K-means text clustering method and device of built-in constraint rules
The invention discloses a k-means text clustering method and device of built-in constraint rules. The method includes the steps of preprocessing a to-be-clustered text set through the second constraint rule to obtain a second preprocessing set corresponding to the second constraint rule, obtaining k...
Saved in:
Main Authors | , , |
---|---|
Format | Patent |
Language | Chinese English |
Published |
20.04.2018
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | The invention discloses a k-means text clustering method and device of built-in constraint rules. The method includes the steps of preprocessing a to-be-clustered text set through the second constraint rule to obtain a second preprocessing set corresponding to the second constraint rule, obtaining k texts in the to-be-clustered text set to serve as the cluster center, if the cluster center is contained in one sub-set of the second preprocessing set, adding texts in another sub-set of the second preprocessing set into a cluster exclusive set corresponding to the cluster center, if current textsin the to-be-clustered text set are contained in x cluster exclusive sets, calculating the distances between other (k-x) cluster centers except the cluster center corresponding to the cluster exclusive set and the current texts, adding the current texts into the cluster corresponding to the cluster center nearest to the current texts, recalculating a new cluster center of each cluster, and if thenew cluster centers meet |
---|---|
Bibliography: | Application Number: CN201711236589 |