Research on a personalized learning path recommendation system based on cognitive graph with a cognitive graph

The necessity for students to clarify their own cognitive structure and the amount of their knowledge mastery for self-reflection is often ignored in building the student model in the adaptive model, which makes the construction of the cognitive structure pointless. Simultaneously, knowledge forgetting causes students' knowledge level to fall short of what is required to enable the subsequent learning stage. The students' cognitive map was displayed using cutting-edge cognitive graph technology to address the aforementioned problems, and the reasoning rules were created using the Dual Process Theory and Meaningful Learning Theory. The degree of memory retention in students was calculated using the universal forgetting curve proposed by Ebbinghaus. To improve semantic information, multimodal data were coupled with knowledge graph. Finally, a cognitive graph integrated into the learning path recommendation system was developed. Comparative tests were conducted to verify the system's efficacy. The experimental group outperformed the control group with an average score of 77.286. The results of the experiment show that the experimental group using the CGLPRS has significantly higher levels of knowledge use and mastery than the control group, showing that the use of cognitive graph and accounting for forgetting can significantly improve conceptual understanding and overall learning satisfaction.