Login| Sign Up| Help| Contact|

Patent Searching and Data


Title:
K-MEANS ALGORITHM-BASED DATA CLUSTERING METHOD AND DEVICE
Document Type and Number:
WIPO Patent Application WO/2017/181660
Kind Code:
A1
Abstract:
The invention relates to the technical field of computers. Provided are a K-means algorithm-based data clustering method and device. The method comprises: a cluster server receives a clustering request, the clustering request comprising a maximum computation load, K, and a data set (201); the cluster server determines, according to the maximum computation load, an adjustment factor corresponding to the maximum computation load (202); the cluster server randomly selects one data item from the data set, and selects K-1 data items from the data set according to the adjustment factor and the randomly selected data item, the randomly selected data item and the K-1 data items constituting K initial cluster centers of the data set (203); and the cluster server performs, according to the K initial cluster centers, clustering on N data items in the data set (204). The method can automatically adjust clustering efficiency according to the maximum computation load, thereby increasing clustering efficiency.

Inventors:
HU FEIRAN (CN)
WANG NANNAN (CN)
CAO JUN (CN)
Application Number:
PCT/CN2016/105949
Publication Date:
October 26, 2017
Filing Date:
November 15, 2016
Export Citation:
Click for automatic bibliography generation   Help
Assignee:
HUAWEI TECH CO LTD (CN)
International Classes:
G06K9/62
Domestic Patent References:
WO2008022341A22008-02-21
Foreign References:
CN105447521A2016-03-30
CN104537067A2015-04-22
CN104376057A2015-02-25
Download PDF: