Supply and demand network community structure mining method

Abstract

The invention discloses a supply and demand network community structure mining method; the method comprises the steps: dividing a supply and demand network into maximum clusters with the same aggregation type according to at least one preset aggregation type, and obtaining at least one first initial community structure; combining the maximum group in each initial community structure to obtain an intermediate community structure; including the isolated nodes in the intermediate community structure in the community network of the intermediate community structure to obtain a target community structure, so that the community structure with better quality is found from all the community structures obtained according to various combination modes, and then including the nodes except the maximum community in the community network of the intermediate community structurs for realizing mining of a supply and demand network community structure with heterogeneity.

Description

technical field [0001] The invention relates to the field of network science, in particular to a heterogeneous supply and demand network community structure mining method and a computer-readable storage medium. Background technique [0002] In the real world, many networks show a dichotomous structure, that is, the network contains two different types of nodes, there are no edges between nodes of the same type, and only edges between nodes of different types. The supply and demand network is composed of two different types of nodes: supply nodes and demand nodes. It is a typical dichotomous heterogeneous network, in which demand nodes are closely related to human beings, supply nodes refer to geographical entities that provide various urban services, and connected edges represent demand nodes. The connection formed with the supply node, and the population flow between the two is used as the edge weight. A typical case is that residents (demand nodes) enjoy the ecosystem ser...

AI Technical Summary

Problems solved by technology

Similar to homogeneous network, community structure is also an important characteristic of supply and demand network. Unlike homogeneous network, since the nodes in bipartite heterogeneous network are naturally divided into different types, if the bipartite heterogeneous network is projected Mining the community structure after forming a homogeneous network will cause information loss and redundancy in the original binary heterogeneous network, and the number of edges will increase dramatically, which will affect the accuracy of the mining results. Therefore, there is an urgent need for a method suitable for mining binary heterogeneity. Methods of Network Community Structure

Images