In order to further improve the clustering effect of Telecom complaint text,so as to analyze and process user feedback more efficiently,this paper first summarizes CFSFDP algorithm and differential evolution algorithm;secondly,an improved CFSFDP clustering method is designed,and the differential evolution algorithm is used to automatically optimize the important parameters of CFSFDP algorithm,which greatly improves the clustering accuracy;finally,experiments show that the improved method designed in this paper performs well in clustering accuracy,purity,recall rate and F value,which provides an innovative solution for efficient clustering of Telecom complaint text.