Transaction data prediction method, prediction model training method, device and equipment

• Main Authors: LIU YUKAI, AN YUNJING, LIU JI
• Format: Patent
• Language: Chinese; English
• Published: 14.11.2023
• 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 provides a transaction data prediction method, a prediction model training method, a device and equipment. The invention relates to the technical field of artificial intelligence, in particular to the fields of neural network models, time sequence prediction and the like. According to the specific scheme, a first time feature sequence of a target object is input into an input layer of a prediction model, a second time feature sequence of the target object is obtained, and the first time feature sequence is used for representing features of the target object in a first time period; inputting the second time feature sequence into a middle layer of a prediction model to obtain a third time feature sequence of the target object; and inputting the third time feature sequence into an output layer of the prediction model to obtain a transaction data prediction value of the target object in the second time period. According to the scheme of the invention, the capability of capturing the key features in