Recognition and population of form fields in an electronic document

• US 10,223,344 B2
• Filed: 01/26/2015
• Issued: 03/05/2019
• Est. Priority Date: 01/26/2015
• Status: Active Grant

• Current Assignee: Adobe Inc.
• Original Assignee: Adobe Inc.
• Inventors: Dakin, Steve, Gaither, Shawn, Swineford, Randy, Thevenet, Frederic, Sherry, David Rudi
• Primary Examiner(s): Zuberi, Mohammed H
• Application Number:
  US14/605,475
• Publication Number:
  US 20160217119A1
• Time in Patent Office: 1,499 Days
• CPC Class Codes: G06F 40/174 Form filling; Merging
• CPC Class Codes: G06F 40/274 Converting codes to words; Guess-ahead of partial word inputs

Abstract

Techniques are disclosed for identifying and populating static form fields using prior responses to similar form fields. An example method includes receiving an electronic form having, encoded in the form, static text and a static form field for containing information specific to a given user of the electronic form. Using an image recognition algorithm, a fillable form field candidate is identified based on a graphical representation of the static form field. An attribute of the fillable form field candidate can be identified based on the static text. A suggested response for populating the fillable form field candidate is selected from prior responses to other form fields having at least one attribute in common with the identified attribute of the fillable form field candidate. The prior responses are inputs obtained from or associated with the given user. The suggested response is presented to the user for subsequent acceptance or rejection.

Claims

1. In a digital medium environment for processing electronic forms, a computer-implemented method for identifying fillable form field candidates and populating fillable form field candidates using prior responses to similar form fields or other user-specific information, the method comprising:

receiving an electronic form having, encoded in the form, static text and a static form field for containing information specific to a given user of the electronic form;

identifying, using an image recognition algorithm, a fillable form field candidate that corresponds to the static form field, wherein the identifying is based on a meaning of the static text corresponding to the static form field;

identifying an attribute of the fillable form field candidate based on the static text;

selecting a suggested response from a ranked set of suggested responses for populating the fillable form field candidate, the ranked set of suggested responses including user-specific information obtained from the given user and based on at least one of;

a plurality of prior responses to other form fields having at least one attribute in common with the identified attribute of the fillable form field candidate, and a context associated with the identified attribute; and

presenting, via a graphical user interface, the suggested response for subsequent acceptance or rejection by the given user.

2. The method of claim 1, wherein the suggested response is selected and presented to the user without a user input that selects any region of the electronic form.

3. The method of claim 1, further comprising identifying, using at least one of content encoded in the electronic form and optical character recognition of the electronic form:

a location of the fillable form field candidate within the electronic form; and

a type of the fillable form field candidate, the type including one of a text field, a signature block, a radio button, and a check box,

wherein the suggested response corresponds to the identified type of the fillable form field candidate.

4. The method of claim 1, further comprising presenting, via the graphical user interface and in response to receiving a user input rejecting the suggested response, at least one alternative suggested response from among the ranked set of suggested responses.

5. The method of claim 1, further comprising generating a word-based label that describes the attribute of the fillable form field candidate, wherein the selecting of the suggested response includes matching at least a portion of the word-based label to another word-based label associated with the other form fields.

6. The method of claim 1, further comprising calculating a weight associated with each response in the ranked set of suggested responses, wherein the suggested response is selected based on the weight.

7. The method of claim 1, wherein the suggested response is selected using a machine learning system.

8. The method of claim 1, wherein the electronic form is encoded according to a rendered format defining rendered text and graphic objects.

9. The method of claim 1, wherein the electronic form is encoded using an image file representation of the electronic form that can be processed via at least one of optical character recognition and graphic object detection.

10. The method of claim 1, wherein the user-specific information includes at least one of:

a plurality of prior responses to other form fields by the given user, and contextual user information associated with the given user.

11. In a digital medium environment for processing electronic forms, a system for identifying fillable form field candidates and populating fillable form field candidates using prior responses to similar form fields, the system comprising:

a storage; and

a processor operatively coupled to the storage, the processor configured to execute instructions stored in the storage that when executed cause the processor to carry out a process comprising;

receiving an electronic form having, encoded in the form, static text and a static form field for containing information specific to a given user of the electronic form;

identifying, using an image recognition algorithm, a fillable form field candidate that corresponds to the static form field, wherein the identifying is based on a meaning of the static text corresponding to the static form field;

identifying an attribute of the fillable form field candidate based on the static text;

selecting a suggested response for populating the fillable form field candidate from among a plurality of prior responses to other form fields having at least one attribute in common with the identified attribute of the fillable form field candidate, the prior responses having been obtained from the given user; and

presenting, via a graphical user interface, the suggested response for subsequent acceptance or rejection by the given user.

12. The system of claim 11, wherein the suggested response is selected and presented to the user without a user input that selects any region of the electronic form.

13. The system of claim 11, wherein the process includes identifying, using at least one of content encoded in the electronic form and optical character recognition of the electronic form:

a location of the fillable form field candidate within the electronic form; and

a type of the fillable form field candidate, the type including one of a text field, a signature block, a radio button, and a check box,

wherein the suggested response corresponds to the identified type of the fillable form field candidate.

14. The system of claim 11, wherein the process includes presenting, via the graphical user interface and in response to receiving a user input rejecting the suggested response, at least one alternative suggested response from among the plurality of prior user responses.

15. The system of claim 11, wherein the process includes generating a word-based label that describes the attribute of the fillable form field candidate, wherein the selecting of the suggested response includes matching at least a portion of the word-based label to another word-based label associated with the other form fields.

16. The system of claim 11, wherein the process includes calculating a weight associated with each of the prior responses, wherein the suggested response is selected based on the weight.

17. A non-transient computer program product having instructions encoded thereon that when executed by one or more processors cause a process to be carried out for identifying fillable form field candidates and populating fillable form field candidates using prior responses to similar form fields, the process comprising:

receiving an electronic form having, encoded in the form, static text and a static form field for containing information specific to a given user of the electronic form;

identifying, using an image recognition algorithm, a fillable form field candidate that corresponds to the static form field, wherein the identifying is based on a semantic context of the static text corresponding to the static form field;

identifying an attribute of the fillable form field candidate based on the static text;

selecting a suggested response for populating the fillable form field candidate from among a plurality of prior responses to other form fields having at least one attribute in common with the identified attribute of the fillable form field candidate, the prior responses having been obtained from the given user; and

presenting, via a graphical user interface, the suggested response for subsequent acceptance or rejection by the given user.

18. The computer program product of claim 17, wherein the process includes identifying, using at least one of content encoded in the electronic form and optical character recognition of the electronic form:

a location of the fillable form field candidate within the electronic form; and

a type of the fillable form field candidate, the type including one of a text field, a signature block, a radio button, and a check box,

wherein the suggested response corresponds to the identified type of the fillable form field candidate.

19. The computer program product of claim 17, wherein the process includes presenting, via the graphical user interface and in response to receiving a user input rejecting the suggested response, at least one alternative suggested response from among the plurality of prior user responses.