基于XQuery的XML文档的关联规则挖掘

Mining association rules from XML document using XQuery

目前,使用XQuery语言实现的Apriori算法基本都是对单个XML文档进行挖掘,而对于现实中的XML文档,有些情况下相关联的数据是存放在多个文档中的,文档之间没有必然的联系,这时就要将多个文档同时考虑进来进行挖掘。针对如何对多个XML文档进行挖掘的问题,对基于XQuery语言的Apriori算法进行改进,引入了collection函数,使之能够对多个XML文档组成集合的节点进行访问,从而实现对多个XML文档的关联规则挖掘,最后通过实验验证其可行性及有效性,使其效果达到和对单个文档挖掘的相同效果。

At present,the Apriori algorithms realized by the XQuery language are basically used for mining the single XML documents.But regarding the reality in XML documents,in some situations related data are deposited in several documents which have no inevitably relations among them.At this point,several documents have to be simultaneously taken into consideration in order to mining the information.In view of the question how to mining several XML documents,to improve the Apriori algorithms based on the XQuery language,the collection function is introduced which can realize the visit to the composition set node of several XML documents.Then it can mining the association rules from several XML documents.Last,the experiment verifies its feasibility and efficiency,make it has the same effect as mining the single XML documents.