TECHNOLOGIES FOR AUTOMATED CONTEXT-AWARE MEDIA CURATION

• US 20170091628A1
• Filed: 09/26/2015
• Published: 03/30/2017
• Est. Priority Date: 09/26/2015
• Status: Active Grant

• Current Assignee: Intel Corporation
• Original Assignee: Intel Corporation
• Inventors: Lu, Hong, Bogia, Douglas P., Nachman, Lama, Asokan, Ashwini, Raffa, Giuseppe, Wouhaybi, Rita H., Sahay, Saurav, Florez, Omar U., Shah, Rahul C., Wan, Chieh-Yih, Huang, Jonathan J., Sharma, Sangita, Shahabdeen, Junaith Ahemed, Durham, Lenitra
• Granted Patent: US 10,380,256 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: G06N 5/022 Knowledge engineering; Knowledge acquisition

Abstract

Technologies for automated context-aware media curation include a computing device that captures context data associated with media objects. The context data may include location data, proximity data, behavior data of the user, and social activity data. The computing device generates inferred context data using one or more cognitive or machine learning algorithms. The inferred context data may include semantic time or location data, activity data, or sentiment data. The computing device updates a user context model and an expanded media object graph based on the context data and the inferred context data. The computing device selects one or more target media objects using the user context model and the expanded media object graph. The computing device may present context-aware media experiences to the user with the target media objects. Context-aware media experiences may include contextual semantic search and contextual media browsing. Other embodiments are described and claimed.

Claims

1. A computing device for contextual media curation, the computing device comprising:

content acquisition module to acquire a plurality of media objects;

context capture module to capture context data associated with a context of one or more media objects of the plurality of media objects;

context analysis module to (i) generate inferred context data based on the context data associated with the context of the one or more media objects, (ii) update a user context model based on the context data associated with the context of the one or more media objects and the inferred context data, and (iii) generate an expanded media object graph based on the context data associated with the context of the one or more media objects and the inferred context data, wherein the expanded media object graph is indicative of relationships between the plurality of media objects; and

media experience module to select one or more target media objects from the plurality of media objects based on the user context model and the expanded media object graph.

2. The computing device of claim 1, wherein:

to capture the context data associated with the context of the one or more media objects comprises to capture location data associated with a mobile computing device associated with the one or more media objects; and

to generate the inferred context data based on the context data comprises to generate semantic location data associated with the context of the one or more media objects based on the location data associated with the mobile computing device.

3. The computing device of claim 1, wherein to capture the context data associated with the context of the one or more media objects comprises to capture user behavior data associated with the one or more media objects from a mobile computing device.

4. The computing device of claim 1, wherein:

to capture the context data associated with the context of the one or more media objects comprises to capture social activity data from a public media server; and

to generate the inferred context data based on the context data comprises to generate inferred context data based on the social activity data.

5. The computing device of claim 1, wherein to capture the context data associated with the context of the one or more media objects comprises to capture proximity data associated with a mobile computing device associated with the one or more media objects, wherein the proximity data is indicative of persons near the mobile computing device.

6. The computing device of claim 1, wherein:

to capture the context data associated with the context of the one or more media objects comprises to capture audio data from a mobile computing device associated with the one or more media objects; and

to generate the inferred context data based on the context data associated with the current context of the one or more media objects comprises to classify an audio environment based on the audio data.

7. The computing device of claim 1, wherein to generate the inferred context data based on the context data associated with the context of the one or more media objects comprises to generate semantic time data based on the context of the one or more media objects.

8. The computing device of claim 1, wherein to generate the inferred context data based on the context data associated with the context of the one or more media objects comprises to generate an activity label associated with the context of the one or more media objects.

9. The computing device of claim 1, wherein to generate the inferred context data based on the context data associated with the context of the one or more media objects comprises to analyze image data of the plurality of media objects.

10. The computing device of claim 1, wherein to select the one or more target media objects from the plurality of media objects based on the user context model and the expanded media object graph comprises to perform a contextual semantic search of the plurality of media objects.

11. The computing device of claim 1, wherein to select the one or more target media objects from the plurality of media objects based on the user context model and the expanded media object graph comprises to rank the one or more target media objects based on relevance of the expanded media object graph associated with the target media objects and a current user context of the user context model.

12. The computing device of claim 1, wherein to select the one or more target media objects from the plurality of media objects based on the user context model and the expanded media object graph comprises to group the one or more target media objects based on the inferred context data.

13. The computing device of claim 1, wherein the media experience module is further to recommend one or more target persons associated with the one or more target media objects based on the user context model and the expanded media object graph.

14. A method for contextual media curation, the method comprising:

acquiring, by a computing device, a plurality of media objects;

capturing, by the computing device, context data associated with a context of one or more media objects of the plurality of media objects;

generating, by the computing device, inferred context data based on the context data associated with the context of the one or more media objects;

updating, by the computing device, a user context model based on the context data associated with the context of the one or more media objects and the inferred context data;

generating, by the computing device, an expanded media object graph based on the context data associated with the context of the one or more media objects and the inferred context data, wherein the expanded media object graph is indicative of relationships between the plurality of media objects; and

selecting, by the computing device, one or more target media objects from the plurality of media objects based on the user context model and the expanded media object graph.

15. The method of claim 14, wherein:

capturing the context data associated with the context of the one or more media objects comprises capturing location data associated with a mobile computing device associated with the one or more media objects; and

generating the inferred context data based on the context data comprises generating semantic location data associated with the context of the one or more media objects based on the location data associated with the mobile computing device.

16. The method of claim 14, wherein:

capturing the context data associated with the context of the one or more media objects comprises capturing social activity data from a public media server; and

generating the inferred context data based on the context data comprises generating inferred context data based on the social activity data.

17. The method of claim 14, wherein selecting the one or more target media objects from the plurality of media objects based on the user context model and the expanded media object graph comprises performing a contextual semantic search of the plurality of media objects.

18. The method of claim 14, wherein selecting the one or more target media objects from the plurality of media objects based on the user context model and the expanded media object graph comprises ranking the one or more target media objects based on relevance of the expanded media object graph associated with the target media objects and a current user context of the user context model.

19. The method of claim 14, further comprising recommending, by the computing device, one or more target persons associated with the one or more target media objects based on the user context model and the expanded media object graph.

20. One or more computer-readable storage media comprising a plurality of instructions that in response to being executed cause a computing device to:

acquire a plurality of media objects;

capture context data associated with a context of one or more media objects of the plurality of media objects;

generate inferred context data based on the context data associated with the context of the one or more media objects;

update a user context model based on the context data associated with the context of the one or more media objects and the inferred context data;

generate an expanded media object graph based on the context data associated with the context of the one or more media objects and the inferred context data, wherein the expanded media object graph is indicative of relationships between the plurality of media objects; and

select one or more target media objects from the plurality of media objects based on the user context model and the expanded media object graph.

21. The one or more computer-readable storage media of claim 20, wherein:

to capture the context data associated with the context of the one or more media objects comprises to capture location data associated with a mobile computing device associated with the one or more media objects; and

to generate the inferred context data based on the context data comprises to generate semantic location data associated with the context of the one or more media objects based on the location data associated with the mobile computing device.

22. The one or more computer-readable storage media of claim 20, wherein:

to capture the context data associated with the context of the one or more media objects comprises to capture social activity data from a public media server; and

to generate the inferred context data based on the context data comprises to generate inferred context data based on the social activity data.

23. The one or more computer-readable storage media of claim 20, wherein to select the one or more target media objects from the plurality of media objects based on the user context model and the expanded media object graph comprises to perform a contextual semantic search of the plurality of media objects.

24. The one or more computer-readable storage media of claim 20, wherein to select the one or more target media objects from the plurality of media objects based on the user context model and the expanded media object graph comprises to rank the one or more target media objects based on relevance of the expanded media object graph associated with the target media objects and a current user context of the user context model.

25. The one or more computer-readable storage media of claim 20, further comprising a plurality of instructions that in response to being executed cause the computing device to recommend one or more target persons associated with the one or more target media objects based on the user context model and the expanded media object graph.