Developing a neural network model for creating technical documents based on design layouts

The talk is devoted to the development of a neural network model for the automatic creation of technical documents based on design layouts. 

The research explores various neural network models, such as ChatGPT, Llama, Gemini (and possibly YandexGPT), used for pre-training tasks in layout recognition and user guide generation. The dataset and prompts used for pre-training are discussed, and the obtained results and analysis of the quality of the generated technical documents are presented. 

In conclusion, the applicability and effectiveness of the neural network model in automating the creation of technical documents from design layouts are evaluated, and the prospects for its development and application in real-world scenarios are discussed.