基于不确定语言环境的绩效考评模型

Model for performance appraisal with uncertain linguistic information

研究了属性权重不完全、属性值以不确定语言变量形式给出的不确定语言绩效考评问题,引入了不确定语言变量的运算法则,以及不确定语言变量之间比较的可能度公式,给出了不确定语言变量间的距离的概念.首先用不确定语言加权平均(ULWA)算子集成得到群不确定语言决策矩阵,然后针对属性权重不完全的情形,给出了一个求解权重的逼近于相对理想点法;然后利用不确定语言加权平均(ULWA)算子,对不确定语言决策信息进行加权集成,并利用可能度公式构造可能度矩阵(互补判断矩阵),继而利用互补判断矩阵排序公式对决策方案进行排序和择优;最后进行实例分析.

In this paper, the problems of the performance appraisal were studied, in which the information about attribute weights is incompletely known and the attribute values take the form of uncertain linguistic variables. The operational laws of uncertain linguistic variables and a formula of possibility degree for the com- parison between uncertain linguistic variables were introduced, and then the concept of deviation degree between uncertain linguistic variables was defined. Firstly, the uncertain linguistic weighting average （ULWA） operator was used to aggregate all the decision matrices into a collective decision matrix. An optimization model based on the ideal point of attribute values was established, by which the attribute weights can be de- termined. The ULWA operator was used to aggregate the uncertain linguistic variables corresponding to each alternative, and the formula of possibility degree was used to construct a possibility degree matrix （ or called complementary judgment matrix） , and then the priority formula of complementary judgment matrix was used to rank the alternatives and select the most desirable one. Finally, an illustrative example is shown to highlight the procedure of the proposed algorithm at the end of this paper.