互联网 qkzz.net
全刊杂志网:首页 > 女性 > 文章正文
刊社推荐

基于用户与服务协同聚类的Web服务发现研究


摘 要:如何从大规模服务集合中快速而准确地发现目标服务是应用Web服务技术的关键。针对现有研究方法主要集中在基于语义的Web服务发现上,其实施难度大且适用性不强,提出一种基于服务日志挖掘的服务发现方法。该方法通过对用户与服务进行协同聚类,缩小查询空间,从而提高发现效率。仿真实验表明,其在召回率与准确率上比基于关键字的匹配算法都有不同程度的改善,且该方法能极大地满足服务执行时动态绑定的特性。
  关键词:服务匹配; 服务发现; 协同聚类; 服务挖掘
  中图分类号:TP391文献标志码:A
  文章编号:1001-3695(2010)03-0986-03
  doi:10.3969/j.issn.10013695.2010.03.048
  Research of services discovery based on coclustering user and services
  
  ZHU Hong-kang 1,2, YU Xue-li1
  
  (1.School of Computer Science& Software Engineering, Taiyuan University of Technology, Taiyuan 030024, China; 2.School of Mathematics & Computer Science, Shanxi Normal University, Linfen Shanxi 041000, China)
  
  Abstract:How to discovery services for user efficiently is the key for application of the Web service technology. The current semanticbased service discovery methods are of great inconvenience and of little flexibility to be used. This paper proposed a novel service discovery method based on service log mining. The method used coclustering between user and services, reduced search space and improved discovery efficiency much. A serial of experiments illustrate the method not only enhances the recall rate and precision as discovery methods based on keyword, but also satisfy greatly the character of Web service execute time dynamic binding. ......
很抱歉,暂无全文,若需要阅读全文或喜欢本刊物请联系《计算机应用研究》杂志社购买。
欢迎作者提供全文,请点击编辑
分享:
 

了解更多资讯,请关注“木兰百花园”
分享:
 
精彩图文


关键字
支持中国杂志产业发展,请购买、订阅纸质杂志,欢迎杂志社提供过刊、样刊及电子版。
关于我们 | 网站声明 | 刊社管理 | 网站地图 | 联系方式 | 中图分类法 | RSS 2.0订阅 | IP查询
全刊杂志赏析网 2017