Spatial data analysis apparatus and spatial data analysis method

• US 7,139,770 B2
• Filed: 03/06/2003
• Issued: 11/21/2006
• Est. Priority Date: 03/06/2002
• Status: Expired due to Fees

• Current Assignee: Kabushiki Kaisha Toshiba (Toshiba Corporation)
• Original Assignee: Kabushiki Kaisha Toshiba (Toshiba Corporation)
• Inventors: Hatano, Hisaaki, Nakase, Akihiko
• Primary Examiner(s): Mizrahi, Diane D.
• Application Number:
  US10/379,919
• Publication Number:
  US 20030187875A1
• Time in Patent Office: 1,356 Days
• Field of Search: 707/104.1, 715/854
• US Class Current: 707/812
• CPC Class Codes: G06F 17/18 for evaluating statistical data , e.g. average values, frequency distributions, probability functions, regression analysis forecasting specially adapted for a specific administrative, business or logistic context G06Q10/04
• CPC Class Codes: Y10S 707/921 Spatial
• CPC Class Codes: Y10S 707/957 Multidimensional
• CPC Class Codes: Y10S 707/99943 Generating database or data structure, e.g. via user interface

Abstract

A spatial data analysis apparatus includes a storage configured to store a record group of records each including a multi-dimensional spatial attribute containing a place and a description attribute regarding the spatial attribute; a divider configured to divide the record group into a plurality of virtual record groups corresponding to a plurality of places according to each of a plurality of conditions determined by the description attribute; a calculator configured to calculate a degree of spatial dispersion of records of each of the plurality of virtual record groups in the places to obtain a plurality of degrees of dispersion; and a selector configured to select from the conditions a condition corresponding to a virtual record group that indicates a lowest degree of dispersion among the degrees of dispersion. The divider re-divides the virtual record group into a plurality of re-divided virtual record groups, and the calculator computes a degree of spatial dispersion of records of each of the re-divided virtual record groups that are recursively generated by re-dividing recursively the virtual record group with the divider, to make a tree structure for determining a final division condition and a final virtual record group.

Claims

1. A spatial data analysis apparatus comprising:

a storage configured to store a record group of records each including a multi-dimensional spatial attribute containing a place and a description attribute regarding the spatial attribute;

a divider configured to divide the record group into a plurality of virtual record groups corresponding to a plurality of places according to each of a plurality of conditions determined by the description attribute;

a calculator configured to calculate a degree of spatial dispersion of records of each of the plurality of virtual record groups in the places to obtain a plurality of degrees of dispersion; and

a selector configured to select from the conditions a condition corresponding to a virtual record group that indicates a lowest degree of dispersion among the degrees of dispersion, and wherein

the divider re-divides the virtual record group into a plurality of re-divided virtual record groups; and

the calculator computes a degree of spatial dispersion of records of each of the re-divided virtual record groups that are recursively generated by re-dividing recursively the virtual record group with the divider, to make a tree structure for determining a final division condition and a final virtual record group.

2. The spatial data analysis apparatus according to claim 1, which further includes a storage configured to store the selected condition and a history of the virtual record group, and a temporary storage configured to store temporarily the virtual record group.

3. The spatial data analysis apparatus according to claim 1, wherein the divider is configured to re-divide the virtual record group selected by the selector to generate a plurality of re-divided record groups, and the calculator calculates a degree of spatial dispersion of records of each of the plurality of re-divided record groups to obtain a plurality of degrees of re-dispersion and determine a re-division condition and a re-divided record group that indicate a lowest degree of dispersion among the plurality of degrees of re-dispersion.

4. The spatial data analysis apparatus according to claim 1, wherein the degree of spatial dispersion is determined by the sum of values each obtained by square of a distance between a center of gravity of a group of all records and a center of gravity of each of the records.

5. A computer-implanted spatial data analysis method comprising:

storing in a storage a record group of records each including a multi-dimensional spatial attribute containing a place and a description attribute regarding the spatial attribute;

dividing the record group into a plurality of virtual record groups corresponding to a plurality of places according to each of a plurality of conditions determined by the description attribute;

computing a degree of spatial dispersion of records of each of the plurality of virtual record groups in the places to obtain a plurality of degrees of dispersion;

selecting from the conditions a condition corresponding to a virtual record group that indicates a lowest degree of dispersion among the degrees of dispersion;

re-dividing the virtual record group into a plurality of re-divided virtual record groups; and

computing with said computer a degree of spatial dispersion of records of each of the re-divided virtual record groups that are recursively generated, to make a tree structure for determining a final division condition and a final virtual record group.

6. The spatial data analysis method according to claim 5, wherein the multi-dimensional attribute is a two-dimensional spatial attribute.

7. The spatial data analysis method according to claim 5, wherein the spatial attribute includes two-dimensional coordinates and the description attribute includes a condition.

8. The spatial data analysis method according to claim 5, which further includes storing the selected condition and a history of the virtual record group in a storage unit, and storing temporarily the virtual record group in a temporary storage unit.

9. The spatial data analysis method according to claim 5, wherein dividing the record group includes re-dividing virtually the selected virtual record group into a plurality of re-divided record groups, and calculating the degree of spatial dispersion includes calculating a degree of spatial dispersion of records of each of the plurality of re-divided record groups to obtain a plurality of degrees of re-dispersion and determining a re-division condition and a re-divided record group that indicate a lowest degree of dispersion among the plurality of degrees of re-dispersion.

10. The spatial data analysis method according to claim 5, wherein the degree of spatial dispersion is determined by the sum of values each obtained by square of a distance between a center of gravity of a group of all records and a center of gravity of each of the records.

11. A computer readable storage medium storing a spatial data analysis program which when executed by a computer causes the computer to perform steps comprising:

storing in a storage a record group of records each including a multi-dimensional spatial attribute containing a place and a description attribute regarding the spatial attribute;

dividing the record group into a plurality of virtual record groups corresponding to a plurality of places according to each of a plurality of conditions determined by the description attribute;

dividing a degree of spatial dispersion of records of each of the plurality of virtual record groups in the places to obtain a plurality of degrees of dispersion;

select selecting from the conditions a condition corresponding to a virtual record group that indicate a lowest degree of dispersion among the plurality of degrees of spatial dispersion;

dividing virtually the selected virtual record group into a plurality of re-divided virtual record groups; and

computing a degree of spatial dispersion of records of each of the re-divided virtual record groups that are recursively generated, to make a tree structure for determining a final division condition and a final virtual record group.

12. The computer readable medium according to claim 11, wherein the spatial data analysis program when executed by a computer causes the computer to perform further steps storing the selected condition and a history of the virtual record group in a storage unit, and storing temporarily the virtual record group in a temporary storage unit.

13. The computer readable medium according to claim 11, wherein the spatial data analysis program when executed by the computer causes the computer to perform further steps comprising determining the degree of dispersion by the sum of values each obtained by square of a distance between a center of gravity of a group of all records and a center of gravity of each of the records.

14. The computer readable medium according to claim 11, wherein the multi-dimensional spatial attribute is a two-dimensional spatial attribute.

15. The computer readable medium according to claim 11, wherein the spatial attribute indicates two-dimensional coordinates and the description attribute indicates a condition.