利用分布式数据库实现高效查找频繁项集  

USING DISTRIBUTED DATABASE REALIZE FINDINGFREQUENT ITEM SETS HIGH EFFECTIVLY

作　　者：胡鹏[1] 童恒建[2] 徐来[2] 

机构地区：[1]中国地质大学计算机学院研200420班 [2]中国地质大学计算机学院

出　　处：《微计算机信息》2006年第05X期175-177,共3页Control & Automation

基　　金：国家863计划空间信息多级网格的框架设计与相关技术研究编号:2003AA132080;地大杰出青年基金编号:CUGQNL0506

摘　　要：数据挖掘的目的是为了发现有效的关联规则从而找到不易发现的规律从而对企业的决策提供帮助,而查找频繁项集是发现有效关联规则的基础,其基础算法是Apriori算法。分布式数据库是目前较为流行的一种的数据库开发模式,它通过将一套完整的数据库系统分别部署在几台电脑上可以实现几台电脑并行处理数据从而提高数据库的效率。本文通过分析一个查找频繁项集的例子提出了一种将改进的频繁项集查找算法与分布式数据库相结合的方法从而实现频繁项集的高效查找。The purpose of Data mining is to find effective Association rules. Through these Association rules to find some rules that are not easy to find. Through these rules to help the headers of the companies to make decisions. Finding frequent item sets is the base of finding Association rules. The base algorithm of finding frequent item sets is Apriori. Distributed database is a popular pattern of developing database, it can distribute a set of Database Manager System on several computers to realize improving the effective of the Database Manager System. Through the analysis of an example of finding frequent item sets this paper present a new method to find frequent item sets. This method combines a new method of finding frequent items and distributed database. Through this method we can find frequent items more effectively.

关 键 词：数据挖掘 分布式数据库 项集 频繁项集 

分 类 号：TP311.133.1[自动化与计算机技术—计算机软件与理论]