COMPREHENSIVE RE-ENGINEERING OF DIGITAL GOVERNMENT SERVICES USING DEEP NEURAL NETWORKS AND SERVICE QUALITY INDICATORS

DOI: 10.31673/2412-4338.2026.019010

Authors

Abstract

The article substantiates a comprehensive concept of using neural networks for reengineering business processes of digital government services. It is shown that large administrative data sets, event logs of information systems and telemetry streams of electronic communications networks can act as a full-fledged source of knowledge about the actual operation of e-services, their “bottlenecks”, hidden load patterns and anomalous scenarios, including those associated with hybrid cyberattacks. A process-oriented mathematical model is proposed in which resource configuration, routing policy, information security parameters and signals of intrusion detection systems (IDS) and security event correlation platforms (SIEM) are reflected in vector features suitable for training various neural network architectures. The application of a multilayer perceptron, convolutional networks, models with long-term short-term memory, as well as autoencoders and hybrid CNN+LSTM and AE+LSTM for predicting the processing time of requests, the probability of SLO violation, detecting anomalous process scenarios and building surrogate models for scenario analysis "what-if" is considered. The features of training on uneven and incomplete administrative samples, methods for taking into account SSL and SNMP vulnerabilities in firmware attacks, integration of Zero Trust principles and Byte2Image approaches for presenting traffic and logs in the form of images are described. Examples of application scenarios in the reengineering of government e-services are given, as well as fragments of Matlab code and options for visualizing results, oriented towards use in the Matlab and Matlab Mobile environments.

Keywords: business process reengineering, digital government services, neural networks, LSTM, CNN+LSTM, AE+LSTM, Zero Trust, IDS, SIEM, Byte2Image, Matlab visualization.

References

  1. Janssen M., van der Voort H. Adaptive governance: Towards a stable, accountable and responsive government // Government Information Quarterly. – 2016. – Том 33, № 1. – С. 1–5. – DOI: 10.1016/j.giq.2016.02.003.
  2. Gil-Garcia J. R. Enacting Electronic Government Success: An Integrative Study of Government-wide Websites, Organizational Capabilities, and Institutions. – Нью-Йорк: Springer, 2012. – 195 с. – DOI: 10.1007/978-1-4614-2015-6.
  3. United Nations. E-Government Survey 2022: The Future of Digital Government. – Нью-Йорк: United Nations, 2022. – 164 с. – DOI: 10.18356/9789210019446.
  4. van der Aalst W. Process Mining: Data Science in Action. – 2-ге вид. – Берлін: Springer, 2016. – 467 с. – DOI: 10.1007/978-3-662-49851-4.
  5. Dumas M., La Rosa M., Mendling J., Reijers H. A. Fundamentals of Business Process Management. – 2-ге вид. – Берлін: Springer, 2018. – 527 с. – DOI: 10.1007/978-3-662-56509-4.
  6. Biazzo S. Process mapping techniques and organisational analysis: Lessons from sociotechnical system theory // Business Process Management Journal. – 2002. – Том 8, № 1. – С. 42–52. – DOI: 10.1108/14637150210418629.
  7. Hochreiter S., Schmidhuber J. Long short-term memory // Neural Computation. – 1997. – Том 9, № 8. – С. 1735–1780. – DOI: 10.1162/neco.1997.9.8.1735.
  8. Tax N., Verenich I., La Rosa M., Dumas M. Predictive business process monitoring with LSTM neural networks // У: Business Process Management Workshops (CAiSE 2017). – Cham: Springer, 2017. – С. 477–492 . – DOI: 10.1007/978-3-319-59536-8_30.
  9. Scarfone K., Mell P. Guide to intrusion detection and prevention systems (IDPS). – NIST Special Publication 800-94. – Гайтерсберг: National Institute of Standards and Technology, 2007. – 143 с. – DOI: 10.6028/NIST.SP.800-94.
  10. Rose S., Borchert O., Mitchell S., Connelly S. Zero trust architecture. – NIST Special Publication 800-207. – Гайтерсберг: National Institute of Standards and Technology, 2020. – 59 с. – DOI: 10.6028/NIST.SP.800-207.
  11. European Commission. eGovernment Benchmark 2022: Synchronising digital governments : background report. – Люксембург: Publications Office of the European Union, 2022. – 126 с. – DOI: 10.2759/204448.
  12. Di Francescomarino C., Dumas M., La Rosa M., Maggi F. M., Palpanas T., Mecella M. Clustering-based predictive process monitoring // IEEE Transactions on Services Computing. – 2018. – Том 12, № 6. – С. 896–909. – DOI: 10.1109/TSC.2016.2645153.
  13. Janssen M., Kuk G. The challenges and limits of big data algorithms in public policy making // Government Information Quarterly. – 2016. – Том 33, № 3. – С. 371–377. – DOI: 10.1016/j.giq.2016.08.011.
  14. Sun T. Q., Medaglia R. Mapping the challenges of artificial intelligence in the public sector // Government Information Quarterly. – 2019. – Том 36, № 2. – С. 368–383. – DOI: 10.1016/j.giq.2018.09.008.
  15. Mendling J., Weber I., van der Aalst W., vom Brocke J., Cabanillas C., et al. Blockchains for business process management – challenges and opportunities // ACM Transactions on Management Information Systems. – 2018. – Том 9, № 1. – Стаття 4. – DOI: 10.1145/3183367.
  16. Janssen M., van der Voort H. Adaptive governance: Towards a stable, accountable and responsive government // Government Information Quarterly. – 2016. – Том 33, № 1. – С. 1–5. – DOI: 10.1016/j.giq.2016.02.003.
  17. Gil-Garcia J. R. Enacting Electronic Government Success: An Integrative Study of Government-wide Websites, Organizational Capabilities, and Institutions. – Нью-Йорк: Springer, 2012. – 195 с. – DOI: 10.1007/978-1-4614-2015-6.
  18. United Nations. E-Government Survey 2022: The Future of Digital Government. – Нью-Йорк: United Nations, 2022. – 164 с. – DOI: 10.18356/9789210019446.
  19. van der Aalst W. Process Mining: Data Science in Action. – 2-ге вид. – Берлін: Springer, 2016. – 467 с. – DOI: 10.1007/978-3-662-49851-4.
  20. Dumas M., La Rosa M., Mendling J., Reijers H. A. Fundamentals of Business Process Management. – 2-ге вид. – Берлін: Springer, 2018. – 527 с. – DOI: 10.1007/978-3-662-56509-4 .
  21. Biazzo S. Process mapping techniques and organisational analysis: Lessons from sociotechnical system theory // Business Process Management Journal. – 2002. – Том 8, № 1. – С. 42–52. – DOI: 10.1108/14637150210418629.
  22. Hochreiter S., Schmidhuber J. Long short-term memory // Neural Computation. – 1997. – Том 9, № 8. – С. 1735–1780. – DOI: 10.1162/neco.1997.9.8.1735.
  23. Tax N., Verenich I., La Rosa M., Dumas M. Predictive business process monitoring with LSTM neural networks // У: Business Process Management Workshops (CAiSE 2017). – Cham: Springer, 2017. – С. 477–492 . – DOI: 10.1007/978-3-319-59536-8_30.
  24. Scarfone K., Mell P. Guide to intrusion detection and prevention systems (IDPS). – NIST Special Publication 800-94. – Гайтерсберг: National Institute of Standards and Technology, 2007. – 143 с. – DOI: 10.6028/NIST.SP.800-94.
  25. Rose S., Borchert O., Mitchell S., Connelly S. Zero trust architecture. – NIST Special Publication 800-207. – Гайтерсберг: National Institute of Standards and Technology, 2020. – 59 с. – DOI: 10.6028/NIST.SP.800-207.
  26. European Commission. eGovernment Benchmark 2022: Synchronising digital governments : background report. – Люксембург: Publications Office of the European Union, 2022. – 126 с. – DOI: 10.2759/204448.
  27. Di Francescomarino C., Dumas M., La Rosa M., Maggi F. M., Palpanas T., Mecella M. Clustering-based predictive process monitoring // IEEE Transactions on Services Computing. – 2018. – Том 12, № 6. – С. 896–909. – DOI: 10.1109/TSC.2016.2645153.
  28. Janssen M., Kuk G. The challenges and limits of big data algorithms in public policy making // Government Information Quarterly. – 2016. – Том 33, № 3. – С. 371–377. – DOI: 10.1016/j.giq.2016.08.011.
  29. Sun T. Q., Medaglia R. Mapping the challenges of artificial intelligence in the public sector // Government Information Quarterly. – 2019. – Том 36, № 2. – С. 368–383. – DOI: 10.1016/j.giq.2018.09.008.
  30. Mendling J., Weber I., van der Aalst W., vom Brocke J., Cabanillas C., et al. Blockchains for business process management – challenges and opportunities // ACM Transactions on Management Information Systems. – 2018. – Том 9, № 1. – Стаття 4. – DOI: 10.1145/3183367. 

Downloads

Published

2026-04-01

Issue

No. 1 (2026)

Section

Articles