Automated form fill

Patent metadata

Field	Value
Publication number	US-10607040-B1
Application number	US-201916281182-A
Country	US
Kind code	B1
Filing date	Feb 21, 2019
Priority date	Feb 21, 2019
Publication date	Mar 31, 2020
Grant date	Mar 31, 2020

Abstract

A method and apparatus for annotating video is provided herein. During the process of annotating a video, important text within a form is identified. Annotations are placed within the video that are related to the important text within the form. In addition to annotating the video with important text taken from the form, Information that is determined based on the text, may be taken from the video in order to help fill the form.

First claim

What is claimed is:

1. A method for inserting text into a form, the method comprising the steps of:
accessing the form and video from memory, wherein the form comprises a document with blank spaces for insertion of required or requested information;
determining keywords based on text within the form;
performing video analysis on the video, wherein the video analysis determines a position within the video related to the keywords;
determining information within the video related to the keywords;
filling in a blank space within the form with the information; and
wherein the step of determining keywords comprises one or both of the following:
determining user-inserted information within the form; or
associating keywords with text within the form having a certain font, location, size, color, and/or orientation.

2. The method of claim 1 further comprising the step of:
annotating the video at the position with text related to the keywords.

3. The method of claim 2 wherein the step of annotating the video comprises the step of annotating the video with the text taken from the form.

4. The method of claim 1 wherein the step of performing video analysis comprises the step of utilizing a software engine that is based on the keywords.

5. The method of claim 1 wherein the keywords comprise text taken from the form, or text derived from the form.

6. An apparatus comprising:
memory storing a form, wherein the form comprises a document with blank spaces for insertion of required or requested information;
memory storing video;
logic circuitry configured to:
access the form and the video;
determine keywords based on text within the form;
perform video analysis on the video in order to determine a position within the video related to the keywords exists;
determine information within the video related to the keywords; and
fill a blank space within the form with the information;
wherein the logic circuitry determines keywords from the form by determining user-inserted information within the form.

7. The apparatus of claim 6 , wherein the logic circuitry is also configured to annotate the video at the position with text related to the keywords.

8. The apparatus of claim 7 , wherein the logic circuitry is also configured to store the annotated video within the memory.

9. The apparatus of claim 6 wherein the logic circuitry performs video analysis by utilizing a software engine that is based on the keywords.

10. The apparatus of claim 6 wherein the keywords comprise text taken from the form, or text derived from the form.

11. An apparatus comprising:
memory storing a form, wherein the form comprises a document with blank spaces for insertion of required or requested information;
memory storing video;
logic circuitry configured to:
access the form and the video;
determine keywords based on text within the form;
perform video analysis on the video in order to determine a position within the video related to the keywords exists;
determine information within the video related to the keywords; and
fill a blank space within the form with the information;
wherein the logic circuitry determines the keywords from the form by associating keywords with text having a certain font, location, size, color, and/or orientation.

Assignees

• Motorola Solutions Inc

Inventors

• Gan Guo Dong
• Chew Yen Hsiang
• Phua Jin Hoe
• Duraimanickam Tejeash

Classifications

• G06F40/174 Primary

  Form filling; Merging · CPC title

• G06F40/169

  Annotation, e.g. comment data or footnotes · CPC title

• G06F16/7867

  using information manually generated, e.g. tags, keywords, comments, title and artist information, manually generated time, location and usage information, user ratings · CPC title

• G06K9/00671

  Physics · mapped topic

• G06V20/62

  Text, e.g. of license plates, overlay texts or captions on TV images · CPC title