Granted Patent B2

US 11,449,921 · App. 16/906,062 · Granted Sep 20, 2022

Inventors: Tejas Naren Tennur Narayanan (Austin, TX); Gautam Kaura (Austin, TX); Stephen Ray Young (Austin, TX); Sathish Kumar Bikumala (Round Rock, TX); Harshit Mehta (Austin, TX); Harshita Dubey (Round Rock, TX); Avanthika Sankararaman (Cedar Park, TX)

Assignee: Dell Products L.P.

G06Q30/0631G06N5/04G06N20/00G06Q10/20G06Q30/012

Abstract

Claims (143)

1. A computer-implemented method comprising:

receiving telemetry data from a computing device, wherein the telemetry data comprises usage data and sensor data;

storing the telemetry data with previously received telemetry data;

determining, by a machine learning algorithm and based on the telemetry data and on the previously received telemetry data, a usage profile associated with the computing device;

determining service request data comprising service requests associated with the computing device;

predicting, using the machine learning algorithm and based on the usage profile and the service request data:

a failure of a component of the computing device; and

a time when the component is predicted to fail;

determining, based on the time that the component is predicted to fail, that the component is predicted to fail outside a warranty period of a current warranty;

determining, using the machine learning algorithm, an estimated cost to repair the computing device outside the warranty period of the current warranty;

determining, based on a purchase date of the computing device and the current warranty associated with the computing device, a warranty option comprising an extended warranty;

performing, using the machine learning algorithm, a cost-benefit analysis based on:

an out-of-pocket cost associated with repairing the computing device outside the warranty period of the current warranty; and

a cost of the extended warranty;

providing a recommendation to purchase the extended warranty, the recommendation including the cost-benefit analysis; and

re-training the machine learning algorithm using the telemetry data and the previously received telemetry data.

2. The computer-implemented method of claim 1 , further comprising:

predicting, using the machine learning algorithm and based on the usage profile and the service request data:

a second failure of a second particular component of the computing device; and

a second time when the second particular component is predicted to fail;

determining, based on the second time that the second particular component is predicted to fail, that the second particular component is predicted to fail within the warranty period of the current warranty;

determining, using the machine learning algorithm, a second estimated cost to repair the computing device within the warranty period of the current warranty;

determining, based on the purchase date of the computing device and the current warranty associated with the computing device, a second warranty option comprising an upgraded warranty;

performing, using the machine learning algorithm, a second cost-benefit analysis based on:

a second out-of-pocket cost associated with repairing the computing device within the warranty period of the current warranty; and

a cost to purchase the upgraded warranty; and

providing a second recommendation to purchase the upgraded warranty, the second recommendation including the second cost-benefit analysis.

3. The computer-implemented method of claim 1 , further comprising:

determining, using the machine learning algorithm and based on the usage profile, that upgrading a particular component of the computing device is predicted to increase a speed to execute a particular task on the computing device;

determining a cost to upgrade the particular component; and

providing a component upgrade recommendation to upgrade the particular component of the computing device including the speed at which the particular task is predicted to execute.

4. The computer-implemented method of claim 1 , further comprising:

determining, using the machine learning algorithm and based on the usage profile, that upgrading from the computing device to a different computing device is predicted to increase a speed to execute a particular task on the computing device;

determining a cost to upgrade to the different computing device; and

providing a device upgrade recommendation to upgrade from the computing device to the different computing device including the speed at which the particular task is predicted to execute.

5. The computer-implemented method of claim 1 , wherein the usage data identifies a minimum, an average, and a maximum of an amount of usage of:

a first amount of time of a central processing unit (CPU) of the computing device;

a second amount of a memory of the computing device; and

a third amount of a storage device of the computing device.

6. The computer-implemented method of claim 1 , wherein the sensor data is generated by sensors comprises one or more of:

an accelerometer;

a gyroscope;

a global positioning system (GPS) sensor;

a barometer; or

a thermometer.

7. The computer-implemented method of claim 1 , wherein the telemetry data is sent by the computing device at:

a predetermined time interval; and

in response to determining that a predetermined set of events have occurred within a predetermined time period.

8. A server comprising:

one or more processors; and

one or more non-transitory computer readable media storing instructions executable by the one or more processors to perform operations comprising:

receiving telemetry data from a computing device, wherein the telemetry data comprises usage data and sensor data;

storing the telemetry data with previously received telemetry data;

determining, by a machine learning algorithm and based on the telemetry data and based on the previously received telemetry data, a usage profile associated with the computing device;

determining service request data comprising service requests associated with the computing device;

predicting, using the machine learning algorithm and based on the usage profile and the service request data:

a failure of a component of the computing device; and

a time when the component is predicted to fail;

determining, based on the time that the component is predicted to fail, that the component is predicted to fail outside a warranty period of a current warranty;

determining, using the machine learning algorithm, an estimated cost to repair the computing device outside the warranty period of the current warranty;

determining, based on a purchase date of the computing device and the current warranty associated with the computing device, a warranty option comprising an extended warranty;

performing, using the machine learning algorithm, a cost-benefit analysis based on:

an out-of-pocket cost associated with repairing the computing device outside the warranty period of the current warranty; and

a cost to purchase the extended warranty;

providing a recommendation to purchase the extended warranty, the recommendation including the cost-benefit analysis; and

re-training the machine learning algorithm using the telemetry data and the previously received telemetry data.

9. The server of claim 8 , the operations further comprising:

predicting, using the machine learning algorithm and based on the usage profile and the service request data:

a second failure of a second particular component of the computing device; and

a second time when the second particular component is predicted to fail;

determining, based on the second time that the second particular component is predicted to fail, that the second particular component is predicted to fail within the warranty period of the current warranty;

determining, using the machine learning algorithm, a second estimated cost to repair the computing device within the warranty period of the current warranty;

determining, based on the purchase date of the computing device and the current warranty associated with the computing device, a second warranty option comprising an upgraded warranty;

performing, using the machine learning algorithm, a second cost-benefit analysis based on:

a second out-of-pocket cost associated with repairing the computing device within the warranty period of the current warranty; and

a cost of the upgraded warranty; and

providing a second recommendation to purchase the upgraded warranty, the second recommendation including the second cost-benefit analysis.

10. The server of claim 9 , the operations further comprising:

determining, using the machine learning algorithm and based on the usage profile, that upgrading a particular component of the computing device is predicted to increase a speed to execute a particular task on the computing device;

determining a cost to upgrade the particular component; and

providing a component upgrade recommendation to upgrade the particular component of the computing device including the speed at which the particular task is predicted to execute.

11. The server of claim 8 , the operations further comprising:

determining, using the machine learning algorithm and based on the usage profile, that upgrading from the computing device to a different computing device is predicted to increase a speed to execute a particular task on the computing device;

determining a cost to upgrade to the different computing device; and

providing a device upgrade recommendation to upgrade from the computing device to the different computing device including the speed at which the particular task is predicted to execute.

12. The server of claim 8 , wherein the usage data identifies a minimum, an average, and a maximum of an amount of usage of:

a first amount of time of a central processing unit (CPU) of the computing device;

a second amount of a memory of the computing device; and

a third amount of a storage device of the computing device.

13. The server of claim 8 , wherein the sensor data is generated by sensors comprises one or more of:

an accelerometer;

a gyroscope;

a global positioning system (GPS) sensor;

a barometer; or

a thermometer.

14. One or more non-transitory computer-readable media storing instructions executable by one or more processors to perform operations comprising:

receiving telemetry data from a computing device, wherein the telemetry data comprises usage data and sensor data;

storing the telemetry data with previously received telemetry data;

determining, by a machine learning algorithm and based on the telemetry data and based on the previously received telemetry data, a usage profile associated with the computing device;

determining service request data comprising service requests associated with the computing device;

predicting, using the machine learning algorithm and based on the usage profile and the service request data:

a failure of a component of the computing device; and

a time when the component is predicted to fail;

determining, based on the time that the component is predicted to fail, that the component is predicted to fail outside a warranty period of a current warranty;

determining, using the machine learning algorithm, an estimated cost to repair the computing device outside the warranty period of the current warranty;

determining, based on a purchase date of the computing device and the current warranty associated with the computing device, a warranty option comprising an extended warranty;

performing, using the machine learning algorithm, a cost-benefit analysis based on:

an out-of-pocket cost associated with repairing the computing device outside the warranty period of the current warranty; and

a cost of the extended warranty;

providing a recommendation to purchase the extended warranty, the recommendation including the cost-benefit analysis; and

re-training the machine learning algorithm using the telemetry data and the previously received telemetry data.

15. The one or more non-transitory computer readable media of claim 14 , the operations further comprising:

predicting, using the machine learning algorithm and based on the usage profile and the service request data:

a second failure of a second particular component of the computing device; and

a second time when the second particular component is predicted to fail;

determining, based on the second time that the second particular component is predicted to fail, that the second particular component is predicted to fail within the warranty period of the current warranty;

determining, using the machine learning algorithm, a second estimated cost to repair the computing device within the warranty period of the current warranty;

determining, based on the purchase date of the computing device and the current warranty associated with the computing device, a second warranty option comprising an upgraded warranty;

performing, using the machine learning algorithm, a second cost-benefit analysis based on:

a second out-of-pocket cost associated with repairing the computing device within the warranty period of the current warranty; and

a cost to purchase the upgraded warranty; and

providing a second recommendation comprising purchasing the upgraded warranty.

16. The one or more non-transitory computer readable media of claim 14 , the operations further comprising:

determining, using the machine learning algorithm and based on the usage profile, that upgrading a particular component of the computing device is predicted to increase a speed to execute a particular task on the computing device;

determining a cost to upgrade the particular component; and

providing a component upgrade recommendation to upgrade the particular component of the computing device including the speed at which the particular task is predicted to execute.

17. The one or more non-transitory computer readable media of claim 14 , the operations further comprising:

determining, using the machine learning algorithm and based on the usage profile, that upgrading from the computing device to a different computing device is predicted to increase a speed to execute a particular task on the computing device;

determining a cost to upgrade to the different computing device; and

providing a device upgrade recommendation to upgrade from the computing device to the different computing device including the speed at which the particular task is predicted to execute.

18. The one or more non-transitory computer readable media of claim 14 , wherein the usage data identifies a minimum, an average, and a maximum of an amount of usage of:

a first amount of time of a central processing unit (CPU) of the computing device;

a second amount of a memory of the computing device; and

a third amount of a storage device of the computing device.

19. The one or more non-transitory computer readable media of claim 14 , wherein the sensor data comprises one or more of:

an accelerometer;

a gyroscope;

a global positioning system (GPS) sensor;

a barometer; or

a thermometer.

20. The one or more non-transitory computer readable media of claim 14 , wherein the telemetry data is sent by the computing device at:

a predetermined time interval; and

in response to determining that a predetermined set of events have occurred within a predetermined time period.

Assignments (9)