<abstract xmlns="http://www.w3.org/1999/xhtml">

<p>With the rapid development of education informatization and intelligence, personalized teaching and course recommendations have gradually become an important research direction in the field of education technology. A knowledge graph, as a structured knowledge representation and organization, provides rich semantic information and a relationship network for teaching course recommendations. Based on this research background, this paper focuses on the research of knowledge graph multivariate environment-aware recommendation algorithms for teaching courses. The article firstly constructs the ontology of course resources, researches and analyzes the methods and steps of acquiring and processing data in order to build the knowledge graph, and then constructs the framework of the recommendation model combining multivariate perception in order to further analyze and explore the user’s course-aware representation learning and the user’s course-aware embedded learning. Embedded Learning, and finally, the teaching course of a school as an empirical study, it is shown that the performance of Ripple_mlp+ and Ripple_mlp in this article are higher than the benchmark algorithms through the experimental class and the control class of the pre and post-test scores have been sorted out and counted. The experimental students’ scores are steadily increasing, and the overall scores are better than the control class. In the experimental class, the significance value is 0.013, indicating that there is a significant difference between the midterm and final grades of the experimental class. Through the paired samples t-test on the midterm and final grades of the experimental class, after analyzing and comparing the midterm and final grades of students at different levels, it can be concluded that the t-value of the superior students is −3.326. The value of significance is 0.049, indicating that there is a significant difference between the midterm and final grades of the exceptional students. The T-value for intermediate students is −0.134, and the value of significance is 0.045, which indicates that there is a significant difference in the midterm final grades of intermediate students. The T-value of −1.623 and the value of significance is 0.534 for advanced students indicates that the difference in midterm final grades of advanced students is not significant.</p>
</abstract>

With the rapid development of education informatization and intelligence, personalized teaching and course recommendations have gradually become an important research direction in the field of education technology. A knowledge graph, as a structured knowledge representation and organization, provides rich semantic information and a relationship network for teaching course recommendations. Based on this research background, this paper focuses on the research of knowledge graph multivariate environment-aware recommendation algorithms for teaching courses. The article firstly constructs the ontology of course resources, researches and analyzes the methods and steps of acquiring and processing data in order to build the knowledge graph, and then constructs the framework of the recommendation model combining multivariate perception in order to further analyze and explore the user’s course-aware representation learning and the user’s course-aware embedded learning. Embedded Learning, and finally, the teaching course of a school as an empirical study, it is shown that the performance of Ripple_mlp+ and Ripple_mlp in this article are higher than the benchmark algorithms through the experimental class and the control class of the pre and post-test scores have been sorted out and counted. The experimental students’ scores are steadily increasing, and the overall scores are better than the control class. In the experimental class, the significance value is 0.013, indicating that there is a significant difference between the midterm and final grades of the experimental class. Through the paired samples t-test on the midterm and final grades of the experimental class, after analyzing and comparing the midterm and final grades of students at different levels, it can be concluded that the t-value of the superior students is −3.326. The value of significance is 0.049, indicating that there is a significant difference between the midterm and final grades of the exceptional students. The T-value for intermediate students is −0.134, and the value of significance is 0.045, which indicates that there is a significant difference in the midterm final grades of intermediate students. The T-value of −1.623 and the value of significance is 0.534 for advanced students indicates that the difference in midterm final grades of advanced students is not significant.

Research on Knowledge Graph Multiple Environment-Aware Recommendation Algorithm for Teaching Course Recommendation

Applied Mathematics and Nonlinear Sciences

This work is licensed under the Creative Commons Attribution 4.0 International License.

With the rapid development of education informatization and intelligence, personalized teaching and course recommendations have gradually become an important...

Research on Knowledge Graph Multiple Environment-Aware Recommendation Algorithm for Teaching Course Recommendation

Data publikacji: 03 cze 2024

Zakres stron: -

Otrzymano: 04 lut 2024

Przyjęty: 14 kwi 2024

DOI: https://doi.org/10.2478/amns-2024-1333

Słowa kluczowe
Knowledge graph, Recommendation algorithm, Convolutional neural network, Recurrent neural network

© 2024 Lina Zhu, published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Research on Knowledge Graph Multiple Environment-Aware Recommendation Algorithm for Teaching Course Recommendation

Data publikacji: 03 cze 2024

Zakres stron: -

Otrzymano: 04 lut 2024

Przyjęty: 14 kwi 2024

DOI: https://doi.org/10.2478/amns-2024-1333

Słowa kluczoweKnowledge graph, Recommendation algorithm, Convolutional neural network, Recurrent neural network

© 2024 Lina Zhu, published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Słowa kluczowe
Knowledge graph, Recommendation algorithm, Convolutional neural network, Recurrent neural network