A Knowledge-Graph and Constraint-Solving Engine for Explainable Engineering Learning Pathways

Authors

1 School of Business, Wake Forest University, Winston-Salem, USA 27109
2 College of Computing, Georgia Institute of Technology, Atlanta, USA 30332
Corresponding author: ychen841@gatech.edu

DOI:

https://doi.org/10.63646/XYHQ3611

Keywords:

Knowledge Graphs, Constraint Programming, Engineering Education, Learning Pathways, Explainable AI, Competency Standards

Abstract

Engineering learners move through pathways that connect standards, local course outcomes, prerequisites, practical tasks, assessment evidence, equipment, and safety requirements. A graph can represent these relationships, but graph reachability alone does not guarantee that a proposed sequence is feasible, accessible, current, or safe. A recommender can rank activities, yet a score does not show which rules made a path admissible or why an alternative was excluded. This article specifies a knowledge-graph and constraint-solving engine for generating explainable engineering learning pathways. The design separates a versioned curriculum graph from a privacy-minimized learner-state view, compiles approved competency goals and graph relationships into a finite-domain constraint model, and uses a constraint programming solver to find sequences that satisfy hard prerequisites, safety, availability, and learner access requirements while optimizing declared preferences. Each path is accompanied by an evidence-linked explanation that identifies the target outcome, prerequisite chain, constraints applied, trade-offs, and unresolved conditions. If no feasible path exists, the system reports a conflict set and offers only policy-approved alternatives; it never relaxes a safety rule automatically. A synthetic microgrid-design scenario illustrates the model, and a conformance and evaluation plan defines tests for semantic integrity, solver correctness, explanation fidelity, accessibility, privacy, and curriculum review. No empirical deployment or learning-effect result is claimed. The engine is intended as decision support that leaves curriculum authority with educators and pathway choice with learners.

How to Cite

Wang, Z., & Chen, Y. (2026). A Knowledge-Graph and Constraint-Solving Engine for Explainable Engineering Learning Pathways. Trends and Reviews of Technological Engineering in Education, 2(3), 96-116. https://doi.org/10.63646/XYHQ3611

References

ABET, “Criteria for Accrediting Engineering Programs, 2025–2026,” Engineering Accreditation Commission, 2025. https://www.abet.org/accreditation/accreditation-criteria/criteria-for-accrediting-engineering-programs-2025-2026/

1EdTech Consortium, “Competencies and Academic Standards Exchange (CASE) Service, Version 1.1 Specification,” accessed 8 October 2026. https://www.1edtech.org/standards/case

S. Zhang, N. Hui, P. Zhai, J. Xu, L. Cao, and Q. Wang, “A Fine-Grained and Multi-Context-Aware Learning Path Recommendation Model over Knowledge Graphs for Online Learning Communities,” Information Processing & Management, vol. 60, no. 5, art. 103464, 2023. https://doi.org/10.1016/j.ipm.2023.103464

A. Garrido, L. Onaindia, and F. Sapena, “Planning and Scheduling in an E-Learning Environment: A Constraint-Programming-Based Approach,” Engineering Applications of Artificial Intelligence, vol. 21, no. 5, pp. 733–743, 2008. https://doi.org/10.1016/j.engappai.2008.03.009

A. Hogan et al., “Knowledge Graphs,” ACM Computing Surveys, vol. 54, no. 4, art. 71, pp. 1–37, 2021. https://doi.org/10.1145/3447772

R. Cyganiak, D. Wood, and M. Lanthaler, eds., “RDF 1.1 Concepts and Abstract Syntax,” W3C Recommendation, 25 February 2014. https://www.w3.org/TR/rdf11-concepts/

W3C OWL Working Group, “OWL 2 Web Ontology Language Document Overview, Second Edition,” W3C Recommendation, 11 December 2012. https://www.w3.org/TR/owl2-overview/

H. Knublauch and D. Kontokostas, eds., “Shapes Constraint Language (SHACL),” W3C Recommendation, 20 July 2017. https://www.w3.org/TR/shacl/

Google for Developers, “CP-SAT Solver,” OR-Tools Documentation, accessed 2026. https://developers.google.com/optimization/cp/cp_solver

B. Bogaerts, E. Gamba, and T. Guns, “A Framework for Step-Wise Explaining How to Solve Constraint Satisfaction Problems,” Artificial Intelligence, vol. 300, art. 103550, 2021. https://doi.org/10.1016/j.artint.2021.103550

E. Gamba, B. Bogaerts, and T. Guns, “Efficiently Explaining CSPs with Unsatisfiable Subset Optimization,” in Proceedings of the 30th International Joint Conference on Artificial Intelligence (IJCAI-21), pp. 1381–1388, 2021. https://doi.org/10.24963/ijcai.2021/191

T. Lebo, S. Sahoo, and D. McGuinness, eds., “PROV-O: The PROV Ontology,” W3C Recommendation, 30 April 2013. https://www.w3.org/TR/prov-o/

R. Dechter, Constraint Processing. San Francisco, CA: Morgan Kaufmann, 2003.

A. K. Mackworth, “Consistency in Networks of Relations,” Artificial Intelligence, vol. 8, no. 1, pp. 99–118, 1977. https://doi.org/10.1016/0004-3702(77)90007-8

A. Pardo and G. Siemens, “Ethical and Privacy Principles for Learning Analytics,” British Journal of Educational Technology, vol. 45, no. 3, pp. 438–450, 2014. https://doi.org/10.1111/bjet.12152

National Institute of Standards and Technology, “NIST Privacy Framework: A Tool for Improving Privacy through Enterprise Risk Management, Version 1.0,” NIST, 2020. https://doi.org/10.6028/NIST.CSWP.01162020

S. Slade and P. Prinsloo, “Learning Analytics: Ethical Issues and Dilemmas,” American Behavioral Scientist, vol. 57, no. 10, pp. 1510–1529, 2013. https://doi.org/10.1177/0002764213479366

W3C, “Web Content Accessibility Guidelines (WCAG) 2.2,” W3C Recommendation, 5 October 2023. https://www.w3.org/TR/WCAG22/