PASER: a curricula synthesis system based on automated problem solving

Abstract

This paper presents PASER, a system for automatically synthesizing curricula using AI Planning and Machine Learning techniques on an ontology of educational resources metadata. The ontology is a part-of hierarchy of learning themes which correspond to RDCEO competencies. The system uses an automated planner, which given the initial state of the problem (learner's profile, preferences, needs and abilities), the available actions (study an educational resource, take an exam, join an e-learning course, etc.) and the goals (obtain a certificate, learn a subject, acquire a skill, etc.) constructs a complete educational curriculum that achieves the goals. PASER is accompanied by a Machine Learning module that classifies textually described users' learning requests to competencies registered within the ontology. Furthermore, the ML module interactively assists content providers in constructing educational resources metadata (LOM records) that comply with the ontology concerning both learning objectives and prerequisites.

An intelligent learning framework for Industry 4.0 through automated planning

“…Previous literature focuses on generating one customized course, so a course-taking plan, in which a series of courses are suggested with a required sequence, is not addressed. Also, most of the previous works do not guarantee optimality in the generated courses under various objective functions or constraints because they used heuristic approaches [5,27,28]. Furthermore, previous approaches lack not only various quality-of-service attributes in objective functions, such as minimization of total tuition or minimization of total credit hours but also those into constraints, such as the maximum number of courses per semester.…”

“…• Maximum course constraints: By setting MaxC, a user can control the maximum number of courses to take within a semester. Equation (28) shows the case that the maximum number of courses in a semester is 3.…”

Planning and scheduling in an e-learning environment. A constraint-programming-based approach

“…Other approaches have introduced hierarchical planners to represent pedagogical objectives and tasks in order to obtain a course structure (Ullrich, 2005). Most recent works, such as the one presented in Vrakas et al (2007), incorporate machine learning techniques to assist content providers in constructing learning objects that comply with the ontology concerning both learning objectives and prerequisites.…”

LRNPlanner: Planning Personalized and Contextualized E-Learning Routes

“…The application of Artificial Intelligence (AI) planning techniques has reported significant advances in the process of designing e-learning routes due to the similarity of both processes [5,8,10]. Designing an e-learning route implies to generate a sequence of learning objects tailored to the learner's goals and individual properties.…”