A Study of Innovative Teaching Methods in Higher Education for Digital Localization

With the rapid development of the Internet and information technology, the data generated by online learning resources has shown explosive growth. In this paper, a personalized recommendation model is used to transform and innovate digital localized education. Firstly, the model is constructed by combining online learning characteristics to generate personalized learning paths. Then, personalized recommendation algorithms are proposed on this basis, and traditional recommendation algorithms are found to have limitations. Therefore, this paper chooses a personalized recommendation algorithm based on a knowledge graph. After the questionnaire survey of the learners, it was concluded that there were significant differences in the three dimensions of learning motivation, cognitive load, and learning self-control through the comparison of the differences between the pre-and post-tests in the five dimensions, and the self-control of the students was improved. Then, the satisfaction analysis of the recommender system was conducted, and most of the learners were satisfied and very satisfied with the system, and “dissatisfied” and “very dissatisfied” were 0. The personalized recommender system provides effective targeted learning methods and improves learning efficiency in the innovation of digital localization education. The personalized recommendation system offers effective targeted learning methods that enhance learning efficiency in the innovation of digital localized education. © 2024 Xining Liu, published by Sciendo.