arXiv cs.CL· Yutai Duan, Yahui Zhao, Zhangti Li, Yu Ma, Zhenfeng Qi, Shaoyang Yuan, Jing Fan, Jie Liu·· 9 天前AI 评分37
中国联通 UniDataAgent：面向企业问报到自动化的本体驱动智能体
UniDataAgent: An Ontology-Grounded Agent for Enterprise Question-to-Report Automation
AI 导读
中国联通提出本体驱动的 UniDataAgent，将语义获取与在线执行分离，用于可复用的企业问报到分析。其本体构建在 27 张企业表、约数千种指标类型上仅需数小时，而人工约需一周；报告生成只需几分钟，而非数个工作日。本体 grounding 在真实业务问题上取得 95.0% 严格准确率，高于文档 RAG 的 72.5%，系统已部署并带来成本节省。
正文 · 原文
Abstract:Enterprise data agents must preserve organization specific semantics, not just translate questions into queries. We present ChinaUnicom DataAgent (UniDataAgent), an ontology grounded system for reusable question-to-report analysis that separates semantic acquisition from online execution. Ontology Acquisition and Validation stage (OAV) builds versioned enterprise ontologies from metadata, business knowledge, and supporting materials through expert authored business skills, constrained generation, question verification, and selected expert review. Question-to-Report Execution (QRE) stage retrieves semantic contracts for each question, coordinates skills and data tools, validates results, and produces evidence linked reports. Across 27 enterprise tables and roughly thousands of metric types, ontology construction took a few hours instead of about one week manually. It took just a few minutes to generate the reports, instead of several working days. Ontology grounding achieved 95.0\% strict accuracy on real business questions, versus 72.5\% for document RAG, especially on structured and compositional tasks. The system has already been deployed to generate cost savings and has the potential to be replicated in other enterprises.
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2609.27257 [cs.CL] |
| (or arXiv:2609.27257v2 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2609.27257 arXiv-issued DOI via DataCite |
Submission history
From: Yutai Duan [view email]
[v1]
Wed, 23 Sep 2026 02:42:34 UTC (2,522 KB)
[v2]
Thu, 8 Oct 2026 09:04:09 UTC (2,522 KB)
来源：arXiv cs.CL · arxiv.org