异质信息环境下基于案例推理和灰色关联分析的多属性决策方法
A multi-attribute decision-making method based on case-based reasoning and grey correlation analysis in heterogeneous information environment
赵敬华 1施佳 1张艳 1林杰2
作者信息
- 1. 上海理工大学管理学院,上海 200093
- 2. 同济大学经济与管理学院,上海 200092
- 折叠
摘要
针对异质信息环境下类案检索无法精准推送相似案例的问题,考虑到决策信息的模糊性和属性间的关联性,提出一种基于案例推理(case-based reasoning,CBR)和灰色关联分析(grey correlation analysis,GCA)的异质多属性决策方法,以提高案例检索的准确性和高效性.首先,依据模糊测度计算不同属性下的广义Shapley值,以此体现属性间的交互作用及权重信息;其次,基于案例推理的思想,运用灰色关联模型确定目标案例与历史案例的相似程度;此外,将广义Shapley值与灰色关联相结合,得到目标案例与历史案例的灰色关联度,从而获得可供当前目标案例参考的处理措施;最后,通过司法执行案件的类案检索问题验证所提方法的可行性和实用性,进而完善异质多属性决策理论体系,为解决司法领域难题拓宽新路径.
Abstract
Considering the ambiguity of decision information and the interaction of attributes,a heterogeneous multi-attribute decision-making method based on case-based reasoning and grey correlation analysis is proposed to solve the issue of the inability to accurately push similar cases in case retrieval with heterogeneous information and improve the accuracy and efficiency of case retrieval.Firstly,the generalized Shapley values under different attributes are calculated based on fuzzy measures to reflect the correlation between attributes and their weight information.Secondly,based on the idea of case-based reasoning,the grey relational model is used to calculate the similarity between the target case and the historical case.In addition,by combining the generalized Shapley value with grey correlation,the grey correlation degree between the target case and historical case is obtained,thereby obtaining processing measures that can be referenced by the current target case.Finally,the feasibility and practicality of the proposed method are verified through the case retrieval problem of judicial enforcement cases,which can improve the heterogeneous multi-attribute decision-making theoretical system,broadening new paths to solve difficulties in the judicial field.
关键词
异质信息/广义Shapley值/案例推理/灰色关联分析/类案检索/多属性决策Key words
heterogeneous information/generalized Shapley values/case-based reasoning/grey relational analysis/case retrieval/multi-attribute decision-making引用本文复制引用
基金项目
国家自然科学基金项目(72201173)
上海市"科技创新行动计划"软科学研究项目(22692108400)
出版年
2024
NETL
NSTL
万方数据