基于XML数据的关联规则挖掘研究  

Study on mining association rules from XML data

作　　者：徐勇[1] 成良玉[1] 李猛[1] 

机构地区：[1]中山大学信息科学与技术学院,广东广州510275

出　　处：《计算机工程与设计》2006年第24期4704-4706,共3页Computer Engineering and Design

摘　　要：XML凭借其诸多优点,在短短的时间内迅速成为表示和交换信息的标准。大量XML数据的涌现给数据挖掘提出了新的挑战。传统关联规则挖掘是基于关系数据库的,因此现有许多XML数据关联规则挖掘的方法都或多或少地利用关系数据库—即把XML数据文档映射成关系数据库来完成的。在仔细研究了XML数据的访问接口后,给出了一个基于Apriori算法可直接从XML文档挖掘关联规则的类接口,并且在.NET平台下用C#语言实现了。Due to its many advantages, XML （extensible markup language） has become as a standard for representing and exchanging information. The large amount of XML data emerges and a new challenge to data mining is given. Although there have been many methods to handle XML documents, these methods rely on the traditional relational databases more or less, i.e, mapping the XML documents into relational dataes. After carefully studying the XML data access class interface, a class interface for mining association rules from native XML data based on Apriori algorithm is given and implemented using C# in the.NET framework.

关 键 词：数据挖掘 关联规则 可扩展标记语言 APRIORI .NET 

分 类 号：TP311.138[自动化与计算机技术—计算机软件与理论]