Dialogue-driven user security levels

• US 9,147,054 B1
• Filed: 12/19/2012
• Issued: 09/29/2015
• Est. Priority Date: 12/19/2012
• Status: Active Grant

• Current Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Original Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Inventors: Owen, Robert David, Thimsen, John Daniel, Beal, Jeff Bradley, Kshirsagar, Sumedha Arvind
• Primary Examiner(s): Zand, Kambiz
• Assistant Examiner(s): Kaplan, Benjamin
• Application Number:
  US13/720,713
• Time in Patent Office: 1,014 Days
• Field of Search: 726/5
• US Class Current: 1/1
• CPC Class Codes: G06F 16/635 Filtering based on additional data, e.g. user or group profiles
• CPC Class Codes: G06F 21/31 User authentication
• CPC Class Codes: G06F 21/32 using biometric data, e.g. fingerprints, iris scans or voiceprints

Abstract

Natural language controlled devices may be implemented in an environment where the devices are configured to operate with multiple different users. The techniques described herein implement security requirements for a device configured to operate in an environment where the multiple different users may request functionality. The security requirements may be implemented based on the whether the functionality requested is personal and/or secured.

Claims

1. A computing system comprising:

one or more processors;

at least one microphone to receive a plurality of audio inputs from a user, the plurality of audio inputs comprising a first audio input, a second audio input, and a third audio input;

one or more computer-readable storage media storing computer-executable instructions;

a speech processing module maintained in the one or more computer-readable storage media and executed by the one or more processors to;

obtain first speech recognition results from a first signal representing the first audio input;

obtain second speech recognition results from a second signal representing the second audio input;

obtain third speech recognition results from a third signal representing the third audio input;

determine a first requested functionality associated with the first speech recognition results;

determine a second requested functionality associated with the second speech recognition results; and

determine a third requested functionality associated with the third speech recognition results;

a security requirements module maintained in the one or more computer-readable storage media and executed by the one or more processors to;

determine that there are no security requirements for the first requested functionality;

determine an identification security requirement for the second requested functionality;

determine an authentication security requirement for the third requested functionality;

determine that the identification security requirement is satisfied using identification information received from the user; and

determine that the authentication security requirement is satisfied using authentication information received from the user; and

an application module maintained in the one or more computer-readable storage media and executed by the one or more processors to execute the first requested functionality, the second requested functionality, and the third requested functionality.

2. The computing system as recited in claim 1, wherein the first requested functionality is one of playing music, playing a movie, setting a timer, requesting information about the weather, or requesting publicly available information from a web page.

3. The computing system as recited in claim 1, wherein the identification information received from the user comprises audio input comprising the user'"'"'s name and wherein the second requested functionality is one of playing music from a playlist of the user, setting a reminder for the user, requesting information from a calendar of the user, or requesting information about email sent to the user.

4. The computing system as recited in claim 1, wherein the authentication information received from the user comprises audio input comprising a password and wherein the third requested functionality is one of requesting information about a bank account, purchasing an item, or sending an email message.

5. The computing system as recited in claim 1, wherein the security requirements module is further executed by the one or more processors to access user security settings, the user security settings being stored in a user profile for the user.

6. The computing system as recited in claim 1, wherein the security requirements module is further executed by the one or more processors to access application security settings associated with an application.

7. A method comprising:

receiving, at a computing device, a signal comprising speech input of a user;

determining a requested functionality from the speech input using at least one of speech recognition and natural language understanding;

determining a security requirement associated with the requested functionality;

determining that the security requirement is satisfied; and

performing the requested functionality.

8. The method as recited in claim 7, wherein the security requirement is that any user may execute the requested functionality.

9. The method as recited in claim 7, wherein the security requirement comprises user identification and wherein determining that the security requirement is satisfied comprises receiving identification information from the user.

10. The method as recited in claim 9, wherein the identification information comprises at least one of the speech input, additional speech input received at the computing device, identity data, behavior data, usage patterns, or biometric data.

11. The method as recited in claim 9, further comprising:

requesting the identification information;

receiving the identification information; and

validating the identification information.

12. The method as recited in claim 7, wherein the security requirement requires user authentication and wherein determining that the security requirement is satisfied comprises receiving authentication information from the user.

13. The method as recited in claim 12, further comprising:

requesting the authentication information;

receiving the authentication information; and

validating the authentication information.

14. The method as recited in claim 12, wherein the authentication information is received electronically from a device associated with the user.

15. The method as recited in claim 7, wherein determining that the security requirement is satisfied comprises determining that the security requirement was previously satisfied within a pre-defined amount of time.

16. The method as recited in claim 7, further comprising accessing user security settings, the user security settings being stored in a user profile for the user.

17. The method as recited in claim 7, further comprising accessing application security settings associated with an application.

18. One or more non-transitory computer-readable media having computer-executable instructions that, when executed by one or more processors, cause the one or more processors to perform operations comprising:

receiving a signal comprising speech input of a user, the user being one of a plurality of users registered at a device;

determining a requested functionality from the speech input using at least one of speech recognition and natural language understanding;

determining that the requested functionality involves a security requirement;

determining that the user has satisfied the security requirement; and

executing the requested functionality after the user has satisfied the security requirement.

19. The one or more non-transitory computer-readable media as recited in claim 18, wherein the security requirement is that any of the plurality of users may execute the requested functionality.

20. The one or more non-transitory computer-readable media as recited in claim 18, wherein the security requirement comprises user identification and wherein determining that the user has satisfied the security requirement comprises audibly receiving a name of the user.

21. The one or more non-transitory computer-readable media as recited in claim 18, wherein the security requirement comprises user authentication and wherein determining that the user has satisfied the security requirement comprises receiving authentication credentials from the user and validating the authentication credentials.

22. One or more non-transitory computer-readable media having computer-executable instructions that, when executed by one or more processors, cause the one or more processors to perform operations comprising:

receiving a first signal comprising speech input from a user;

determining a requested functionality from the speech input using at least one of speech recognition and natural language understanding;

determining that the requested functionality requires user authentication as a security requirement before execution;

requesting that the user provide one or more authentication credentials;

receiving a second signal corresponding to the one or more authentication credentials;

determining that the one or more authentication credential satisfy the security requirement; and

executing the requested functionality.

23. The one or more non-transitory computer-readable media as recited in claim 22, wherein the one or more authentication credentials are requested audibly and the second signal is received audibly.

24. The one or more non-transitory computer-readable media as recited in claim 22, wherein the one or more authentication credentials are requested audibly by a first electronic device and the second signal is received from a second electronic device associated with the user.

25. A method comprising:

operating a voice-controlled device in a first mode that executes a first function independent of user identification and user authentication;

receiving a request to perform a second function;

determining that the second function requires user identification or user authentication;

switching operation of the voice-controlled device from a first mode to a second mode that involves user identification or user authentication as a security requirement;

accessing information that identifies or authenticates a user that provides the request;

creating a session for the user, wherein the second function is executed during the session;

terminating the session after a pre-determined period of time; and

switching operation of the voice-controlled device from the second mode to the first mode after the session is terminated.

26. The method of claim 25, wherein the first mode is an unrecognized mode in which the voice-controlled device executes non-personal and unsecured functionality common to a plurality of different users.

27. The method of claim 25, wherein the second mode is a recognized mode that requires user identification and the second function is personal to the user.

28. The method of claim 25, wherein the second mode is an authenticated mode that requires user authentication and the second function includes secured operations or secured information.