Microsoft uses machine learning models to determine whether certain types of devices can upgrade the system. This strategy has been going on for a long time. Of course, Microsoft will continue to use it. According to Microsoft, machine learning models can improve the efficiency of push and potential problems, but this requires various upgrade data for model training to improve efficiency. Windows 10 20H2 will be forced to upgrade to Windows 10 21H2 version.
“We will continue to train our machine learning model through all phases to intelligently rollout new versions of Windows 10, and deliver a smooth update experience,” Microsoft said.
This version was selected because the
Windows 10 20H2 version will reach the end of its life cycle on May 10, 2022, that is, this version is about to expire and needs to be upgraded. Microsoft encourages users to upgrade to a new supported version as soon as possible, but if users do not actively upgrade and there is no setting to prohibit upgrades, Microsoft will consider forced upgrades. It is said that the forced upgrade is actually an automatic upgrade. In theory, as long as the user does not set a policy that prohibits the upgrade, the system will perform automatic upgrades in the follow-up. All kinds of data generated during the upgrade will be used to train new machine learning models to improve accuracy so that Windows 10 version 21H2 will be pushed in the next.