Supercharge Your Innovation With Domain-Expert AI Agents!

Method, system and storage medium for discovering overlapping communities in linear flow based on edge graph

A technology of overlapping communities and discovery methods, applied in data processing applications, instruments, geometric CAD, etc., can solve problems such as low time efficiency and resolution limitations, and achieve the effect of improving community quality and community division.

Active Publication Date: 2021-11-30
CENT SOUTH UNIV
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In the algorithms introduced above, the time efficiency of these algorithms is generally low due to the need for continuous iteration or conversion of the network. (3) Resolution limitation
Due to the complexity of the network structure, such as the 6 real-world networks shown in Table 1 and the 6 LFR artificial networks shown in Table 2, these algorithms are generally only applicable to some networks, and there is a problem of resolution limitation.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Method, system and storage medium for discovering overlapping communities in linear flow based on edge graph
  • Method, system and storage medium for discovering overlapping communities in linear flow based on edge graph
  • Method, system and storage medium for discovering overlapping communities in linear flow based on edge graph

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0037] This embodiment discloses a method for discovering overlapping communities of linear streams based on an edge graph.

[0038] In this embodiment, according to the definition of the community, there are more connections inside the community than outside the community, then when an edge is randomly selected in the network, this edge is more likely to appear inside the community. Given a network G=(V, E), where V represents a set of nodes, E represents a set of edges, and an edge e connecting two nodes u and v is expressed as e=(u, v). Given A, B are two subsets of V, thus giving the following definitions:

[0039] e(A)={(u,v)∈E:u∈A or v∈A} (1)

[0040] e(A,B)={(u,v)∈E:u∈A and v∈B} (2)

[0041]

[0042]

[0043]

[0044] when For communities to be discovered, define Intra k (C) is the event that the first k edges of e(C) belong to e(C,C), then this probability is expressed as definition (4), for all l=0,1,...,k-1, When the value of l is small, φ l(C) closer...

specific Embodiment approach

[0057] For ease of description: the above step S2 to step S4 can be defined as a Link-based streaming overlapping community detection algorithm (LBSA) process initiated by the present invention. An optional specific implementation is described in detail as follows:

[0058] The edges in the constructed edge graph network are randomly processed sequentially. According to the basic principle, in this process, if an edge (u, v) is processed first, the algorithm will put nodes u and v in the same community. Otherwise put it in a different community. Define the weight w of node i on the current edge i Expressed as:

[0059]

[0060] Among them, W i0 is the initial weight of node i in the edge graph, d i Indicates the current degree of node i (initially 0, and increases as the number of associated edges processed decreases). This definition means that after the edges of the network are processed sequentially, the degree d of node i i increases, the closeness between node i ...

Embodiment 2

[0091] Similar to the above-mentioned embodiment 1, this embodiment is further detailed as follows for specific scenarios:

[0092] Data acquisition: UCI Machine Learning Resource Library (http: / / snap.stanford.edu / data / ) and theKoblenz Network Collection (http: / / konect.uni-koblenz.de / ) can obtain different data collected in the real world Network data in the field, such as social networks, protein networks, etc.; through the extended LFR network generation algorithm proposed by Lancichinetti et al., artificial complex networks that simulate real networks of different scales and structures can be obtained. The obtained network is generally in txt format, where each line represents an edge of the network, and the two numbers in each line represent two nodes of the edge.

[0093] Edge graph construction and preprocessing: convert the network format G=(V,E) in the above txt format into an edge graph network LG=(LV,LE), and at the same time obtain the initial weights of the edge gr...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention relates to the technical field of big data mining, and discloses an edge graph-based linear flow overlapping community discovery method, system and storage medium, so as to improve efficiency and obtain better community division results. The method of the present invention includes: S1, converting the original network into an edge graph network; S2, randomly selecting and processing the edges in the obtained edge graph network in random order, and restoring the edge graph network to the original network when processing each edge , the weight of the current edge and the respective weights of the two associated nodes are calculated from the edge clustering coefficient in the original network and the current updated node degree; S3, compare the weight of the current edge with the first threshold, if the weight of the current edge If it is greater than the first threshold, add the node with a small weight corresponding to the current edge to the community where the node with a large weight is located; otherwise, do not divide the current edge into a community; S4, repeat the above S2 and S3, and process each edge of the edge graph network in turn Finally, the first overlapping community partition map of the entire network is obtained.

Description

technical field [0001] The invention relates to the technical field of big data mining, in particular to a method, system and storage medium for discovering overlapping communities of linear streams based on edge graphs. Background technique [0002] Community discovery in a complex network refers to the mining of the community structure in the network. The community structure is the characteristic of the aggregation of nodes in the network. In a network with a community structure, the nodes in the same community are closely connected while the nodes in different communities are sparsely connected. . Community discovery has important theoretical significance for understanding the structure and function of the network, understanding the dynamics and evolution mechanism of the network, and has good practical application value. For example, in various video, shopping, and search engine networks, community discovery can be used to cluster content of similar types or themes toge...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06F30/18G06Q50/00
CPCG06Q50/01G06F30/18
Inventor 王斌李强盛津芳孙泽军
Owner CENT SOUTH UNIV
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com