Dynamic user authentication

• US 10,027,662 B1
• Filed: 12/06/2016
• Issued: 07/17/2018
• Est. Priority Date: 12/06/2016
• Status: Active Grant

• Current Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Original Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Inventors: Mutagi, Rohan, Gohil, Chintan, Kopuri, Sai Sailesh, Lee, Philip Alexander, Wu, Felix, Liang, Nancy Yi
• Primary Examiner(s): PYZOCHA, MICHAEL J
• Application Number:
  US15/370,103
• Time in Patent Office: 588 Days
• CPC Class Codes: G06F 21/32 using biometric data, e.g. fingerprints, iris scans or voiceprints
• CPC Class Codes: G10L 13/02 Methods for producing synthetic speech; Speech synthesisers
• CPC Class Codes: G10L 13/033 Voice editing, e.g. manipulating the voice of the synthesiser
• CPC Class Codes: G10L 13/06 Elementary speech units used in speech synthesisers; Concatenation rules
• CPC Class Codes: G10L 13/08 Text analysis or generation of parameters for speech synthesis out of text, e.g. grapheme to phoneme translation, prosody generation or stress or intonation determination
• CPC Class Codes: G10L 15/02 Feature extraction for speech recognition; Selection of recognition unit
• CPC Class Codes: G10L 15/16 using artificial neural networks
• CPC Class Codes: G10L 15/1815 Semantic context, e.g. disambiguation of the recognition hypotheses based on word meaning
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 17/06 Decision making techniques; Pattern matching strategies
• CPC Class Codes: G10L 17/22 Interactive procedures; Man-machine interfaces
• CPC Class Codes: G10L 2015/088 Word spotting
• CPC Class Codes: G10L 2015/223 Execution procedure of a spoken command
• CPC Class Codes: G10L 2015/227 of the speaker; Human-factor methodology
• CPC Class Codes: G10L 25/78 Detection of presence or absence of voice signals switching of direction of transmission by voice frequency in two-way loud-speaking telephone systems H04M9/10
• CPC Class Codes: G10L 25/84 for discriminating voice from noise
• CPC Class Codes: H04L 2463/082 applying multi-factor authentication cryptographic mechanisms or cryptographic arrangements including means for verifying the identity or authority of a user of the system or for message authentication H04L9/32
• 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

Abstract

Systems, methods, and devices for dynamically authenticating a user are disclosed. A speech-controlled device captures a spoken command, and sends audio data corresponding thereto to a server. The server determines the audio data includes a spoken command to receive content, and therefrom determines a source storing the content. The server also determines threshold user authentication confidence score data associated with the content source. Based at least in part on the threshold user authentication confidence score data, the server determines a user authentication technique, and a device configured to capture user authentication data. The server determines user authentication confidence score data using user authentication data received from the device, and determines weighted user authentication confidence score data therefrom. If the weighted user authentication confidence score data satisfies the threshold user authentication confidence score data, the server receives the requested content from the content source.

Claims

1. A computer-implemented method, comprising:

receiving, from a first device, first input audio data corresponding to a first spoken utterance;

performing speech recognition processing on the first input audio data to generate first input text data;

performing natural language processing on the first input text data to determine a first request to receive first content;

determining a first content source associated with the first content;

sending, to the first content source, first data requesting the first content;

receiving, from the first content source, a first threshold representing a first user authentication confidence threshold associated with the first content;

determining, based at least in part on the first threshold, at least one user authentication technique;

determining user profile data associated with the first input audio data, the user profile data representing a first plurality of devices;

determining, in the user profile data, first location data associated with the first device;

sending, to the first device based at least in part on the first location data and the at least one user authentication technique, second data requesting first user authentication data;

receiving, from the first device, second input audio data corresponding to a second spoken utterance;

determining, using the second input audio data, a first value representing a first user authentication confidence;

determining a first reliability weight associated with the first device;

determining, using the first value and the first reliability weight, a first weighted value representing a first weighted user authentication confidence; and

sending, to the first content source, first weighted value.

2. The computer-implemented method of claim 1, wherein the plurality of devices further includes a second device, and wherein the computer-implemented method further comprises:

receiving, from the second device, third data representing one of fingerprint data or password data;

determining, using the third data, a second value representing a second user authentication confidence;

determining a second reliability weight associated with the second device;

determining, using the second value and the second reliability weight, a second weighted value representing a second weighted user authentication confidence;

determining, using the first weighted value and the second weighted value, a normalized value representing a normalized user authentication confidence;

sending, to the first content source, the normalized value; and

receiving the first content from the first content source.

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

receiving, from the first device, third input audio data corresponding to a third spoken utterance;

performing speech recognition processing on the third input audio data to generate second input text data;

performing natural language processing on the second input text data to determine a second request to receive the second content;

determining the first content source is associated with the second content;

sending, to the first content source, third data requesting the second content;

receiving, from the first content source, a second threshold representing a second user authentication confidence threshold associated with the second content, the second threshold being greater than the first threshold;

determining a second device to receive second user authentication data from;

sending, to the second device, fourth data requesting the second user authentication data;

receiving, from the second device, fifth data including one of fingerprint data or password data;

determining, using the fifth data, a second value representing a second user authentication confidence;

determining a second reliability weight associated with the second device;

determining, using the second value and the second reliability weight, a second weighted value representing a second weighted user authentication confidence;

determining, using the first weighted value and the second weighted value, a normalized value representing a normalized user authentication confidence;

sending, to the first content source, the normalized value; and

receiving the second content from the first content source.

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

receiving, from the first device, third input audio data corresponding to a third spoken utterance;

performing speech recognition processing on the third input audio data to generate second input text data;

performing natural language processing on the second input text data to determine a second request to receive second content;

determining a second content source associated with the second content; and

determining, in a library indicating a second plurality of content sources, a second threshold associated with the second content source, the second threshold representing a second user authentication confidence threshold.

5. A system, comprising:

at least one processor; and

at least one memory including instructions that, when executed by the at least one processor, cause the system to;

receive first user input requesting first content be output;

determine a first threshold representing a first user authentication confidence threshold;

based at least in part on the first threshold, determine at least a first user authentication technique;

determine user profile data associated with the first user input, the user profile data representing a plurality of devices;

determine, in the user profile data, first location data associated with a first device;

receive, from the first device based at least in part on the first location data and the at least one first user authentication technique, first user authentication data;

determine, based at least in part on the first user authentication data, a first value representing a first user authentication confidence;

determine the first value satisfies the first threshold; and

after determining the first value satisfies the first threshold, cause the first content to be output.

6. The system of claim 5, wherein the at least one memory further includes instructions that, when executed by the at least one processor, further cause the system to:

send, to a content source associated with the first content, first data requesting the first content; and

receive, from the content source, the first threshold.

7. The system of claim 5, wherein the at least one memory further includes instructions that, when executed by the at least one processor, further cause the system to:

receive second user input requesting second content be output;

access a storage indicating content sources associated with respective user authentication confidence thresholds;

determine a content source associated with the second content; and

determine, in the storage, the content source is associated with a second threshold representing a second user authentication confidence threshold.

8. The system of claim 5, wherein the at least one memory further includes instructions that, when executed by the at least one processor, further cause the system to:

determine a first reliability weight associated with one of the first device or the at least a first user authentication technique;

determine, based at least in part on the first value and the first reliability weight, a weighted value representing a weighted user authentication confidence;

determine the weighted value satisfies the first threshold; and

receive the first content after determining the weighted value satisfies the first threshold.

9. The system of claim 5, wherein the at least one memory further includes instructions that, when executed by the at least one processor, further cause the system to:

determine the first value is less than the first threshold;

receive, from the first device, second user authentication data;

determine, based at least in part on the second user authentication data, a second value representing a second user authentication confidence;

determine, based at least in part on the first value and the second value, a normalized value representing a normalized user authentication confidence;

determine the normalized value satisfies the first threshold; and

receive the first content after determining the normalized value satisfies the first threshold.

10. The system of claim 5, wherein the first user authentication data represents at least one of:

a specified-portion of an alphanumeric passcode;

a specified portion of a pass phrase;

speech recognition results;

facial recognition results;

or

biometric verification results.

11. The system of claim 5, wherein the at least one memory further includes instructions that, when executed by the at least one processor, further cause the system to:

determine a second device configured to provide the first user authentication data.

12. The system of claim 5, wherein the at least one memory further includes instructions that, when executed by the at least one processor, further cause the system to:

receive a second user input requesting second content be output;

determine a second threshold representing a second user authentication confidence threshold, the second threshold being greater than the first threshold;

receive, from a second device, second user authentication data;

determine, based at least in part on the second user authentication data, a second value representing a second user authentication confidence;

determine, based at least in part on the first value and the second value, a normalized value representing a normalized user authentication confidence;

determine the normalized value satisfies the second threshold; and

receive the second content after determining the normalized value satisfies the second threshold.

13. A computer-implemented method, comprising:

receive first user input requesting first content be output;

determining a first threshold representing a first user authentication confidence threshold;

based at least in part on the first threshold, determine at least a first user authentication technique;

determining user profile data associated with the first user input, the user profile data representing a plurality of devices;

determining, in the user profile data, first location data associated with a first device;

receiving, from the first device based at least in part on the first location data and the first user authentication technique, first user authentication data;

determining, based at least in part on the first user authentication data, a first value representing a first user authentication confidence;

determining the first value satisfies the first threshold; and

after determining the first value satisfies the first threshold, causing the first content to be output.

14. The computer-implemented method of claim 13, wherein determining the first threshold confidence comprises:

sending, to a content source associated with the first content, first data requesting the first content; and

receiving, from the content source, the first threshold.

15. The computer-implemented method of claim 13, further comprising:

receiving second user input requesting second content be output;

accessing a storage indicating content sources associated with respective user authentication confidence thresholds;

determining a content source associated with the second content; and

determining, in the storage, the content source is associated with a second threshold representing a second user authentication confidence threshold.

16. The computer-implemented method of claim 13, further comprising:

determining a first reliability weight associated with one of the first device or the at least a first user authentication technique;

determining, based at least in part on the first value and the first reliability weight, a weighted value representing a weighted user authentication confidence;

determining the weighted value satisfies the first threshold; and

receiving the first content after determining the weighted value satisfies the first threshold.

17. The computer-implemented method of claim 13, further comprising:

determining the first value is less than the first threshold;

receiving, from the first device, second user authentication data;

determining, based at least in part on the second user authentication data, a second value representing a second user authentication confidence;

determining, based at least in part on the first value and the second value, a normalized value representing a normalized user authentication confidence;

determining the normalized value satisfies the first threshold; and

receiving the first content after determining the normalized value satisfies the first threshold.

18. The computer-implemented method of claim 13, wherein receiving the first user authentication data comprises receiving at least one of:

a specified portion of an alphanumeric passcode;

a specified portion of a pass phrase;

speech recognition results;

facial recognition results;

or

biometric verification results.

19. The computer-implemented method of claim 13, further comprising:

determining a second device configured to provide the first user authentication data.

20. The computer-implemented method of claim 13, further comprising:

receiving a second user input requesting second content be output;

determining a second threshold representing a second user authentication confidence threshold, the second threshold being greater than the first threshold;

receiving, from a second device, second user authentication data;

determining, based at least in part on the second user authentication data, a second value representing a second user authentication confidence;

determining, based at least in part on the first value and the second value, a normalized value representing a normalized user authentication confidence;

determining the normalized value satisfies the second threshold; and

receiving the second content after determining the normalized value satisfies the second threshold.