Automated Construction of Job–Skill Knowledge Graphs Based on Multi-Agent Consensus and Four-Layer Verification
Journal of Big Data and Computing · 2026-09 · 4 (3) · 133-145
DOI: 10.62517/jbdc.202601318 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Big Data and Computing, 2026-09. Verfasst von Lusheng Sun und 8 weiteren Autor:innen. Die Arbeit nennt 19 Literaturangaben.
Abstract (Originalsprache)
To construct reliable job–skill knowledge graphs from heterogeneous recruitment texts, this study combines multi-agent consensus with a four-layer verification cascade. Three large language models from different vendors (iFlytek Spark, DeepSeek, Zhipu GLM-4-Flash) first annotate each JD independently under distinct cognitive roles, then converge through peer review and voting; uncertain skills are subsequently checked against knowledge graph lookup, ESCO alignment, web search, and manual review. Evaluated on 3,942 real-world JDs, the method attains an F1-score of 89.0%, improving by 4.2 points over the best single model and 13.5 points over traditional NER; the cascade reduces the hallucination rate from 15.0% to 1.4%. The ESCO alignment rate of 71.5% leaves room for improvement in covering indigenous Chinese technologies, yet the framework offers a practical pathway for occupational skill standardization and intelligent talent services.
Zitieren
APA
Sun, L., Zhou, H., Chen, M., Song, M., Wang, Q., Guo, H., Yang, J., Zhao, Q., & Yan, R. (2026). Automated Construction of Job–Skill Knowledge Graphs Based on Multi-Agent Consensus and Four-Layer Verification. Journal of Big Data and Computing, 4(3), 133-145. https://doi.org/10.62517/jbdc.202601318
Vancouver
Sun L, Zhou H, Chen M, Song M, Wang Q, Guo H, et al. Automated Construction of Job–Skill Knowledge Graphs Based on Multi-Agent Consensus and Four-Layer Verification. Journal of Big Data and Computing. 2026;4(3):133-145. doi:10.62517/jbdc.202601318
BibTeX
@article{Sun2026,
author = {Sun, Lusheng and Zhou, Hangyu and Chen, Mengfei and Song, Mengfan and Wang, Qi and Guo, Hengxu and Yang, Jingyuan and Zhao, Qihang and Yan, Ruian},
title = {Automated Construction of Job–Skill Knowledge Graphs Based on Multi-Agent Consensus and Four-Layer Verification},
journal = {Journal of Big Data and Computing},
year = {2026},
volume = {4},
number = {3},
pages = {133--145},
doi = {10.62517/jbdc.202601318}
}
EUVIMED