关键词: 隐式反馈, 分布式模型, 兴趣模型, IPTV

Abstract: According to the implicit characteristics of IPTV user viewing behavior data, a novel implicit rating model is proposed in this paper. Firstly, in this paper, the main features of IPTV user viewing behavior data are introduced, and a new mixed feature implicit scoring model is proposed, which combines viewing ratio, user interest bias factors and video type influence factors. Secondly, the strategy of screening behavior based on viewing time and viewing ratio is proposed. Thirdly, a distributed model architecture based on Hadoop is designed and implemented. Finally, the experimental results show that this novel model effectively improves the quality of the recommended results in the IPTV system, improves the time efficiency, and has good scalability for large amounts of data.

Key words: Implicit feedback, Distributed model, Interest model, IPTV