EXPLAINING QUANTITATIVE SYSTEMS TO UNINITIATED USERS

The importance of explanation in expert systems has been documented fr om the early days of their development; there is an equally pressing n eed for explanation in systems that employ a decision-making process b ased on quantitative reasoning This is particularly necessary for user s who do nor have a sophisticated understanding of the formal apparatu s that the system employs to reach its decisions. In order to generate meaningful answers to questions asked by such unsophisticated users, an explanation facility must translate the formal structures of the pr oblem solving system into the concepts with which the user understands the problem domain. Previous work on the explanation of quantitative systems is based on the assumption that the user has al least a basic grasp of the formal approach of the problem solving system. However, i n realistic application situations, it is more likely the case that in order for the human user to understand why a mathematically-based adv ice-giving system makes the suggestions that it does, the problem solv ing rationale of the system must be explained in the user's own terms, which are typically different from those of the mathematical system. To develop an explanation methodology that is capable of justifying th e results of a system based on quantitative reasoning to an uninitiate d user we employ a representation that enables our explanation facilit y to translate the abstract mathematical relationships that make up a quantitative system into the domain-specific concepts with which a typ ical user approaches the problem solving task. In our system, the proc ess of generating explanations, therefore, involves translating one se t of concepts into another. An added feature of this system is that it is capable of providing explanations from two perspectives: that of t he quantitative problem solving system, and that of the human user who is familiar with the domain problem but not with the mathematical app roach. We have implemented this approach to explaining quantitative sy stems by creating an explanation facility for a problem in the manufac turing domain. This facility responds to user queries about a scheduli ng system that uses a mathematically-based heuristic to choose jobs fo r an annealing furnace.