Article Details

Title · Authors · Abstract · Keywords · DOI · References

Research on Knowledge Graph Construction Methods for Human Factors Engineering Experimental Teaching Based on LLMs

YAO Yanzi, YAN Jingbin

(Department of Industrial Engineering, Tsinghua University, Beijing 100084, China)

Section：Information Application · Vol. 2026, Issue 6 · Pages：161-168 · 2096-4706（2026）06-0161-08 · CLC number：TP391.1 · Document code：A · DOI：10.19850/j.cnki.2096-4706.2026.06.030

Abstract

To address the complexity, resource fragmentation, and weak logical structure in human factors engineering experimental teaching, this study proposes a method for constructing a knowledge graph for human factors engineering experimental teaching based on Large Language Models (LLMs). By constructing a standardized corpus for human factors engineering, designing the conceptual nodes and a knowledge ontology, and fine-tuning the GLM-4-Flash model, the accurate semantic analysis of human factors experimental design is finally achieved. Meanwhile, the Neo4j graph database is used to dynamically construct the Knowledge Graph to lower the barrier to knowledge learning. The innovation of this study lies in the first-time in-depth integration of LLM-based semantic understanding and dynamic graph construction in the field of human factors engineering experimental teaching, providing a scalable technical solution for the intellectualization of human factors engineering experimental teaching.

Keywords

human factors engineering; experimental teaching; Knowledge Graph; Neo4j graph database

References

  1. [1] International Organization for Standardization. Ergonomics Principles in the Design of Work Systems: ISO 6385: 2016 [S].Geneva: International Organization for Standardization，2016.
  2. [2] RIZUN M. Knowledge Graph Application in Education: A Literature Review [J].Acta Universitatis Lodziensis.Folia Oeconomica，2019，3（342）：7-19.
  3. [3] CARTA S，GIULIANI A，PIANO L，et al. Iterative Zero-shot LLM Prompting for Knowledge Graph Construction [J/OL].arXiv:2307.01128 [cs.CL].（2023-07-03）.https://arxiv.org/abs/2307.01128.
  4. [4] ABU-RASHEED H，JUMBO C，AMIN R A，et al. LLM-assisted Knowledge Graph Completion for Curriculum and Domain Modelling in Personalized Higher Education Recommendations [J/OL].arXiv:2501.12300 [cs.HC].（2025-01-21）.https://arxiv.org/abs/2501.12300.
  5. [5] ZHU Y Q，WANG X H，CHEN J，et al. LLMs for Knowledge Graph Construction and Reasoning: Recent Capabilities and Future Opportunities [J/OL].arXiv:2305.13168 [cs.CL].（2023-05-22）.https://arxiv.org/abs/2305.13168.
  6. [6] IDE T，MURATA E，KAWAHARA D，et al. PHALM: Building a Knowledge Graph from Scratch by Prompting Humans and a Language Model [J/OL].arXiv:2310.07170 [cs.CL].（2023-10-11）.https://arxiv.org/abs/2310.07170.
  7. [7] REALES D，MANRIQUE R，GRÉVISSE C. Core Concept Identification in Educational Resources via Knowledge Graphs and Large Language Models [J/OL].SN Computer Science，2024，5（8）：1029（2024-11-06）[2025-06-11].https://link.springer.com/article/10.1007/s42979-024-03341-y.
  8. [8] BUI T，TRAN O，NGUYEN P，et al. Cross-data Knowledge Graph Construction for LLM-enabled Educational Question-answering System: A Case Study at HCMUT [C]//AIQAM '24: Proceedings of the 1st ACM Workshop on AI-Powered Q&A Systems for Multimedia.Phuket：ICMR，2024：36-43.
  9. [9] DU Z X，QIAN Y J，LIU X，et al. GLM: General Language Model Pretraining with Autoregressive Blank Infilling [J/OL].arXiv:2103.10360 [cs.CL].（2021-03-18）.https://arxiv.org/abs/2103.10360.
  10. [10] PAN J Z. Resource Description Framework [M]//Handbook on Ontologies.Berlin：Springer，2009：71-90.
  11. [11] SANDERS M S，MCCORMICK E J. Human Factors in Engineering and Design：6th ed [M].New York：Mcgraw-Hill Book Company，1987.
  12. [12] ALYAN E，SAAD N M，KAMEL N. Effects of Workstation Type on Mental Stress：FNIRS Study [J].Human Factors，2021，63（7）：1230-1255.
  13. [13] HU E J，SHEN Y，WALLIS P，et al. LoRA：Low-Rank Adaptation of Large Language Models [J/OL].arXiv:2106.09685 [cs.CL].（2021-06-17）.https://arxiv.org/abs/2106.09685.
  14. [14] FRANCIS N，GREEN A，GUAGLIARDO P，et al. Cypher: An Evolving Query Language for Property Graphs [C]//SIGMOD'18: Proceedings of the 2018 International Conference on Management of Data.Houston：ACM，2018：1433-
  15. 1445.
  16. [15] ROBINSON I，WEBBER J，EIFREM E. Graph Databases: New Opportunities for Connected Data：2nd ed [M].Sebastopol：O'Reilly Media，2015.

About the authors

Yao Yanzi (July 2004-), female, Han ethnicity, from Daqing, Heilongjiang Province, is currently pursuing a bachelor's degree. Her research interests include the application of large model intelligent agents and the application of large models in the field of quantitative trading; Yan Jingbin (1972.11-), female, Han ethnicity, from Fuzhou, Fujian, is a senior engineer with a master's degree. Her research interests include human factors engineering, production and logistics management, systems engineering, and system simulation.