Transforming Business Communication with Solutions Based on Artificial Intelligence Technologies with Support for Natural Language Processing

V. IATSIUTA; V. KOBETS

doi:10.15407/scine21.05.126

Authors

V. IATSIUTA Kherson State University https://orcid.org/0009-0001-8610-2862
V. KOBETS Kherson State University https://orcid.org/0000-0002-4386-4103

DOI:

https://doi.org/10.15407/scine21.05.126

Keywords:

business request, artificial intelligence, NLP, software architecture, data-processing

Abstract

Introduction. Information has become one of the most critical resources in today’s dynamic world, with data collection and analysis technologies evolving rapidly. Every organization requires fast, accurate, and secure data
analysis to respond to queries and support informed decision-making.
Problem Statement. Artificial intelligence (AI) has become an integral part of modern life, and data processing remains at its core — from understanding a company’s current state to performing complex risk assessments and forecasting decision outcomes.
Purpose. To develop a system that enhances evaluation and decision-making processes by providing users with
integrated, user-friendly access to relevant datasets.
Materials and Methods. Various system architectures have been examined, with their advantages and limitations described. A prototype system for processing business queries using ChatGPT has been developed. The main
input types and examples of diff erent request scenarios have been presented, along with an overview of potential
issues and proposed solutions.
Results. The system has been validated, and strategies for improving data processing quality have been proposed. The study has aimed to streamline the request lifecycle — from initial formulation to response delivery — while ensuring compliance with corporate policies and data security standards.
Conclusions. The fi ndings have demonstrated the effectiveness of artificial intelligence in automating business
query processing — specifically in transforming natural language inputs into SQL queries and generating accurate responses. This opens new opportunities for automating and optimizing enterprise processes, reducing the
workload on IT departments, and improving data accessibility for non-technical users. In practical terms, the results can be applied by organizations to develop intelligent analytics systems, interactive dashboards, and database chatbots, as well as to build next-generation business intelligence interfaces based on natural language.

Downloads

Download data is not yet available.

References

Hajipour, V., Hekmat, S., Amini, M. (2023). A value-oriented Artificial Intelligence-as-a-Service business plan using integrated tools and services. Decision Analytics Journal, 8, 100302. https://doi.org/10.1016/j.dajour.2023.100302

Basole, R. C., Park, H., Seuss, C. D. (2024). Complex business ecosystem intelligence using AI-powered visual analytics. Decision Support Systems, 178, 114133. https://doi.org/10.1016/j.dss.2023.114133

Nistala, P., Rajbhoj, A., Kulkarni, V., Noronha, S., Joshi, A. (2024). An industrial experience report on model-based, AIenabled proposal development for an RFP/RFI. Science of Computer Programming, 233, 103058. https://doi.org/10.1016/j.scico.2023.103058

Siciliani, L., Taccardi, V., Basile, P., Ciano, M. D., Lops, P. (2023). AI-based decision support system for public procurement. Information Systems, 119, 102284. https://doi.org/10.1016/j.is.2023.102284

Gill, S. S., Xu, M., Ottaviani, C., Patros, P., Bahsoon, R., Shaghaghi, A.,…, Uhlig, S. (2022). AI for next generation computing: Emerging trends and future directions. Internet of Things, 19, 100514. https://doi.org/10.1016/j.iot.2022.100514

Ahmad, K., Abdelrazek, M., Arora, C., Bano, M., Grundy, J. (2023). Requirements engineering for artificial intelligence systems: A systematic mapping study. Information and Software Technology, 158, 107176. https://doi.org/10.1016/j.infsof. 2023.107176

Tripathi, M. A., Madhavi, K., Kandi, V. S. P., Nassa, V. K., Mallik, B., Chakravarthi, M. K. (2023). Machine learning models for evaluating the benefits of business intelligence systems. Journal of High Technology Management Research, 34, 100470. https://doi.org/10.1016/j.hitech.2023.100470

Ouaddia, C., Benaddia, L., Jakimia, A. (2024). Architecture, Tools, and DSLs for Developing Conversational Agents: An Overview. Procedia Computer Science, 231, 293—298. https://doi.org/10.1016/j.procs.2023.12.206

Saka, A. B., Oyedele, L. O., Akanbi, L. A., Ganiyu, S. A., Chan, D. W. M., Bello, S. A. (2023). Conversational artificial intelligence in the AEC industry: A review of present status, challenges and opportunities. Advanced Engineering Informatics, 55, 101869. https://doi.org/10.1016/j.aei.2022.101869

Wei, R., Pardo, C. (2022). Artificial intelligence and SMEs: How can B2B SMEs leverage AI platforms to integrate AI technologies? Industrial Marketing Management, 107, 466—483. https://doi.org/10.1016/j.indmarman.2022.10.008

Javaida, M., Haleema, A., Singh, R. P. (2023). A study on ChatGPT for Industry 4.0: Background, potentials, challenges, and eventualities. Journal of Economy and Technology, 1, 127—143. https://doi.org/10.1016/j.ject.2023.08.001

De Bock, K. W., Coussement, K., De Caigny, A., Słowiński, R., Baesens, B., Boute, R. N., Choi, T., …, Weber, R. (2023). Explainable AI for Operational Research: A defining framework, methods, applications, and a research agenda. European Journal of Operational Research, 317(2), 249—272. https://doi.org/10.1016/j.ejor.2023.09.026

Ouaddi, C., Benaddi, L., Khriss, I., Jakimi, A. (2023). Developing Conversational Agent Using Deep Learning Techniques. Computer Sciences & Mathematics Forum, 6. https://doi.org/10.3390/cmsf2023006003

Kenton, W. Business Segment Reporting Definition, Importance, Example. URL: https://www.investopedia.com/terms/ b/business-segment-reporting.asp (Last accessed: 03.07.2024).

Bondar, S., Ruppert, C., Stjepandić, J. (2014). Ensuring data quality beyond change management in virtual enterprise. International Journal of Agile Systems and Management, 7(3—4) 304—323. https://doi.org/10.1504/ĲASM.2014.065346

Iatsiuta, V., Kobets, V., Ivanov, O. (2023). Creating of a General Purpose Language for the Construction of Dynamic Reports. In: Maślankowski, J., Marcinkowski, B., Rupino da Cunha, P. (Еds.) Digital Transformation. PLAIS EuroSymposium 2023. Lecture Notes in Business Information Processing, vol. 495. Springer, Cham. https://doi.org/10.1007/978- 3-031-43590-4_2

Nguyen, M.-T., Le, D. T., Le, L. (2021). Transformers-based information extraction with limited data for domain-specific business documents. Engineering Applications of Artificial Intelligence, 97, 104100. https://doi.org/10.1016/j.engappai. 2020.104100

Kobets, V., Yatsenko, V., Mazur, A., Zubrii, M. (2020). Data analysis of personalized investment decision making using Robo-Advisers. Science and Innovation, 16(2), 80—93. https://doi.org/10.15407/scine16.02.080

Kobets, V., Tsiuriuta, N., Lytvynenko, V., Novikov, M., Chizhik, S. (2020). Recruitment web-service management system using competence-based approach for manufacturing enterprises. Lecture Notes in Mechanical Engineering, 138—148. https://doi.org/10.1007/978-3-030-22365-6_14

Khurana, D., Koli, A., Khatter, K., Singh, S. (2023). Natural language processing: state of the art, current trends and challenges. Multimed Tools Appl., 82, 3713—3744. https://doi.org/10.1007/s11042-022-13428-4

LangChain. URL: https://python.langchain.com/docs/get_started/introduction (Last accessed: 28.06.2024).

Davenport, T. H., Ronanki, R. Artificial Intelligence for the Real World. URL: https://hbr.org/2018/01/artificial-intelligencefor-the-real-world (Last accessed: 28.06.2024).

OpenAI API, GPTs, Documentation and CookBook. URL: https://chat.openai.com/g/g-I1XNbsyDK-api-docs (Last accessed: 28.06.2024).