Viewing suggestions based on closed-captioned content from multiple tuners

• US 9,900,632 B1
• Filed: 01/17/2017
• Issued: 02/20/2018
• Est. Priority Date: 12/30/2016
• Status: Active Grant

• Current Assignee: Dish Technologies LLC (Dish Network Corporation)
• Original Assignee: Echostar Technologies LLC (Echostar Corporation)
• Inventors: Flores Guerra, Jesus
• Primary Examiner(s): Pierorazio, Michael B
• Application Number:
  US15/408,060
• Time in Patent Office: 399 Days
• Field of Search: 725116
• 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: H04N 21/4263 involving specific tuning arrangements, e.g. two tuners
• CPC Class Codes: H04N 21/435 Processing of additional data, e.g. decrypting of additional data, reconstructing software from modules extracted from the transport stream
• CPC Class Codes: H04N 21/44008 involving operations for analysing video streams, e.g. detecting features or characteristics in the video stream arrangements characterised by components specially adapted for monitoring, identification or recognition of video in broadcast systems H04H60/59
• CPC Class Codes: H04N 21/47214 for content reservation or setting reminders; for requesting event notification, e.g. of sport results or stock market stock exchange data over packet-switching network H04L12/1804; push services over packet-switching network H04L12/1859; notification of incoming messages in packet switching networks H04L51/224
• CPC Class Codes: H04N 21/4755 for defining user preferences, e.g. favourite actors or genre retrieval personalisation and generation of user profiles for the retrieval of video data G06F16/739; user profiles in network data switching protocols H04L67/306
• 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 21/8405 represented by keywords

Abstract

Described are systems, methods and computer program products for suggesting television programs to a user by, for example, analyzing closed caption or subtitle content of unwatched or unrecorded video content to determine if the video content is of interest to the user. The user may indicate one or more keywords for use in the analysis and the analysis may scan the text of the closed caption or subtitle content to identify matches to the keywords. Beside user input keywords, the keywords may also be determined through analysis of video content watched or recorded by the user to determine frequently encountered words. These frequently encountered words may automatically be used in matching the text of the closed caption or subtitle content. The users may also or alternatively select particular words of the frequently encountered words to use for matching.

Claims

1. A television receiver, comprising:

one or more processors;

a plurality of tuners communicatively coupled with the one or more processors;

an audio-video output interface communicatively coupled with the one or more processors; and

a non-transitory computer readable storage medium communicatively coupled with and readable by the one or more processors and having stored therein processor-readable instructions that, when executed by the one or more processors, cause the one or more processors to perform operations including;

receiving video content using an inactive tuner of the plurality of tuners;

obtaining text data corresponding to an audio portion of the video content;

evaluating the text data to identify frequencies of words appearing in the text data;

receiving input corresponding to determination of one or more user-designated keywords;

storing the one or more user-designated keywords to a word list, wherein the word list includes at least a first keyword;

determining that the first keyword appears in the text data with a first frequency greater than a first threshold frequency; and

generating a first interface for output by the audio-video output interface for displaying on a display device in real-time upon determining that the first frequency is greater than the first threshold frequency, wherein the first interface includes a notification identifying a match of the first keyword.

2. The television receiver of claim 1, wherein the inactive tuner corresponds to a tuner of the plurality of tuners that is not being actively used to display live video content on the display device or that is not being actively used to record video content according to a recording schedule or timer.

3. The television receiver of claim 1, wherein obtaining the text data includes decoding a closed caption portion of the video content to generate the text data, decoding a subtitle portion of the video content to generate the text data, retrieving the text data from a network location, processing the audio portion of the video content using a speech-to-text algorithm to generate the text data, or rendering the video content with embedded closed captions or subtitles and generating the text data by performing character recognition on the embedded closed captions or subtitles.

4. The television receiver of claim 1, wherein evaluating includes generating a database including one or more words in the text data and tracking appearances of the one or more words in the text data using the database.

5. The television receiver of claim 1, wherein the input corresponds to user entry of one or more user-designated keywords or selection of one or more user-designated keywords from a word list.

6. The television receiver claim 1, further comprising automatically adding one or more keywords to the word list without user input.

7. The television receiver of claim 1, further comprising generating the word list, wherein generating the word list includes:

monitoring recorded or watched text data corresponding to audio portions of at least one of video content recorded by the television receiver and video content output by the television receiver for immediate display on the display device;

evaluating the recorded or watched text data to rank words appearing in the watched or recorded text data by frequency; and

adding one or more words appearing in the recorded or watched text data having rankings greater than a threshold ranking to the word list.

8. The television receiver of claim 1, wherein the word list includes a second keyword and wherein the operations further include:

determining that the second keyword appears in the text data with a second frequency greater than a second threshold frequency,

wherein generating the first interface includes generating the first interface in real-time upon determining that both the first frequency is greater than the first threshold frequency and the second frequency is greater than the second threshold frequency, and wherein the first interface includes the notification identifying a match of the first keyword, the second keyword, or both the first keyword and the second keyword.

9. A method, comprising:

receiving, by a television receiver, video content using an inactive tuner of the television receiver;

obtaining, by the television receiver, text data corresponding to an audio portion of the video content;

evaluating, by the television receiver, the text data to identify frequencies of words appearing in the text data;

receiving, by the television receiver, input corresponding to determination of one or more user-designated keywords;

storing the one or more user-designated keywords to a word list, wherein the word list includes at least a first keyword;

determining, by the television receiver, that the first keyword appears in the text data with a first frequency greater than a first threshold frequency; and

generating, by the television receiver, a first interface for display on a display device in real-time upon determining that the first frequency is greater than the first threshold frequency, wherein the first interface includes a notification identifying a match of the first keyword.

10. The method of claim 9, wherein the television receiver includes a plurality of tuners, and wherein the inactive tuner corresponds to one of the plurality of tuners that is not being actively used to display live video content on the display device or that is not being actively used to record video content according to a recording schedule or timer.

11. The method of claim 9, wherein obtaining the text data includes decoding a closed caption portion of the video content to generate the text data, decoding a subtitle portion of the video content to generate the text data, retrieving the text data from a network location, processing the audio portion of the video content using a speech-to-text algorithm to generate the text data, or rendering the video content with embedded closed captions or subtitles and generating the text data by performing character recognition on the embedded closed captions or subtitles.

12. The method of claim 9, wherein evaluating includes generating a database including one or more words in the text data and tracking appearances of the one or more words in the text data using the database.

13. The method of claim 9, wherein the input corresponds to user entry of one or more user-designated keywords or selection of one or more user-designated keywords from a word list.

14. The method of claim 9, further comprising automatically adding one or more keywords to the word list without user input.

15. The method of claim 9, further comprising generating the word list, wherein generating the word list includes:

monitoring recorded or watched text data corresponding to audio portions of at least one of video content recorded by the television receiver and video content output by the television receiver for immediate display on the display device;

evaluating the recorded or watched text data to rank words appearing in the watched or recorded text data by frequency; and

adding one or more words appearing in the recorded or watched text data having rankings greater than a threshold ranking to the word list.

16. The method of claim 9, wherein the word list includes a second keyword and wherein the method further comprises:

determining that the second keyword appears in the text data with a second frequency greater than a second threshold frequency,

wherein generating the first interface includes generating the first interface in real-time upon determining that both the first frequency is greater than the first threshold frequency and the second frequency is greater than the second threshold frequency, wherein the first interface includes the notification identifying a match of the first keyword, the second keyword, or both the first keyword and the second keyword.

17. A non-transitory computer readable storage medium comprising instructions that, when executed by one or more processors, cause the one or more processors to perform operations including:

receiving video content using an inactive tuner of a television receiver;

obtaining text data corresponding to an audio portion of the video content;

evaluating the text data to identify frequencies of words appearing in the text data;

receiving input corresponding to determination of one or more user-designated keywords;

storing the one or more user-designated keywords to a word list, wherein the word list includes at least a first keyword;

determining that the first keyword appears in the text data with a first frequency greater than a first threshold frequency; and

generating a first interface for display on a display device in real-time upon determining that the first frequency is greater than the first threshold frequency, wherein the first interface includes a notification identifying a match of the first keyword.

18. The non-transitory computer readable storage medium of claim 17, wherein the television receiver includes a plurality of tuners, and wherein the inactive tuner corresponds to one of the plurality of tuners that is not being actively used to display live video content on the display device or that is not being actively used to record video content according to a recording schedule or timer.

19. The non-transitory computer readable storage medium of claim 17, wherein obtaining the text data includes decoding a closed caption portion of the video content to generate the text data, decoding a subtitle portion of the video content to generate the text data, retrieving the text data from a network location, processing the audio portion of the video content using a speech-to-text algorithm to generate the text data, or rendering the video content with embedded closed captions or subtitles and generating the text data by performing character recognition on the embedded closed captions or subtitles.

20. The non-transitory computer readable storage medium of claim 17, further comprising generating the word list, wherein generating the word list includes:

monitoring recorded or watched text data corresponding to audio portions of at least one of video content recorded by the television receiver and video content output by the television receiver for immediate display on the display device;

evaluating the recorded or watched text data to rank words appearing in the watched or recorded text data by frequency; and

adding one or more words appearing in the recorded or watched text data having rankings greater than a threshold ranking to the word list.