Combining Ontology-based Domain Knowledge to AutoMated Planner

摘要

There are much research into Artificial Intelligence (AI) and Semantic Web over the past few years and intelligent behaviour such as learning, analysing, problem solving, planning and abstracting is displayed by modern computer systems. Automatically acquiring control-knowledge for planning, as it is the case for Machine Learning in general, strongly depends on the training material. In planning, there is a novel ways to store examples into ontology when solving problems. This Paper presents a new architecuture for the design and development of training material, where metadata and the knowledge build into them are captured and fully reusable. These System use AI Planning and Semantic Ontology technologies, allowing to construct learning rules dynamically based on the general Domain independent Planner even from disjoint learning objects, and meeting the learner's profile, preferences needs and abilitity.