Information pushing method, storage medium and server

A server, comprising:

• one or more processors;
• and
• memory;
• and
• a plurality of instructions stored in the memory, wherein the instructions, when executed by the one or more processors, cause the one or more processors to perform the following operations:
• acquiring a respective feature label vector of each seed user of a plurality of seed users;
• forming a first preset number of clusters corresponding to the first preset number of information categories according to the respective feature label vectors of the plurality of seed users;
• calculating a central vector of a corresponding cluster according to the respective feature label vectors of the seed users in each cluster of the first preset number of information categories;
• acquiring a feature weight vector corresponding to the information categories the first preset number of information categories;
• acquiring a respective feature label vector of each potential user in a potential user group;
• calculating respective first distances from the potential users to the central vector of the first preset number of information categories according to the feature label vectors of the potential users, the feature weight vectors and the central vectors corresponding to the first preset number of information categories;
• selecting a second number of potential users corresponding to the shortest first distances from the first distances for as target users;
• and
• transmitting push information which is matched with corresponding information categories of the target users to the terminals of the target users.

A non-transitory computer-readable storage medium storing a plurality of instructions configured for execution by a server having one or more processors, wherein the plurality of instructions cause the server to perform the following operations:

• acquiring a respective feature label vector of each seed user of a plurality of seed users;
• forming a first preset number of clusters corresponding to the first preset number of information categories according to the respective feature label vectors of the plurality of seed users;
• calculating a central vector of a corresponding cluster according to the respective feature label vectors of the seed users in each cluster of the first preset number of information categories;
• acquiring a feature weight vector corresponding to the information categories the first preset number of information categories;
• acquiring a respective feature label vector of each potential user in a potential user group;
• calculating respective first distances from the potential users to the central vector of the first preset number of information categories according to the feature label vectors of the potential users, the feature weight vectors and the central vectors corresponding to the first preset number of information categories;
• selecting a second number of potential users corresponding to the shortest first distances from the first distances for as target users;
• and
• transmitting push information which is matched with corresponding information categories of the target users to the terminals of the target users.