Mahsup service clustering method based on density peak detection

Abstract

The invention discloses a Mahsup service clustering method based on density peak detection, and the method comprises the following steps: 1, carrying out the local density, inter-vector distance and higher density nearest distance calculation of all feature vectors of Mashup services participating in clustering; 2, based on the density information calculated in the step 1, screening out candidatepoints of a clustering center from all Mashup service feature vectors; and 3, for the clustering center candidate points obtained in the step 2, further screening out the most appropriate K initial clustering centers, and performing K-means clustering. According to the method, the Mashup service clustering precision can be effectively improved, and the service search space is reduced.

Description

technical field [0001] The invention relates to the field of Mashup service clustering, in particular to a Mahsup service clustering method based on density peak detection. Background technique [0002] Mashup technology is a convenient and efficient web application development technology. It can quickly build a mashup service that meets user needs by mixing and matching a variety of web APIs with different functions. With the support of Mashup technology, software developers can usually refer to Mashup services with similar functions to complete the construction of Mashup services. However, with the rapid increase in the number and types of mashup services on the Internet, how to quickly and accurately find the mashup service that meets the most reference value from these massive service collections has become a challenging problem. [0003] A lot of research work has shown that if the Mashup service is accurately clustered in advance, the search space of the service can b...

AI Technical Summary

Problems solved by technology

Although the idea of ​​the DPC algorithm is concise and efficient, there are still some problems in practical applications: (1) the clustering effect is very dependent on the selection of the cut-off distance; (2) when the amount of data is large, it may not be easy to pick out Appropriate cluster center point