Research on the Application of Personalized Learning Paths and Recommendation Algorithms in Gardening

This paper proposes a learning path recommendation algorithm based on prefix growth. The algorithm dynamically constructs learning paths suitable for different learners by mining learners' behavioral data, and optimizes the order of pushing learning content. The method includes data collection, prefix tree construction, learning path generation and recommendation optimization to ensure the accuracy and practicality of the recommendation results. In addition, this paper will also use model simulation to verify the effectiveness of the method. This paper selected a group of landscape architecture students with practical application value as the research objects, and conducted in-depth research on their accuracy, coverage and learning efficiency in practical applications. Experiments have shown that the method proposed in this paper can effectively improve students' learning efficiency, with an accuracy rate of 92.5% and a coverage of 88.3%, which has good promotion value. The research results of this project will provide new ideas and methods for the personalized learning path recommendation problem for landscape teaching. This method has broad application prospects.