DeepDomain AI: System Design and Validation for Enterprise AI Talent Training
Journal of Big Data and Computing · 2026-09 · 4 (3) · 166-176
DOI: 10.62517/jbdc.202601321 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Big Data and Computing, 2026-09. Verfasst von Pengyue He und 4 weiteren Autor:innen. Die Arbeit nennt 12 Literaturangaben.
Abstract (Originalsprache)
Enterprise AI roles evolve faster than conventional course catalogs, while direct use of large language models (LLMs) for training-content generation introduces risks such as unsupported claims, non-executable code, and incomplete audit trails. This paper presents DeepDomain AI, a prototype platform for personalized enterprise AI training. Built with React 18 and FastAPI, the platform compares learner evidence with a structured catalog of 15 AI roles, identifies readiness gaps, and organizes role-oriented training paths. Its resource workflow produces foundation-oriented and project-oriented candidates, records structured review results, and applies a publish/correct/reject quality gate. Pydantic schemas constrain model outputs, and a Docker sandbox scores code through task-specific executable assertions rather than source-code keywords. Functional tests cover job analysis, path generation, knowledge recommendation, state persistence, and sandbox execution. In an offline evaluation of 45 constructed learner profiles, dynamic ranking achieved a Top-3 hit rate of 93.33%; on the 30 same-direction profiles used for comparison, the static-label baseline achieved 80.00%. A 20-sample threshold-consistency test produced a 100% interception rate for rule-violating resources and a 0% false-positive rate for rule-compliant resources. In this study, the system was tested with constructed learner profiles rather than data collected from employees. The results therefore describe how the implemented rules and ranking method performed in our test setting; they do not yet show whether the generated resources improve learning or meet expert expectations in practice.
Zitieren
APA
He, P., Cheng, S., Wang, W., Ma, L., & Li, Y. (2026). DeepDomain AI: System Design and Validation for Enterprise AI Talent Training. Journal of Big Data and Computing, 4(3), 166-176. https://doi.org/10.62517/jbdc.202601321
Vancouver
He P, Cheng S, Wang W, Ma L, Li Y. DeepDomain AI: System Design and Validation for Enterprise AI Talent Training. Journal of Big Data and Computing. 2026;4(3):166-176. doi:10.62517/jbdc.202601321
BibTeX
@article{He2026,
author = {He, Pengyue and Cheng, Suya and Wang, Weili and Ma, Lulu and Li, Yutong},
title = {DeepDomain AI: System Design and Validation for Enterprise AI Talent Training},
journal = {Journal of Big Data and Computing},
year = {2026},
volume = {4},
number = {3},
pages = {166--176},
doi = {10.62517/jbdc.202601321}
}
EUVIMED