有趣Web日志关联规则挖掘算法  

Interesting association rule mining algorithm from web log data

作　　者：董祥和[1] 仲丛友[1] 董荣和[2] 

机构地区：[1]天津工程师范学院商贸管理系,天津300222 [2]西北工业大学计算机学院,陕西西安710072

出　　处：《计算机工程与设计》2009年第4期1036-1038,共3页Computer Engineering and Design

基　　金：天津工程师范学院科研发展基金项目(SK-JH2007001)

摘　　要：对Web日志关联规则挖掘算法进行了研究,普通的关联规则挖掘算法发现的规则数量太多,里面含有大量用户不感兴趣的规则,规则知识很难为用户所使用。根据网站拓扑结构和矩阵迭代技术实现了一种有趣关联规则(IMIA)算法,能够快速迭代求解任意两个页面间的关联概率,对关联规则进行有趣度评价,得出有趣度高的规则。实验结果表明,该算法是有效的,可以进一步改善网站性能,提高智能服务质量和性能,从而很好地应用到电子商务领域。Web log association rules mining algorithms are studied. The traditional association rules mining algorithms produce too many redundant rules which users are not interested in or cannot be used effectively. According to web topology structure and a matrix iteration method, an interesting matrix iteration association rules algorithm （IMIA） is presented. It can efficiently calculate association probabilities between every two resources. It can evaluate the interest of each association rule and generate association rules with high interest. The experimental results indicate that this proposed algorithm is feasible and efficient. It is used to improve network performance, enhance quality and performance of intelligent services. Therefore, it is successfully applied to E-Commerce.

关 键 词：WEB日志 网站拓扑 矩阵迭代 概率模型 有趣关联规则 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程] TP391[自动化与计算机技术—控制科学与工程]