| 摘要: |
| 伴随着无线通信技术和智能移动终端的快速发展,基于位置的服务(location-based services,简称LBS)以其移动性、实用性、随时性和个性化的特点,在军事、交通、物流等诸多领域得到了广泛的应用,成为最具发展潜力的移动增值业务之一.在一个基于位置的网络服务推荐框架的基础上,给出了一种基于位置的移动用户偏好相似度计算方法,同时证明了其满足近邻相似测度的一般性质;然后,提出一种符合社会学概念的信任值计算方法.把它们应用于基于移动用户位置的网络服务推荐过程中,从而形成了一种基于移动用户位置的网络服务推荐方法.该方法有效地提高了网络服务推荐的准确性和可靠性,同时缓解了推荐过程中可能存在的数据稀疏性以及冷启动问题.最后,通过公开的MIT数据集验证了该推荐方法的准确度和可行性. |
| 关键词: 位置服务 个性化服务 相似度 推荐系统 协同过滤 信任关系 |
| DOI：10.13328/j.cnki.jos.004561 |
| 分类号: |
| 基金项目:国家自然科学基金(60872051);北京市教育委员会共建项目 |
|
| Approach to Network Services Recommendation Based on Mobile Users' Location |
|
LIU Shu-Dong1,2, MENG Xiang-Wu1,2
|
|
1.Beijing Key Laboratory of Intelligent Telecommunications Software and Multimedia Beijing University of Posts and Telecommunication, Beijing 100876, China;2.School of the Computer Science,(Beijing University of Posts and Telecommunication), Beijing 100876, China
|
| Abstract: |
| Along with the development of wireless communication technologies and smart mobile devices, location-based services (LBS), with its characteristics of mobility, practicality, momentary and personalization, has been widely applied in military, transportation, logistics etc, and it has become one of the most potential mobile value-added services. Based on a proposed framework of location-based network services recommendation, this paper first provides an approach to compute mobile users' preferences similarity from their geographic location, and proves that it satisfies the general properties of neighbor similarity measure. Then according with the concept of trust in sociology, a new method is presented for calculating trust value. By importing them into network services recommendation process, an approach of location-based network services recommendation is proposed, which effectively improves its accuracy and reliability, and mitigates data sparsity of users' similarity matrix and cold start users problem in recommendation process. Finally the proposed algorithm is proved to be more accurate and feasible in experiments by using the public dataset MIT. |
| Key words: location-based service personalized service similarity recommender system collaborative filtering trust relationship |
