Systems and methods for extracting pedigree and family relationship information from documents

• US 8,670,618 B2
• Filed: 08/18/2010
• Issued: 03/11/2014
• Est. Priority Date: 08/18/2010
• Status: Active Grant

• Current Assignee: Blue Bulls Incorporated
• Original Assignee: youwho, Inc.
• Inventors: Brummer, Andre, Roylance, Sean
• Primary Examiner(s): Seth, Manav
• Application Number:
  US12/859,120
• Publication Number:
  US 20120045150A1
• Time in Patent Office: 1,301 Days
• Field of Search: None
• US Class Current: 382/190
• CPC Class Codes: G06Q 10/06 Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling

Abstract

A computer-implemented method for extracting information about individuals from a family history document includes applying optical character recognition (OCR) to a digital image of a family history document to create an OCR copy, identifying a person'"'"'s name in the digital image, extracting name data and related information from the OCR copy representing the name, identifying a family relationship indicator corresponding to the identified person'"'"'s name in the digital image, confirming accuracy of the extracted name data, and publishing the extracted name data and related information in a searchable format.

Claims

1. A computer-implemented method for extracting personal information from a family history document, comprising:

applying optical character recognition (OCR) to a digital image of a family history document to create an OCR copy;

identifying a person'"'"'s name in the digital image;

extracting name data from the OCR copy representing the name;

confirming accuracy of the extracted name data;

publishing the extracted name data in a searchable format;

identifying a family relationship indicator corresponding to the identified person'"'"'s name in the digital image, and extracting relationship data from the OCR copy representing the family relationship indicator.

2. The method of claim 1, further comprising identifying at least one of a birth date, a death date, and a marriage date corresponding to the identified person'"'"'s name in the digital image, and extracting data from the OCR copy representing the identified birth date, death date, or marriage date.

3. The method of claim 2, further comprising automatically associating the at least one of a birth date, a death date, and a marriage date with the person'"'"'s name.

4. The method of claim 3, further comprising using predicative algorithms to automatically associate the at least one of a birth date, a death date, and a marriage date with the person'"'"'s name.

5. The method of claim 1, wherein extracting name data includes highlighting the identified name, manually selecting the highlighted name, and mapping to data in the OCR copy representing the identified name.

6. The method of claim 1, further comprising manually correcting incorrect OCR characters from the OCR copy.

7. The method of claim 1, further comprising comparing the person'"'"'s name with a database of names to assess correct spelling of the person'"'"'s name, wherein the names in the database are organized by at least one of a historical time period, a gender, and a location.

8. The method of claim 2, further comprising identifying errors in at least one of the birth date, death date, and marriage date by comparison between at least two of the birth date, death date, and marriage date.

9. A computer-implemented method for extracting personal information from a family history document, comprising:

applying optical character recognition (OCR) to a digital image of a family history document to create an OCR copy;

identifying a person'"'"'s name in the digital image;

extracting name data from the OCR copy representing the name;

confirming accuracy of the extracted name data;

publishing the extracted name data in a searchable format;

identifying at least one of a birth date, a death date, and a marriage date corresponding to the identified person'"'"'s name in the digital image, and extracting data from the OCR copy representing the identified birth date, death date, or marriage date;

identifying errors in at least one of the birth date, death date, and marriage date by comparison between at least two of the birth date, death date, and marriage date.

10. The method of claim 9, further comprising automatically associating the at least one of a birth date, a death date, and a marriage date with the person'"'"'s name.

11. The method of claim 10, further comprising using predicative algorithms to automatically associate the at least one of a birth date, a death date, and a marriage date with the person'"'"'s name.

12. The method of claim 9, wherein extracting name data includes highlighting the identified name, manually selecting the highlighted name, and mapping to data in the OCR copy representing the identified name.

13. The method of claim 9, further comprising manually correcting incorrect OCR characters from the OCR copy.

14. The method of claim 9, further comprising comparing the person'"'"'s name with a database of names to assess correct spelling of the person'"'"'s name, wherein the names in the database are organized by at least one of a historical time period, a gender, and a location.

15. A computer-implemented method for extracting personal information from a family history document, comprising:

applying optical character recognition (OCR) to a digital image of a family history document to create an OCR copy;

identifying a person'"'"'s name in the digital image;

extracting name data from the OCR copy representing the name, wherein extracting name data includes highlighting the identified name, manually selecting the highlighted name, and mapping to data in the OCR copy representing the identified name;

confirming accuracy of the extracted name data;

publishing the extracted name data in a searchable format.

16. The method of claim 15, further comprising identifying at least one of a birth date, a death date, and a marriage date corresponding to the identified person'"'"'s name in the digital image, and extracting data from the OCR copy representing the identified birth date, death date, or marriage date, and automatically associating the at least one of a birth date, a death date, and a marriage date with the person'"'"'s name.

17. The method of claim 16, further comprising using predicative algorithms to automatically associate the at least one of a birth date, a death date, and a marriage date with the person'"'"'s name.

18. The method of claim 15, further comprising manually correcting incorrect OCR characters from the OCR copy.

19. The method of claim 15, further comprising comparing the person'"'"'s name with a database of names to assess correct spelling of the person'"'"'s name, wherein the names in the database are organized by at least one of a historical time period, a gender, and a location.