O.V. Blinova1, D.V. Komanich2, E.V. Pankratova3, A.V. Taratukhin4, S.А. Мalgina5

1–4 V.A. Trapeznikov Institute of Control Sciences of RAS (Moscow, Russia)
5 FSUE RFNC-VNIIEF (Sarov, Russia)
1 blinovaov@ipu.ru, 2 komanich.d.@ipu.ru, 3 pankratova@ipu.ru, 4 avt@ipu.ru, 5 samalgina@vniief.ru

One of the key features of scientific organizations is the production and user interaction with large data streams. The explosive growth in the number of scientific and technical documentation stored and received in various research areas leads to the need to find new ways to automate and intellectualize the collection, processing, storage, systematization and analysis of information. The diverse problematic issues and tasks of processing text documentation that arise require the study of a human-oriented interface and the combination of various tools and methods within the framework of fulfilling a single user request for a relevant sample of documentation.  Modern scientific and technical documentation processing systems do not allow us to fully implement user requirements for the quality and effectiveness of dialogue with these systems.

The study of characteristic features in the context of a scenario description of a human-oriented dialogue with an intelligent information and analytical system under development, which allows combining existing and developing documentation analysis technologies to obtain multi-criteria slices of partially structured information when working with documents of various formats.

From a practical point of view, the set of user tasks has been unified in the implementation of operational information search and obtaining slices of scientific and technical documentation; the elements of accurate and semantic search have been clarified in the context of diverse scenarios for their implementation in the implemented interface when generalizing user experience. Moreover, within each query, semantic search, voice input, contextual query constructor, categorization based on metadata or user specialization are used for spot search or document sampling.

The study of the dialogue with the intelligent information and analytical system was carried out based on the results of testing the prototype (Intelligent Control System of the National Center for Physics and Mathematics, ISU NCFM). Through the formalization of the characteristic features of complex and repeatable user queries and the subsequent implementation of human-oriented search scenarios in the developed original system, the process of analyzing scientific and technical information has been comprehensively investigated and automated.

Blinova O.V., Komanich D.V., Pankratova E.V., Taratukhin A.V., Мalgina S.А. A study of dialogue scenarios for the human-oriented interface of scientific and technical documentation processing systems // Dynamics of complex systems. 2026. V. 20. № 4. P. 95−107. DOI: 10.18127/j19997493-202604-08

1. Zuluaga M., Robledo S., Arbelaez-Echeverri O., Osorio-Zuluaga G.A., Duque-Méndez N. Tree of science-ToS: A web-based tool for scientific literature recommendation. search less, research more! Issues in Science and Technology Librarianship. 2022. № 100. P. 1–10.
2. Keyvan K., Huang J.X. How to approach ambiguous queries in conversational search: A survey of techniques, approaches, tools, and challenges. ACM Computing Surveys. 2022. V. 55. № 6. P. 1–40.
3. Belov S.D., Zrelova D.P., Zrelov P.V., Koren`kov V.V. Obzor metodov avtomaticheskoj obrabotki tekstov na estestvennom yazy`ke. Sistemny`j analiz v nauke i obrazovanii. 2020. № 3. S. 1–15. (In Russian).
4. Kononova O.V., Prokudin D.E. Texnologii izvlecheniya i intellektual`nogo analiza danny`x v nauchny`x issledovaniyax. SPb.: Universitet ITMO. 2021. 135 s. (In Russian).
5. Ivanova G.S., Marty`nyuk P.A. Analiz sistem izvlecheniya informacii iz nestrukturirovanny`x tekstovy`x dokumentov. Nejrokomp`yutery`: razrabotka, primenenie. 2025. T. 27. № 1. S. 5–27. DOI: https://doi.org/10.18127/j19998554-202501-01 (In Russian).
6. Blinova O.V., Farxadov M.P., Pankratova E.V., Smirnov V.A. Cheloveko-orientirovanny`e interfejsy` s ispol`zovaniem estestvennogo yazy`ka i golosovy`x komand upravleniya informacionny`mi sistemami. Materialy` XXVI Xaritonovskix tematicheskix nauchny`x chtenij «Iskusstvenny`j intellekt i bol`shie danny`e v texnicheskix, promy`shlenny`x, prirodny`x i social`ny`x sistemax» (Sarov, 2025). Sarov: FGUP «RFYaCz-VNIIE`F». 2025. S. 33–35. (In Russian).
7. Wilson M. Search-User Interface Design. Springer Nature. 2022. 125 p.
8. Brooke J. SUS-A quick and dirty usability scale. Usability evaluation in industry. 1996. V. 189. № 194. P. 4–7.
9. Brooke J. SUS: a retrospective. Journal of usability studies. 2013. V. 8. Iss. 2. P. 29–40.
10. Sauro J., Lewis J.R. Quantifying the user experience: Practical statistics for user research. Morgan Kaufmann. 2016. 350 p.
11. Borisova N.V., Kochueva Z.A. Indeksirovanie polnotekstovy`x dokumentov dlya zadachi intellektual`nogo poiska informacii po klyuchevy`m slovam. Vostochno-Evropejskij zhurnal peredovy`x texnologij. 2014. № 1(2). S. 4–8. (In Russian).
12. Farxadov M.P., Pankratova E.V., Blinova O.V., Smirnov V.A. Principy` postroeniya formal`nogo kontekstno-logicheskogo konstruktora zaprosov dlya tochnogo poiska soby`tij v bol`shix massivax geterogennoj informacii. Vestnik Tomskogo gosudarstvennogo universiteta. Upravlenie, vy`chislitel`naya texnika i informatika. 2023. № 64. S. 138–145. (In Russian).
13. Quamar A., Efthymiou V., Lei C., Lei C. Natural language interfaces to data. Foundations and Trends in Databases. 2022. V. 11. № 4. P. 319–414.
14. Terexov V.I., Skry`l` S.V., Baldin A.V., Goryachkin B.S., Ivchenko D.D. Osnovny`e polozheniya koncepcii proektnoj e`rgonomiki avtomatizirovanny`x sistem otobrazheniya informacii. Dinamika slozhny`x sistem. 2024. T. 18. № 2. S. 28−35. DOI: 10.18127/j19997493-202402-03 (In Russian).
15. Shalagin N.D. Obzor algoritmov semanticheskogo poiska po tekstovy`m dokumentam. International Journal of Open Information Techno­logies. 2024. T. 12. №. 9. S. 11–21.
16. Yang A. et al. Qwen3 technical report // arXiv. 2025. P. 1–35. URL: https://arxiv.org/abs/2505.09388 (data obrashheniya: 07.05.2026).
17. Ataeva O.M., Serebryakov V.A., Tuchkova N.P. Model` poiska sxozhix dokumentov v semanticheskoj biblioteke. Nauchny`j servis v seti Internet: trudy` XXIII Vseros. nauchnoj konf. (20–23 sentyabrya 2021 g., onlajn). M.: IPM im. M.V. Keldy`sha. 2021. S. 54–64. (In Russian).
18. Milkova M.A., Nevolin I.V., Pigorev D.P. Sovremenny`e metody` izvlecheniya klyuchevoj informacii iz normativny`x dokumentov. E`konomicheskaya nauka sovremennoj Rossii. 2021. № 2(93). S. 101–114. (In Russian).
19. Golubinskij A.N., Tolsty`x A.A., Tolsty`x M.Yu. Avtomaticheskaya generaciya annotacij nauchny`x statej na osnove bol`shix yazy`kovy`x modelej. Informatika i avtomatizaciya. 2025. T. 24. № 1. S. 275–301. (In Russian).
20. Koh H. Y., Ju J., Liu M., Pan S. An empirical survey on long document summarization: Datasets, models, and metrics. ACM computing surveys. 2022. V. 55. № 8. P. 1–35.