This invention provides a method, device, terminal, and medium for assistive training in the
rehabilitation of
spasticity after brain injury. The method includes: acquiring surface
electromyography (EMG) signals and the
start time of postural transition; obtaining average amplitude, maximum voluntary contraction amplitude, left-right symmetry index,
stability index, and pre-activation time; obtaining a core
muscle group function score based on the calculated average amplitude, maximum voluntary contraction amplitude, left-right symmetry index,
stability index, and pre-activation time; determining the patient's training position, training goals, training mode,
initial treatment parameters, and treatment optimization goals; guiding the patient in adaptive
rehabilitation training, collecting surface EMG signals of the patient's core
muscle groups in real time, dynamically adjusting stimulation parameters through an adaptive prediction model and the surface EMG signals, and completing the assistive
rehabilitation training for
spasticity after brain injury after the adaptive prediction model converges. This reduces reliance on the therapist's subjective experience and achieves precise
rehabilitation training.