《计算机应用》唯一官方网站 ›› 2021, Vol. 41 ›› Issue (11): 3171-3177.DOI: 10.11772/j.issn.1001-9081.2021010047

• 人工智能 • 上一篇    下一篇

基于胶囊网络的交互式网络电视视频点播推荐模型

高铭蔚, 桑楠, 杨茂林()   

  1. 电子科技大学 信息与软件工程学院,成都 610054
  • 收稿日期:2021-01-12 修回日期:2021-04-22 接受日期:2021-04-29 发布日期:2021-05-07 出版日期:2021-11-10
  • 通讯作者: 杨茂林
  • 作者简介:高铭蔚(1996—),男,河南南阳人,硕士研究生,主要研究方向:推荐系统、深度学习
    桑楠(1964—),男,四川营山人,教授,硕 士,主要研究方向:嵌入式系统、软件工程
    杨茂林(1987—),男,四川江安人,助理研究员,博士,主要研究方向:嵌入式实时系统。

IPTV video-on-demand recommendation model based on capsule network

Mingwei GAO, Nan SANG, Maolin YANG()   

  1. School of Information and Software Engineering,University of Electronic Science and Technology of China,Chengdu Sichuan 610054,China
  • Received:2021-01-12 Revised:2021-04-22 Accepted:2021-04-29 Online:2021-05-07 Published:2021-11-10
  • Contact: Maolin YANG
  • About author:GAO Mingwei,born in 1996,M. S. candidate. His research interests include recommendation system,deep learning
    SANG Nan,born in 1964,M. S.,professor. His research interests include embedded system,software engineering
    YANG Maolin,born in 1987,Ph. D.,assistant research fellow. His research interests include embedded real-time system.

摘要:

在交互式网络电视(IPTV)应用中,家庭电视终端往往由多名家庭成员共用,现有推荐算法难以从终端历史数据中分析出家庭成员的不同兴趣偏好。为了满足同一终端下不同成员的视频点播需求,提出了一种基于胶囊网络的IPTV视频点播推荐模型CapIPTV。首先,设计了一种基于胶囊网络路由机制的用户兴趣生成层,将终端历史行为数据作为输入,并通过胶囊网络的聚类特性得到不同家庭成员的兴趣表达;其次,利用注意力机制给不同的兴趣表达动态分配注意力权重;最后,提取出不同家庭成员的兴趣向量和点播视频的表示向量,计算两者内积后得出Top-N偏好推荐。在公开数据集MovieLens和真实广电数据集IPTV上的实验结果表明,CapIPTV的命中率(HR)、召回率(Recall)和归一化折损累计增益(DNCG)优于其他五种同类推荐模型。

关键词: 推荐系统, 交互式网络电视, 胶囊网络, 动态路由, 注意力机制

Abstract:

In Internet Protocol Television (IPTV) applications, a television terminal is usually shared by several family members. The exiting recommendation algorithms are difficult to analyze the different interests and preferences of family members from the historical data of terminal. In order to meet the video-on-demand requirements of multiple members under the same terminal, a capsule network-based IPTV video-on-demand recommendation model, namely CapIPTV, was proposed. Firstly, a user interest generation layer was designed on the basis of the capsule network routing mechanism, which took the historical behavior data of the terminal as the input, and the interest expressions of different family members were obtained through the clustering characteristic of the capsule network. Then, the attention mechanism was adopted to dynamically assign different attention weights to different interest expressions. Finally, the interest vector of different family members and the expression vector of video-on-demand were extracted, and the inner product of them was calculated to obtain the Top-N preference recommendation. Experimental results based on both the public dataset MovieLens and real radio and television dataset IPTV show that, the proposed CapIPTV outperforms the other 5 similar recommendation models in terms of Hit Rate (HR), Recall and Normalized Discounted Cumulative Gain (NDCG).

Key words: recommender system, Internet Protocol Television (IPTV), capsule network, dynamic routing, attention mechanism

中图分类号: