摘要
传统的协同过滤推荐算法未充分考虑时间因素的影响。基于人的记忆遗忘特性和记忆激活特性,提出基于时间上下文的个性化电影推荐算法HMC-CF。根据记忆遗忘特性,得到基于用户群的评分预测,根据记忆激活特性得到基于产品群的评分预测,融合记忆遗忘和记忆激活两种评分预测方式,得到混合后的综合评分预测。通过对比实验,表明基于时间上下文的推荐算法在推荐准确率、覆盖率上更具优势。
The traditional collaborative filtering recommendation algorithm does not fully consider the influence of time.Based on the characteristics of human memory forgetting and memory activation,a personalized movie recommendation algorithm HMC-CF based on temporal context is proposed.According to the characteristics of memory forgetting,score prediction based on user group is obtained.According to the characteristics of memory activation,the score prediction based on product group is obtained.Combining memory forgetting and memory activation,the comprehensive score prediction is obtained.Through comparative experiments,the results show that the recommendation algorithm based on time context has more advantages in recommendation accuracy and coverage.
作者
张正风
唐敏
李清秀
ZHANG Zheng-feng;TANG Min;LI Qing-xiu(Graphic Information Center,Xuzhou Bioengineering Technical College,Xuzhou Jiangsu 221006,China)
基金
2020年度徐州市社会科学研究立项课题(20XSS-057)
徐州生物工程职业技术学院2018年校级科技计划项目“学院内网资源导航系统的设计与开发”。
关键词
协同过滤推荐
HMC-CF
艾宾浩斯遗忘曲线
时间上下文
collaborative filtering recommendation algorithm
HMC-CF
Ebbinghaus forgetting curve
time contect
