Geocoding multi-feature addresses

• US 8,150,848 B2
• Filed: 01/04/2008
• Issued: 04/03/2012
• Est. Priority Date: 01/04/2008
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Gupta, Apurv, Khot, Tushar
• Primary Examiner(s): Xue, Belinda
• Application Number:
  US11/969,510
• Publication Number:
  US 20090177643A1
• Time in Patent Office: 1,551 Days
• Field of Search: None
• US Class Current: 707/736
• CPC Class Codes: G06F 16/29 Geographical information databases
• CPC Class Codes: G06F 40/20 Natural language analysis semantic analysis of natural language G06F40/30
• CPC Class Codes: Y10S 707/918 Location
• CPC Class Codes: Y10S 707/919 Geographic
• CPC Class Codes: Y10S 707/921 Spatial

Abstract

A system and method of parsing natural language descriptions of features to determine an approximate location. An embodiment includes splitting the natural language descriptions into components, geocoding each component, and returning the geocode with the highest confidence level. The geocode references a specific location, and this information may be determined by content from a variety of sources. The system may use an assortment of techniques for determining highest confidence level.

Claims

1. A method of geocoding a multi-feature address, comprising:

(a) receiving an address term comprising a region and two or more features;

(b) splitting the address term into the region, at least a first feature and second feature, and at least one or more delimiters, wherein a start or an end of each feature is determined by the one or more of the delimiters, and wherein the first feature includes two or more components, and the second feature includes one or more components;

for each component of each feature in the address term;

(c) determining at least one geocode based on the splitted region and the component, wherein two or more geocodes are determined for at least one component of the first feature,

(d) determining a component confidence score inversely related to a number of geocodes determined in (c) for the component, and

(e) determining a component geocode representing a location of the component based on the at least one geocode determined in (c);

(f) for each feature in the address term, selecting a feature geocode representing a location of the feature as the component geocode determined in (e) having a greatest corresponding component confidence score determined in (d); and

(g) determining an address geocode based on every feature geocode selected in (f), wherein steps (a)-(g) are each performed on at least one computing device.

2. The method of claim 1, wherein the determining (c) comprises:

generating geographical coordinate information that includes latitude and longitude values.

3. The method of claim 2, wherein the generating geographical coordinate information comprises:

selecting the geographical coordinate information from a geocode database.

4. The method of claim 2, wherein the generating geographical coordinate information comprises:

selecting the geographical coordinate information from a publicly available user created geocode database.

5. The method of claim 1, wherein the determining (e) comprises:

determining the component geocode as a centroid of the geocodes in (c).

6. The method of claim 1, wherein the determining (g) comprises:

determining the address geocode as a centroid of the feature geocodes in (f).

7. The method of claim 1, wherein each of the one or more delimiters includes one of a word, a punctuation character, or a blank space.

8. A system of geocoding a multi-feature address, comprising:

an address parser, configured to receive an address term comprising a region and two or more features, and split the address term into the region, at least a first feature and second feature, and at least one or more delimiters, wherein a start or an end of each feature is determined by the one or more of the delimiters, and wherein the first feature includes two or more components, and the second feature includes one or more components;

a geocoder configured, for each component of each feature in the address term;

to determine at least one geocode based on the splitted region and the component, wherein two or more geocodes are determined for at least one component of the first feature,

to determine a component confidence score inversely related to a number of geocodes for the component, and

to determine a component geocode representing a location of the component based on the at least one geocode;

a geocode confidence analyzer configured, for each feature in the address term, to select a feature geocode representing a location of the feature as the component geocode having a greatest corresponding component confidence score; and

a highest confidence geocode intersector configured to determine an address geocode based on the feature geocodes determined by the geocode confidence analyzer,

wherein the address parser, geocoder, geocode confidence analyzer, and highest confidence geocode intersector are implemented on at least one computing device.

9. The system of claim 8, wherein the geocoder generates geographical coordinate information that includes latitude and longitude values.

10. The system of claim 9, further comprising:

a geocode database,

wherein the geocoder selects the geographical coordinate information from the geocode database.

11. The system of claim 9, further comprising:

a publicly available user created geocode database;

wherein the geocoder selects the geographical coordinate information from a publicly available user created geocode database.

12. The system of claim 8, the geocoder determines the component geocode as a centroid of the geocodes determined by the geocoder for the component.

13. The system of claim 8, the highest confidence geocode intersector determines the address geocode as a centroid of the feature geocodes by the geocode confidence analyzer.

14. The system of claim 8, wherein each of the one or more delimiters includes one of a word, a punctuation character, or a blank space.