Design and Application of an AIGC Music Generation Framework
International Journal of Knowledge Management · 20.02.2026 · 22 (1) · 1-18
DOI: 10.4018/ijkm.402193 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Knowledge Management, erschienen am 20.02.2026. Verfasst von Hongyu Zhao. Die Arbeit nennt 29 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 3.0).
Abstract (Originalsprache)
In creative industries, AIGC music technologies hold promise for advancing organizational knowledge creation and reuse, but face barriers in resource efficiency, collaborative controllability, and alignment with knowledge management goals. This study develops a hybrid Transformer-GNN framework with a dual-loop control mechanism, tailored to support KM processes: knowledge capture, transfer, and reuse. Evaluations on MAESTRO-v3, Lakh-Clean, and a custom dataset show the framework outperforms mainstream models in Pitch Accuracy (85.3%), Harmonic Coherence (0.78), and Structure Completeness (0.73), with optimized resource use (36-hour training, 18.8 GB peak GPU memory). User studies confirm a 26% reduction in manual revisions, enhancing knowledge transfer between AI and human teams. This work provides a deployable AIGC solution bridging technical innovation and organizational KM needs in creative contexts.
Zitieren
APA
Zhao, H. (2026). Design and Application of an AIGC Music Generation Framework. International Journal of Knowledge Management, 22(1), 1-18. https://doi.org/10.4018/ijkm.402193
Vancouver
Zhao H. Design and Application of an AIGC Music Generation Framework. International Journal of Knowledge Management. 2026;22(1):1-18. doi:10.4018/ijkm.402193
BibTeX
@article{Zhao2026,
author = {Zhao, Hongyu},
title = {Design and Application of an AIGC Music Generation Framework},
journal = {International Journal of Knowledge Management},
year = {2026},
volume = {22},
number = {1},
pages = {1--18},
doi = {10.4018/ijkm.402193}
}
EUVIMED