Power service data processing method based on feature recognition and FCM
Aiming at the problems of low efficiency and poor clustering analysis ability of existing data processing methods for power grid user service,this paper proposes a data processing and analysis method based on Knowledge Graph(KG)and improved Fuzzy C-Means clustering(FCM).This method utilizes KG to break down the complex user data text processing process into knowledge element structures,and uses a knowledge base to extract the required feature content and perform standardization processing.By introducing an improved FCM algorithm for clustering analysis of processed samples,potential information in user data was discovered.The experimental analysis results show that the proposed method can effectively extract various types of user information and achieve clustering.Among the clustering evaluation indicators,the compactness index is 0.96,the FMI index is 0.97,and the separation index is 0.53.Compared with traditional methods,it has better clustering analysis and global optimization capabilities.
Knowledge GraphFCMfeature recognitionclustering analysispower userservice data
万方数据
维普
