• 中国计算机学会会刊
  • 中国科技核心期刊
  • 中文核心期刊

J4 ›› 2010, Vol. 32 ›› Issue (9): 119-121.doi: 10.3969/j.issn.1007130X.2010.

• 论文 • 上一篇    下一篇

基于本体的任务和知识个体匹配模型研究

刘景方1,邹平1,张朋柱2   

  1. (1.昆明理工大学管理与经济学院,云南 昆明 650093;2.上海交通大学安泰经济与管理学院,上海 200052)
  • 收稿日期:2010-03-13 修回日期:2010-06-10 出版日期:2010-09-02 发布日期:2010-09-02
  • 作者简介:刘景方(1980),男,山东青州人,博士生,研究方向为语义Web、本体论和知识管理;邹平,教授,博士生导师,研究方向为知识管理;张朋柱,教授,博士生导师,研究方向为电子政务和群决策支持系统。
  • 基金资助:

    国家自然科学基金重点资助项目(70533030);国家自然科学基金资助项目(70471085)

Research on the Matching Model Between Tasks and Knowledge Individuals Based on Ontology

LIU Jingfang1,ZOU Ping1,ZHANG Pengzhu2   

  1.  (1.School of Management and Economics,Kunming University of Science and Technology,Kunming 650093;
    2.Antai School of Economics and Management,Shanghai Jiaotong University,Shanghai 200052,China)
  • Received:2010-03-13 Revised:2010-06-10 Online:2010-09-02 Published:2010-09-02

摘要:

为实现在知识产品在线定制过程中任务和知识个体的有效匹配,鉴于传统的基于关键词的匹配技术忽略语义信息的缺点,本文提出了一个基于本体的任务和知识个体匹配模型。首先提出了一种综合改进的概念语义相似度计算方法用以提高概念间的语义相似度计算的准确性,然后将任务信息和知识个体的信息分别抽象为任务概念向量和能力概念向量,通过计算两个概念向量之间的语义相似度,得到任务和知识个体的匹配结果。实验结果表明,该模型具有较高的准确率和召回率,能够为知识产品在线定制提供有效的匹配服务。

关键词: 务, 知识个体, 匹配

Abstract:

To achieve effective matching between tasks and knowledge individuals during the online knowledgebased products customization, and taking the lack of semantic information in the traditional technique based on the keywords into account, the paper presents a model of task and knowledge individual matching based on ontology. Firstly it presents a comprehensive improved method of concept semantics similarity computing to improve accuracy in the concept semantics similarity computation, and then abstracts the task and knowledge individual’s information to be the task concept vector and skill concept vector, and gets the matching result of tasks and knowledge individuals by computing the semantic similarity between double concept vectors. The testing result shows that the model can obtain high precision and recall rates, and can provide effective matching services during the online knowledgebased product customization.

Key words: task;knowledge individual;matching