结合FCA与Jena的领域本体半自动构建方法研究

Research on domain ontology semi-automatic construction based on FCA and Jena

针对本体构建中难于发现隐含知识及本体编码效率低下等问题,提出了一种结合FCA与Je-na的领域本体半自动构建方法。该方法根据实例集合和它们所具有的属性集合来构造初始本体,即形式背景,接着构造概念格,将本体可视化,进而发现隐含的概念以及概念间的关系;再将这些概念及其之间的关系映射成本体主干;最后根据提供的属性值丰富本体主干。基于Jena选用OWL对以上建立的本体原型进行编码和形式化,完成领域本体的构建。以云南旅游领域为背景构建旅游本体原型系统,证明了本文所提出的本体构建方法的有效性,并在领域可移植性、本体构建效率及自动化程度等方面进行系统评测,取得良好效果。经与人工构建结果对比,证明了构建结果的有效性。

To aim at solving the difficult problems of discovering the implicit knowledge and coding for ontology inefficiently in ontology construction, this paper proposes a semi-automatic approach to construct the domain ontology based on FCA and Jena. At first, formal context is built up by clustering the instance sets and the attribute sets of the domain concept repeatedly and then the concept lattice is built up. Secondly, the domain ontology needs to be visualized. Furthermore, the potential concepts and relations among concepts are found to form the ontology trunk. At last, the ontology trunk is enriched by adding the corresponding attribute values. After that, the OWL is selected to code and formalize the above original ontology based on Jena in order to complete the construction of domain ontology. Taking the Yunnan tourism domain as background, the tourism ontology prototype system is constructed, which demonstrates the validity of the domain ontology semi-automatic construction approach proposed in this paper, and some evaluations on field portability, ontology building efficiency and degree of auto- mation have good results. Compared with artificial construct results, it shows the construction validity.