Abstract: Under the interval-valued intuitionistic fuzzy information environment, with respect to the multiple attribute group decision making problem in which the attribute weights are completely unknown, based on the bi-direction projection weights model, a novel multi-attribute group decision making (MAGDM) method is developed. First, the idea alternative and critical alternative are obtained in accordance with collection decision making matrix provided by decision makers, and the correlation coefficient and projection length are determined on the basis of projection formula. Then, with the principle of maximization and minimization of objective functions, a multi-objective optimization model is constructed to get the attribute weights. Finally, the bi-direction projection optimization model of attribute weight vector is investigated, the ranking order based on the improved VIKOR and TOPSIS is obtained, and a numerical example about the logistics transportation partner selection is provided to illustrate the effectiveness of the developed method.

Key words: Interval-valued intuitionistic fuzzy sets, multi-attribute group decision making, weight vector, bi-direction projection

摘要： 在区间直觉模糊信息环境下，针对属性权重完全未知的多属性群决策问题，基于双向投影权重模型，构建了一种的新的多属性群决策模型。首先基于决策者提供的综合决策矩阵确定理想方案和临界方案，并依据投影公式计算各备选方案的关联系数和投影长度；其次，分别以最大化和最小化为目标函数，建立多目标最优化模型获取对应的属性最优权重；最后，构建属性权重向量的双向投影优化模型，运用改进的VIKOR和TOPSIS方法进行方案排序，并通过物流运输伙伴选择实例说明所提方法的有效性。

关键词: 区间直觉模糊集, 多属性群决策, 权重向量, 双向投影