图书馆杂志

图书馆杂志 ›› 2024, Vol. 43 ›› Issue (402): 50-59.

• 理论探索 • 上一篇    下一篇

生成式人工智能驱动的索引编制方法及其在学术规范和评价中的应用

朱 禹 叶继元 (南京大学信息管理学院)   

  • 出版日期:2024-10-15 发布日期:2024-10-28
  • 作者简介:朱 禹 南京大学信息管理学院,硕士研究生。 研究方向:信息资源建设、人工智能生成内容。作者贡献:论文撰写与修改。E-mail:zhu.yu@smail.nju. edu.cn 江苏南京 210023 叶继元 南京大学信息管理学院,教授,博士生导师。研究方向:信息资源建设、图书情报学理论与方法、学术规范与评价。作者贡献:论文指导与提出修改 意见。江苏南京 210023

Generative AI-driven Indexing Method and Its Application in Academic Norms and Evaluation

Zhu Yu, Ye Jiyuan (School of Information Management, Nanjing University)   

  • Online:2024-10-15 Published:2024-10-28
  • About author:Zhu Yu, Ye Jiyuan (School of Information Management, Nanjing University)

摘要: 为提高索引编制的效率与质量,应用生成式人工智能的实验方法,针对传统基于规则和概率的索引软件的不足,提出了运用生成式人工智能RAG 技术编制索引的方案,即以期刊的卷为单位,利用大语言模型基于论文摘要中的索引词对全文进行主题标引。设计了论文摘要索引数据库系统,能够实现基于大模型海量知识涌现和推理的文本概念抽取和主题标引,从摘要中提取关键信息和新兴知识。探讨了将索引、论文摘要、学术规范与评价关联起来的实际方式,展示了生成式人工智能在索引学和索引编制领域的潜在价值,能够为生成式人工智能技术在图书情报领域的应用推广提供参考。

关键词: 索引 主题索引 生成式人工智能 检索增强生成 学术规范 学术评价

Abstract: In order to improve the efficiency and quality of indexing, an experimental method using generative artificial intelligence is applied to address the shortcomings of traditional rule-based and probabilistic indexing software. A scheme for indexing using the retrieval-augmented generation of generative AI is proposed. Specifically, the journal volume is used as a unit, and the full text is subject-indexed based on indexing words derived from the abstracts of the papers by utilizing a large language model. The paper presents the design of an article abstract indexing database system, which can realize textual concept extraction and subject indexing based on the large model of massive knowledge emergence and reasoning capabilities, as well as key information and emerging knowledge extracted from abstracts. Additionally, this paper explores practical ways to associate index and abstract with academic norms and evaluation, demonstrating the potential value of generative AI in the field of indexing. It provides insights into promoting the application of generative AI technology in library and information science.

Key words: Index, Subject index, Generative artificial intelligence, Retrieval-augmented generation, Academic norm, Academic evaluation