Agent-based IT support for knowledge management

2009

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 engi

Knowledge Management is the process of collecting information which supports to create disseminate and utilize the knowledge between the individuals, groups within an organization or independent organization. The process of knowledge management involves various steps such as identifying, collecting, storing, sharing, applying, creating and selling knowledge. Agents are autonomous intelligent computer programs that perform tasks on behalf of the user or user-initiated process by using its knowledge base. Agents are designed and developed in such a way that they are goal-oriented, adaptive, reactive and mobile. Agents incorporated in the process of knowledge management should be capable of communicating with other agents by using its common characteristics namely cooperate, coordinate and collaborate. These common characteristics will improve the performance of knowledge management process by helping the agents to discover the knowledge from it. Agent uses its learning characteristics to update its knowledge base whenever it encounters new information from the organization. Agent’s uses its dynamic characteristics for knowledge sharing among users in an organization. Knowledge sharing is done both at work group and at company level. During this process agent roles associated with the knowledge management and knowledge discovery are identified. This paper aims at describing such agents and their roles.

The importance of knowledge management has, in recent years, led to the incorporation of Knowledge Management Systems (KMS) into companies. Some of these KMS could be considered as Recommender Systems that are able to recommend knowledge, which is part of the company's intellectual capital. However, these KMS are not always welcome in the company, since the knowledge is not stored by using a quality control, or because employees feel that these kinds of systems, rather then helping them, cause them extra work. In this paper we present an agent architecture combined with a trust algorithm trying to avoid some of the problems that appear when a KMS is introduced into companies.

A university knowledge management system is composed by three components: the educational management, the research management, and the institutional management. The high complexity of the whole university knowledge management system, that is also a distributed system, can be handled by using a multi-agent system. Through communication and cooperation the agents are solving different problems specific to knowledge management in a real or virtual university. The agents are associated to the humans involved in all processes (e.g. educational, research, institutional) that are running in a university, such as professors, assistants, students, researchers, technical staff, management staff, administrative staff etc. The paper presents an university knowledge management system based on agents technology. Two case studies are described in detail, one for the university research management, and the other for the educational management. The implementation of the agent-based system was done in ZEUS, a toolkit for multiagent systems development.

Till date, e-commerce organizations still have competency challenges in Customer Knowledge Management (CKM). Organizations need to develop competencies in all aspects of CKM, from understanding who their customers really are and what they want, to designing platforms specifically for customers. It is particularly important for customer processes involving information for, collected from and about customers to be turned into knowledge, disseminated and really used. Also, most companies do not always take full advantage of the knowledge sources that exist through customers’ interaction withtheir websites. All these processes appear complex and fuzzy, which the introduction of agent technology in this paper poses a potential solution to this problem, in order to achieve an effective CKM in a dynamic business environment as e-commerce organizations.

2004

This work presents a multi -agent system designed to manage the information and knowledge generated during the software maintenance process. The system has different types of agents, each devoted to a particular type of information. Agents use different reasoning techniques to generate new knowledge from previous information and to learn from their own experience. Thereby the agents become experts in the type of knowledge they are responsible for. Additionally, agents communicate with each other to share information and knowledge. Thus, there is reuse of knowledge and knowledge management in the multi-agent architecture itself.

Studies in Computational Intelligence, Vol. 363, 2011

In this paper, we propose a knowledge management system that employs 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 inquiry, investigation, sharing and updating of knowledge bases, including previous 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 assistant system and have run several experiments to measure a number of functionalities 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.

2012

Software engineering is the process of design; develop Implement and Maintenance a particular task with certain goal by the help of logical activity perform by the knowledge communities. Especially, In Knowledge Organization around 80 Percent Problem is recognized by the Knowledge communities i.e. related to the people. Much work is recognized in the field of knowledge management support for Software Organization but knowledge manager are still facing Problem Related to organizational Knowledge management. While, we are crossing the dynamic and multi facet environment where work to be performing 24*7*365n in manner. So, we need an environment which acts as a multi agent for knowledge management communities. In this work we are proposing a Model for Software Companies who are seeking for optimum Knowledge management practices (OKMP) at the organization. In order to get this objective we have splitting the work into five phases; Which begins from Identification of the various Problems related to software Engineering or Software engineering Practices (SEP)? To overcome these problems we are bringing knowledge management and it's Various Practices including the consequences of such Practices? Then after we are keeping Multi Agent System in Knowledge Management and then we are putting MAS and KM as a whole in Software Engineering. Finally, we are looking for the result of such merger which would further term as SE-MABKM (Support for Software Engineering via Multi agent based Knowledge Management).

Intelligent Knowledge-Based Systems, 2005

This paper concerns the problem of bridging gaps between two different but hot topics in organizational theory and computer science-knowledge management and distributed artificial intelligence. Knowledge management has become increasingly important for effective operation of organizations and decision making. Two approaches have appeared in knowledge management-people track knowledge management and information technology track knowledge management. Representatives of the first track, as a rule, are educated in humanities while representatives of the second track have education in computer science. As a consequence, these two communities have rather different understanding of the essence of knowledge management. Distributed artificial intelligence community have borrowed ideas from sociology, organizational theory, economics, linguistics, computer science, etc. and have worked out concepts of intelligent agents and multiagent systems. The use of these concepts in knowledge management may produce a synergy effect reaching the balance between both tracks of knowledge management.

2013