Ontology-based Merchandise Evaluation and Search

Merchandise search differs from general Internet search in many ways. First, the notion of a "good" answer to a query is quite different. When searching goods, the notion of a "good" answer is often defined as the "right" answer. Finding the right answer is often more difficult than finding the best answer in general Internet search. Second, Merchandise search includes many elements such as price, quality and location etc. In this paper, an ontology-based merchandise evaluation and search approach is presented, in order to improve the search relevance and precision. In this approach, three level mixed indices are established including word indices, ontology indices and ontology relationship patterns indices. With this approach, we can obtain the “right” answer quickly and efficiently, and the search processing can be integrated with a relational database system seamlessly.