Flexible strategy coordination approach for supporting resource awareness in multi agent filtering framework

A flexible information filtering system, which combines multiple strategies in order to effectively exploit available resources, has to explore the properties of novel strategies without dramatically increasing the response time while learning their strengths and weaknesses. The major drawback of many existed systems, which try to make different synergies between filtering strategies, is usually concerned with not taking care of resource availability, being especially critical for the presenting of successful commercial deployments. The essence of the presented solution is both in the encapsulation of many known searching algorithms inside separate filtering agents, and in the integration of flexible resource aware coordination mechanisms into one manager agent. The flexibility of the realised coordination scheme in facilitating an easy integration of novel strategies is practically demonstrated in a system serving as an intelligent personal information assistant. Experimental results, obtained during two week long system usage, show the successful elimination of long lasting jobs with duration over 1000 seconds in spite of the regular integration of novel strategies.