Affiliation:
1. School of Xia Qing Media of Handan University, Handan, Hebei, China
2. School of Music, Handan University, Handan, Hebei, China
Abstract
Individualized recommendation of imperceptible social heritage and materials in schools under the double reduction policy is to evaluate and judge students’ learning interests and specialties and recommend suitable imperceptible social heritage and materials to students. Aiming at the problem that the collaborative filtering recommendation method does not match the individualized needs of primary and secondary school students under the double reduction policy, in this paper, we suggest a personalized recommendation system of imperceptible social heritage and materials in schools under the double reduction policy based on joint template feature matching and interest feature point mining. First, taking the information management platform of imperceptible social heritage and materials in schools as the structural model, the grading model and homomorphic distribution attribute model of imperceptible social heritage and materials for primary and secondary school students under the double reduction policy are constructed. Second, the probability density characteristic analysis method of joint template matching is used to construct the personalized recommendation model of the imperceptible social heritage and materials in schools. Third, then the personalized characteristic distribution and fitness parameter extraction of the imperceptible social heritage and materials in schools under the double reduction policy are carried out, so as to realize the reasonable matching of personalized characteristic requirements and project interest points and realize the personalized recommendation of imperceptible social heritage and materials in schools under the double reduction policy. Finally, a simulation experiment was carried out to test and evaluate the outcomes. The outcomes express that the personalized recommendation items of imperceptible social heritage and materials in schools with this method have higher scores, and the average absolute error and root mean square error are smaller, which improves the quality of dynamic and accurate matching between imperceptible social heritage and materials and students’ hobby characteristics.
Subject
Computer Networks and Communications,Computer Science Applications
Reference26 articles.
1. Collaborative filtering recommendation method based on improved heuristic similarity model [J];N. Zhang;Journal of Computer Applications,2016
2. Recommendation model of penetration path based on reinforcement learning[J];H. Zhao;Journal of Computer Applications,2022
3. Path weights in concentration graphs
4. Upper and lower degree-constrained graph orientation with minimum penalty
5. Co-creation of local eco-rehabilitation strategies for energy improvement of historic urban areas