Software implementation of the system for learning to write Chinese characters

Abstract

Objective. The purpose of the work is devoted to the development and description of the mathematical model of the Chinese character recognition system, taking into account all the features of writing the Chinese language. The Chinese language learning app with character recognition module can help you replace a native speaker or home teacher for self-study. However, the developed software applications are based only on the creation of a neural network and cannot provide recognition, taking into account all the features of the language, which is so important when studying, therefore this topic is still relevant.
Method. The neural network training model is based on the use of artificial neural networks using the backpropagation algorithm.
Result. The article presents a software implementation of a system for teaching Chinese characters, taking into account the peculiarities of writing, the direction of each feature and its exact definition, taking into account the correct sequence and location in the character, as well as controlling the length of the features.
Conclusion. Each of the writing features is an integral part of learning a language, since it can not only completely change the meaning of the written hieroglyph, but also help the learner to memorize the hieroglyph in a structured way, giving him a clear structure and algorithm of actions for writing the hieroglyph. When errors are detected when writing, the system will indicate to the user where exactly and in what area the error was made, what feature of the language he did not take into account, and attention should be paid to it.