Data clustering method, apparatus and storage medium

Abstract

The invention discloses a data clustering method, a device and a storage medium, belonging to the technical field of data mining. The method comprises the following steps: the original sample data setis uniformly sampled to obtain a uniform sample data set; the positions of each sample in the uniform sample data set are updated to obtain a data set after updating the positions; data clustering isperformed on the updated dataset of the position by aggregation clustering technique. As that original sample data set is uniformly sample, the number of sample is reduced, As a result, the terminalrunning resources are reduced, the clustering speed is improved, the positions of each sample in the obtained uniform sample data set are updated subsequently, and the data clustering is carried out on the data set after the position updating through the aggregation clustering technology, so that the accuracy rate of clustering the samples is improved, and the accuracy rate of clustering the samples is improved.

Description

technical field [0001] The invention relates to the technical field of data mining, in particular to a data clustering method, device and storage medium. Background technique [0002] In the big data environment, shape clustering algorithms need to be used in many application scenarios to solve problems. For example, in the field of geographic information processing, clustering algorithms are used to extract terrain information of mountains and rivers; in the field of image processing, people or objects in images are identified; in the field of medicine, protein structures are clustered to identify different types of protein and more. Among them, a clustering algorithm refers to an algorithm that divides similar data samples into the same cluster through the similarity between each data sample in a data set, thereby realizing the algorithm of dividing the samples of the original data set into multiple clusters. [0003] At present, clustering algorithms usually require cer...

AI Technical Summary

Problems solved by technology

[0005] The embodiment of the present invention provides a data clustering method, device and storage medium, which are used to solve the problem of low clustering efficiency and low accuracy in related technologies

Images