IP Library Granted Patent US 10,963,924
Granted Patent B1
US 10,963,924 · App. 14/203,260 · Granted Mar 30, 2021

Media processing techniques for enhancing content

Inventors: Douglas Ryan Gray (Mountain View, CA); Arnab Sanat Kumar Dhua (Mountain View, CA); Xiaofan Lin (Palo Alto, CA); Zhijiang Mark Lu (Union City, CA)
Assignee: A9.com, Inc.
G06Q30/0277G06F40/14
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 10,963,924
App. No.
14/203,260
Granted
Mar 30, 2021
Kind
B1
Abstract

A computing device can obtain data describing at least one document, the at least one document referencing at least one media object, wherein a portion of the at least one media object includes one or more characters. The computing device can obtain data describing the one or more characters in the at least one media object in the at least one document. The computing device can generate an updated copy of the at least one document that includes the data describing the one or more characters in the at least one media object. The computing device can present, on a display screen of the computing device and through an interface, the updated copy of the at least one document, wherein the one or more characters in the at least one media object are able to be selected or searched.

Claims (81)

1. A computing device, comprising

one or more processors; and

memory storing instructions that, when executed by the one or more processors, cause the computing device to perform operations, comprising:

generating at least one webpage corresponding to a website for a display of the computing device;

identifying at least one image in the at least one webpage corresponding to the website, wherein the at least one image includes at least a non-selectable representation of text;

extracting, from the at least one image, data describing at least one object in the at least one image;

obtaining, based at least in part on the data describing the at least one object, one or more respective tags that describe the at least one object;

generating, using an optical character recognition technique, extracted text from at least a portion of the non-selectable representation of text included in the at least one image;

generating, based at least in part on the one or more respective tags and on the extracted text, an updated copy of the at least one webpage by at least an update to code of the webpage, the updated copy including the extracted text and the one or more respective tags as an invisible overlay over the at least one image, the extracted text in the invisible overlay being selectable and searchable;

obtaining, based at least in part on the extracted text and the one or more respective tags, at least one electronic advertisement that is relevant to the at least image; and

providing the at least one electronic advertisement to be displayed along with the updated copy of the at least one webpage, wherein the at least one electronic advertisement is able to be placed in the updated copy of the at least one webpage displayed on the display.

2. The computing device of claim 1 , wherein obtaining, based at least in part on the at least one extracted object and the one or more respective tags further comprises:

identifying one or more objects that match the at least one object; and

obtaining the one or more respective tags associated with the identified one or more objects, wherein the one or more respective tags are associated with the at least one webpage for obtaining one or more electronic advertisements that are related to the one or more respective tags.

3. The computing device of claim 1 , wherein the one or more respective tags describe at least one of: a particular logo, a particular product, or a type of object.

4. The computing device of claim 1 , wherein generating, based at least in part on the extracted text and the one or more respective tags, an updated copy of the at least one webpage further comprises:

updating markup language code for the at least one webpage to include the extracted data and the one or more respective tags, wherein the markup language code is updated to include the extracted data and the one or more respective tags using an “alt” attribute or a “div” tag.

5. A computer-implemented method, the method comprising:

generating, by one or more computer systems, at least one webpage corresponding to a website to be displayed on a computing device;

extracting, from a media object in the at least one webpage, data describing at least one object;

extracting, from the media object in the at least one webpage, text referenced in the media object, the text referenced in the media object being non-selectable;

obtaining, based at least in part on the data describing the at least one object, one or more respective tags that describe the object and the extracted text from the media object;

generating an updated copy of the at least one webpage by at least an update to code of the at least one webpage to include the extracted text and the one or more respective tags as an invisible overlay over the media obbject, the extracted text in the invisible overlay being selectable and searchable; and

providing the updated copy of the at least one webpage for display on the computing device.

6. The computer-implemented method of claim 5 , further comprising:

obtaining, based at least in part on the extracted text or the one or more respective tags, at least one electronic advertisement that is relevant to the media object.

7. The computer-implemented method of claim 5 , further comprising:

extracting a first object and a second object from a second media object in the at least one webpage;

determining that the extracted first object has a threshold similarity to a first matching object;

determining that the extracted second object does not have a threshold similarity to at least one matching object;

obtaining, for the first extracted object, one or more respective second tags that describe the first matching object; and

generating a second updated copy of the at least one webpage to include the one or more respective second tags that describe the first matching object.

8. The computer-implemented method of claim 5 , further comprising:

extracting a first object and a second object from a second media object in the at least one webpage;

determining that the extracted first object has a threshold similarity to a first matching object;

determining that the extracted second object has a threshold similarity to a second matching object;

obtaining, for the first extracted object, one or more respective second tags that describe the first matching object;

obtaining, for the second extracted object, one or more respective third tags that describe the second matching object; and

generating a second updated copy of the at least one webpage to include the one or more respective second tags that describe the first matching object and the one or more third respective tags that describe the second matching object.

9. The computer-implemented method of claim 5 , wherein generating the updated copy of the at least one webpage further comprises updating markup language code of the at least one webpage to include the extracted text or the one or more respective tags.

10. The computer-implemented method of claim 5 , further comprising:

extracting a first object from a second media object in the at least one webpage;

determining that the extracted first object has a threshold similarity to a first matching object based at least in part on an ImageMatch technique or a logo recognition technique;

obtaining, for the first extracted object, one or more respective seconds tags that describe the first matching object; and

generating a second updated copy of the at least one webpage to include the one or more respective second tags that describe the first matching object.

11. The computer-implemented method of claim 5 , further comprising:

obtaining second data describing a default language associated with a user operating the computing device; and

generating the updated copy of the at least one webpage to include the extracted text in the language associated with the user.

12. The computer-implemented method of claim 5 , further comprising:

determining that the extracted text matches a specified keyword included in a blacklist; and

generating a second copy of the at least one webpage to prevent the extracted text from being included in the code of the at least one webpage.

13. A non-transitory computer-readable storage medium including instructions that, when executed by at least one processor of a computer system, cause the computer system to perform operations comprising:

generating at least one webpage corresponding to a website to be displayed on the computing system;

extracting, from a media object in the at least one webpage, data describing at least one object;

extracting, from the media object in the at least one webpage, text referenced in the media object, the text referenced in the media object being non-selectable;

obtaining, based at least in part on the data describing the at least one object, one or more respective tags that describe the at least one object and the text extracted from the media object;

generating an updated copy of the at least one webpage by at least an update to code of the at least one webpage to include the extracted text and the one or more respective tags as an invisible overlay over the media object, the extracted text in the invisible overlay being selectable and searchable; and

providing the updated copy of the at least one webpage for display on the computing system.

14. The non-transitory computer-readable storage medium of claim 13 , wherein the operations further comprise:

obtaining, based at least in part on extracted text or the one or more respective tags, at least one electronic advertisement that is relevant to the media object.

15. The non-transitory computer-readable storage medium of claim 13 , wherein the operations further comprise:

extracting a first object and a second object from a second media object in the at least one webpage;

determining that the extracted first object has a threshold similarity to a first matching object;

determining that the extracted second object does not have a threshold similarity to at least one matching object;

obtaining, for the first extracted object, one or more respective second tags that describe the first matching object; and

generating a second updated copy of the at least one webpage to include the one or more respective second tags that describe the first matching object.

16. The non-transitory computer-readable storage medium of claim 13 , wherein the operations further comprise:

extracting a first object and a second object from a second media object in the at least one webpage;

determining that the extracted first object has a threshold similarity to a first matching object;

determining that the extracted second object has a threshold similarity to a second matching object;

obtaining, for the first extracted object, one or more respective second tags that describe the first matching object;

obtaining, for the second extracted object, one or more respective third tags that describe the second matching object; and

generating a second updated copy of the at least one webpage to include the one or more respective second tags that describe the first matching object and the one or more respective third tags that describe the second matching object.

17. The non-transitory computer-readable storage medium of claim 13 , wherein generating the updated copy of the at least one webpage further comprises updating markup language code of the at least one webpage to include the extracted text or the one or more respective tags.

18. The non-transitory computer-readable storage medium of claim 17 , wherein the markup language code is updated to include the extracted text or the one or more respective tags using an “alt” attribute or a “div” tag.

19. The non-transitory computer-readable storage medium of claim 13 , wherein the operations further comprise:

obtaining second data describing a default language associated with a user operating the computing device; and

generating the updated copy of the at least one webpage to include the extracted text in the language associated with the user.

20. The non-transitory computer-readable storage medium of claim 13 , further comprising:

determining that the extracted text matches a specified keyword included in a blacklist; and

generating a second copy of the at least one webpage to prevent the extracted text from being included in the code of the at least one webpage.

Assignments (2)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Oct 13, 2024
From: A9.COM, INC.
To: AMAZON TECHNOLOGIES, INC.
Reel/Frame 069167/0493 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jul 11, 2017
From: GRAY, DOUGLAS RYAN; DHUA, ARNAB SANAT KUMAR; LIN, XIAOFAN; LU, ZHIJIANG MARK
To: A9.COM, INC.
Reel/Frame 042977/0558 →