Dynamic Generation of Knowledge Graph Supporting STEAM Learning Theme Design

Abstract

Instructional framework based on a knowledge graph makes up for the interdisciplinary theme design ability of teachers in a single discipline, to some extent, and provides a curriculum-oriented theme generation path for STEAM instructional design. This study proposed a dynamic completion model of a knowledge graph based on the subject semantic tensor decomposition. This model can be based on the tensor calculation of multi-disciplinary curriculum standard knowledge semantics to provide more reasonable STEAM project-based learning themes for teachers of those subjects. First, the STEAM multi-disciplinary knowledge semantic dataset was generated through the course’s standard text and open-source encyclopedia data. Next, based on the semantic tensor decomposition of specific STEAM topics, the dynamic generation of knowledge graphs was realized, providing interdisciplinary STEAM learning topic sequences for teachers of a single discipline. Finally, the application experiment of generating STEAM learning themes proved the effectiveness of our model.