信息资源管理学报 ›› 2024, Vol. 14 ›› Issue (5): 36-44.doi: 10.13365/j.jirm.2024.05.036

• 专题·大语言模型下的古籍智能信息处理 • 上一篇    下一篇

大语言模型下古籍智能信息处理：构成要素、框架体系与实践路径研究

张海1,2　赵雪3　王东波2,3   

  1. 1.嘉兴南湖学院商贸管理学院，嘉兴，314001；
    2.人文与社会计算江苏省高校哲学社会科学重点研究基地，南京，210095；
    3.南京农业大学信息管理学院，南京，210095
  • 出版日期:2024-09-26 发布日期:2024-10-15
  • 作者简介:张海，副教授，博士研究生，研究方向为数字人文、用户信息行为；赵雪，博士研究生，研究方向为数字人文；王东波（通讯作者），教授，博士，博士生导师，研究方向为数字人文、智能信息组织，Email：db.wang@njau.edu.cn。
  • 基金资助:
    本文系国家社会科学基金重大项目“中国古代典籍跨语言知识库构建及应用研究”（21&ZD331）的研究成果之一。

Research on Intelligent Information Processing of Ancient Books under the Large Language Model: Constituent Elements, Framework System, and Practical Path

Zhang Hai1,2　Zhao Xue3　Wang Dongbo2,3   

  1. 1.School of Business and Management, Jiaxing Nanhu University, Jiaxing, 314001;
    2.Research Center for Humanities and Social Computing, Nanjing Agricultural University, Nanjing,210095；
    3.School of Information Management, Nanjing Agricultural University, Nanjing, 210095
  • Online:2024-09-26 Published:2024-10-15
  • About author:Zhang Hai, associate professor, Ph.D. candidate, research area: digital humanities and user information behavior; Zhao Xue, Ph.D. candidate, research area: digital humanities; Wang Dongbo(corresponding author), professor, Ph.D., doctoral supervisor,research interests include digital humanities and intelligent information organization, Email: db.wang@njau.edu.cn.
  • Supported by:
    This work is supported by the Major Project of the National Social Science Fund of China "Research on the Construction and Application of a Cross-Language Knowledge Base for Ancient Chinese Books"(21&ZD331).

PDF

38

摘要： 为实现大语言模型与古籍智能信息处理领域的深度融合，丰富信息资源管理学科在古籍智能信息处理领域的理论体系和技术体系，本研究借鉴编码解构的思路，通过对28位领域用户的访谈数据进行编码分析，凝练出大语言模型下古籍智能信息处理的构成要素，进而总结出“政策-技术-古籍-用户”四位一体的框架体系，并以此为基础，结合信息资源管理学科特色，提出了具体实践路径。研究结果显示，政策因素、技术因素、古籍因素和用户因素是大语言模型与古籍智能信息处理领域深度融合的关键要素，最后结合大语言模型技术和古籍智能信息处理领域的发展实际，从理论路径体系、技术路径体系和用户服务体系三个方面详细阐释了实践路径和可行策略。

关键词: 大语言模型, 生成式人工智能, 技术韧性, 古籍智能信息处理, 框架体系, 实践路径

Abstract: With the rapid advancement of large language models (LLMs), there is growing potential for their integration into the intelligent information processing of ancient books. This study seeks to bridge the gap between LLMs and the field of ancient books processing, enhancing the theoretical and technical foundations of the information resource management discipline. Drawing on a coding-based deconstruction method, this study analyzed interviews from 28 domain experts to identify the key factors necessary for effective integration. The analysis reveals a comprehensive framework that centers on four critical dimensions: policy, technology, ancient books, and users. Building on this framework, this study proposes a set of practical paths tailored to the unique demands of the discipline. The findings suggest that these four dimensions are essential to the successful application of LLMs in the domain. Finally, this study offers detailed strategies for implementation across theoretical, technical, and user service, providing a roadmap for future development in this emerging field.

Key words: Large language model, Artificial intelligence generative content, Technology resilience, Ancient books intelligent information processing, Framework system, Practical path

中图分类号: 

地址：武汉市武昌路珞珈山 武汉大学信息管理学院 邮编：430072 电话：027-68754779 E-mail：xxzyglxb@163.com
版权所有 © 《信息资源管理学报》编辑部     鄂ICP备05003330号-1
本系统由北京玛格泰克科技发展有限公司设计开发 技术支持：support@magtech.com.cn