Distributed knowledge extracted by a mas using ontology alignment methods

Nowadays new product development involves different types of actors (technician, managers, board of directors) which must be able to share knowledge, experiences and work together efficiently. Each actor has a professional specialty and uses one or several software tools (CAO, project management tools, PLM tools ...) dedicated to her specific activities. Each of these software tools produces different information sources (databases, XML files, text files) which are distributed through the enterprise network. In this paper, we present the design of a multi-agent software architecture that allows the capitalization of distributed and heterogeneous knowledge. We then describe how the agents assist users to create domain ontologies matching with professional software tools databases and how the agent build semantic queries to extract knowledge.