SEMANTIC MATCHING BY CONTENT ANALYSIS

• US 20120191692A1
• Filed: 01/26/2011
• Published: 07/26/2012
• Est. Priority Date: 01/26/2011
• Status: Active Grant

• Current Assignee: Hulu LLC (The Walt Disney Company)
• Original Assignee: Hulu LLC (The Walt Disney Company)
• Inventors: Wang, Dong
• Granted Patent: US 8,909,617 B2
• Time in Patent Office: Days
• US Class Current: 707/709
• CPC Class Codes: G06F 16/958 Organisation or management of web site content, e.g. publishing, maintaining pages or automatic linking

Abstract

A method, apparatus, system, article of manufacture, and computer readable storage medium provide media content. A web page context for a web page is determined and stored in a database. One or more media content files are analyzed to extract information that is stored in the database. The information is compared to the web page context. A matching media content file is determined from the one of the one or more media content files that matches the web page context based on the comparison. The matching media content file is then provided (e.g., to an internet portal web site).

Claims

1. A computer-implemented method for providing media content comprising:

determining when a change has been made to a web page since a previous analysis of the web page;

in response to determining the change, determining a web page context for the web page, wherein the web page context is associated with the change in the web page;

storing the web page context in a database;

analyzing content included in one or more media content files to extract information categorizing the content included in the one or more media content files;

storing the information in the database;

comparing the information from the database to the web page context;

determining a matching media content file, from the one or more media content files, that matches the web page context based on the comparing, the matching media content file including content that is categorized in a category that is determined to match the web page context that is associated with the change in the web page; and

automatically providing the matching media content file to the web page in response to determining the change being made to the web page.

2. The computer-implemented method of claim 1, wherein the web page context is determined using a web crawler.

3. The computer-implemented method of claim 2, wherein the web crawler determines when any changes have been made to the web page since the previous analysis of the web page.

4. The computer-implemented method of claim 1, wherein the web page context is determined dynamically without a request from an internet portal web site.

5. The computer-implemented method of claim 1, wherein the web page context is determined based on metadata of the web page.

6. The computer-implemented method of claim 1, wherein the web page context is based on a text analysis.

7. The computer-implemented method of claim 6, wherein the text analysis comprises support vector machine based text categorization.

8. The computer-implemented method of claim 1, wherein the web page context is determined based on an image analysis.

9. The computer-implemented method of claim 1, wherein the one or more media content files are analyzed based on closed captioning data.

10. The computer-implemented method of claim 1, wherein the one or more media content files are analyzed based on noisy speech recognition.

11. The computer-implemented method of claim 1, wherein the one or more media content files are analyzed using a facial recognition application.

12. The computer-implemented method of claim 1, wherein the determining a matching media content file is based on a frequency of the information compared to the web page context.

13. The computer-implemented method of claim 1, wherein the determining a matching media content file comprises:

determining two or more potential matching media content files from the one or more media content files;

sorting the two or more potential matching media content files by a frequency of the information in the two or more potential matching media content files compared to the web page context; and

selecting one of the two or more potential matching media content files as the matching media content file based on the sorting.

14. The computer-implemented method of claim 1, wherein the determining a matching media content file comprises:

determining two or more potential matching media content files from the one or more media content files;

temporally sorting the two or more potential matching media content files; and

selecting one of the two or more potential matching media content files as the matching media content file based on the sorting.

15. The computer-implemented method of claim 1, wherein the determining a matching media content file comprises:

determining two or more potential matching media content files from the one or more media content files;

sorting the two or more potential matching media content files by a type of content of the information in the two or more potential matching media content files; and

selecting one of the two or more potential matching media content files as the matching media content file based on the sorting.

16. The computer-implemented method of claim 1, wherein the matching media content file is provided via email from a media content provider.

17. The computer-implemented method of claim 1, wherein the matching media content file is provided by supplying a link to the matching media content file.

18. A system for providing media content, the system comprising:

one or more computer processors; and

a computer-readable storage medium comprising instructions for controlling the one or more computer processors to be operable for;

determining when a change has been made to a web page since a previous analysis of the web page;

in response to determining the change, determining a web page context for the web page, wherein the web page context is associated with the change in the web page;

storing the web page context in a database;

analyzing content included in one or more media content files to extract information categorizing the content included in the one or more media content files;

storing the information in the database;

comparing the information from the database to the web page context;

determining a matching media content file, from the one or more media content files, that matches the web page context based on the comparing, the matching media content file including content that is categorized in a category that is determined to match the web page context that is associated with the change in the web page; and

automatically providing the matching media content file to the web page in response to determining the change being made to the web page.

19. The system of claim 18, wherein the web crawler determines when any changes have been made to the web page since the previous analysis of the web page.

20. The system of claim 18, wherein the web page context is determined dynamically without a request from an internet portal web site.

21. The system of claim 18, wherein the web page context is determined based on metadata of the web page.

22. The system of claim 18, wherein the web page context is based on a text analysis.

23. The system of claim 22, wherein the text analysis comprises support vector machine based text categorization.

24. The system of claim 18, wherein the web page context is determined based on an image analysis.

25. The system of claim 18, wherein the one or more media content files are analyzed based on closed captioning data.

26. The system of claim 18, wherein the one or more media content files are analyzed based on noisy speech recognition.

27. The system of claim 18, wherein the one or more media content files are analyzed using a facial recognition application.

28. The system of claim 18, wherein the determining a matching media content file is based on a frequency of the information compared to the web page context.

29. The system of claim 18, wherein the matching engine determines a matching media content file by:

determining two or more potential matching media content files from the one or more media content files;

sorting the two or more potential matching media content files by a frequency of the information in the two or more potential matching media content files compared to the web page context; and

selecting one of the two or more potential matching media content files as the matching media content file based on the sorting.

30. The system of claim 18, wherein the matching engine determines a matching media content file by:

determining two or more potential matching media content files from the one or more media content files;

temporally sorting the two or more potential matching media content files; and

selecting one of the two or more potential matching media content files as the matching media content file based on the sorting.

31. The system of claim 18, wherein the matching engine determines a matching media content file by:

determining two or more potential matching media content files from the one or more media content files;

sorting the two or more potential matching media content files by a type of content of the information in the two or more potential matching media content files; and

selecting one of the two or more potential matching media content files as the matching media content file based on the sorting.

32. The system of claim 18, wherein the matching media content file is provided via email from a media content provider.

33. The system of claim 18, wherein the matching media content file is provided by supplying a link to the matching media content file.

34. A non-transitory computer readable storage medium having stored thereon instructions executed by a processor to cause the processor to be configured for:

determining when a change has been made to a web page since a previous analysis of the web page;

in response to determining the change, determining a web page context for the web page, wherein the web page context is associated with the change in the web page;

storing the web page context in a database;

analyzing content included in one or more media content files to extract information categorizing the content included in the one or more media content files;

storing the information in the database;

comparing the information from the database to the web page context;

determining a matching media content file, from the one of the one or more media content files, that matches the web page context based on the comparing, the matching media content file including content that is categorized in a category that is determined to match the web page context that is associated with the change in the web page; and

automatically providing the matching media content file to the web page in response to determining the change being made to the web page.