Search result prefetching of voice queries

• US 10,133,821 B2
• Filed: 01/06/2016
• Issued: 11/20/2018
• Est. Priority Date: 01/06/2016
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google LLC (Alphabet Inc.)
• Inventors: Tandiono, Christopher Bo, Buchanan, Michael, Howard, Nathan David, Rabinovitz, Ishai
• Primary Examiner(s): Stevens, Robert
• Application Number:
  US14/988,990
• Publication Number:
  US 20170193111A1
• Time in Patent Office: 1,049 Days
• Field of Search: 707706
• CPC Class Codes: G06F 16/243 Natural language query formulation
• CPC Class Codes: G06F 16/248 Presentation of query results
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence

Abstract

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for receiving audio data encoding an utterance; obtaining an intermediate transcription of the utterance; before a final transcription of the utterance is obtained: i) determining that the intermediate transcription of the utterance is associated with a previously received search query, ii) obtaining one or more results that are identified as responsive to the previously received search query, and iii) storing one or more of the results; obtaining the final transcription of the utterance; determining that the final transcription of the utterance is also associated with the previously received search query; and in response to determining that the final transcription of the utterance is also associated with the previously received search query, providing the stored one or more results for output.

Claims

1. A method comprising:

receiving, from a digital assistant device or mobile device and by a front end-server of a query processing system that includes (i) the front-end server, (ii) a continuous speech recognizer, (iii) a completion engine, and (iv) a search engine, audio data encoding an utterance received at the digital assistant device or the mobile device;

obtaining, by the continuous speech recognizer of the query processing system, an intermediate transcription of an initial portion of the utterance;

before the continuous speech recognizer generates a final transcription of the entire utterance;

i) determining, by the completion engine of the query processing system, that the intermediate transcription of the initial portion of the utterance is associated with a previously received search query,

ii) obtaining, by the search engine of the query processing system, one or more results that are identified as responsive to the previously received search query, and

iii) storing, by the front-end server of the query processing system, one or more of the results;

obtaining, by the continuous speech recognizer of the query processing system, the final transcription of the entire utterance;

determining, by the completion engine of the query processing system, that the final transcription of the entire utterance is also associated with the previously received search query; and

in response to determining that the final transcription of the entire utterance is also associated with the previously received search query, providing, by the front-end server of the query processing system, the stored one or more results for output without submitting the final transcription of the entire utterance to the search engine.

2. The method of claim 1, further comprising determining, by the completion engine of the query processing system, that the intermediate transcription of the utterance is of a threshold size, wherein the intermediate transcription of the utterance is determined to be associated with the previously received search query only after determining that the intermediate transcription is of the threshold size.

3. The method of claim 1, further comprising after determining that the intermediate transcription of the initial portion of the utterance is associated with the previously received search query, submitting, by the front-end server of the query processing system, the previously received search query for re-execution by a search engine.

4. The method of claim 1, wherein the audio data further includes location data of the digital assistant device or the mobile device, wherein determining that the intermediate transcription of the initial portion of the utterance is associated with the previously received search query comprises determining, by the completion engine of the query processing system, that the location data is associated with a location associated with the previously received search query.

5. The method of claim 1, wherein determining that the intermediate transcription of the initial portion of the utterance is associated with the previously received search query comprises determining, by the completion engine of the query processing system, that the intermediate transcription of the utterance is associated with a previously received search query, the previously received search query submitted by a same user that provided the audio data encoding the utterance.

6. The method of claim 1, wherein determining that the intermediate transcription of the initial portion of the utterance is associated with the previously received search query comprises determining, by the completion engine of the query processing system, that the intermediate transcription of the utterance is associated with a previously received search query, the previously received search query submitted by a different user than a user that provided the audio data encoding the utterance.

7. The method of claim 1, wherein the utterance is a voice command.

8. The method of claim 1, wherein determining that the intermediate transcription of the initial portion of the utterance is associated with a previously received search query further comprises determining, by the completion engine of the query processing system, that the intermediate transcription of the utterance matches a prefix portion of the previously received search query.

9. The method of claim 1, wherein determining that the intermediate transcription of the initial portion of the utterance is associated with a previously received search query further comprises determining, by the completion engine of the query processing system, that the intermediate transcription of the utterance is within a predetermined edit distance of a prefix portion of the previously received search query.

10. A system comprising:

one or more computers and one or more storage devices storing instructions that are operable, when executed by the one or more computers, to cause the one or more computers to perform operations comprising;

receiving, from a digital assistant device or mobile device and by a front end-server of a query processing system that includes (i) the front-end server, (ii) a continuous speech recognizer, (iii) a completion engine, and (iv) a search engine, audio data encoding an utterance received at the digital assistant device or the mobile device;

obtaining, by the continuous speech recognizer of the query processing system, an intermediate transcription of an initial portion of the utterance;

before the continuous speech recognizer generates a final transcription of the entire utterance;

i) determining, by the completion engine of the query processing system, that the intermediate transcription of the initial portion of the utterance is associated with a previously received search query,

ii) obtaining, by the search engine of the query processing system, one or more results that are identified as responsive to the previously received search query, and

iii) storing, by the front-end server of the query processing system, one or more of the results;

obtaining, by the continuous speech recognizer of the query processing system, the final transcription of the entire utterance;

determining, by the completion engine of the query processing system, that the final transcription of the entire utterance is also associated with the previously received search query; and

in response to determining that the final transcription of the entire utterance is also associated with the previously received search query, providing, by the front-end server of the query processing system, the stored one or more results for output without submitting the final transcription of the entire utterance to the search engine.

11. The system of claim 10, the operations further comprising determining, by the completion engine of the query processing system, that the intermediate transcription of the utterance is of a threshold size, wherein the intermediate transcription of the utterance is determined to be associated with the previously received search query only after determining that the intermediate transcription is of the threshold size.

12. The system of claim 10, the operations further comprising after determining that the intermediate transcription of the initial portion of the utterance is associated with the previously received search query, submitting, by the front-end server of the query processing system, the previously received search query for re-execution by a search engine.

13. The system of claim 10, wherein the audio data further includes location data of the digital assistant device or the mobile device, wherein determining that the intermediate transcription of the initial portion of the utterance is associated with the previously received search query comprises determining, by the completion engine of the query processing system, that the location data is associated with a location associated with the previously received search query.

14. The system of claim 10, wherein determining that the intermediate transcription of the initial portion of the utterance is associated with the previously received search query comprises determining, by the completion engine of the query processing system, that the intermediate transcription of the utterance is associated with a previously received search query, the previously received search query submitted by a same user that provided the audio data encoding the utterance.

15. A non-transitory computer-readable medium storing software comprising instructions executable by one or more computers which, upon such execution, cause the one or more computers to perform operations comprising:

receiving, from a digital assistant device or mobile device and by a front end-server of a query processing system that includes (i) the front-end server, (ii) a continuous speech recognizer, (iii) a completion engine, and (iv) a search engine, audio data encoding an utterance received at the digital assistant device or the mobile device;

obtaining, by the continuous speech recognizer of the query processing system, an intermediate transcription of an initial portion of the utterance;

before the continuous speech recognizer generates a final transcription of the entire utterance;

i) determining, by the completion engine of the query processing system, that the intermediate transcription of the initial portion of the utterance is associated with a previously received search query,

ii) obtaining, by the search engine of the query processing system, one or more results that are identified as responsive to the previously received search query, and

iii) storing, by the front-end server of the query processing system, one or more of the results;

obtaining, by the continuous speech recognizer of the query processing system, the final transcription of the entire utterance;

determining, by the completion engine of the query processing system, that the final transcription of the entire utterance is also associated with the previously received search query; and

in response to determining that the final transcription of the entire utterance is also associated with the previously received search query, providing, by the front-end server of the query processing system, the stored one or more results for output without submitting the final transcription of the entire utterance to the search engine.

16. The computer-readable medium of claim 15, the operations further comprising determining, by the completion engine of the query processing system, that the intermediate transcription of the utterance is of a threshold size, wherein the intermediate transcription of the utterance is determined to be associated with the previously received search query only after determining that the intermediate transcription is of the threshold size.

17. The computer-readable medium of claim 15, the operations further comprising after determining that the intermediate transcription of the initial portion of the utterance is associated with the previously received search query, submitting, by the front-end server of the query processing system, the previously received search query for re-execution by a search engine.