Nowadays, a significant amount of data about learners and their digital activities is collected, which can help educational institutions better understand learning processes, improve them, and provide more effective learning assistance. In this research endeavour, custom knowledge- and data-driven recommendation algorithms will offer students in higher education integrated learning assistance. The prerequisite for this is a learner model that is as comprehensive as possible, which should first be created and then kept mainly up-to-date automatically to individualise and personalise the learning experience. To create such a learner model, a roadmap is presented that outlines the individual phases, from model creation to evaluation. The paper presents the research method for this endeavour and explores the research question of how learners can be supported with personalised, situation-specific learning recommendations.