推論パスネットワークによる高速仮説推論システム

抄録

The handling of incomplete knowledge is a key technology for next-generation knowledge-based systems. A logic-based hypothetical reasoning can deal with incomplete knowledge as hypothesis. Most hypothetical reasoning system have been built so far using SLD resolution with depth-first search strategy embedded in Prolog. The inference speed of these systems is not satisfactory for practical use, because it includes a number of backtrackings due to the inconsistency among adopted hypotheses in addition to the ordinary failure of proving a goal. This paper describes a fast hypothetical reasoning system named KICK-SHOTGAN, which avoids inefficient backtracking by forming a compiled inference-path network followed by the foward synthesis of necessary hypothesis combination along this network. The formation of this inference-path network is based on a linear-time algorithm for the satisfiability testing of propositional Horn clauses. This system differs from ATMS mainly in its total problem solving nature. That is, it works for the logical problem-solving framework which yields a solution for a given goal, whereas the ATMS calculates possible data supported by hypotheses incrementally in response to the input of a justification (rule) from a problem solver existing outside the ATMS. The inference speed of this fast hypothetical reasoning system is thousands of times faster than that of existing systems implemented in Prolog.