Minimum k faction detecting method in picture data, device and equipment

Abstract

The application provides a minimum k faction detecting method in picture data, a device and equipment, and relates to the field of data excavation. The method includes steps of loading picture data, wherein every top point in the picture data is corresponding to respective top point ID; calculating a neighbor top point set corresponding to every top point in the picture data, wherein the neighbortop point set comprises a neighbor top point corresponding to the top point, and the top point ID of the neighbor top point is more than that of the top point; according to the neighbor top point set,calculating common neighbor top points of two top points on every side in the picture data; determining the minimum K faction in the picture data according to two top points and common neighbor top point on every side in the picture data. Based on the maximum value principle, only the neighbor top point of which top point ID is more than own top point ID is reserved; compared with the calculatingmethod of the neighbor top point set in the prior art, the middle data volume is reduced by a half, thus the subsequent useless calculation is reduced, the calculation load is decreased, and the calculation efficiency is improved.

Description

technical field [0001] The present application relates to the field of data mining, in particular to a minimum K faction detection method, device and equipment in graph data. Background technique [0002] As a common data mining method in the era of big data, graph data mining (also known as graph computing) is widely used in community structure mining, edge aggregation coefficient calculation, vertex intimacy calculation and vertex similarity calculation, etc. field. [0003] When graph data mining is performed, the data to be mined is stored in the form of graph data. In the graph data, the vertex is used to store the vertex value, and the edge is used to represent the relationship between the vertices, and two connected by an edge vertices are neighbor vertices. In graph data, a set of vertices where any two vertices are connected is called a clique, and a 3-clique is called a minimum K clique. When mining graph data, the minimum K faction detection (that is, detecting...

AI Technical Summary

Problems solved by technology

[0006] The embodiment of the present application provides a minimum K faction detection method, device and equipment in graph data, which can solve the problem of the high expansion rate of intermediate data in the calculation process during the minimum K faction detection process. In some cases, the amount of calculation is too large, which affects the calculation efficiency and even leads to the problem that the calculation cannot be completed

Images