Validation techniques to improve data accuracy

Abstract

An automated method and system for validating (cross-validating) data fields in an electronic document, such as a document that has been passed through an optical character recognition (“OCR”) or Intelligent Document Recognition (“IDR”) system or software, to improve accuracy of the electronic document.

1 - 10 . (canceled) 
     
     
         11 . An automated document-analysis method comprising the steps of:
 automatically selecting a data field in an electronic document;   automatically obtaining a data value and a confidence value of the data field;   automatically identifying an at least one business rule applicable to the data field;   automatically applying the at least one business rule to the data value;   automatically determining a confidence level for the data value based on a result of the business rule applying step; and   adjusting the confidence value of the data field based on the determined confidence level.   
     
     
         12 . The automated document-analysis method of  claim 11 ,
 wherein the at least one business rule is selected from a set of business rules comprising (i) a valid data-range rule; (ii) a valid amount-range rule; (iii) a valid social-security number rule; (iv) a valid address rule; (v) a valid field-range rule; (vi) a valid enumerated-field rule; (vii) a regular-expression rule; (viii) a checkmark rule; and (ix) a mandatory-value rule.   
     
     
         13 . The automated document-analysis method of  claim 11 , wherein the electronic document is a loan-processing document. 
     
     
         14 . An automated document-analysis method comprising the steps of:
 receiving an electronic document comprising a plurality of sections;   classifying the plurality of sections;   for each classified section, applying an at least one of (i) an intra-class rule; and (ii) an inter-class rule;   wherein the intra-class rule comprises an at least one of (i) a single-subclass versioning rule; and (ii) a date versioning rule; and   wherein the inter-class rule comprises an at least one of (i) a versioning-pass rule, and (ii) a-versioning-match rule; and   based on a result of the applying step, for each respective classified section,   performing an at least one of (i) versioning the classified section; (ii) adjusting a data value of a data field in the classified section; and (iii) adjusting a confidence value of a data field of the classified section.   
     
     
         15 . The automated document-analysis method of  claim 14 , wherein the single-subclass versioning rule comprises identifying a classified section comprising a single subsection. 
     
     
         16 . The automated document-analysis method of  claim 14 , wherein the date-versioning rule comprises:
 identifying a classified section comprising a plurality of subsections, wherein the classified section belongs to a class of sections that comprises a date field; and   analyzing a data value of the date field in each subsection of the plurality of subsections.   
     
     
         17 . The automated document-analysis method of  claim 16 , wherein the date-versioning rule further comprises
 using a predetermined data field in the classified section to separate the plurality of subsection into a first subsection-category and a second subsection-category,   wherein the step of analyzing a data value of the date field in each subsection of the plurality of subsections includes separately analyzing a data value of the date field in each of the first subsection-category and the second subsection-category.   
     
     
         18 . The automated document-analysis method of  claim 14 , wherein the versioning-pass rule comprises:
 selecting, from the plurality of sections, a first classified section and a second classified section;   identifying a final-version subsection of the first classified section;   identifying a final-version subsection of the second classified section; and   comparing a data value of a data field in the final-version subsection of the first classified section to a data value in a data field in the final-version subsection of the second classified section.   
     
     
         19 . The automated document-analysis method of  claim 14 , wherein the versioning-match rule comprises:
 selecting, from the plurality of sections, a first classified section and a second classified section;   identifying a final-version subsection of the first classified section;   identifying a set of subsections of the second classified section; and   for each subsection in the set of subsections of the second classified section,   comparing a data value of a data field in the subsection to a data value of a data field in the final-version subsection.   
     
     
         20 . The automated document-analysis method of  claim 14 , wherein the electronic document is a loan-processing document. 
     
     
         21 . An automated document-analysis method comprising the steps of:
 receiving an electronic document comprising a plurality of sections;   receiving a corresponding pre-classification value for each section of the plurality of sections;   classifying the electronic document, such that a corresponding classification value is determined for each section of the plurality of sections;   comparing the corresponding pre-qualification value for at least one section of the plurality of sections against the determined corresponding classification value for the section;   if the corresponding pre-qualification value does not match the determined corresponding classification value, performing an at least one of (i) identifying the section as mis-classified; (ii) designating the section for a manual review; and (iii) designating the section for an automated review.   
     
     
         22 . The automated document-analysis method of  claim 21 , wherein the electronic document is a loan-processing document. 
     
     
         23 - 26 . (canceled)