PROCESSING GEOGRAPHICAL LOCATION DATA IN A DOCUMENT

• US 20120271624A1
• Filed: 10/20/2011
• Published: 10/25/2012
• Est. Priority Date: 10/25/2010
• Status: Active Grant

• Current Assignee: Atreus Labs LLC
• Original Assignee: International Business Machines Corporation
• Inventors: Chen, Jian, Fei, Ben, Ma, Rui, Su, Zhong, Wu, Xian
• Granted Patent: US 8,589,780 B2
• Time in Patent Office: Days
• US Class Current: 704/9
• CPC Class Codes: G09B 29/106 using electronic means

Abstract

Techniques for processing geographical location data in a document comprise: obtaining geographical location data in the document; grading the geographical location data according to a predetermined condition to determine an associated relationship between the geographical location data; marking on an electronic map the associated relationship between the geographical location data; and presenting the marked electronic map.

Claims

1. A method for processing geographical location data in a document, comprising:

obtaining geographical location data in the document;

grading the geographical location data according to a predetermined condition to determine an associated relationship between the geographical location data;

marking on an electronic map the associated relationship between the geographical location data; and

presenting the marked electronic map.

2. The method according to claim 1, further comprising:

disambiguating the obtained geographical location data, including expressing the geographical location data in a uniform manner.

3. The method according to claim 1, wherein the predetermined condition further comprises one or more of the following:

grading according to importance of the geographical location data;

grading according to a cause-effect relation between events represented by the geographical location data; and

grading according to a time sequence between events represented by the geographical location data.

4. The method according to claim 3, wherein

if the predetermined condition is to grade according to importance of the geographical location data, then grading the geographical location data according to a predetermined condition to determine an associated relationship between the geographical location data further comprises:

determining a feature for deciding importance of the geographical location data;

deciding the importance of the geographical location data in the document according to the feature for deciding importance of the geographical location data, wherein the feature comprises one or more of the following;

locations where the geographical location data appear in the document, and times that the geographical location data appear in the document.

5. The method according to claim 3, wherein

if the predetermined condition is to grade according to a cause-effect relation between events represented by the geographical location data, then grading the geographical location data according to a predetermined condition to determine an associated relationship between the geographical location data further comprises:

performing word segmentation on a context where the geographical location data appear according to a grammatical structure;

deciding whether the context comprises words expressing a cause-effect relation between the events represented by the geographical location data based on the word segmentation result; and

determining the cause-effect relation between the events represented by the geographical location data based on the deciding result.

6. The method according to claim 3, wherein

if the predetermined condition is to grade according to a time sequence between events represented by the geographical location data, then grading the geographical location data according to a predetermined condition to determine an associated relationship between the geographical location data further comprises:

performing word segmentation on a context where the geographical location data appear according to a grammatical structure;

deciding whether the context comprises words expressing a time sequence between the events represented by the geographical location data based on the word segmentation result; and

determining the time sequence between the events represented by the geographical location data based on the deciding result.

7. The method according to claim 1, wherein the grading the geographical location data according to a predetermined condition to determine an associated relationship between the geographical location data further comprises:

based on a context where the geographical location data appear, filtering out geographical location data that do not need to be marked.

8. The method according to claim 1, further comprising:

performing specific positioning on the geographical location data, thereby using a fine granularity expression of the geographical location data to represent the geographical location data.

9. The method according to claim 1, further comprising:

determining a preferred level for presenting the marked electronic map, wherein the presenting the marked electronic map further comprises presenting the marked electronic map according to the preferred layer.

10. The method according to claim 1, the marking on the electronic map the geographical location data and their associated relationship further comprises:

marking an associated relationship between the geographical location data with one or more of the following;

a connection line, a contour line, and a verb connecting geographical location data in the document.

11. A system for processing geographical location data in a document, comprising:

geographical location data obtaining means, configured for obtaining geographical location data in the document;

associated relationship determining means, configured for grading the geographical location data according to a predetermined condition to determine an associated relationship between the geographical location data;

marking means, configured for marking on an electronic map the correlation relationship between the geographical location data; and

presenting means, configured for presenting the marked electronic map.

12. The system according to claim 11, further comprising:

disambiguation means, configured for disambiguating the obtained geographical location data, including expressing the geographical location data in a uniform manner.

13. The system according to claim 11, wherein the predetermined condition further comprises one or more of the following:

grading according to importance of the geographical location data;

grading according to a cause-effect relation between events represented by the geographical location data; and

grading according to a time sequence between events represented by the geographical location data.

14. The system according to claim 13, wherein

if the predetermined condition is to grade according to importance of the geographical location data, then the associated relationship determining means further comprises:

importance feature determining means, configured for determining a feature for deciding the importance of the geographical location data; and

importance deciding means, configured for deciding the importance of the geographical location data in the document according to said feature for deciding the importance of the geographical location data, wherein the feature comprises one or more of the following;

locations where the geographical location data appear in the document, and times that the geographical location data appear in the document.

15. The system according to claim 13, wherein

if the predetermined condition is to grade according to a cause-effect relation between events represented by the geographical location data, then the associated relationship determining means further comprises:

grammatical structure analyzing means, configured for performing word segmentation on a context where the geographical location data appear according to a grammatical structure;

cause-effect relation deciding means, configured for deciding whether the context comprises words expressing the cause-effect relation between the events represented by the geographical location data based on the word segmentation result; and

cause-effect relation determining means, configured for determining the cause-effect relation between the events represented by the geographical location data according to the deciding result.

16. The system according to claim 13, wherein

if the predetermined condition is to grade according to a time sequence between events represented by the geographical location data, then the associated relationship determining means further comprises:

grammatical structure analyzing means, configured for performing word segmentation on a context where the geographical location data appear according to a grammatical structure;

time-sequence deciding means, configured for deciding whether the context comprises words expressing the time sequence between the events represented by the geographical location data based on the word segmentation result; and

time sequence determining means, configured for determining a time sequence between the events represented by the geographical location data according to the deciding result.

17. The system according to claim 11, wherein the associated relationship determining means further comprises:

filtering means, configured for filtering out geographical location data that do not need to be marked based on a context where the geographical location data appear.

18. The system according to claim 11, further comprising:

positioning means, configured for performing specific positioning on the geographical location data, thereby using a fine granularity expression of the geographical location data to represent the geographical location data.

19. The system according to claim 12, further comprising:

preferred layer determining means, configured for determining a preferred layer for presenting the marked electronic map, and

the presenting means further presents the marked electronic map according to the preferred layer.

20. The system according to claim 11, the marking means is further configured for marking an associated relationship between the geographical location data with one or more of the following:

a connection line, a contour line, and a verb connecting the geographical location data in the document.

21. An apparatus for processing geographical location data in a document, comprising:

a memory; and

a processor coupled to the memory and configured to;

obtain geographical location data in the document;

grade the geographical location data according to a predetermined condition to determine an associated relationship between the geographical location data;

mark on an electronic map the associated relationship between the geographical location data; and

present the marked electronic map.

22. An article of manufacture for processing geographical location data in a document comprising a computer readable storage medium having tangibly embodied thereon computer readable program code which, when executed, causes a computer to:

obtain geographical location data in the document;

grade the geographical location data according to a predetermined condition to determine an associated relationship between the geographical location data;

mark on an electronic map the associated relationship between the geographical location data; and

present the marked electronic map.