Video viewer targeting based on preference similarity

Patent metadata

Field	Value
Publication number	US-9612995-B2
Application number	US-201113111705-A
Country	US
Kind code	B2
Filing date	May 19, 2011
Priority date	Sep 17, 2008
Publication date	Apr 4, 2017
Grant date	Apr 4, 2017

Abstract

Presentation of a video clip is made to persons having a high probability of viewing the clip. A database containing viewers of previously offered video clips is analyzed to determine similarities of preferences among viewers. When a new video clip has been watched by one or more viewers in the database, those viewers who have watched the new clip with positive results are compared with others in the database who have not yet seen it. Prospective viewers with similar preferences are identified as high likelihood candidates to watch the new clip when presented. Bids to offer the clip are based on the degree of likelihood. For one embodiment, a data collection agent (DCA) is loaded to a player and/or to a web page to collect viewing and behavior information to determine viewer preferences. Viewer behavior may be monitored passively by different disclosed methods.

First claim

The invention claimed is:

1. A computer implemented method for outputting a video clip to a display screen of a viewer, comprising:
building, by one or more processors and storing in a computer-readable medium, a database of viewer preferences respective of a first set of video clips;
analyzing, by the one or more processors, the database of viewer preferences respective of a first set of video clips to determine preference similarities among viewers in a first viewer list who watched the first set of video clips;
recording, by the one or more processors and storing, in the database viewer preferences respective of a second video clip;
analyzing, by the one or more processors, viewer preferences respective of the second video clip with respect to the database to:
identify a second list of viewers who watched the second video clip and who viewed the second video clip in at least one of a plurality of positive manners;
produce a third list of viewers in the database who have not yet viewed the second video clip and are most likely to watch the second video clip based on preference similarities with viewers in both: (1) the first list of viewers of the first set of video clips, and (2) the second list of viewers of the second video clip who viewed the second video clip in the at least one of the plurality of positive manners; and

causing the second video clip to be output to a display screen of at least one viewer in the third list of viewers who are most likely to watch the second video clip,
wherein a likelihood determination for viewers in the third list who are most likely to watch the second video clip is made by:
analyzing preference-related parameters associated with viewers,
weighting the parameters,
developing a likelihood score based on the weighted parameters, and comparing the likelihood score with a defined likelihood level.

2. The method of claim 1 , wherein viewer preferences are collected passively without requesting the viewer for a specific input for rating a video clip.

3. The method of claim 2 , wherein viewer preferences reflecting viewer actions prior to playing the video clip comprise any of:
viewing a pre-roll advertisement;
accessing the video clip by a particular method comprising any of: authenticating or logging-in, or being incentivized to see the video clip;
adjusting a bit rate for streaming or downloading the video clip prior to playing the video clip, including a direction in which the viewer adjusted the bit rate; or
clicking play if the video clip is not an auto-playing video clip.

4. The method of claim 2 , wherein viewer preferences reflecting viewer actions while playing the video clip comprise any of:
adjusting volume level, muting, or un-muting the video clip;
pausing or un-pausing the video clip;
fast-forwarding or rewinding the video clip;
replaying the video clip, how many times the video clip was replayed, and what portion of the video clip was replayed;
viewing the video clip for a recorded duration and percent completion;
viewing the video clip in full-screen mode;
adjusting a bit rate for streaming or downloading the video clip while playing it, including a direction in which the viewer adjusted the bit rate of the video clip;
clicking-through on an overlay image or on the video clip itself to be taken to another webpage or website;
spending time viewing certain segments of the video clip that are judged to have higher value based on actions of previous viewers; or
viewing a mid-roll advertisement.

5. The method of claim 2 , wherein viewer preferences reflecting viewer actions after playing the video clip comprise any of:
sharing the video clip via an embedded code;
sharing the video clip via e-mail;
sharing the video clip via a social network;
sharing the video clip in multiple separate events, where a number of separate sharing events initiated by the viewer to share the video clip are recorded;
waiting for a time duration between viewing the video clip and initiating a sharing event,
wherein said time duration is recorded;
bookmarking the video clip for later viewing;
downloading and saving the video clip for later viewing; or
subscribing to a channel or feed for a video clip content producer or artist.

6. The method of claim 1 , wherein said analyzing the database to determine preference similarities is determined at least in part with a collaborative filter.

7. The method of claim 1 , wherein the second video clip is a video advertisement.

8. The method of claim 7 , further comprising:
assigning a bid value for an ad impression of the video advertisement to be offered to an identified prospective viewer, the assignment of the bid value based on a relative likelihood that the identified prospective viewer will watch the video advertisement.

Assignees

• Lopatecki Jason
• Rose Adam
• Hughes John
• Wilson Brett
• Adobe Systems Inc

Inventors

• Lopatecki Jason
• Rose Adam
• Hughes John
• Wilson Brett

Classifications

• G06F16/7867

  using information manually generated, e.g. tags, keywords, comments, title and artist information, manually generated time, location and usage information, user ratings · CPC title

• H04N21/2668

  Creating a channel for a dedicated end-user group, e.g. insertion of targeted commercials based on end-user profiles {(information retrieval from the Internet by querying with filtering and personalisation G06F16/9535; arrangements for replacing or switching information during the broadcast H04H20/10; push services over packet-switching network H04L12/1859; adaptation of message content in packet-switching networks H04L51/063)} · CPC title

• G06F16/743

  a collection of video files or sequences · CPC title

• H04N21/278

  Content descriptor database or directory service for end-user access {(details of content or meta data based information retrieval of video data in video databases G06F16/739)} · CPC title

• G06F15/16 Primary

  Combinations of two or more digital computers each having at least an arithmetic unit, a program unit and a register, e.g. for a simultaneous processing of several programs {(coordinating program control therefor G06F9/52; in regulating and control system G05B)} · CPC title