Overlapping community discovery method, device, equipment and storage medium
A technology of overlapping communities and discovery methods, applied in the field of social networks, can solve the problems of high complexity of calculation algorithms, failure to consider information such as user social time, and reduce the accuracy of results, etc., to achieve the effect of reducing complexity
Active Publication Date: 2018-09-11
GCI SCI & TECH +1
View PDF5 Cites 10 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0003] However, the inventor found in the process of implementing the present invention that the traditional community discovery method does not consider information such as the user's social time, which reduces the accuracy of the results, and the traditional calculation algorithm is complex and cannot quickly perform community discovery
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
no. 2 example
[0074] On the basis of the first embodiment, the community attribution of each of the discrete points is obtained according to each of the comprehensive spatio-temporal similarities and a preset threshold, specifically: calculating according to each of the comprehensive spatio-temporal similarities Threshold: According to the comprehensive spatio-temporal similarity of each discrete point and the threshold, the community belonging of each discrete point is obtained.
[0075]In this embodiment, the threshold can be calculated according to the comprehensive spatiotemporal similarity between the discrete point and the community core, and the threshold directly determines whether the discrete point belongs to one community or multiple communities. Here, the threshold is calculated by multiplying the comprehensive spatio-temporal similarity of discrete points and community kernels. For example, the threshold setting of the spatio-temporal similarity of mobile users is calculated by...
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
Login to View More Abstract
The invention disclose an overlapping community discovery method, including obtaining social contact data, and according to the social contact data, constructing a social contact network using users in the social contact data as nodes and user relations as sides; preprocessing the social contact network, deleting nonstable sides in the social contact network and generating a target social contactnetwork; dividing the target social contact network to obtain at least one community core and at least one discrete point; according to the social contact data, calculating space-time similarity between each discrete point and each node in each community cores; according to the space-time similarity, calculating comprehensive space-time similarity between each discrete point and each community core; and according to each comprehensive space-time similarity and a preset threshold value, obtaining community affiliation of each discrete point. The invention also discloses an overlapping communitydiscovery device, equipment and storage medium, reduces complexity of calculation, and improves accuracy of an overlapping community discovery result.
Description
technical field [0001] The present invention relates to the technical field of social networks, in particular to a method, device, equipment and storage medium for discovering overlapping communities. Background technique [0002] With the continuous promotion of Internet applications, people are increasingly participating in social networks, and people are no longer limited to geographical differences but are closely connected. With the rapid development of social networks, researchers have studied community discovery more and more deeply. By mining the community structure in the social network, it is possible to discover the hidden organizational structure information or group structure information in the social network. Traditional community discovery methods can be divided into three categories: methods based on label propagation, methods based on node splitting and methods based on modularity optimization. [0003] However, the inventor found in the process of impleme...
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
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G06Q50/00
CPCG06Q50/01
Inventor 杜翠凤
Owner GCI SCI & TECH