The Development of Generative AI Integration System to Provide Automated Specialized Information Services
Article Sidebar
Main Article Content
Abstract
The development of generative AI integration system to provide automated specialized information services involves linking widely available online generative AI technology to specified knowledge base and messaging platform. The aim is to solve the problem of expert shortage in answering questions and to reduce users waiting time by providing real-time and automated specialized answering services. The system was developed using the Agile methodology, implemented in JavaScript under the Node.js runtime, and utilizes the OpenAI library to call large language models (LLMs) for natural language processing to support multi-language functionality. The system communicates with users through the LINE messaging platform and a self-developed chat board. In satisfaction assessment conducted with 11 library information resource provider staff, the average satisfaction rating was 4.20 points out of 5, which is 84 percent. Additionally, the system's accuracy was assessed by 61 public users using a Tri-Level Rubric based on all possible outcomes of the system, resulting in an average score of 2.508 out of 3, which is 83.61 percent.
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
References
Adigun, T. A., & Igboechesi, G. P. (2024). Exploring the role of generative artificial intelligence in enhancing information retrieval and knowledge discovery in academic libraries. International Journal of Library and Information Science Studies, 10(2), 1–14. https://doi.org/10.37745/ijliss.15/vol10n2114
Almuntashiri, A., Ibáñez, L.-D., & Chapman, A. (2024). LLMs for the post-hoc creation of provenance [Paper presentation]. 2024 IEEE European Symposium on Security and Privacy Workshops (EuroS&PW), Vienna, Austria.
Bello, A. A., & Musa, I. F. (2020). Subject specialist in academic libraries: An overview. International Journal of Knowledge Dissemination (IJKD), 1(2), 83–93. http://140.105.46.67/index.php/ijkd/article/view/28
Cox, A. M. (2019). The intelligent library: Thought leaders’ views on the likely impact of artificial intelligence on academic libraries. Library Hi Tech, 37(3), 418–435. https://doi.org/10.1108/LHT-08-2018-0105
Feuerriegel, S., Hartmann, J., Janiesch, C., & Zschech, P. (2023). Generative AI. Business & Information Systems Engineering, 65(2), 111–126. https://doi.org/10.1007/s12599-023-00784-w
Forbes, C. S. (2011). Statistical distributions (4th ed.). Wiley.
Gião, H. d., Pereira, R., & Cunha, J. (2023). CI/CD meets block-based languages. In 2023 IEEE Symposium on Visual Languages and Human-Centric Computing (VL/HCC) [Symposium] (pp. 232–234). IEEE, Washington, DC, USA.
Harvard Business Review. (2024). Generative AI: The insights you need from Harvard Business Review. Harvard Business Review Press.
Likert, R. (1932). A technique for the measurement of attitudes. Archives of Psychology, 22(140), 55.
Nord, R. L., & Tomayko, J. E. (2006). Software architecture-centric methods and agile development. IEEE Software, 23(2), 47–53. https://doi.org/10.1109/MS.2006.58
Okunlaya, R. O., Abdullah, N. S., & Alias, R. A. (2022). Artificial intelligence (AI) library services innovative conceptual framework for the digital transformation of university education. Library Hi Tech, 40(6), 1869–1892. https://doi.org/10.1108/LHT-07-2021-0242
