Automatically inserting advertisements into source video content playback streams

Patent metadata

Field	Value
Publication number	US-9554093-B2
Application number	US-62625107-A
Country	US
Kind code	B2
Filing date	Jan 23, 2007
Priority date	Feb 27, 2006
Publication date	Jan 24, 2017
Grant date	Jan 24, 2017

Abstract

Systems and methods for automatically inserting advertisements into source video content playback streams are described. In one aspect, the systems and methods communicate a source video content playback stream to a video player to present source video to a user. During playback of the source video, and in response to receipt of a request from the user to navigate portions of the source video (e.g., a user command to fast forward the source video, rewind the source video, or other action), the systems and methods dynamically define a video advertisement clip insertion point (e.g., and insertion point based on a current playback position). The systems and methods then insert a contextually relevant and/or targeted video advertisement clip into the playback stream for presentation to the user.

First claim

The invention claimed is:

1. A method at least partially implemented by a computer system, the method comprising:
communicating a video content stream to a user to present at least a portion of a source video to the user;
determining one or more insertion points in the video content stream for inserting one or more advertisements using a timeline of the source video;
receiving a video navigation request to skip a portion of the video content stream that includes an insertion point for a particular advertisement during a playback of the video content stream, and in response to receiving another video navigation request to resume the playback of the video content stream following the skip of the portion of the video content stream, determining an additional insertion point for the particular advertisement in a subsequent portion of the video content stream; and
inserting the particular advertisement at the additional insertion point for display when the playback of the video content stream reaches the additional insertion point.

2. The method of claim 1 , wherein the portion of the source video comprise one or more of a shot, a scene, and a chapter.

3. The method of claim 1 , wherein each of the one or more insertion points is a statically determined insertion point.

4. The method of claim 1 , wherein an insertion point corresponds to a shot boundary or a scene boundary in the source video.

5. The method of claim 1 , wherein the particular advertisement is a video advertisement clip.

6. The method of claim 1 , wherein the particular advertisement is at least one of contextually relevant to a segment of the source video adjacent to the additional insertion point or targeted to information in a user profile associated with the user.

7. The method of claim 1 , wherein the communicating further comprises streaming the source video to a remote computing device for presentation to the user.

8. The method of claim 1 , wherein the method further comprises:
extracting a first set of metadata from the source video;
extracting second sets of metadata from a set of advertisements;
evaluating the first set of metadata and the second sets of metadata to identify a set of candidate advertisements that are contextually relevant to source video content adjacent to an insertion point; and
selecting the advertisements from the set of candidate advertisements.

9. The method of claim 8 , wherein each set of metadata comprise low-level content-based features, high-level semantic attributes, or textual information.

10. A computer-readable data storage device having computer-executable instructions for performing steps comprising:
extracting sets of metadata from a source video and a set of video advertisement clips, at least a portion of the metadata being text data inserted into the source video by an administrator;
evaluating the sets of metadata to identify a contextual relevancy of each video advertisement clip to a segment in the source video;
evaluating a profile of a user and the set of video advertisement clips to identify a user profile relevancy of each video advertisement clip to the profile of the user;
assigning a first weight to a corresponding contextual relevancy of each video advertisement clip and a second weight to a corresponding user profile relevancy of each video advertisement clip to the profile of the user, the first weight being different from the second weight;
calculating a corresponding total measured relevancy for each video advertisement clip based on the corresponding contextual relevancy and the corresponding user profile relevancy;
ranking the set of video advertisement clips based on total measured relevancies to identify a particular video advertisement clip that is most contextually relevant to the segment and most user profile relevant to the user profile;
inserting the particular video advertisement clip into a playback stream at an insertion point in the source video during playback of the source video for presentation to the user, wherein the insertion point is adjacent to the segment in the source video being streamed;
receiving, during the playback of the source video, a video navigation request to skip a portion of the playback stream that includes the insertion point for the particular video advertisement clip; and
in response to receiving another video navigation request to resume the playback of the source video following the skip of the portion of the playback stream, determining an additional insertion point for the particular video advertisement clip in a subsequent portion of the playback stream.

11. The computer-readable data storage device of claim 10 , wherein the sets of metadata comprise low-level content-based features, high-level semantic attributes, or textual information.

12. The computer-readable data storage device of claim 10 , wherein the metadata includes text identifying a predetermined insertion point defined with respect a shot or scene boundary of the source video.

13. The computer-readable data storage device of claim 10 , wherein the sets of metadata comprise data identifying color, motion, genre, location, objects, and text.

14. The computer-readable data storage device of claim 10 , wherein the insertion point is a dynamic insertion point defined responsive to receipt of a source video navigation request from the user.

15. The computer-readable data storage device of claim 10 , wherein the computer-executable instructions further comprise instructions for performing steps comprising collecting user click-through statistics information to generate the profile of the user.

16. The computer-readable data storage device of claim 10 , wherein the inserting the particular video advertisement clip into a playback stream at an insertion point in the source video comprises:
overlaying the particular video advertisement clip in a window on the source video; or
superimposing a caption or text associated with the particular video advertisement on a portion of the source video.

17. The computer-readable data storage device of claim 10 , wherein the determining the additional insertion point for the particular video advertisement clip comprises dynamically defining the additional insertion point at a position where the source video resumes the playback.

18. A computing device comprising:
a processor; and
a memory coupled to the processor, the memory comprising computer-program instructions executable by the processor for performing steps comprising:
collecting advertisement click-through data associated with a user by identifying one or more links embedded in each of one or more advertisements that the user has selected, the one or more advertisements being inserted into a plurality of source videos viewed by the user;
determining one or more insertion points for a source video based at least on the advertisement click-through data of the user;
responsive to a request from the user to stream the source video to the user for presentation, evaluating a profile of the user to locate a video advertisement clip that is relevant to information in a profile associated with the user;
during streaming of the source video to the user, automatically inserting the video advertisement clip into the source video at the one or more insertion points to generate a modified video stream;
receiving a video navigation request to skip a portion of the modified video stream that includes the one or more insertion points; and
in response to receiving another video navigation request to resume playback of the modified vid

Assignees

• Hua Xian-Sheng
• Lai Wei
• Ma Wei-Ying
• Li Shipeng
• Microsoft Technology Licensing Llc

Inventors

• Hua Xian-Sheng
• Lai Wei
• Ma Wei-Ying
• Li Shipeng

Classifications

• H04N21/6587

  Control parameters, e.g. trick play commands, viewpoint selection · CPC title

• H04N21/47202

  for requesting content on demand, e.g. video on demand · CPC title

• H04N21/2387

  Stream processing in response to a playback request from an end-user, e.g. for trick-play · CPC title

• H04N21/23424 Primary

  involving splicing one content stream with another content stream, e.g. for inserting or substituting an advertisement · CPC title

• H04N21/8133

  specifically related to the content, e.g. biography of the actors in a movie, detailed information about an article seen in a video programme · CPC title