Identification and Classification of Deep Web Query Interfaces via Ontology

Abstract

In order to obtain the large quantities of valuable information on Deep Web, it is required to discover the related individual query interface and design the integrated query interface on which user query request can be submitted. The key challenges are to identify and classify the Deep Web query interface accurately. In view of the regular data of Deep Web, we consider to construct the Deep Web domain ontology to help identify and classify the Deep Web query interfaces. Correspondingly, one domain ontology construction approach by referring to the hierarchal schema of query interface is proposed. Based on the constructed domain ontology, the modified interface expression algorithm and the identification and classification algorithm for Deep Web query interfaces are also presented, respectively. Experimental results show the effectiveness of our proposed algorithms. .