基于区别度概念格的关联规则的挖掘

Association rules mining based on discriminative concept lattice

针对大部分文献在构造概念格时都把属性看做是同等重要,而将导致冗余问题,提出了一个新的概念———属性区别度(内涵区别度)。在建造概念格的过程中将去掉那些属性区别度(D ISP)比较低的内涵,从而加速概念格的构造;同时不再每一次都扫描数据库计算项集或内涵的支持度,而是有条件地计算和重置D ISP,这将减少扫描数据库的次数,从而达到减少生成关联规则时间的目的。

Most of literatures did not take into account the differences of attributed when building concept lattice. This paper proposed a new concept called discriminative attribute （discriminative intension）. Every attribute had DISP. In the process of building concept lattice, it could remove the attributes of low discriminative power, then sped up the step of constructing the lattice. Furthermore, there had been a new method to calculate the DISP and reset the value under some condition, but scan the database on each layer, which reduce the number of scanning the database, then decrease the time of generate association rules.