A Case-based Reasoning Approach to Internet Intelligent Tutoring System Authoring

Intelligent tutoring systems (ITSs) have shown great promise in military training domains and can achieve many of the same benefits as one-on-one instruction, in a cost-effective manner. However, the key to the effectiveness of this instruction is the successful transition of laboratory systems to real-world domains and the extent of the technical knowledge the system contains. Traditional approaches to development of ITSs are hampered by the knowledge acquisition bottleneck - the need to construct an explicit expert mental model. We propose an innovative approach to Internet Multi Media (MM) ITS development using a case-based reasoning (CBR) paradigm which largely circumvents the difficult and time-consuming process of knowledge elicitation. A case-based approach to knowledge gathering is highly intuitive, and authoring of the training course is greatly simplified and requires no special computer training.In Phase I, we will investigate a CBR approach to ITS development and explore the feasibility of semi-automated knowledge elicitation techniques to speed collection and structuring of domain knowledge from experts. We will develop a prototype Internet MM ITS using these techniques within a specific Air Force instructional domain and produce a generic Internet MM ITS architecture applicable in many other domains. We have used this CBR approach with much success in other training domains.