XML结构聚类

针对当前XML文档结构聚类算法的一些不足，提出采用段匹配的概念来计算两棵XML文档树中的路径相似性，并在此基础上得出两棵树整体的相似度量。在整个聚类过程中，算法还把一组相关文档与一个XML聚类代表相关联，该聚类代表就包含了一个文档集合中所有文档的最相关的特征。为了构建聚类代表，算法通过构造最佳匹配树，合并树，修剪树三步来实现。通过比较聚类代表，发现新的聚类时更新聚类代表来完成文档聚类。实验结果就充分展现了算法的有效性。

XML documents structured Cluster

This article proposed a novel way for clustering XML documents against the defects of the methods in existence. Based on the conception of segment matching, calculation the similarity of two XML trees, which was used to measure the similarity between the two integrated XML trees. In the whole clustering procession, it equiped each cluster with XML cluster representative, which subsumed the most typical structural specifics of a set of XML documents. The cluster representative was constructed by three successive steps named Tree matching, Tree merging and Tree pruning. Then clustering was accomplished by comparing cluster representatives, and updating the representatives as soon as new clusters are detected. And finally the effectiveness of the clustering method is evaluated by testing results.