• 中国计算机学会会刊
  • 中国科技核心期刊
  • 中文核心期刊

计算机工程与科学

• 高性能计算 • 上一篇    下一篇

商品搭配大数据推荐方法研究综述

陈鑫1,王斌1,曾范清2   

  1. (1.南京财经大学信息工程学院,江苏 南京 210023; 2.南京财经大学经济管理实验教学中心,江苏 南京 210023)
  • 收稿日期:2019-05-24 修回日期:2019-07-12 出版日期:2020-01-25 发布日期:2020-01-25
  • 基金资助:

    国家自然科学基金(61372158);江苏省高校优秀科技创新团队项目(2017-15);江苏省高校哲学社会科学研究一般项目(2019);江苏省研究生科研与实践创新计划项目(KYCX18_1389)

Reviewing big data recommendation
methods of commodity collocation

CHEN Xin1,WANG Bin1,ZENG Fan-qing2   

  1. (1.School of Information Engineering,Nanjing University of Finance and Economics,Nanjing 210023;
    2.Experimental Teaching Center of Economics & Management,Nanjing University of Finance and Economics,Nanjing 210023,China)
     
  • Received:2019-05-24 Revised:2019-07-12 Online:2020-01-25 Published:2020-01-25

摘要:

随着电子商务的不断发展,推荐系统面临着数据来源多样、结构复杂、推荐多样性差、冷启动等问题。商品搭配大数据推荐方法不仅可以有效解决以上问题,还具有给予消费者搭配建议并帮助商家促进销售的重要意义。首先,通过对国内外相关文献进行梳理,阐述了搭配推荐方法的基本概念和形式,分析其与传统推荐方法的区别以及优势。然后,探讨了搭配推荐方法的分类,包括基于商品内容的搭配推荐、基于协同过滤的搭配推荐和混合搭配推荐。最后,在这些研究和分析的基础上,指出了未来的研究热点将聚焦于多个商品的搭配推荐、基于多源异构数据融合的搭配推荐和基于知识图谱的搭配推荐。特别是将知识图谱应用于搭配推荐领域,将是未来非常有前景的研究工作。
 

关键词: 推荐系统, 商品搭配, 多源异构, 冷启动, 知识图谱

Abstract:

With the continuous development of e-commerce, recommender systems are facing problems such as diverse data sources, complex data structure, poor recommendation diversity and cold start. The big data recommendation methods of commodity collocation can not only solve the above problems effectively, but also have the important significance of giving suggestions to consumers and helping businesses to promote sales. Firstly, through reviewing the relevant domestic and foreign literatures, the paper explains the basic conception and form of collocation recommendation methods, and analyzes their differences and advantages compared with the traditional recommendation methods. Then, the classification of collocation recommendation methods is discussed, including collocation recommendation based on commodity content, collocation recommendation based on collaborative filtering, and hybrid collocation recommendation. Finally, based on the aforementioned research and analysis, it is pointed out that the future research hotspots will focus on the collocation recommendation of multiple commodities, collocation recommendation based on multi-source heterogeneous data fusion, and collocation recommendation based on knowledge graph. In particular, applying knowledge graph to collocation recommendation field will be a very promising research work in the future.
 

Key words: recommender system, commodity collocation, multi-source heterogeneous, cold start, knowledge graph