A Knowledge-Model for AI-Driven Tutoring Systems

Abstract

A powerful new complement to traditional synchronous teaching is emerging: intelligent tutoring systems. The narrative: A learner interacts with a digital agent. The agent reviews, selects and proposes individually tailored educational resources and processes - i.e. a meaningful succession of instructions, tests or groupwork. The aim is to make personal tutored learning the new norm in higher education - especially in groups with heterogeneous educational backgrounds. The challenge: Today, there are no suitable data that allow computer-agents to learn how to take reasonable decisions. Available educational resources cannot be addressed by a computer logic because up to now they have not been tagged with machine-readable information at all or these have not been provided uniformly. And what's worse: there are no agreed conceptual and structured models of what we understand by 'learning', how this model-to-be could be implemented in a computer algorithm and what those explicit decisions are that a tutoring system could take. So, a prerequisite for any future digital agent is to have a structured, computer-accessible model of 'knowledge'. This model is required to qualify and quantify individual learning, to allow the association of resources as learning objects and to provide a base to operationalize learning for AI-based agents. We will suggest a conceptual model of 'knowledge' based on a variant of Bloom's taxonomy, transfer this concept of cognitive learning objectives into an ontology and describe an implementation into a web-based database application. The approach has been employed to model the basics of abstract knowledge in engineering mechanics at university-level. This paper addresses interdisciplinary aspects ranging from a teaching methodology, the taxonomy of knowledge in cognitive science, over a database-application for ontologies to an implementation of this model in a Grails service. We aim to deliver this web-based ontology, its user-interfaces and APIs into a research network that qualifies AI-based agents for competence-based tutoring.