Fecha de publicación: 26/03/2020 Fuente: WIPO Food Portada A method for controlling a food material processing robot, comprising: acquiring an image of a food material to be processed (S100); obtaining food material type information of the food material to be processed and corresponding food material processing information by means of a neural network model according to the image of the food material to be processed, and outputting a corresponding food material processing instruction (S200), wherein the neural network model is obtained by training according to food material processing images and/or videos. When the food material is processed, the food material type is identified by means of the neural network model and the corresponding food material processing information is obtained. The robot processes the food material according to the food material processing information, that is, different processing processes are performed for different food materials, such that the manner of food material processing is more flexible. According to different food material processing images and/or videos, food material processing information of a plurality of types of different food materials is learned, so that the application range is wider, and food material processing is more scientific and reasonable.