In this paper, we firstly propose an art style classification system based on the RNN model to study the development of the art industry, and continuously fine-tune this white noise image according to the long and short-term memory network and gated recurrent unit network until it makes this white noise image similar to the artwork image style, and the ink painting image feature extraction is mainly studied from the recurrent neural network based ink style feature extraction and the overall nested edge based The two aspects of brushstroke feature extraction based on overall nested edge detection are studied. Then, based on the art industry and big data, the ink painting style classification system is constructed, and the effectiveness of the system is verified by model art classification effect analysis. The results show that the RNN performs well on the face dataset, where the accuracy of multiple classifications up to 10 categories is above 85%. This indicates that the RNN model in this paper can maintain good performance in the ink painting art classification task.