基于图模式的犯罪情报数据集挖掘算法  

An Algorithm for Mining Criminal Intelligence Data Set Based on Graph Pattern

作　　者：唐德权[1] 史伟奇[1] 刘绪崇[1] TANG Dequan;SHI Weiqi;LIU Xuchong(Department of Information Technology,Hunan Police Academy,Changsha 410138,China)

机构地区：[1]湖南警察学院信息技术系,湖南长沙410138

出　　处：《中国人民公安大学学报（自然科学版）》2021年第3期74-78,共5页Journal of People’s Public Security University of China(Science and Technology)

基　　金：国家自然科学基金项目(61471169);湖南省科技重大专项项目(2017SK1040);湖南省教育厅重点项目(20A172)。

摘　　要：从图模式中挖掘频繁子图的最大挑战是候选模式的大量产生,特别在大型图模式的情报数据集中,以至于合理的计算资源无法完整枚举频繁子图的总数。文中提出一种基于图模式的犯罪情报数据集挖掘k-频繁子图算法。首先,将图模式进行预处理得到k个顶点子图的新数据集;然后,从新图模式集中获得所有k个顶点的生成子图;最后,通过k顶点的生成子模式得到k-频繁子图,在真实犯罪情报数据集上验证了算法的有效性。One fundamental challenge for mining frequent subgraphs from graph patterns is the overwhelming abundance of candidate patterns,especially in the intelligence data set of large graph patterns,the total number of frequent subgraphs can become too large to allow a full enumeration using reasonable computational resources.We propose an algorithm for mining k-frequent subgraphs based on graph patterns in criminal intelligence data sets.Firstly,the graph pattern is preprocessed to obtain a new data set of k-vertex subgraphs.Then,the generated subgraphs of all k-vertices are obtained from the new graph pattern set.Finally,k frequent subgraphs are obtained by generating sub-patterns of k-vertices.Finally,the effectiveness of the algorithm is verified on the real criminal intelligence data set.

关 键 词：图模式 数据挖掘 生成子图 k-频繁子图 

分 类 号：D918.2[政治法律—法学]