Research Topics

The ACACIA project (INRIA-Sophia-Antipolis) is a multidisciplinary project composed of computer scientists and cognitive psychologists. It aims at offering methodological and software support (i.e. models, methods and tools) for knowledge management (i.e., for building, managing and distributing a corporate memory).

We study technical memory, profession memory and project memory, in particular in concurrent design. We study the case where the building of a corporate memory relies on exploitation of knowledge underlying documents, on the management of links between documents and knowledge bases or on the modelling of multiple viewpoints. We study knowledge acquisition, modelling and management from multiple expertise sources (experts and documents).

We study the problems involved in the dissemination of knowledge through a knowledge server and via an intranet or the internet: we regard the semantic Web as a privileged means of assistance for the management of knowledge distributed within or between firms. Then, a knowledge server enables searching for information in a heterogeneous corporate memory, this search being intelligently guided by ontologies or knowledge models.

This work is a contribution to the construction of a semantic Web for a company or a community. We study the exploitation of XML as a pivotal technology between knowledge modeling and corporate memory.

For representing ontologies or knowledge models, we use the CommonKADS acquisition method, the conceptual graphs formalism of Sowa and the languages of the XML galaxy. (especially RDF - Resource Description Framework).

Main research topics :

* Support designing of a corporate memory :
  • Methodology for building a corporate memory;
  • Multi-agents architecture for corporate memory;
  • Project memory and technical memory for concurrent design;
  • Management of multi-expertise :
    • Acquisition, modeling and capitalizing knowledge from several experts;
    •   Managing multiple expert models;
    •   Managing multiple ontologies;
  • Acquisition, modeling and capitalizing knowledge from texts
    *Supporting broadcast and use of the corporate  memory :
    • Knowledge servers on the Web;
    • Tools for querying and browsing ontologies and documents;
    • Supporting intelligent information retrieval :
      •  in a distributed and heterogeneous corporate memory,on the Web or on an intranet,
      •   exploiting knowledge models or ontologies.
bas de page