SYSTEM AND METHOD FOR INFERRING USER INTENT FROM SPEECH INPUTS

• US 20140365209A1
• Filed: 06/06/2014
• Published: 12/11/2014
• Est. Priority Date: 06/09/2013
• Status: Active Grant

• Current Assignee: Apple Inc.
• Original Assignee: Apple Inc.
• Inventors: EVERMANN, Gunnar
• Granted Patent: US 10,176,167 B2
• Time in Patent Office: Days
• US Class Current: 704/9
• CPC Class Codes: G06F 40/35 Discourse or dialogue representation
• CPC Class Codes: G10L 15/1822 Parsing for meaning understanding
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence

Abstract

A text string with a first and a second portion is provided. A domain of the text string is determined by applying a first word-matching process to the first portion of the text string. It is then determined whether the second portion of the text string matches a word of a set of words associated with the domain by applying a second word-matching process to the second portion of the text string. Upon determining that the second portion of the text string matches the word of the set of words, it is determined whether a user intent from the text string based at least in part on the domain and the word of the set of words.

Claims

1. A method for determining a user intent from a text string, comprising:

at an electronic device with one or more processors and memory storing one or more programs for execution by the one or more processors;

providing a text string corresponding to a speech input, wherein the text string comprises a first portion and a second portion;

determining a domain of the text string using natural language processing by applying a first word-matching process to at least the first portion of the text string;

determining whether the second portion of the text string matches at least one word of a set of words associated with the domain by applying a second word-matching process to the second portion of the text string; and

upon determining that the second portion of the text string matches at least one word of the set of words, determining a user intent from the text string based at least in part on the domain and the at least one word of the set of words.

2. The method of claim 1, wherein word-matching criteria applied by the second word-matching process is more relaxed than word-matching criteria applied by the first word-matching process.

3. The method of claim 1, wherein the first word-matching process requires exact matches between words, and the second word-matching process does not require exact matches between words.

4. The method of claim 1, wherein the second word-matching process applies approximate string matching techniques.

5. The method of claim 4, wherein the second word-matching process comprises determining an edit distance between a word of the second portion of the text string and a word of the set of words associated with the domain.

6. The method of claim 5, wherein the edit distance is a Levenshtein distance.

7. The method of claim 1, wherein the second word-matching process applies phonetic matching techniques.

8. A method for determining a user intent from a text string, comprising:

at an electronic device with one or more processors and memory storing one or more programs for execution by the one or more processors;

providing a plurality of candidate text strings for a speech input, wherein the candidate text strings are generated by a speech recognition process;

selecting at least a subset of the plurality of candidate text strings, the subset including at least two candidate text strings;

determining a plurality of user intents from the selected subset of the plurality of text strings; and

selecting, as a selected user intent, a user intent from the plurality of user intents.

9. The method of claim 8, wherein the plurality of user intents are associated with a plurality of intent deduction confidence scores.

10. The method of claim 8, further comprising selecting the user intent based on the plurality of intent deduction confidence scores.

11. The method of claim 8, wherein the selected user intent is the user intent with the highest intent deduction confidence score.

12. The method of claim 11, wherein the plurality of candidate text strings are associated with a plurality of speech recognition confidence scores.

13. The method of claim 12, further comprising selecting the user intent based on the speech recognition confidence scores and the intent deduction confidence scores.

14. The method of claim 12, further comprising determining a plurality of composite confidence scores for the plurality of user intents.

15. The method of claim 14, wherein the selected user intent is the user intent with the highest composite confidence score.

16. A method for determining a user intent from a text string, comprising:

at an electronic device with one or more processors and memory storing one or more programs for execution by the one or more processors;

providing a plurality of text strings corresponding to a speech input, wherein the plurality of text strings is associated with a plurality of speech recognition confidence scores and a plurality of user intents, and wherein the plurality of user intents is associated with a plurality of intent deduction confidence scores; and

selecting one of the plurality of user intents as a selected user intent based on one or both of the speech recognition confidence scores and the intent deduction confidence scores.

17. The method of claim 16, further comprising determining a plurality of composite confidence scores for the plurality of user intents.

18. The method of claim 17, wherein selecting one of the plurality of user intents includes selecting the user intent with the highest composite confidence score.

19. The method claim 16, further comprising performing one or more actions to satisfy the selected user intent.

20. An electronic device, comprising:

one or more processors;

memory; and

one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs including instructions for;

providing a text string corresponding to a speech input, wherein the text string comprises a first portion and a second portion;

determining a domain of the text string using natural language processing by applying a first word-matching process to at least the first portion of the text string;

determining whether the second portion of the text string matches at least one word of a set of words associated with the domain by applying a second word-matching process to the second portion of the text string; and

upon determining that the second portion of the text string matches at least one word of the set of words, determining a user intent from the text string based at least in part on the domain and the at least one word of the set of words.

21. The electronic device of claim 20, wherein word-matching criteria applied by the second word-matching process is more relaxed than word-matching criteria applied by the first word-matching process.

22. The electronic device of claim 20, wherein the first word-matching process requires exact matches between words, and the second word-matching process does not require exact matches between words.

23. The electronic device of claim 20, wherein the second word-matching process applies approximate string matching techniques.

24. The electronic device of claim 20, wherein the second word-matching process applies phonetic matching techniques.

25. A non-transitory computer readable storage medium storing one or more programs, the one or more programs comprising instructions, which when executed by an electronic device with one or more processors and memory, cause the device to:

provide a text string corresponding to a speech input, wherein the text string comprises a first portion and a second portion;

determine a domain of the text string using natural language processing by applying a first word-matching process to at least the first portion of the text string;

determine whether the second portion of the text string matches at least one word of a set of words associated with the domain by applying a second word-matching process to the second portion of the text string; and

upon determining that the second portion of the text string matches at least one word of the set of words, determine a user intent from the text string based at least in part on the domain and the at least one word of the set of words.

26. The non-transitory computer readable storage medium of claim 25, wherein word-matching criteria applied by the second word-matching process is more relaxed than word-matching criteria applied by the first word-matching process.

27. The non-transitory computer readable storage medium of claim 25, wherein the first word-matching process requires exact matches between words, and the second word-matching process does not require exact matches between words.

28. The non-transitory computer readable storage medium of claim 25, wherein the second word-matching process applies approximate string matching techniques.

29. The non-transitory computer readable storage medium of claim 25, wherein the second word-matching process applies phonetic matching techniques.