基于风险加权的同构化区间型多属性决策新算法

New Isomorphic Algorithm of Interval Multi-attributes Decision-making Based on Risk-weighted Similarity

多属性决策问题的复杂性、决策因素影响的不确定和传统评判方法的局限性,使不确定决策因素的属性测度常常难以精确量化,往往只能用区间数进行大致估量。为了精确量化表征属性决策因素测度值不确定性,根据同构化基本原理与相似性科学相关理论及相关思想,针对区间型多属性决策问题提出了一种基于同构化多属性决策新方法的新算法。该新算法的主要特点是:1)提出了决策者风险偏好权重;2)采用了同构化风险测度三元组(拟下限相似度,风险程度,风险偏好值),来精确量化决策过程中存在的风险程度以及决策者对此风险程度的偏好;3)生成了可描述各属性与决策目标关系的标杆方案;4)定义了方案相似度新概念;5)构造了风险加权相似度量算子(RWSMO),来度量各决策方案与标杆方案之间风险加权相似度的大小;6)挑选出风险加权相似度最大的方案作为最优或满意方案。

With the complexity of multi-objective decision making, the indefinite of policy-making factor influence and the limitation of traditional judgment method, precisely measuring the attributes＇ values is very difficult frequently, so the attributes＇ values often can be only estimated approximately by using the interval number. For precisely quantify uncertainty, according to the isomorphic fundamental principles and the relative theories and the thought of the similar science, a new algorithm based on an isomorphism multi-ohjective decision-making new method was proposed. The new algorithm＇s main characteristics are：1） propose the policy maker risk preference weight; 2） use the isomorphism risk measure triad （Low limit similarity, Risk degree, Risk preference value） to precisely quantify the risk-degree existing in the decision-making process; 3） produce pole plan to describe the relationship between various attributes and the policymaking goal; 4） define the new concept-plan similarity; 5） construct risk-weighting similar measure operator （RWSMO）, to measure the risk-weighting similarity size between decision scheme and the pole plan; 6） pick out the plan with the maximum of risk-weighting similar measure （RWSM） as the optimum or satisfied plan.