Subject object parameter prediction method and device based on QGRU

• Main Author: MA HONGLI
• Format: Patent
• Language: Chinese; English
• Published: 22.11.2022
• 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; PHYSICS; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE,COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTINGPURPOSES, NOT OTHERWISE PROVIDED FOR

The invention discloses a QGRU-based subject matter target parameter prediction method and device, and the method comprises the steps: obtaining a data set of a subject matter in a period of time, and setting a training data set and a test data set; inputting the training data set into a preset quantum gating recurrent neural network, completing training when a convergence state is reached, storing parameters of the quantum gating recurrent neural network, and generating a subject matter target parameter prediction model; and inputting the test data set, and outputting a predicted value by the subject matter target parameter prediction model. A data set of the subject matter in a certain period of time in the past is obtained, so that time sequence data of relevant parameters of the subject matter can be obtained. The data set is divided into a training data set and a test data set, the training data set is input into the quantum gating recurrent neural network, parameters are stored after a convergence state