AB test method and device and computer readable storage medium

Abstract

The invention discloses an AB test method and device and a computer readable storage medium. The method comprises the steps of receiving a test data stream and outputting test result data based on a current test model and the test data stream; acquiring real result data corresponding to the test data flow in a database; generating model performance information based on the test result data and the real result data; judging whether the current test model needs to be modified or not based on the model performance information, and if yes, modifying the current test model according to the model performance information and a preset modification rule; and comparing the test result data output by the current test model with the real result data to generate model performance information, so that the current state of the model is clearly and clearly displayed, and whether the performance of the current test model needs to be modified and replaced or not is accurately judged.

Description

technical field [0001] The invention relates to the field of computer testing, in particular to an AB testing method, device and computer-readable storage medium. Background technique [0002] In order to verify whether the user experience and marketing are correct, AB testing is usually used to conduct comparative experiments to determine the best solution according to the actual effect, that is, to make two (A / B) or multiple (A / B) for the web or APP interface or process. B / n) version, in the same time dimension, let visitor groups (target groups) with the same composition (similar) randomly visit these versions, collect user experience data and business data of each group, and finally analyze and evaluate The best version, officially adopted, usually implants a test method based on statistics into the model, so that the model can automatically perform AB testing. [0003] However, the models used in the current AB test are usually compared based on some simple statistical...

AI Technical Summary

Problems solved by technology

[0003] However, the models used in the current AB test are usually compared based on some simple statistical methods. When the application environment changes, it is necessary to manually retrain and replace the model with new data on a regular basis. Each test needs to be manually executed in a planned way. The length of time is also limited. If the model is replaced frequently, a lot of resources and costs will be wasted. If the replacement is too slow, the performance and performance of the test model will drop sharply, which will affect the business.

Images