Sender and recipient disambiguation

Patent metadata

Field	Value
Publication number	US-10848591-B2
Application number	US-201715616713-A
Country	US
Kind code	B2
Filing date	Jun 7, 2017
Priority date	Apr 25, 2017
Publication date	Nov 24, 2020
Grant date	Nov 24, 2020

Abstract

Systems and methods for sender profile and/or recipient profile disambiguation and/or confirmation are disclosed. In instances where a sender profile is not indicated by a user sending a communication from a communal device, heuristic data may be utilized to infer the sender profile. Similar heuristic data may also be used when selection of the sender profile is associated with a low confidence level. Heuristic data may also be used to infer the recipient profile when the user does not indicate the recipient profile or when selection of the recipient profile is associated with a low confidence. Various confirmations may result from the sender and recipient profile disambiguation.

First claim

What is claimed is:

1. A method comprising:
receiving audio data representing user speech;
determining intent data representing the audio data, the intent data indicating a request to send a communication;
determining a recipient profile to be associated with the communication;
determining that a sender profile identifier is absent from the audio data;
identifying, based at least in part on heuristic data and when the sender profile identifier is absent from the audio data, a sender profile of user profiles associated with a communal device, wherein the heuristic data indicates that a first contact list of the sender profile is associated with the recipient profile that is unassociated with a second contact list of the user profiles other than the sender profile; and
sending the communication in association with the sender profile and to the recipient profile.

2. The method of claim 1 , wherein the heuristic data further includes identifying a first user profile as the sender profile based at least in part on first data indicating that the first user profile and a second user profile are the only user profiles associated with the communal device and the second user profile corresponds to the recipient profile.

3. The method of claim 1 , wherein the user profiles include a first user profile and a second user profile, the heuristic data including:
first data indicating that contact information associated with the recipient profile is identified in a first contact list associated with the first user profile and a second contact list associated with the second user profile; and
second data indicating that communications with the recipient profile have only been associated with the first user profile.

4. The method of claim 1 , further comprising causing an audio output speaker of the communal device to output audio confirming that the communication is to be sent from the sender profile, the audio including at least one of prerecorded or synthesized speech that indicates a first name associated with the recipient profile, a second name associated with the sender profile, and the request.

5. The method of claim 1 , wherein the heuristic data includes data indicating that a previous communication was associated with a user profile within a threshold amount of time of receiving the audio data.

6. The method of claim 1 , wherein the communal device is associated with a set of communal devices, the heuristic data including usage data of the communal device by a user profile to send communications.

7. The method of claim 1 , wherein the heuristic data includes identification of at least one of a trigger expression, a speaker identification, or a received signal strength indicator.

8. The method of claim 1 , wherein the audio data comprises first audio data, the user speech comprises first user speech, and the method further comprises:
receiving, from the communal device, second audio data corresponding to second user speech, the second user speech representing the communication; and
determining, based at least in part on the second audio data, that the communication is associated with the recipient profile.

9. The method of claim 1 , further comprising:
causing output of audio indicating that the communication is to be sent in association with the sender profile;
determining that additional audio data is not received from the communal device within a threshold period of time of causing output of the audio; and
wherein sending the communication in association with the sender profile comprises sending the communication in association with the sender profile based at least in part on determining that the additional audio data is not received from the communal device with the threshold period of time.

10. A system comprising:
one or more processors; and
non-transitory computer-readable media storing instructions that, when executed by the one or more processors, cause the one or more processors to perform operations comprising:
receiving audio data representing user speech;
determining intent data representing the audio data, the intent data indicating a request to send a communication;
determining a recipient profile to be associated with the communication;
identifying, based at least in part on the recipient profile and heuristic data, a sender profile of user profiles associated with a communal device, wherein the sender profile is to be associated with the communication when a sender profile identifier is absent from the audio data, wherein the heuristic data indicates that a first contact list of the sender profile is associated with the recipient profile that is unassociated with a second contact list of the user profiles other than the sender profile; and
sending the communication in association with the sender profile and to the recipient profile.

11. The system of claim 10 , wherein the heuristic data includes identifying a first user profile as the sender profile based at least in part on data indicating that the first user profile and a second user profile represent the user profiles associated with the communal device and the second user profile corresponds to the recipient profile.

12. The system of claim 10 , wherein the user profiles include a first user profile and a second user profile, the heuristic data including:
first data indicating that contact information associated with the recipient profile is identified in a first contact list associated with the first user profile and a second contact list associated with the second user profile; and
second data indicating that communications with the recipient profile have only been associated with the first user profile.

13. The system of claim 10 , the operations further comprising causing an audio output speaker of the communal device to output audio confirming that the communication is to be sent from the sender profile, the audio including at least one of prerecorded or synthesized speech that indicates a first name associated with the recipient profile, a second name associated with the sender profile, and the request.

14. The system of claim 10 , wherein the heuristic data includes data indicating that a previous communication was associated with a user profile within a threshold amount of time of receiving the audio data.

15. The system of claim 10 , wherein the communal device is associated with a set of communal devices, the heuristic data including usage data of the communal device by a user profile to send communications.

16. The system of claim 10 , wherein the heuristic data includes identification of at least one of a trigger expression, a speaker identification, or a received signal strength indicator.

17. The system of claim 10 , wherein the audio data comprises first audio data, the user speech comprises first user speech, and the operations further comprise:
receiving, from the communal device, second audio data corresponding to second user speech, the second user speech representing the communication; and
determining, based at least in part on the second audio data, that the communication is associated with the recipient profile.

18. A system comprising:
one or more processors; and
non-transitory computer-readable media storing instructions that, when executed by the one or more processors, cause the one or more processors to perform operations comprising:
determining intent data based at least in part on audio data received from a communal device, the intent data indicating a request to send a communication;
determining a recipient profile to be associated

Assignees

• Amazon Tech Inc

Inventors

• Devaraj Christo Frank
• Stanton James Alexander
• Kshirsagar Sumedha Arvind
• Parker Christopher Geiger
• Barnet Aaron Takayanagi
• Kancharla Venkatesh
• Hart Gregory Michael

Classifications

• H04M1/72433

  for voice messaging, e.g. dictaphones (for answering incoming calls H04M1/64) · CPC title

• G10L15/26

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

• H04M3/53366

  Message disposing or creating aspects · CPC title

• H04M3/42238

  in systems with telephone lines with multiple users · CPC title

• G06Q10/10

  Office automation; Time management · CPC title