基于本体的数字图书馆检索模型研究（Ⅳ）——历史领域知识推理机制  

Research On Ontology-based Retrieval Model of Digital Library（Ⅳ ） --Inference Mechanism of History Domain Knowledge

作　　者：董慧[1] 余传明[1] 徐国虎[1] 姜赢[1] 敖青[1] 陈亮[1] 王国育[1] 夏阳[1] 

机构地区：[1]武汉大学信息资源研究中心,武汉430072

出　　处：《情报学报》2006年第6期666-678,共13页Journal of the China Society for Scientific and Technical Information

基　　金：本文属国家自然科学基金资助项目（批准号：70373047）.

摘　　要：基于本体的领域知识推理主要分为基于逻辑的领域知识检错推理和基于关系的领域蕴涵知识发现推理。对本体描述的领域知识进行推理，可以检测知识逻辑体系错误，减少领域本体构建繁琐的工作量，减轻对领域专家的依赖，发现领域蕴涵知识。在国共合作领域知识进行语义关系分析的基础上，提炼推理规则库，并分别运用TABLEAU算法和RETE模式匹配算法，在推理引擎Racer和Jena中实现了逻辑检错推理和蕴涵知识发现推理。In our opinion, ontology-based domain knowledge inference includes logic error-check inference and domain deductive knowledge detection reasoning. Inferences on ontology-based domain knowledge can help us check out the mistakes and flaws in the knowledge logic system, reduce fussy workload of ontology buildings, lessen our dependence on the domain experts and represent deductive domain knowledge. Based on the analysis of the semantic relations in the GGHZ domain knowledge, we developed an inference rules base （including 107 static rules and dynamic rules）, and based our inferences on TABLEAU arithmetic and RETE arithmetic, then implemented logic error-check inferences and deductive knowledge detection reasoning through two reasoning engines of Racer and Jena.

关 键 词：知识推理 领域本体 推理规则 推理引擎 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]