运筹与管理 ›› 2019, Vol. 28 ›› Issue (8): 41-47.DOI: 10.12005/orms.2019.0173

• 理论分析与方法探讨 • 上一篇    下一篇

混合不确定性下基于区间证据随机抽样的统一赋权法

闫英1, 锁斌2, 甘蜜3   

  1. 1.西南科技大学 经济管理学院,四川 绵阳 621010;
    2.中国工程物理研究院 电子工程研究所,四川 绵阳 621900;
    3.西南交通大学 交通运输与物流学院,四川 成都 610031
  • 收稿日期:2017-03-15 出版日期:2019-08-25
  • 作者简介:闫英(1979-),女,黑龙江方正人,博士、副教授,主要从事决策分析、物流金融等研究。
  • 基金资助:
    国家自然科学基金资助项目(71403225);四川省社科联学科共建项目(SC17XK076);四川省教育厅项目(XHJJ-1817);绵阳市社科联(SCXX2017YB09)

An Unified Method for Determining Index Weight Based on IntervalEvidence Random Sampling under Hybrid Uncertainties

YAN Ying1, BIN Suo2, GAN Mi3   

  1. 1.School of Economics and Management, Southwest University of Science and Technology, Mianyang 621010, China;
    2.China Academy of Engineering Physics, Mianyang 621900, China;
    3.School of Traffic Transportation & Logistics, Southwest Jiaotong University, Chengdu 610031, China
  • Received:2017-03-15 Online:2019-08-25

摘要: 由于评价问题的复杂性,以及专家知识和经验的局限性,群决策信息中往往同时包含不同程度的不确定性。在区间证据理论框架下对认知不确定性信息、多区间概率信息、不完全信息等混合不确定信息进行统一表示,进而根据区间证据间的相似度对群决策信息进行融合;采用区间数对评语等级进行定量化,并根据融合结果构造个指标重要程度的概率分布函数;最后通过概率分布函数的蒙特卡洛随机抽样确定指标权重。算例分析结果表明了新方法的有效性。

关键词: 群决策, 指标赋权, 混合不确定信息, 区间证据理论, 蒙特卡洛抽样

Abstract: As the complexity of evaluation problem and limitation of experts’ knowledge and experiments, there are various types of uncertainties in group decision making information. The method of translating hybrid uncertain information for interval evidence body uniformly is studied, which includes epistemic uncertain information, multi-interval probabilities, and incomplete information. Hybrid uncertainties quantify the remark grades, and the probability distribution function of index importance is constructed with fused information. Last, Monte Carlo sampling is used to determine the index weight. The numerical examples show the effectiveness of proposed method.

Key words: group decision-making, index weight, hybrid uncertain information, interval evidence theory, Monte Carlo sampling

中图分类号: