US 12,175,293 B2
Allocating computing resources based on properties associated with location
Erich Peter Stuntebeck, Johns Creek, GA (US); Ravish Chawla, Chamblee, GA (US); and Kar Fai Tse, Peachtree Corners, GA (US)
Assigned to Omnissa, LLC, Mountain View, CA (US)
Filed by Omnissa, LLC, Mountain View, CA (US)
Filed on Oct. 25, 2021, as Appl. No. 17/452,153.
Application 17/452,153 is a continuation of application No. 16/451,632, filed on Jun. 25, 2019, granted, now 11,182,214.
Prior Publication US 2022/0043686 A1, Feb. 10, 2022
This patent is subject to a terminal disclaimer.
Int. Cl. G06F 9/50 (2006.01); G06K 19/07 (2006.01); G06N 20/00 (2019.01); G06F 9/455 (2018.01)
CPC G06F 9/5027 (2013.01) [G06F 9/5077 (2013.01); G06K 19/0723 (2013.01); G06N 20/00 (2019.01); G06F 9/45533 (2013.01); G06F 9/45541 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A system, comprising:
at least one computing device;
program instructions stored in memory and executable in the at least one computing device that, when executed by the at least one computing device, cause the at least one computing device to:
receive a first request from a user account for at least one virtual machine that provides a computing resource to the user account in a computing environment;
determine that the user account is a new account that is not associated with any past usage data;
execute a general usage model trained on aggregated usage data collected from a plurality of other user accounts;
select a location to deploy the virtual machine based on the execution of the general usage model and deploy the virtual machine in the selected location;
collect usage data for a client device associated with the user account, the usage data including a location history of the client device;
train a predictive usage model associated with the user account in the computing environment based on the usage data, the predictive usage model generating a predicted location of the client device;
in response to a second request received from the user account, execute the predictive usage model to determine a plurality of location properties associated with the predicted location; and
allocate at least one computing resource based upon the predictive usage model and the plurality of location properties such that the at least one virtual machine is available at a future time associated with the predicted location of the client device.