摘要
现有的适应兴趣变化的协同过滤算法不能反应用户兴趣变化的频率,对即时热点也不足够敏感。同时,因为计算量大,不适应大数据场景。为此我们采用对时间分层的推荐模型结合热点权重函数,解决了传统算法存在问题,在生产环境中具备较高的应用价值。
The existing collaborative filtering algorithms that adapt to the change of interest can not reflect the frequency of the change of user interest,and are not sensitive to real-time hot spots.At the same time,because of the large amount of calculation,it does not adapt to the big data scene.For this reason,we use the time hierarchical recommendation model combined with the hot spot weight function to solve the problems of the traditional algorithm and have high application value in the production environment.
作者
冀晓亮
翁玉玲
JI Xiaoliang;WENG Yuling
出处
《科技创新与应用》
2020年第20期14-16,共3页
Technology Innovation and Application
关键词
个性化推荐
协同过滤
推荐算法
兴趣变化
大数据推荐系统
相似度计算
personalized recommendation
collaborative filtering
recommendation algorithm
interest change
big data recommendation system
similarity calculation
