Voice and Connection Platform

• US 20160098992A1
• Filed: 09/30/2015
• Published: 04/07/2016
• Est. Priority Date: 10/01/2014
• Status: Active Grant

• Current Assignee: XBrain, Inc.
• Original Assignee: XBrain, Inc.
• Inventors: Renard, Gregory, Herbaux, Mathias
• Granted Patent: US 10,235,996 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 3/167 Audio in a user interface, e.g. using voice commands for navigating, audio feedback
• CPC Class Codes: G10L 15/18 using natural language modelling
• CPC Class Codes: G10L 15/1822 Parsing for meaning understanding
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 15/24 Speech recognition using non-acoustical features
• CPC Class Codes: G10L 15/30 Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
• CPC Class Codes: G10L 2015/223 Execution procedure of a spoken command
• CPC Class Codes: G10L 2015/226 using non-speech characteristics
• CPC Class Codes: G10L 2015/227 of the speaker; Human-factor methodology
• CPC Class Codes: G10L 2015/228 of application context

Abstract

A system and method for providing a voice assistant including receiving, at a first device, a first audio input from a user requesting a first action; performing automatic speech recognition on the first audio input; obtaining a context of user; performing natural language understanding based on the speech recognition of the first audio input; and taking the first action based on the context of the user and the natural language understanding.

Claims

1. A method comprising:

receiving, at a first device, a first audio input from a user requesting a first action;

performing automatic speech recognition on the first audio input;

obtaining a context of user;

performing natural language understanding based on the speech recognition of the first audio input; and

taking the first action based on the context of the user and the natural language understanding.

2. The method of claim 1, wherein the first audio input is received responsive to an internal event.

3. The method of claim 1, comprising:

initiating a voice assistant without user input and receiving the first audio input from the user subsequent to the initiation of the voice assistant.

4. The method of claim 1, wherein the context includes one or more of a context history, a dialogue history, a user profile, a user history, a location and a current context domain.

5. The method of claim 1, comprising:

subsequent to taking the action, receiving a second audio input from the user requesting a second action unrelated to the first action;

taking the second action;

receiving a third audio input from the user requesting a third action related to the first action, the third audio input missing information used to take the third action;

obtaining the missing information using the context; and

taking the third action.

6. The method of claim 5, wherein the missing information is one or more of an action, an actor and an entity.

7. The method of claim 1, comprising:

receiving, at a second device, a second audio input from the user requesting a second action related to the first action, the second audio input missing information used to take the second action;

obtaining the missing information using the context; and

taking the second action based on the context.

8. The method of claim 1, comprising:

determining that the context and the first audio input are missing information used to take the first action;

determining what information is the missing information; and

prompting the user to provide a second audio input supplying the missing information.

9. The method of claim 1, comprising:

determining that information used to take the first action is unable to be obtained from the first audio input;

determining what information is the missing information; and

prompting the user to provide a second audio input supplying the information unable to be obtained from the first audio input.

10. The method of claim 1, comprising:

determining that information used to take the first action is unable to be obtained from the first audio input;

determining what information is missing from information used to take the first action;

providing for selection by the user a plurality of options, an option supplying potential information for completing the first action; and

receiving a second audio input selecting a first option from the plurality of options.

11. A system comprising:

one or more processors; and

a memory storing instructions that when executed by the one or more processors, cause the system to perform the steps including;

receive, at a first device, a first audio input from a user requesting a first action;

perform automatic speech recognition on the first audio input;

obtain a context of user;

perform natural language understanding based on the speech recognition of the first audio input; and

take the first action based on the context of the user and the natural language understanding.

12. The system of claim 11, wherein the first audio input is received responsive to an internal event.

13. The system of claim 11, comprising instructions that when executed by the processor cause the system to:

initiate a voice assistant without user input and receiving the first audio input from the user subsequent to the initiation of the voice assistant.

14. The system of claim 11, wherein the context includes one or more of a context history, a dialogue history, a user profile, a user history, a location and a current context domain.

15. The system of claim 11, comprising instructions that when executed by the processor cause the system to:

subsequent to taking the action, receive a second audio input from the user requesting a second action unrelated to the first action;

take the second action;

receive a third audio input from the user requesting a third action related to the first action, the third audio input missing information used to take the third action;

obtain the missing information using the context; and

take the third action.

16. The system of claim 15, wherein the missing information is one or more of an action, an actor and an entity.

17. The system of claim 11, comprising instructions that when executed by the processor cause the system to:

receive, at a second device, a second audio input from the user requesting a second action related to the first action, the second audio input missing information used to take the second action;

obtain the missing information using the context; and

take the second action based on the context.

18. The system of claim 11, comprising instructions that when executed by the processor cause the system to:

determine that the context and the first audio input are missing information used to take the first action;

determine what information is the missing information; and

prompt the user to provide a second audio input supplying the missing information.

19. The system of claim 11, comprising instructions that when executed by the processor cause the system to:

determine that information used to take the first action is unable to be obtained from the first audio input;

determine what information is the missing information; and

prompt the user to provide a second audio input supplying the information unable to be obtained from the first audio input.

20. The system of claim 11, comprising instructions that when executed by the processor cause the system to:

determine that information used to take the first action is unable to be obtained from the first audio input;

determine what information is missing from information used to take the first action;

provide for selection by the user a plurality of options, an option supplying potential information for completing the first action; and

receive a second audio input selecting a first option from the plurality of options.