System for analyzing television programs

• US 6,295,092 B1
• Filed: 07/30/1998
• Issued: 09/25/2001
• Est. Priority Date: 07/30/1998
• Status: Expired due to Fees

• Current Assignee: CBS Corporation (ViacomCBS Incorporated)
• Original Assignee: CBS Corporation (ViacomCBS Incorporated)
• Inventors: Ross, Robert, Mandel, Alan F., Trosky, William J., Hullinger, Richard A., Bartels, John D., Schultz, Brian A.
• Primary Examiner(s): Eisenzopf, Reinhard J.
• Assistant Examiner(s): DESIR, JEAN WICEL
• Application Number:
  US09/134,667
• Time in Patent Office: 1,153 Days
• Field of Search: H04/N.708, H04/N.7087, H04/N.5445, 348/465, 348/468, 348/460, 348/461, 348/473, 348/478, 348/906, 348/907, 725/2, 725/14, 725/18, 725/22, 725/20, 725/32, 725/37, 725/40, 725/43, 725/45, 725/46, 725/55, 345/327, 345/440, 345/140, 704/3, 704/8, 704/10, 707/531, 707/532, 707/536
• US Class Current: 348/468
• CPC Class Codes: H04H 60/37 for identifying segments of broadcast information, e.g. scenes or extracting programme ID
• CPC Class Codes: H04H 60/64 for providing detail information
• CPC Class Codes: H04H 60/66 for using the result on distributors' side
• CPC Class Codes: H04N 21/21 Server components or server architectures
• CPC Class Codes: H04N 21/23 Processing of content or additional data; Elementary server operations; Server middleware
• CPC Class Codes: H04N 21/812 involving advertisement data advertising per se G06Q30/02
• CPC Class Codes: H04N 7/165 Centralised control of user terminal subsequent to an upstream request signal H04N7/17345; Registering at central by two-way working H04N7/17309

Abstract

A system that automatically captures one or more local news program broadcasts and separates the broadcasts into the individual news stories or segments. The system then compares the stories to historical data concerning the competitive characteristics of the stories for each station and determines the topic (local, national, crime, etc.), talent (newscaster 1, newscaster 2, etc.) and production (live, studio, voice-over-tape, etc.) characteristics of the stories. Other characteristics that affect the popularity and therefor the competitive characteristics of the broadcasts can also be displayed, such as pacing, average story length, news-to-advertisement ratio, broadcast ordering (news then weather then news then sports, etc.), etc. The characteristics are displayed in a visual format, such as a graph, with other historical data, such as show ratings that can be divided into increments such as ¼ hour, and optionally with the actual video/audio broadcast allowing assessment of competitors local news broadcasts.

Claims

1. An apparatus for analyzing television broadcasts, comprising:

a capture system capturing a designated television broadcast; and

an analysis system analyzing the broadcast and determining competitive characteristics of the broadcast;

wherein said capture system removes meaningless text characters from closed-captioned text of the broadcast, determines a broadcast slot for the broadcast and truncates text lines longer than a predetermined length.

2. An apparatus as recited in claim 1, wherein the competitive characteristics comprise one of broadcast topic, talent and production.

3. An apparatus as recited in claim 1 where said analysis system separates the broadcast into individual stories.

4. An apparatus as recited in claim 1, wherein said analysis system determines the competitive characteristics by comparing spoken text of the broadcast with statistical information accumulated about prior broadcasts.

5. An apparatus as recited in claim 1, further comprising a user interface displaying the competitive characteristics of the broadcast for a user.

6. An apparatus as recited in claim 5, wherein said interface graphically displays the characteristics.

7. An apparatus as recited in claim 5, wherein said interface simultaneously displays the characteristics and the broadcast.

8. An apparatus as recited in claim 5, wherein said interface simultaneously displays the characteristics and ratings data for the broadcast.

9. An apparatus as recited in claim 1, wherein said analysis system scores segments of the closed captioned text, determines whether the segments can be combined and rescores the combined segments.

10. An apparatus as recited in claim 9, wherein said apparatus scores and rescores by comparing the text to a vocabulary table and determining a score table from the vocabulary table and accumulating scores for the text from the score table with the highest score for each classification category becoming a classification for the text.

11. An apparatus as recited in claim 10, further comprising a score table tree of statistical information.

12. An apparatus as recited in claim 1, wherein said capture system comprises a capture machine for each television station being analyzed.

13. An apparatus as recited in claim 12, wherein each capture machine comprises:

a closed-caption unit receiving capturing closed captioned text for the broadcast; and

a video/audio capture unit converting a video of the broadcast into digital images and an audio of the broadcast into digital sound.

14. An apparatus for analyzing television broadcasts, comprising:

a capture system having a capture machine for each television station and capturing designated television broadcasts, each capture machine removing meaningless text characters from closed-captioned text of the broadcasts, determining broadcast slots for the broadcasts and truncating text lines longer than a predetermined length, each capture machine comprising;

a closed-caption unit receiving capturing the closed captioned text for the broadcast; and

a video/audio capture unit converting a video of the broadcasts into digital images and an audio of the broadcast into digital sound;

an analysis system separating the captured broadcasts into individual stories, analyzing the individual stories and determining competitive characteristics of the broadcast by comparing the closed-captioned text of the stories with statistical information accumulated about prior broadcasts including scoring all segments of text, determining whether the segments can be combined and rescoring the combined segments, said analysis system scoring and rescoring by comparing the text to a vocabulary table, determining a score table from the vocabulary table and accumulating scores for the text from the score table with the highest score for each classification category becoming a classification for the text, said competitive characteristics comprising one of broadcast topic, talent and production; and

a user interface simultaneously graphically displaying the competitive characteristics of the broadcast and the broadcast for a user.

15. An apparatus, comprising:

storage storing a television broadcast and competitive characteristics of the broadcast;

a graphical user interface system graphically displaying the competitive characteristics; and

a capture unit providing the broadcast and the competitive characteristics;

wherein said system provides an ability to display at least one of broadcast pacing, story length, ratio of news broadcast time to advertisement broadcast time, a list of story segments indicating competitive characteristics of the segments, time related viewer retention data and lead-in related viewer retention data.

16. An apparatus as recited in claim 15, wherein said system displays the broadcast with the characteristics.

17. An apparatus as recited in claim 15, wherein said storage stores ratings data for a broadcast and said system displays the characteristics and the ratings data.

18. An apparatus as recited in claim 15, wherein said storage stores plural broadcasts and corresponding competitive characteristics of the broadcasts and said system simultaneously displays the corresponding characteristics.

19. An apparatus as recited in claim 18, wherein said system simultaneously plays the plural broadcasts.

20. An apparatus as recited in claim 19, wherein the system synchronizes the broadcasts to a one of the broadcasts whose audio is being played.

21. An apparatus as recited in claim 15, wherein said system provides an ability to select at least one of television station, date of capture and time of capture.

22. An apparatus as recited in claim 16, wherein said system performs non-linear playback of video segments.

23. An apparatus, comprising:

a capture system capturing a designated television broadcast, analyzing the broadcast and determining competitive characteristics of the broadcast, said capture system having a capture machine for each television station and capturing designated television broadcasts, each capture machine removing meaningless text characters from closed-captioned text of the broadcasts, determining broadcast slots for the broadcasts and truncating text lines longer than a predetermined length, separating the captured broadcasts into individual stories, analyzing the individual stories and determining competitive characteristics of the broadcast by comparing the closed-captioned text of the stories with statistical information accumulated about prior broadcasts including scoring all segments of text, determining whether the segments can be combined and rescoring the combined segments, said analysis system scoring and rescoring by comparing the text to a vocabulary table, determining a score table from the vocabulary table and accumulating scores for the text from the score table with the highest score for each classification category becoming a classification for the text, and each capture machine comprising;

a closed-caption unit receiving capturing the closed captioned text for the broadcast; and

a video/audio capture unit converting a video of the broadcasts into digital images and an audio of the broadcast into digital sound;

a storage system storing the television broadcasts, competitive characteristics of the broadcasts and ratings data for the broadcasts;

a graphical user interface system graphically displaying the competitive characteristics comprising topic, talent, production, broadcast pacing, story length, ratio of news broadcast time to advertisement broadcast time, time related viewer retention data and lead-in related viewer retention data, playing the stored broadcasts and displaying the ratings data for the broadcasts; and

a storage media storing a process of the capture machine performing the capturing a designated television broadcast and the analyzing the broadcast and the determining competitive characteristics of the broadcast.

24. An apparatus for analyzing television broadcasts including a capture system for capturing designated television broadcasts having competitive characteristics and for receiving ratings data for the broadcasts, characterized by:

a processor for parsing text recovered from said broadcasts into text segments, classifying the text segments according to said competitive characteristics of the broadcasts, and identifying video frames corresponding to the text segments; and

a user interface for presenting the identified video frames and ratings data associated with the identified video frames to a user.

25. An apparatus according to claim 24, further characterized in that said processor includes:

a vocabulary table containing words included in said text; and

a score table containing scores for the words in said vocabulary table.

26. An apparatus according to claim 24, further characterized in that said text includes portions of closed caption text of said broadcast.

27. An apparatus according to claim 24, further characterized in that said processor correlates said competitive characteristics with said ratings data.

28. An apparatus according to claim 24, further characterized in that said competitive characteristics include at least one of:

topic, talent and production type of said broadcast.

29. A method for analyzing television broadcasts including the steps of capturing designated television broadcasts and receiving ratings data for said broadcasts, the method characterized by the steps of:

parsing text recovered from said broadcast into text segments;

classifying the text segments according to competitive characteristics of the broadcasts;

identifying video frames corresponding to the text segments; and

presenting the identified video frames and ratings data associated with the identified video frames to a user.

30. The method of claim 29, further characterized in that the step of classifying the text segments according to competitive characteristics of the broadcasts includes the steps of:

comparing the text segments to a stored vocabulary of text segments; and

scoring the text segments in accordance with scores associated with the stored vocabulary of text segments.

31. The method of claim 30, further characterized by the step of:

combining adjacent text segments corresponding to similar competitive characteristics of the broadcasts to produce combined text segments; and

scoring the combined text segments in accordance with scores associated with the stored vocabulary of text segments.

32. The method of claim 29, further characterized by the steps of:

preparsing closed caption text from said broadcasts to create a preprocessed text file; and

using the preprocessed text file in the step of parsing text recovered from said broadcast into text segments.

33. The method of claim 29, further characterized by the step of:

using header information in a closed caption portion of said broadcasts to establish a date and time of capture.