基于粗糙集的Web事务聚类算法  

Web Transactions Clustering Algorithm on Rough Set

作　　者：邱波[1] 

机构地区：[1]江苏师范大学现代教育技术中心

出　　处：《微型电脑应用》2014年第2期56-58,共3页Microcomputer Applications

摘　　要：针对现有Web数据挖掘方法发现的知识和规则存在不精确或不完全的问题,将粗糙集引入到Web挖掘中,进行Web事务聚类。粗糙近似算法基于用户访问序列的顺序和内容建立用户事务相似度矩阵,运用基于相似度矩阵的粗糙上近似提取初始类,使用相对相似性的条件作为合并准则,基于约束相似性的上近似形成后续类。粗糙近似算法能够有效挖掘Web访问日志,聚类Web事务,发现用户访问Web页面的模式。Web usage mining can mine useful information from web access log.The discovered knowledge or unexpected rules are likely to be imprecise or incomplete.Rough set is introduced into the web mining to cluster web transactions.The set as well as sequence similarity of users＇ sessions is considered to form similarity matrix.Initial clusters are formed using a similarity upper approximation.Subsequent clusters are formed using the concept of constrained-similarity upper approximation wherein a condition of relative similarity is used as a merging criterion.Using this approach,users can effectively mine web log records to discover web page access patterns.

关 键 词：WEB挖掘 粗糙集 相似上近似 约束相似性上近似 事务聚类 

分 类 号：TP301[自动化与计算机技术—计算机系统结构]