基于有序FP-tree结构和二维表的最大频繁模式挖掘算法  

Maximum Frequent Pattern Mining Algorithm Based on Ordered FP-tree Structure and Two-dimensional Tables

作　　者：王利军[1] 唐立 WANG Li-jun;TANG Li(Department of Information Engineering,Anhui Institute of Economics Management,Hefei 230031,Anhui,China)

机构地区：[1]安徽经济管理学院信息工程系

出　　处：《韶关学院学报》2019年第9期21-25,共5页Journal of Shaoguan University

基　　金：安徽省质量工程项目（2018jxtd044）

摘　　要：Order Table FPMax是基于有序FP-tree结构和二维表的最大频繁模式挖掘算法.有序FP-tree结构可以减少空间的浪费.基于树结构的有序性,算法在挖掘数据时可以减少挖掘事务项的数量,加快挖掘效率.算法采用二维表存储挖据事务项的路径信息及交集,采用相应的计算方法可以在不产生条件子树的情况下快速得到最大频繁项集,并避免没必要的挖掘过程减少超集检测,既减少了空间的浪费,又加快了执行效率.Order Table FPMax is a mining algorithm of maximum frequent pattern based on ordered FP-tree structure and two-dimensional tables. Ordered FP-tree structure can reduce the waste of space. The algorithm based on tree structure’s orderliness can reduce the number of transaction items when mining data, thus speeding up the mining efficiency. The algorithm uses two-dimensional tables to store the path information and intersection of mining transaction items. The corresponding calculation method can quickly obtain the Maximum Frequent Itemsets without generating conditional subtrees and avoid unnecessary mining process to reduce superset detection, thus reducing the waste of space and speeding up the execution efficiency.

关 键 词：有序FP-tree 二维表 最大频繁项集 OrderTableFPMax 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]