基于属性分类的混合型多属性消错决策方法

An Error-Eliminating Solution of Hybrid Multi-Attribute Decision Making Problem Based on Attribute Classified

混合型多属性决策包含不同的数据类型的属性值，此类决策现有方法往往忽略对属性不同功能的区分，而且没有考虑对错误损失的规避．针对上述问题，从损失规避的角度提出一种基于属性分类的混合多属性消错决策方法，通过对属性的功能特性分类，然后采用相应的错误函数计算属性的错误值、错误极限损失值，统一不同数据类型的属性偏离为错误损失值，比较各备选策略错误损失值的大小优选策略．文章最后以实际算例说明该方法的有效可行性．

The attribute values of hybrid multi-attribute decision making problem usually have different data types. The existing solutions generally ignore distinguishing the importance of different attributes and make decision without avoiding the loss when error occurring. Ac- cording to the error-eliminating theory and on the view of error avoiding, an error-eliminating solution is proposed in this paper. Classifying the attributes according to their importance, calculating the error value and maximum error-loss value with corresponding error function, uniforming the attribute deviation in different data forms to error loss, a prior scheme can be selected based on the order of error loss value. At last an example shows the efficiency and feasibility of the solution.