计算机科学与探索2024，Vol.18Issue(6)：1637-1647,11.DOI:10.3778/j.issn.1673-9418.2311098
基于大语言模型的水工程调度知识图谱的构建与应用
Construction and Application of Knowledge Graph for Water Engineering Sched-uling Based on Large Language Model
摘要
Abstract
With the growth of water conservancy and the increasing demand for information,handling and represent-ing large volumes of water-related data has become complex.Particularly,scheduling textual data often exists in nat-ural language form,lacking clear structure and standardization.Processing and utilizing such diverse data necessi-tates extensive domain knowledge and professional expertise.To tackle this challenge,a method based on large lan-guage model has been proposed to construct a knowledge graph for water engineering scheduling.This approach in-volves collecting and preprocessing scheduling rule data at the data layer,leveraging large language models to extract embedded knowledge,constructing the ontology at the conceptual layer,and extracting the"three-step"method prompt strategy at the instance layer.Under the interaction of the data,conceptual,and instance layers,high-performance extraction of rule texts is achieved,and the construction of the dataset and knowledge graph is completed.Experimental results show that the F1 value of the extraction method in this paper reaches 85.5%,and the effectiveness and ratio-nality of the modules of the large language model are validated through ablation experiments.This graph integrates dispersed water conservancy rule information,effectively handles unstructured textual data,and offers visualization querying and functionality tracing.It aids professionals in assessing water conditions and selecting appropriate scheduling schemes,providing valuable support for conservancy decision-making and intelligent reasoning.关键词
知识图谱/大语言模型(LLM)/本体构建/知识抽取/水工程调度Key words
knowledge graph/large language model(LLM)/ontology construction/knowledge extraction/water en-gineering scheduling分类
信息技术与安全科学引用本文复制引用
冯钧,畅阳红,陆佳民,唐海麟,吕志鹏,邱钰淳..基于大语言模型的水工程调度知识图谱的构建与应用[J].计算机科学与探索,2024,18(6):1637-1647,11.基金项目
国家重点研发计划(2023YFC3209203) （2023YFC3209203）
国家自然科学基金(62306007) （62306007）
江苏省水利科技项目(2022002,2023044) （2022002,2023044）
水利部重大科技项目(SKS-2022132).This work was supported by the National Key Research and Development Program of China(2023YFC3209203),the National Natural Science Foundation of China(62306007),the Water Conservancy Science and Technology Program of Jiangsu Province(2022002,2023044),and the Major Science and Technology Program of the Ministry of Water Resources of China(SKS-2022132). （SKS-2022132）
