Customized speech generation

• US 8,706,827 B1
• Filed: 06/21/2012
• Issued: 04/22/2014
• Est. Priority Date: 06/21/2012
• Status: Expired due to Fees

• Current Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Original Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Inventors: Noble, Isaac S., Karakotsios, Kenneth M., Halberg, Gabrielle M., Watanabe, Yuzo
• Primary Examiner(s): Roberts, Shaun
• Application Number:
  US13/529,788
• Time in Patent Office: 670 Days
• Field of Search: 345/171, 709206-207, 704/9, 704/270
• US Class Current: 709/206
• CPC Class Codes: G06F 40/20 Natural language analysis semantic analysis of natural language G06F40/30
• CPC Class Codes: G06F 40/56 Natural language generation
• CPC Class Codes: G10L 13/027 Concept to speech synthesisers; Generation of natural phrases from machine-based concepts generation of parameters for speech synthesis out of text G10L13/08
• CPC Class Codes: G10L 15/18 using natural language modelling
• CPC Class Codes: H04L 51/00 User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail
• CPC Class Codes: H04L 51/02 using automatic reactions or user delegation, e.g. automatic replies or chatbot-generated messages
• CPC Class Codes: H04M 1/64 Automatic arrangements for answering calls; Automatic arrangements for recording messages for absent subscribers; Arrangements for recording conversations centralised dictation systems H04M11/10
• CPC Class Codes: H04M 1/7243 with interactive means for internal management of messages
• CPC Class Codes: H04M 2250/10 including a GPS signal receiver

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.

Claims

1. A computer-implemented method comprising:

under control of one or more computer systems configured with executable instructions,

storing dialog patterns for a type of communication between a user and a type of recipient, the dialog patterns including at least one of words or phrases from one or more past communications between the user and one or more recipients of the type of recipient;

generating a dialog profile for the type of recipient based at least in part upon the dialog patterns;

determining at least one context associated with the user sending a communication to a recipient of the one or more recipients of the type of recipient, the at least one context being associated with at least one behavioral pattern of the user;

determining a subsequent occurrence of the at least one context;

adjusting the dialog profile associated with the recipient to include dialog patterns associated with the at least one context;

generating at least one subsequent communication to be sent to the recipient based at least in part on the dialog patterns associated with the dialog profile of the recipient and the at least one context.

2. The computer-implemented method of claim 1, further comprising:

enabling the user to approve the at least one subsequent communication before sending the at least one subsequent communication to the recipient.

3. The computer-implemented method of claim 1, wherein the type of recipient is at least one of a business contact, a friend contact, or a family member contact.

4. The computer-implemented method of claim 1, further comprising:

accessing textual information to determine a dialog pattern, the textual information being accessed from at least one of email messages, social network feeds, text messages, instant messages, chat sessions, or voice data.

5. The computer-implemented method of claim 1, wherein the at least one context comprises one or more of:

a location, a time of day, an occurrence of an event, or a subject.

6. The computer-implemented method of claim 1, wherein the at least one context is determined by one or more of using at least one Global Positioning System (GPS) sensor, determining an occurrence of an event, determining a time of day, or determining a day of a week.

7. A computer-implemented method comprising:

under control of one or more computer systems configured with executable instructions,

maintaining communication data associated with a contact type based at least in part upon past communications between a user and one or more contacts associated with the contact type, the communication data including;

a type of communication sent to the one or more contacts of the contact type by the user in a context, the context being associated with at least one behavioral pattern of the user; and

a dialog pattern associated with the type of communication in the context, the dialog pattern including at least one of words or phrases from one or more past communications between the user and the one or more contacts associated with the contact type;

generating a dialog profile for the contact type based at least in part upon the dialog patterns;

identifying a current context as being related to the context;

adjusting the dialog profile associated with the one or more contacts to include dialog patterns associated with the context; and

generating a communication for the current context based at least in part upon the dialog patterns associated with the dialog profile and the context.

8. The computer-implemented method of claim 7, further comprising:

prompting the user before at least one of generating the communication or sending the communication.

9. The computer-implemented method of claim 7, wherein the type of communication is at least one of a text message, an instant message, a short message service message, a chat message, or an email message.

10. The computer-implemented method of claim 7, wherein the contact type is at least a business contact group, a friend group, or a family group.

11. The computer-implemented method of claim 7, wherein the current context is determined using at least one of a location, a time of day, an occurrence of an event, or a particular subject.

12. The computer-implemented method of claim 7, further comprising:

receiving voice input from the user to approve the communication.

13. The computer-implemented method of claim 7, wherein maintaining communication data includes:

monitoring information sent by the user in communications to the one or more contacts associated with the contact type;

monitoring context information related to the communications; and

storing the information sent by the user in the communications and the context information.

14. A computer-implemented method comprising:

monitoring information in a communication sent by a user;

monitoring context information related to the communication, the context information being associated with at least one behavioral pattern of the user;

identifying a communication pattern between the user and one or more contacts associated with a contact group based at least in part upon at least one of the information or the monitored context information, the communication pattern including at least one of words or phrases from one or more past communications between the user and the one or more contacts associated with the contact group;

generating a communication model based at least in part on the communication pattern; and

in response to receiving a communication from a contact associated with the contact group

adjusting the communication model to include dialog patterns associated with the context information, and

generating a context-appropriate response based at least in part on the communication pattern associated with the communication model associated with the contact group and the context information.

15. The computer-implemented method of claim 14, wherein the communication is at least one of a phone call, a text message, an instant message, a short message service message, a chat message, or an email message.

16. A computing device, comprising:

a device processor;

a display screen; and

a memory device including instructions operable to be executed by the processor to perform a set of actions, enabling the computing device to;

maintain communication data associated with a contact type based at least in part upon past communications between a user and one or more contacts associated with the contact type, the communication data including;

a type of communication sent to the one or more contacts of the contact type by the user in a context, the context being associated with at least one behavioral pattern of the user; and

a dialog pattern associated with the type of communication in the context, the dialog pattern including at least one of words or phrases associated with one or more past communications between the user and the one or more contacts associated with the contact type;

generate a dialog profile for the contact type based at least in part upon the dialog patterns;

identify a current context as being related to the context;

adjust the dialog profile associated with the one or more contacts to include dialog patterns associated with the context; and

generate a communication for the current context based at least in part upon the dialog patterns associated with the dialog profile and the context.

17. The computing device of claim 16, further comprising:

prompt the user for an input to at least one of generate the communication or send the communication.

18. The computing device of claim 16, wherein the current context is determined by at least one of determining a location using a Global Positioning System (GPS) sensor or determining an occurrence of an event by accessing data associated with at least one of a calendar or email application of the computing device.

19. The computing device of claim 17, wherein the instructions, when executed by the processor, further enabling the computing device to:

in response to receiving an input from the user, send the communication,

wherein the input is at least one of a voice input provided to a conversational interface or a touch input provided to the display screen of the computing device.

20. A non-transitory computer-readable storage medium storing instructions that, when executed by a processor, cause the processor to:

maintain communication data associated with a contact type based at least in part upon past communications between a user and one or more contacts associated with the contact type, the communication data including;

a type of communication sent to the one or more contacts of the contact type by the user in a context, the context being associated with at least one behavioral pattern of the user; and

a dialog pattern associated with the type of communication in the context, the dialog pattern including at least one of words or phrases associated with one or more past communications between the user and the one or more contacts associated with the contact type;

generate a dialog profile for the contact type based at least in part upon the dialog patterns;

identify a current context as being related to the context;

adjust the dialog profile associated with the one or more contacts to include dialog patterns associated with the context; and

generate a communication for the current context based at least in part upon the dialog patterns associated with the dialog profile and the context.

21. The non-transitory computer-readable storage medium of claim 20, wherein maintaining the communication data includes monitoring information sent by the user in communications to the one or more contacts associated with the contact type, monitoring context information related to the communications, and storing the information sent in the communications and the context information.

22. The non-transitory computer-readable storage medium of claim 20, wherein the instructions when executed further cause the processor to:

enable the user to approve the communication before sending the communication to a recipient.