Customized speech generation

Patent metadata

Field	Value
Publication number	US-9363104-B2
Application number	US-201414257922-A
Country	US
Kind code	B2
Filing date	Apr 21, 2014
Priority date	Jun 21, 2012
Publication date	Jun 7, 2016
Grant date	Jun 7, 2016

Abstract

Various approaches enable automatic communication generation based on patterned behavior in a particular context. For example, a computing device can monitor behavior of a user to determine patterns of communication behavior in certain situations. In response to detecting multiple occurrences of the certain situation, a computing device can prompt a user to perform an action corresponding to the pattern of behavior. In some embodiments, a set of speech models corresponding to a type of contact is generated. The speech models include language consistent with patterns of speech between a user and the type of contact. Based on context and on the contact, a message using language consistent with past communications between the user and contact is generated from a speech model associated with the type of contact.

First claim

What is claimed is:

1. A system, comprising:
at least one device processor; and
memory including instructions that, when executed by the at least one device processor, cause the system to:
receive a first communication between a first user and a second user;
analyze text contained in the first communication to identify at least one communication pattern;
generate a communication model, to be associated with at least one of the first user and the second user, based at least in part on the at least one communication pattern;
receive a second communication from the second user, the second communication requesting a response from the first user;
obtain activity information associated with the first user; and
in response to the first user not responding to the second communication within a predetermined period of time, generate a message to be sent to the second user, the message including textual content based at least in part on the activity information and corresponding to the communication model.

2. The system of claim 1 , further comprising:
enable the first user to approve the message, and
send the message to the second user.

3. The system of claim 1 , wherein the first communication comprises at least one of an email message, a message in a social network feed, a text message, an instant message, a chat session, or voice data.

4. The system of claim 1 , wherein the activity information is associated with at least one of a calendar, a time of day, a location of the first user, or historical behavior data of the first user.

5. A computer-implemented method, comprising
under control of one or more computer systems configured with executable instructions,
receiving one or more communications between a first user and one or more other users;
analyzing text contained in the one or more communications to identify at least one communication pattern;
generating a communication model, the communication model based at least in part on the at least one communication pattern;
receiving an incoming communication from a second user, the incoming communication requesting a response from the first user;
obtaining activity information associated with the first user; and
generating a message to be sent to the second user, the message including textual content based at least in part on the activity information and corresponding to the communication model.

6. The method of claim 5 , wherein generating the message to be sent to the second user is based at least in part on a type of relationship between the first user and the second user.

7. The method of claim 5 , further comprising:
calculating a level of confidence for the first user to respond to the second user, the level of confidence based at least in part on historical behavior data of the first user.

8. The method of claim 7 , wherein the level of confidence is further based at least in part on analyzing text contained in the incoming communication.

9. The method of claim 7 , wherein the level of confidence is further based at least in part on a type of relationship between the first user and the second user.

10. The method of claim 5 , wherein the incoming communication comprises one of a phone call, a video call, a text message, an email, a social network feed or voice data.

11. The method of claim 5 , wherein the message further includes textual content based at least in part on the incoming communication.

12. The method of claim 5 , wherein the message includes a cancellation to respond to the incoming communication.

13. The method of claim 5 , further comprising:
generating a second message; and
enabling the first user to select at least one of the message or the second message.

14. The method of claim 5 , further comprising:
determining a type of relationship between the first user and the second user using at least one of text contained previous communications between the first user and the second user or a label associated with the second user.

15. The method of claim 5 , wherein the one or more communications includes at least one of email messages, social network feeds, text messages, instant messages, chat sessions, or voice data.

16. The method of claim 5 , wherein the activity information is associated with at least one of a calendar, a time of day, a location of the first user, or historical behavior data of the first user.

17. A non-transitory computer readable storage medium storing one or more sequences of instructions executable by one or more processors to perform a set of operations comprising:
receiving one or more communications between a first user and one or more other users;
analyzing text contained in the one or more communications to identify at least one communication pattern;
generating a communication model, the communication model based at least in part on the at least one communication pattern;
receiving an incoming communication from a second user, the incoming communication requesting a response from the first user;
obtaining activity information associated with the first user;
generating one or more messages to be sent to the second user, at least one of the one or more messages including textual content based at least in part on the activity information and corresponding to the communication model; and
enabling the first user to select a message from the one or more messages.

18. The non-transitory computer readable storage medium of claim 17 , further comprising instructions executed by the one or more processors to perform the operations of:
calculating a level of confidence for the first user to respond to the second user, the level of confidence based at least in part on at least one of historical behavior data of the first user or text contained in the incoming communication.

19. The non-transitory computer readable storage medium of claim 17 , further comprising instructions executed by the one or more processors to perform the operations of:
determining a type of relationship between the first user and the second user using at least one of text contained in previous communications between the first user and the second user or a label associated with the second user.

20. The non-transitory computer readable storage medium of claim 17 , wherein the textual content is further based at least in part on text contained in the incoming communication.

Assignees

• Amazon Tech Inc

Inventors

• Noble Isaac Scott
• Halberg Gabrielle M
• Karakotsios Kenneth Mark
• Watanabe Yuzo

Classifications

• H04M2250/10

  including a GPS signal receiver · CPC title

• H04L51/02

  using automatic reactions or user delegation, e.g. automatic replies or chatbot-generated messages · CPC title

• G10L15/18

  using natural language modelling · CPC title

• H04M1/64

  Automatic arrangements for answering calls; Automatic arrangements for recording messages for absent subscribers; Arrangements for recording conversations (centralised dictation systems H04M11/10) · CPC title

• G06F40/56

  Natural language generation · CPC title