基于用户偏好的多媒体视频个性化智能推荐方法研究  

Research on personalized intelligent recommendation method for multimedia video based on user preferences

作　　者：董雯[1] 曹奕萱[1] 于小婷[1] DONG Wen;CAO Yixuan;YU Xiaoting(Modern College of Northwest University,Xi’an 710130,China)

机构地区：[1]西北大学现代学院,陕西西安710130

出　　处：《电子设计工程》2024年第11期192-195,共4页Electronic Design Engineering

摘　　要：为了满足用户个性化需求,提出基于用户偏好的多媒体视频个性化智能推荐方法。采集用户历史浏览行为数据,对提取的视频特征向量作相似度计算,生成视频候选集,建立视频浏览兴趣点(PoI)关联图,根据用户浏览时间计算其对不同类别视频PoI的兴趣偏好度,选择排名靠前的N个视频生成推荐列表,实现多媒体视频个性化智能推荐。实验结果表明,该方法可实现多媒体视频个性化推荐,当其维度为180时,视频推荐的Top-1指标最高;兴趣吻合度指标均值达到94.9%,Top-1均值为95.51%。In order to meet the individual needs of users,a personalized intelligent recommendation method of multimedia video based on user preference is proposed.The user’s historical browsing behavior data is collected,the extracted video feature vector is used for similarity calculation,video candidate set is generated,video browsing Point of Interest(PoI)association graph is established,and then the user’s interest and preference for different categories of video PoI are calculated according to the browsing time,and the top N videos are selected to generate a recommendation list to achieve personalized intelligent recommendation of multimedia videos.The experimental results show that this method can realize personalized recommendation of multimedia video.When dimension is 180,the Top-1 index of video recommendation is the highest.The average of interest coincidence index was 94.9%,and the average of Top-1 was 95.51%.

关 键 词：用户偏好 多媒体视频 个性化推荐 词向量 兴趣点(PoI) 推荐列表 

分 类 号：TN98[电子电信—信息与通信工程]