关键词: 数据挖掘, 关联规则, 遗传算法, 相关分析

Abstract: Association rule is one of the important modes in data mining and has a very important value.However，the traditional algorithms of association rules which are based on support and confidence framework have lots of limitation in practical applications.A new algorithm for mining positively correlated association rules based on genetic algorithms is designed.Finally，the algorithm is applied to the mining and analysis of clinical experience of famous herbalist doctors.Experimental results show that the new method can remedy the deficiency of traditional association rules algorithm.

Key words: data mining, association rules, genetic algorithms, correlated calculation