A community discovery algorithm in an enterprise map based on relationship weights

Abstract

The invention discloses a community discovery algorithm in an enterprise map based on relationship weights. The community discovery algorithm comprises the following steps: (1) weights of relationships in the enterprise map are determined; (2) the similarity between enterprises are determined; (3) Modularity is used to evaluate the results of community discovery in complex networks; (4) convergingis carried out based on modularity constraint algorithm ; (5) Confidence probability table is calculated based on LPA algorithm. By discovering the communities in the enterprise map, the algorithm divides the entire enterprise map into sub-graphs. The divided enterprise map can not only help to analyze the industry prospects according to its community attributes, but also can be used to analyze the financial guarantee information, cooperation information, investment information and so on. And according to community attributes, the government or relevant departments are helped to formulate policies to adjust the market in a timely manner.

Description

technical field [0001] The invention relates to the technical field of community discovery algorithms, and more specifically relates to a community discovery algorithm in an enterprise graph based on relationship weights. Background technique [0002] A business graph is a complex network of companies and the relationships between them. A complex network is a network with some or all of the properties of self-organization, self-similarity, attractor, small-world, and scale-free. A complex network is an abstraction of a complex system. In reality, many complex systems can be described and analyzed using the relevant characteristics of a complex network. The enterprise map constructed using the full amount of enterprise data is one of the complex networks, which can be used to analyze relevant national data. A system composed of all enterprises and self-employed. [0003] The study of complex networks has been a hot topic in many research fields, among which community detect...

AI Technical Summary

Problems solved by technology

[0007] Although the LPA algorithm can divide the communities in the complex network, there are certain defects in the process of applying it to the enterprise map

First of all, the LPA algorithm requires that a node can only have one label. In the process of node propagation, the previous state of each node will be erased, which makes the process of label propagation very absolute and will cause certain information loss; secondly , the LPA algorithm does not consider the closeness of node associations. In the enterprise map, there are differences in the degree of closeness of association between individuals and enterprises and between enterprises and enterprises. For example, two individual nodes have invested in a certain enterprise, but the investment amount There is a gap. It is obvious that personal nodes with large investment should be more closely connected with the enterprise, while the LPA algorithm only counts the number of occurrences of tags, ignoring the closeness of the relationship; finally, the application of the LPA algorithm in the enterprise map lacks a Appropriate convergence constraints, the iterative process can only be terminated by limiting the number of times, and the algorithm lacks a clear evaluation standard in the enterprise map

Therefore, the LPA algorithm is not suitable for direct application to community discovery in enterprise graphs

Images