Web日志挖掘中的用户访问模式识别

Web Data Mining for Path Traversal Patterns

本文探索了一种新的Web日志挖掘算法,以便更有效地捕获用户访问模式．该算法首先把原始的用户访问序列转换为一个最长前向访问序列的集合,在转换中过滤掉了用户的回退操作；算法的第二步是根据第一步所得到的结果求得一个用户频繁访问模式．算法经实验模拟测试具有较为满意的时间复杂度和空间复杂度．

In this paper, we explore a new Web data mining algorithm which involves mining traversal patterns in Web data logs. First, we convert the original sequence data of log data into a set of maximal forward reference and filter out the effect of some backward references which are mainly made for ease traveling. Second, we derive an algorithm to determine the frequent traversal patterm, i.e., large reference sequences, from the maximal forward references obtained.