Granted Patent B1

US 10,706,846 · App. 15/911,987 · Granted Jul 7, 2020

Inventors: William Folwell Barton (Concord, MA); Raluca Teodora Stoain (Cambridge, MA); James Alfed Cuff (Medway, MA); Matthew Aaron Cember (Somerville, MA)

Assignee: Amazon Technologies, Inc.

G10L15/22G10L13/043G10L15/063G10L15/1815G10L2015/223

Abstract

Claims (97)

1. A method, comprising:

receiving, from a first device, first audio data representing first speech corresponding to a first user question;

generating first text data representing the first user question;

processing the first text data to determine a first answer to the first user question is unknown;

after determining the first answer is unknown, storing the first user question text data in storage;

after storing the first user question in the storage, receiving, from a second device, second audio data representing second speech requesting a question without an answer be output;

determining a user identifier associated with the second audio data;

after receiving the second audio data, determining previously received user inputs associated with the user identifier;

determining at least a portion of the previously received user inputs corresponds to a topic;

determining the first user question corresponds to the topic; and

causing the second device to output the first user question.

2. The method of claim 1 , further comprising:

causing the second device to request whether an additional answerable question is to be output;

receiving, from the second device, third audio data indicating a further answerable question is to be output;

determining, in the storage, a second user question corresponding to the topic; and

causing the second device to output the second user question.

3. The method of claim 1 , further comprising:

receiving, from the second device, third audio data representing a second answer to the first user question; and

associating, in the storage, the first user question with the second answer.

4. The method of claim 3 , further comprising:

determining the user identifier is associated with a first ranking representing a trustworthiness of received data associated with the user identifier;

associating, in the storage, the second answer with the first ranking;

determining the second answer is associated with a plurality of positive feedbacks;

determining the plurality of positive feedbacks satisfy a threshold amount of positive feedbacks; and

associating, in the storage, the second answer with a second ranking, the second ranking being greater than the first ranking.

5. A method, comprising:

receiving, from a first device, first data corresponding to a first user question;

determining a first answer to the first user question is unknown;

after determining the first answer is unknown, storing the first user question in storage;

after storing the first user question in the storage, receiving, from a second device, second data requesting a question without an answer be output;

determining a user identifier associated with the second data;

after receiving the second data, determining previously received user inputs associated with the user identifier;

determining at least a portion of the previously received user inputs corresponds to a topic;

determining the first user question corresponds to the topic; and

causing the second device to output the first user question.

6. The method of claim 5 , further comprising:

receiving, from the second device, third data representing a second answer to the first user question; and

associating, in the storage, the first user question with the second answer.

7. The method of claim 5 , wherein the storage comprises text data representing the first user question and wherein the method further comprises:

performing text-to-speech (TTS) processing on the text data to generate audio data; and

causing the second device to output the audio data.

8. The method of claim 5 , further comprising:

determining, in the storage, a second user question corresponding to the topic; and

causing the second device to present the first user question and the second user question in a list of answerable questions.

9. The method of claim 5 , further comprising:

causing the second device to request whether an additional answerable question is to be output;

receiving, from the second device, third data indicating a further answerable question is to be output;

determining, in the storage, a second user question corresponding to the topic; and

causing the second device to output the second user question.

10. The method of claim 6 , further comprising:

determining the user identifier is associated with a first ranking representing a trustworthiness of received data associated with the user identifier; and

associating, in the storage, the second answer with the first ranking.

11. The method of claim 10 , further comprising:

determining the second answer is associated with a plurality of positive feedbacks;

determining the plurality of positive feedbacks satisfy a threshold amount of positive feedbacks; and

associating, in the storage, the second answer with a second ranking representing a trustworthiness of the second answer, the second ranking being greater than the first ranking.

12. The method of claim 10 , further comprising:

determining the second answer is associated with a plurality of negative feedbacks;

determining the plurality of negative feedbacks satisfy a threshold amount of negative feedbacks; and

associating, in the storage, the second answer with a second ranking representing a trustworthiness of the second answer, the second ranking being less than the first ranking.

13. A computing system, comprising:

at least one processor; and

at least one memory comprising instructions that, when executed by the at least one processor, cause the system to:

receive, from a first device, first data corresponding to a first user question;

determine a first answer to the first user question is unknown;

after determining the first answer is unknown, store the first user question in storage;

after storing the first user question in the storage, receive, from a second device, second data requesting a question without an answer be output;

determine a user identifier associated with the second data;

after receiving the second data, determine previously received user inputs associated with the user identifier;

determine at least a portion of the previously received user inputs corresponds to a topic;

determine the first user question corresponds to the topic; and

cause the second device to output the first user question.

14. The computing system of claim 13 , wherein the at least one memory further comprises instructions that, when executed by the at least one processor, further cause the system to:

receive, from the second device, third data representing a second answer to the first user question; and

associate, in the storage, the first user question with the second answer.

15. The computing system of claim 13 , wherein the storage comprises text data representing the first user question and wherein the at least one memory further comprises instructions that, when executed by the at least one processor, further cause the system to:

perform text-to-speech (TTS) processing on the text data to generate audio data; and

cause the second device to output the audio data.

16. The computing system of claim 13 , wherein the at least one memory further comprises instructions that, when executed by the at least one processor, further cause the system to:

determine, in the storage, a second user question corresponding to the topic; and

cause the second device to present the first user question and the second user question in a list of answerable questions.

17. The computing system of claim 13 , wherein the at least one memory further comprises instructions that, when executed by the at least one processor, further cause the system to:

cause the second device to request whether an additional answerable question is to be output;

receive, from the second device, third data indicating a further answerable question is to be output;

determine, in the storage, a second user question corresponding to the topic; and

cause the second device to output the second user question.

18. The computing system of claim 14 , wherein the at least one memory further comprises instructions that, when executed by the at least one processor, further cause the system to:

determine the user identifier is associated with a first ranking representing a trustworthiness of received data associated with the user identifier; and

associate, in the storage, the second answer with the first ranking.

19. The computing system of claim 18 , wherein the at least one memory further comprises instructions that, when executed by the at least one processor, further cause the system to:

determine the second answer is associated with a plurality of positive feedbacks;

determine the plurality of positive feedbacks satisfy a threshold amount of positive feedbacks; and

associate, in the storage, the second answer with a second ranking representing a trustworthiness of the second answer, the second ranking being greater than the first ranking.

20. The computing system of claim 18 , wherein the at least one memory further comprises instructions that, when executed by the at least one processor, further cause the system to:

determine the second answer is associated with a plurality of negative feedbacks;

determine the plurality of negative feedbacks satisfy a threshold amount of negative feedbacks; and

associate, in the storage, the second answer with a second ranking representing a trustworthiness of the second answer, the second ranking being less than the first ranking.

Assignments (1)

Continuity (1)

Cited By (9)

US 12,192,130 US 12,223,951 US 12,307,505 US 12,327,230 US 12,381,673 US 12,400,279 US 12,518,112 US 12,579,528 US 12,700,961