K.A. Kuznetsova1

1National University of Science and Technology “MISIS” (Moscow, Russia)
1 k.a.kuznecova@gmail.com

The research is aimed at solving the problem of increasing the efficiency of integrating the scientific and technical potential of educational institutions with existing enterprises in Russia. A combination of graph theory and fuzzy set theory is proposed as a mathematical apparatus.

Goal – to develop the functions and architecture of an expert-analytical system in the field of educational and personnel processes.

In order to select relevant vacancies, taking into account the length of service and academic performance of graduates, an expert recommendation system was developed that provides a list of relevant vacancies sorted in descending order of the estimated salary, taking into account the length of service and the level of knowledge of the graduate.

Tools have been developed for analyzing and visualizing graphs of current vacancies and areas of graduate training for research and comparison of skills, requirements for applicants, geography and other information collected from open sources. The algorithm of a fuzzy recommendation system is described, which takes into account the length of service and the level of knowledge of the graduate (test scores or grades in specialized subjects). The developed analytics and visualization tools contribute to the effective management of integration processes in the interests of universities and enterprises.

Kuznetsova K.A. Functions and architecture of the expert-analytical system in the field of educational and personnel processes. Nonlinear World. 2024. V. 22. № 2. P. 54-63. DOI: https://doi.org/10.18127/ j20700970-202402-06 (In Russian)

1. Gorelova G.V., Karelin V.P. Metody teorii grafov v kognitivnom analize i modelirovanii social'no-ekonomicheskih system. Vestnik Taganrogskogo instituta upravleniya i ekonomiki. 2005. № 1. S. 74–78 (In Russian).
2. Pileckij I.I., Batura M.P., Volorova N.A. Graf znanij i mashinnoe obuchenie kak bazis metodologii iskusstvennogo intellekta v obuchenii. 2021 (In Russian).
3. Kudryavcev D. V. i dr. Metod kollektivnoj vizual'noj razrabotki ontologicheskogo grafa znanij. Iskusstvennyj intellekt i prinyatie reshenij. 2019. № 1. S. 27–38 (In Russian).
4. Abdul A. et al. COGAM: measuring and moderating cognitive load in machine learning model explanations. Proceedings of the 2020 CHI conference on human factors in computing systems. 2020. P. 1–14.
5. Willard J. et al. Integrating scientific knowledge with machine learning for engineering and environmental systems. ACM Computing Surveys. 2022. V. 55. № 4. P. 1–37.
6. Ji S. et al. A survey on knowledge graphs: Representation, acquisition, and applications. IEEE transactions on neural networks and learning systems. 2021. V. 33. № 2. P. 494–514.
7. Fensel D. et al. Knowledge graphs. Switzerland: Springer International Publishing, 2020.
8. Gutierrez C., Sequeda J. F. Knowledge graphs. Communications of the ACM. 2021. V. 64. № 3. P. 96–104.
9. Reimann D. Weighing the visual evidence–Experiments on the perception of data graphs: Дис. – Dissertation, Hagen, FernUniversität in Hagen. 2020.
10. Baumann T. Theoretical Computational Models for the Cognitive Map: Thesis. Universität Tübingen. 2023.
11. Peer M. et al. Structuring knowledge with cognitive maps and cognitive graphs. Trends in cognitive sciences. 2021. V. 25. № 1. P. 37–54.
12. Xia L. et al. Toward cognitive predictive maintenance: A survey of graph-based approaches. Journal of Manufacturing Systems. 2022. V. 64. P. 107–120.
13. Poduval P. et al. Graphd: Graph-based hyperdimensional memorization for brain-like cognitive learning //Frontiers in Neuroscience. 2022. V. 16. P. 757125.
14. Putri S.N., Saputro D.R.S. Construction fuzzy logic with curve shoulder in inference system mamdani. Journal of Physics: Conference Series. IOP Publishing, 2021. V. 1776. № 1. P. 012060.
15. Yunan A., Ali M. Study and implementation of the fuzzy Mamdani and Sugeno methods in decision making on selection of outstanding students at the South Aceh polytechnic. Jurnal Inotera. 2020. V. 5. № 2. P. 152–164.
16. Sharma V., Jain S. Teaching Staff Performance Analysis by Fuzzy Mamdani Inference System. 2020 3rd International Conference on Intelligent Sustainable Systems (ICISS). IEEE. 2020. P. 876–880.
17. Khomeiny A.T. et al. Grading system recommendations for students using fuzzy mamdani logic. 2020 4th International Conference on Vocational Education and Training (ICOVET). IEEE. 2020. P. 1–6.