Online handwritten signature character segmentation method and system, storage medium and electronic equipment

The invention requests to protect an online handwritten signature character segmentation method. An online handwritten character is segmented by using a deep learning technology to form an end-to-end scheme, collected signature stroke data is preprocessed to obtain a stroke feature sequence of paired data, a data set is formed, the data set is input into a basic prediction model for training, and the training result is obtained. The output of the basic prediction model is the same length of probability distribution vectors of the stroke feature sequence, a label prediction probability corresponding to the position of the signature stroke feature sequence, an index value corresponding to the maximum value of the probability prediction probability is taken, the index value is mapped into a label according to a mapping relation, and then a point index corresponding to each signature is obtained according to the label. A sampling point data sequence obtained by a related writing device is input, and a character s