METHOD AND APPARATUS FOR ADAPTING A CONTEXT MODEL

• US 20130226850A1
• Filed: 07/01/2010
• Published: 08/29/2013
• Est. Priority Date: 07/01/2010
• Status: Active Grant

• Current Assignee: Piece Future Pte., Ltd.
• Original Assignee: Nokia Corporation
• Inventors: Hannuksela, Miska, Eronen, Antti, Leppanen, Jussi
• Granted Patent: US 9,679,257 B2
• Time in Patent Office: Days
• US Class Current: 706/14
• CPC Class Codes: G06F 16/432 Query formulation
• CPC Class Codes: G06F 16/58 Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G10L 25/48 specially adapted for particular use

Abstract

A method, devices, computer program products and an internet service is disclosed for adapting a context model. In the method a media clip is received. Also sensor data captured at least partly when the media clip was captured is received. A context is derived using a context model based at least partly on the sensor data and an indication on the context is provided to a user. Feedback on the relevance of the context is received from the user. Based on the feedback, the context model may then be adapted.

Claims

1. A method in an apparatus comprising:

receiving a media clip;

receiving sensor data captured at least partly in connection with a capture of the media clip;

deriving at least one context using a context model based at least partly on the sensor data;

causing an indication on the context to be provided to a user;

receiving feedback on the relevance of the context from the user; and

adapting the context model based on the feedback.

2. The method according to claim 1 additionally comprising deriving a first parameter value indicating a probability of the sensor data matching the context.

3. The method according to claim 1 additionally comprising using the context model independently of the reception of the media clip for determining at least one of an activity context, an audio context, and a social context.

4. The method according to claim 1, wherein said providing an indication on the context to the user comprises:

associating a set of keywords with the context; and

presenting the set of keywords to the user.

5. The method according to claim 4, wherein said receiving feedback of the relevance of the context from the user comprises receiving a selection of a keyword from the set of keywords by the user.

6. The method according to claim 1, wherein said indicating the context to the user comprises:

receiving a search query having at least one context-related search criterion;

deriving a similarity between the context and the at least one context-related search criterion; and

presenting at least a part of the media clip as a response to the search query.

7. The method according to claim 6, wherein said receiving feedback of the relevance of the context from the user comprises receiving feedback on relevance of the media clip relative to the at least one context-related search criterion.

9. The method according to claim 2 comprising deriving a similarity between the context and the at least one context-related search criterion, wherein adapting the context model is additionally based on the similarity and the method additionally comprises adapting the first parameter value based on at least one of the feedback or the similarity.

10. The method according to claim 1, wherein indicating the context to the user comprises:

receiving a search query, the search query being an example including or accompanying a first context-related data item;

deriving a similarity between the context and the first context-related data item; and

presenting at least a part of the media clip as a response to the search query.

11. The method according to claim 10, wherein said receiving feedback of the relevance of the context from the user comprises receiving feedback on relevance of the media clip relative to the first context-related data item.

8. (canceled)

12-24. -24. (canceled)

25. An apparatus comprising:

at least one processor

and at least one memory including computer program code

the at least one memory and the computer program code configured to, with the at least one processor, cause the apparatus at least to

receive a media clip;

receive sensor data captured at least partly in connection with a capture of the media clip;

derive at least one context using a context model based at least partly on the sensor data;

cause an indication on the context to be provided to a user;

receive feedback on the relevance of the context from the user; and

adapt the context model based on the feedback.

26. The apparatus according to claim 25, wherein the at least one memory and the computer program code are further configured to, with the at least one processor, cause the apparatus at least to derive a first parameter value indicating a probability of the sensor data matching the context.

27. The apparatus according to claim 25, wherein the at least one memory and the computer program code are further configured to, with the at least one processor, cause the apparatus at least to use the context model independently of the reception of the media clip for determining at least one of an activity context, an audio context, and a social context.

28. The apparatus according to claim 25, wherein the at least one memory and the computer program code are further configured to, with the at least one processor, cause the apparatus at least to:

associate a set of keywords with the context; and

present the set of keywords to the user.

29. The apparatus according to claim 28, wherein the at least one memory and the computer program code are further configured to, with the at least one processor, cause the apparatus at least to receive a selection of a keyword from the set of keywords by the user.

30. The apparatus according to claim 25, wherein the at least one memory and the computer program code are further configured to, with the at least one processor, cause the apparatus at least to:

receive a search query having at least one context-related search criterion;

derive a similarity between the context and the at least one context-related search criterion; and

present at least a part of the media clip as a response to the search query.

31. The apparatus according to claim 30, wherein the at least one memory and the computer program code are further configured to, with the at least one processor, cause the apparatus at least to receive feedback on relevance of the media clip relative to the at least one context-related search criterion.

33. The apparatus according to claim 26, wherein the at least one memory and the computer program code are further configured to, with the at least one processor, cause the apparatus at least to:

derive a similarity between the context and the at least one context-related search criterion;

adapt the context model additionally based on the similarity; and

adapt the first parameter value based on at least one of the feedback or the similarity.

34. The apparatus according to claim 25, wherein the at least one memory and the computer program code are further configured to, with the at least one processor, cause the apparatus at least to:

receive a search query, the search query being an example including or accompanying a first context-related data item;

derive a similarity between the context and the first context-related data item; and

present at least a part of the media clip as a response to the search query.

32. (canceled)

35-48. -48. (canceled)

49. A computer program product comprising at least one computer-readable storage medium having computer-executable program code portions stored therein, the computer-executable program code portions comprising program code instructions for:

receiving a media clip;

receiving sensor data captured at least partly in connection with a capture of the media clip;

deriving at least one context using a context model based at least partly on the sensor data;

causing an indication on the context to be provided to a user;

receiving feedback on the relevance of the context from the user; and

adapting the context model based on the feedback.