SYSTEMS, METHODS, AND COMPUTER-READABLE MEDIA FOR INTERPRETING GEOGRAPHICAL SEARCH QUERIES

• US 20170344582A1
• Filed: 08/21/2017
• Published: 11/30/2017
• Est. Priority Date: 03/13/2013
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Jurca, Radu
• Granted Patent: US 10,127,245 B2
• Time in Patent Office: Days
• CPC Class Codes: G06F 16/29 Geographical information databases

Abstract

Systems, methods, and computer-readable media for interpreting geographical search queries are provided. Query templates for geographical search queries are generated from search logs of previously executed geographical search queries. Unique queries are extracted from the search logs and interpretations for these queries are obtained. Based on these interpretations, query templates having an arrangement of term types are extracted. Additionally, probability distributions for the query templates for a context, such as a locale, language, client type, etc., are determined.

Claims

1. A computer-implemented method for interpreting geographical search queries, comprising:

receiving a geographical search query from a client computer;

obtaining, by one or more processors, a plurality of geographical search queries, each of the plurality of geographical search queries having a plurality of terms;

determining, by the one or more processors, a plurality of query templates based on the plurality of geographical search queries, each of the plurality of query templates including an arrangement of several geographic term types determined from the plurality of terms, wherein at least some of the plurality of query templates have different arrangements of geographic term types for different locales or languages;

determining, by the one or more processors, one or more query templates of the plurality of query templates corresponding to different locales or languages; and

providing, by the one or more processors, the one or more query templates as one or more interpretation candidates for interpreting the geographical search query corresponding to a locale or language from which the geographical search query was received.

2. The computer-implemented method of claim 1, wherein determining the one or more query templates corresponding to different locales or languages includes determining probability distributions for the plurality of query templates.

3. The computer-implemented method of claim 2, wherein the probability distributions provide a likelihood that a certain query template is a correct interpretation for a given geographical search query and a given locale or language.

4. The computer-implemented method of claim 3, further comprising:

selecting, by the one or more processors, one of the one or more interpretation candidates; and

obtaining, by the one or more processors, search results for the geographic search query based on the selected interpretation candidate.

5. The computer-implemented method of claim 4, further comprising:

providing, by the one or more processors, the search results to the client computer.

6. The computer-implemented method of claim 4, wherein selecting one of the one or more interpretation candidates includes:

ranking, by the one or more processors, the one or more interpretation candidates based on the likelihoods that each of the interpretation candidates is the correct interpretation for the given geographic search query and the given locale or language; and

selecting, by the one or more processors, a highest ranking interpretation candidates of the one or more interpretation candidates.

7. The computer-implemented method of claim 1, wherein the several geographic term types include two or more of:

a number of an address, a route, a locality, a type of entity, a province, a state, and a country.

8. The computer-implemented method of claim 1, wherein the at least some of the plurality of query templates having different arrangements of geographic term types for different locales or languages include a first query template having a plurality of geographic term types in a first order for a first locale or first language and a second query template having the same plurality of geographic term types in a second order different from the first order for a second locale or second language.

9. The computer-implemented method of claim 1, wherein the plurality of query templates are determined based on the plurality of geographical search queries and user actions associated with the plurality of geographical search queries, the user actions including at least one of:

(i) selecting a search result or (ii) refining the geographical search query.

10. A computing device for interpreting geographical search queries, the computing device comprising:

one or more processors; and

a non-transitory computer-readable memory coupled to the one or more processors and storing instructions thereon that, when executed by the one or more processors, cause the computing device to;

receive a geographical search query from a client computer;

obtain a plurality of geographical search queries, each of the plurality of geographical search queries having a plurality of terms;

determine a plurality of query templates based on the plurality of geographical search queries, each of the plurality of query templates including an arrangement of several geographic term types determined from the plurality of terms, wherein at least some of the plurality of query templates have different arrangements of geographic term types for different locales or languages;

determine one or more query templates of the plurality of query templates corresponding to different locales or languages; and

provide the one or more query templates as one or more interpretation candidates for interpreting the geographical search query corresponding to a locale or language from which the geographical search query was received.

11. The computing device of claim 10, wherein to determine the one or more query templates corresponding to different locales or languages, the instructions cause the computing device to determine probability distributions for the plurality of query templates.

12. The computing device of claim 11, wherein the probability distributions provide a likelihood that a certain query template is a correct interpretation for a given geographical search query and a given locale or language.

13. The computing device of claim 12, wherein the instructions further cause the computing device to:

select one of the one or more interpretation candidates; and

obtain search results for the geographic search query based on the selected interpretation candidate.

14. The computing device of claim 12, wherein the instructions further cause the computing device to provide the search results to the client computer.

15. The computing device of claim 12, wherein to select one of the one or more interpretation candidates, the instructions cause the computing device to:

rank the one or more interpretation candidates based on the likelihoods that each of the interpretation candidates is the correct interpretation for the given geographic search query and the given locale or language; and

select a highest ranking interpretation candidates of the one or more interpretation candidates.

16. The computing device of claim 10, wherein the several geographic term types include two or more of:

a number of an address, a route, a locality, a type of entity, a province, a state, and a country.

17. The computing device of claim 10, wherein the at least some of the plurality of query templates having different arrangements of geographic term types for different locales or languages include a first query template having a plurality of geographic term types in a first order for a first locale or first language and a second query template having the same plurality of geographic term types in a second order different from the first order for a second locale or second language.

18. The computing device of claim 10, wherein the plurality of query templates are determined based on the plurality of geographical search queries and user actions associated with the plurality of geographical search queries, the user actions including at least one of:

(i) selecting a search result or (ii) refining the geographical search query.

20. The computer-implemented method of claim 15, wherein the geographic term types include two or more of:

a number of an address, a route, a locality, a type of entity, a province, a state, and a country.

19. A computer-implemented method for displaying search results in response to geographical search queries, comprising:

receiving, at a client device, a geographical search query from a user at a first locale or in a first language, the geographical search query having a plurality of terms with an arrangement of geographic term types;

obtaining, by the client device, a first set of search results from a remote computing device in response to the geographical search query, the first set of search results based on a first query template of a plurality of query templates having an arrangement of geographic term types corresponding to the first locale or first language from which the geographical search query was received;

displaying, by the client device, the first set of search results;

receiving, at the client device, a geographical search query from the user at a second locale or in a second language, the second locale or second language different from the first locale or first language, and the geographical search query having a plurality of terms with an arrangement of geographic term types;

obtaining, by the client device, a second set of search results from the remote computing device in response to the geographical search query, the second set of search results based on a second query template of a plurality of query templates having a different arrangement of geographic term types than the first query template and corresponding to the second locale or second language from which the geographical search query was received; and

displaying, by the client device, the second set of search results.