SYSTEM AND METHOD OF PROVIDING INTENT PREDICTIONS FOR AN UTTERANCE PRIOR TO A SYSTEM DETECTION OF AN END OF THE UTTERANCE

• US 20160148610A1
• Filed: 11/24/2015
• Published: 05/26/2016
• Est. Priority Date: 11/26/2014
• Status: Active Grant

• Current Assignee: Cerence Inc.
• Original Assignee: VoiceBox Technologies Corporation (Microsoft Corporation)
• Inventors: Kennewick, JR., Michael R., Carter, Daniel B.
• Granted Patent: US 10,614,799 B2
• Time in Patent Office: Days
• CPC Class Codes: G10L 15/18 using natural language modelling
• CPC Class Codes: G10L 2015/228 of application context

Abstract

In certain implementations, intent prediction is provided for a natural language utterance based on a portion of the natural language utterance prior to a system detection of an end of the natural language utterance. In some implementations, a first portion of a natural language utterance of a user may be received. Speech recognition may be performed on the first portion of the natural language utterance to recognize one or more words of the first portion of the natural language utterance. Context information for the natural language utterance may be obtained. Prior to a detection of an end of the natural language utterance, a first intent may be predicted based on the one or more words of the first portion and the context information. One or more user requests may be determined based on the first predicted intent.

Claims

1. A method of providing intent prediction for a natural language utterance based on a portion of the natural language utterance prior to a system detection of an end of the natural language utterance, the method being implemented on a computer system that includes one or more physical processors executing computer program instructions which, when executed by the one or more physical processors, perform the method, the method comprising:

receiving, at the computer system, a first portion of a natural language utterance of a user;

predicting, by the computer system, prior to a detection of an end of the natural language utterance, a first intent associated with the natural language utterance based on the first portion of the natural language utterance; and

generating, by the computer system, one or more user requests based on the first predicted intent.

2. The method of claim 1, further comprising:

performing, by the computer system, speech recognition on the first portion of the natural language utterance to recognize one or more words of the first portion of the natural language utterance; and

obtaining, by the computer system, context information for the natural language utterance,

wherein predicting the first intent comprises predicting, prior to the detection of the end of the natural language utterance, the first intent based on the one or more words of the first portion and the context information.

3. The method of claim 2, further comprising:

inferring, by the computer system, one or more words of a portion of the natural language utterance that the user has not yet spoken based on the first predicted intent; and

providing, by the computer system, prior to the detection of the end of the natural language utterance, a set of words for presentation to the user that comprises the one or more words of the first portion and the one or more inferred words of the not-yet-spoken portion.

4. The method of claim 3, wherein the set of words comprises a first set of words having the one or more inferred words of the non-yet-spoken portion, the method further comprising:

receiving, at the computer system, a user selection of the first set of words responsive to the presentation of the set of words,

wherein generating the one or more user requests based on the first predicted intent comprises generating a user request related to the set of words responsive to the user selection of the first set of words.

5. The method of claim 4, further comprising:

providing, by the computer system, prior to the detection of the end of the natural language utterance, a second set of words for presentation to the user that comprises one or more inferred words of a second non-yet-spoken portion of the natural language utterance,

wherein receiving the user selection of the first set of words comprises receiving a user selection of the first set of words responsive to the presentation of the first set of words and the second set of words.

6. The method of claim 1, further comprising:

generating, by the computer system, a first user request based on the first predicted intent;

obtaining, by the computer system, one or more first results related to the first user request;

receiving, at the computer system, a second portion of the natural language utterance;

predicting, by the computer system, a second intent associated with the natural language utterance based on the second portion of the natural language utterance;

generating, by the computer system, a second user request based on the second predicted intent;

obtaining, by the computer system, one or more second results related to the first user request;

settling, by the computer system, on an intent of the user in speaking at least a portion of the natural language utterance;

determining, by the computer system, whether at least one of the first intent or the second intent corresponds to the intent of the user; and

generating, by the computer system, a response for presentation to the user;

(a) using the one or more first results responsive to a determination that the first intent corresponds to the intent of the user; and

(b) using the one or more second results responsive to a determination that the second intent corresponds to the intent of the user.

7. The method of claim 6, wherein generating the response comprises generating the response using the one or more first results and without using the one or more second results responsive to a determination that the first intent corresponds to the intent of the user and that the second intent does not correspond to the intent of the user.

8. The method of claim 1, further comprising:

determining, by the computer system, a first user request based on the first predicted intent;

obtaining, by the computer system, one or more first results related to the first user request; and

providing, by the computer system, prior to the detection of the end of the natural language utterance, the one or more first results for presentation to the user.

9. The method of claim 1, further comprising:

performing, by the computer system, speech recognition on one or more portions of the natural language utterance to recognize one or more words of the one or more portions of the natural language utterance; and

performing, by the computer system, semantic processing on the one or more words of the one or more portions to detect the end of the natural language utterance.

10. The method of claim 1, wherein the one or more user requests comprise at least one of a command or a query.

11. A system for providing intent prediction for a natural language utterance based on a portion of the natural language utterance prior to a system detection of an end of the natural language utterance, the system comprising:

one or more physical processors programmed with computer program instructions which, when executed, cause the one or more physical processors to;

receive a first portion of a natural language utterance of a user;

predict, prior to a detection of an end of the natural language utterance, a first intent associated with the natural language utterance based on the first portion of the natural language utterance; and

generate one or more user requests based on the first predicted intent.

12. The system of claim 11, wherein the one or more physical processors are further caused to:

perform speech recognition on the first portion of the natural language utterance to recognize one or more words of the first portion of the natural language utterance; and

obtain context information for the natural language utterance,

wherein predicting the first intent comprises predicting, prior to the detection of the end of the natural language utterance, the first intent based on the one or more words of the first portion and the context information.

13. The system of claim 12, wherein the one or more physical processors are further caused to:

infer one or more words of a portion of the natural language utterance that the user has not yet spoken based on the first predicted intent; and

provide, prior to the detection of the end of the natural language utterance, a set of words for presentation to the user that comprises the one or more words of the first portion and the one or more inferred words of the not-yet-spoken portion.

14. The system of claim 13, wherein the set of words comprises a first set of words having the one or more inferred words of the non-yet-spoken portion, and wherein the one or more physical processors are further caused to:

receive a user selection of the first set of words responsive to the presentation of the set of words,

wherein generating the one or more user requests based on the first predicted intent comprises generating a user request related to the set of words responsive to the user selection of the first set of words.

15. The system of claim 14, wherein the one or more physical processors are further caused to:

provide, prior to the detection of the end of the natural language utterance, a second set of words for presentation to the user that comprises one or more inferred words of a second non-yet-spoken portion of the natural language utterance,

wherein receiving the user selection of the first set of words comprises receiving a user selection of the first set of words responsive to the presentation of the first set of words and the second set of words.

16. The system of claim 11, wherein the one or more physical processors are further caused to:

determine a first user request based on the first predicted intent;

obtain one or more first results related to the first user request;

receive a second portion of the natural language utterance after the receipt of the first portion of the natural language utterance;

predict a second intent associated with the natural language utterance based on the second portion of the natural language utterance;

determine a second user request based on the second predicted intent;

obtain one or more second results related to the first user request;

settle on an intent of the user in speaking at least a portion of the natural language utterance;

determine whether at least one of the first intent or the second intent corresponds to the intent of the user; and

generate a response for presentation to the user;

(a) using the one or more first results responsive to a determination that the first intent corresponds to the intent of the user; and

(b) using the one or more second results responsive to a determination that the second intent corresponds to the intent of the user.

17. The system of claim 16, wherein generating the response comprises generating the response using the one or more first results and without using the one or more second results responsive to a determination that the first intent corresponds to the intent of the user and that the second intent does not correspond to the intent of the user.

18. The system of claim 11, wherein the one or more physical processors are further caused to:

determine a first user request based on the first predicted intent;

obtain one or more first results related to the first user request; and

provide, prior to the detection of the end of the natural language utterance, the one or more first results for presentation to the user.

19. The system of claim 11, wherein the one or more physical processors are further caused to:

perform speech recognition on one or more portions of the natural language utterance to recognize one or more words of the one or more portions of the natural language utterance; and

perform semantic processing on the one or more words of the one or more portions to detect the end of the natural language utterance.

20. The system of claim 11, wherein the one or more user requests comprise at least one of a command or a query.

21. A method of providing intent prediction for a natural language utterance based on a portion of the natural language utterance prior to a system detection of an end of the natural language utterance, the method being implemented on a computer system that includes one or more physical processors executing computer program instructions which, when executed by the one or more physical processors, perform the method, the method comprising:

receiving, at the computer system, a first portion of a natural language utterance of a user;

performing, by the computer system, speech recognition on the first portion of the natural language utterance to recognize one or more words of the first portion of the natural language utterance;

obtaining, by the computer system, context information for the natural language utterance;

predicting, by the computer system, prior to the detection of the end of the natural language utterance, the first intent based on the one or more words of the first portion and the context information;

inferring, by the computer system, one or more words of a portion of the natural language utterance that the user has not yet spoken based on the first predicted intent; and

providing, by the computer system, a set of words for presentation to the user that comprises the one or more words of the first portion and the one or more inferred words of the not-yet-spoken portion.

22. The method of claim 21, further comprising:

receiving, at the computer system, a user selection of the set of words responsive to the presentation of the set of words; and

determining, by the computer system, a user request related to the set of words responsive to the user selection of the set of words.

23. The method of claim 22, wherein the set of words comprises a first set of words having the one or more words of the first portion and the one or more inferred words of the non-yet-spoken portion, the method further comprising:

providing, by the computer system, prior to the detection of the end of the natural language utterance, a second set of words for presentation to the user that comprises one or more inferred words of a second non-yet-spoken portion of the natural language utterance,

wherein receiving the user selection of the set of words comprises receiving a user selection of the first set of words responsive to the presentation of the first set of words and the second set of words, and

wherein generating the user request related to the set of words comprises generating a user request related to the first set of words responsive to the user selection of the first set of words.

24. The method of claim 21, further comprising:

receiving, at the computer system, a second utterance of the user;

determining, by the computer system, second context information for the second utterance based on the one or more words of the first portion of the natural language utterance and the one or more inferred words of the not-yet-spoken portion of the natural language utterance; and

determining, by the computer system, one or more user requests based on the second utterance and the second context information.

25. The method of claim 21, wherein the second utterance is received after the receipt of the natural language utterance.

26. The method of claim 21, wherein the second utterance is received prior to the receipt of the natural language utterance.

27. A method of providing intent prediction for a natural language utterance based on a portion of the natural language utterance prior to a system detection of an end of the natural language utterance, the method being implemented on a computer system that includes one or more physical processors executing computer program instructions which, when executed by the one or more physical processors, perform the method, the method comprising:

receiving, at the computer system, a first portion of a natural language utterance of a user;

predicting, by the computer system, prior to a detection of an end of the natural language utterance, a first intent associated with the natural language utterance based on the first portion of the natural language utterance;

determining, by the computer system, a first user request based on the first predicted intent; and

obtaining, by the computer system, one or more first results related to the first user request.

28. The method of claim 27, further comprising:

receiving, at the computer system, a second portion of the natural language utterance;

predicting, by the computer system, a second intent associated with the natural language utterance based on the second portion of the natural language utterance;

determining, by the computer system, a second user request based on the second predicted intent;

obtaining, by the computer system, one or more second results related to the first user request;

settling, by the computer system, on an intent of the user in speaking at least a portion of the natural language utterance;

determining, by the computer system, whether at least one of the first intent or the second intent corresponds to the intent of the user; and

generating, by the computer system, a response for presentation to the user based on whether at least one of the first intent or the second intent corresponds to the intent of the user.

29. The method of claim 28, wherein generating the response comprises generating the response:

(a) using the one or more first results responsive to a determination that the first intent corresponds to the intent of the user; and

(b) using the one or more second results responsive to a determination that the second intent corresponds to the intent of the user.

30. The method of claim 29, wherein generating the response comprises generating the response using the one or more first results and without using the one or more second results responsive to a determination that the first intent corresponds to the intent of the user and that the second intent does not correspond to the intent of the user.