基于数据仓库的高效关联规则的挖掘  

Mining Association Rule Based on Data Warehouse

作　　者：赖邦传[1] 陈晓红[1] 周辉[2] 

机构地区：[1]中南大学商学院,长沙410083 [2]中国建设银行长沙市河西支行,长沙410006

出　　处：《计算机工程》2004年第5期6-8,共3页Computer Engineering

基　　金：国家自然科学基金委国家杰出青年科学基金资助项目(70125002)

摘　　要：提出在基于数据仓库的关联规则发现中生成最小关联规则集来代替完全关联规则集，最小关联规则集必须具备两个条件：(1)最小关联规则集是最小、最简单的关联规则集合；(2)最小关联规则集与完全关联规则集有相同的置信度。通过最小关联规则集，可以有效地剪除弱关联规则，大幅度减少候选频繁项目集，从而提高规则发现效率。最后，在传统经典算法Apriori基础上设计了一个相应的高效算法。In the paper, we replaced the complete association rule set with the least association rule set in the process of association rule mining. The least association rule set should at least comply with two requirements including: (1) it should be the minimal and the simplest association rule set and (2) its confidence should be the same as that of the complete association rule set. By adopting the least association rule set, the pruning of weak rules can be effectively carried out so as to greatly reduce the number of frequency itemset, and therefore the mining efficiency can be improved. Moreover, corresponding efficient algorithms are developed based on the classical Apriori algorithm.

关 键 词：数据仓库 数据挖掘 关联规则挖掘 最小关联规则集 

分 类 号：TP311.131[自动化与计算机技术—计算机软件与理论]