The research of handwritten Chinese character recognition method has been the topic which the scholars in the related domain endeavor to explore. Chinese character recognition can be divided into online and offline handwritten Chinese character recognition. Deep Learning is a general term for a class of pattern analysis methods. It is a branch algorithm in the field of ML (Machine Learning) . The ultimate goal of deep learning is to make machines capable of human‐like analytical learning, recognizing speech, image, text and other data. This paper analyzes a new method of handwritten Chinese character recognition based on deep learning. The method uses convolutional neural network to build a deep learning model and uses the model to recognize Chinese handwriting in images. Through this system, the user can recognize the complete handwritten Chinese character information, and has a high recognition rate for similar characters.