Forms processing method

• US 10,042,839 B2
• Filed: 11/03/2017
• Issued: 08/07/2018
• Est. Priority Date: 06/21/2016
• Status: Expired due to Fees

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Reddy, Dandala Vinod
• Primary Examiner(s): Bashore, William
• Assistant Examiner(s): Faber, David
• Application Number:
  US15/803,704
• Publication Number:
  US 20180046607A1
• Time in Patent Office: 277 Days
• CPC Class Codes: G06F 40/151 Transformation
• CPC Class Codes: G06F 40/174 Form filling; Merging
• CPC Class Codes: G06F 40/186 Templates
• CPC Class Codes: G06F 40/232 Orthographic correction, e.g. spell checking or vowelisation
• CPC Class Codes: G06F 40/242 Dictionaries
• CPC Class Codes: G16H 15/00 ICT specially adapted for medical reports, e.g. generation or transmission thereof

Abstract

A forms processing method involves accessing an individual scanned form, analyzing the individual form, based upon the analysis, selecting a proper forms-scanning template, loading multiple field-specific dictionaries linked to individual fields in the selected forms-scanning template, analyzing, text content, on a field by field basis using the field-specific dictionary linked to each respective field, for misspellings or improper entries, attempting to identify whether a closest fit between the particular content and contents of the field-specific dictionary linked to that field exists and, if the closest fit exists, automatically replacing the particular content with an entry from the field-specific dictionary linked to that field corresponding to the closest fit.

Claims

1. A computerized forms processing method comprising:

i) accessing an individual scanned form using at least one processor;

ii) analyzing, using the at least one processor, the individual form;

iii) based upon the analysis, selecting a proper forms-scanning template from among multiple selectable forms-scanning templates stored in non-transitory storage, each of the multiple selectable forms-scanning templates

A) being selectable for use with at least one intelligent character recognition (ICR) or intelligent word recognition (IWR) program based upon the analysis of the individual form to be scanned for text conversion using the at least one ICR or IWR program, and

B) having multiple fields, defining specific content areas for filled-in forms to be scanned for graphic content that is to be recognized and converted into text content using the at least one ICR or IWR program;

iv) once the proper forms-scanning template has been selected, loading multiple field-specific dictionaries linked to individual fields in the selected forms-scanning template, each of the field-specific dictionaries being usable by an intelligent analysis module to check for any improper content entry, that is not a misspelling, that is within converted text content located within a content area of a scanned filled-in form document corresponding to the individual fields to which the field-specific dictionaries are linked;

v) analyzing, using the intelligent analysis module, text content converted by the at least one ICR or IWR program and present in the individual fields, on a field by field basis using the field-specific dictionary linked to each respective field, for improper entries;

vi) when analysis of particular content in one of the analyzed fields indicates that particular content therein may be improper, attempting, using the intelligent analysis module, to identify whether a closest fit between the particular content entry that is improper, and contents of the field-specific dictionary linked to that field that would be proper, exists, and

A) if the closest fit exists and a discrepancy between the particular content and the entry is not likely, automatically replacing, using the intelligent analysis module, the particular content with an entry from the field-specific dictionary linked to that field that corresponds to the closest fit.