Towards an Agent-Based Knowledge Management System - Developing Concepts in Applied Intelligence - page 94

Towards an Agent-Based Knowledge
Management System
Marwan Altawil 1 , Asma Moubaiddin 2 , and Nadim Obeid 1
1 Department of Computer Information Systems,
King Abdullah II School for Information Technology,
The University of Jordan
[e-mail]
2 Department of Linguistics,
Faculty of Foreign Languages,
The University of Jordan
Abstract. In this paper, we propose a knowledge management system that em-
ploys agents and case-based reasoning to extract tacit knowledge and support
organizational learning and decision making at the level of individual workers,
group workers and the whole organization. Agents will perform the tasks of in-
quiry, investigation, sharing and updating of knowledge bases, including previ-
ous similar cases, in order to help in finding the required knowledge for a
specific problem. We have applied the system to develop a banking training as-
sistant system and have run several experiments to measure a number of func-
tionalities such as reliability, efficiency, the impact of weight parameters on
extracted results, and the degree of match between the results produced by our
system and the opinions of randomly selected experts in the chosen application.
Keywords: Knowledge Management, Case-Based Reasoning, Multi-Agent.
1 Introduction
Knowledge is considered as a critical component of organization competency and an
essential asset that requires careful management so that organizations can enhance
and facilitate the decision making process [6]. We distinguish between explicit and
tacit knowledge. Explicit knowledge could be explored and easily shared with others
using documents, databases, and so on [1]. Tacit (embodied) knowledge is embedded
inside a person's mind, therefore it is difficult to extract and share with others [4].
Organizational Knowledge/Memory (OM) refers to more than just databases and
information systems involved in an organization. It encompasses processes and peo-
ple. Decision makers (DM) in an organization often need to employ both explicit and
tacit knowledge that are related to the specific problem which needs to be solved. The
study of OM seeks to understand how knowledge is created, stored, accessed, trans-
formed, handled and used effectively. Knowledge Management (KM) should provide
relevant knowledge to assist processes in performing knowledge intensive tasks [12].
A Knowledge Management System (KMS) should involve providing knowledge,
experiences and insights at the right time, to the right place, in the right form to the
right knowledge worker [9, 10, 12]. These features characterize intelligent agents.