|
|
|
| Artificial Intelligence-Driven Knowledge Organization and Services |
| Wang Wentao1, Cheng Kun1, Su Xinning2 |
1.School of Management, Anhui University, Hefei 230601 2.School of Information Management, Nanjing University, Nanjing 210023 |
|
|
|
|
Abstract Knowledge organization is guided by the requirements of knowledge services and aims to proliferate knowledge and develop higher-order insights by organizing resources. The evolution of knowledge organization tools reveals a close relationship between knowledge organization and services. Advances in large language models (LLMs), retrieval-augmented generation (RAG), tool calling, and multi-agent systems have extended artificial intelligence (AI) applications beyond standalone content generation, to integrated agent systems capable of perception, planning, execution, and feedback. This shift is transforming the traditional approaches of knowledge organization. This study examines AI-driven knowledge organization and services via first tracing their co-evolution, and then analyzing the innovations enabled by AI in both areas. Based on this analysis, we developed a collaborative framework for knowledge organization and services in an AI-enabled environment, and outline future directions for agent-driven development. This analysis suggests that innovating knowledge organization requires advances in AI technologies and corresponding changes in organizational methods. Knowledge organization should respond to service requirements by structuring knowledge resources, enriching their semantic relationships, enabling AI-assisted processing, and generating additional knowledge value. These processes encourage advanced knowledge services by facilitating the development of higher-order insights and collaborative knowledge creation.
|
|
Received: 29 July 2026
|
|
|
|
1 胡键. 知识的历时性传播、共时性传播与中国知识的成长[J]. 云南师范大学学报(哲学社会科学版), 2022, 54(4): 93-104. 2 戎军涛. 基于关联数据的知识组织深度序化机制研究[J]. 图书情报工作, 2015, 59(13): 134-141. 3 成全, 罗栋, 钟晶晶. 知识组织的理论缘起及演进路径探析[J]. 图书馆论坛, 2014, 34(11): 26-34. 4 苏新宁. 面向知识服务的知识组织理论与方法[M]. 北京: 科学出版社, 2014. 5 李静. 基于知识组织的知识服务研究[D]. 天津: 天津师范大学, 2008. 6 李辉, 张惠娜, 付宏. 情报3.0时代科技情报服务能力构建[M]. 北京: 社会科学文献出版社, 2017. 7 苏新宁. 面向知识服务的领域知识组织纵论[J]. 情报学报, 2022, 41(9): 889-899. 8 赵志耘, 刘耀, 朱礼军, 等. 复杂信息环境下知识组织和再利用模式与方法研究[J]. 情报学报, 2022, 41(12): 1266-1279. 9 刘洪波. 知识组织与知识社会化过程[J]. 中国图书馆学报, 1991, 17(1): 24-29, 91. 10 Pan S R, Luo L H, Wang Y F, et al. Unifying large language models and knowledge graphs: a roadmap[J]. IEEE Transactions on Knowledge and Data Engineering, 2024, 36(7): 3580-3599. 11 刘峥, 孙坦, 张建勇. NSTL资源的深度组织和揭示: 从资源描述到语义描述[J]. 数字图书馆论坛, 2020(7): 60-66. 12 贾君枝. 面向数据网络的信息组织演变发展[J]. 中国图书馆学报, 2019, 45(5): 51-60. 13 陈涛, 张永娟, 单蓉蓉, 等. 书目数据语义化知识模型构建与关联研究[J]. 图书馆杂志, 2019, 38(1): 65-73. 14 王曰芬, 董校一, 何劲. 基于多源数据聚合的场景式情报服务方案生成及评价研究[J]. 科技情报研究, 2024, 6(3): 56-68. 15 李广建, 仵轩, 潘佳立. 从通用AI走向情报AI: 背景、框架及关键技术[J]. 图书情报工作, 2025, 69(20): 3-15. 16 汪大锟, 化柏林. 基于BERTopic的新兴技术主题识别研究[J]. 科技情报研究, 2025, 7(1): 131-140. 17 袁虎声, 唐嘉乐, 赵洗尘, 等. ChatLib: 重构智慧图书馆知识服务平台[J]. 大学图书馆学报, 2024, 42(2): 72-80. 18 张心源, 肖浩宇, 李白杨. 大语言模型与知识图谱协同增强知识组织理论架构研究[J]. 数字图书馆论坛, 2025, 21(5): 1-10. 19 张贞港, 余传明. 基于实体与关系融合的知识图谱补全模型研究[J]. 数据分析与知识发现, 2023, 7(2): 15-25. 20 周凡倩, 毛进, 李纲. 知识增强大模型驱动的智能科技情报洞察: 内涵、实现路径与挑战[J]. 图书情报知识, 2025, 42(3): 44-52, 117. 21 常远, 李紫玥, 孔源博, 等. 大语言模型驱动的科学假设生成研究综述[J]. 数据分析与知识发现, 2026, 10(4): 66-88. 22 苏新宁. 传统知识组织方法的智能力[J]. 科技情报研究, 2024, 6(1): 1-9. 23 王曰芬, 范丽鹏, 靳嘉林, 等. 知识推荐驱动的用户需求挖掘型知识融合模式实现研究[J]. 图书情报工作, 2026, 70(9): 3-12. 24 Awasthi R, Kholkar G. Mitigating knowledge entropy: a multi-agent framework with decoupled reranking and governance-by-design[C]// Women in Machine Learning Workshop @ NeurIPS 2025. 25 Wang X, Huang X W, Sang J T. Understanding the information cocoon: a multidimensional assessment and analysis of news recommendation systems[PP/OL]. V1. arXiv (2025-09-14) [2026-09-02]. https://doi.org/10.48550/arXiv.2509.11139. 26 Maragheh R Y, Deldjoo Y. The future is agentic: definitions, perspectives, and open challenges of multi-agent recommender systems[PP/OL]. V3. arXiv (2026-06-28) [2026-09-02]. https://doi.org/10.48550/arXiv.2507.02097. 27 Basu D, Das U. The fair game: auditing & debiasing AI algorithms over time[J]. Cambridge Forum on AI: Law and Governance, 2025, 1: e27. 28 Cheng Y Y, Dobreski B, Chou C, et al. Reimagining knowledge organization with AI and human-in-the-loop[J]. Proceedings of the Association for Information Science and Technology, 2025, 62(1): 1218-1221. 29 贾开, 蒋余浩. 人工智能治理的三个基本问题: 技术逻辑、风险挑战与公共政策选择[J]. 中国行政管理, 2017(10): 40-45. 30 王亮. 检索增强生成(RAG)驱动的知识服务: 原理、范式及评估[J]. 科技与出版, 2025(4): 37-46. 31 Qian P B, Zhao S, Jiang W H, et al. Exploring the role of AI anchor image-news content congruency in news-viewing experience among gen zers: a mixed-method study in the Chinese context[J]. International Journal of Human-Computer Interaction, 2026, 42(7): 4853-4881. 32 张晓林. AI赋能的P4ST决策智能分析:寻找知识服务的新质生产力[J]. 数据分析与知识发现, 2024, 8(3): 1-9. 33 李广建, 仵轩. AI时代的情报工作回归: 构建“脑-智”双轨协同模式[J]. 数据分析与知识发现, 2026, 10(5): 1-8. 34 周红磊, 张海涛, 张春龙, 等. 面向重大突发事件双重响应体系的情报感知研究[J]. 图书情报工作, 2024, 68(11): 42-55. 35 杨建林, 苗蕾, 申姝婧, 等. 数智赋能科技情报服务能力现代化的动因与进路研究[J]. 科技情报研究, 2023, 5(4): 1-16. 36 张晓林, 梁娜. 知识的智慧化、智慧的场景化、智能的泛在化——探索智慧知识服务的逻辑框架[J]. 中国图书馆学报, 2023, 49(3): 4-18. 37 Li H C, Ren Y H, Qian P B, et al. Pleasure, arousal, and dominance: exploring the emotional drivers of virtual reality service adoption in academic libraries[J]. The Journal of Academic Librarianship, 2026, 52(3): 103232. 38 张记川. 图书馆使用类ChatGPT工具的算法歧视及规制策略[J]. 图书馆研究与工作, 2025(1): 13-19. 39 朱鑫汝, 段美珍, 初景利. 从替代到协同: AIGC赋能图书馆人智协同咨询服务模式研究[J]. 图书情报工作, 2026, 70(4): 56-70. 40 范炜. 技术赋能下图书情报的知识组织研究[J]. 图书馆杂志, 2026, 45(2): 33-40. 41 谭晓, 李辉, 许海云. 基于多维数据知识内容和关联深层融合的知识发现研究综述[J]. 科技情报研究, 2021, 3(4): 58-68. 42 叶梓萌, 钱力, 刘细文, 等. 面向图书馆数据资源建设的智慧数据研究: 内涵界定、技术应用与研究启示[J]. 情报科学, 2024, 42(12): 31-41. 43 罗然, 王晰巍, 李姝璇. 图书馆场景下知识服务智能问答机器人人智交互效果评价[J]. 图书情报工作, 2026, 70(4): 100-115. 44 彭希珺, 华宁. AI赋能科技期刊知识服务的实施框架与路径[J]. 中国科技期刊研究, 2025, 36(9): 1135-1142. 45 李默, 杨彬. 从生成式人工智能到通用人工智能: 赋能图书馆知识服务模式创新[J]. 农业图书情报学报, 2024, 36(6): 50-61. 46 赵浜, 曹树金. 生成式AI大模型结合知识库与AI Agent开展知识挖掘的探析[J]. 图书情报知识, 2025, 42(4): 88-101. 47 Bajoria S, Ranjan S, M A, et al. From language models to agentic AI: a survey of autonomous, action-enabled, and collaborative LLM agents[J]. Cognitive Computation, 2026, 18(1): Article No.103. 48 刘细文, 孙蒙鸽, 付芸. 从管理信息系统到情报智能体: 重塑科技情报工作范式[J]. 图书情报工作, 2025, 69(17): 3-15. 49 Lim H, Choi D, Nam S, et al. Understanding human-multi-agent team formation for creative work[C]// Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems. New York: ACM Press, 2026: Article No.70. 50 Trajanoska M, Stojanov R, Trajanov D. A multi-agent system for semantic mapping of relational data to knowledge graphs[PP/OL]. V1. arXiv (2025-11-09) [2026-09-02]. https://doi.org/10.48550/arXiv.2511.06455. 51 Miles A, Bechhofer S. SKOS simple knowledge organization system reference[EB/OL]. (2009-08-18) [2026-09-02]. https://www.w3.org/TR/2009/REC-skos-reference-20090818/. 52 Antakli A, Kazimov A, Spieldenner D, et al. AJAN: an engineering framework for semantic web-enabled agents and multi-agent systems[C]// Proceedings of the 21st International Conference on Practical Applications of Agents and Multi-Agent Systems. Cham: Springer, 2023: 15-27. 53 Lin X X, Ning Y C, Zhang J W, et al. LLM-based agents suffer from hallucinations: a survey of taxonomy, methods, and directions[PP/OL]. V2. arXiv (2025-11-18) [2026-09-02]. https://doi.org/10.48550/arXiv.2509.18970. 54 Tyen G, Mansoor H, C?rbune V, et al. LLMs cannot find reasoning errors, but can correct them given the error location[C]// Findings of the Association for Computational Linguistics: ACL 2024. Stroudsburg: Association for Computational Linguistics, 2024: 13894-13908. 55 Zhang Y X, Chen J, Wang J J, et al. ToolBeHonest: a multi-level hallucination diagnostic benchmark for tool-augmented large language models[C]// Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing. Stroudsburg: Association for Computational Linguistics, 2024: 11388-11422. 56 Kapoor S, Stroebl B, Siegel Z S, et al. AI agents that matter[PP/OL]. V1. arXiv (2024-07-01) [2026-09-02]. https://doi.org/10.48550/arXiv.2407.01502. |
|
|
|