论文部分内容阅读
一个视频网站不断发展,视频数会不断增加,部分视频由于存放时间长而被新添加的视频埋没,但这些旧视频也可能是用户感兴趣的。为了解决这些问题,个性化推荐系统应运而生。个性化推荐系统是建立在用户海量历史浏览数据上,挖掘出视频关联,以帮助视频网站为其用户提供个性化服务的视频推荐。本文针对视频播放具有观看时长的特点,讨论一种通过观看视频的时长来自动对节目评分,并利用相似度算法完成个性化推荐的方法。
As a video site continues to evolve, the number of videos will continue to increase, some videos will be buried in newly added videos due to their long storage life, but these old videos may also be of interest to users. In order to solve these problems, personalized recommendation system came into being. Personalized recommendation system is based on the user massive historical browsing data, dig out the video link to help video sites to provide personalized video services to their users. In this paper, we focus on the characteristics of video playback with viewing time and discuss a method of automatically grading the program by watching the video duration and using the similarity algorithm to complete the personalized recommendation.