Sender and recipient disambiguation

Patent metadata

Field	Value
Publication number	US-11968271-B2
Application number	US-202218089974-A
Country	US
Kind code	B2
Filing date	Dec 28, 2022
Priority date	Apr 25, 2017
Publication date	Apr 23, 2024
Grant date	Apr 23, 2024

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 system comprising:
one or more processors; and
non-transitory computer-readable media storing instructions that, when executed by the one or more processors, causes 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, utilizing the audio data and based at least in part on heuristic data associated with the audio data, a first sender profile of user profiles associated with a communal device, wherein the first sender profile is to be associated with the communication when a sender profile identifier is absent from the audio data; and
sending the communication in association with the first sender profile and to the recipient profile.

2. The system of claim 1 , the operations further comprising:
determining account data associated with the communal device;
identifying, utilizing the account data, heuristic datasets associated with the communal device; and
identifying the heuristic data from the heuristic datasets.

3. The system of claim 1 , the operations further comprising:
storing first data representing a first voice signature as spoken by a first user associated with the communal device, the first user associated with the first sender profile; and
determining that a second voice signature of the audio data corresponds to the first voice signature, wherein the heuristic data indicates that the first sender profile is to be identified based at least in part on the second voice signature corresponding to the first voice signature.

4. The system of claim 1 , the operations further comprising:
storing first data representing a first voice signature as spoken by a first user associated with the communal device, the first user associated with the first sender profile;
storing second data representing a second voice signature as spoken by a second user associated with the communal device, the second user associated with a second sender profile; and
determining that a third voice signature of the audio data corresponds to the first voice signature instead of the second voice signature, wherein the heuristic data indicates that the first sender profile is to be identified based at least in part on the third voice signature corresponding to the first voice signature instead of the second voice signature.

5. The system of claim 1 , the operations further comprising:
associating the heuristic data with the first sender profile;
associating additional heuristic data with a second sender profile, the additional heuristic data differing from the heuristic data; and
determining that the user speech is associated with the heuristic data instead of the additional heuristic data.

6. The system of claim 1 , the operations further comprising:
identifying, utilizing the audio data, a user identifier of a person that provided the user speech; and
determining that the user identifier is associated with the first sender profile, wherein the heuristic data indicates that the first sending profile is to be identified based at least in part on the user identifier being associated with the first sender profile.

7. The system of claim 1 , the operations further comprising determining, utilizing scheduling data associated with the communal device, that, at a time when the audio data is received, the first sender profile is unassociated with a scheduled event having a location that differs from where the communal device is situated, wherein the heuristic data indicates that the first sender profile is to be identified based at least in part on determining that the first sender profile is unassociated with the scheduled event.

8. The system of claim 1 , the operations further comprising:
receiving an indication that the communal device, at a time when the audio data is received, is in communication with a device; and
determining that a device identifier of the device is associated with the first sender profile wherein the heuristic data indicates that the first sender profile is to be identified based at least in part on determining that the device identifier is associated with the first sender profile.

9. The system of claim 1 , the operations further comprising determining that a first characteristic of the audio data corresponds to a second characteristic of prior audio data associated with a prior communication, the prior communication being sent in association with the sender profile, wherein the heuristic data indicates that the first sender profile is to be identified based at least in part on the first characteristic corresponding to the second characteristic.

10. The system of claim 1 , the operations further comprising:
determining a confidence value associated with sending the communication in association with a selected sender profile; and
determining that the confidence value does not satisfy a threshold confidence value, wherein the heuristic data indicates that the first sender profile is to be identified based at least in part on the confidence value not satisfying the threshold confidence value.

11. 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;
identifying, utilizing the audio data and based at least in part on heuristic data associated with the audio data, a first sender profile of user profiles associated with a communal device, wherein the first sender profile is to be associated with the communication when a sender profile identifier is absent from the audio data; and
sending the communication in association with the first sender profile and to the recipient profile.

12. The method of claim 11 , further comprising:
determining account data associated with the communal device;
identifying, utilizing the account data, heuristic datasets associated with the communal device; and
identifying the heuristic data from the heuristic datasets.

13. The method of claim 11 , further comprising:
storing first data representing a first voice signature as spoken by a first user associated with the communal device, the first user associated with the first sender profile; and
determining that a second voice signature of the audio data corresponds to the first voice signature, wherein the heuristic data indicates that the first sender profile is to be identified based at least in part on the second voice signature corresponding to the first voice signature.

14. The method of claim 11 , further comprising:
storing first data representing a first voice signature as spoken by a first user associated with the communal device, the first user associated with the first sender profile;
storing second data representing a second voice signature as spoken by a second user associated with the communal device, the second user associated with a second sender profile; and
determining that a third voice signature of the audio data corresponds to the first voice signature instead of the second voice signature, wherein the heuristic data indicates that the first sender profile is to be identified based at least in part on the third voice signature corresponding to the first voice signature instead of the second voice signature.

15. The method of claim 11 , further comprising:
associating the heuristic data with the first sender

Assignees

• Amazon Tech Inc

Inventors

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

Classifications

• H04L67/306 Primary

  User profiles · CPC title

• G06Q10/10

  Office automation; Time management · CPC title

• H04M1/72433

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

• H04M3/42238

  in systems with telephone lines with multiple users · CPC title

• H04M3/53366

  Message disposing or creating aspects · CPC title