Media agent

• US 20040220925A1
• Filed: 05/24/2004
• Published: 11/04/2004
• Est. Priority Date: 11/30/2001
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Chen, Zheng, Zhang, Hong-Jiang, Liu, Wen-Yin
• Granted Patent: US 7,493,312 B2
• Time in Patent Office: Days
• US Class Current: 707/3
• CPC Class Codes: G06F 16/40 of multimedia data, e.g. slideshows comprising image and additional audio data retrieval of still image data G06F16/50; retrieval of audio data G06F16/60; retrieval of video data G06F16/70
• CPC Class Codes: G06F 16/48 Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
• CPC Class Codes: Y10S 707/99933 Query processing, i.e. searching
• CPC Class Codes: Y10S 707/99934 Query formulation, input preparation, or translation
• CPC Class Codes: Y10S 707/99935 Query augmenting and refining, e.g. inexact access
• CPC Class Codes: Y10S 707/99936 Pattern matching access
• CPC Class Codes: Y10S 707/99937 Sorting
• CPC Class Codes: Y10S 707/99943 Generating database or data structure, e.g. via user interface

Abstract

Systems and methods for a media agent are described. In one aspect, user access of a media content source is detected. Responsive to this detection, a piece of media content and associated text is collected from the media content source. Semantic text features are extracted from the associated text and the piece of media content. The semantic text features are indexed into a media database.

Claims

1. In a computer system, a method comprising:

detecting user access of a media content source;

responsive to detecting the user access;

collecting a piece of media content and associated text from the media content source;

extracting semantic text features from the associated text and the piece of media content; and

indexing the semantic text features into a media database.

2. A method as recited in claim 1, wherein the media database is a personalized media database.

3. A method as recited in claim 1, further comprising indexing the piece of media content in the media database or separate from the media database.

4. A method as recited in claim 1, wherein the media content source comprises an e-mail message, wherein the media content is an attached to the e-mail message or a link to the media content, and wherein the associated text is a body of the e-mail message.

5. A method as recited in claim 1, wherein the media content source comprises a word processing document, wherein the media content is inserted media content, and wherein the associated text is document text.

6. A method as recited in claim 1, wherein the media content source comprises a Web page.

7. A method as recited in claim 1, wherein at least a portion of the semantic text features in the media database include an indication of relevancy with respect to individual ones of the media content, and wherein the method further comprises:

monitoring user actions;

identifying patterns of media content use from the user actions; and

for each semantic text feature in the at least a portion, modifying its indication of relevancy to individual ones of the media content based on the patterns of media content use.

8. A method as recited in claim 1, further comprising:

detecting user input;

performing an analysis of the user input to determine that the user desires to access media content;

responsive to performing the analysis;

generating search criteria based on linguistic features of the user input;

identifying, based at least in part on the search criteria, one or more media files that are semantically related to the user input from the media database; and

presenting information corresponding to the one or more media files to the user.

9. A method as recited in claim 8, wherein the linguistic features are lexical, syntactical, and/or partial sentence pattern features.

10. A method as recited in claim 8, wherein the analysis is based at least in part on patterns of previous media content use, the patterns corresponding to the user.

11. In a computer system, a method comprising:

monitoring a plurality of user actions;

determining media content use preferences based on the user actions;

collecting media content and associated text from a media content source;

extracting semantic text features from the media content and the associated text;

determining that the media content is of interest to the user based at least in part on semantic similarity between the media content use preferences and the semantic text features; and

responsive to determining that the media content is of interest to the user, indexing the semantic text features into a media database.

12. A method as recited in claim 11, wherein the media content use preferences are further based on keywords extracted from information corresponding to the user actions.

13. A method as recited in claim 11, wherein the media content use preferences comprise a plurality of user preference models, each user preference model comprising semantically similar keywords that correspond to the user actions, and wherein media content is determined to be of interest to the user if there is semantic similarity between the media content and at least one of the user preference models.

14. A method as recited in claim 11, further comprising:

detecting that the computer system is in an idle state; and

wherein the acts of collecting, extracting and determining are performed responsive to detecting the idle state.

15. A Computer-readable medium comprising computer-executable instructions for:

detecting user access of a media content source;

responsive to detecting the user access;

collecting a piece of media content and associated text from the media content source;

extracting semantic text features from the associated text and the piece of media content; and

indexing the semantic text features into a media database.

16. A computer-readable medium as recited in claim 15, further comprising computer-executable instructions for indexing the piece of media content in the media database or separate from the media database.

17. A computer-readable medium as recited in claim 15, wherein the media content source is an e-mail message, wherein the media content is an attached to the e-mail message or a link to the media content, and wherein the associated text is a body of the e-mail message.

18. A computer-readable medium as recited in claim 15, wherein the media content source comprises a word processing document, wherein the media content is inserted media content, and wherein the associated text is document text.

19. A computer-readable medium as recited in claim 15, wherein at least a portion of the semantic text features in the media database include an indication of relevancy with respect to individual ones of the media content, and wherein the computer-executable instructions further comprise instructions for:

monitoring user actions;

identifying patterns of media content use from the user actions; and

for each semantic text feature in the at least a portion, modifying its indication of relevancy to individual ones of the media content based on the patterns of media content use.

20. A computer-readable medium as recited in claim 15, further comprising instructions for:

detecting an action by a user comprising insertion of text;

performing an analysis of the text to determine that the user desires to access media content;

responsive to performing the analysis;

generating search criteria based on linguistic features of the text;

identifying, based at least in part on the search criteria, one or more media files that are semantically related to the text from the media database; and

presenting information corresponding to the one or more media files to the user.

21. A computer-readable medium as recited in claim 20, wherein the linguistic features are lexical, syntactical, and/or partial sentence pattern features.

22. A computer-readable medium as recited in claim 20, wherein the analysis is based at least in part on patterns of previous media content use, the patterns corresponding to the user.

23. A computer-readable medium comprising computer-executable instructions for:

monitoring a plurality of user actions;

determining media content use preferences based on the user actions;

collecting media content and associated text from a media content source;

extracting semantic text features from the media content and the associated text;

determining that the media content is of interest to the user based at least in part on semantic similarity between the media content use preferences and the semantic text features; and

responsive to determining that the media content is of interest to the user, indexing the semantic text features into a media database.

24. A computer-readable medium as recited in claim 23, wherein the media content use preferences are further based on keywords extracted from information corresponding to the user actions.

25. A computer-readable medium as recited in claim 23, wherein the media content use preferences comprise a plurality of user preference models, each user preference model comprising semantically similar keywords that correspond to the user actions, and wherein media content is determined to be of interest to the user if there is semantic similarity between the media content and at least one of the user preference models.

26. A computer-readable medium as recited in claim 23, further comprising computer-executable instructions for:

detecting that the computer system is in an idle state; and

wherein the instructions for collecting, extracting and determining are performed responsive to detecting the idle state.

27. A computing device comprising:

a processor;

a memory coupled to the processor, the memory comprising computer-executable instructions, the processor being configured to fetch and execute the computer-executable instructions for;

detecting user access of a media content source;

responsive to detecting the user access;

collecting a piece of media content and associated text from the media content source;

extracting semantic text features from the associated text and the piece of media content; and

indexing the semantic text features into a media database.

28. A computing device as recited in claim 27, further comprising computer-executable instructions for indexing the piece of media content in the media database or separate from the media database.

29. A computing device as recited in claim 27, wherein the media content source is an e-mail message, wherein the media content is an attached to the e-mail message or a link to the media content, and wherein the associated text is a body of the e-mail message.

30. A computing device as recited in claim 27, wherein the media content source comprises a word processing document, wherein the media content is inserted media content, and wherein the associated text is document text.

31. A computing device as recited in claim 27, wherein at least a portion of the semantic text features in the media database include an indication of relevancy with respect to individual ones of the media content, and wherein the computer-executable instructions further comprise instructions for:

monitoring user actions;

identifying patterns of media content use from the user actions; and

for each semantic text feature in the at least a portion, modifying its indication of relevancy to individual ones of the media content based on the patterns of media content use.

32. A computing device as recited in claim 27, further comprising instructions for:

detecting an action by a user comprising insertion of text;

performing an analysis of the text to determine that the user desires to access media content;

responsive to performing the analysis;

generating search criteria based on linguistic features of the text;

identifying, based at least in part on the search criteria, one or more media files that are semantically related to the text from the media database; and

presenting information corresponding to the one or more media files to the user.

33. A computing device as recited in claim 32, wherein the linguistic features are lexical, syntactical, and/or partial sentence pattern features.

34. A computing device as recited in claim 32, wherein the analysis is based at least in part on patterns of previous media content use, the patterns corresponding to the user.

35. A computing device comprising:

processing means for;

detecting user access of a media content source;

responsive to detecting the user access;

collecting a piece of media content and associated text from the media content source;

extracting semantic text features from the associated text and the piece of media content; and

indexing the semantic text features into a media database.

36. A computing device comprising:

a processor;

a memory coupled to the processor, the memory comprising computer-executable instructions, the processor being configured to fetch and execute the computer-executable instructions for;

monitoring a plurality of user actions;

determining media content use preferences based on the user actions;

collecting media content and associated text from a media content source;

extracting semantic text features from the media content and the associated text;

determining that the media content is of interest to the user based at least in part on semantic similarity between the media content use preferences and the semantic text features; and

responsive to determining that the media content is of interest to the user, indexing the semantic text features with the media content into a media database.

37. A computing device as recited in claim 36, wherein the media content use preferences are further based on keywords extracted from information corresponding to the user actions.

38. A computing device as recited in claim 36, wherein the media content use preferences comprise a plurality of user preference models, each user preference model comprising semantically similar keywords that correspond to the user actions, and wherein media content is determined to be of interest to the user if there is semantic similarity between the media content and at least one of the user preference models.

39. A computing device as recited in claim 36, further comprising computer-executable instructions for:

detecting that the processor is in an idle state; and

wherein the instructions for collecting, extracting and determining are performed responsive to detecting the idle state.

40. A computing device comprising:

processing means for;

monitoring a plurality of user actions;

determining media content use preferences based on the user actions;

collecting media content and associated text from a media content source;

extracting semantic text features from the media content and the associated text;

determining that the media content is of interest to the user based at least in part on semantic similarity between the media content use preferences and the semantic text features; and

responsive to determining that the media content is of interest to the user, indexing the semantic text features into a media database.

41. A computing device as recited in claim 40, further comprising processing means for:

detecting that the processor is in an idle state; and

wherein the means for collecting, extracting and determining are performed responsive to detecting the idle state.