Keywords
Abstract
With the advancement of time and technology, library services and their functions continue to evolve. Globally, library reference services have undergone significant transformations driven by technological progress. Paper-based information sources have gradually transitioned to digital formats, and traditional face-to-face reference consultations have shifted to email-based and online chat services. With the rapid growth of Artificial Intelligence (AI), libraries have entered a new stage of intelligent services. Chatbots that interact through text or voice have enabled the development of smart reference services.The application of AI in libraries has not only improved the accuracy of information retrieval and recommendation processes but has also introduced new service models such as personalized reading recommendations, intelligent classification, and knowledge graph construction. In recent years, Large Language Models (LLMs) have matured considerably, and the emergence of ChatGPT-4 has triggered a transformation in library services. These models possess powerful natural language understanding and generation capabilities, significantly enhancing service efficiency and meeting the diverse and personalized needs of modern users [1].
This article examines the challenge of delivering relevant content to users in the context of information overload. The AI-based recommendation system of the Xiaoshu platform is analyzed. The study explores the system’s voice interaction mechanism, knowledge retrieval and integration framework, service experience and user interaction, response accuracy, and overall service effectiveness.
References
1. Xie Xanyi. Smart Library: An Intelligent Librarian Powered by GPT-4. Master’s Program in Digital Innovation, Tunghai University. – China, 2024. p. 3.
2. Salton G., McGill M. J. Introduction to Modern Information Retrieval. – New York : McGraw-Hill, 1983. – 448 p
3. Ricci, F., Rokach, L., & Shapira, B. (2015). Recommender Systems Handbook (2nd ed.). Springer. https://doi.org/10.1007/978-1-4899-7637-6
4. Aggarwal, C. C. (2016). Recommender Systems: The Textbook. Springer. https://doi.org/10.1007/978-3-319-29659-3
5. Lewis, P., Perez, E., Piktus, A., Petroni, F., Karpukhin, V., Goyal, N., & Kiela, D. (2020). Retrieval-augmented generation for knowledge-intensive NLP tasks. Advances in Neural Information Processing Systems, 33, 9459-9474.
6. Liu, Z.-E. (2024). 聊天機器人之讀者體驗研究：以國立公共資訊圖書館為例 [A study of reader experience with chatbots: A case study of the National Library of Public Information]. In 2024 圖書資訊學術與實務研討會會議論文集 (pp. 199-206). Library Association of the Republic of China (Taiwan).
7. Yang, J., Jin, H., Tang, R., Han, X., Feng, Q., Jiang, H., & Hu, X. (2024). Harnessing the power of LLMs in practice: A survey on ChatGPT and beyond. ACM Transactions on Knowledge Discovery from Data, 18(6), 1–32. https://doi.org/10.1145/3649506 Zhao, W. X.,
8. Zhou, K., Li, J., Tang, T., Wang, X., Hou, Y., & Wen, J. R. (2023). A survey of large language models. arxiv preprint arxiv:2303.18223. https://arxiv.org/abs/2303.18223
9. Zheng, Q., Tang, Y., Liu, Y., Liu, W., & Huang, Y. (2022, April). UX research on conversational human-AI interaction: A literature review of the ACM Digital Library. In S. Barbosa & C. Lampe (Eds.), Proceedings of the 2022 CHI Conference on Human Factors in Computing Systems (pp. 1-24). Association for Computing Machinery. https://doi.org/10.1145/3491102.3501855
10. Hsiang-Ping Ma, Yun-Fan Chen. Implementation and Application of a Generative AI Virtual Librarian: A Case Study of the National Library of Public Information, Taiwan. - INTERNATIONAL JOURNAL OF LIBRARIANSHIP, 10(4), 137-148