18 results about "Community search" patented technology

According to the privacy enhancement type (k, d)-truss community search method for the social network, a novel KTG tree structure is constructed by fusing k-truss and G-tree indexes. According to the index structure, hierarchical community decomposition of a social graph and social distance information are fused, a refined boundary vector coding scheme is designed to support efficient distance calculation, and a double-cloud-server non-collusion architecture integrating improved homomorphic encryption and matrix encryption technologies is constructed. Through a two-stage security query process of first structure filtering and then distance verification, on the premise of protecting full-process privacy of a graph structure, a query intention, a distance matrix and an intermediate calculation result, efficient and accurate search of a close community in a large-scale social network is realized. The method is suitable for various scenes such as social recommendation, risk control, public opinion analysis and anti-fraud, and the problems of privacy disclosure and calculation efficiency in social network analysis are effectively solved.

This invention provides a privacy-preserving community search method and system for graph data streams. It utilizes a secret shared domain comprised of multiple servers. Within this domain, each server can only access the first encrypted data of the graph data stream's list structure and the second encrypted data of the search parameters. Throughout the community search process, the search parameters and all information in the graph data stream except for the time of generation are processed within the encrypted domain and are not leaked to the querying server, thus achieving privacy protection during the community search process for graph data streams.

This invention provides a method, system, program, and storage medium for community search with enhanced embedding preferences. The system includes a social network node embedding device, a community search device, a random walk sequence acquisition device, and a system control device. The method dynamically combines embedding learning and community search, utilizing a Check2Vec model to learn node embeddings, improving the modeling ability of check-in information. In community search, it comprehensively considers node attributes and check-in information to obtain more accurate user-location binary communities. The advantages of this invention include multimodal information integration, applicability to multiple data domains, and flexible adjustability, providing a powerful means to improve the effectiveness and personalization of community search.

The application relates to a community search method and device on an attribute graph with a limited scale and a readable storage medium, relates to the technical field of community search, and comprises the following steps: obtaining preset subgraph constraint information, wherein the subgraph constraint information comprises a query node, an attribute set and a scale limitation range; performing heuristic community search on a preset attribute graph based on the subgraph constraint information and a preset first pruning rule to obtain a target subgraph with the highest graph attribute score, wherein the first pruning rule comprises discarding a candidate node which cannot form a triangle with any two nodes in a current optimal solution set obtained through search, and the candidate node is a neighbor node of the query node; and taking the target subgraph as an optimal community. Through the application, the accuracy and efficiency of the community search on the attribute graph with the limited scale can be effectively improved.

The invention discloses a community search query system and method based on a knowledge graph, and the method comprises the steps: receiving a natural language question inputted by a user, and recognizing the natural language question inputted by the user according to a preset element category in a network search engine knowledge graph to obtain a natural language question element, matching the natural language question element with a semantic template in a preset template library in a network search engine knowledge graph to obtain a natural language question element matching template; performing community search on the natural language question element matching template through a community search threshold constraint method or a maximum community measurement constraint method to obtain an optimal community subgraph of natural language question elements; generating a query statement according to the natural language question element matching template, and searching in the optimal community subgraph of the natural language question element according to the query statement to obtain an answer corresponding to the natural language question input by the user.

This invention belongs to the field of computer science, specifically relating to a community search method for product recommendation in an e-commerce network. The method includes: converting the e-commerce network into an undirected attribute graph G; initializing parameters and calculating the attribute-enhancing conductance of each node in the undirected attribute graph based on the initialization parameters; extracting candidate coarse communities based on the attribute-enhancing conductance; selecting coarse communities from the candidate coarse communities; processing the coarse communities using a trained neural community optimization model to obtain an encoding state; optimizing the coarse communities based on the encoding state to obtain refined communities; and recommending products based on online community search results. This invention combines deep learning technology with traditional predefined structural constraints. This method organically combines the advantages of both, thereby significantly improving the quality of community search.

The application belongs to the technical field of social search and particularly relates to a community search method based on sub-graph electric conductance; the method comprises the following steps: obtaining a social network graph, sampling a social sub-graph from the social network graph by using breadth-first search; selecting multiple maximum groups containing query vertices as initial communities in the social sub-graph; adding user nodes capable of reducing electric conductance of the initial communities in each initial community to obtain multiple complete communities; performing boundary pruning on the complete communities to obtain multiple high-quality communities; and selecting a high-quality community with the best performance from the multiple high-quality communities as a final community search result; the application saves the calculation cost, improves the accuracy of community search, and can realize effective and high-speed friend recommendation.

The invention discloses a distributed graph community search method based on odd-even overstep synchronous control, and belongs to the field of distributed computing, and the search method comprises the following specific steps: I, taking a corresponding query vertex as a starting point, carrying out initialization, and sending connectivity messages to all neighbor vertexes after the initialization is completed; iI, on the basis of the corresponding connectivity message, each neighbor vertex updates the own state, checks the corresponding degree after updating is completed, and updates the state of the corresponding vertex according to the check result; according to the method, invalid activation can be remarkably reduced, local optimal and invalid expansion is avoided, the number of messages is greatly reduced, and communication and calculation burdens are reduced; meanwhile, the search range can be narrowed, repeated calculation in an invalid area is avoided, the calculation efficiency and the resource utilization rate are improved, and the method is adaptive to a super-large-scale distributed environment.

The application relates to a comment display method and device based on Internet community comment likes, which comprises the following steps: when receiving a like operation of a user on any comment in an Internet community, searching for and identifying a keyword in the comment; when the keyword is identified in the comment, determining whether the keyword is in a search flow keyword blacklist; when the keyword is not in the search flow keyword blacklist, determining whether the number of posts in an Internet community search result corresponding to the keyword is greater than or equal to a preset threshold; when the number of posts is greater than or equal to the preset threshold, obtaining an Internet community search result page URL corresponding to the keyword, and associating the Internet community search result page URL with the keyword; and highlighting the keyword in the comment. Through the technical scheme, small and special interest topics in a community can find users who are really interested in the topics, and the content transmission efficiency of the community platform is improved.

The invention relates to the technical field of data mining and graph theory, in particular to a large-scale symbol graph personalized influence community search method based on lightweight index and multi-level pruning. The method aims to solve the problems of inaccurate positive and negative influence modeling, insufficient individuation ability, low search efficiency and lack of external influence evaluation in the prior art. The method comprises the following core steps: 1) constructing a node aggregation influence probability model, and defining the positive aggregation influence probability of the whole community by calculating the path propagation probability between nodes to evaluate the external influence; 2) performing multi-level pruning to generate a candidate node set; 3) dividing a core area and an edge area to construct a lightweight index; and 4) quickly positioning candidate communities containing the node by using the index, and returning r communities with the most influence according to the positive aggregation influence probability ranking. According to the method, the precision and efficiency of personalized community search in the large-scale symbol graph are improved, and the method is suitable for real-time analysis of million-level nodes.

A cross-dataset universal community search method, belonging to the field of graph data mining and information retrieval technology, comprises the following steps: Step 1: Constructing the required sample set and training graph; Step 2: Using spectral awareness for feature alignment to form spectral awareness aligned training features; Step 3: Constructing hybrid token sequences for nodes in the training graph; Step 4: Encoding the token sequences using a Transformer encoder to obtain a unified community-aware representation; Step 5: Reconstructing the representation using a diffusion model; Step 6: Training the model; Step 7: Inputting the target dataset into the model obtained in Step 6 for community search to obtain the results. This invention, through the above method, allows the target dataset to be directly input into the model for inference and community search during the application stage, without the need for retraining or fine-tuning, thereby improving the efficiency and search quality of cross-dataset deployment.

The invention provides an unsupervised heterogeneous community search method, program and system based on behavior modeling and a storage medium. The system comprises a data acquisition device, a model training device and a community searching device. According to the method CLHComS, a framework of type perception feature mapping and double-view contrast learning is adopted, firstly, node local relation features are captured through a relation perception GNN module, then high-order semantic association is mined through a metapath Transform module, unsupervised training is completed in combination with a loss function in a view and a loss function between views, and node embedding capable of describing heterogeneous network symbol features is generated. According to the CLHComS method, community retrieval can be efficiently completed on the heterogeneous symbol network, and target communities which contain query nodes and are dense in forward interaction are automatically mined through an iteration expansion criterion of single-type expectation scoring gains. The method can be deployed at the rear end of each server room, and can be widely applied to the application fields of community search and the like under heterogeneous graph scenes such as social networks and the like.

The invention provides a community search method and system oriented to new hardware. The method comprises the following steps: acquiring an original image to be subjected to community search and converting the original image into a tensor form; constructing an index based on-truss hierarchical decomposition for the original image in the tensor form through a tensor operator; and performing community search on the index based on the-truss hierarchical decomposition by a community search algorithm based on tensor calculation to obtain a community search result of the original image. According to the method, the original image is converted into the tensor format, and the efficient index based on-truss hierarchical decomposition is constructed, so that efficient community search based on new hardware is realized.

The present application relates to a kind of community detection encryption method of blockchain empowerment, belong to privacy protection and identity information management technical field.This method is while the behavior of data owner in community detection is constrained, protect the security of user digital identity information, establish new decentralized trust mechanism.First, realize distributed identity authentication using blockchain technology, realize dynamic authorization with the aid of smart contract.In terms of data, introduce vector commitment technology to constrain the data uploaded by data owner, and at the same time, the committed data is placed on the blockchain to realize verifiability and traceability.Through the construction of reliable trust foundation, the security and reliability of identity management system are ensured.In addition, by combining community search algorithm, according to the status and role of user in community, differentiated identity permission management is realized, which greatly improves the accuracy and efficiency of management.

The application provides a community search method, device, medium and equipment, the method comprises the following steps: according to complex network data set, the multiple graph model of dynamic attribute network is constructed, input specified parameter l, k and θ, wherein l represents sequence length threshold value, k represents support threshold value, and θ represents search score threshold value;The range of the edge time stamp in the network is determined to determine the time span, and the multiple graph model is divided into different time snapshots;In each time snapshot, the number of triangles formed by each edge in the current time snapshot is calculated as the support of the edge, and each dynamic edge is traversed, and the dynamic edge whose support is less than k or does not meet the existence in the continuous time snapshot of length l is deleted in a loop;Based on the search score threshold value θ, the remaining nodes of all time snapshots are integrated, and the (l, k, θ)‑truss structure model is obtained, and the induced subgraph of the (l, k, θ)‑truss structure model in the original multiple graph model G is taken as the result community.

The invention relates to an extensible and unsupervised heterogeneous information network community search method, which comprises the following steps of: 1, setting a target node type as a meta path, and constructing a homograph; 2, constructing new semantic features for nodes in the same composition under each meta path; 3, generating a community feature Token used for representing different views; 4, realizing feature fusion and representation learning irrelevant to a graph structure; 5, unsupervised comparative learning and node classification training tasks are carried out at the same time under the condition of no community label supervision, and the model is guided to obtain community embedding representation; step 6, performing community representation generation on target type nodes in the data graph, and predicting node classification results of the nodes; and step 7, for a query node, calculating community scores of the node and other nodes according to the community representation, and generating a community query result in combination with node classification consistency and structure connectivity constraint conditions. By means of the method, the efficient and accurate community searching method is provided.

The application provides a community searching method and device based on maximum clique search on uncertain graph, and relates to the field of data processing.The method comprises the following steps: obtaining an initial graph corresponding to a social network to be processed; determining reference values of each vertex in the initial graph; deleting vertices with reference values not greater than heuristic solution values in the initial graph to obtain a vertex set corresponding to the heuristic solution values, and determining an intermediate subgraph based on the vertex set; performing multiple search operations on each vertex in the intermediate subgraph, determining a target subgraph with the largest number of vertices based on candidate subgraphs obtained through the search operations, and ensuring that there is an edge between any two different vertices in the target subgraph and the product of the existence probabilities of all edges is greater than a preset probability value; and determining a target social user community in the social network to be processed based on the target subgraph.The application can search for a social user community based on uncertain correlation data between social users.