This article presents a study of a dictionary-based pre-filter for safe educational content generation in a school environment. An Android application based on the MVVM architecture was developed as an experimental implementation with local pre-moderation, where user prompts are checked against indicator lexical items before being sent to an external API. The experiment was conducted under educational conditions. The evaluation covered the blocking rate, its distribution by reason, differences across learning task types, and on-device latency. The results show that this approach provides a basic level of safety with minimal impact on user interaction.
| Mualliflar | Ибрагимов, Диёрбек, Абдуллаев, Темурбек |
|---|---|
| Jurnal | Al-Farg'oniy avlodlari |
| Nashr sanasi | 2026-03-18 |
| Son | 1 |
| Betlar | 276-281 |
| Til | Rus |
generative ai, educational technologies, pre-moderation, dictionary-based filter, content safety, school environment, response latency, генеративный ии, образовательные технологии, предмодерация, словарный фильтр, безопасность контента, школьная среда, задержка отклика, generativ sun'iy intellekt, ta'lim texnologiyalari, oldindan moderatsiya, lug'atli filtr, kontent xavfsizligi, maktab muhiti, javob kechikishi
This article analyzes current trends in the field of cybersecurity. Today, the stable and protected operation of data transmission networks, computer systems, and mobile devices has become a fundamental condition…
This article analyzes two methods of adversarial attacks created against machine — training — based pest program detection systems-JSMA (Jacobian Saliency Map Attack) and Carlini & Wagner (C&W) - in a practical…
The scarcity of labeled data remains a fundamental limitation of supervised learning models. This study proposes an autoencoder-based unsupervised approach for detecting anomalies in network traffic. Experiments…
This paper proposes a speech recognition system for automatically recognizing separately pronounced Uzbek words. The system uses MFCC for acoustic feature extraction and a Gaussian Hidden Markov Model for word modeling…
This article analyzes the effectiveness of malware detection methods using artificial intelligence technologies. With the rapid development of modern information and communication technologies, the number of malicious…
In this work, methods and algorithms for improving the quality of a given image are studied. Methods for reducing noise, improving contrast, increasing sharpness, and clearly displaying image elements during image…
This study presents a comprehensive simulation analysis of germanium (Ge) diffusion into silicon (Si) substrates with a resistivity of 100 Ω·cm (n-type) in the temperature range of 800–1200 °C using the Synopsys…
This article describes the research conducted by training the neural network model proposed by NVIDIA in speech recognition with a speech dataset of the Uzbek language. Currently, various models of neural networks are…
This article examines the mathematical modeling of heat and mass transfer processes under turbulent flow conditions. Flow characteristics are analyzed based on the Reynolds-Averaged Navier-Stokes (RANS) approach…
While large-scale pre-trained models have significantly advanced multilingual Automatic Speech Recognition (ASR), many low-resource languages remain under-served due to the scarcity of high-quality annotated speech…