Forms recognition management system and method

• US 5,394,487 A
• Filed: 10/27/1993
• Issued: 02/28/1995
• Est. Priority Date: 10/27/1993
• Status: Expired due to Fees

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Sun, Hsiao H., Burger, Mark E.
• Primary Examiner(s): Mancuso, Joseph
• Assistant Examiner(s): DEL ROSSO, GERARD DOMNICK
• Application Number:
  US08/141,734
• Time in Patent Office: 489 Days
• Field of Search: 382/61, 382/30, 382/36, 382/37, 382/18
• US Class Current: 382/209
• CPC Class Codes: G06V 30/10 Character recognition
• CPC Class Codes: G06V 30/1444 Selective acquisition, locating or processing of specific regions, e.g. highlighted text, fiducial marks or predetermined fields
• CPC Class Codes: G06V 30/242 Division of the character sequences into groups prior to recognition; Selection of dictionaries

Abstract

Document form templates are grouped into groups of related form templates. The number of times a particular template is used by the system is counted for each group during a forms processing interval. Then when processing submitted forms, the method scans in a plurality of them in an aggregated submission. Forms recognition processing starts for a first form. The method begins searching for a form template to match the first form, starting with the most frequent group. If recognition of the first form is successful with the most frequent primary form template, then the method searches the group for the remaining submitted forms. If recognition of the first form is not successful with the most frequent group, then the method tries to match the first form with a template in the second most frequently processed primary group. In this manner, forms recognition of preprinted forms is managed, with the order of searching the template changed, in response to the frequency with which particular form types are processed.

Claims

1. In a data processing system, a method of aggregated submitted forms recognition where an aggregated submission includes a plurality of mutually related forms included with each submission, comprising the steps of:

providing form templates for recognizing forms in the aggregated submission;

grouping all form templates into groups of related form templates;

counting the number of times the first submitted form of each aggregated submission is matched to a particular group of related form templates during submitted forms processing;

arranging the order of search of groups of related form templates from groups most frequently having a match with the first submitted form of each aggregated submission to those least frequently having a match with the first submitted form of each aggregated submission;

scanning in a plurality of submitted forms in an aggregated submission;

starting a submitted forms recognition process for a first submitted form in the aggregated submission;

searching for a form template to match the first submitted form, starting with the group of related form templates most frequently having a match, and continuing the searching with the other groups of related form templates in the arranged order until a match between the first submitted form and a form template is found;

starting a submitted forms recognition process for a next submitted form in the aggregated submission, after a match has been found in one of said form template groups for the first submitted form;

searching for a form template to match the next submitted form, starting with the group of related form templates where the previous match was found, if a match is not found in the group of related form templates where the previous match was found, the next group of related form templates in the arranged order is searched until a match is found; and

continuing the submitted forms recognition process for the remaining submitted forms in the aggregated submission, as set forth in the previous step.

2. A data processing system to manage aggregated submitted forms recognition, where an aggregated submission includes a plurality of mutually related forms included in with each submission, comprising:

a template archive storage in said system, for storing document form templates in groups of related form templates;

processor means coupled to an input for receiving a plurality of aggregated submission document forms, for counting the number of times the first submitted form of each submission is matched to a particular group of form templates during forms processing;

said processor means coupled to said archive storage, for arranging the order of search of groups of related templates from groups most frequently having a match with the first submitted form of each aggregated submission to those least frequently having a match with the first submitted form of each aggregated submission;

scanning means coupled to said input, for scanning in a plurality of submitted forms in the aggregated submission;

said processor means searching for a form template to match the first submitted form, beginning with the group most frequently having a match and continuing to the next group most frequently having a match in the arranged order until a match between the first submitted form and a form template is found;

said processor means starting a forms recognition process for a next submitted form in the aggregate submission, if recognition of the first form is successful;

said processor means searching for a form template to match the next submitted form, starting with form templates in the group where the previous match was found and continuing with the next group of related form templates most frequently having a match from said template archive storage until a match between the next submitted form and a form template is found; and

said processor means continuing the forms recognition process for the remaining submitted forms in the aggregated submission.

3. A data processing system to manage aggregated submitted forms recognition where an aggregated submission includes a plurality of mutually related submitted forms included with each submission, comprising:

a template archive storage in said system, for storing document form templates in groups of related form templates;

a first processor means coupled to an input for receiving submitted document forms, said processor means counting the number of times the first submitted form of each submission is matched to a particular group of form templates during forms processing;

said first processor means coupled to said archive storage, for arranging the order of search of groups of related templates from groups most frequently having a match with the first submitted form of each aggregated submission to those least frequently having a match with the first submitted form of each aggregated submission;

scanning means coupled to said input, for scanning in a plurality of submitted forms in the aggregated submission;

said first processor means searching for a form template to match the first submitted form, beginning with the group most frequently having a match;

said first processor means transferring the identity of said first submitted form to a second processing means in the system, when recognition of the first form is successful;

said second processor means searching for a form template to match the next submitted form, starting with form templates in the group having a match for said first submitted form and continuing with next group most frequently having a match until a match between the next submitted form and a form template is found; and

said second processor means starting a forms recognition process for a next submitted form in the submission, if recognition of the previous form is successful with the group in which the previous match was found.

4. A data processing system to manage forms recognition, comprising:

a template archive storage in said system, for storing document form templates in groups of related form templates;

a document counting means coupled to an input for receiving submitted document forms, for counting the number of times the first form in plurality of aggregated submissions is matched for each group of related forms templates during forms processing;

a search ordering means coupled to said archive storage, for arranging the order of searching groups of related templates from most frequently having a match with the first form in a plurality of aggregated submissions to those least frequently having a match with the first form in a plurality of aggregated submissions;

a scanning means coupled to said counting means input, for scanning in a plurality of submitted forms in the aggregated submission;

forms recognition means coupled to said scanning means, for starting a forms recognition process for a first form in the submission;

searching means coupled to said search ordering means, for searching for a form template to match the first submitted form, starting with the group most frequently having a match with the first form in a plurality of aggregated submissions and continuing with the next group most frequently having a match in order until a match is found between the first submitted form and a form template;

said forms recognition means starting a forms recognition process for a next submitted form in the aggregate submission, if recognition of the first form is successful;

said searching means searching for a form template to match the next submitted form, starting with form templates in said group having the previous match; and

said forms recognition means continuing the forms recognition process for the remaining submitted forms in the aggregated submission, if recognition of the next submitted form is successful.

5. In a data processing system, a method of aggregated submitted forms recognition where an aggregated submission includes a plurality of mutually related forms included with each submission, comprising the steps of:

a) providing form templates for recognizing forms in the aggregated submission;

b) grouping all form templates into groups of related form templates;

c) scanning in a plurality of submitted forms in an aggregated submission;

d) starting a submitted forms recognition process for a first submitted form in the aggregated submission;

e) searching for a form template to match the first submitted form in the groups of related forms by searching the groups of related forms in a predetermined order until a match between the first submitted form and a form template is found;

f) counting the number of times the first submitted form of each submission is matched to a particular group of related form templates during submitted forms processing;

g) starting a submitted forms recognition process for a next submitted form in the aggregated submission, after a match has been found in one of said form template groups for the first submitted form;

h) searching for a form template to match the next submitted form, starting with form templates in said group of related templates where the previous match was found, if a match is not found in said group of related templates where the previous match was found, the next group of related templates in the arranged order is searched until a match is found;

i) continuing the submitted forms recognition process for remaining submitted forms in the aggregated submission, as set forth in the previous step;

j) periodically arranging the order of search of form template groups from most frequently having a match with the first submitted form of each aggregated submission to those least frequently having a match with the first submitted form of each aggregated submission to create a new predetermined order; and

k) repeating steps c through j.