ITSのための汎用フレームワークFITSにおける教授戦略の運用法

抄録

To realize an intelligent tutor on a computer, we must clarify two types of knowledge such as a set of primitive tutoring behaviors and scheduling knowledge for tutoring. We have already formalized twenty-two tutoring strategies which are independent of the teaching materials. Those tutoring strategies are designed as primitives of appropriate grainsize. Sequences of tutoring behaviors are generated by combining one or more such primitives. Realization of sophisticated scheduling requires well-organized knowledge concerning student model, tutoring history, effects of tutoring actions taken and so on. Among them, special attention should be paid on tutoring goals. In this paper, we discuss the hierarchical structure of tutoring goals, the mechanism and the knowledge to make them operational, which properly capture the relationship among the tutoring goals, the tutoring strategies, and characteristics of the domain knowledge. Some concrete examples of the knowledge to operate tutoring strategies and the generated tutoring discourses are also presented.