Virtual keyboard design method based on electromyographic signals

The invention provides a virtual keyboard design method based on electromyographic signals, and relates to the technical field of human-computer interaction and intelligence. The method of the presentinvention comprises the steps of: collecting a training sample of an electromyographic signal generated when a user clicks a keyboard, wherein labels of the training samples are gesture action sequences; denoising the electromyographic signals and converting the electromyographic signals into a time-frequency diagram, training an established gesture recognition model by using the time-frequency diagram of a training sample, recognizing the electromyographic signals acquired in real time by using the trained gesture recognition model, acquiring a gesture action sequence by using a CTC technology, and performing key code conversion on the recognized gesture action sequence. The keyboard layout designed by the invention is a T9 keyboard; as long as a user wears the MYO armlet, any plane canbe imagined into a three-r