Multi-Agent Corporate Memory Management System

This paper presents an approach to design a multi-agent system managing a corporate memory in the form of a distributed semantic web and describes the resulting architecture. The system was designed during the CoMMA European project (Corporate Memory Management through Agents) and aims at helping users in the management of a corporate memory, facilitating the creation, dissemination, transmission and reuse of knowledge in an organisation. The implementation integrated several emerging technologies: multi-agents system technology (using the JADE FIPA-compliant platform), knowledge modelling and XML technology for information retrieval (using the CORESE semantic search engine) and machine learning techniques. Here, we describe the agent roles and interactions, we explain the design rationale for the agent societies and we discuss the configuration and implementation issues. Materialising and managing a distributed corporate memory With our entrance in the information society, organisations had to adapt to the shift in the economy and market rules that followed. Information systems are becoming backbones of organisations and therefore their interest in corporate knowledge management grows stronger. Corporate knowledge management aims at facilitating creation, dissemination, transmission and reuse of knowledge in an organisation (Rabarijaona et al., 1999). It can rely on an organisational memory i.e. an explicit, disembodied and persistent representation of knowledge and information in an organisation, in order to facilitate their access and reuse by members of the organisation, for their tasks (Dieng et al., 2001). The stake in building a corporate memory management system is the coherent integration of this dispersed knowledge to promote knowledge growth, knowledge communication and in general to preserve knowledge within an organisation (Steels, 1993). The work presented here was achieved in the context of the CoMMA European project (CoMMA, 2000) aiming at implementing a corporate memory management framework in the context of two application scenarios: • Assist the integration of new members in the organisation by providing them with the information they need to become operational as quickly as possible. • Support the technology monitoring processes by diffusing newly available information to relevant members. This first part presents the motivations for our design rationale and technical choices. It then explains how the memory was materialised so as to be manageable by agents. Finally we compare our project to related works. 3 Engineering choices and motivating observations The multi-agent approach, relying on loosely-coupled software components, is naturally prone to facilitate integration of different technologies in one system. This was an important need …