Aggregating metasearch engine results based on maximal entropy OWA operator  

基于极大熵OWA算子的元搜索引擎搜索结果集成(英文)

作　　者：桑秀芝[1] 刘新旺[1] 

机构地区：[1]东南大学经济管理学院,南京211189

出　　处：《Journal of Southeast University(English Edition)》2013年第2期139-144,共6页东南大学学报（英文版）

基　　金：The National Natural Science Foundation of China(No.71171048)

摘　　要：The maximal entropy ordered weighted averaging （ME-OWA） operator is used to aggregate metasearch engine results, and its newly analytical solution is also applied. Within the current context of the OWA operator, the methods for aggregating metasearch engine results are divided into two kinds. One has a unique solution, and the other has multiple solutions. The proposed method not only has crisp weights, but also provides multiple aggregation results for decision makers to choose from. In order to prove the application of the ME-OWA operator method, under the context of aggregating metasearch engine results, an example is given, which shows the results obtained by the ME-OWA operator method and the minimax linear programming （ minimax-LP ） method. Comparison between these two methods are also made. The results show that the ME-OWA operator has nearly the same aggregation results as those of the minimax-LP method.将极大熵有序加权平均(ME-OWA)算子应用于元搜索引擎搜索结果的集成,并使用最新的极大熵有序加权平均算子的解析算法求解集成结果.在现有的加权有序集成算子(OWA)环境下,把用于集成元搜索引擎搜索结果的方法分为2类:有唯一解和多解信息集成方法.所提出的极大熵有序加权平均算子不仅可以得到精确的权重值,还能为决策者提供多种集成结果供选择.为了证明此集成算子的实用性,在集成元搜索引擎搜索结果的应用背景下,用极大熵有序加权平均算子和极小极大线性规划算法进行求解,并对2种方法的运算结果加以比较和讨论.结果显示,极大熵有序加权平均算子具有和极小极大线性规划算法几乎一样的结果.

关 键 词：maximal entropy ordered weighted averagingoperator minimax linear programming metasearch engine information aggregation 

分 类 号：C934[经济管理—管理学]