ISSN 1000-1239 CN 11-1777/TP

计算机研究与发展 ›› 2018, Vol. 55 ›› Issue (3): 613-628.doi: 10.7544/issn1000-1239.2018.20160521

• 人工智能 • 上一篇    下一篇

基于组合历史的交互式服务推荐方法

潘伟丰1,姜波1,李兵2,胡博3,宋贝贝1   

  1. 1(浙江工商大学计算机与信息工程学院 杭州 310018); 2(武汉大学计算机学院 武汉 430072); 3(金蝶国际软件集团金蝶研究院 广东深圳 518057) (wfpan1982@163.com)
  • 出版日期: 2018-03-01
  • 基金资助: 
    国家自然科学基金项目(61202048,61273216,61402406);浙江省自然科学基金项目(LY15F020004)

Interactive Service Recommendation Based on Composition History

Pan Weifeng1, Jiang Bo1, Li Bing2, Hu Bo3, Song Beibei1   

  1. 1(School of Computer and Information Engineering, Zhejiang Gongshang University, Hangzhou 310018); 2(School of Computer Science, Wuhan University, Wuhan 430072); 3(Kingdee Research, Kingdee International Software Group Co. Ltd, Shenzhen, Guangdong 518057)
  • Online: 2018-03-01

摘要: 随着服务种类和数量的飞速增长,如何发现满足用户需求的服务成为亟待解决的关键问题之一.服务推荐技术被认为是解决服务资源过载问题的有效方法之一.但是,现有的服务推荐方法存在数据难以获取和未考虑所推荐服务的可用性及与已有服务的可组合性等问题.有鉴于此,提出了一种基于服务组合历史的交互式服务推荐方法.该方法使用隶属网抽象服务组合历史(复合服务、原子服务及他们之间的隶属关系),通过单模投影获取服务间的组合关系,并利用骨干网挖掘过滤无效的服务组合关系;使用度和度分布分析服务的使用模式;考虑服务的失效问题,并根据服务的不同使用场景提出了相应的服务推荐算法.最后,使用ProgrammableWeb网站提供的真实服务数据验证了所提方法的正确性和有效性.

关键词: 服务推荐, 服务网络, 骨干网挖掘, k-核分解, 复杂网络

Abstract: With the rapid increasing number of services and their types, how to discover the composible services which can meet uer’s requirements is one of the key issues that need to be resolved. Service recommendation technique has become one of the effective methods to deal with the problem of service resource overload. However, the existing service recommendation techniques usually ultilize service data which are hard to be collected and they also neglect the usability and composiblity of the services to be recommended. To avoid these limitations, this paper, utilizing service composition histories, introduces the theory and methodology in the complex network research and proposes an interactive service recommendation approach. It uses an affiliation network to abstract service composition histories (i.e., composite services, atomic services, and the affiliation relationships between them), obtains the service composition relationships by one-mode projection, and introduces the backbone network extraction technology to filter out the invalid compostion relationships; it uses degree and degree distribution to mine the service usage patterns; it takes into account the situation of the failure of services and finally proposes several algorithms for service recommendation according to three usage scenarios. Real data of services crawed from ProgrammableWeb are used as subjects to demonstrate the correctness and feasibility of the proposed approach.

Key words: service recommendation, service network, backbone network extraction, k-core decomposition, complex network

中图分类号: