System for locating, interpreting and extracting data from documents

1. A method for extracting data from a document, the method comprising:

receiving, at a document input module, a first sample list including a first sample document and a first set of sample data, the first set of sample data having indicia a user desires to have extracted from the first sample document;

assigning, by a locating module, a first signature to the first sample document and a location for every indicia included in the first set of sample data, wherein the location for every indicia included in the first set of sample data is determined without utilizing optical character recognition (OCR);

receiving, at the document input module, a second sample list including a second sample document and a second set of sample data, the second set of sample data having indicia the user desires to have extracted from the second sample document;

assigning, by the locating module, a second signature to the second sample document and a location for every indicia included in the second set of sample data, wherein the location for every indicia included in the second set of sample data is determined without utilizing optical character recognition (OCR);

determining, by a training module, similarities between the first signature and the second signature and similarities between the first set of sample data and the second set of sample data;

generating, by a template module, a template including a third signature based upon the determined similarities between the first signature and the second signature, and similarities between the first set of sample data and the second set of sample data;

receiving, at the document input module, an extraction document in a text format, the extraction document containing a set of extraction data that a user desires to have extracted;

assigning, by the locating module, a fourth signature to the extraction document;

matching, by the training module, the fourth signature to the third signature of the template, wherein the template includes a location for every word or number included in the set of extraction data;

locating, by the locating module, every word or number included in the set of extraction data in the extraction document without utilizing optical character recognition (OCR);

extracting, by an extraction module, every word or number included in the set of extraction data from the extraction document; and

generating, at a computing device, a validation score representing an accuracy of the extracting step after not utilizing OCR to locate every word or number included in the set of extraction data in the extraction document.

2. The method of claim 1 , wherein the fourth signature includes a location for every word or number within the extraction document.

3. The method of claim 1 , wherein every word or number included in the fourth signature is existing in the third signature.

4. The method of claim 3 , wherein the fourth signature has less words or numbers than the third signature.

5. The method of claim 1 , wherein the locating module determines a location of every word or number that comprise the fourth signature and the set of extraction data by absolute or relative positioning.

6. The method of claim 5 , wherein OCR is not utilized to locate the words or numbers that comprise the fourth signature and the set of extraction data.

7. A non-transitory computer-readable medium having stored thereon computer-executable instructions that, when executed by at least one processor of a computer, cause the computer to perform steps comprising:

receiving, at a document input module, a first sample list including a first sample document and a first set of sample data, the first set of sample data having indicia a user desires to have extracted from the first sample document;

assigning, by a locating module, a first signature to the first sample document and a location for every indicia included in the first set of sample data, wherein the location for every indicia included in the first set of sample data is determined without utilizing optical character recognition (OCR);

receiving, at the document input module, a second sample list including a second sample document and a second set of sample data, the second set of sample data having indicia the user desires to have extracted from the second sample document;

assigning, by the locating module, a second signature to the second sample document and a location for every indicia included in the second set of sample data, wherein the location for every indicia included in the second set of sample data is determined without utilizing optical character recognition (OCR);

determining, by a training module, similarities between the first signature and the second signature and similarities between the first set of sample data and the second set of sample data;

generating, by a template module, a template including a third signature based upon the determined similarities between the first signature and the second signature, and similarities between the first set of data and the second set of sample data,

receiving, at the document input module, an extraction document in a text format, the extraction document containing a set of extraction data that a user desires to have extracted;

assigning, by the locating module, a fourth signature to the extraction document;

matching, by the training module, the fourth signature to the third signature of the template wherein the template includes a location for every word or number included in the set of extraction data;

locating, by the locating module, every word or number included in the set of extraction data in the extraction document without utilizing optical character recognition (OCR);

extracting, by an extraction module, every word or number included in the set of extraction data, wherein instructions for locating every word or number included in the set of extraction data are stored within the template; and

generating a validation score representing an accuracy of the extracting step after not utilizing OCR to locate every word or number included in the set of extraction data in the extraction document.

8. The non-transitory computer-readable medium of claim 7 , wherein every word or number included in the set of extraction data includes only the words and numbers the user desires to have extracted.