Information push object prediction model obtaining method, terminal and storage medium

Abstract

The invention provides an information push object prediction model obtaining method, a terminal and a storage medium. The method comprises the steps of receiving an initial desensitization data set; performing data screening in the initial desensitization data set according to a preset data screening strategy to obtain a screened data set; combining the data with the same user identification information in the screened data set to obtain a combined data set; obtaining target data in the merged data set according to a preset field screening strategy to obtain a training set; and taking the input field value in the training set as the input of a deep neural network to be trained, and taking the output field value in the training set as the output of the deep neural network to be trained to train the deep neural network to be trained so as to obtain the deep neural network of the target push object for information prediction. According to the embodiment of the invention, the method achieves the effective prediction of the missing field in the data set, does not need the manual revisit to complement the missing value, and improves the data processing efficiency.

Description

technical field [0001] The present invention relates to the technical field of data processing, in particular to a method for acquiring a prediction model of an information push object, a terminal and a storage medium. Background technique [0002] At present, in the user data information obtained during the operation of the enterprise, some data may have missing data values ​​in multiple fields. For example, in the banking field, in the user data obtained by banks, some data have no missing values ​​in each field. , and the authenticity of the data is high, but the field values ​​of some data are seriously missing, more specifically, whether the identification field of credit card users is missing. The absence of key data fields leads to inefficiency in determining whether to push notification information based on the key fields. [0003] In order to better complement the missing values ​​of the data, it is necessary to predict the missing values, so as to determine whethe...

AI Technical Summary

Problems solved by technology

[0005] In view of the deficiencies in the prior art above, the purpose of the present invention is to provide a method for obtaining a prediction model of an information push object, a terminal, and a storage medium, aiming at solving the problem of missing key fields in each data set in the prior art. The problem of inefficiency in determining whether to push notification information based on this key field

Images