Domain-oriented Deep Web Data Sources' Discovery and Identification

摘要: As Deep Web contains tremendous well-structured data sources, how to integrate sources in has become a hotspot current research. Accurately discovering and identifying related specific domain key issues. We propose Domain-Oriented source Discovery method (DO-DWD) novel Domain Identification strategy of (DIDW). In the discovery stage, we use machine learning algorithms some heuristic rules find query interfaces sources; identification identify associated with by calculating relevance between interface based on semantic similarity. Finally, have extensive experiments real set showing that DO-DWD DIDW are high correctness accuracy.