Service state level classification method, classification model training method and electronic equipment

• Main Authors: BO KAITAO, CHEN HAO, HAN JUNHUA, WU ZHENYU, PENG XIN, LYU XIAOMENG
• Format: Patent
• Language: Chinese; English
• Published: 01.08.2023
• Subjects: CALCULATING; COMPUTING; COUNTING; DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FORADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORYOR FORECASTING PURPOSES; ELECTRIC DIGITAL DATA PROCESSING; PHYSICS; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE,COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTINGPURPOSES, NOT OTHERWISE PROVIDED FOR

The embodiment of the invention relates to the technical field of communication, in particular to a service state level classification method, a classification model training method and electronic equipment, and the service state level classification method comprises the following steps: carrying out feature extraction on real-time alarm slice data; inputting the extracted features of the alarm slice data into a pre-trained classification model used for predicting a service state level; obtaining a service state level output by the classification model, and obtaining a service state level of the real-time alarm slice data; wherein the classification model is obtained by training under a self-training framework of semi-supervised learning, an alarm sample data set used for training the classification model comprises a first type of alarm sample data and a second type of alarm sample data, the first type of alarm sample data comprises features of alarm slice data and annotation information of service state leve