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 ›› 2019, Vol. 45 ›› Issue (2): 310-314. doi: 10.19678/j.issn.1000-3428.0049091

• 开发研究与工程应用 • 上一篇    下一篇

面向智慧社区基于可信联盟的服务推荐算法

付蔚,杜亮,张开碧,潘光吉   

  1. 重庆邮电大学 自动化学院,重庆 400065
  • 收稿日期:2017-10-27 出版日期:2019-02-15 发布日期:2019-02-15
  • 作者简介:付蔚(1981—),女,副教授,主研方向为智慧社区、无线传感网;杜亮,硕士研究生;张开碧,副教授;潘光吉,硕士研究生。
  • 基金资助:

    重庆市基础科学与前沿技术研究专项“基于家居物联网的变量安全操作协议的研究与设计”(cstc2016jcyjA2069);重庆市社会事业与民生保障科技创新专项“智慧城市关键技术研究及示范应用”(cstc2017shmsA0841)。

Service Recommendation Algorithm Based on Trusted Alliance for Intelligent Community

FU Wei,DU Liang,ZHANG Kaibi,PAN Guangji   

  1. College of Automation,Chongqing University of Posts and Telecommunications,Chongqing 400065,China
  • Received:2017-10-27 Online:2019-02-15 Published:2019-02-15

摘要:

针对现有推荐算法同等看待每个用户评价信息的问题,提出一种面向智慧社区的基于可信联盟的服务推荐算法。引入用户的信誉度和服务使用频率,改进传统相似度计算公式,建立基于用户信任模型的信任关系。在此基础上,面向智慧社区用户,引入社区因子,构建可信联盟,从而对目标用户进行个性化推荐。实验结果表明,与基于云模型的链式推荐等算法相比,该推荐算法的精确度更优。

关键词: 智慧社区, 服务推荐, 可信联盟, 社区因子, 协同过滤

Abstract:

Aiming at the problem that the existing recommendation algorithms treat each user’s evaluation information equally,a service recommendation algorithm based on trusted alliance for intelligent community is proposed.By introducing user reputation and service usage frequency,the traditional similarity calculation formula is improved,and the trust relationship based on user trust model is established.On this basis,the community factor is introduced and the trusted alliance is constructed for the intelligent community users,and then the personalized recommendation for the target users is carried out.Experimental results show that the accuracy of the proposed algorithm is better than that of the chain recommendation algorithm based on cloud model.

Key words: intelligent community, service recommendation, trusted alliance, community factor, collaborative filtering

中图分类号: