关键词: XML, 数据挖掘, 频繁查询模式

Abstract: To study XML query with tree structure modeling, a query and detection method based on tree isomorphism was proposed, systematically enumerating the same root subtree of query pattern tree with the most right branch expansion. In the enumeration process, the Diffset data structure was used to record the query item logo of item set, and the DiffFRSTMiner mining algorithm was proposed. This item set includes the same root subtree. The experimental results prove that the algorithm is efficient, and can reduce definite memory overhead.

Key words: XML, data mining, frequent query pattern