Recommendation method based on a food safety grade score value and food similarity of a user

The invention discloses a recommendation method based on a food safety grade score value and food similarity of a user. The recommendation method comprises the following steps: 1) obtaining score data of the user on food; 2) calculating the scoring weight of each piece of scoring data; 3) inputting the scoring data and the scoring weight into a machine learning model for parameter training; and 4) after the parameter training is completed, obtaining a food similarity matrix, and finally calculating and generating a food recommendation list of the user through the score data of the user and the food similarity matrix, so that food is recommended to the user. According to the method, a machine learning model is trained, a neighborhood-based collaborative filtering method is combined and used, a similarity matrix of food is learned from scoring data of the food by a user, and sparsity is introduced into the similarity matrix while the time sequence of the scoring data is considered, so that recommendation can be