Property record document data verification systems and methods

• US 9,639,751 B2
• Filed: 06/30/2015
• Issued: 05/02/2017
• Est. Priority Date: 03/17/2006
• Status: Active Grant

• Current Assignee: First American Financial Corporation
• Original Assignee: First American Financial Corporation
• Inventors: Newcomer, Daniel A., Seely, Jon Scott, Branham, Dennis Lee, Kosan, Paul
• Primary Examiner(s): HU, FRED H.
• Application Number:
  US14/788,380
• Publication Number:
  US 20150379346A1
• Time in Patent Office: 672 Days
• Field of Search: None
• CPC Class Codes: G06F 16/23 Updating
• CPC Class Codes: G06F 16/5866 using information manually generated, e.g. tags, keywords, comments, manually generated location and time information
• CPC Class Codes: G06F 16/93 Document management systems
• CPC Class Codes: G06V 30/416 Extracting the logical structure, e.g. chapters, sections or page numbers; Identifying elements of the document, e.g. authors
• CPC Class Codes: G06V 30/418 Document matching, e.g. of document images

Abstract

A data verification system is configured to verify machine-recognized data elements acquired during a machine-implemented data acquisition process. The system includes a data verification workstation, an image server, and a data entry server. The data verification workstation is configured to obtain document images from the image server, present portions of document images to an operator, wherein the document images include text, and receive input from the operator based on the text. The input includes data elements. The data verification workstation is also configured to acquire machine-recognized data elements from the data entry server. The machine-recognized data elements were acquired from the document image during a machine-implemented data acquisition process based on the text. The data verification workstation is also configured to compare the data elements received from the operator to the machine-recognized data elements and selectively prompt the operator to re-input the data elements based on the comparison.

Claims

1. A system comprising:

one or more processors;

one or more non-transitory computer-readable mediums operatively coupled to the one or more processors, and having instructions stored thereon, that when executed by the one or more processors cause a computing device to;

receive a document image file of a property record comprising one or more images;

recognize a document title in the document image file;

determine a document type of the property record based on the document title;

recognize other data strings in the document image file;

identify from the other data strings validation candidate data strings for validation based on the determined document type and a set of rules;

search a validation server for target data strings that were extracted from at least one property document that precedes the property record;

compare the validation candidate data strings and the target data strings to determine a validation score for each of the validation candidate data strings, wherein each of the validation scores indicates a confidence that a respective validation candidate data string was correctly recognized.

2. The system of claim 1, wherein the instructions are further configured to cause the computing device to:

verify that a first validation candidate data string is valid if the first validation candidate data string'"'"'s respective validation score exceeds a first predetermined threshold; and

verify that a second validation candidate data string is valid if the second validation candidate data string'"'"'s respective validation score exceeds the first predetermined threshold.

3. The system of claim 2, wherein the instructions are further configured to cause the computing device to:

store the first validation candidate data string and a location for the first validation candidate data string, wherein the location specifies where the first validation candidate data string is located in the document image file; and

display a portion of the document image file corresponding to the stored location for operator verification if the validation score of the first validation candidate data string falls below the first predetermined threshold and exceeds a second predetermined threshold.

4. The system of claim 1, wherein the first set of rules used to identify the validation candidate data strings for validation are applicable in a hierarchical fashion according to a state, a county, or a recording jurisdiction associated with the property record.

5. The system of claim 1, wherein the validation title data strings comprise a plurality of selections from a group comprising:

a grantor name, a grantee name, a property address, a property legal description, and a transfer date.

6. The system of claim 1, wherein the instructions are further configured to cause the computing device to:

verify that a first validation candidate data string is valid based on the first validation candidate data string'"'"'s respective validation score;

dynamically update the set of rules based on the verification; and

identify an additional validation candidate data string for validation based on the updated set of rules.

7. The system of claim 6, wherein the first validation candidate data string comprises a condominium name, and wherein the additional validation candidate data string comprises a unit number associated with the condominium.

8. The system of claim 1, wherein searching the validation server comprises searching for the target data strings based on the first set of rules, wherein the first set of rules are based on a recording jurisdiction associated with the property record.

9. The system of claim 1, wherein the instructions are further configured to cause the computing device to:

validate each of the scored validation candidate data strings; and

store the validated validation candidate data strings in the validation server for use in future validation processes.

10. A computer-implemented method, comprising:

receiving a document image file of a property record comprising one or more images;

recognizing a document title in the document image file;

determining a document type of the property record based on the document title;

recognizing other data strings in the document image file;

identifying from the other data strings validation candidate data strings for validation based on the determined document type and a set of rules;

searching a validation server for target data strings that were extracted from at least one property document that precedes the property record;

comparing the validation candidate data strings and the target data strings to determine a validation score for each of the validation candidate data strings, wherein each of the validation scores indicates a confidence that a respective validation candidate data string was correctly recognized.

11. The method of claim 10, further comprising:

verifying that a first validation candidate data string is valid if the first validation candidate data string'"'"'s respective validation score exceeds a first predetermined threshold; and

verifying that a second validation candidate data string is valid if the second validation candidate data string'"'"'s respective validation score exceeds the first predetermined threshold.

12. The method of claim 11, further comprising:

storing the first validation candidate data string and a location for the first validation candidate data string, wherein the location specifies where the first validation candidate data string is located in the document image file; and

displaying a portion of the document image file corresponding to the stored location for operator verification if the validation score of the first validation candidate data string falls below the first predetermined threshold and exceeds a second predetermined threshold.

13. The method of claim 10, wherein the first set of rules used to identify the validation candidate data strings for validation are applicable in a hierarchical fashion according to a state, a county, or a recording jurisdiction associated with the property record.

14. The method of claim 10, wherein the validation title data strings comprise a plurality of selections from a group comprising:

a grantor name, a grantee name, a property address, a property legal description, and a transfer date.

15. The method of claim 10, further comprising:

verify that a first validation candidate data string is valid based on the first validation candidate data string'"'"'s respective validation score;

dynamically update the set of rules based on the verification; and

identify an additional validation candidate data string for validation based on the updated set of rules.

16. The method of claim 15, wherein the first validation candidate data string comprises a condominium name, and wherein the additional validation candidate data string comprises a unit number associated with the condominium.

17. The method of claim 10, wherein searching the validation server comprises searching for the target data strings based on the first set of rules, wherein the first set of rules are based on a recording jurisdiction associated with the property record.

18. The method of claim 10, further comprising:

validating each of the scored validation candidate data strings; and

storing the validated validation candidate data strings in the validation server for use in future validation processes.

19. A system comprising:

a validation server; and

a computing device configured to;

receive a document image file of a property record comprising one or more images;

recognize a document title in the document image file;

determine a document type of the property record based on the document title;

recognize other data strings in the document image file;

identify from the other data strings validation candidate data strings for validation based on the determined document type and a set of rules;

search the validation server for target data strings that were extracted from at least one property document that precedes the property record;

compare the validation candidate data strings and the target data strings to determine a validation score for each of the validation candidate data strings, wherein each of the validation scores indicates a confidence that a respective validation candidate data string was correctly recognized.

20. The system of claim 19, wherein the computing device is further configured to:

verify that a first validation candidate data string is valid based on the first validation candidate data string'"'"'s respective validation score;

dynamically update the set of rules based on the verification; and

identify an additional validation candidate data string for validation based on the updated set of rules.