Knowledge graph construction for intelligent physical education and its application in training
Bibliographic record
Abstract
Knowledge mapping, as an emerging knowledge management tool, provides a new perspective of knowledge learning for physical education teaching. In this study, knowledge mapping is introduced into physical education teaching, and a comprehensive physical education knowledge map is constructed by integrating the teaching resources and contents of physical education teaching and utilizing related techniques such as knowledge extraction and knowledge fusion. The method of fusion of sports knowledge graph is also proposed, including three parts: graph approximation, similarity calculation, and subgraph fusion. Finally, the constructed knowledge graph is practically applied, and a recommendation model based on sports knowledge graph and neural network is constructed to realize the sports teaching application of intelligent educational knowledge graph. The entity recognition module optimized the recognition accuracy rate on the objective existence entities of sports by 1.45%, and the relationship extraction module outperformed AGGCN in all three indicators. The training method of this paper is better than the MICT sports training method in improving students’ cardiorespiratory capacity and flexibility quality. The improvement of students’ 800m running performance under this paper’s training program is 0.13min more than that of MICT.It is proved that the sports course recommendation model based on knowledge graph and neural network provides a reference for the management and application of knowledge data in physical education, with a view to promoting the progress in the field of intelligent education.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.003 | 0.004 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".