{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,10]],"date-time":"2026-10-10T00:49:46Z","timestamp":1791593386113,"version":"4.3.4"},"reference-count":12,"publisher":"Darcy & Roy Press Co. Ltd.","issue":"1","license":[{"start":{"date-parts":[[2026,10,9]],"date-time":"2026-10-09T00:00:00Z","timestamp":1791504000000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["FCIS"],"abstract":"<jats:p>Urban rail transit data are distributed across heterogeneous operational systems, where inconsistent semantics and fragmented metric definitions complicate the controlled use of large language models (LLMs) for natural language analytics. This study proposes a semantic data governance and collaborative analytics architecture for this setting. A lakehouse-based data foundation, a semantic middle layer, and a unified metric store are used to organize physical schemas, business terminology, and statistical definitions. Domain rules, network topology, and a controlled execution workflow are then introduced to constrain query generation and support cross-domain analysis. Two representative scenarios\u2014power-supply fault assistance and passenger-flow\u2013traction-energy analysis\u2014are used to illustrate how data governance, knowledge augmentation, and execution validation work together. The contribution is an engineering architecture and its semantic governance mechanisms rather than a comparative evaluation of general-purpose LLM algorithms. The proposed approach provides a practical reference for integrating LLM-based analytics with existing urban rail transit data environments.<\/jats:p>","DOI":"10.54097\/h1w4bf42","type":"journal-article","created":{"date-parts":[[2026,10,10]],"date-time":"2026-10-10T00:02:37Z","timestamp":1791590557000},"page":"138-143","source":"Crossref","is-referenced-by-count":0,"title":["Semantic Data Governance and Collaborative Architecture for LLM-Based Natural Language Analytics in Urban Rail Transit"],"prefix":"10.54097","volume":"18","author":[{"given":"Shiqi","family":"Xiong","sequence":"first","affiliation":[{"name":"School of Intelligent Manufacturing, Jianghan University, Wuhan, Hubei, 430100, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guodong","family":"Liu","sequence":"additional","affiliation":[{"name":"Beijing Urban Construction Design & Development Group Co., Limited, Beijing, 100037, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"32412","published-online":{"date-parts":[[2026,10,9]]},"reference":[{"key":"468375","unstructured":"[1] Chen, L., Yang, Y., & Gong, B. (2025). Security protection system for intelligent rail transit data: Challenges, technologies, and future evolution. Urban Rapid Rail Transit. (in Chinese)"},{"key":"468376","unstructured":"[2] Yao, Q., Yang, T., Yang, J., Wu, J., & Huang, M. (2025, November 24). Design and implementation of a multi-agent collaborative intelligent question-answering system for radio management. Radio Communications Technology. (in Chinese)"},{"key":"468377","unstructured":"[3] Liu, Y., Huang, W., & Zhou, S. (2025). A collaborative multi-agent architecture for risk intelligence perception and early warning in emergencies. Library and Information Service. (in Chinese)"},{"key":"468378","unstructured":"[4] Jia, Z., Zhang, J., He, H., Feng, S., & Liu, Y. (2026). Survey on mutually augmenting technologies and applications of large models and knowledge graphs. Computer Science, 53(8), 219\u2013228. https:\/\/doi.org\/10.11896\/jsjkx.250700129. (in Chinese)"},{"key":"468379","unstructured":"[5] Zhu, X., Yao, H., Liu, J., & Xiong, X. (2024). Review of the evolution of large language model algorithms. ZTE Technology Journal, 30(2), 9\u201320. (in Chinese)"},{"key":"468380","unstructured":"[6] Zhou, Y., Cai, P., & Dong, Z. (2024). Large language model knowledge management system. ZTE Technology Journal, 30(2), 63\u201371. (in Chinese)"},{"key":"468381","unstructured":"[7] Jiang, X., Zang, Y., Xie, Z., Ju, Y., Liu, Y., & Sheng, G. (2025). Application model of DeepSeek-like paradigm in fault diagnosis of power equipment. High Voltage Engineering, 51(8), 4006\u20134021. (in Chinese)"},{"key":"468382","doi-asserted-by":"crossref","unstructured":"[8] Kou, G., Tang, X., Chen, X., Wang, X., & Chang, J. (2025). A new paradigm of large-model collaborative digital-intelligent decision-making: Key mechanisms and future prospects. Bulletin of National Natural Science Foundation of China, 39(5), 728\u2013735. https:\/\/doi.org\/10.3724\/BNSFC-2025.07.14.0001. (in Chinese)","DOI":"10.3724\/BNSFC-2025.07.14.0001"},{"key":"468383","unstructured":"[9] Cui, L., Wang, Z., Bao, Y., & Zhao, H. (2026). A survey on question answering systems and evaluation in the era of large models. Computer Engineering and Applications, 62(5), 1\u201317. https:\/\/doi.org\/10.3778\/j.issn.1002-8331.2503-0004. (in Chinese)"},{"key":"468384","unstructured":"[10] Han, Y., & Wei, G. (2026). Overview of task optimization and domain application development of knowledge graph and recommendation algorithm. Computer Engineering and Applications, 62(10), 26\u201353. https:\/\/doi.org\/10.3778\/j.issn.1002-8331.2505-0279. (in Chinese)"},{"key":"468385","unstructured":"[11] Han, B., & Liu, T. (2024). Key technologies and applications of large models. ZTE Technology Journal, 30(2), 76\u201388. https:\/\/doi.org\/10.12142\/ZTETJ.202402012. (in Chinese)"},{"key":"468386","unstructured":"[12] Tian, H., Zhang, M., Chang, R., & Tong, X. (2024). A survey on large model training technologies. ZTE Technology Journal, 30(2), 21\u201328. https:\/\/doi.org\/10.12142\/ZTETJ.202402004. (in Chinese)"}],"container-title":["Frontiers in Computing and Intelligent Systems"],"original-title":[],"link":[{"URL":"https:\/\/drpress.org\/ojs\/index.php\/fcis\/article\/download\/36068\/35224","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/drpress.org\/ojs\/index.php\/fcis\/article\/download\/36068\/35224","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,10]],"date-time":"2026-10-10T00:02:40Z","timestamp":1791590560000},"score":1,"resource":{"primary":{"URL":"https:\/\/drpress.org\/ojs\/index.php\/fcis\/article\/view\/36068"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10,9]]},"references-count":12,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,9,28]]}},"URL":"https:\/\/doi.org\/10.54097\/h1w4bf42","relation":{},"ISSN":["2832-6024"],"issn-type":[{"value":"2832-6024","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,9]]}}}