The mechanism of Web mining is studied. Using large reference sequences as user browsing patterns is developed. After analyzing the feature in mining large reference sequences, a large reference sequences mining algorithm is proposed in Web log mining. The algorithm can find large reference sequences accurately and quickly from Web logs.%研究了Web日志挖掘的机理,提出了使用频繁遍历路径作为用户浏览模式,并在分析挖掘频繁遍历路径的问题特征和对其进行形式化描述的基础上,进一步提出了一种在Web日志中挖掘频繁遍历路径的类Apriori算法,该算法能够正确、快速地从Web日志中抽取频繁遍历路径.
展开▼