Skip to Main content Skip to Navigation
Theses

Exploitation du web sémantique pour la veille technologique

Abstract : The rise of Internet supported the appearance of numerous information available on line, which is potentially useful for the technological and scientific watch of a company. Various techniques of information retrieval on the Web are proposed in order to build tools enabling to refine the search in order to get relevant results. However, in the context of the current Web, in spite of large progresses in the field of information retrieval, these tools showed their limits in terms of precision and recall. The application of Semantic Web technologies, in particular of ontologies, thus seems to us to be useful to improve the performance of technological and scientific watch task on the Web. This thesis was prepared in the framework of a cooperation between the CSTB (Scientific and Technical Centre for Building) and the ACACIA Team at INRIA Sophia Antipolis. The main objective of this thesis is to use the Semantic Web technologies to develop a system for technology monitoring (OntoWatch). This system is guided by ontologies, in order to collect, capture, filter, classify and structure the Web content coming from several information sources in a scenario of assistance to the technological et scientific watch. In a first part, we model the CSTB¤s technological watch process relying on the generic model of monitoring proposed by Lesca. We identify the potential contributions of ontology in the various stages of the process then we build an ontology dedicated to the technological watch system. This ontology integrates a part of an existing ontology and vocabularies offered in thesaurus of the CSTB domain. After that, we propose several algorithms using an ontology to improve document search on the Web and to generate automatically semantic annotations (in RDF format) for these documents. These annotations feed the annotation bases of the system, bases on which the semantic search of information relies. Finally, we propose a multiagents architecture for implementation of the OntoWatch system. We focus in particular on the design of the sub-societies of agents dedicated to search and automatic annotation of documents on the Web.
Document type :
Theses
Complete list of metadata

Cited literature [36 references]  Display  Hide  Download

https://tel.archives-ouvertes.fr/tel-00311767
Contributor : Estelle Nivault Connect in order to contact the contributor
Submitted on : Thursday, August 21, 2008 - 10:01:07 AM
Last modification on : Monday, June 28, 2021 - 6:58:33 PM
Long-term archiving on: : Thursday, June 3, 2010 - 6:40:47 PM

File

Identifiers

  • HAL Id : tel-00311767, version 1

Collections

Citation

Tuan Dung Cao. Exploitation du web sémantique pour la veille technologique. Informatique [cs]. Université Nice Sophia Antipolis, 2006. Français. ⟨tel-00311767⟩

Share

Metrics

Record views

1015

Files downloads

3481