Empirical ad pod detection

• US 9,584,858 B2
• Filed: 03/14/2013
• Issued: 02/28/2017
• Est. Priority Date: 03/19/2012
• Status: Active Grant

• Current Assignee: comScore, Inc.
• Original Assignee: comScore, Inc.
• Inventors: Vinson, Michael, Loper, Maria, Yazdani, Amir, Goerlich, Bruce
• Primary Examiner(s): VU, NGOC K
• Application Number:
  US13/827,842
• Publication Number:
  US 20130247080A1
• Time in Patent Office: 1,447 Days
• Field of Search: 725/9, 725/14, 725/16, 725/21, 705/14.41, 705/14.44, 705/14.46
• US Class Current: 1/1
• CPC Class Codes: H04N 21/42213 for facilitating data entry
• 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 21/44204 Monitoring of content usage, e.g. the number of times a movie has been viewed, copied or the amount which has been watched monitoring of user activities for profile generation for accessing a video database G06F16/739; protecting generic digital content where the protection is independent of the precise nature of the content G06F21/10; arrangements for monitoring the use made of the broadcast services in broadcast systems H04H60/31
• 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 21/44218 Detecting physical presence or behaviour of the user, e.g. using sensors to detect if the user is leaving the room or changes his face expression during a TV program methods or arrangements for recognising human body or animal bodies or body parts G06V40/10; methods or arrangements for acquiring or recognising human faces, facial parts, facial sketches, facial expressions G06V40/16; methods or arrangements for recognising movements or behaviour G06V40/20; arrangements for identifying users in broadcast systems H04H60/45
• CPC Class Codes: H04N 21/44224 Monitoring of user activity on external systems, e.g. Internet browsing
• 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 21/47217 for controlling playback functions for recorded or on-demand content, e.g. using progress bars, mode or play-point indicators or bookmarks specific graphical features in visual interfaces H04N21/4312
• CPC Class Codes: H04N 21/6582 Data stored in the client, e.g. viewing habits, hardware capabilities, credit card number arrangements where receivers interact with the broadcast H04H20/38
• CPC Class Codes: H04N 21/812 involving advertisement data advertising per se G06Q30/02

Abstract

A system and method for analyzing the viewing behavior of end users that are viewing video content to determine the likely presence of one or more advertisements being viewed and to assess the viewers who stop viewing during the course of such advertisements. The system periodically or continuously receives tune data reflecting the viewing behavior of end users, analyzes the cumulative viewing behavior reflected by the received tune data, and delivers a report of the analysis to advertisers, agencies, media sellers, or other parties that are interested in measuring the effectiveness of advertisements on end users. The analysis by the system can be done over multiple different types of content-distribution platforms.

Claims

1. A computer-implemented method performed at a viewing behavior analysis system in communication across a network with a plurality of content providers and a plurality of video playback devices, the method for assessing drops in viewership during one or more advertisements that are broadcast in association with content having a scheduled programming variation, the method comprising:

receiving, at the viewing behavior analysis system, tune data across the network from one or more clients, each client associated with a video playback device of the plurality of playback devices and capturing events representing viewing behavior of content on the associated video playback device;

receiving, at the viewing behavior analysis system, a selection of content from a user on which to perform a viewing analysis, the selection including the variation from scheduled programming;

analyzing, at the viewing behavior analysis system, tune data associated with the selected content in order to construct a profile of viewership across a number of clients, the viewership profile reflecting an actual or extrapolated number of viewers that viewed the content during a corresponding presentation period, the presentation period including the variation from scheduled programming;

analyzing, at the viewing behavior analysis system, the viewership profile to identify one or more drops in viewers during the corresponding presentation period that exceeds a threshold rate, the identified one or more drops indicative of an advertisement or advertisements presented in conjunction with the content;

for each of the identified drops that exceeds the threshold rate, estimating, at the viewing behavior analysis system, a start point and an end point for the identified drop;

calculating, at the viewing behavior analysis system, a viewership loss rate for each drop, wherein the loss rate is calculated over a time interval determined by the estimated start point and end point and wherein the loss rate reflects a drop in viewership as a result of the advertisements; and

providing, from the viewing behavior analysis system, a report of the viewership loss rate for each drop, the report indicating when the advertisements were offset in response to the variation from scheduled programming in a time series graphical representation.

2. The method of claim 1, wherein the tune data includes power-up or power-down events, channel changing or content switching events, or playback events.

3. The method of claim 1, wherein the clients include a set-top box client, a digital video recorder client, a viewer measurement device client, and a computing device client.

4. The method of claim 1, wherein the content is selected by the user by specifying a time period during which content was presented.

5. The method of claim 1, wherein the content is selected by the user specifying a program or other discrete piece of content.

6. The method of claim 1, wherein the extrapolated number of viewers is determined by taking an actual number of viewers and estimating a number of viewers for which tune data is missing from clients.

7. The method of claim 1, further comprising adjusting the actual or extrapolated number of viewers based on a confidence in the tune data received from certain clients.

8. The method of claim 7, wherein the adjustment is made by applying a weighting factor to tune data from one or more clients.

9. The method of claim 1, wherein the threshold rate is based on a percentage of the tune data and the number of viewers at the start of the presentation period.

10. The method of claim 1, further comprising:

analyzing the identified drops to determine if a start point and an end point of different adjacent drops overlap in time; and

applying a reconciliation process for those identified adjacent drops that have overlapping start points and end points.

11. The method of claim 1, further comprising using the calculated viewership loss rate for each drop to calculate an ad retention index for the corresponding content.

12. The method of claim 1, further comprising:

receiving a desired geographic or demographic segmentation; and

filtering the analyzed tune data associated with the selected content to only use tune data associated with the desired geographic or demographic segmentation.

13. A non-transitory computer readable medium encoded with instructions that, when executed by a processor, perform a method for assessing drops in viewership during one or more advertisements that are broadcast in association with content having a scheduled programming variation, the method comprising:

receiving, at a viewing behavior analysis system, tune data across a network from one or more clients, each client associated with a video playback device of a plurality of playback devices and capturing events representing viewing behavior of content on the associated video playback device;

receiving, at the viewing behavior analysis system, a selection of content from a user on which to perform a viewing analysis, the selection including a variation from scheduled programming;

analyzing, at the viewing behavior analysis system, tune data associated with the selected content in order to construct a profile of viewership across a number of clients, the viewership profile reflecting an actual or extrapolated number of viewers that viewed the content during a corresponding presentation period, the presentation period including the variation from scheduled programming;

analyzing, at the viewing behavior analysis system, the viewership profile to identify one or more drops in viewers during the corresponding presentation period that exceeds a threshold rate, the identified one or more drops indicative of an advertisement or advertisements presented in conjunction with the content;

for each of the identified drops that exceeds the threshold rate, estimating, at the viewing behavior analysis system, a start point and an end point for the identified drop;

calculating, at the viewing behavior analysis system, a viewership loss rate for each drop, wherein the loss rate is calculated over a time interval determined by the estimated start point and end point and wherein the loss rate reflects a drop in viewership as a result of the advertisements; and

providing, from the viewing behavior analysis system, a report of the viewership loss rate for each drop, the report indicating when the advertisements were offset in response to the variation from scheduled programming in a time series graphical representation.

14. The non-transitory computer readable medium of claim 13, wherein the tune data includes power-up or power-down events, channel changing or content switching events, or playback events.

15. The non-transitory computer readable medium of claim 13, wherein the extrapolated number of viewers is determined by taking an actual number of viewers and estimating a number of viewers for which tune data is missing from clients.

16. The non-transitory computer readable medium of claim 13, further comprising:

adjusting the actual or extrapolated number of viewers based on a confidence in the tune data received from certain clients.

17. The non-transitory computer readable medium of claim 15, wherein the adjustment is made by applying a weighting factor to tune data from one or more clients.

18. The non-transitory computer readable medium of claim 13, wherein the threshold rate is based on a percentage of the tune data and the number of viewers at the start of the presentation period.

19. The non-transitory computer readable medium of claim 13, further comprising:

receiving a desired geographic or demographic segmentation; and

filtering the analyzed tune data associated with the selected content to only use tune data associated with the desired geographic or demographic segmentation.

20. The non-transitory computer readable medium of claim 13, further comprising:

using the calculated viewership loss rate for each drop to calculate an ad retention index for the corresponding content.