System and method of analyzing internet protocol television content for closed-captioning information

• US 8,910,232 B2
• Filed: 09/14/2009
• Issued: 12/09/2014
• Est. Priority Date: 09/14/2009
• Status: Expired due to Fees

• Current Assignee: AT&T Intellectual Property I LP (AT&T, Inc.)
• Original Assignee: AT&T Intellectual Property I LP (AT&T, Inc.)
• Inventors: White, Scott, Cansler, James L.
• Primary Examiner(s): Flynn, Nathan
• Assistant Examiner(s): Marandi, James R
• Application Number:
  US12/558,991
• Publication Number:
  US 20110067079A1
• Time in Patent Office: 1,912 Days
• US Class Current: 725/133
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: H04N 21/4334 Recording operations recording of a television signal H04N5/76; arrangements for recording or accumulating broadcast information or broadcast-related information H04H60/27
• CPC Class Codes: H04N 21/4394 involving operations for analysing the audio stream, e.g. detecting features or characteristics in audio streams arrangements characterised by components specially adapted for monitoring, identification or recognition of audio in broadcast systems H04H60/58
• CPC Class Codes: H04N 21/442 Monitoring of processes or resources, e.g. detecting the failure of a recording device, monitoring the downstream bandwidth, the number of times a movie has been viewed, the storage space available from the internal hard disk arrangements for monitoring broadcast services or broadcast-related services H04H60/29; arrangements for identifying or recognising characteristics with a direct linkage to broadcast information H04H60/35; monitoring of user activities for profile generation for accessing a video database G06F16/739; monitoring in wireless networks H04W24/00
• CPC Class Codes: H04N 21/4532 involving end-user characteristics, e.g. viewer profile, preferences monitoring of user activities for profile generation for accessing a video database G06F16/739; user profiles in network data switching protocols H04L67/306; processing of user preferences or user profiles in wireless networks H04W8/18
• CPC Class Codes: H04N 21/4826 using recommendation lists, e.g. of programs or channels sorted out according to their score
• CPC Class Codes: H04N 21/4884 for displaying subtitles
• CPC Class Codes: H04N 5/76 Television signal recording

Abstract

An Internet Protocol television (IPTV) system includes a selector module that selects a content item and sends a stream of the content item to a set-top box. The set-top box analyzes content information associated with the content item using a speech interpretation algorithm or a text interpretation algorithm to create an index of the content information and determines to record the content item based upon the index of the content information. A method includes sending a content item from an IPTV network to a set-top box, directing the set-top box to analyze content information associated with the content item using a speech interpretation algorithm or a text interpretation algorithm, and directing the set-top box to record the content item based upon the analysis of the content information.

Claims

1. A server device of an Internet Protocol television system, comprising:

a memory to store instructions; and

a processor coupled to the memory, wherein the processor, responsive to executing the instructions, performs operations comprising;

selecting a content item;

sending the content item that is selected to a set-top box; and

directing the set-top box to perform operations comprising;

recording the content item on the set-top box as a recorded content item;

determining first information based on a personalization profile of a subscriber, wherein the first information comprises subjects of interest for the subscriber;

determining that metadata of the content item does not match the first information;

responsive to determining that the content item does not match the first information;

analyzing content information associated with the recorded content item using a speech interpretation algorithm to create an index of the content information;

determining, based on the index, whether the content information matches the first information;

recommending the recorded content item to the subscriber if the content information matches the first information of the personalization profile; and

deleting the recorded content item if the content information does not match the first information of the personalization profile.

2. The server of claim 1, wherein analyzing the content information further comprises using a text interpretation algorithm that is adapted to analyze a closed captioning track of the recorded content item.

3. The server of claim 2, wherein the text interpretation algorithm is further adapted to analyze the closed captioning track using a screen-to-text algorithm.

4. The server of claim 1, wherein the processor further performs operations comprising modifying the personalization profile responsive to recommending the recorded content item.

5. The server of claim 1, wherein the speech interpretation algorithm is adapted to analyze an audio track of the recorded content item.

6. The server of claim 5, wherein the speech interpretation algorithm is further adapted to analyze the audio track using a speech-to-text algorithm.

7. The server of claim 6, wherein the speech interpretation algorithm is adapted to determine that a search term is included in the audio track.

8. A set-top box, comprising:

a memory to store instructions; and

a processor coupled to the memory, wherein the processor, responsive to executing the instructions, performs operations comprising;

recording a content item from an interactive television network;

determining first information based on a personalization profile of a subscriber,

wherein the first information comprises subjects of interest for the subscriber;

determining that metadata of the content item does not match the first information;

responsive to determining that the content item does not match the first information;

analyzing content information associated with the recorded content item using a text interpretation algorithm to create an index of the content information;

determining, based on the index, whether the content information matches the first information;

recommending the recorded content item to the subscriber if the content information matches the first information of the personalization profile; and

deleting the recorded content item if the content information does not match the first information of the personalization profile.

9. The set-top box of claim 8, wherein the text interpretation algorithm is adapted to analyze a closed captioning track of the recorded content item.

10. The set-top box of claim 9, wherein the text interpretation algorithm is further adapted to analyze the closed captioning track using a screen-to-text algorithm.

11. The set-top box of claim 10, wherein the text interpretation algorithm is adapted to determine that a search term is included in the closed captioning track.

12. The set-top box of claim 8, wherein analyzing the content information further comprises using a speech interpretation algorithm that is adapted to analyze an audio track of the recorded content item.

13. The set-top box of claim 12, wherein the speech interpretation algorithm is further adapted to analyze the audio track using a speech-to-text algorithm.

14. The set-top box of claim 13, wherein the speech interpretation algorithm is adapted to determine that a search term is included in the audio track.

15. A method, comprising:

sending, by a system comprising a processor, a content item to a set-top box;

directing, by the system, the set-top box to record the content item as a recorded content item;

determining, by the system, first information based on a personalization profile of a subscriber, wherein the first information comprises subjects of interest for the subscriber;

determining, by the system, that metadata of the content item does not match the first information;

responsive to determining that the content item does not match the first information;

directing, by the system, the set-top box to analyze content information associated with the recorded content item as an analysis of the content information;

directing, by the system, the set-top box to determine based on the analysis of the content information whether the content information associated with the recorded content item matches the first information;

directing, by the system, the set-top box to recommend the recorded content item to the subscriber if the content information matches the first information of the personalization profile; and

directing, by the system, the set-top box to delete the recorded content item if the content information does not match the first information of the personalization profile.

16. The method of claim 15, wherein the analysis of the content information comprises an analysis of a closed captioning track of the recorded content item.

17. The method of claim 16, wherein the analysis of the closed captioning track comprises a screen-to-text algorithm.

18. The method of claim 15, wherein the analysis of the content information comprises determining that a search term is included in a closed captioning track of the recorded content item.

19. The method of claim 15, wherein the analysis of the content information comprises analysis of an audio track of the recorded content item.

20. The method of claim 19, wherein the analysis of the audio track comprises a speech-to-text algorithm.