Data processing method, device and equipment and storage medium

Abstract

The embodiment of the invention discloses a data processing method, device and equipment and a storage medium. The method comprises the steps of taking acquired first historical data and a processingresult of the first historical data as training samples, and performing training based on at least one machine learning algorithm to obtain at least one updating model, wherein the first historical data is data received from a first historical moment to a current moment; selecting a candidate model from the at least one updating model, and distributing the currently obtained to-be-processed data to the candidate model and a currently used target model for processing; and determining a new target model from the candidate model and the currently used target model according to the processing result, and processing the new data by adopting the new target model. According to the embodiment of the invention, the performance of each model for processing the current data is tested on line, so thatthe optimal model is accurately and efficiently determined as the target model, and rapid and smooth updating of the model is realized.

Description

technical field [0001] Embodiments of the present invention relate to the technical field of data processing, and in particular, to a data processing method, device, device, and storage medium. Background technique [0002] Machine learning is the process of obtaining a data model by analyzing known data, and using the model to predict unknown data. Different machine learning models can be trained based on different specific algorithms and logic criteria. [0003] With the development of online business, the scale of data continues to increase, and the rate of data change is getting faster and faster. There are differences between the training data used in the development and training process and the prediction data when applying the machine learning model. Using traditional machine learning algorithms to obtain The model can not adapt well to the changing law of the new data, which reduces the accuracy of the prediction of unknown data using the model. Therefore, it is of...

AI Technical Summary

Problems solved by technology

With the support of certain training data, the accuracy rate of the updated models obtained may be almost the same. Without the support of more data, it is impossible to judge which model is more suitable for unknown data changes. If the performance of each model is tested one by one, inefficient

Images