节点文献

基于本体的中医古籍叙词表构建方法研究

The Research on the Method of Ontology-based Construction of the Thesaurus of Traditional Chinese Medicine Classics

【作者】 杨继红

【导师】 柳长华;

【作者基本信息】 中国中医科学院 , 中医医史文献, 2008, 博士

【摘要】 中医古籍历史悠久,卷帙浩繁,在过去二十多年里,中医古籍整理研究工作已经逐渐由传统的手工整理方式向数字化资源建设的方向转变,在吸收传统古籍整理成果的基础上,中医古籍数字化较好地解决了古籍的保存和利用之间的矛盾,尤其是中医古籍全文数据库、古籍知识库的发展,对检索和利用古籍中的内容提高了显著的效率和方便。但由于中医古籍知识库中的信息资源缺少统一的语义机制的描述,计算机程序不能正确理解其含义,用户难以更加准确、快速的查找到需要的资源,因此,中医古籍知识库亟待寻找一种有利的语义管理工具,以真正实现中医古籍知识库的知识发现与知识重用。基于本体的中医古籍叙词表的构建为解决这一问题提供了比较有效的途径。本文在调研了中医古籍信息资源组织方式的基础上,系统分析了知识的组织体系及表示方法,阐述了叙词表、本体的基础理论和研究进展,在柳长华教授提出的基于“知识元”的中医古籍计算机知识表示方法建设的中医古籍知识库的工作基础上,充分利用中医传统知识保护课题组有关中医传统知识分类的研究成果,借鉴本体论的思想,采用自上而下的方法编制了适合知识库建设的中医古籍分类表和古籍概念关系体系,做为分类主题一体化中医古籍叙词表的基础。然后再用自下而上的方法,断代选取有代表性的(唐)孙思邈《备急千金要方》一书,通过中医古籍整理专家对《备急千金要方》在知识元层面的标引、解析,运用情报学、统计学、文献学、中医学、计算机与信息科学、语义学等多种理论与方法,制订概念词的抽取原则,在中医古籍知识分类表的基础上,建立《备急千金要方》的中医古籍概念词模型,深入研究方剂、中药、诊法、病证、病因、病机等知识的语义结构及语义关系,并进行了OWL的形式化表达和可视化展示,以期通过实证研究,为计算机环境下、规模巨大的中医古籍叙词表的建立提供技术支撑,为中医古籍叙词表向本体的转换奠定基础。最后,本文得出以下结论,基于本体的中医古籍叙词表,不同于以往有着严格规范的、静态的、线性的传统叙词表,而是一个介于本体与传统叙词表之间的,开放的、可扩展的、有着网状概念语义关系的、动态的自然语言叙词表。

【Abstract】 Traditional Chinese medicine has a long history and a vast collection of ancient literature.In the past 20 years,the systematization and researching of Chinese classics have been transformed gradually from the traditional manual systematization to digital resource construction.Based on the achievements of traditional systematization of ancient literature,the contradiction between the preservation and the use of ancient books has been intelligently solved by the digitalization of ancient Chinese medical classics. The development of the databases and knowledge base of traditional Chinese medicine classics have significantly promoted the efficiency and convenience of the search and the use of ancient literatures.However,because of the lack of the semantic description with a uniform mechanism in the information resources of the knowledge base of TCM classics,it is very difficult for the computer program to correctly understand the semantics,and more difficult for the users to find the resources correctly and quickly.Therefore,a kind of semantic management tools is badly needed by the knowledge base of the traditional Chinese medicine classics in order to truly achieve its knowledge discovery and knowledge reuse.The construction of the thesaurus of Traditional Chinese Medicine classics which is based on ontology provides an effective way to resolve this problem.Based on the investigation into the organization of the information resources of ancient Chinese medicine classics,this paper offers a systematic analysis of the organizational system and expression method of knowledge,and makes an exposition of the basic theory and research progress of thesaurus and ontology.By making good use of the research results of traditional knowledge classification offered by the Research Group of TCM Knowledge Protection and using the theory of ontology for reference,The classification table of TCM and the system of conception relationship are based on the computer knowledge expression method of TCM classics put forward by Prof.Liu Changhua which is based on "the knowledge element" With the top-down approach,the classification table of TCM and the system of conception relationship which are suited to the construction of knowledge base are compiled and be used as the foundation of the thesaurus of TCM classics which can provide the themes integration of classification.Then select different versions of Precious Essential Formulary for Emergency(PEFE) in different dynasties by the bottom-up approach.The principle of extraction of concept of word is made on the basis of the indexing and analysis in the level of knowledge element made by finishing (systematization)experts on ancient classics of TCM,and by using theories and methods of information science,statistics,philology,TCM,computer and information science and semantics,etc.,to establish the model of concept of the word for Precious Essential Formulary for Emergency(PEFE) on the foundation of the knowledge classification table of ancient classics of TCM.An in-depth study of the semantic structure and relationships of the knowledge of formulary, Chinese herbs,consultation,syndrome,etiology and pathogenesis and formal expression and visualization of the display of OWL are needed in order to provide technical supports for the construction of the huge thesaurus under computer supported environment,and offer the foundation for the transformation from thesaurus to ontology.Finally,this paper draws the conclusion:the thesaurus of TCM classics which is based on ontology differs from the strict standard,static,and linear traditional ones.It is the thesaurus between ontology and traditional ones, which is open,scalable,and dynamic natural language with mesh semantic relations.

  • 【分类号】R-5;R2-03
  • 【被引频次】10
  • 【下载频次】813
节点文献中: 

本文链接的文献网络图示:

本文的引文网络