The invention relates to a myoelectric 
prosthesis gesture and force control method and belongs to the technical field of myoelectric 
prosthesis. The method comprises the steps of acquiring 
forearm surface electromyogram signals; transmitting the multiple channels of surface electromyogram signals into a gesture identification model and a 
finger force identification model by segments through a 
moving window; in the gesture identification model, detecting the mobile segment of each 
signal firstly, extracting biological electromyogram 
signal feature information, and conducting 
data dimension reduction on the feature information; conducting real-time action identification and classification according to the feature information obtained after dimension reduction; in the 
finger force identification model, conducting normalization on 
original data of the 
forearm surface electromyogram signals, selecting a channel of surface electromyogram signals most closely related to each 
finger force linearly through 
correlation analysis, and conducting 
linear control on the finger force of myoelectric 
prosthesis with the surface electromyogram signals corresponding to different fingers respectively. By the adoption of the method, a prosthesis user can naturally and directly control the gesture and finger force of myoelectric prosthesis to achieve basic daily movement, and therefore the identity sense and living convenience of the prosthesis user are improved.