Determining program boundaries through viewing behavior

• US 20060041902A1
• Filed: 08/23/2004
• Published: 02/23/2006
• Est. Priority Date: 08/23/2004
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Zigmond, Daniel J.
• Granted Patent: US 7,614,064 B2
• Time in Patent Office: Days
• US Class Current: 725/9
• CPC Class Codes: H04H 60/31 Arrangements for monitoring the use made of the broadcast services
• CPC Class Codes: H04H 60/37 for identifying segments of broadcast information, e.g. scenes or extracting programme ID
• CPC Class Codes: H04N 21/25866 Management of end-user data customer care in data networks H04L41/5077
• CPC Class Codes: H04N 21/2747 Remote storage of video programs received via the downstream path, e.g. from the server
• CPC Class Codes: H04N 21/4325 by playing back content from the storage medium reproduction of recorded television signals H04N5/76; reproduction of recorded television signals H04N9/79
• 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 21/44213 Monitoring of end-user related data arrangements for monitoring the users' behaviour or opinions in broadcast systems H04H60/33
• CPC Class Codes: H04N 21/4667 Processing of monitored end-user data, e.g. trend analysis based on the log file of viewer selections
• CPC Class Codes: H04N 21/812 involving advertisement data advertising per se G06Q30/02
• CPC Class Codes: H04N 21/8456 by decomposing the content in the time domain, e.g. in time segments
• CPC Class Codes: H04N 7/17336 Handling of requests in head-ends

Abstract

Program boundaries are determined through viewing behavior. More specifically, edge and/or commercial boundaries of programs may be determined by monitoring viewing behavior of different video segments using forward and backward correlations between video segments. In a described implementation, a video portion is divided into segments. To monitor the viewing of the video portion, whether each particular segment is played by a viewer (as compared to being unviewed or viewed in an accelerated manner) is tracked for a number of different viewers. For each segment, correlations with previous and subsequent segments are calculated based on viewership. The segments may then be categorized. A segment that is strongly correlated with subsequent segments but not previous segments is categorized as a starting segment. A segment that is strongly correlated with previous segments but not subsequent segments is categorized as an ending segment. Middle and island segments may also be categorized.

Claims

1. One or more processor-accessible media comprising processor-executable instructions that, when executed, direct a device to perform actions comprising:

monitoring viewing behavior of segments of a video stream;

calculating correlations between segments responsive to the monitoring; and

determining at least one boundary of the video stream based on the calculated correlations.

2. The one or more processor-accessible media as recited in claim 1, wherein the action of monitoring comprises an action of:

tracking, for a plurality of clients, which segments of the video stream are played.

3. The one or more processor-accessible media as recited in claim 1, wherein the action of monitoring comprises an action of:

tracking, for a plurality of clients, which segments of the video stream are viewed at an accelerated rate.

4. The one or more processor-accessible media as recited in claim 1, wherein the action of calculating comprises an action of:

calculating forward and backward correlations for multiple segments of the video stream based on the monitored viewing behavior.

5. The one or more processor-accessible media as recited in claim 1, wherein the action of determining comprises an action of:

comparing forward and backward correlations of respective segments to one or more thresholds to determine the at least one boundary of the video stream.

6. The one or more processor-accessible media as recited in claim 1, wherein the action of determining comprises an action of:

determining a boundary segment that comprises an edge boundary or a commercial boundary of the video stream.

7. The one or more processor-accessible media as recited in claim 1, wherein the processor-executable instructions, when executed, direct the device to perform further actions comprising:

detecting a request from a client to play a portion of the video stream; and

beginning the portion of the video stream for the client at the determined at least one boundary.

8. The one or more processor-accessible media as recited in claim 1, wherein:

the action of monitoring comprises an action of receiving respective information from respective clients of a plurality of clients, the respective information regarding which segments of the video stream are being played and which segments are being viewed at an accelerated rate at the respective clients; and

the processor-executable instructions, when executed, direct the device to perform a further action comprising;

transmitting the determined at least one boundary of the video stream to another plurality of clients.

9. A server comprising:

a segment viewing monitor that is adapted to monitor how segments of video streams are viewed for each client of a plurality of clients;

a segment playing correlator that is adapted to calculate playing correlations between segments using the segment monitoring; and

a boundary determiner that is adapted to determine boundaries in the video streams using the playing correlations.

10. The server as recited in claim 9, wherein the server comprises at least part of a headend of television-based system.

11. The server as recited in claim 9, further comprising:

a video stream segmenter that is adapted to divide the video streams into time segments that can be monitored individually by the segment viewing monitor.

12. The server as recited in claim 9, wherein the segment viewing monitor is further adapted to track whether the segments of the video streams are being played, are being viewed at an accelerated rate, or are not being viewed for each client of the plurality of clients.

13. The server as recited in claim 9, wherein the segment playing correlator is further adapted to calculate a forward correlation and a backward correlation for each segment of multiple segments of a given video stream.

14. The server as recited in claim 13, wherein a calculation length for the forward correlation and the backward correlation is expressed in units of segments and is selected responsive to an expected duration of a program being measured.

15. The server as recited in claim 13, wherein correlations with respect to each secondary segment are weighted by proximity of the secondary segment to a primary segment being categorized.

16. The server as recited in claim 9, wherein the boundary determiner is further adapted to determine edge boundaries and commercial boundaries of programs in the video streams.

17. The server as recited in claim 9, wherein the boundary determiner is further adapted to categorize segments as starting segments if the playing thereof is strongly correlated with subsequent segments but not with previous segments.

18. The server as recited in claim 9, wherein the boundary determiner is further adapted to categorize segments as ending segments if the playing thereof is strongly correlated with previous segments but not with subsequent segments.

19. The server as recited in claim 9, wherein the boundary determiner is further adapted to categorize segments as middle segment if the playing thereof is strongly correlated with both previous and subsequent segments.

20. The server as recited in claim 9, wherein the boundary determiner is further adapted to categorize segments as island segments if the playing thereof fails to be strongly correlated with either previous or subsequent segments.

21. The server as recited in claim 20, further comprising:

a commercial skipper that is adapted to skip commercial portions of the video streams, the commercial portions identified by amalgamating contiguous segments that are categorized as island segments.

22. An arrangement for determining program boundaries through viewing behavior, the arrangement comprising:

viewing monitor means for monitoring which segments of a video stream are being played;

playing correlator means for calculating correlations for segments of the video stream with regard to whether each segment is played; and

boundary determination means for determining at least one program boundary using the calculated correlations.

23. The arrangement as recited in claim 22, further comprising:

stream segmentation means for segmenting the video stream into a plurality of segments corresponding to discrete time units.

24. The arrangement as recited in claim 22, wherein the viewing monitor means comprises:

means for receiving viewing reports from a plurality of client devices, each viewing report indicating whether at least one segment of the video stream was played by a respective user at a respective client device of the plurality of client devices.

25. The arrangement as recited in claim 22, wherein the viewing monitor means comprises:

means for tracking segments that are being played by respective clients;

means for tracking segments that are not being viewed by the respective clients; and

means for tracking segments that are being viewed at an accelerated rate by the respective clients.

26. The arrangement as recited in claim 22, wherein the boundary determination means comprises:

comparison means for comparing a forward correlation value to a predetermined forward threshold and a backward correlation value to a predetermined backward threshold for each segment of the segments of the video stream.

27. The arrangement as recited in claim 22, wherein the boundary determination means comprises:

categorization means for categorizing the segments of the video stream to identify at least a start segment.

28. The arrangement as recited in claim 27, wherein the categorization means comprises:

comparison means for identifying at least one start segment;

comparison means for identifying at least one end segment;

comparison means for identifying middle segments; and

comparison means for identifying island segments.

29. The arrangement as recited in claim 22, wherein the arrangement comprises at least one of (i) one or more processor-accessible media or (ii) at least one device.

30. A device that is capable of monitoring a segmented video stream to detect which segments are being played by client devices, the device adapted to determine program boundaries of the segmented video stream based on which segments are being played by the client devices.

31. The device as recited in claim 30, wherein the device is further adapted to calculate forward correlations for primary segments with respect to subsequent secondary segments and to calculate backward correlations for the primary segments with respect to previous secondary segments.

32. The device as recited in claim 31, wherein the device is further adapted to compare the forward correlations to a predetermined forward threshold and to compare the backward correlations to a predetermined backward threshold in order to determine segments bounding commercial portions of the segmented video stream;

and wherein the device is capable of creating an index of the commercial portions using the segments bounding the commercial portions so that the commercial portions can be skipped during playback of the segmented video stream.

33. The device as recited in claim 31, wherein the device is further adapted to compare the forward correlations to a predetermined forward threshold and to compare the backward correlations to a predetermined backward threshold in order to determine at least one boundary segment.

34. The device as recited in claim 33, wherein the device is further adapted to categorize a segment as a starting segment if the forward correlation thereof is greater than the predetermined forward threshold and if the backward correlation thereof is less than the predetermined backward threshold.

35. A method comprising:

calculating a backward correlation and a forward correlation for a segment of a video stream with respect to other segments of the video stream and with regard to whether the segments have been played; and

categorizing the segment as a starting segment if the forward correlation is high and the backward correlation is low as compared to at least one threshold.

36. The method as recited in claim 35, further comprising:

monitoring viewing of the video stream to track segments that are played and segments that are viewed at an accelerated rate.

37. The method as recited in claim 35, further comprising:

informing a client device that the segment has been identified as the starting segment for a program of the video stream.

38. The method as recited in claim 35, further comprising:

categorizing the segment as an ending segment if the forward correlation is low and the backward correlation is high as compared to the at least one threshold;

or

categorizing the segment as a middle segment if the forward correlation is high and the backward correlation is high as compared to the at least one threshold.

39. The method as recited in claim 35, further comprising:

categorizing the segment as an island segment if the forward correlation is low and the backward correlation is low as compared to the at least one threshold; and

amalgamating the island segment with other contiguous island segments to identify an island zone corresponding to a commercial portion of the video stream.

40. The method as recited in claim 35, wherein the calculating comprises:

calculating the forward correlation using;

$C_f<br><br>\left(S_n\right)=\underset{i=1}{\overset{l}{\sum <br><br>}}<br><br>\frac{1}{i}<br><br>C<br><br>\left(S_n,S_{n+i}\right);<br><br>\mathrm{and}$

calculating the backward correlation using;

$C_b<br><br>\left(S_n\right)=\underset{i=1}{\overset{l}{\sum <br><br>}}<br><br>\frac{1}{i.}<br><br>C<br><br>\left(S_n,S_{n-i}\right);<br><br>$

wherein S_n represents the primary segment being categorized, l represents a number of secondary segments being considered in the forward or backward direction, and C(S_n, S<sub>n+l−

i</sub>) represents a correlation value between segments S_n and S<sub>n+l−

i</sub>.