Classification of ambiguous geographic references

• US 9,323,738 B2
• Filed: 09/26/2014
• Issued: 04/26/2016
• Est. Priority Date: 12/30/2004
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Egnor, Daniel
• Primary Examiner(s): Hwa, Shyue Jiunn
• Application Number:
  US14/497,903
• Publication Number:
  US 20150012542A1
• Time in Patent Office: 578 Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/285 Clustering or classification
• CPC Class Codes: G06F 16/29 Geographical information databases
• CPC Class Codes: G06F 16/31 Indexing; Data structures therefor; Storage structures
• CPC Class Codes: G06F 16/9537 Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
• CPC Class Codes: H04L 67/10 in which an application is distributed across nodes in the network software deployment G06F8/60; multiprogramming arrangements G06F9/46
• CPC Class Codes: Y10S 707/99935 Query augmenting and refining, e.g. inexact access

Abstract

A location classifier generates location information based on textual strings in input text. The location information defines potential geographical relevance of the input text. In determining the location information, the location classifier may receive at least one geo-relevance profile associated with at least one string in the input text, obtain a combined geo-relevance profile for the document from the at least one geo-relevance profile, and determine geographical relevance of the input text based on the combined geo-relevance profile.

Claims

1. A method comprising:

identifying, by a device, a first phrase in a document as being geographically significant,

the first phrase being identified as geographically significant based on previous occurrences of the first phrase being determined to be statistically significant to first geographic information;

identifying, by the device, a second phrase in the document as being geographically significant,

the second phrase being identified as geographically significant based on previous occurrences of the second phrase being determined to be statistically significant to second geographic information;

determining, by the device, that the first phrase is associated with a first plurality of geographic areas;

determining, by the device, that the second phrase is associated with a second plurality of geographic areas;

determining, by the device, that a geographic area of the first plurality of geographic areas matches a geographic area of the second plurality of geographic areas;

associating, by the device and based on determining that the geographic area of the first plurality of geographic areas matches the geographic area of the second plurality of geographic areas, the document with a particular geographic area, the particular geographic area corresponding to the geographic area of the first plurality of geographic areas and the geographic area of the second plurality of geographic areas;

storing, by the device, information indicating the association of the document with the particular geographic area;

generating, based on located geographic information associated with a phrase in a respective document, a histogram for the phrase; and

storing the generated histogram.

2. The method of claim 1, where

the first phrase is a partial address, and

the method further includes:

generating, based on the information indicating the association of the document with the particular geographic area, a full address of the first phrase.

3. The method of claim 1, where

the second phrase is a partial address, and

the method further includes:

generating, based on the information indicating the association of the document with the particular geographic area, a full address of the second phrase.

4. The method of claim 1, where, when determining that the geographic area of the first plurality of geographic areas matches the geographic area of the second plurality of geographic areas, the method includes:

determining that the geographic area of the first plurality of geographic areas matches the geographic area of the second plurality of geographic areas using the generated histogram.

5. The method of claim 1, where, when locating the geographic information, the method includes:

locating the geographic information using a pattern matching technique.

6. The method of claim 1, where the document is:

a search query, or

a web page.

7. A device comprising:

a memory to store instructions; and

a processor to execute the instructions to;

identify a first phrase in a document as being geographically significant,

the first phrase being identified as geographically significant based on previous occurrences of the first phrase being determined to be statistically significant to first geographic information;

identify a second phrase in the document as being geographically significant,

the second phrase being identified as geographically significant based on previous occurrences of the second phrase being determined to be statistically significant to second geographic information;

receive information indicating that the first phrase is associated with a first plurality of geographic areas;

receive information indicating that the second phrase is associated with a second plurality of geographic areas;

determine that a geographic area of the first plurality of geographic areas matches a geographic area of the second plurality of geographic areas;

associate, based on determining that the geographic area of the first plurality of geographic areas matches the geographic area of the second plurality of geographic areas, the document with a particular geographic area, the particular geographic area corresponding to the geographic area of the first plurality of geographic areas and the geographic area of the second plurality of geographic areas;

store information indicating the association of the document with the particular geographic area, the stored information permitting a determination to be made as to whether the document is relevant to the particular geographic area;

generate, based on located geographic information associated with a phrase in a respective document, a histogram for the phrase; and

store the generated histogram.

8. The device of claim 7, where

the first phrase is a partial address, and

the processor executes the instructions to:

generate, based on the information indicating the association of the document with the particular geographic area, a location identifier associated with the first phrase.

9. The device of claim 7, where

the second phrase is a partial address, and

the processor executes the instructions to:

generate, based on the information indicating the association of the document with the particular geographic area, a location identifier associated with the second phrase.

10. The device of claim 7, where at least one of the first phrase or the second phrase does not include at least one of:

a postal code,

a city name, or

a state name.

11. The device of claim 7, where the document is a search query and the processor executes the instructions to:

perform a search of web pages associated with the particular geographic area using the search query.

12. The device of claim 7, where the processor, when determining that the geographic area of the first plurality of geographic areas matches the geographic area of the second plurality of geographic areas, executes the instructions to:

determine that the geographic area of the first plurality of geographic areas matches the geographic area of the second plurality of geographic areas using the generated histogram.

13. A non-transitory computer-readable medium storing instructions, the instructions comprising:

one or more instructions which, when executed by a processor a device, cause the processor to;

receive information identifying a first phrase in a document as being geographically significant, the first phrase being identified as geographically significant based on previous occurrences of the first phrase being determined to be statistically significant to first geographic information;

receive information identifying a second phrase in the document as being geographically significant, the second phrase being identified as geographically significant based on previous occurrences of the second phrase being determined to be statistically significant to second geographic information;

determine that the first phrase is associated with a first plurality of geographic areas;

determine that the second phrase is associated with a second plurality of geographic areas;

determine that a geographic area of the first plurality of geographic areas matches a geographic area of the second plurality of geographic areas;

associate, based on determining that the geographic area of the first plurality of geographic areas matches the geographic area of the second plurality of geographic areas, the document with a particular geographic area, the particular geographic area corresponding to the geographic area of the first plurality of geographic areas and the geographic area of the second plurality of geographic areas;

store information indicating the association of the document with the particular geographic area, the stored information permitting a determination to be made that the document is related to the particular geographic area;

generate, based on located geographic information associated with a phrase in a respective document, a histogram for the phrase; and

store the generated histogram.

14. The non-transitory computer-readable medium of claim 13, where the one or more instructions to determine that the geographic area of the first plurality of geographic areas matches the geographic area of the second plurality of geographic areas include:

one or more instructions to determine that the geographic area of the first plurality of geographic areas matches the geographic area of the second plurality of geographic areas using the generated histogram.

15. The non-transitory computer-readable medium of claim 13, where the one or more instructions to locate the geographic information include:

one or more instructions to locate the geographic information using a pattern matching technique.

16. The non-transitory computer-readable medium of claim 13, where the document is:

a search query, or

a web page.

17. The non-transitory computer-readable medium of claim 13, where the document is a search query and the instructions further include:

one or more instructions to perform a search of documents associated with the particular geographic area using the search query.