Determining user language intent

• US 8,874,599 B2
• Filed: 02/01/2013
• Issued: 10/28/2014
• Est. Priority Date: 11/30/2011
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Murphy, Bruce Winston, Bayliss-McCulloch, Jordan John
• Primary Examiner(s): Shmatov, Alexey
• Application Number:
  US13/757,656
• Publication Number:
  US 20130144900A1
• Time in Patent Office: 634 Days
• Field of Search: 707/722, 707/760
• US Class Current: 707/760
• CPC Class Codes: G06F 16/243 Natural language query formulation
• CPC Class Codes: G06F 16/24522 Translation of natural language queries to structured queries
• CPC Class Codes: G06F 16/3337 Translation of the query language, e.g. Chinese to English
• CPC Class Codes: G06F 40/263 Language identification
• CPC Class Codes: G06F 40/58 Use of machine translation, e.g. for multi-lingual retrieval, for server-side translation for client devices or for real-time translation

Abstract

A system and machine-implemented method for determining a language intent of a user submitted query is provided. A user query comprising text and a user location is received and a language usage signal based on the text of the user query is identified, wherein the language usage signal is associated with a first language. A second language associated with the user location is identified and a translation of the text of the user query from the first language to the second language is generated. A strength of the language usage signal is determined based on an amount of variation between the text of the user query and the translation of the text. When the strength of the language usage signal is greater than a predetermined threshold, an output language for the query is adjusted and results for the query are returned according to the output language.

Claims

1. A computer-implemented method of determining a language intent of a user submitted query, the method comprising:

receiving a user query comprising text and a user location;

identifying at least one language usage signal based on the text of the user query, wherein the at least one language usage signal is associated with a first language;

identifying a second language associated with the user location;

generating a translation of the text of the user query from the first language to the second language;

determining a strength of the at least one language usage signal based on an amount of variation between the text of the user query and the translation of the text of the user query,

wherein the strength of the at least one language usage signal increases as the amount of variation between the text of the user query and the translation of the text of the user query increases;

selecting, when the strength of the at least one language usage signal is greater than a predetermined threshold, the first language as the output language in which results of the user query are returned, based on the language usage signal; and

returning the results for the query according to the output language.

2. The method of claim 1, wherein the amount of variation between the text of the user query and the translation of the text of the user query is based on differences in a spelling of the text of the user query and a spelling of the translation of the text of the user query.

3. The method of claim 2, wherein the amount of variation between the text of the user query and the translation of the text of the user query is based on at least one of a number of different letters in the translation of the text of the user query from the text of the user query, a number of omitted letters in the translation of the text of the user query from the text of the user query, and a number of additional letters in the translation of the text of the user query from the text of the user query.

4. The method of claim 1, wherein the identifying of the at least one language usage signal from the text of the user query is based on at least one of a usage of different languages for common terms or a usage of different geographically biased proper terms.

5. The method of claim 1, wherein the text of the user query corresponds to address data comprising two or more components, the method further comprising:

identifying an order in which the two or more components are presented in the address data corresponding to the user query, wherein the order corresponds to a geographical region with an associated language, and wherein the identifying of the at least one language usage signal is based on the order in which the two or more components are presented in the address data corresponding to the user query.

6. The method of claim 5, wherein the two or more components comprise at least two of a street field, a city field, a state field, a province field, a postal code field, and a country field.

7. The method of claim 1, further comprising returning information associated with the results for the query, the associated information being translated according to the output language.

8. The method of claim 7, wherein the information associated with the results for the query comprises web-based advertisements.

9. The method of claim 1, further comprising:

determining an elapsed time since a last adjustment to the output language; and

reverting the output language to a default language when the elapsed time since the last adjustment to the output language exceeds a predetermined time threshold.

10. A system for determining a language intent of a user submitted query, the system comprising:

one or more processors; and

a non-transitory machine-readable medium comprising instructions stored therein, which when executed by the processors, cause the processors to perform operations comprising;

receiving a user query comprising text and a user location;

identifying at least one language usage signal based on the text of the user query, wherein the at least one language usage signal is associated with a first language;

identifying a second language associated with the user location;

generating a translation of the text of the user query from the first language to the second language;

determining a strength of the at least one language usage signal based on an amount of variation between the text of the user query and the translation of the text of the user query,

wherein the strength of the at least one language usage signal increases as the amount of variation between the text of the user query and the translation of the text of the user query increases;

selecting, when the strength of the at least one language usage signal is greater than a predetermined threshold, the first language as the output language in which results of the user query are returned, based on the language usage signal; and

returning the results for the query according to the output language.

11. The system of claim 10, wherein the amount of variation between the text of the user query and the translation of the text of the user query is based on differences in a spelling of the text of the user query and a spelling of the translation of the text of the user query.

12. The system of claim 11, wherein the amount of variation between the text of the user query and the translation of the text of the user query is based on at least one of a number of different letters in the translation of the text of the user query from the text of the user query, a number of omitted letters in the translation of the text of the user query from the text of the user query, and a number of additional letters in the translation of the text of the user query from the text of the user query.

13. The system of claim 10, wherein the identifying of the at least one language usage signal from the text of the user query is based on at least one of a usage of different languages for common terms or a usage of different geographically biased proper terms.

14. The system of claim 10, wherein the text of the user query corresponds to address data comprising two or more components, and wherein the operations further comprise:

identifying an order in which the two or more components are presented in the address data corresponding to the user query, wherein the order corresponds to a geographical region with an associated language, and wherein the identifying of the at least one language usage signal is based on the order in which the two or more components are presented in the address data corresponding to the user query.

15. The system of claim 10, wherein the operations further comprise returning web-based advertisements, associated with the results for the query, that are translated according to the output language.

16. The system of claim 10, wherein the operations further comprise:

determining an elapsed time since a last adjustment to the output language; and

reverting the output language to a default language when the elapsed time since the last adjustment to the output language exceeds a predetermined time threshold.

17. A non-transitory computer-readable medium comprising instructions stored therein, which when executed by a system, cause the system to perform operations comprising:

receiving a user query comprising text and a user location;

identifying at least one language usage signal based on the text of the user query, wherein the at least one language usage signal is associated with a first language;

identifying a second language associated with the user location;

generating a translation of the text of the user query from the first language to the second language;

determining a strength of the at least one language usage signal based on an amount of variation between the text of the user query and the translation of the text of the user query,

wherein the strength of the at least one language usage signal increases as the amount of variation between the text of the user query and the translation of the text of the user query increases;

selecting, when the strength of the at least one language usage signal is greater than a predetermined threshold, the first language as the output language in which results of the user query are returned, based on the language usage signal; and

returning the results for the query according to the output language.

18. The non-transitory computer-readable medium of claim 17, wherein the amount of variation between the text of the user query and the translation of the text of the user query is based on differences in a spelling of the text of the user query and a spelling of the translation of the text of the user query.