基于粗糙集的AHP评估模型研究

Research on Evaluation Model of Analytic Hierarchy Process Based on Rough Sets

判断矩阵是层次分析法(Analytic Hierarchy Process,AHP)进行相对重要度计算的重要依据,而判断矩阵一般由专家根据个人经验而建立,因而伴有较多的主观因素,甚至生成的判断矩阵出现不一致性,不利于客观地进行系统评估;针对此问题,将粗糙集引入到AHP中,建立了基于粗糙集的AHP评估模型,为了提高属性集属性约简效率,改进了集合近似质量属性约简算法;应用粗糙集理论计算相同层次两两评价指标的近似质量差,根据差的大小确定指标重要性,并通过实例证明了该模型的合理性和正确性。

As the basic information of Analytic hierarchy process and important warranty to do relative computing of importance degree, determination matrix always created by experts according to their experience, has many subjective factors and even generates inconsistencies which is go against to objective evaluation system. To solve the problem, AHP evaluation model based on soft computing is constructed, in order to boost the attributes reduction efficiency of attributes sets, the set approximate quality reduction algorithm is improved. In the model, approximate quality difference of two evaluations in the same level is computed by rough sets, and the importance degree is determined by difference. The model is validated by instance.