基于智能多agent的推荐系统-计算机系统应用.PDFVIP

2010 年 第 19卷 第 2 期 计 算 机 系 统 应 用 ① 基于智能多agent 的推荐系统 王卫平 赵 明 刘迎意 王 选 ( 中国科学技术大学 管理学院 安徽 合肥 230026) 摘 要： 针对传统推荐系统存在的用户评分稀疏性和系统扩展性问题，提出了一种基于智能多 agent 的推荐 系统 MASRS。首先采用余弦公式处理用户-项评分矩阵得到用户初始邻居集；然后将用户评分映射 到相应项的属性值上，生成用户-属性值偏好矩阵 UPm，并基于此矩阵进行用户相似性度量，得到用 户产品推荐集，该方法有效缓解用户评分稀疏性问题；通过智能多 agent 架构推荐系统，使大量复 杂计算在线下进行，从而改善系统存在的扩展性问题。同时实验表明新系统在推荐精度上收敛性更好。 关键词： 推荐系统；稀疏性；用户—属性值偏好矩阵；智能多agent A Recommendation System Based on Intelligence Multi -Agent WANG Wei-Ping, ZHAO Ming, LIU Ying-Yi, WANG Xuan (School of Management, University of Science and Technology of China, Hefei 230026, China) Abstract : Traditional recommendation system has the problem of sparse user ratings and system scalability. This paper proposes a recommendation system based on intelligence multi -agent. At first, the cosine similarity measure has been used to handle user -item rating matrix, thus the initial neighbor set for target users can be gained. Then, user ratings have been mapped to relevant item attributes for generating user -attributes value preference matrix UPm of each user. Thus, user similarity can be computed based on UPm and rating sparsity has been alleviated simultaneously. The recommendation system of intelligence multi-agent makes calculating an online processing, and thus improves the system scalability. Experimental results show that the new system achieves a better accuracy in recommended convergence. Keywords: recommendation system; sparsity; user-attributes value preference matrix; intelligence multi-agent