Image analysis-based adaptation techniques for localization of content presentation

Inventors: Sathish Kumar Bikumala (Round Rock, TX); Parminder Singh Sethi (Ludhiana, IN)

Assignee: Dell Products L.P.

G06F40/58 G06F40/30 G06K9/6215

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 11,443,122
App. No.: 16/807,899
Granted: Sep 13, 2022
Kind: B2

External Links

USPTO Patent Center↗ Full Patent PDF↗

Abstract

Techniques for localization of a content presentation in an information processing system are provided. In one example, a method adapts translated content to accommodate an original content design structure (e.g., wireframe) when such translated content is inconsistent with the original content design structure. In another example, a method adapts the original content design structure when translated content is inconsistent with the original content design structure. In yet another example, an image analysis method is used to adapt translated content determined to be inconsistent with the original content design structure.

Claims (37)

1. A system, comprising:

at least one processing device comprising a processor operatively coupled to a memory, wherein the at least one processing device, for a given content presentation, is configured to:

obtain source content in a source language and a first content design structure that is consistent with the source content;

translate the source content to translated content, the translated content being in at least one destination language and associated with a second content design structure that is consistent with the translated content;

obtain a first image of the source content and the first content design structure and a second image of the translated content and the second content design structure;

compare the first image and the second image to identify one or more inconsistent portions associated with one or more second image portions of the second image relative to one or more corresponding first image portions of the first image; and

adapt the one or more inconsistent portions of at least the translated content of the second image to generate one or more adapted portions of translated content that are consistent with the first content design structure such that the given content presentation is localized for the at least one destination language.

2. The system of claim 1 , wherein identifying one or more inconsistent portions further comprises determining that one or more portions of the translated content are out of scope with respect to the first content design structure.

3. The system of claim 2 , wherein a portion of translated content is out of scope when the portion of translated content is one of truncated and misaligned in the first content design structure as compared with the corresponding portion of source language content.

4. The system of claim 1 , wherein adapting one or more inconsistent portions of translated content to generate one or more adapted portions of translated content that are consistent with the first content design structure further comprises obtaining one or more portions of alternative translated content that have a same or similar meaning to the one or more inconsistent portions of translated content and that are consistent with one or more dimensions associated with corresponding components of the first content design structure.

5. The system of claim 1 , wherein comparing the first image and the second image to identify one or more inconsistent portions of the translated content further comprises applying an artificial intelligence-based image analysis algorithm to the first image and the second image.

6. The system of claim 1 , wherein the given content presentation localized for the at least one destination language is at least one web page.

7. The system of claim 1 , wherein the source content in the source language comprises one or more of text, an image and a design element.

8. The system of claim 1 wherein comparing the first image and the second image to identify one or more inconsistent portions includes identifying one or more diversions in corresponding components of the first content design structure and the second content design structure.

9. A method, comprising:

obtaining, for a given content presentation, source content in a source language and a first content design structure that is consistent with the source content;

translating the source content to translated content, the translated content being in at least one destination language and associated with a second content design structure that is consistent with the translated content;

obtaining a first image of the source content and the first content design structure and a second image of the translated content and the second content design structure;

comparing the first image and the second image to identify one or more inconsistent portions associated with one or more second image portions of the second image relative to one or more corresponding first image portions of the first image; and

adapting the one or more inconsistent portions of at least the translated content of the second image to generate one or more adapted portions of translated content that are consistent with the first content design structure such that the given content presentation is localized for the at least one destination language;

wherein the steps are performed by at least one processing device comprising a processor operatively coupled to a memory.

10. The method of claim 9 , wherein identifying one or more inconsistent portions further comprises determining that one or more portions of the translated content are out of scope with respect to the first content design structure.

11. The method of claim 10 , wherein a portion of translated content is out of scope when the portion of translated content is one of truncated and misaligned in the first content design structure as compared with the corresponding portion of source language content.

12. The method of claim 9 , wherein adapting one or more inconsistent portions of translated content to generate one or more adapted portions of translated content that are consistent with the first content design structure further comprises obtaining one or more portions of alternative translated content that have a same or similar meaning to the one or more inconsistent portions of translated content and that are consistent with one or more dimensions associated with corresponding components of the first content design structure.

13. The method of claim 9 , wherein comparing the first image and the second image to identify one or more inconsistent portions of the translated content further comprises applying an artificial intelligence-based image analysis algorithm to the first image and the second image.

14. The method of claim 9 , wherein the given content presentation localized for the at least one destination language is at least one web page.

15. The method of claim 9 , wherein the source content in the source language comprises one or more of text, an image and a design element.

16. An article of manufacture comprising a non-transitory processor-readable storage medium having stored therein program code of one or more software programs, wherein the program code when executed by at least one processing device causes said at least one processing device to perform steps of:

obtaining, for a given content presentation, source content in a source language and a first content design structure that is consistent with the source content;

obtaining a first image of the source content and the first content design structure and a second image of the translated content and the second content design structure;

17. The article of claim 16 , wherein identifying one or more inconsistent portions further comprises determining that one or more portions of the translated content are out of scope with respect to the first content design structure.

18. The article of claim 17 , wherein a portion of translated content is out of scope when the portion of translated content is one of truncated and misaligned in the first content design structure as compared with the corresponding portion of source language content.

19. The article of claim 16 , wherein adapting one or more inconsistent portions of translated content to generate one or more adapted portions of translated content that are consistent with the first content design structure further comprises obtaining one or more portions of alternative translated content that have a same or similar meaning to the one or more inconsistent portions of translated content and that are consistent with one or more dimensions associated with corresponding components of the first content design structure.

20. The article of claim 16 , wherein comparing the first image and the second image to identify one or more inconsistent portions of the translated content further comprises applying an artificial intelligence-based image analysis algorithm to the first image and the second image.

Assignments (13)

RELEASE OF SECURITY INTEREST IN PATENTS PREVIOUSLY RECORDED AT REEL/FRAME (052851/0917) Recorded Jun 23, 2022