基于粗糙集和模糊聚类的政务本体学习模型

根据政务信息资源的特点，提出了一种新的政务本体学习模型。首先通过命名实体获取领域概念，然后利用粗糙集和模糊聚类理论对模式匹配算法进行改进，进而采用改进的模式匹配算法获取领域概念之间的显式和隐式关系。大量的实践证明：利用该模型能够从庞大的政务信息资源中有效地进行政务本体学习，克服了传统模式匹配算法不能很好地获取概念之间隐式关系的问题。

Model of government ontology learning based on rough set and fuzzy clustering

According to the characteristics of government information resources,this paper presents a new model of government ontology learning.First of all, the concept is acquired by naming entities, and then pattern matching algorithm is improved by using the rough set theory and fuzzy clustering, and then the concepts of explicit and implicit relations are acquired by using the improved pattern matching algorithm.A lot of practice proves that using the model can efficiently acquire the ontology from the huge government resources,and overcome the question of the traditional pattern matching algorithm which cannot get the implicit relations.