摘要
传统的协同过滤推荐算法面临严峻的数据稀疏性和推荐实时性困境,推荐质量明显不高.为提高推荐效果,首先对基于云模型的用户评分项和相似性度量方法展开研究.然后定义基于云模型的推荐系统信任约束,并改进主观信任云模型的约束函数、信任变化云模型的信任变化函数.最后提出一种基于云模型的协同过滤推荐算法.实验结果表明,相比传统算法,该算法在用户评分数据稀疏的状况下仍然可以取得良好的推荐效果,具有较高的实用价值.
The traditional collaborative filtering recommendation algorithms face the dilemma of severe data sparsity and real time of recommendation, their recommendation quality is not obviously high. To improve recommendation efficiency, firstly, user rating items and similarity measurement method based on cloud model were researched. Then the definition of recommendation system trust constraint based on cloud model was given, and improved the constraint function of subjective trust cloud model and trust change function of trust change cloud model. Finally, a collaborative filtering recommendation algorithm based on cloud model was put forword. The experimental results show that the algorithm still obtains good recommendation efficiency on situation of user rating data sparsity compared to the traditional algorithms, it has high utility.
出处
《计算机系统应用》
2015年第5期140-146,共7页
Computer Systems & Applications
关键词
云模型
相似性度量
约束函数
信任变化函数
协同过滤推荐
cloud model
similarity measure
constraint function
trust change function
collaborative filteringrecommendation
