Метод синхронізації даних термінологічних баз знань
Вантажиться...
Файли
Дата
Автори
Назва журналу
Номер ISSN
Назва тому
Анотація
Method for data synchronization in terminological knowledge bases is proposed, based on the use of a neural network and
classification by subject area topics. Text data synchronization is one of the key tasks for efficient data processing, which
involves systematizing knowledge based on its semantic component and addresses the problem of understanding context
based on already known data. To solve this problem, a comprehensive approach is used, which includes a set of solutions
and synchronization algorithms at all levels of data processing, including semantic analysis, software and hardware-level
algorithms, and the use of optimized data models for specific tasks. During the research, an algorithm for optimal data
distribution in terminological knowledge bases was developed based on the semantic value of terms. The main criteria for the
distribution of textual data in terminological knowledge bases were identified. The task of updating data in terminological
knowledge bases during their population was examined. The problem of conflicting term synchronization based on semantic
affiliation to related subject areas was formulated and described. Algorithms for term comparison based on semantic analysis,
cosine similarity, the Jaccard method, and the term frequency-inverse document frequency (TF-IDF) method were
considered. A description of the synchronization method in accordance with the created models and data structures is
provided. The advantages and disadvantages of known methods for text data synchronization using data processing
algorithms and methods are described, with examples given of data storage and retrieval tasks. The effectiveness of the
synchronization method is demonstrated using examples. Data structures were optimized for efficient storage and retrieval of
text data for text classification tasks. A prototype of terminological knowledge bases was created, and the synchronization
method was applied using the example of the call center subject area.
Опис
Ключові слова
УДК
Тип документа
Мова
ISSN
Бібліографічний опис
Яровий А. А., Кудрявцев Д. С. Метод синхронізації даних термінологічних баз знань // Матеріали XVII Міжнародної конференції «Контроль і управління в складних системах (КУСС-2024)», м. Вінниця, 16-17 жовтня 2024 р. Електрон. текст. дані. 2024. С. 99-103. URI: https://conferences.vntu.edu.ua/index.php/mccs/mccs2024/paper/view/22184.
Схвалення
Рецензія
Доповнено
Цитується в
Список використаної літератури (8)
- [Kaya, Cem & Kilimci, Zeynep & Uysal, Mitat & Kaya, Murat. (2024). A Review of Metaheuristic Optimization Techniques in Text Classification. International Journal of Computational and Experimental Science and Engineering. 10. 10.22399/ijcesen.295.
- Mohabir, S.E., Joshi, Y.C. A bibliometric analysis of the knowledge base on multinational corporations’ behavior. SN Bus Econ 4, 105 (2024). https://doi.org/10.1007/s43546-024-00705-7.
- Ünver, Mehmet. (2023). Improved cosine similarity measures for q-Rung orthopair fuzzy sets. Qeios. 10.32388/EOGFR4.
- TF–IDF. In: Sammut, C., Webb, G.I. (eds) Encyclopedia of Machine Learning. Springer, Boston, MA. https://doi.org/10.1007/978-0-387-30164-8_832
- Travieso, Gonzalo & Benatti, Alexandre & da F. Costa, Luciano. (2024). An Analytical Approach to the Jaccard Similarity Index. 10.13140/RG.2.2.23119.70562
- Berger, Bonnie & Waterman, Michael & Yu, Yun. (2020). Levenshtein Distance, Sequence Comparison and Biological Database Search. IEEE Transactions on Information Theory. PP. 1-1. 10.1109/TIT.2020.2996543.
- A. Yarovyi and D. Kudriavtsev, "Multi-purpose search to determine the context of a text message based on the dictionary data structure," 2021 IEEE 16th International Conference on Computer Sciences and Information Technologies (CSIT), LVIV, Ukraine, 2021, pp. 65-68, doi: 10.1109/CSIT52700.2021.9648803.
- Gabriel A. (2020, January). Kensho Derived Wikimedia Dataset. Retrieved September 1, 2024 from https://www.kaggle.com/datasets/kenshoresearch/kensho-derived-wikimedia-data.