| CPC G06Q 30/0201 (2013.01) [G06Q 50/01 (2013.01); H04L 67/306 (2013.01)] | 17 Claims |
|
1. A method for generating a user profile, executed by a computing device, the method comprising:
acquiring user characteristic data of a first user and user characteristic data of at least two second users, each of the at least two second users having a social relationship with the first user;
clustering the at least two second users to obtain at least two user sets, a similarity between the user characteristic data of any two second users in each user set satisfying a similarity condition;
determining first key user characteristic data corresponding to the each user set according to the user characteristic data of the second users in the each user set; and
generating a user profile of the first user according to the first key user characteristic data corresponding to the each user set and the user characteristic data of the first user,
wherein clustering the at least two second users comprises:
acquiring a category number corresponding to the user characteristic data of the at least two second users as a first number;
acquiring a Gaussian mixture model according to the first number, where the Gaussian mixture model includes K Gaussian components, and K is the same as the first number;
acquiring a probability that the user characteristic data of each of the at least two second users belongs to an i-th Gaussian component as a target probability, where i is a positive integer less than or equal to K; and
clustering the second users whose target probability is greater than a probability threshold among the at least two second users to obtain a user set corresponding to the i-th Gaussian component.
|