基于判断矩阵行一致信息的指标权重均值算法

Index weight mean value algorithm based on consistency information in judgment matrix rows

为了使层次分析法所得指标权重更接近实际,提出基于判断矩阵行一致信息的指标权重均值算法。算法通过提取蕴涵于判断矩阵每行的专家一致性判断信息,构造一组以每行元素为基础的一致性矩阵,根据多次测量所得平均值更接近被测对象真值的原理,取所得一致性矩阵的单位特征向量的平均向量作为指标权重。算法不需要对专家判断矩阵进行一致性检验,彻底避免了调整判断矩阵可能会丢掉专家判断信息的风险。实例计算表明,该算法切实可行。

To make the index weight obtained from AHP more close to the actual one,the index weight mean value algorithm based on consistency information of rows in judgment matrix is put forward. A group of consistency matrix which takes each row′s element as foundation is constructed by extracting consistency information of experts judgment contained in each row of judgment matrix. According to the principle that the average value obtained from multiple measurement is more close to the true value of the measured object,the average vector of unit eigenvector obtained from the consistency matrix is taken as the index weight. Since the algorithm needn′t check the consistency for the expert judgment matrix,the risk that the adjustment of judgment matrix may lose the expert judgment information can be avoided completely. The instance calculation shows that the algorithm is feasible.