Alternate response generation

Patent metadata

Field	Value
Publication number	US-11854573-B2
Application number	US-202017016873-A
Country	US
Kind code	B2
Filing date	Sep 10, 2020
Priority date	Dec 10, 2018
Publication date	Dec 26, 2023
Grant date	Dec 26, 2023

Abstract

Techniques for performing conversation recovery of a system/user exchange are described. In response to determining that an action responsive to a user input cannot be performed, a system may determine a topic to recommend to a user. The topic may be unrelated to the original substance of the user input. The system may have access to various data representing a context in which a user provides an input to the system. The system may use these inputs and various data at runtime to make a determination regarding whether a user should be recommended a topic, as well as what that topic should be. The system may cause a question be output to the user, with the question asking the user about the topic, for example whether the user would like a song played, whether the user would like to hear information about a particular individual (e.g., artist), whether the user would like to know about a particular skill (e.g., a skill having a significantly high popularity among users of the system), or whether the user would like to know about some other topic. If the user responds affirmatively to the recommended topic, the system may pass the user experience off to an appropriate component of the system (e.g., one that is configured to perform an action related to the topic). If the user responds negatively, does not respond at all, or the system is unsure whether the user's response was affirmative or negative, the system may cease interaction with the user, thereby enabling the user to interact with the system as the user desires.

First claim

What is claimed is:

1. A method, comprising:
receiving, from a first device, first data representing a first input;
determining the first data corresponds to a user identifier;
determining an error condition in response to the first input;
determining second data representing at least one previous user input corresponding to the user identifier, wherein the at least one previous user input relates to speech processing data associated with the user identifier and/or an action previously performed based on the speech processing data associated with the user identifier;
using the second data to determine, from a plurality of techniques for recovering from the error condition, a technique for recovering from the error condition;
using the technique to determine output data corresponding to a response to the first input; and
causing the output data to be sent to the first device.

2. The method of claim 1 , further comprising:
selecting a topic based at least in part on the at least one previous user input,
wherein the output data includes a representation of the topic.

3. The method of claim 2 , further comprising:
determining the topic corresponds to the at least one previous user input; and
determining the at least one previous user input occurred within a certain amount of time from the first input.

4. The method of claim 2 , further comprising:
determining the topic was not recommended within a certain amount of time from the first input.

5. The method of claim 2 , further comprising:
receiving, from the first device, third data representing a second input;
determining the third data represents information, corresponding to the topic, is to be output;
generating fourth data corresponding to the information; and
sending the fourth data to the first device.

6. The method of claim 5 , further comprising:
causing the first device to output content requesting whether an action, related to the topic, is to be performed;
receiving, from the first device, fifth data representing a third input;
determining the fifth data represents the action is to be performed;
determining a skill configured to perform the action; and
causing the skill to execute.

7. The method of claim 1 , wherein the first data comprises audio data and wherein determining the first data corresponds to a user identifier comprises:
processing the audio data with respect to stored data corresponding to a voice associated with the user identifier; and
based at least in part on the processing, determining the audio data includes a representation of the voice.

8. The method of claim 1 , further comprising:
determining an intent corresponding to the at least one previous user input, wherein:
the technique corresponds to the intent, and
determining the output data is based at least in part on the intent.

9. The method of claim 1 , further comprising:
determining location data corresponding to the user identifier,
wherein determining the output data is based at least in part on the location data.

10. The method of claim 1 , wherein:
the first input corresponds to a first dialog session; and
the at least one previous user input corresponds to a second dialog session different from the first dialog session.

11. A 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 representing a first input;
determine the first data corresponds to a user identifier;
determine an error condition in response to the first input;
determine second data representing at least one previous user input corresponding to the user identifier, wherein the at least one previous user input relates to speech processing data associated with the user identifier and/or an action previously performed based on the speech processing data associated with the user identifier;
determine based, at least in part on the error condition, to recommend a topic;
select the topic based at least in part on the at least one previous user input;
use the second data to determine a technique for recovering from the error condition;
use the technique to determine output data corresponding to a response to the first input; and
cause the output data to be sent to the first device,
wherein the output data includes a representation of the topic.

12. The system of claim 11 , 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 topic corresponds to the at least one previous user input; and
determine the at least one previous user input occurred within a certain amount of time from the first input.

13. The system of claim 11 , 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 topic was not recommended within a certain amount of time from the first input.

14. The system of claim 11 , 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 first device, third data representing a second input;
determine the third data represents information, corresponding to the topic, is to be output;
generate fourth data corresponding to the information; and
send the fourth data to the first device.

15. The 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:
cause the first device to output content requesting whether an action, related to the topic, is to be performed;
receive, from the first device, fifth data representing a third input;
determine the fifth data represents the action is to be performed;
determine a skill configured to perform the action; and
cause the skill to execute.

16. The system of claim 11 , wherein the first data comprises audio data and wherein the instructions that cause the system to determine the first data corresponds to a user identifier comprise instructions that, when executed by the at least one processor, cause the system to:
process the audio data with respect to stored data corresponding to a voice associated with the user identifier; and
based at least in part on the processing, determine the audio data includes a representation of the voice.

17. The system of claim 11 , wherein the at least one memory further comprises instructions that, when executed by the at least one processor, further cause the system to:
determine an intent corresponding to the at least one previous user input, wherein:
the technique corresponds to the intent, and
determining the output data is based at least in part on the intent.

18. The system of claim 11 , wherein the at least one memory further comprises instructions that, when executed by the at least one processor, further cause the system to:
determine location data corresponding to the user identifier,
wherein determining the output data is based at least in part on the location data.

19. The system of claim 11 , wherein:
the first input corresponds to a first dialog session; and
the at least one previous user input corresponds to a second dialog session different from the first dialog session.

20. The system of claim 11 , wherein selecting a topic comprises selecting a topic that is unrelat

Assignees

• Amazon Tech Inc

Inventors

• Newell Gregory
• Kahan Eliav
• Yasa Ravi Chandra Reddy
• Suarez David
• Toledano Joel

Classifications

• G10L25/51 Primary

  for comparison or discrimination · CPC title

• G10L15/1822

  Parsing for meaning understanding · CPC title

• G10L15/22

  Procedures used during a speech recognition process, e.g. man-machine dialogue · CPC title

• G10L15/26

  Speech to text systems (G10L15/08 takes precedence) · CPC title

• G10L2015/223

  Execution procedure of a spoken command · CPC title