph database are obtained, and the metadata comprise structural definitions of vertex types and edge types; performing full-sampling analysis on vertex data and edge data in the source graph database, and constructing a distribution mapping relation from vertexes to types and a connection mapping relation from edges to vertex types; generating a graph structure definition statement of the target graph database based on the metadata, the distribution mapping relation and the connection mapping relation in combination with a preset migration strategy; and sending the graph structure definition statement to the target graph database for execution, and completing graph structure modeling. According to the method, the migration requirement between different versions of graph databases can be met, the consistency and integrity of the data are ensured, and the method has a wide application prospect.

The invention discloses a photoetching hot spot detection method based on edge level positioning, which comprises the following steps: firstly, an integrated circuit layout is constructed into a graph structure, each node corresponds to one edge of a polygon in the integrated circuit layout, and the edge corresponds to the connection relationship between the nodes; introducing an edge type, wherein the edge type comprises an adjacent edge, a graph edge and a space edge; and extracting edge features and node features, constructing a complete graph structure, inputting the graph structure into a pre-trained machine learning model, and outputting a hotspot prediction result of each node. According to the method, a method for rasterizing the layout into images or segmenting the layout into rectangles is abandoned, nodes of the layout are constructed by directly using the most basic geometric elements forming the layout, high-precision positioning and non-Manhattan layout support are further realized, and possibility is provided for accurately mapping hot spots to specific problem edges.