A Distributed Problem Solving Approach to Cooperative Information Gathering
Tim Oates, Munaga V. N. K. Prasad, Victor Lesser, Keith Decker · 1995
this paper, we present a model of information gathering designed specifically for such complex environments, a model of Cooperative Information Gathering (CIG). In addition to the complexity of query specification, control of the acquisition process may itself be complex and dynamic in IG systems. Traditional Information Retrieval (IR) is a limited sub-case of such information gathering systems in which queries generally map onto static, pre-specified retrieval plans. In this paper, we propose a cooperative agent-based solution for information gathering. Top level queries drive the creation of partially elaborated information gathering plans, resulting in the employment of multiple semi-autonomous, cooperative agents for the purpose of achieving goals and subgoals within those plans. Cooperation between agents implies management of interdependencies between their activities so as to integrate and evolve consistent clusters of high quality information from distributed heterogeneous sources. This paper draws upon a long history of thought in Distributed Problem Solving (DPS) to present a model of this type of cooperative information acquisition.