Helping to Develop Knowledge Management Systems by Using a Multi-Agent Approach

AbstrAct Efforts to develop Knowledge Management have increased in recent years. However, many of the systems implanted in companies are still not greatly used by the employees because the knowledge that these systems have is often not valuable or on other occasions, is useful but employees do not know how to search for that which is most suitable. Moreover, employees often receive too many answers when they consult this kind of systems and they need to waste time evaluating all of them in order to find that which is most suitable for their necessities. On the other hand, many technical aspects should also be considered when developing a multi-agent system such as what knowledge representation or retrieval technique is going to be used. To find a balance between both aspects is important if we want to develop a successful system. However, developers often focus on technical aspects giving less importance to knowledge issues. In order to avoid this, we have developed a model to help computer science engineers to develop these kinds of systems. In our proposal, first we define a knowledge life cycle model that, according to literature and our experience, ponders all the stages that a knowledge management system should give support to. Later, we describe the technology (software agents) that we recommend to support the activities of each stage. The chapter explains why we consider that software agents are suitable for this end and how they can work in order to reach their goals. Furthermore, a prototype that uses these agents is also described.