Human-agent service matching using natural language queries: system test and training

Abstract

Abstract Smart environments, ambient intelligence and intelligent agents leave the user lost between large amounts of services. Ad-hoc networks, mobile agents and mobile devices make the set of available services dynamic over time and space, increasing the user¿s problems to find the service he needs. Earlier, we presented a ServiceMatcher that can find the agent best fitting to the user¿s natural language request. This paper presents performance results of the ServiceMatcher. The test queries come from human users in a realistic scenario (see our other paper in this issue). With a short training of the agent vocabularies, over 80% correct service matches are found.