计算机工程与应用 ›› 2017, Vol. 53 ›› Issue (10): 79-84.DOI: 10.3778/j.issn.1002-8331.1602-0049

• 大数据与云计算 • 上一篇    下一篇

Spark平台下基于上下文信息的影片混合推荐

缪雪峰1,陈群辉1,胡罗凯2,刘  进1   

  1. 1.武汉大学 计算机学院 软件工程国家重点实验室,武汉 430070
    2.湖北第二师范学院 计算机学院,武汉 430070
  • 出版日期:2017-05-15 发布日期:2017-05-31

Context-aware movie hybrid recommendation on Spark platform

MIAO Xuefeng1, CHEN Qunhui1, HU Luokai2, LIU Jin1   

  1. 1.State Key Laboratory of Software Engineering, Computer School, Wuhan University, Wuhan 430070, China
    2.College of Computer, Hubei University of Education, Wuhan 430070, China
  • Online:2017-05-15 Published:2017-05-31

摘要: 响应速度较慢和推荐内容与用户上下文信息匹配程度低是当前影片推荐系统迫切需要解决的问题。针对上述挑战,提出Spark平台下基于上下文信息的影片混合推荐方法。它利用分布式并行计算技术Spark进行加速,来提高系统对于海量数据的检索与计算速度,从而减少了系统响应时间。同时该方法将“上下文推荐”和“交替最小二乘的协同过滤(ALS)”融合成一种混合推荐方法,提高了系统的推荐精度。实验结果表明,所提出的混合推荐方法有不错的效果。

关键词: 影片推荐系统, Spark平台, 上下文信息, 混合推荐

Abstract: Slow response and recommended movies inconsistent with the users’ requests are key urgent problems in current movie recommendation system. To address this problem, a context-aware movie hybrid recommendation method on Spark platform is proposed. The method takes advantage of Spark, a distributed parallel computing technology, to improve retrieval and calculation speed for mass data, which reduces the response time of the recommendation system. At the same time, it fuses the user’s context information and ALS(Alternating Least Squares of collaborative filtering) to a hybrid recommendation method, which improves the recommendation accuracy of system. The results show that our method has a better performance than others.

Key words: movie recommendation system, Spark platform, context aware, hybrid recommendation