带特征指标约束描述的设计模式分类挖掘

Design pattern classification mining with feature metrics constraints

为解决设计模式挖掘正确率较低的问题,提出一种带特征指标约束描述的设计模式分类挖掘方法。归纳了47种特征指标,给出了设计模式约束定义,对设计模式特征进行了描述,以Adapter模式、Command模式、Factory Method模式为例,分结构型、行为型与创建型3类挖掘设计模式,设计了3个基准系统与4个经典系统的设计模式挖掘试验。试验结果表明,本研究方法对基准系统的Adapter模式、Command模式、Factory Method模式挖掘正确率为96.13%、91.67%、72.23%,对经典系统挖掘正确率分别为84.3%、81.26%、73.17%,与传统方法比较,本研究方法取得了较好的效果。

To solve low accuracy for design pattern mining,a method for design pattern classification mining with feature metrics constraints was presented.47 feature metrics information based on structural pattern,behavioral pattern and creative pattern was classified and summarized,and definition of design pattern were given,and features of design patterns were described,three benchmark systems and four well-known system experiments for design pattern mining were designed.Experimental results show that proposed method is effective,and the accuracy of the proposed method was 96.13%,91.67%,72.23%for Adapter pattern.Command pattern and Factory method pattern for three benchmark systems,and the accuracy of the proposed method is 84.3%,81.26%,73.17%for Adapter,Command and Factory Method of design pattern for four well-known systems,compared to well-known methods by experiment of design pattern mining,indicating the effectiveness of the proposed method.