An Approach to Representation Changes While Executing Problem Solver Intelligent Systems

The choice of an appropriate representation is generally assumed to play a decisive part in problem solving, both in human and computer performance. Some AI problem solvers have so far succeeded in performing automatic representation change, but none of them is actually able to do so once the resolution process is started. This inability proves to be a drawback so as to achieving a suitable representation is concerned. Also it should be observed that in human problem solving representation changes can actually occur in every stage of the resolution process. Taking all this into account, in the present paper we deal with a technique for changing representation while problem solving by making use of specific procedures which assign and modify a certain relevance value to every attribute involved in the problem representation, on behalf of their respective importance so as to actually solve the problem. This technique allows adapting representation to the peculiarities of each problem while the actual problem solving process takes place.