Image selection method and electronic device

An electronic device, comprising one or more processor, a memory, and a display screen, the memory being coupled to the one or more processors, the memory being configured to store computer program code comprising computer instructions, and the one or more processors invoking the computer instructions to cause the electronic device to perform operations comprising:

• detecting first feedback information, the first feedback information comprising a plurality of images and a user operation acting on an image in the plurality of images;
• adjusting parameters of a decision model according to the first feedback information to obtain an updated decision model, wherein the decision model is an algorithm model configured to select an optimal image from multiple images obtained through continuous shooting, and the decision model includes one or more image features, each of the one or more image features being associated with one or more scores used for scoring the image feature in an image, and a weight being specified for each of the one or more image features;
• and
• selecting a first image from a first image group as the optimal image of the first image group according to the updated decision model,
• wherein the first feedback information comprises a first facial feature and a proportion of images comprising the first facial feature in a gallery,
• the first facial feature being a facial feature corresponding to the largest quantity of images in the gallery that comprise the facial feature, and the gallery comprising images stored in the electronic device,
• wherein the one or more processors are further configured to invoke the computer instructions to cause the electronic device to perform operations comprising:
• increasing the weight of a facial expression score of the first facial feature in the decision model, the one or more image features in the decision model comprising one or more facial features, the one or more facial features comprising the first facial feature,
• wherein the facial expression score is used for scoring an expression of the first facial feature of an image, and a greater weight of a facial feature indicates a greater probability that an image including the facial feature is selected as the optimal image.