Research On An Approach Of Fuzzy Technique And Ontology

Nowadays much of the existing electronic data lies outside of database management system, data structure are non-relational, sometimes irregular, as in HTML or SGML documents. In particular the subset of the Web formed by XML documents is growing into a large XML data repository. Our knowledge extraction approach is particular useful in those cases where XML information is available that was built over a wide vocabulary of optional tags, even more so if the tags are allowed to occur multiple times within documents.Similarity between XML documents can be studied in different ways, in particular depending of the fact that we take into consideration only the structure of the document, its content, or both of them. In this paper, a fuzzy technique to compare XML fragments belonging to a semi-structured flow and sharing a common vocabulary of tags is used. This approach is based on the idea of representing documents as fuzzy bags, using a measure of comparison, evaluating structural similarities between them. Then this paper suggests how to organize the extracted knowledge in a class hierarchy based on cluster-heads.Firstly, the paper gives an overview of related research, and then it outlines our application of fuzzy techniques to. efficient structure-based encoding and clustering of XML data, followed with how content-based clustering can be coupled with structure-based techniques to produce a finer-gained classification. At last it includes the method how to abstract the relationship is-a and part-of and a worked-out example of XML clustering, as well as how clusters can be used as a basis for generating an ontology. Using a clustering technique and a graph based approach it is possible to build a taxonomy that can be represented through an ontology language OWL.