Dynamic determination of location-identifying search phrases

• US 7,987,195 B1
• Filed: 04/08/2008
• Issued: 07/26/2011
• Est. Priority Date: 04/08/2008
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Li, Xin, Falola, Dolapo
• Primary Examiner(s): Fleurantin; Jean B
• Application Number:
  US12/099,762
• Time in Patent Office: 1,204 Days
• Field of Search: 707600-831
• US Class Current: 707/765
• CPC Class Codes: G06F 16/40 of multimedia data, e.g. slideshows comprising image and additional audio data retrieval of still image data G06F16/50; retrieval of audio data G06F16/60; retrieval of video data G06F16/70
• CPC Class Codes: G06F 16/9537 Spatial or temporal dependent retrieval, e.g. spatiotemporal queries

Abstract

A computer-implemented method includes providing location factors for first phrases in a collection of phrases, where each location factor for a first phrase is associated with a likelihood that a second phrase of a search query is associated with a location when the first phrase and the second phrase are used in the search query. A search query is received, where the received search query includes a first phrase from the collection of phrases and a second phrase. Whether the second phrase of the received search query refers to a location is determined based, at least in part, on the location factor for the first phrase of the search query.

Claims

1. A computer-implemented method comprising:

providing location factors for first phrases in a collection of phrases, each location factor for a first phrase being associated with a likelihood that a second phrase of a search query is associated with a location when the first phrase and the second phrase are used in the search query;

receiving a search query, the received search query including a first phrase from the collection of phrases and a second phrase;

determining that the second phrase does not correspond to a location that can be identified by the second phrase alone, by;

determining a name score indicating a popularity of the second phrase for the location;

obtaining a signature for the location, wherein the signature includes a set of combinations of location specifiers, wherein each combination of location specifiers refers to the location;

determining a signature score that indicates a popularity of the signature for the location; and

determining that the location cannot be identified by the second phrase alone based on the name score and the signature score for the location; and

determining whether the second phrase of the received search query refers to a location based, at least in part, on the location factor for the first phrase of the search query.

2. The method of claim 1, wherein providing a location factor for a first phrase includes:

receiving a plurality of search queries, each search query having a plurality of search phrases, at least some of the queries including the first phrase;

providing search results in response to each of the plurality of search queries;

receiving responses to the provided search results; and

determining a location factor for the first phrase based on responses to the search results.

3. The method of claim 2, wherein determining a location factor for the first phrase based on the responses to the search results includes:

determining a first frequency with which a search result associated with a known location is selected in response to search results presented for queries including the first phrase and a third phrase;

determining a second frequency with which a search result associated with a known location is selected in response to search results presented for queries including the first phrase but not including the third phrase; and

comparing the first frequency to the second frequency.

4. The method of claim 2, wherein determining a location factor for the first phrase based on the responses to the search results includes:

determining how often responses to a search result associated with a known location are received relative to how often responses to a search result not associated with a known location are received.

5. The method of claim 4, wherein determining a location factor for the first phrase based on the responses to the search results further includes:

determining a number of different known locations associated with the search results for which responses are received; and

determining a distribution of the responses as a function of the different known locations.

6. The method of claim 1, wherein determining whether the second phrase refers to a location includes:

determining a language factor based on a language associated with the search query; and

determining whether the second phrase refers to a location based, at least in part, on the language factor.

7. The method of claim 1, wherein determining whether the second phrase refers to a location includes:

determining an origin factor based on an origin associated with the search query; and

determining whether the second phrase refers to a location based, at least in part, on the origin factor.

8. The method of claim 7, wherein determining the origin factor includes determining the origin factor based on a location from which the search query originates.

9. The method of claim 7, wherein determining the origin factor includes determining the origin factor based on a domain name of a search engine through which the search query is received.

10. The method of claim 1, further comprising:

when the second phrase is determined to refer to a location, providing search results in response to the search query, the search results being ranked to give preference to search results related to the location when providing the search results.

11. The method of claim 10, further comprising:

providing at least some of the provided search results in a format designed for presenting location-specific search results.

12. The method of claim 10, further comprising billing an advertiser for providing a search result that includes information related to the location referred to by the second phrase.

13. The method of claim 1, wherein the received search query includes an unstructured text query.

14. A computer program product tangibly embodied on a computer-readable storage medium and including executable code that, when executed, is configured to cause a data processing apparatus to:

provide location factors for first phrases in a collection of phrases, each location factor for a first phrase being associated with a likelihood that a second phrase of a search query is associated with a location when the first phrase and the second phrase are used in the search query;

receive a search query, the received search query including a first phrase from the collection of phrases and a second phrase;

determine that the second phrase does not correspond to a location that can be identified by the second phrase alone, by;

determining a name score indicating a popularity of the second phrase for the location;

obtaining a signature for the location, wherein the signature includes a set of combinations of location specifiers, wherein each combination of location specifiers refers to the location;

determining a signature score that indicates a popularity of the signature for the location; and

determining that the location cannot be identified by the second phrase alone based on the name score and the signature score for the location; and

determine whether the second phrase of the received search query refers to a location based, at least in part, on the location factor for the first phrase of the search query.

15. The computer program product of claim 14, wherein providing a location factor for a first phrase includes:

receiving a plurality of search queries, each search query having a plurality of search phrases, including the first phrase;

providing search results in response to each of the plurality of search queries;

receiving responses to the provided search results; and

determining location factors for the first phrase based on responses to the search results.

16. The computer program product of claim 14, wherein determining a location factor for the first phrase based on the responses to the search results includes:

determining how often responses to a search result associated with a known location are received relative to how often responses to a search result not associated with a known location are received.

17. The computer program product of claim 16, wherein determining a location factor for the first phrase based on the responses to the search results further includes:

determining a number of different known locations associated with the search results for which responses are received; and

determining a distribution of the responses as a function of the different known locations.

18. The computer program product of claim 14, further comprising executable code that, when executed, is configured to cause the data processing apparatus to:

provide search results in response to the search query when the second phrase is determined to refer to a location, the search results being ranked to give preference to search results related to the location when providing the search results.

19. The computer program product of claim 18, further comprising executable code that, when executed, is configured to cause the data processing apparatus to:

provide at least some of the provided search results in a format designed for presenting location-specific search results.

20. The computer program product of claim 18, further comprising executable code that, when executed, is configured to cause the data processing apparatus to:

bill an advertiser for providing a search result that includes information related to the location referred to by the second phrase.

21. The computer program product of claim 14, wherein the received search query includes an unstructured text query.

22. The system of claim 21, wherein the first server is further configured to provide search results in response to the search query when the second phrase is determined to refer to a location, the search results being ranked to give preference to search results related to the location.

23. A system comprising:

a storage medium configured to store location factors for first phrases in a collection of phrases, each location factor for a first phrase being associated with a likelihood that a second phrase of a search query is associated with a location when the first phrase and the second phrase are used in the search query;

a first server configured to receive a search query, the received search query including a first phrase from the collection of phrases and a second phrase;

at least one processor configured to determine that the second phrase does not correspond to a location that can be identified by the second phrase alone, by;

determining a name score indicating a popularity of the second phrase for the location;

obtaining a signature for the location, wherein the signature includes a set of combinations of location specifiers, wherein each combination of location specifiers refers to the location;

determining a signature score that indicates a popularity of the signature for the location; and

determining that the location cannot be identified by the second phrase alone based on the name score and the signature score for the location; and

at least one processor configured to determine whether the second phrase of the received search query refers to a location based, at least in part, on the location factor for the first phrase of the search query.

24. The system of claim 23, further comprising:

a second server, the second server being configured to;

receive a plurality of search queries, each search query having a plurality of search phrases, including a first phrase;

provide search results in response to each of the plurality of search queries; and

receive responses to the provided search results; and

at least one processor being configured to;

determine a location factor for the first phrase based on responses to the search results; and

provide the location factor for the first phrase for storage in the storage medium.

25. The system of claim 24, wherein determining a location factor for the first phrase based on the responses to the search results includes:

determining how often responses to a search result associated with a known location are received relative to how often responses to a search result not associated with a known location are received.

26. The system of claim 25, wherein determining a location factor for the first phrase based on the responses to the search results further includes:

determining a number of different known locations associated with the search results for which responses are received; and

determining a distribution of the responses as a function of the different known locations.