摘要
针对Deep Web中模式匹配难度大的问题,根据目前模式匹配的特点,提出一种基于本体和BP网络相融合的的模式匹配新方法。该方法利用具有相同含义的本体分组来确立模式之间的对应关系,降低匹配的复杂度;利用BP网络的自我学习能力提高匹配的自动化程度。实验结果表明该方法能明显提高模式匹配的精确度和召回率,有效地提高了匹配质量。
Towards the difficulty of the schema matching in Deep Web and according to the features of the existing schema matc- hing,we proposes a new approach using different groups of the ontology with the same meaning to establish the relationship between schemas, in this way the complexity can be reduced, at the same time by using the self-study ability of neural network the automation of the matching has been improved too. The experimental results show that this approach can improve the precision ratio and recall ratio of the schema matching obviously, and it can effectively improve the quality of the schema matching.
出处
《济南大学学报（自然科学版）》
CAS
北大核心
2011年第1期23-26,共4页
Journal of University of Jinan(Science and Technology)
基金
山东省自然科学基金(ZR2009GM009)
