Drainage data counterfeiting discrimination method and system based on comparative learning

• Main Authors: ZHU BIN, ZHANG RIGUANG, LONG LIHUI, CHAN SHENGNING, YAO XIAOCHUN, LI CHENYANG, LI BAIYUN, ZHANG HAOBIN
• Format: Patent
• Language: Chinese; English
• Published: 24.05.2024
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; 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 invention discloses a drainage data counterfeiting discrimination method and system based on comparative learning. The method comprises the following steps: preprocessing historical data; building a comparative learning encoder based on cavity convolution and Transform information extraction according to the time sequence of the historical data, and learning and optimizing the comparative learning encoder by using the historical data; obtaining real-time data of drainage, and training the regression model as a training set; predicting drainage data by using the trained training regression model to obtain a predicted value; setting a judgment threshold value; and judging whether drainage data counterfeiting exists or not according to the true value and the predicted value of the real-time drainage data and the judgment threshold value. Enterprise drainage training and prediction are carried out by using coded data, a judgment threshold value is set based on real drainage data and predicted drainage data, a