INTEGRATION AND USE OF ARTIFICIAL INTELLIGENCE FOR AUTOMATED MACROS CREATION
DOI:
https://doi.org/10.34185/1562-9945-5-154-2024-02Keywords:
automation and optimization of workflows, macro, human-machine interaction, artificial intelligence, LLMs, Prompt Engineering, computerized devicesAbstract
In today's world, automation and optimization of work processes are becoming key success factors. This work examines the combination of automation systems and artificial intelligence (AI) and their impact on the optimization of work processes. The technology of integration into the process automation system and learning of a large language model for the automated creation of macros using the example of the author's software "Draw & GO" has been developed and proposed.
References
Draw & GO, URL: https://drawgo.azurewebsites.net.
Antonyuk V., Sydorova M. (2021) Synthesis of software architectures for cross-platform appli- cation development. Actual problems of automation and information technology. Vol.25. PP. 3-12. DOI: 10.15421/432101
Antonyuk V., Sydorova M. (2022) A Cross-Platform Mobile Development for accelerating soft- ware development lifecycle. Actual problems of automation and information technology. Vol.26. PP. 3-8. DOI: 10.15421/432201
Antonyuk V., Sydorova M. (2023) The concept of associative graphical interface in the work- flow automation system. System technologies. Vol. 5 No. 148. PP. 133-140 DOI: 10.34185/1562- 9945-5-148-2023-12
Reynolds L, McDonell K. (2021) Prompt programming for large language models: beyond the few-shot paradigm. Extended Abstracts of the CHI Conference on Human Factors in Computing Systems P. 1–7. URL: doi.org/10.48550/arXiv.2102.07350
Kojima T, Gu SS, Reid M, Matsuo Y, Iwasawa Y. (2022) Large language models are zero-shot reasoners. Advances in Neural Information Processing Systems. 35:22199–22213. URL: doi.org/10.48550/arXiv.2205.11916
Prompt Engineering Guide, URL: https://www.promptingguide.ai/
B. Chen, Z. Zhang, N. Langrené, S. Zhu (2023) Unleashing the potential of prompt engineering in Large Language Models: a comprehensive review. URL: doi.org/10.48550/arXiv.2310.14735
P. Liu, W. Yuan, J. Fu, Z. Jiang, H. Hayashi, G. Neubig (2021) Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing. URL: doi.org/10.48550/arXiv.2107.13586
Brown T.B, Mann B, Ryder N, Subbiah M, Kaplan J, Dhariwal P, et al. (2020) Language mod- els Are Few-Shot Learners. Proceedings of the 34th International Conference on Neural Infor- mation Processing Systems. NIPS’20 URL: doi.org/10.48550/arXiv.2005.14165
C#/.NET SDK for accessing the OpenAI APIs URL: https://github.com/OkGoDoIt/OpenAI- API-dotnet
Downloads
Published
Issue
Section
License
Copyright (c) 2024 System technologies
This work is licensed under a Creative Commons Attribution 4.0 International License.
