Data processing method, server and electronic device

Abstract

The present invention provides a data processing method, a server and an electronic device, which can train a prediction model by using a circulating neural network, and the prediction model is used for predicting a target index of a predetermined device. In a process of training the prediction model, In addition to taking training samples as model input, equipment state information of the predetermined equipment corresponding to an index to be predicted is also introduced, and the first equipment state information outputted from the upper sample of the first training sample in the training process is taken as the state input information of the first training sample at the time of training, this enables the equipment state information to be transmitted in the training process of each sample according to the training order of each sample, Correspondingly, the obtained prediction model can achieve the long-term memory effect of the equipment state information, and when the prediction model is used for subsequent prediction, the target index can be predicted by combining the data of the prediction sample and the memorized equipment state information, so that the prediction result canhave a higher accuracy rate.

Description

technical field [0001] The invention belongs to the technical field of big data analysis and prediction, and in particular relates to a data processing method, a server and an electronic device. Background technique [0002] In the process manufacturing industry represented by the petrochemical industry, it is very critical to accurately predict the yield of its target output (such as gasoline, liquefied gas, etc. in the petrochemical industry) to guide the production process and maximize economic benefits. . [0003] Because the process manufacturing industry involves many processes, complex processes, and complex interactions between each process, it will be difficult to accurately predict the yield of its target output. Therefore, for the process manufacturing industry, it is necessary to provide a solution to effectively and accurately predict indicator data such as target output yield and other indicators. SUMMARY OF THE INVENTION [0004] In view of this, the purpo...

AI Technical Summary

Problems solved by technology

[0003] Due to the many processes involved in the process manufacturing industry, the processes are complex, and there are often complex interactions among the various processes, which makes it difficult to accurately predict the yield of the target output.

Images