Retrieval and display of related content using text stream data feeds

• US 8,996,496 B2
• Filed: 02/18/2010
• Issued: 03/31/2015
• Est. Priority Date: 02/18/2010
• Status: Active Grant

• Current Assignee: TiVo Corporation (Adeia Inc.)
• Original Assignee: MobiTV Incorporated (Adeia Inc.)
• Inventors: Stiers, Todd
• Primary Examiner(s): PHILLIPS, III, ALBERT M
• Application Number:
  US12/708,350
• Publication Number:
  US 20110202515A1
• Time in Patent Office: 1,867 Days
• Field of Search: 707/796, 707/707
• US Class Current: 707/707
• CPC Class Codes: G06F 16/435 Filtering based on additional data, e.g. user or group profiles
• CPC Class Codes: G06F 16/437 Administration of user profiles, e.g. generation, initialisation, adaptation, distribution
• CPC Class Codes: G06F 16/438 Presentation of query results
• 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: G06F 16/7867 using information manually generated, e.g. tags, keywords, comments, title and artist information, manually generated time, location and usage information, user ratings
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06F 16/9538 Presentation of query results
• CPC Class Codes: H04L 51/52 for supporting social networking services
• CPC Class Codes: H04L 65/60 Network streaming of media packets
• CPC Class Codes: H04L 65/65 Network streaming protocols, e.g. real-time transport protocol [RTP] or real-time control protocol [RTCP]
• CPC Class Codes: H04L 65/762 at the source reformatting of additional data in video distribution servers H04N21/2355
• CPC Class Codes: H04L 67/10 in which an application is distributed across nodes in the network software deployment G06F8/60; multiprogramming arrangements G06F9/46
• CPC Class Codes: H04L 67/306 User profiles
• CPC Class Codes: Y10S 707/914 Video

Abstract

Mechanisms are provided for retrieving and presenting related content using text stream data feeds. Text stream data feeds such as caption information associated with media content or conversations associated with social networking applications are aggregated and used to retrieve related media content, text documents, and advertisements. Text stream data feeds that a user is exposed to may indicate that the user is interested or at least primed for particular types of related content. In particular examples, an inverse vector space search engine is used to determine particular pieces of related content and categories of interest. Post filtering may also be applied to the results.

Claims

1. A method, comprising:

receiving a first video stream including caption information and text obtained between scene changes over a first medium, the first video stream requested by a user;

receiving a social networking feed including social networking information over a second medium, the social networking feed corresponding to the user;

aggregating the caption information, the text obtained between scene changes, and the social networking information to generate an aggregated text stream, wherein a search vector is generated using the aggregated text stream, the search vector including one or more elements selected from one or more social networking conversations described by the social networking information;

selecting a second video stream from a plurality of video streams by using the generated search vector, wherein the second video stream includes content corresponding to the aggregated text stream as identified by a processor;

transmitting the second video stream to the user over the first medium.

2. The method of claim 1, wherein a plurality distances between the search vector and a plurality of content vectors in an inverse vector space search engine matrix are determined.

3. The method of claim 1, wherein a user is profiled based on categories of content provided.

4. The method of claim 3, wherein post filtering is applied to remove inappropriate content.

5. The method of claim 1, wherein the first medium is a real-time broadcast.

6. The method of claim 5, wherein the second medium is web content.

7. The method of claim 1, wherein content provided comprises a recommendation.

8. The method of claim 1, wherein the second video stream comprises an advertisement.

9. The method of claim 1, wherein the caption information and the social networking information are aggregated upon reaching a threshold of words or characters.

10. The method of claim 1, wherein the caption information and the social networking information are aggregated during predetermined intervals.

11. The method of claim 1, wherein the caption information and the social networking information are aggregated upon detecting one of a plurality of keywords.

12. The method of claim 1, wherein the caption information is a real-time data feed.

13. A system, comprising:

an interface configured to receive a first video stream including caption information and text obtained between scene changes over a first medium, the first video stream requested by a user, wherein the interface is further configured to receive a social networking feed including social networking information over a second medium, the social networking feed corresponding to the user;

a processor configured to;

aggregate the caption information, the text obtained between scene changes, and the social networking information to generate an aggregated text stream,

generate a search vector using the aggregated text stream, the search vector including one or more elements selected from one or more social networking conversations described by the social networking information, and

select a second video stream from a plurality of video streams by using the search vector, wherein the second video stream includes content corresponding to the aggregated text stream as identified by a processor;

identify a second video stream using the aggregated text stream;

wherein the second video stream is transmitted to the user over the first medium.

14. The system of claim 13, wherein a plurality distances between the search vector and a plurality of content vectors in an inverse vector space search engine matrix are determined.

15. The system of claim 13, wherein a user is profiled based on categories of content provided.

16. The system of claim 15, wherein post filtering is applied to remove inappropriate content.

17. The system of claim 13, wherein the first medium is a real-time broadcast.

18. A non-transitory computer readable medium, comprising:

computer code for receiving a first video stream including caption information and text obtained between scene changes over a first medium, the first video stream requested by a user;

computer code for receiving a social networking feed including social networking information over a second medium, the social networking feed corresponding to the user;

computer code for aggregating the caption information, the text obtained between scene changes, and the social networking information to generate an aggregated text stream, wherein a search vector is generated using the aggregated text stream, the search vector including one or more elements selected from one or more social networking conversations described by the social networking information;

computer code for selecting a second video stream from a plurality of video streams by using the search vector, wherein the second video stream includes content corresponding to the aggregated text stream as identified by a processor;

identifying a second video stream using the aggregated text stream;

computer code for transmitting the second video stream to the user over the first medium.