Information pushing method and device, electronic equipment and computer readable medium

Abstract

The embodiment of the invention discloses an information pushing method and device, electronic equipment and a computer readable medium. A specific embodiment of the method comprises the steps of splitting a feedback user feature vector set corresponding to a feedback target into primary feedback user feature vector subsets according to time granularity information; for each primary feedback user feature vector subset, performing clustering processing on each primary feedback user feature vector to obtain each secondary feedback user feature vector subset; performing optimization processing on each obtained secondary feedback user feature vector subset to obtain a seed user feature vector set; in response to the received target user feature vector, generating similarity information; and in response to the similarity information meeting a preset similarity condition, pushing the preset channel information to a user terminal corresponding to the target user feature vector. According to the embodiment, the accuracy and recall rate of the selected seed users are improved, the association effect of similar crowd amplification is improved, and the computing power resource is saved.

Description

technical field [0001] The embodiments of the present disclosure relate to the field of computer technology, and in particular, to an information push method, device, electronic equipment, and computer-readable medium. Background technique [0002] Crowd lookalike is a technology based on seed users to find more similar groups with potential relevance. At present, when selecting seed users, the usual method is: manually select seed users or use real-time feedback users as seed users. [0003] However, when using the above-mentioned methods to circle seed users, there are often the following technical problems: when there are many user portrait tags, the accuracy and recall rate of the seed users circled by manual means is low; the feedback users are directly used as seed users, The characteristics of seed users are relatively scattered, and the correlation effect of similar crowd amplification is poor. At the same time, when there are many feedback users, similar crowd sear...

AI Technical Summary

Problems solved by technology

[0003] However, when using the above-mentioned methods to circle seed users, there are often the following technical problems: when there are many user portrait tags, the accuracy and recall rate of the seed users circled by manual means is low; the feedback users are directly used as seed users, The characteristics of seed users are relatively scattered, and the correlation effect of similar crowd amplification is poor. At the same time, when there are many feedback users, similar crowd search is performed, resulting in a waste of computing resources

Images