Abstract: A method for classifying tap events on a touch panel includes collecting the tap events on the touch panel and recording the type of each of the tap events as a sample; generating a sample set including a plurality of the samples; using the sample set to train a deep neural network to determine an optimized weighting parameter group; taking the deep neural network and the optimized weighting parameter group as a tapping classifier and deploying it in a touch panel product. The present disclosure also provides a system corresponding to the classifying method, and a touch panel product.