计算机工程与应用 ›› 2008, Vol. 44 ›› Issue (19): 150-152.

• 数据库、信号与信息处理 • 上一篇    下一篇

基于XML数据的FP-growth算法挖掘研究

杨 科,赖朝安,赵 阳   

  1. 华南理工大学 现代制造信息系统研究中心,广州 510640
  • 收稿日期:2007-09-26 修回日期:2007-12-17 出版日期:2008-07-01 发布日期:2008-07-01
  • 通讯作者: 杨 科

Study on FP-growth algorithm for mining based on XML data

YANG Ke,LAI Chao-an,ZHAO Yang   

  1. Research Center of Contemporary Manufacturing Information System,South China University of Technology,Guangzhou 510640,China
  • Received:2007-09-26 Revised:2007-12-17 Online:2008-07-01 Published:2008-07-01
  • Contact: YANG Ke

摘要: XML是跨平台的数据表示、交换技术,由于其本身在自描述性、开放性等方面的优势,在短短的时间内迅速成为行业标准。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,即把XML数据文档映射成关系数据库来完成。给出一个使用FP-growth算法直接从XML文档挖掘关联规则的类接口,并且在J2EE平台下用Java语言实现。

Abstract: XML is a technology for representing and exchanging data on different platform.Due to its advantages of self-description,opening etc,XML has become as an industrial standard in a short time.The large amount of XML data emerges and a new challenge to data mining is given.Traditional mining methods of association rules rely on the relational database,viz.mapping the XML documents into relational databases.A class interface for mining association rules from native XML data based on FP-growth algorithm is given and implemented using Java in the J2EE platform.