A data processing method and related device

Abstract

The embodiment of the present application discloses a data processing method and a related device. For the product to be promoted, the historical content push data of the target product related to the product to be promoted is acquired, and the historical content push time and history in the historical content push data are obtained. At the actual conversion moment, you can obtain the information on how long the historical pushed object has been converted after being pushed. When training the survival model based on the object characteristics of the historical pushed object, the aforementioned data dimension of the conversion time is introduced, and the object is in the The probability of conversion occurring in multiple consecutive time periods turns the problem of whether to convert into a problem of delayed conversion, which enhances the learning of delayed conversion in the survival model in the time dimension, and realizes a strong correlation between the original historical content push data and the target product The decoupling of , so that the first survival model trained can also temporarily replace the conversion rate model in the cold start phase to provide conversion rate prediction for products to be promoted.

Description

technical field [0001] The present application relates to the field of data processing, in particular to a data processing method and related devices. Background technique [0002] For a new product, it is necessary to increase the exposure of the product through the Internet through content push, etc., so that a large number of users can learn about the product through the pushed content in a short period of time, so as to quickly increase the audience of the product and promote the product. Conversion rate (or clickthrough rate, CVR) is a measure of the probability of successfully converting a user through content push. Successful conversion usually refers to the user's behavior of obtaining the product corresponding to the content. If the conversion rate corresponding to the user can be accurately predicted before the content is pushed, It can effectively improve the efficiency of content push, and increase the audience of new products as much as possible with limited pus...

AI Technical Summary

Problems solved by technology

However, this positive example may be converted after the new product is launched. However, in many cases, the actual reaction of users after the new product is launched is not as popular as when making an appointment. As a result, a large proportion of reserved users do not actually convert. Some of the positive examples for training the booking model are actually not positive examples, such as unconverted booking users

[0005] As a result, the reservation model based on reservation behavior training did not accurately learn the user's preference for new products. The CVR value predicted by the reservation model will be significantly higher than the actual situation. In the cold start stage, the reservation model will directly Reduce the effect of subsequent content push

Images