一种优化的Apriori关联规则算法  

An optimized Apriori association rule algorithm

作　　者：朱奎兵 刘彦戎[1] ZHU Kui-bing;LIU Yan-rong(School of Public Course Training and Teaching Center,Shaanxi Institute of International Trade&Commerce,Xi’an 712046,China)

机构地区：[1]陕西国际商贸学院公共课实训教学中心,西安712046

出　　处：《信息技术》2022年第5期77-81,87,共6页Information Technology

基　　金：陕西省重点研发计划(2019NY-185)。

摘　　要：在数据挖掘中,Apriori算法用于从大型数据库中提取频繁项集,从而获取用于发现知识的关联规则。文中指出了原始的Apriori算法在生成频繁项集的过程中需要大量的时间扫描数据库,由此产生庞大的候选项集,存在算法执行效率低的问题。对于以上问题,提出一种优化的Apriori关联规则算法,该算法通过减少扫描部分事务的时间,从而达到减少生成候选项集的方法。文中通过多组实验数据验证表明,优化的Apriori关联规则算法具有较高的执行效率。In data mining,the Apriori algorithm is used to extract frequent item sets from large databases to obtain association rules for knowledge discovery.This paper points out that the original Apriori algorithm requires a lot of time to scan the database in the process of generating frequent item sets,which results in a huge candidate item set,leading to a problem of low algorithm execution efficiency.Based on the above problems,an optimized Apriori association rule algorithm is proposed.The algorithm reduces the time of scanning partial transaction to reduce the generation of candidate item sets.This paper verifies through multiple sets of experimental data that the optimized Apriori association rule algorithm has high execution efficiency.

关 键 词：计算机应用技术 优化的Apriori算法 频繁项集 支持度 候选项集 

分 类 号：TP305[自动化与计算机技术—计算机系统结构]