Business Method Using The Automated Processing of Paper and Unstructured Electronic Documents

• US 20070118391A1
• Filed: 10/24/2006
• Published: 05/24/2007
• Est. Priority Date: 10/24/2005
• Status: Active Grant

• Current Assignee: ICE Mortgage Technology, Inc. (Intercontinental Exchange, Inc.)
• Original Assignee: Capsilon FSG Incorporated
• Inventors: Malaney, Vikram, Kulkarni, Parag, Malaney, Sanjeev, Viswanathan, Krishnawami
• Granted Patent: US 7,747,495 B2
• Time in Patent Office: Days
• US Class Current: 382/229
• CPC Class Codes: G06Q 10/00 Administration; Management
• CPC Class Codes: G06Q 40/00 Finance; Insurance; Tax strategies; Processing of corporate or income taxes
• CPC Class Codes: G06Q 40/02 Banking, e.g. interest calculation or account maintenance credit or loans G06Q40/03
• CPC Class Codes: G06Q 50/18 Legal services

Abstract

The invention features a business method that takes advantage of the ability to convert unorganized information in the form of paper documents, document images, and electronic documents arid converts the information to an organized electronic form referred to as Knowledge Objects. The invention further encompasses forming electronic Business Objects, such as documents and data sets, useful for business decision making and information exchange. The methods of the invention may utilize computerized storage and computerized decision-making systems to enable making more rapid critical business decisions.

Claims

1. A method of doing business by processing a group of Dox Packages from the mortgage industry wherein each Dox Package has at least two pages wherein minimal human intervention is involved.

4. The method of claim 1, wherein said step of performing optical character recognition is performed by, or with the assistance of, a computer.

5. The method of claim 1, wherein said step of classifying is performed by, or with the assistance of, a computer.

6. The method of claim 5, wherein said step of classifying is performed by Image Based Classification.

7. The method of claim 1, wherein said step of verifying is performed by, or with the assistance of, a computer.

8. The method of claim 1, wherein said step of collating is performed by, or with the assistance of, a computer.

9. The method of claim 1, wherein said step of versioning and sequencing is performed by, or with the assistance of, a computer.

10. The method of claim 1, wherein said step of extracting data is performed by, or with the assistance of, a computer.

11. The method of claim 1, wherein said step of scrubbing is performed by, or with the assistance of, a computer.

12. The method of claim 1, wherein said step of formation of Knowledge Object is performed by, or with the assistance of, a computer.

13. The method of claim 1, wherein said step of outputting is performed by, or with the assistance of, a computer.

14. The method of claim 1, wherein said step of formation of Business Object is performed by, or with the assistance of, a computer.

15. The method of claim 1, wherein said step of displaying is performed by, or with the assistance of, a computer.

16. The method of claim 1, wherein ambiguities at any step are escalated to a human operator.

17. The method of any of claim 1, wherein an ambiguity in a classification step, a field location step, or a data extraction step are escalated to a human collaborator.

18. The method of any of claims 2-16, wherein said group of documents is a group of mortgage loan documents.

2. A method of doing business by processing a group of Dox Packages from the mortgage industry wherein each Dox Package has at least two pages wherein the information is extracted from the Dox Packages and organized ten times as fast as a human operator.

3. A method of doing business by processing a group of documents comprising the steps of:

(1) performing optical character recognition from said discrete documents using said device to generate one or more sets of text-based information;

(2) classifying at least some of said discrete documents using said sets of text-based information, wherein multiple classification engines are employed and said classifying is based on a consensus of said classification engines;

(3) classifying at least some of the discrete documents using Image Based Classification;

(4) verifying any of said remaining discrete documents that are not classified in said steps of classifying by employing a Location Diagram with said remaining discrete documents or a portion thereof;

(5) collating said at least two of said discrete documents;

(6) versioning and sequencing at least two of said discrete documents;

(7) locating said fields containing data in said at least two of said discrete documents;

(8) extracting data from said fields of said at least two discrete documents to generate extracted data;

(9) scrubbing values from said extracted data to generate values therefrom;

(10) forming Knowledge Objects;

(11) storing said values in a data storage device;

(12) forming Business Objects;

(13) displaying at least some of said values to a user.