一种商空间理论下信息熵的属性权重确定方法  

A Method for Determining Property Weights of Information Entropy under Quotient Space Theory

作　　者：阎红灿 姚美红 郭小雨 YAN Hong-can;YAO Meihong;GUO Xiao-yu(College of Science,North China University of Science and Technology,Tangshan Hebei 063210,China;Hebei Key Laboratory of Data Science and Application,Tangshan Hebei 063210,China)

机构地区：[1]华北理工大学理学院,河北唐山063210 [2]河北省数据科学与应用重点实验室,河北唐山063210

出　　处：《华北理工大学学报（自然科学版）》2023年第3期58-64,共7页Journal of North China University of Science and Technology：Natural Science Edition

基　　金：河北省高等教育教学改革研究与实践项目(2020GJJG158)。

摘　　要：在对多属性多目标方案进行排序或决策时,属性权重的确定对最终决策结果的影响非常重要。针对无决策属性的多样本数据,提出了一种基于层次商空间信息熵的属性计算方法。该方法通过对样本数据的相似度和等价关系矩阵分层建立商空间结构,重新定义商空间理论下的信息熵,在商集上计算确定属性权重。最后将该方法应用到一个既无决策属性又无核属性的油田开发多目标决策数据集中,验证了该方法的科学性和可行性。When ranking or making decisions on multi-attribute and multi-objective schemes,the determination of attribute weights is very important to the final decision results.Aimingat multi-sample data without decision attributes,an attribute calculation method based on hierarchical quotient spatial information entropy was presented.The quotient space structure by layering the sample data similarity and equivalence relation matrixwereestablishedbythis method,and the information entropy under the quotient space theorywasredefined,andthen the attribute weight on the quotient setwascalculated and determined.Finally,the method is applied to a multi-objective decision-making dataset for oilfield development without decision attributes and core attributes,which verifies the scientific and feasibility of the method.

关 键 词：商空间 信息熵 属性权重 等价关系矩阵 

分 类 号：O29[理学—应用数学]