Digital portrait and intelligent recommendation system for physical education teaching based on hybrid collaborative filtering

This study aims to effectively address issues in traditional physical education (PE) teaching, such as blind course selection, mismatched teaching resources, and lack of personalized guidance. This study investigates the development of a digital portrait and intelligent recommendation system for physical education instruction based on hybrid collaborative filtering (HCF). The system constructs digital portraits of students for PE course scenarios by integrating multidimensional information—including basic attributes, physical abilities, learning behaviors, and interest preferences. It further uses adaptive feature weights to capture individual differences among students. In the recommendation model, a user interest confidence mechanism is introduced to construct user-side similarity relationships driven by digital portraits. Meanwhile, a course-side similarity relationship is established by incorporating a popularity correction strategy. Through the fusion of information from both sides, personalized recommendations for PE courses are achieved. The results demonstrate that the HCF-based digital portrait consruction and intelligent recommendation system for PE can stably accomplish course recommendation tasks. The experimental results demonstrate that the proposed model maintains strong recommendation performance on the public education dataset, the self-constructed PE dataset, and the external recommendation dataset. It also exhibits robust adaptability in cold-start user scenarios. Further teaching validation experiments indicate that the intelligent recommendation-based course matching approach can improve the suitability of students’ course selections. It also exerts positive effects on learning engagement and course performance. This study provides a feasible technical solution for personalized course recommendation and digital teaching management in PE, offering valuable insights for the integration of information technology into PE reform.

Authors

Institutions

Publication Details

Journal
Discover Artificial Intelligence
Published
2026-11-17
DOI
https://doi.org/10.1007/s44163-026-02340-7
Primary Topic
Recommender Systems and Techniques
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Digital portrait and intelligent recommendation system for physical education teaching based on hybrid collaborative filtering

Yuan Xue, Pengyu Qi, Zhihong Hou
3 links
Discover Artificial Intelligence
Recommender Systems and Techniques
article

Digital portrait and intelligent recommendation system for physical education teaching based on hybrid collaborative filtering

Yuan Xue, Pengyu Qi, Zhihong Hou
article en

Abstract

This study aims to effectively address issues in traditional physical education (PE) teaching, such as blind course selection, mismatched teaching resources, and lack of personalized guidance. This study investigates the development of a digital portrait and intelligent recommendation system for physical education instruction based on hybrid collaborative filtering (HCF). The system constructs digital portraits of students for PE course scenarios by integrating multidimensional information—including basic attributes, physical abilities, learning behaviors, and interest preferences. It further uses adaptive feature weights to capture individual differences among students. In the recommendation model, a user interest confidence mechanism is introduced to construct user-side similarity relationships driven by digital portraits. Meanwhile, a course-side similarity relationship is established by incorporating a popularity correction strategy. Through the fusion of information from both sides, personalized recommendations for PE courses are achieved. The results demonstrate that the HCF-based digital portrait consruction and intelligent recommendation system for PE can stably accomplish course recommendation tasks. The experimental results demonstrate that the proposed model maintains strong recommendation performance on the public education dataset, the self-constructed PE dataset, and the external recommendation dataset. It also exhibits robust adaptability in cold-start user scenarios. Further teaching validation experiments indicate that the intelligent recommendation-based course matching approach can improve the suitability of students’ course selections. It also exerts positive effects on learning engagement and course performance. This study provides a feasible technical solution for personalized course recommendation and digital teaching management in PE, offering valuable insights for the integration of information technology into PE reform.

Discover Artificial IntelligenceVol. 6(1)
Qinhuangdao Vocational and Technical College (CN)
Quality education
Recommender Systems and Techniques
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon