Webpage clustering processing method based on improved K-means algorithm

Abstract

The invention discloses a webpage clustering processing method based on an improved K-means algorithm. The webpage clustering processing method based on the improved K-means algorithm is a webpage clustering processing method based on the improved K-means algorithm. According to the method, an initial clustering center selection algorithm and a K-means clustering algorithm are mainly combined to replace a traditional K-means algorithm to cluster webpage information. According to the algorithm, the reliability and authenticity of a clustering result are ensured from the source. And the method is applied to webpage big data processing. It is further found through experimental result analysis that compared with a traditional algorithm, the advantages of the improved algorithm is not only reflected by the accuracy of the clustering result, but also reflected by the operation efficiency, and the improved algorithm is completely suitable for webpage clustering analysis, optimizes the clustering effect of webpages and improves the stability of the algorithm.

Description

technical field [0001] The invention belongs to the field of data mining, in particular to a processing method based on K-means algorithm improvement applied to web page clustering. Background technique [0002] Clustering analysis technology is one of the important basic research topics in the field of current data mining technology. Our so-called clustering refers to putting data objects with high similarity into In a cluster, it is a clustering analysis technique that puts other data objects with high dissimilarity in different clusters as much as possible. The K-means algorithm is the most representative machine learning algorithm. A large number of practical studies have clearly confirmed that this algorithm has multiple advantages, such as simple operation and reliable results. As far as the present stage is concerned, this algorithm has derived multiple classifications, such as density, model, etc. Although the algorithm has achieved large-scale popularization and ac...

AI Technical Summary

Problems solved by technology

As far as the present stage is concerned, this algorithm has derived multiple classifications, such as density, model, etc. Although the algorithm has achieved large-scale popularization and active use in many fields by virtue of its own strong advantages, its optimal solution is subject to multiple factors

Images