User preference evaluation method and device, electronic equipment and storage medium

The invention relates to the technical field of big data science, and provides a user preference evaluation method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining user data of a target user; inputting the user data into a user preference evaluation model to obtain preference information of the target user output by the user preference evaluation model; wherein the user preference evaluation model is obtained by training according to sample user data, labels of the sample user data, Q values of the labels and mutual information among the labels; the Q value represents a probability of being rejected but correct. According to the method, the user preference evaluation model is trained by adding the Q values corresponding to the labels of the sample user data and the mutual information between the labels, so that the problem of deviation of user preference estimation can be effectively solved, and the accuracy of preference information obtained by evaluating t