Method and system for determining correlated geographic areas

• US 8,732,219 B1
• Filed: 08/22/2011
• Issued: 05/20/2014
• Est. Priority Date: 08/25/2010
• Status: Active Grant

• Current Assignee: United Services Automobile Association
• Original Assignee: United Services Automobile Association
• Inventors: Ferries, John Robert Thomas, Bueche, Michael Patrick Jr., Young, Barrington R.
• Primary Examiner(s): GIRMA, ANTENEH B
• Application Number:
  US13/215,022
• Time in Patent Office: 1,002 Days
• Field of Search: None
• US Class Current: 707/825
• CPC Class Codes: G06F 16/24578 using ranking
• CPC Class Codes: G06F 16/29 Geographical information databases
• CPC Class Codes: G06F 16/444 Spatial browsing, e.g. 2D maps, 3D or virtual spaces
• CPC Class Codes: G06F 16/50 of still image data
• CPC Class Codes: G06F 16/56 having vectorial format
• CPC Class Codes: G06F 16/583 using metadata automatically derived from the content
• CPC Class Codes: G06F 16/5838 using colour
• CPC Class Codes: G06Q 50/01 Social networking

Abstract

A method of determining a geographic area having similar characteristics to a first geographic area associated with a user includes receiving a plurality of inputs related to characteristics of a plurality of geographic areas and constructing a feature vector for each of the geographic areas based on the plurality of inputs. The method also includes receiving a plurality of inputs related to characteristics of the first geographic area and constructing a feature vector for the first geographic area associated with the user. The method further includes receiving an input from the user related to a city of interest, comparing the feature vector for the first geographic area to feature vectors associated with geographic areas located in or adjacent to the city of interest, and ranking the geographic areas located in or adjacent to the city of interest using the comparing step.

Claims

1. A method of suggesting a new neighborhood to a user using information related to the user'"'"'s previous neighborhoods, the method comprising:

computing a timeline feature vector for each of the user'"'"'s previous neighborhoods, each of the user'"'"'s previous neighborhoods having a plurality of characteristics associated therewith, wherein the timeline feature vector is calculated using the plurality of characteristics associated with each of the user'"'"'s previous neighborhoods;

determining a combination timeline feature vector using one or more of the timeline feature vectors, wherein the combination timeline feature vector is predictive of the user'"'"'s preference for the new neighborhood using the information related to the user'"'"'s previous neighborhoods;

receiving an input from the user related to a city of interest;

retrieving a plurality of feature vectors from a database storing feature vectors associated with neighborhoods located in or adjacent to the city of interest;

comparing the combination timeline feature vector with each of the plurality of feature vectors; and

determining one or more of the neighborhoods located in or adjacent to the city of interest defined by a minimum distance between the combination timeline feature vector and one of the plurality of feature vectors.

2. The method of claim 1 further comprising adjusting the combination timeline feature vector using user input prior to comparing the combination timeline feature vector with the plurality of feature vectors.

3. The method of claim 1 further comprising prioritizing the user'"'"'s previous neighborhoods using the user'"'"'s preference and weighing the one or more timeline feature vectors according to the user'"'"'s preference in calculating the combination timeline feature vector.

4. The method of claim 1 further comprising ranking the one or more neighborhoods located in or adjacent to the city of interest by increasing distance between the combination timeline feature vector and the plurality of feature vectors.

5. The method of claim 1 further comprising:

displaying the one or more of the neighborhoods located in or adjacent to the city of interest to the user;

receiving a selection, from the user, of a desired neighborhood having a desired feature vector from the one or more of the neighborhoods located in or adjacent to the city of interest;

computing a difference between at least one of the timeline feature vectors of the previous neighborhoods and the desired feature vector associated with the desired neighborhood; and

displaying the difference to the user.

6. The method of claim 5 wherein displaying the difference comprises displaying a cost differential between a similar home in the selected desired neighborhood and at least one of the user'"'"'s previous neighborhoods.

7. The method of claim 2 wherein the user input includes defining a boundary for each of the user'"'"'s previous neighborhoods prior to computing the timeline feature vector for the each of the user'"'"'s previous neighborhoods.

8. A method of suggesting a new neighborhood to a user, the method comprising:

computing a current feature vector for a current neighborhood in or adjacent to a current city, wherein the current feature vector is calculated using a plurality of characteristics of the current neighborhood and wherein the current neighborhood has a selected characteristic and the current city has a corresponding selected characteristic;

calculating a first percent difference between a mean value of the selected characteristic associated the current neighborhood and a mean value of the corresponding selected characteristic associated with the current city;

receiving an input from the user related to a city of interest;

retrieving a plurality of feature vectors from a database storing feature vectors associated with neighborhoods located in or adjacent to the city of interest, wherein each of the neighborhoods has the selected characteristic and the city of interest has the corresponding selected characteristic;

comparing the current feature vector with each of the plurality of feature vectors;

calculating a second percent difference between a mean value of the selected characteristic associated each of the neighborhoods located in or adjacent to the city of interest and a mean value of the corresponding selected characteristic associated with the city of interest; and

determining one or more of the neighborhoods located in or adjacent to the city of interest characterized by;

a minimum difference between the current feature vector and each of the plurality of feature vectors; and

the first percent difference being similar to the second percent difference.

9. The method of claim 8 wherein the selected characteristic is a home price.

10. The method of claim 8 wherein the selected characteristic is a school ranking or a crime rate.

11. The method of claim 8 further comprising adjusting the current feature vector using user input prior to comparing the current feature vector with the plurality of feature vectors.

12. The method of claim 11 wherein the user input includes defining a boundary for the current neighborhood prior to computing the current feature vector.

13. The method of claim 8 further comprising:

displaying the one or more of the neighborhoods located in or adjacent to the city of interest to the user;

receiving a selection, from the user, of a desired neighborhoods having a desired feature vector from the one or more of the neighborhoods in or adjacent to the city of interest;

computing a difference between the current feature vector and the desired feature vector associated with the selected desired neighborhood; and

displaying the difference to the user.

14. The method of claim 13 wherein displaying the difference comprises displaying a cost differential between a similar home in the current neighborhood and the desired neighborhood.