Affiliations: [a]
Nanjing University of Aeronautics and Astronautics, Nanjing, Jiangsu, China
| [b]
Jinling Institute of Technology, Nanjing, Jiangsu, China
Correspondence:
[*]
Corresponding author. Liu Lin, Nanjing University of Aeronautics and Astronautics, Nanjing, Jiangsu, China. E-mail: [email protected].
Abstract: The difficulty of knowledge point recommendation based on the learning diagnosis model lies in how to perform feature recognition and selection of recommended knowledge points. At present, the recommendation system has certain problems in the accuracy of recommended knowledge points. Based on this, this study mainly studies the personalized problem recommendation of middle school students in the field of education. Moreover, this study takes the answer records of students’ exercises as data, and combines the characteristics of the field of education to propose an exercise recommendation algorithm based on hidden knowledge points and an exercise recommendation method based on the decomposition of student exercise weight matrix. In addition, in order to verify the effectiveness of this research algorithm, this paper selects the accuracy rate and recall rate as evaluation indicators to analyze the recommendation results of this algorithm and the current more advanced CF algorithm, and the statistical experiment results are drawn into charts. The research results show that the method proposed in this paper has certain advantages and can be used as one of the subsystems of the learning system.
Keywords: Text vector model, support vector machine, learning information, personalized recommendation
