基于大语言模型的教育事业统计指标体系知识图谱构建

doi:10.3976/j.issn.1002-4026.2025079

山东科学

• 情报分析与数据管理 •

基于大语言模型的教育事业统计指标体系知识图谱构建

王朋宇¹，姜树明^1*，魏志强¹，余军¹，张萌萌²

收稿时间：2025-07-25 修回时间：2025-11-02

作者简介：王朋宇（2002—），男，硕士研究生，研究方向为数字图书馆技术与系统。E-mail: 19153969328@163.com

*通信作者，姜树明，男，副研究员，研究方向为多媒体数据处理。E-mail: jsm@qlu.edu.cn 电话：0531-68606133

1 齐鲁工业大学（山东省科学院）山东省科学院情报研究所，山东济南 250014；2 聊城市科技信息研究中心，山东聊城 252000

收稿日期:2025-07-25 接受日期:2025-11-02 上线日期:2026-01-07
通信作者: 姜树明 E-mail:jsm@qlu.edu.cn
作者简介:王朋宇（2002—），男，硕士研究生，研究方向为数字图书馆技术与系统。E-mail: 19153969328@163.com

Construction of a knowledge graph for the educational statistical indicator system based on large language models

WANG Pengyu¹，JIANG Shuming^1*，WEI Zhiqiang¹，YU Jun¹，ZHANG Mengmeng²

1. Information Research Institute of Shandong Academy of Sciences, Qilu University of Technology (Shandong Academy of Sciences), Jinan 250014, China；2. Liaocheng Science and Technology Information Research Center, Liaocheng 252000, China

Received:2025-07-25 Accepted:2025-11-02 Online:2026-01-07
Contact: JIANG Shuming E-mail:jsm@qlu.edu.cn

摘要/Abstract

摘要： 当前教育事业统计工作面临知识检索效率低、数据利用门槛高等问题，文章以教育事业统计工作依据的指标体系相关知识为研究对象，针对知识文档化特点提出一种基于大语言模型的教育事业统计指标体系知识图谱构建方法，旨在为解决上述问题提供知识支撑。具体构建了涵盖数据处理层、本体构建层、图谱构建层和应用展望层的研究框架，在数据处理层，将原始文档转化为Markdown格式并进行清洗，以增强模型的结构解析能力；在本体构建层，采用七步法构建教育事业统计指标体系本体；在图谱构建层，提出融合思维链提示与本体结构的增强提示词策略，引导大语言模型完成知识抽取，并基于Neo4j实现知识存储与可视化。实验结果表明，该策略在实体–属性抽取任务中的F1值为96.22%，在实体–关系抽取任务中的F1值为92.23%，显著优于基础提示词方案，验证了思维链提示在复杂信息抽取中的有效性。研究所构建的知识图谱有效表达了教育事业统计指标体系的复杂知识，为实现领域智能信息检索、自然语言数据查询提供了知识基础，也为其他统计领域的知识组织提供了参考。

关键词: 教育事业统计, 指标体系, 知识图谱, 大语言模型, 本体构建, 思维链提示

Abstract: Current statistical work in the field of educational development faces challenges such as low knowledge-retrieval efficiency and high technical barriers to data utilization. This study focuses on the knowledge related to the indicator system that underpins educational statistical work and proposes a large language model (LLM)-based method for constructing a knowledge graph for the educational statistical indicator system so as to provide knowledge support for addressing the above issues. Specifically, a research framework comprising the following layers is established: data processing, ontology construction, graph construction, and application prospect. In the data processing layer, original documents are converted into Markdown format and cleaned to enhance structural parsing. In the ontology construction layer, a seven-step method is used to construct the ontology of the educational statistical indicator system. In the graph construction layer, an enhanced prompting strategy integrating chain-of-thought prompting with the ontology structure guides the LLM in knowledge extraction, with Neo4j used for storage and visualization. Experimental results show that this strategy achieved an F1 score of 96.22% for entity–attribute extraction and 92.23% for entity–relation extraction, significantly outperforming the basic prompting strategy, thereby verifying the effectiveness of chain-of-thought prompting in complex information extraction. The constructed knowledge graph effectively represents the complex knowledge in the educational statistical indicator system, providing a knowledge foundation for intelligent information retrieval and natural language data querying and offering insights for knowledge organization in other statistical fields.

Key words: , Educational Statistics, Indicator System, Knowledge Graph, Large Language Model, Ontology Construction, Chain-of-Thought Prompting

中图分类号:

TP391.1

王朋宇, 姜树明, 魏志强, 余军, 张萌萌. 基于大语言模型的教育事业统计指标体系知识图谱构建[J]. 山东科学, 0, (): 1-.

WANG Pengyu, JIANG Shuming, WEI Zhiqiang, YU Jun, ZHANG Mengmeng. Construction of a knowledge graph for the educational statistical indicator system based on large language models[J]. Shandong Science, 0, (): 1-.

参考文献

[1] 徐增林,盛泳潘,贺丽荣,等.知识图谱技术综述[J].电子科技大学学报,2016,45(4):589-606.

[2] 张吉祥,张祥森,武长旭,等.知识图谱构建技术综述[J].计算机工程,2022,48(3):23-37.DOI:10.19678/j.issn.1000-3428.0061803.

[3] 李叶叶,李贺,沈旺,等.基于多源异构数据挖掘的在线评论知识图谱构建[J].情报科学,2022,40(2):65-73.DOI:10.13833/j.issn.1007-7634.2022.02.009.

[4] 张恒郡,李飞,刘鸣飞,等.基于大语言模型的风机装配工艺文档多模态图谱建模技术[J/OL].东华大学学报(自然科学版),1-13[2025-07-15].https://doi.org/10.19886/j.cnki.dhdz.2024.0229.

[5] 张才科,李小龙,郑胜,等.基于大语言模型的知识图谱构建及应用研究[J].计算机科学与探索,2024,18(10):2656-2667.

[6] 孟秋晴,郑铭瑞,田玥璐,等.面向多源异构医疗健康数据的知识图谱构建研究[J/OL].情报科学,1-11[2025-07-15].http://kns.cnki.net/kcms/detail/22.1264.G2.20250623.1646.002.html.

[7] LIU X, ZHANG S, WEI F, et al. Recognizing named entities in tweets[C]//Proceedings of the 49thannual meeting of the association for computational linguistics: human language technologies. 2011: 359-367.

[8] MENG F, YANG S, WANG J, et al. Creating knowledge graph of electric power equipment faults based on BERT–BiLSTM–CRF model[J]. Journal of electrical engineering & technology, 2022, 17(4): 2507-2516.

[9] 张坤丽,王影,付文慧,等.大语言模型驱动下知识图谱的构建及应用综述[J/OL].郑州大学学报(理学版),1-9[2025-07-15].https://doi.org/10.13705/j.issn.1671-6841.2024165.

[10] 周正达,王昊,汪琳,等.ChatKG：一种基于大语言模型和提示工程的非遗知识图谱构建框架:以中国非遗陶瓷制作工艺为例[J/OL].图书馆杂志,1-30[2025-07-15].http://kns.cnki.net/kcms/detail/31.1108.g2.20250224.1136.008.html.

[11] Zhang Y ,Hao Y .Traditional Chinese Medicine Knowledge Graph Construction Based on Large Language Models[J].Electronics,2024,13(7):1395-.

[12] ZHOU S ,LIU K ,LI D , et al.Augmenting general-purpose large-language models with domain-specific multimodal knowledge graph for question-answering in construction project management[J].Advanced Engineering Informatics,2025,65(PA):103142-103142.

[13] 陈宋生,王明.基于大语言模型的财会知识图谱构建及应用展望[J].会计之友,2025(5):152-161.

[14] 张朋杨,生龙,王巍,等.基于大语言模型的矿山事故知识图谱构建[J].工矿自动化,2025,51(2):76-83.DOI:10.13272/j.issn.1671-251x.2024080031.

[15] 杨阳蕊,董方宁,王鹏斐,等.基于大语言模型的水利工程运行管理质量概念模型及知识图谱自动化构建[J].水利学报,2025,56(5):634-645.DOI:10.13243/j.cnki.slxb.20250027.

[16] 徐增林,盛泳潘,贺丽荣,等.知识图谱技术综述[J].电子科技大学学报,2016,45(4):589-606.

[17] 李爱华,徐以则,迟钰雪.本体构建及应用综述[J].情报理论与实践,2023,46(11):189-195.DOI:10.16353/j.cnki.1000-7490.2023.11.024.

[18] 马捷,刘小乐,黄岚,等.教育领域本体构建研究[J].情报理论与实践,2012,35(7):104-108.DOI:10.16353/j.cnki.1000-7490.2012.07.003.

[19] Xu L, Li A, Zhu L, et al. Superclue: A comprehensive chinese large language model benchmark[J]. arXiv preprint arXiv:2307.15020, 2023.

[20] 陆伟,汪磊,程齐凯,等.数智赋能信息资源管理新路径：指令工程的概念、内涵和发展[J].图书情报知识,2024,41(1):6-11.DOI:10.13366/j.dik.2024.01.006.

[21] WEI J, WANG X, SCHUURMANS D, et al. Chain-of-thought prompting elicits reasoning in large language models[J]. Advances in neural information processing systems, 2022, 35: 24824-24837.

[22] 岳文玉,曹树金,曹茹烨,等.基于深度学习的中共党史知识图谱构建[J].图书馆论坛,2025,45(2):22-34.

[23] 刘雪颖,云静,李博,等.基于大型语言模型的检索增强生成综述[J].计算机工程与应用,2025,61(13):1-25.

基于大语言模型的教育事业统计指标体系知识图谱构建

Construction of a knowledge graph for the educational statistical indicator system based on large language models

PDF (PC)

赞

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 5

Metrics

本文评价

推荐阅读 0

[1]	王恒昆, 谷金, 宋之凡, 王江锋. 基于iTransformer的高速公路通行费精准预测模型[J]. 山东科学, 2025, 38(1): 120-128.
[2]	郭梦萦，贾辛欣，朱文. 山东省17市创新能力评价研究[J]. 山东科学, 2018, 31(1): 110-.
[3]	杨其鸣,贾元华. 基于五元联系度的公交服务满意度评价模型[J]. 山东科学, 2016, 29(2): 76-81.
[4]	胡志垚，朱海洋. 最优目标博弈下的空车调配效率模糊综合评价[J]. 山东科学, 2015, 28(1): 71-77.
[5]	郑达，贾元华，薛宏娇，牛忠海. 基于AHP-entropy与多级可拓的城市轨道交通运营服务质量评价[J]. J4, 2013, 26(1): 81-86.