An agent-based approach for integrating user profile into a knowledge management process

Abstract

This paper presents an approach based on a user agent to permit a number of users connected to distant machines to access different information sources in order to satisfy their requests. This user agent permits the simplification of the information search from distributed sources by making them transparent to the users. The agent considers the specific needs of each user during the search and responds with reference to their profile. It also permits the processing of one or more information requests by one or more users, as well as concurrent responses to each of them. Moreover, the agent provides its users with a measure of interaction, in order to enhance the quality and quantity of the results obtained. As a result, the agent is endowed with the ability to filter and refine the search, thus improving its service to the users.

Introduction

The progress attained in the domain of information technologies over recent years has produced a great expansion in the sources of information distributed throughout the world. The enormous quantities of information render the task of information research increasingly complex. It has therefore become necessary to provide users with knowledge management mechanisms to facilitate this task.

On the Internet, information derives from heterogeneous information systems and are presented under a variety of file formats. Several search tools are being used to find information (Yahoo, Alta Vista, Excite, etc.) some of which are more efficient than others. However, some of them do not allow users to reuse the results obtained in order to improve them. Others do not take into account the interests or the profiles of the users at the time of the information search.

In order to be efficient, a research tool must be able to filter information and refine the search in accordance with the profile of the user. This tool may be conceived as an agent capable of taking into account the individual needs of each user and of responding to one or several requests for information originating from one or several users. In addition, the agent should allow the users a certain interaction, so as to improve the quality and the quantity of the results obtained. To this end, it must be capable of filtering and refining the search in order to respond adequately to different types of users.

In general, a user profile consists of a set of specifications and characteristics which describe a particular user. In the framework of information search, this profile can represent the needs and interests of the user and its role is to direct the search according to those needs. Indeed, if the interests of the user of a given request are taken into account, the quality of the results yielded can be greatly improved upon as a function of the needs of this user.

This paper deals with the integration of the user profile into the process of the search for information. In this context, we discuss an agent-based approach which enables a number of users connected to distant machines to access information sources in order to fulfill their requests. Section 2 outlines previous work in this domain by showing the representation model called “vector space”. Section 3 presents the spherical model, proposed as a means of integrating the user profile into the information search process for the purpose of filtering. Section 4 focuses on the implementation and application of this model.