基于知识图谱检索增强生成的滑坡监测预警系统

吴润泽; 李浩; 梅红波; 王成彬; 朱敏毅; 王红群; 张亮; 胡光鸿; 马明杰; 望致文; 张隆隆; 黄旻; 李振华

doi:10.3799/dqkx.2025.127

基于知识图谱检索增强生成的滑坡监测预警系统

doi: 10.3799/dqkx.2025.127

吴润泽^{1, 2, ,},
李浩³,
梅红波³,
王成彬³,
朱敏毅¹,
王红群¹,
张亮⁴,
胡光鸿⁴,
马明杰⁴,
望致文⁴,
张隆隆³,
黄旻³,
李振华^{4, 5, , ,}

1.
中国地质调查局武汉地质调查中心, 湖北武汉 430205
2.
高坝大库运行安全湖北省重点实验室(中国长江三峡集团有限公司), 湖北宜昌 443133
3.
中国地质大学(武汉)资源学院, 湖北武汉 430074
4.
中国地质大学(武汉)计算机学院, 湖北武汉 430078
5.
新疆理工学院信息工程学院, 新疆阿克苏 843100

基金项目:

中国地质调查局武汉地质调查中心三峡库区后续地质灾害防治信息系统建设项目 0001212012AC50001

详细信息

作者简介:
吴润泽（1979-），男，高级工程师，长期从事地质灾害防治信息化研究. ORCID：0000-0003-1063-1431. E-mail：jcywurunze@mail.cgs.gov.cn

通讯作者:
李振华（1969-），男，教授，ORCID：0000-0003-1497-4407. E-mail: zhli@cug.edu.cn

中图分类号: P694
计量
- 文章访问数: 208
- HTML全文浏览量: 10
- PDF下载量: 20
- 被引次数: 0
出版历程
- 收稿日期: 2025-03-04
- 刊出日期: 2025-10-25

A Landslide Monitoring and Early Warning System with Retrieval-Augmented Generation Enhanced by Knowledge Graph

1.
Wuhan Center of China Geological Survey, Wuhan 430205, China
2.
Hubei Key Laboratory of Operation Safety of High Dam and Large Reservoir (China Three Gorges Corporation), Yichang 443133, China
3.
School of Earth Resources, China University of Geosciences, Wuhan 430074, China
4.
School of Computer, China University of Geosciences, Wuhan 430078, China
5.
School of Information Engineering, Xinjiang Institute of Technology, Akesu 843100, China

摘要

摘要: 针对当前滑坡防治工作中文字报告中的知识提取和利用问题，探索出一套基于地灾资料和数据的知识图谱构建和运用方法，促进地灾防控工作从数据管理到知识管理转型.对182份报告、22篇规范、5篇文献、4 668个滑坡点和313项治理工程的基础数据、3年来的历史灾情数据、当前滑坡监测数据和预报的天气数据进行了知识提取和图谱构建，并采用检索增强生成技术实现多源知识的整合和输出.建成了一个具有12 797个实体、34 873个关系、9 658个chunk的知识图谱系统，实现了4 518个滑坡的10天预警.知识图谱技术可有效提取文字报告中的知识，检索增强生成技术可有效整合多个知识来源，提高知识问答的准确性.
- 三峡库区 /
- 滑坡监测预警 /
- 知识图谱 /
- 大语言模型 /
- 检索增强生成 /
- 工程地质学
Abstract: Aiming at the current problem of knowledge extraction and utilization from text reports in landslide prevention and control work, this study explores a set of methods for constructing and applying a knowledge graph based on geological disaster data and materials, promoting the transformation of geological disaster prevention from data management to knowledge management. Knowledge extraction and knowledge graph construction were conducted on basic data from 182 reports, 22 specifications, 5 literatures, 4 668 landslide points, and 313 governance projects, as well as three years of historical disaster data, current landslide monitoring data, and forecasted weather data. Retrieval-augmented generation (RAG) technology was adopted to integrate and output multi-source knowledge. A knowledge graph system with 12 797 entities, 34 873 relationships, and 9 658 chunks was established, enabling 10-day early warning for 4 518 landslides. Knowledge graph technology effectively extracts knowledge from text reports, and RAG technology efficiently integrates multiple knowledge sources, improving the accuracy of knowledge question-answering.
- Three Gorges reservoir area /
- landslide monitoring and early warning /
- knowledge graph /
- large language model /
- retrieval-augmented generation /
- engineering geology

HTML全文

图 1 三峡库区滑坡监测预警知识图谱构建技术路线

Fig. 1. Construction approach of a knowledge graph for landslide monitoring and early warning in the Three Gorges reservoir area

下载: 全尺寸图片幻灯片

图 2 三峡库区滑坡灾害监测预警本体模型

Fig. 2. Ontology model for landslide monitoring and early warning in the Three Gorges reservoir area

下载: 全尺寸图片幻灯片

图 3 三峡库区滑坡监测预警知识图谱模式层

Fig. 3. Schema layer of the knowledge graph for landslide monitoring and early warning in the Three Gorges reservoir area

下载: 全尺寸图片幻灯片

图 4 基于结构化数据映射的知识图谱

Fig. 4. Knowledge graph based on structured data mapping

下载: 全尺寸图片幻灯片

图 5 基于Prodigy的实体与关系标注

Fig. 5. Entity and relation annotation using Prodigy

下载: 全尺寸图片幻灯片

图 6 张家湾滑坡勘察报告信息抽取实例

Fig. 6. An example of information extraction from Zhangjiawan landslide investigation report

下载: 全尺寸图片幻灯片

图 7 基于大型语言模型的知识图谱构建实例

Fig. 7. Knowledge graph construction based on large language model

下载: 全尺寸图片幻灯片

图 8 三峡库区滑坡监测预警系统RAG问答架构

Fig. 8. RAG Q & A architecture of the landslide monitoring and early warning in the Three Gorges reservoir area

下载: 全尺寸图片幻灯片

参考文献(45)

Abu-Salih, B., 2021. Domain-Specific Knowledge Graphs: A Survey. Journal of Network and Computer Applications, 185: 103076. https://doi.org/10.1016/j.jnca.2021.103076
Cao, X. G., Zhang, M. Y., Lei, Z., et al., 2021. Construction and Application of Knowledge Graph for Coal Mine Equipment Maintenance. Industry and Mine Automation, 47(3): 41-45 (in Chinese with English abstract).
Cheatham, M., Krisnadhi, A., Amini, R., et al., 2018. The GeoLink Knowledge Graph. Big Earth Data, 2(2): 131-143. https://doi.org/10.1080/20964471.2018.1469291
Chen, L. J., Peng, L., & Yang, L. N., 2024. Improving Landslide Prediction: Innovative Modeling and Evaluation of Landslide Scenario with Knowledge Graph Embedding. Remote Sensing, 16(1): 145. https://doi.org/10.3390/rs16010145
Du, Z. Q., Li, Y., Zhang, Y. T., et al., 2020. Knowledge Graph Construction Method on Natural Disaster Emergency. Geomatics and Information Science of Wuhan University, 45(9): 1344-1355 (in Chinese with English abstract).
Fan, R. Y., Wang, L. Z., Yan, J. N., et al., 2020. Deep Learning-Based Named Entity Recognition and Knowledge Graph Construction for Geological Hazards. ISPRS International Journal of Geo-Information, 9(1): 15. https://doi.org/10.3390/ijgi9010015
Feng, J., Xu, X., Lu, J. M., 2019. Construction and Application of Water Conservancy Information Knowledge Graph. Computer and Modernization, (9): 35-40 (in Chinese with English abstract).
Gui, H., L. Yuan, L., Ye, H., et al., 2024. Iepile: Unearthing Large-Scale Schema-Based Information Extraction Corpus. https://arxiv.org/pdf/2402.14710
Han, T., Huang, H. S., Yao, L. G., 2021. Entity Extraction for Aero-Engine Fault Knowledge Graph. Modular Machine Tool & Automatic Manufacturing Technique, (10): 69-73, 78 (in Chinese with English abstract).
Hogan, A., Blomqvist, E., Cochez, M., et al., 2021. Knowledge Graphs. ACM Computing Surveys, 54(4): 1-37. https://doi.org/10.1145/3447772
Li, X. P., Xu, J. H., Guo, Z. M., et al., 2019. Construction and Application of Knowledge Graph of Power Dispatching Automation System. Electric Power, 52(2): 70-77, 157 (in Chinese with English abstract).
Liu, W. C., 2022. Construction and Application of Landslide Knowledge Graph (Dissertation). Hefei University of Technology, Hefei (in Chinese with English abstract).
Lyu, H. K., Hong, L., Ma, F. C., 2020. Constructing Knowledge Graph for Financial Equities. Data Analysis and Knowledge Discovery, 4(5): 27-37 (in Chinese with English abstract).
Ma, X. G., Ma, C., Wang, C. B., 2020. A New Structure for Representing and Tracking Version Information in a Deep Time Knowledge Graph. Computers & Geosciences, 145: 104620. https://doi.org/10.1016/j.cageo.2020.104620
Pu, T. J., Tan, Y. P., Peng, G. Z., et al., 2021. Construction and Application of Knowledge Graph in the Electric Power Field. Power System Technology, 45(6): 2080-2091 (in Chinese with English abstract).
Qi, G. L., Gao, H., Wu, T. X., 2017. The Research Advances of Knowledge Graph. Technology Intelligence Engineering, 3(1): 4-25 (in Chinese with English abstract).
Qiu, Q. J., Wu, L., Ma, K., et al., 2023. A Knowledge Graph Construction Method for Geohazard Chain for Disaster Emergency Response. Earth Science, 48(5): 1875-1891 (in Chinese with English abstract).
Raskin, R. G., Pan, M. J., 2005. Knowledge Representation in the Semantic Web for Earth and Environmental Terminology (SWEET). Computers & Geosciences, 31(9): 1119-1125. https://doi.org/10.1016/j.cageo.2004.12.004
Ruan, T., Sun, C. L., Wang, H. F., et al., 2016. Construction of Traditional Chinese Medicine Knowledge Graph and Its Application. Journal of Medical Informatics, 37(4): 8-13 (in Chinese with English abstract).
Singhal, 2012. Official Google Blog: Introducing the Knowledge Graph: Things, not Strings. http://googleblog.blogspot.pt/2012/05/introducing-knowledge-graph-things-not.html
Wang, C. B., Ma, X. G., Chen, J. G., et al., 2018. Information Extraction and Knowledge Graph Construction from Geoscience Literature. Computers & Geosciences, 112: 112-120. https://doi.org/10.1016/j.cageo.2017.12.007
Xu, Q., Cui, S. H., Huang, W., et al., 2023. Construction of a Landslide Knowledge Graph in the Field of Engineering Geology. Geomatics and Information Science of Wuhan University, 48(10): 1601-1615 (in Chinese with English abstract).
Xu, Z. L., Sheng, Y. P., He, L. R., et al., 2016. Review on Knowledge Graph Techniques. Journal of University of Electronic Science and Technology of China, 45(4): 589-606 (in Chinese with English abstract).
Zhang, X. Y., Huang, Y., Zhang, C. J., et al., 2022. Geoscience Knowledge Graph (GeoKG): Development, Construction and Challenges. Transactions in GIS, 26(6): 2480-2494. https://doi.org/10.1111/tgis.12985
Zhang, Z. X., 2023. Stability Evaluation of High Slopes under Earthquake and Rainfall Based on Transfer Coefficient Method. Shaanxi Water Resources, (4): 14-15, 18 (in Chinese with English abstract).
Zhou, C. H., Wang, H., Wang, C. S., et al., 2021. Research on Geo-Knowledge Map in the Age of Big Data. Scientia Sinica (Terrae), 51(7): 1070-1079 (in Chinese). doi: 10.1360/SSTe-2020-0337
Zhou, Y. F., Duan, H., Zhao, H. L., et al., 2024. Hydrological Modeling Knowledge Graph Construction and Application. Journal of Hydraulic Engineering, 55(1): 80-91 (in Chinese with English abstract).
Zhu, Y. Q., Sun, K., Wang, S., et al., 2023. An Adaptive Representation Model for Geoscience Knowledge Graphs Considering Complex Spatiotemporal Features and Relationships. Science China Earth Sciences, 66(11): 2563-2578. https://doi.org/10.1007/s11430-022-1169-9
Zou, X. H., 2020. A Survey on Application of Knowledge Graph. Journal of Physics: Conference Series, 1487(1): 012016. https://doi.org/10.1088/1742-6596/1487/1/012016
曹现刚, 张梦园, 雷卓, 等, 2021. 煤矿装备维护知识图谱构建及应用. 工矿自动化, 47(3): 41-45.
杜志强, 李钰, 张叶廷, 等, 2020. 自然灾害应急知识图谱构建方法研究. 武汉大学学报(信息科学版), 45(9): 1344-1355.
冯钧, 徐新, 陆佳民, 2019. 水利信息知识图谱的构建与应用. 计算机与现代化, (9): 35-40.
韩涛, 黄海松, 姚立国, 2021. 面向航空发动机故障知识图谱构建的实体抽取. 组合机床与自动化加工技术, (10): 69-73, 78.
李新鹏, 徐建航, 郭子明, 等, 2019. 调度自动化系统知识图谱的构建与应用. 中国电力, 52(2): 70-77, 157.
刘文聪, 2022. 滑坡知识图谱构建及应用(硕士学位论文). 合肥: 合肥工业大学.
吕华揆, 洪亮, 马费成, 2020. 金融股权知识图谱构建与应用. 数据分析与知识发现, 4(5): 27-37.
蒲天骄, 谈元鹏, 彭国政, 等, 2021. 电力领域知识图谱的构建与应用. 电网技术, 45(6): 2080-2091.
漆桂林, 高桓, 吴天星, 2017. 知识图谱研究进展. 情报工程, 3(1): 4-25.
邱芹军, 吴亮, 马凯, 等, 2023. 面向灾害应急响应的地质灾害链知识图谱构建方法. 地球科学, 48(5): 1875-1891. doi: 10.3799/dqkx.2022.313
阮彤, 孙程琳, 王昊奋, 等, 2016. 中医药知识图谱构建与应用. 医学信息学杂志, 37(4): 8-13.
许强, 崔圣华, 黄维, 等, 2023. 面向工程地质领域的滑坡知识图谱构建方法研究. 武汉大学学报(信息科学版), 48(10): 1601-1615.
徐增林, 盛泳潘, 贺丽荣, 等, 2016. 知识图谱技术综述. 电子科技大学学报, 45(4): 589-606.
张忠孝, 2023. 基于传递系数法地震及降雨作用下库岸高边坡稳定性评价. 陕西水利, (4): 14-15, 18.
周成虎, 王华, 王成善, 等, 2021. 大数据时代的地学知识图谱研究. 中国科学: 地球科学, 51(7): 1070-1079.
周逸凡, 段浩, 赵红莉, 等, 2024. 水文模型知识图谱构建与应用. 水利学报, 55(1): 80-91.

施引文献

资源附件(9)

附图5 数据查询型问答示例.jpg
附图1 三峡库区滑坡知识图谱示意图.jpg
附图6 知识查询型问答示例.jpg
附图4 三峡库区滑坡预警结果图.jpg
附图2 三峡库区滑坡监测预警知识管理界面.jpg
附图7 统计分析型问答示例.jpg
附图8 统计推理型问答示例.jpg
附图3 张家湾滑坡的知识图谱画像.jpg
附图9 预测预报型问答示例.jpg