作者投稿和查稿 主编审稿 专家审稿 编委审稿 远程编辑

计算机工程 ›› 2011, Vol. 37 ›› Issue (7): 187-189,192. doi: 10.3969/j.issn.1000-3428.2011.07.063

• 人工智能及识别技术 • 上一篇    下一篇

基于神经网络的用户兴趣度估计

刘 建1,2,孙 鹏2,倪 宏2   

  1. (1. 中国科学院研究生院,北京 100190;2. 中国科学院声学研究所国家网络新媒体工程技术研究中心,北京 100190)
  • 出版日期:2011-04-05 发布日期:2011-03-31
  • 作者简介:刘 建(1982-),男,博士研究生,主研方向:网络通信,网络新媒体;孙 鹏,副研究员;倪 宏,研究员、博士生导师
  • 基金资助:
    国家科技支撑计划基金资助项目(2008BAH28B04)

Estimation of User Interest Degree Based on Neural Network

LIU Jian  1,2, SUN Peng  2, NI Hong  2   

  1. (1. Graduate University of Chinese Academy of Sciences, Beijing 100190, China; 2. National Network New Media Engineering Research Center, Institute of Acoustics, Chinese Academy of Sciences, Beijing 100190, China)
  • Online:2011-04-05 Published:2011-03-31

摘要: 针对个性化服务研究中用户兴趣度估计的要求,分析用户行为特征与兴趣度的相互关系,选取页面关注时间、滚动/翻页次数、页面大小作为用户兴趣度的判别依据,提出一种基于RBF神经网络模型的用户兴趣度量化估计方法。仿真实验证明,与多元线性回归模型的计算结果相比,该方法在平均残差和预测准确度方面均有更好的效果。

关键词: 个性化服务, 用户兴趣度, RBF神经网络

Abstract: The Aiming at the requirements for estimating the user interest degree in the personalization services researching, this paper analyzes the relationship between the characteristics of user’s behavior and the interest degree and selects the page-concerned time, number of page rolling and page size as the implicit indicators, then proposes a method based on RBF neural network to quantitatively estimate the user interest degree. Experimental results show that compared with the multiple linear regression model, this method achieves better results both on the average residuals and the predicting accuracy.

Key words: personalization service, user interest degree, RBF neural network

中图分类号: