Інтелектуальна технологія оптимізації керування потоками замовлень сервісних систем із неточно визначеними і природномовними даними

V. V. Skalozub; V. M. Horiachkin; І. А. Terletskyi

doi:10.15802/stp2023/288077

Authors

V. V. Skalozub Ukrainian State University of Science and Technologies, Ukraine https://orcid.org/0000-0002-1941-4751
V. M. Horiachkin Ukrainian State University of Science and Technologies, Ukraine https://orcid.org/0000-0002-8952-952X
І. А. Terletskyi Ukrainian State University of Science and Technologies, Ukraine https://orcid.org/0000-0001-9187-3955

DOI:

https://doi.org/10.15802/stp2023/288077

Keywords:

software, intelligent information technology, modified Hamming networks, natural language data, uncertainty conditions, product procedures, optimization, order flows, service systems

Abstract

Purpose. The tasks of data classification and optimization of order flow management in service systems are widespread. The development of an intelligent information technology (IIT) for optimal management of order flows in service systems (OMFS&S), taking into account imprecisely defined and natural language data characteristics (IDD), implemented on the basis of a modified Hamming network (MHN), is currently relevant, scientific and practical. The main purpose of the work is to develop and improve mathematical models and procedures of the OMFS&S and the formation of IIT based on the MHN with IDD. Methodology. New formulations of the tasks of the OMFS&S, which are characterized by the IDD, are proposed. Mathematical models and intellectual procedures for optimizing the flows of OMFS&S based on MHN have been improved. Software tools for IIT based on MHN and procedures of OMFS&S processes were developed. Numerical studies of the correctness and efficiency of solutions were carried out. Findings. New task formulations of the OMFS&S according to the IDD were formed, which differ in the ability to take into account the results of the choice of controls in the previous steps. Improved mathematical models and productive intellectual procedures of the OMFS&S based on MHN were developed, and the scope of their application was analyzed. IIT software tools for the processes of OMFS&S with IDD were developed and studied, and a numerical experiment was conducted to confirm the reliability and efficiency of the proposed models and methods of OMFS&S processes. Originality. The paper improves mathematical models and productive intelligent procedures for optimizing flows based on the results of classification by MHN. Variants of models for the functioning of OMFS&S procedures have been developed, where flow elements are considered either in isolation from others, or the optimal control choice for the current element affects the maintenance of subsequent elements. Practical value. The intelligent information technology developed on the basis of modified Hamming networks allows optimizing the management of order flows in service systems with imprecisely defined and natural language data characteristics.

References

Vasilev, V. I. (1998). Induktsiya i reduktsiya v problemakh ekstrapolyatsii. Cybernetics and Computer Engineering, 116, 65-81. (Russian)

Velykoivanenko, Gh. I. (2018). Ocinjuvannja rivnja ekonomichnoji bezpeky na pidgrunti vidstani Khemmingha. Retrieved from https://core.ac.uk/download/pdf/197269753.pdf

Kolesnyk, A. S., & Khairova, N. F. (2022). Justification for the use of Cohen’skappa statistic in experimental studies of NL Pand Text Mining. Kibernetykata Systemnyi Analiz, 58(2), 143-153. (in Ukrainian)

Skalozub, V. V., Horiachkin, V. M., Klymenko, I. V., Terletskyi, І. А., & Terlenko, A. P. (2022). Investigation of Hamming Network Procedures for Controlling Service Systems with Imprecisely Defined and Natural Language Data. Science and Transport Progress, 3-4(99-100), 33-47. DOI: https://doi.org/10.15802/stp2022/276411 (in Ukrainian)

Skalozub, V., Horiachkin, V., & Terletskii, I. (2021). Intellectual Procedures for Ordering Sequence Orders by Inhomogeneous Forming Operators. Transport Systems and Transportation Technologies, 22, 67-79. DOI: https://doi.org/10.15802/tstt2021/247885 (in Ukrainian)

Shynkarenko, V. I., & Demidovich, I. M. (2021). Determination of the attributes of authorship of natural texts. Artificial intelligence, 3, 27-35. (in Ukrainian)

Berkovich, M., Leimeister, J. M., Hoffmann, A., & Krcmar, H. (2012). A requirements data model for product service systems. Requirements Engineering, 19(2), 161-186. DOI: https://doi.org/10.1007/s00766-012-0164-1 (in English)

Cao, Y., Ying, M., & Chen, G. (2007). Retraction and Generalized Extension of Computing With Words. IEEE Transactions on Fuzzy Systems, 15(6), 1238-1250. DOI: https://doi.org/10.1109/tfuzz.2007.896301 (in English)

Cohen, J. (1960). A Coefficient of Agreement for Nominal Scales. Educational and Psychological Measurement, XX(1), 37-46. DOI: https://doi.org/10.1177/001316446002000104 (in English)

Freitag, R. M. Ko. (2019). Kappa statistic for judgment agreement in Sociolinguistics / Estatística Kappa para concordância de julgamento em Sociolinguística. Revista de Estudos da Linguagem, 27(4), 1591-1612. DOI: https://doi.org/10.17851/2237-2083.0.0.1591-1612 (in English)

Haykin, S. (1999). Neural networks: A Comprehensive Foundation. Prentice hall: New Jersey. (in English)

Hopfield, J. J. (1995). Pattern recognition computation using action potential timing for stimulus representation. Nature, 376, 33-36. DOI: https://doi.org/10.1038/376033a0 (in English)

Kim, Y., & Doh, K.-G. (2007, April). The Service Modeling Process Based on Use Case Refactoring. Business Information Systems, 10th International Conference BIS 2007 (pp. 108–120). Poznan, Poland. DOI: https://doi.org/10.1007/978-3-540-72035-5_9 (in English)

Kloock-Schreiber, D., Gembarski, P. Ch., & Lachmayer, R. (2017). Modeling and configuration for Product-Service Systems: State of the art and future research. International Configuration Workshop, 19, 72-79. (in English)

Korb, K. B., & Nicholson, A. E. (2010). Bayesian Artificial Intelligence. CRC Press. DOI: https://doi.org/10.1201/b10391 (in English)

Li Min Fu, & Shortliffe, E. H. (2000). The application of certainty factors to neural computing for rule discovery. IEEE Transactions on Neural Networks, 11(3), 647-657. DOI: https://doi.org/10.1109/72.846736 (in English)

Munandar, Tb. Ai., & Suherman, Sumiati. (2012). The Use of Certainty Factor with Multiple Rules for Diagnosing Internal Disease. International Journal of Application or Innovation in Engineering & Management (IJAIEM), 1(1), 58-63. (in English)

Poels, G. (2009). The Resource-Service-System Model. DOI: https://doi.org/10.1007/978-3-642-16385-2_15 Retrieved from https://www.researchgate.net/publication/228674056_The_Resource-Service-System_Model (in English)

Shynkarenko, V. I., & Demidovich, I. M. (2021, April). Authorship Determination of Natural Language Texts by Several Classes of Indicators with Customizable Weights. In COLINS-2021: 5th International Conference on Computational Linguistics and Intelligent Systems (Vol. I., pp. 832-844). Lviv, Ukraine. (in English)

Skalozub, V., Horiachkin, V., & Klymenko, I. (2022). Models and intellectual technologies used for analysis and process management under uncertainty. Access Journal - Access to Science, Business, Innovation in the Digital Economy, 3(2), 185-200. DOI: https://doi.org/10.46656/access.2022.3.2(8) (in English)

Tilkov, S., & Vinoski, S. (2010). Node.js: Using JavaScript to Build High-Performance Network Programs. IEEE Internet Computing, 14(6), 80-83. DOI: https://doi.org/10.1109/mic.2010.145 (in English)

Timm, H. (2001). Fuzzy cluster analysis of classified data. In Proceedings Joint 9th IFSA World Congress and 20th NAFIPS International Conference (Cat. No. 01TH8569) (Vol. 3, pp. 1431-1436). DOI: https://doi.org/10.1109/nafips.2001.943759 (in English)