摘要
协同过滤是个性化推荐系统中采用最广泛的推荐技术,但已有的方法是将用户不同时间的兴趣等同考虑,时效性不足。针对此问题,提出了一种改进的协同过滤算法,使得越接近采集时间的点击兴趣,在推荐过程中具有更大的权值,从而提高了推荐的准确性。
Collaborative filtering is the most widely used recommendation technology in the personalized recommendation system. However, the user＇s interests in different time have been taken into equal consideration with the method being used, which leads to the lack of effectiveness in the given period of time. In view of this problem, this paper presented an improved collaborative fihering algorithm to make the click interests, approaching the gathering time, have bigger weight in the recommendation process, thereby to improve the accuracy of the recommendation.
出处
《计算机应用》
CSCD
北大核心
2007年第9期2302-2303,2326,共3页
journal of Computer Applications
基金
河南省高校杰出科研人才创新基金资助项目(2006KYCX004)
河南省青年骨干教师基金资助项目(134)
关键词
协同过滤
个性化推荐
邻居用户
时间权值
collaborative filtering
individual recommendation
neighbor user
time weight
