Computer Engineering and Applications ›› 2011, Vol. 47 ›› Issue (6): 223-224.

• 工程与应用 • Previous Articles     Next Articles

Research of similarity in recommender system based on dependent function

CUI Chunsheng1,2,WU Qizong1   

  1. 1.School of Management and Economics,Beijing Institute of Technology,Beijing 100081,China
    2.School of Computer,Henan University of Economics and Law,Zhengzhou 450046,China

  • Received:1900-01-01 Revised:1900-01-01 Online:2011-02-21 Published:2011-02-21

基于关联函数的推荐系统相似性研究

崔春生1,2,吴祈宗1   

  1. 1.北京理工大学 管理与经济学院,北京 100081
    2.河南财经政法大学 计算机学院,郑州 450046

Abstract: The similarity measure in recommender system of electric commerce is studied.Based on the dependent function,the definition of “distance” is introduced.Meanwhile,with the insurance of the similarity’s nature and based on the theory of vague sets,a new similarity measure method is gotten.The method satisfies the need of similarity measure in recommender system,and the resultant is in line with people’s perceptual.So the method not only offers a new idea to recommender system,but also introduces a wide range of theoretical foundation in this field.

Key words: recommender system, vague sets, similarity measure, dependent function

摘要: 针对电子商务推荐系统中相似性的计算,借助关联函数,通过点与区间“距”的引入,在相似度性质的各个性质的保证下,运用vague集理论,构建了一种新的相似性度量公式。一方面满足了推荐系统对相似性计算的要求,另一方面使结果更加符合人们的感性认识,不仅为推荐系统的研究提供了一种新的思路、也为这一领域的研究引入了更为广泛的理论基础。

关键词: 推荐系统, vague集, 相似性, 关联函数