摘要
在对基于统计数据仓库的海量历史数据进行数据挖掘和知识发现过程中,产生出一大类带有时态特征的衍生信息,可以归结定义为衍生过程.本文介绍了在万峰统计数据仓库中进行数据挖掘和知识发现过程中的衍生现象,定义了衍生过程的数学模型,并对统计数据挖掘中衍生过程模型的建立提出了相关规则.
In the data mining and knowledge discovering processing based on the statistic data warehousing,a large scale of temporal derivative information was produced as by product,which was named as derivative procedure.This paper introduce the derivative phenomena in data mining processing on Wanfeng statistic data warehousing,gives the mathematical model and corresponding rule for it.
出处
《广西师范大学学报(自然科学版)》
CAS
2003年第A01期127-130,共4页
Journal of Guangxi Normal University:Natural Science Edition
关键词
数据仓库
数据挖掘
衍生过程
data warehouse
data mining
derivative procedure