Decision criteria for automated form population

A method for populating a form comprising:

• capturing an image of a physical document;
• applying optical character recognition to the captured image to identify textual content;
• tagging candidate text segments in the textual content for fields of the form;
• for each of a plurality of the fields of the form, estimating a manual entry time and a manual correction time for the field, wherein the estimated manual entry time is an estimated time period for a user to enter a text segment into the field without automatic population and the estimated manual correction time is an estimated time period for a user to correct a text segment in the field after automatic population;
• and
• automatically populating a field of the form with the tagged candidate text segment if the field is designated as an automatically populated field, otherwise leaving the field blank, the designation of the field depending on the estimated manual entry time and manual correction time and at least one of:
• a text length parameter,
• a predetermined tagging error rate,
• an optical character recognition error rate, and
• a field relevance parameter which has been previously assigned to that field.

An apparatus for populating a form comprising:

• memory which holds instructions for:
• an optical character recognition engine configured to identify textual content in a captured image of a hardcopy document;
• a tagging module which tags candidate text segments in the textual content for population of fields of a form to be populated;
• and
• a field exclusion module which for each of a plurality of fields of the form, designates the field as a manual entry field or an automatically populated field, based on a field exclusion parameter, and automatically populates the fields designated as automatically populated fields, leaving the manually populated fields blank, the field exclusion parameter being a function of a manual entry time and a manual correction time for a respective one of the plurality of fields, and at least one of a predetermined tagging error rate, an optical character recognition error rate, and a field relevance parameter which has been assigned to the field based on whether the field is mandatory or not, wherein the estimated manual entry time is an estimated time period for a user to enter a text segment into the field without automatic population and the estimated manual correction time is an estimated time period for a user to correct a text segment in the field after automatic population;
• and
• a processor which executes the instructions.

A graphical user interface configured to display a form in which fields are automatically designated as manually populated or automatically populated based on:

• a determination of manual correction and manual entry times for the field, wherein the estimated manual entry time is an estimated time period for a user to enter a text segment into the field without automatic population and the estimated manual correction time is an estimated time period for a user to correct a text segment in the field after automatic population,
• average length of content of the field, and
• a relevance of the field;
• the graphical user interface configured for populating those fields designated as automatically populated with candidate text segments derived from a captured image of a document and leaving fields blank that are designated as manually populated.