Abstract: Personal recommendation is a crucial implementation to solve the problem of information overloading on the Internet. On the basis of researching personal recommendation skills and corresponding technologies, an application-driven personal recommendation algorithm in multidimensional and weighted social network was proposed. First, this algorithm built multidimensional and weighted social network between users, then applied the complex network clustering method—CPM (Clique Percolation Method) to find neighbor users, finally made recommendation on the grounds of the similarity between users. The experimental results show that the recommendation system of multidimensional network applying this algorithm can achieve higher recall and precision compared to content-based and collaborative filtering recommendation systems, and the quality of personal recommendation has been improved to some extent.

Key words: personal recommendation, social network, weight, complex network, CPM (Clique Percolation Method) clustering

摘要： 个性化推荐是解决Internet中信息过载的重要工具，在研究有关个性化推荐的技术和相关动态的基础上，以用户实际应用为驱动，提出一种多维加权社会网络中的个性化推荐算法。首先，该算法构建了用户之间的多维加权网络；然后利用复杂网络的聚类方法——CPM算法寻找邻居用户；最后基于用户之间的相似性做出推荐。实验结果表明，应用该算法的多维网络的推荐系统与基于内容推荐系统和协同过滤推荐系统相比，有较高的查全率和准确率，个性化推荐质量有了一定程度的提高。

关键词: 个性化推荐, 社会网络, 权重, 复杂网络, CPM聚类