USER PROFILE SELECTION USING CONTEXTUAL AUTHENTICATION

• US 20160182502A1
• Filed: 12/23/2014
• Published: 06/23/2016
• Est. Priority Date: 12/23/2014
• Status: Active Grant

• Current Assignee: Hyundai Motor Company (Hyundai Motor Group), Kia Corp.
• Original Assignee: Intel Corporation
• Inventors: Scurfield, Hannah L., Smith, Ned M., Heldt-Sheller, Nathan, Sheller, Micah J., Goss, Nathaniel J., Wells, Kevin C., Pandian, Sindhu
• Granted Patent: US 9,628,477 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 21/31 User authentication
• CPC Class Codes: G06F 21/316 by observing the pattern of computer usage, e.g. typical user behaviour
• CPC Class Codes: G06F 2221/2105 Dual mode as a secondary aspect
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: H04L 63/0861 using biometrical features, e.g. fingerprint, retina-scan cryptographic mechanisms or cryptographic arrangements for entity authentication using biological data H04L9/3231
• CPC Class Codes: H04L 63/0884 by delegation of authentication, e.g. a proxy authenticates an entity to be authenticated on behalf of this entity vis-à-vis an authentication entity
• CPC Class Codes: H04L 67/306 User profiles

Abstract

In embodiments, apparatuses, methods and storage media (transitory and non-transitory) are described that are associated with user profile selection using contextual authentication. In various embodiments, a first user of a computing device may be authenticated and have an access control state corresponding to a first user profile established, the computing device may select a second user profile based at least in part a changed user characteristic, and the computing device may present a resource based at least in part on the second user profile. In various embodiments, the computing device may include a sensor and a user profile may be selected based at least in part on an output of the sensor and a previously stored template generated by a machine learning classifier.

Claims

1. A computing device comprising:

one or more processors;

a memory coupled with the one or more processors;

a login module operated by the one or more processors to authenticate a first user of the device and establish a first access control state corresponding to a first user profile associated with the first user;

a contextual authentication module operated by the one or more processors to select a second user profile based at least in part on a changed user characteristic; and

a presentation module operated by the one or more processors to present a resource based at least in part on the second user profile.

2. The computing device of claim 1, wherein the computing device further comprises a sensor, and wherein the contextual authentication module comprises:

a profile selection module operated by the one or more processors to select the second user profile based at least in part on an output of the sensor and a previously stored template generated by a machine learning classifier.

3. The computing device of claim 2, wherein the sensor is a motion sensor and wherein the profile selection module comprises a biometric machine learning classifier, wherein the profile selection module is to perform a biometric information classification of the output of the sensor and select the second user profile based at least in part on the biometric information classification and the previously stored template.

4. The computing device of claim 1, wherein the login module is to authenticate the first user of the device based at least in part on an active authentication factor.

5. The computing device of claim 1, wherein the computing device further comprises:

an access control module operated by the one or more processors to establish a second access control state based at least in part on the second user profile; and

a user proximity module operated by the one or more processors to determine a proximity status associated with the first user, wherein the access control module is operated by the one or more processors to terminate the second access control state if the proximity status reaches a predetermined value.

6. The computing device of claim 1, further comprising a trusted execution environment operated by one of the processors to host operation of the contextual authentication module.

7. The computing device of claim 1, wherein the contextual authentication module is operated by the one or more processor to select a delegate profile as the second user profile.

8. The computing device of claim 1, wherein the computing device is a tablet computing device, wherein the contextual authentication module comprises a profile selection module operated by the one or more processors in a trusted execution environment to select a second user profile based at least in part on a previously stored template generated by a machine learning classifier.

9. A computer implemented method comprising:

authenticating, by a computing device, a first user of the device;

establishing, by the computing device, a first access control state corresponding to a first user profile associated with the first user;

selecting, by the computing device, a second user profile based at least in part on a changed user characteristic; and

presenting, by the computing device, a resource based at least in part on the second user profile.

10. The method according to claim 9, wherein selecting, by the computing device, the second user profile comprises:

receiving, by the computing device, a sensor output;

performing a classification of the sensor output to generate sample data; and

selecting, by the computing device, the second user profile based at least in part on the sample data and a previously stored template generated by a machine learning classifier.

11. The method according to claim 10, wherein receiving comprises receiving a sensor output from a motion sensor, wherein performing comprises performing a biometric classification of the motion sensor output to generate biometric sample data, and wherein selecting comprises selecting the second user profile based at least in part on the biometric sample data and a previously stored biometric template generated by a biometric machine learning classifier.

12. The method according to claim 9, wherein authenticating, by the computing device, the first user of the device is based at least in part on an active authentication factor.

13. The method according to claim 9, further comprising:

establishing, by the computing device, a second access control state based at least in part on the second user profile;

determining, by the computing device, a proximity status associated with the first user; and

terminating, by the computing device, the second access control state if the proximity status reaches a predetermined value.

14. The method according to claim 9, wherein selecting, by the computing device, the second user profile based at least in part on the changed user characteristic is performed in a trusted execution environment.

15. The method according to claim 9, wherein the second user profile is a delegate profile.

16. The method according to claim 9, wherein the computing device is a tablet computing device, wherein selecting, by the computing device, the second user profile based at least in part on the changed user characteristic comprises selecting in a trusted execution environment, by the computing device, a second user profile based at least in part on a previously stored template generated by a machine learning classifier.

17. At least one non-transitory computer-readable medium comprising instructions stored thereon that, in response to execution of the instructions by a computing device, cause the computing device to:

authenticate a first user of the device;

establish a first access control state corresponding to a first user profile associated with the first user;

select a second user profile based at least in part on a changed user characteristic; and

present a resource based at least in part on the second user profile.

18. The at least one non-transitory computer-readable medium of claim 17, wherein to select the second user profile, the computing device is caused to:

perform a classification of a sensor output to generate sample data; and

select a second user profile based at least in part on the sample data and a previously stored template generated by a machine learning classifier.

19. The at least one non-transitory computer-readable medium of claim 18, wherein the computing device is caused to perform a biometric classification of a motion sensor output to generate biometric sample data and wherein the computing device is caused to select the second user profile based at least in part on the biometric sample data and a previously stored biometric template generated by a biometric machine learning classifier.

20. The at least one non-transitory computer-readable medium of claim 17, wherein the computing device is caused to authenticate the first user of the device based at least in part on an active authentication factor.

21. The at least one non-transitory computer-readable medium of claim 17, wherein the computing device is further caused to:

establish a second access control state based at least in part on the second user profile;

determine a proximity status associated with the first user; and

terminate the second access control state if the proximity status reaches a predetermined value.

22. The at least one non-transitory computer-readable medium of claim 17, wherein the computing device is further caused to select the second user profile in a trusted execution environment.

23. The at least one non-transitory computer-readable medium of claim 17, wherein the computing device is further caused to select a delegate profile as the second user profile.

24. The at least one non-transitory computer-readable medium of claim 17, wherein the computing device is a tablet computing device, wherein the tablet computing device is caused to select the second user profile in a trusted execution environment of the tablet computing device based at least in part on a previously stored template generated by a machine learning classifier.