面向动态学习环境的自适应学习路径推荐模型

Adaptive Learning Path Recommendation Model for Dynamic Learning Environments

自适应学习路径作为实现个性化学习的一项关键技术,受到研究者广泛关注。近年来,强化学习成为自适应学习路径推荐的主流方法,但在动态学习环境表征的完整性和学习路径的适应性方面仍存在不足。基于此,文章提出了融合领域知识特征的自适应学习路径推荐模型。首先,模型将知识点概念覆盖和难度两个特征引入动态学习环境中,使对动态学习环境的表征更完整。其次,采用深度强化学习算法实现学习路径的推荐,提升学习路径的适应性。最后,开展技术对比实验和应用实验。技术对比实验表明,该模型提高了学习路径的有效性和适应性。应用实验表明,该模型可以准确地判断学习者的薄弱知识点概念,并能为学习者推荐适合其认知特征的自适应学习路径。

Adaptive learning path,as a key technology to realize personalized learning,has received extensive attention from researchers.In recent years,reinforcement learning has become the mainstream method for adaptive learning path recommendation,but there are still deficiencies in the completeness of dynamic learning environment representation and the adaptability of learning path.Based on this,this paper proposes an adaptive learning path recommendation model that incorporates domain knowledge characteristics.Firstly,the model introduces the two features of the coverage of knowledge concepts and the difficulty into the dynamic learning environment to make the representation of the dynamic learning environment more complete. Secondly, a deep reinforcement learning algorithms is used to realize the recommendation of learning paths and improve the adaptability of learning paths. Finally, technology comparison experiment and application experiment are conducted. The technology comparison experiment demonstrates that the model improves the effectiveness and adaptability of the learning paths. The application experiment shows that the model can accurately identify the learners' weak knowledge concepts and recommend adaptive learning paths suitable for their cognitive characteristics.