基于K-means算法的关联规则数据挖掘方法

A Data Mining Method of Association Rules Based on K-means Algorithm

常规的关联规则数据挖掘方法主要使用事物数据库制定挖掘规则,容易生成较多搜索项集,导致数据挖掘支持度过低,因此基于K-means算法设计了全新的数据挖掘方法。以挖掘信任度为基础,通过模糊查询获取关联规则模糊约束值,生成K-means数据挖掘模型,再进行综合处理,挖掘最大频繁项目集,完成关联挖掘。实验结果表明,设计的挖掘方法在不同数据集下均有较好的数据挖掘支持度,证明设计方法的挖掘性能良好,具有一定的应用价值,可以作为后续网络数据处理的参考。

Conventional association rule data mining methods mainly use the transaction database to formulate mining rules,which is easy to generate more search item sets,resulting in low data mining support.Therefore,this paper designs a new data mining method based on K-means algorithm.On the basis of mining trust,the fuzzy constraint value of association rules is obtained through fuzzy query,K-means data mining model is generated,and then comprehensive processing is carried out to mine the maximum frequent item set to complete association mining.The experimental results show that the designed mining method has good data mining support under different data sets,which proves that the mining performance of the designed method is good and has certain application value,and can be used as a reference for subsequent network data processing.