Design of college personalised career planning utilising multidisciplinary approaches

This paper proposes a personalised learning path design method for college students' career planning under an interdisciplinary perspective, aiming to improve the efficiency of learning path generation. Firstly, college students' career planning knowledge graph (CPKG) is constructed, and the set of knowledge points that students have mastered and the target knowledge points are mapped into the CPKG. Then, the neighbourhood expansion rule of graph convolutional neural network is combined to add the association strength of relations to entities to capture learner preferences. The importance of knowledge points is calculated by adjusting the corresponding weights through the features of knowledge points in CPKG, and the optimal personalised learning path is designed for learners by combining learner preferences and the importance of knowledge points. Experimental results show that the proposed method takes only 9.2 s to generate the optimal path, which can provide learners with satisfactory learning paths.