Author(s)

Xianjie Xie ¹

Affiliation(s)

¹ Faculty of Computer Information, Kunming Metallurgy College, Kunming, 650033, China

Corresponding Author

Xianjie Xie

ABSTRACT

Linux practical training requires students to coordinate command syntax, file-path reasoning, permission management, service administration, and shell scripting. However, vocational learners often enter laboratory work with markedly different levels of prior knowledge and practical fluency. This study develops a learning-path recommender that combines a 40-point Linux course knowledge graph with a graph-constrained Q-learning policy. The graph encodes prerequisite relations and maps 12 practical tasks to their required knowledge points, while Q-learning prioritizes eligible units according to learner state and task progress. A transparent simulator representing five pedagogically motivated learner profiles was used for pre-deployment evaluation. In a five-strategy comparison, the proposed KG+Q method achieved the highest mean mastery (0.4693) and task-completion rate (0.3744), the lowest error count (26.3533), and zero prerequisite violations. Ablation results indicate that graph constraints preserve instructional order, while modeled adaptive support contributes to mastery improvement and error control. Parameter sensitivity analyses and 20 independent simulation repetitions showed consistent performance patterns. The proposed framework provides an interpretable basis for designing and testing adaptive Linux practical-training paths, although classroom evaluation remains necessary before conclusions about student learning effectiveness can be drawn.

KEYWORDS

Technical and vocational education and training; Knowledge graph; Q-learning; Learning path recommendation; Linux practical training

CITE THIS PAPER

Xianjie Xie. A Knowledge-Graph-Constrained Learning Path Recommender for Linux Practical Training in Chinese Higher Vocational Education. Advances in Vocational and Technical Education (2026). Vol. 8, No. 2, 53-60. DOI: http://dx.doi.org/10.23977/avte.2026.080207.

REFERENCES

[1] Nabizadeh AH, Leal JP, Rafsanjani HN, Shah RR. Learning path personalization and recommendation methods: A survey of the state-of-the-art. Expert Systems with Applications. 2020;159:113596. doi: 10.1016/j.eswa.2020.113596.
[2] Durand G, Belacel N, Laplante F. Graph theory based model for learning path recommendation. Information Sciences. 2013;251:10-21. doi: 10.1016/j.ins.2013.04.017.
[3] Shi D, Wang T, Xing H, Xu H. A learning path recommendation model based on a multidimensional knowledge graph framework for e-learning. Knowledge-Based Systems. 2020;195:105618. doi: 10.1016/j.knosys.2020.105618.
[4] Zhang S, Hui N, Zhai P, Xu J, Cao L, Wang Q. A fine-grained and multi-context-aware learning path recommendation model over knowledge graphs for online learning communities. Information Processing & Management. 2023;60(5):103464. doi: 10.1016/j.ipm.2023.103464.
[5] Tan C, Han R, Ye R, Chen K. Adaptive learning recommendation strategy based on deep Q-learning. Applied Psychological Measurement. 2020;44(4):251-266. doi: 10.1177/0146621619858674.
[6] Rafferty AN, Brunskill E, Griffiths TL, Shafto P. Faster teaching via POMDP planning. Cognitive Science. 2016;40(6):1290-1332. doi: 10.1111/COGS.12290.
[7] Watkins CJCH, Dayan P. Q-learning. Machine Learning. 1992;8(3-4):279-292. doi: 10.1007/BF00992698.
[8] Sutton RS, Barto AG. Reinforcement Learning: An Introduction. 2nd ed. Cambridge, MA: MIT Press; 2018.
[9] Mirkovic J, Aggarwal A, Weinman D, Lepe P, Mache J, Weiss R. Using terminal histories to monitor student progress on hands-on exercises. In: Proceedings of the 51st ACM Technical Symposium on Computer Science Education; 2020. p. 866-872. doi: 10.1145/3328778.3366935.
[10] Freedman R. Using an operating systems class to strengthen students’ knowledge of C++. In: Proceedings of the 51st ACM Technical Symposium on Computer Science Education; 2020. p. 947-953. doi: 10.1145/3328778.3366936.
[11] Chu ETH, Fang CW. CALEE: A computer-assisted learning system for embedded OS laboratory exercises. Computers & Education. 2015;84:36-48. doi: 10.1016/j.compedu.2015.01.006.
[12] Zhang F, Feng X, Wang Y. Personalized process-type learning path recommendation based on process mining and deep knowledge tracing. Knowledge-Based Systems. 2024;303:112431. doi: 10.1016/j.knosys.2024.112431.
[13] Ma D, Zhu H, Liao S, Chen Y, Liu J, Tian F, Chen P. Learning path recommendation with multi-behavior user modeling and cascading deep Q networks. Knowledge-Based Systems. 2024;294:111743. doi: 10.1016/j.knosys.2024.111743.
[14] Corbett AT, Anderson JR. Knowledge tracing: Modeling the acquisition of procedural knowledge. User Modeling and User-Adapted Interaction. 1995;4:253-278. doi: 10.1007/BF01099821.
[15] Piech C, Bassen J, Huang J, Ganguli S, Sahami M, Guibas LJ, Sohl-Dickstein J. Deep knowledge tracing. In: Advances in Neural Information Processing Systems. 2015;28:505-513.
[16] Romero C, Ventura S. Educational data mining and learning analytics: An updated survey. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery. 2020;10(3):e1355. doi: 10.1002/widm.1355.
 

Sponsors, Associates, and Links

---

• Advances in Educational Technology and Psychology
  
  
• Curriculum and Teaching Methodology
  
  
• Transactions on Comparative Education
  
  
• Applied & Educational Psychology
  
  
• Adult and Higher Education