57 results about "Community finding" patented technology

Disclosed are a secure interaction method and device for reversely screening for a derived feature. The method comprises: by means of community discovery, determining a community to which each data transmission apparatus belongs; reversely screening for a target community on the basis of data security indexes of communities; determining a derived feature of a target data transmission apparatus on the basis of an association relationship between the target data transmission apparatus and the target community; and identifying a data transmission security level of the target data transmission apparatus on the basis of the derived feature, and transmitting data on the basis of the data transmission security level. According to the present invention, the target community is reversely screened for in combination with the community discovery and the data security indexes of the communities, the derived feature of the target data transmission apparatus is determined on the basis of the association relationship between the target data transmission apparatus and the target community, and the data transmission security level of the apparatus is identified by means of the derived feature from the perspective of the association with the community, so that the identification accuracy of malicious attacks on the data by the plurality of apparatuses working together is improved, and the security of data exchange is guaranteed.

The invention discloses a modular layout method based on community discovery and collaborative optimization, and the method comprises the steps: carrying out the initialization modeling of a special-shaped printed circuit board, and defining a layout constraint condition; based on the connection characteristics of the circuit, dividing devices on the special-shaped printed circuit board into a plurality of functional modules by adopting a community discovery method; performing global layout on the module by adopting a global optimization method according to the layout constraint condition, and generating an initial layout scheme; according to the initial layout scheme, a directional random disturbance strategy is adopted to adjust the module position, and the direction with the lowest layout density is dynamically selected for module movement to generate a global layout design result; and performing legalization processing on a global layout design result, and adjusting positions of illegal devices one by one. The method provided by the invention can improve the automatic layout effect and efficiency of the special-shaped PCB containing the layout forbidding area.

The invention discloses a data annotation method and device based on a graph structure and community discovery and a storage medium, and belongs to the field of data processing. Customer transactions, commodity attributes, behavior tracks and environment data are obtained, and a heterogeneous graph network including a basic physical layer (transaction association and commodity attribute mapping), a behavior semantic layer (behavior pattern and semantic association) and an environment association layer (environment dynamic influence) is constructed. A community discovery algorithm is adopted to mine customer groups with cross-department business values, and a three-level label system for quantifying basic value attributes and fluctuation coefficients, behavior patterns and commodity preferences and dynamic track characteristics is constructed. Therefore, unified understanding of customer behaviors, deep mining of multi-dimensional customer relationships, dynamic evolution capture of customer values and hierarchical customer cognition construction are realized, and the problems that data islands are caused by task guidance, dynamic value mining is restricted by single data dimensions, and hierarchical cognition construction is restricted by flattening of a label system in a traditional method are solved.

The embodiment of the invention provides a community discovery method and device for banking business, equipment, a medium and a program product, and relates to the field of big data. The method comprises the following steps: acquiring user and banking service opening information, and constructing a network model; according to the network model, calculating the local density and the segmentation distance of each node; determining a clustering center node according to the local density and the segmentation distance of each node; distributing each non-clustering center node to a community where a node which is closest to the non-clustering center node and of which the local density is higher than that of the non-clustering center node is located for the first time; for each non-enveloping node, calculating the membership degree of the non-enveloping node to a community to which the adjacent node belongs; and if the degree of membership of the non-enveloping node to the community to which any adjacent node belongs is greater than the degree of membership of the non-enveloping node in the initially allocated community, adding the node to the community to which the adjacent node belongs. According to the method, the accuracy of bank user community division is improved.

The invention relates to a community division method based on structure enhancement and a graph convolutional network, and belongs to the field of multi-view clustering. The objective of the invention is to solve the problems of structural information redundancy and insufficient representation information fusion in a deep clustering algorithm. According to the method, firstly, a redundant edge matrix is learned by utilizing an adversarial learning mechanism through a structure enhancement module, the structure information of a graph is enhanced, and redundant connection is removed; and then, extracting attribute information of the graph by using an automatic encoder, and fusing the attribute information and the enhanced structure information by using a graph convolutional neural network to obtain a better embedded representation. According to the method, a double-self-supervision mechanism is designed, data representation is optimized by learning high-confidence assignment, and the clustering effect and the representation capability of the module are improved. And finally, directly obtaining expressed clustering distribution through a one-step clustering module, and avoiding sub-optimal clustering performance. According to the method, the accuracy and robustness of community discovery can be effectively improved, and more accurate representation and better support are provided for downstream tasks.

The invention discloses a text deep clustering-based community discovery method, which comprises the following steps of: 1, training a text by utilizing a training model to generate a word vector, and converting the preprocessed text into a word matrix; 2, extracting global context information of the text and local information between continuous words, splicing to obtain text feature vectors, calculating cosine similarity of the text feature vectors, and constructing a text network; step 3, performing community discovery based on clustering to obtain an initial community center node and a community discovery result; and step 4, constructing a deep self-supervised clustering loss function, updating the text network and the community center by minimizing the loss function, and obtaining an updated text feature vector and a community discovery result. The problems that an existing community discovery method singly considers global and local features of a text and model parameters cannot be optimized according to a community division result in the community discovery process can be solved.

This invention relates to a community detection method based on graph compression, comprising the following steps: acquiring initial graph information, sorting the importance of graph nodes, and selecting nodes to be compressed; compressing the nodes to be compressed to obtain a compressed graph, reconstructing the adjacency matrix using the compressed graph, and performing community detection on the compressed graph based on a graph convolutional network; expanding the communities detected in the compressed graph, restoring the community detection state of the initial graph, and obtaining the community detection result. Compared with existing technologies, this invention has advantages such as being able to compress the graph to a smaller size and achieving higher accuracy.

The application discloses a botnet domain name determination method and device and electronic equipment. It relates to the technical field of data processing, the field of network security and other related technical fields. The method comprises the following steps: constructing a target network relationship graph according to target DNS data; performing community division on the target network relationship graph according to a community discovery algorithm to obtain multiple community structure information; and determining a target botnet domain name from the target DNS data according to the multiple community structure information. Through the application, the problem that the determination accuracy of the botnet domain name is relatively low in the related art, which is caused by calculating the similarity between the target domain name and the historical botnet domain name to determine whether the target domain name is a botnet domain name, is solved.

The invention relates to a complex network node influence sorting method and system based on structure entropy, and belongs to the technical field of social network analysis. The method comprises the following steps: constructing a social network graph according to a data set, and carrying out community discovery by utilizing two-dimensional structure entropy to obtain stable overlapping communities; calculating the influence of the nodes in the community and the influence of the nodes across the community, and performing linear combination on the influence of the nodes in the community and the influence of the nodes across the community to obtain a comprehensive influence value of each node; and sorting all the nodes according to the comprehensive influence value, and identifying the key node with the maximum influence in the social network. According to the method, the importance of the nodes in the social network is evaluated by measuring the two-dimensional structure entropy change of the nodes in the communities and among the communities, so that the key nodes are identified and sorted, and the method for effectively identifying and sorting the key nodes is provided for obtaining the important nodes in the social network.

This invention discloses a method for community detection in social networks with unknown community cardinality. The method first constructs an encoder, trains it using an arbitrary unsupervised method, maps the input social network to Euclidean space, and obtains the representation vectors of the vertices. It then calculates the similarity matrix of vertex pairs, sorts the similarities, selects vertex pairs with high similarity as positive samples, and selects vertex pairs with low similarity as negative samples, assigning pseudo-labels to each to form the training set. Next, it constructs a community relationship prediction model, trains it using a binary cross-entropy loss function, predicts the community relationships of vertex pairs, and optimizes hyperparameters. Finally, it constructs a structure graph based on the model's prediction results, inputs the structure graph into the Liu-Wen algorithm to obtain the final community detection result. Experiments show that, without providing community cardinality, this method can accurately detect the community structure in social networks.

The application discloses a numa-aware community discovery method based on k-truss decomposition, comprising a data input module, a calculation support module and a K-truss decomposition module, and the method comprises the following steps: reading a graph in the form of text from a graph data file stored in a hard disk through the data input module, placing the graph topology structure into a memory, then building a CSR and generating an edge mapping array according to a CSR edge set array; selecting a triangle counting method by using the calculation system module, selecting a triangle counting method according to the size of the graph (the number of edges obtained by each thread), the density of the graph (the average vertex degree) and the balance degree of the vertex degree of the graph (the gap between the maximum degree, the minimum degree and the average degree); the support degree of each edge is calculated according to the method in the above step; the K-truss decomposition module is used for decomposition, including calculating the size of each execution unit, calculating the task interval of each unit, initializing the support degree of each unit, performing K-truss decomposition on a single unit and updating the global k value list.

The invention discloses a community discovery method of a graph neural network based on multi-view information fusion, and belongs to the technical field of data mining. The method comprises the following steps: preprocessing data, performing PCA dimension reduction on an attribute matrix, and normalizing an adjacent matrix; inputting the correlation matrix combination into an automatic encoder and a graph attention automatic encoder to obtain a new matrix representation and fusing the new matrix representation into a final node representation matrix; then back-propagating the optimization model by using various loss functions; and finally, community division is realized by using a k-means clustering algorithm. According to the method, the structure and attribute information of the original data are fully utilized, multi-view information is effectively fused, the accuracy of community discovery is improved, and the method has great significance in the fields of research on citation networks, recommendation systems and the like.

The application discloses a multi-view social network community discovery method, system and device, relates to the field of social network data analysis, and comprises the following steps: acquiring multi-view network data; filtering and processing the multi-view network data by using a low-pass filter to obtain a smooth representation of each view; fusing the smooth representation of each view by using an attention mechanism fusion mechanism to obtain a fused representation; fusing a Laplace matrix corresponding to each view by using a learning weight to obtain a fused Laplace matrix; determining an embedding representation by using an MLP network based on the attention mechanism fusion mechanism which has been trained according to the fused representation and the fused Laplace matrix; and clustering the embedding representation to obtain a final clustering result, thereby realizing community discovery in a social network. The application can realize stable and accurate social network user community identification.

This invention discloses a microblog group identification method based on community discovery, comprising the following steps: S1, data collection and cleaning; S2, feature extraction and representation; S3, establishing a classification model; S4, community tagging and influence analysis. In this invention, an optimized Dynamic Topic Model (DTM) is used to mine specific groups within the microblog community. Microblog posts from the past year are selected as the research object, and the similarity of topics in posts from different authors is used as the weight of links between authors, mapping the microblog network into a directed weighted network. Community discovery is performed using the Label Propagation Algorithm (LPA), identifying the inherent community structure within the social relationship network. This invention conducts in-depth analysis of user relationships within the microblog network, and based on identification methods for user-generated content characteristics, user association characteristics, and environmental characteristics, it mines potential topics to identify users with similar interests and active user groups in specific fields.

This invention discloses a method for optimizing the allocation of epidemic prevention and control resources based on complex networks. The method includes: acquiring big data from online social platforms to measure participants' attitudes and opinions on epidemics and corresponding prevention and control measures; designing and executing specific decision-making experiments to measure participants' feedback to different types of incentives and information; analyzing experimental results and data to extract individual behavioral rules in different research scenarios and constructing a new generation of agent-based epidemic transmission models; conducting multi-layer community analysis based on deep learning to achieve accurate community discovery within a multi-layer framework; combining community discovery with impact maximization research to identify key user sets in the multi-layer system, allocate prevention and control resources, explore the evolutionary patterns of epidemics, and achieve optimized control of the epidemic transmission process under multi-dimensional uncertainties in parameters and models. This invention contributes to the rational allocation of epidemic prevention and control resources, providing effective protection for the lives and health of the people.

This invention relates to the field of computer network security technology, specifically to a CWE (Cost Evidence-Based Weapon) segmentation method, device, and storage medium based on a community discovery algorithm, aiming to improve the benefits of vulnerability classification for vulnerability intelligence analysis. The proposed CWE segmentation method based on a community discovery algorithm includes: constructing a knowledge graph based on the relationships between different CWEs; assigning each CWE in the knowledge graph to a separate community; and using a modularity-based community discovery algorithm to progressively merge communities until the modularity no longer increases, resulting in the final segmented CWE communities. Furthermore, this invention proposes, from an attack benefit perspective, constructing a joint CAPEC and CWE knowledge graph, and using a community discovery algorithm to segment CWEs into communities, significantly improving the benefits of vulnerability classification for vulnerability intelligence analysis.

The present invention provides a method and system for discovering software ecological communities based on semantic embedding, including: step 1: selecting heterogeneous nodes, designing meta-paths, and constructing a software ecological heterogeneous information network; step 2: according to the meta-paths and the constructed heterogeneous information network, using the Skip-Gram model to obtain the probability of occurrence of nodes, and setting the nodes with large probability of occurrence (the top 20%) as seed nodes; step 3: with the seed nodes as the center, looking for similar nodes, and finally discovering heterogeneous communities. The present invention uses meta-paths to obtain the hidden semantic information between heterogeneous nodes, and constructs a heterogeneous information network based on this, and finally identifies heterogeneous communities around seed nodes, which is more in line with the heterogeneity of community members in real life, and has practical significance for studying the development of software communities.

The invention discloses a community evolution method based on a deep tense neural network. The method comprises the following steps: 1) inputting a graph structure set of tense graph data at multiple moments; and step 2) obtaining respective node representation of the tense diagram data at different moments through a GAT neural network. Then time coding information of a plurality of moments is obtained through time coding, and splicing operation is conducted on the time coding information and node representations of different moments; step 3) predicting node features of the tense graph at the next moment by using a graph attention mechanism, and performing dimension reduction operation on the obtained node features through MLP to obtain a node feature matrix of the tense graph at the next moment; 4) clustering the nodes by using a DBSCAN algorithm in a clustering algorithm according to the node features by a community discovery module in the deep tense neural network, and dividing an obtained clustering result into final communities; according to the method, the representation capability of the node vector to the tense graph is improved by fusing the multi-angle features, so that the accuracy of the tense community structure is improved.

The invention discloses a community discovery method combining local expansion and importance sequence updating rules, and aims to solve the problems of oscillation, randomness and local optimum of a traditional label propagation algorithm in a complex network. The network is subjected to preliminary community division in combination with the influence of the nodes and the weight information of the edges, and the influence of the nodes is calculated through the characteristics of degree centrality, betweenness centrality, graph embedding and the like. And node labels are updated by using asynchronous label propagation, so that the oscillation phenomenon in the traditional LPA is avoided. The obtained community is optimized through spectral clustering, the community structure is further refined from a global perspective by using a Laplacian matrix and a feature vector, and the accuracy and stability of community division are improved. According to the method, the community division precision in a large-scale and dynamic network can be effectively improved, and noise interference and random influence of a traditional algorithm are overcome. A more accurate, stable and explainable solution is provided for a community discovery task, and deep development of complex network analysis is promoted.

The invention provides a two-stage extension community discovery method based on a local triangle, relates to the technical field of community discovery, and designs node governing power, and comprehensively considers the degree and cosine similarity of node neighborhoods on the basis of node degrees, which requires that seed nodes not only have large degrees, but also have compact structures in the neighborhoods, so that the degree and cosine similarity of node neighborhoods are considered. The node with the maximum node control force is selected as a seed every time, so that seed nodes can be screened out more accurately. For the seed nodes with weak aggregation capability, a targeted community expansion strategy is adopted, and meanwhile, large-scale community expansion is performed on the basis of the undirected network, so that the influence of the seed nodes is expanded, and the accuracy of community expansion is improved. A new matching degree function is provided, the number of triangular structures formed by the nodes and the interiors and exteriors of the community is added on the basis of considering the nodes and the interiors and exteriors of the community, and whether each node can be added into the community only needs to be calculated once, so that the community discovery efficiency is improved.

The application relates to the technical field of big data, and particularly discloses a user behavior identification method and device, equipment, a storage medium and a program product. The method comprises the following steps: acquiring a community network to be processed, the community network comprising a plurality of nodes and a plurality of edges, each node being used for representing user data of a user to be identified, and each edge being used for representing association weight information between two nodes; using a community discovery algorithm to perform a graph reconstruction cycle on the community network in a plurality of processes until the modularity gain between the plurality of nodes in the community network is all lower than a gain threshold; wherein the community discovery algorithm is used for performing community merging on the plurality of nodes in the community network according to the plurality of edges in the community network, and performing sub-community splitting according to the connected state between the nodes in the merged community; and the user behavior of the user to be identified is inferred according to the optimized community network. The method can improve the identification accuracy of the user behavior.

The present application relates to the technical field of intelligent household appliances, in particular to a room intelligent cleaning method and device based on local community discovery; the present application takes a movable cleaning robot with a camera and a mechanical arm as a room cleaning device, scans a target room to obtain a current image, compares the current image with an initial image of the target room, and distinguishes a plurality of to-be-processed objects; then the to-be-processed objects are converted and classified into a plurality of to-be-stored nodes and to-be-reset nodes; then the to-be-stored nodes are processed by using local community discovery, a local community is constructed, and the local community with the largest priority is stored, and the process is restarted until all the to-be-stored objects are stored; then the optimal degree of the to-be-reset nodes is calculated, and the to-be-reset node with the smallest optimal degree is reset, and the process is restarted until all the to-be-reset objects are reset. The present application realizes the good application of local community discovery in room cleaning work, and effectively improves the efficiency and intelligent level of room cleaning.

The embodiment of the present application provides a community discovery method, device, equipment and computer storage medium, and belongs to the field of network analysis. The embodiment of the present application obtains user nodes and edges in a community, the edges include behavior relationships between the user nodes, the edges include edge labels, calculates the influence of the edges by the ratio of the degree of the edges and the degree of the connecting edges of the user nodes connected with the edges, the degree of the edges includes the degree of the user nodes connected with the edges, and updates the edge label of the edges to the edge label with the highest appearance frequency in the edge labels of the connecting edges of the user nodes connected with the edges according to the order of the influence of the edges from large to small. The edge label of each edge is used as the label of the user nodes connected with the edge, and the user nodes with the same label are determined to be in the same community. The embodiment of the present application can avoid randomness in the label propagation process, and further avoid that the user nodes are divided into inappropriate communities, thereby improving the accuracy of community division.

The present application discloses a data annotation method, device and storage medium based on graph structure and community discovery, which belongs to the field of data processing. The present application obtains customer transactions, product attributes, behavior trajectories and environmental data, and constructs a heterogeneous graph network including a basic physical layer (transaction association and product attribute mapping), a behavioral semantic layer (behavioral pattern and semantic association), and an environmental association layer (dynamic impact of the environment). A community discovery algorithm is used to mine customer groups with cross-departmental business value, and a three-level labeling system is constructed to quantify basic value attributes and fluctuation coefficients, behavioral patterns and product preferences, and dynamic trajectory characteristics. This achieves a unified understanding of customer behavior, in-depth mining of multi-dimensional customer relationships, dynamic evolution capture of customer value, and hierarchical customer cognition construction, solving the problems of data silos caused by task orientation in traditional methods, the constraints of dynamic value mining caused by a single data dimension, and the restrictions of hierarchical cognition construction caused by the flattening of the labeling system.

The embodiment of the invention provides a synonym set construction method and device. The method comprises the steps of performing named entity extraction on a target text library, and obtaining an entity word set according to an extraction result; for a target entity word in the entity word set, determining other entity words forming synonym pairs with the target entity word and relevancy scores of the synonym pairs; taking each entity word in the entity word set as a node, establishing a connection edge between two entity words forming a synonym pair, and taking the relevancy score as an edge weight of the connection edge to obtain a relation network graph; based on the edge weight, executing a modularity-based community discovery algorithm for each node in the relation network diagram to obtain a plurality of initial communities; for each initial community, deleting semantic outlier entity words in the initial community by using a large language model to obtain an updated community; and by taking each updated community as a node, executing the community discovery algorithm based on modularity again to obtain a merged community as a synonym set.

This invention discloses a community detection method, system, device, and medium based on a graph dual autoencoder, relating to the field of community detection technology. The method includes inputting a given citation network into a graph dual autoencoder to obtain graph structure representation information and graph attribute representation information; fusing the graph structure representation information and graph attribute representation information to obtain fused graph representation information; and using a clustering method to divide the fused graph representation information into communities to obtain the community detection result. This invention improves the accuracy of community division in citation networks.

The application discloses a kind of based on community discovery and dynamic window strategy's retired battery hierarchical reorganization method, system, equipment and storage medium, belongs to battery echelon utilization technical field.The method is first based on relaxation time distribution Construction battery dynamics fingerprint, utilize jensen-shannon divergence Construction electrochemical similarity network, through community discovery algorithm realizes the precise decoupling of aging mode;Then utilize multilayer perception machine prediction residual capacity, and adopt dynamic greedy sliding window algorithm to carry out module reconstruction, this algorithm is through descending order priority matching and window self-adapting reduction mechanism, while guaranteeing module consistency, significantly improve group rate.The application effectively solves the mechanism mismatch and group rate low double problems brought by the heterogeneity of retired battery, and the system includes test module, graph calculation module, capacity prediction module and grouping decision module.The application also relates to electronic equipment and storage medium for implementing the method.

The invention relates to the technical field of heterogeneous networks, in particular to a financial heterogeneous network community discovery method of combined comparative learning and generative learning based on a matching rate, and the method comprises the steps: obtaining a target financial heterogeneous network; the target financial heterogeneous network is input into a preset community discovery model, a community discovery result of the target financial heterogeneous network is output, the community discovery model is used for constructing the target financial heterogeneous network into a high-order fusion graph and obtaining node representation of the high-order fusion graph by constructing the target financial heterogeneous network into a semantic tree, and the node representation of the high-order fusion graph is used for obtaining the community discovery result of the target financial heterogeneous network. And carrying out comparison learning and generation learning to obtain a community discovery result of the target financial heterogeneous network. Compared with the prior art, the community discovery method and model provided by the invention are more effective and reasonable.

The invention relates to a multi-level living-recreation space structure identification method based on an overlapping community discovery algorithm. The method comprises the following steps: S1, constructing a living-recreation network based on mobile phone signaling data; s2, converting the living-recreation network into a weighted edge network; s3, based on the weighted edge network, identifying an edge community structure in the weighted edge network; s4, mapping the side community structure back to the living-recreation network, and obtaining a node community structure corresponding to each original node; s5, constructing a hypergraph based on the node community structure, and identifying and obtaining an Nth-layer community structure by using a louvain community discovery algorithm based on the hypergraph; and S6, eliminating communities of which the community scale is smaller than a preset value in the Nth layer of community structure, and iteratively executing the step S5 for the reserved communities until an iteration ending condition is met, so as to obtain the multi-layer living-recreation space structure of the city. Compared with the prior art, the invention provides the method for automatically identifying the urban multi-level living-recreation space structure based on the resident activity rule.

The application relates to the technical field of data intelligent classification, in particular to a local community discovery method and device based on node-enhanced hypergraph, wherein the method comprises the following steps: inputting initial seed nodes in a hypergraph data set according to an application scene; obtaining an extended seed set based on the initial seed nodes; extracting a quality-enhanced seed node set from the extended seed set, and taking the quality-enhanced seed node set as an initial point to calculate local node diffusion, so as to output a local community discovery subgraph. Therefore, the problems that the community discovery work in the related art can only be applied to small-scale hypergraphs, the applicability of the local community discovery work is reduced, the influence of the quality of the seed nodes on the performance is great, the precision of the local community discovery work is reduced, and the demand of the local community discovery work cannot be met and the like are solved.