Granted Patent B1

US 12,457,153 · App. 18/647,708 · Granted Oct 28, 2025

Inventors: Sumukh A. Shevde (Encinitas, CA); Nazih Almalki (Waterloo, CA)

Assignee: Google LLC

H04L41/0806H04L41/082H04L41/16

Abstract

Claims (77)

1. A method comprising:

obtaining, by one or more processors executing at a manager system, usage data from a plurality of devices, wherein each device of the plurality of devices is associated with one or more device types of a plurality of device types, and wherein each device type of the plurality of device types specifies a usage behavior;

storing, by the one or more processors, common information based on the usage data, the common information specifying device configurations shared between each of the plurality of devices;

for each device type of the plurality of device types: storing, by the one or more processor, device type features for a device type based on the usage data corresponding to one or more devices of the plurality of devices associated with the device type, the device type features specifying device configurations for the device type that is different than the common information;

determining, by the one or more processors, a provisioning device type for a first device not included in the plurality of devices, the provisioning device type specifying at least one device type of the plurality of device types;

determining, by the one or more processors, configuration information for provisioning the first device based on stored device type features associated with the provisioning device type and the common information; and

provisioning, by the one or more processors, the first device based on the configuration information.

2. The method of claim 1 , wherein determining the provisioning device type for the first device comprises: obtaining, by the one or more processors, a request to provision the first device, the request specifying the provisioning device type.

3. The method of claim 1 , wherein storing device type features for the device type comprises:

providing a machine learning model the usage data and the common information; and

outputting, by the machine learning model, the device type features.

4. The method of claim 1 , wherein determining configuration information for provisioning the first device comprises: combining device configurations specified by the common information with device configurations specified by device type features associated with the provisioning device type.

5. The method of claim 1 , wherein provisioning the first device comprises:

generating, based on the configuration information for provisioning the first device, a schedule of a set of operations, wherein the schedule includes an allocation of computational resources associated with execution of the set of operations; and

sending the schedule to the first device.

6. The method of claim 1 , wherein the usage data includes at least one of user interactions with the plurality of devices and operations executed by each of the plurality of devices.

7. The method of claim 1 , further comprising:

obtaining first usage data from the first device;

updating, based on the first usage data, the common information to specify device configurations shared between each of the plurality of devices and the first device;

updating device type features associated with the provisioning device type based on the first usage data and updated common information;

determining new configuration information for provisioning the first device based on the updated device type features associated with the provisioning device type; and

provisioning the first device based on the new configuration information.

8. The method of claim 1 , further comprising:

determining a new device type for a second device not included in the plurality of devices;

obtaining second usage data from the second device;

updating, based on the second usage data, the common information to specify device configurations shared between each of the plurality of devices, the first device, and the second device; and

storing, based on the second usage data, device type features specifying device configurations for the new device type that is different than the updated common information.

9. A manager device comprising:

at least one processor; and

a storage device that stores instructions executable by the at least one processor to:

obtain usage data from a plurality of devices, wherein each device of the plurality of devices is associated with one or more device types of a plurality of device types, and wherein each device type of the plurality of device types specifies a usage behavior;

store common information based on the usage data, the common information specifying device configurations shared between each of the plurality of devices;

for each device type of the plurality of device types: storing device type features for a device type based on the usage data corresponding to one or more devices of the plurality of devices associated with the device type, the device type features specifying device configurations for the device type that is different than the common information;

determine a provisioning device type for a first device not included in the plurality of devices, the provisioning device type specifying at least one device type of the plurality of device types;

determine configuration information for provisioning the first device based on stored device type features associated with the provisioning device type and the common information; and

provision the first device based on the configuration information.

10. The manager device of claim 9 , wherein, to store device type features for the device type, the storage device stores instructions executable by the at least one processor to:

provide a machine learning model the usage data and the common information; and

output, by the machine learning model, the device type features.

11. The manager device of claim 9 , wherein, to determine configuration information for provisioning the first device, the storage device stores instructions executable by the at least one processor to: combine device configurations specified by the common information with device configurations specified by device type features associated with the provisioning device type.

12. The manager device of claim 9 , wherein, to provision the first device, the storage device stores instructions executable by the at least one processor to:

generate, based on the configuration information for provisioning the first device, a schedule of a set of operations, wherein the schedule includes an allocation of computational resources associated with execution of the set of operations; and

send the schedule to the first device.

13. The manager device of claim 9 , wherein the storage device further stores instructions executable by the at least one processor to:

obtain first usage data from the first device;

update, based on the first usage data, the common information to specify device configurations shared between each of the plurality of devices and the first device;

update device type features associated with the provisioning device type based on the first usage data and updated common information;

determine new configuration information for provisioning the first device based on the updated device type features associated with the provisioning device type; and

provision the first device based on the new configuration information.

14. The manager device of claim 9 , wherein the storage device further stores instructions executable by the at least one processor to:

determine a new device type for a second device not included in the plurality of devices;

obtain second usage data from the second device;

update, based on the second usage data, the common information to specify device configurations shared between each of the plurality of devices, the first device, and the second device; and

store, based on the second usage data, device type features specifying device configurations for the new device type that is different than the updated common information.

15. A non-transitory computer-readable storage medium encoded with instructions that, when executed, cause at least one processor of a computing system to:

obtain usage data from a plurality of devices, wherein each device of the plurality of devices is associated with one or more device types of a plurality of device types, and wherein each device type of the plurality of device types specifies a usage behavior;

store common information based on the usage data, the common information specifying device configurations shared between each of the plurality of devices;

for each device type of the plurality of device types: store device type features for a device type based on the usage data corresponding to one or more devices of the plurality of devices associated with the device type, the device type features specifying device configurations for the device type that is different than the common information;

determine a provision device type for a first device not included in the plurality of devices, the provision device type specifying at least one device type of the plurality of device types;

determine configuration information for provision the first device based on stored device type features associated with the provision device type and the common information; and

provision the first device based on the configuration information.

16. The non-transitory computer-readable storage medium of claim 15 , wherein, to store device type features for the device type, the instructions cause the at least one processor of the computing system to:

provide a machine learning model the usage data and the common information; and

output, by the machine learning model, the device type features.

17. The non-transitory computer-readable storage medium of claim 15 , wherein, to provision the first device, the instructions cause the at least one processor of the computing system to:

generate, based on the configuration information for provisioning the first device, a schedule of a set of operations, wherein the schedule includes an allocation of computational resources associated with execution of the set of operations; and

send the schedule to the first device.

18. The non-transitory computer-readable storage medium of claim 15 , wherein the usage data includes at least one of user interactions with the plurality of devices and operations executed by each of the plurality of devices.

19. The non-transitory computer-readable storage medium of claim 15 , wherein the instructions further cause the at least one processor of the computing system to:

obtain first usage data from the first device; update, based on the first usage data, the common information to specify device configurations shared between each of the plurality of devices and the first device;

update device type features associated with the provisioning device type based on the first usage data and updated common information;

determine new configuration information for provisioning the first device based on the updated device type features associated with the provisioning device type; and

provision the first device based on the new configuration information.

20. The non-transitory computer-readable storage medium of claim 15 , wherein the instructions further cause the at least one processor of the computing system to:

determine a new device type for a second device not included in the plurality of devices; obtain second usage data from the second device;

update, based on the second usage data, the common information to specify device configurations shared between each of the plurality of devices, the first device, and the second device; and

store, based on the second usage data, device type features specifying device configurations for the new device type that is different than the updated common information.

Assignments (1)

References Cited (8)