Data clustering method, server and system and computer readable storage medium

Abstract

The invention relates to the technical field of data processing, particularly provides a data clustering method, server, and system and a storage medium, and aims to solve the technical problem of howto quickly cluster a large batch of to-be-clustered data. For the purpose, according to the method provided by the embodiment of the invention, a similar data retrieval result corresponding to the to-be-clustered data set fed back by each grouping node server can be received, and the to-be-clustered data set and the similar data retrieval result are clustered. Through similar data retrieval, thedata samples with poor similarity with the to-be-clustered data in the data samples can be screened out, so that the data volume when computer equipment is used for clustering processing can be remarkably reduced, and the defect that the operational capability of the computer equipment is reduced is overcome. Meanwhile, the to-be-clustered data is dispersed to different retrieval node servers forsimilar data retrieval, and the defect that the operational capability of the servers is reduced due to the fact that similar data retrieval is conducted on a large batch of data at the same time canbe overcome.

Description

technical field [0001] The present invention relates to the technical field of data processing, and in particular, to a data clustering method, server, system and computer-readable storage medium. Background technique [0002] When performing face category analysis based on face images, cluster analysis is usually performed between the image features of the face images to be analyzed and the image features of face samples in the database, and the face images to be analyzed and the database are judged according to the results of the cluster analysis. which face samples in the face images belong to the same category, and then determine the category of the face image to be analyzed according to the category of these face samples (for example, determine which person the face image to be analyzed belongs to). At present, conventional data clustering systems mainly use a single server to store face samples and face data to be clustered, and then cluster the face samples and face d...

AI Technical Summary

Problems solved by technology

However, when face data clustering is performed in application scenarios with a large amount of face data to be clustered, such as a station, security monitoring in an administrative area, etc., these face data to be clustered will not only significantly increase the number of data clusters The data storage pressure of the similar system will also greatly reduce the data computing capability of the data clustering system, so that the data clustering system cannot quickly complete the clustering of the face data to be clustered

Images