Serving video content segments

• US 9,066,122 B1
• Filed: 03/08/2013
• Issued: 06/23/2015
• Est. Priority Date: 03/08/2013
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Rajkumar, Nareshkumar, Ramachandran, Vinod Kumar, Chung, Wook Jin, Rattazzi, Nicholas Urbano
• Primary Examiner(s): Harold, Jefferey
• Assistant Examiner(s): Monshi, Samira
• Application Number:
  US13/789,951
• Time in Patent Office: 837 Days
• US Class Current: 1/1
• CPC Class Codes: H04N 21/251 Learning process for intelligent management, e.g. learning user preferences for recommending movies details of learning user preferences for the retrieval of video data in a video database G06F16/739; computer systems using learning methods G06N3/08
• CPC Class Codes: H04N 21/26233 involving content or additional data duration or size, e.g. length of a movie, size of an executable file
• CPC Class Codes: H04N 21/2668 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 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 21/6582 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 method, executed on a processor, for serving a video content segment at an online resource includes receiving a request for a video content segment having one or more playback features; identifying, by the processor, one or more candidate video content segments responsive to the request; accessing, by the processor, for each of the candidate video content segments, a score based on (i) one or more metrics related to a measure of the probability of the video content segment being played and (ii) a bid; identifying, by the processor, one or more candidate sets of candidate video segments, where, for each set, the candidate video content segments in the set collectively satisfy the one or more playback features; and selecting, by the processor, in response to the request, one of the candidate sets whose cumulative scores are higher than at least one other candidate set.

Claims

1. A method, executed on a processor, for maximizing revenue from serving a video content segment at an online resource, comprising:

receiving, by the processor, a request for a video content segment having one or more playback features;

identifying, by the processor, one or more candidate video content segments responsive to the request;

computing, by the processor, a length factor (LF) for each candidate video content segment based on a duration of the candidate video content segment, a higher length factor (LF) corresponding to a shorter duration;

computing, by the processor, an interestingness factor (IF) for each candidate video content segment, the interestingness factor (IF) representing the probability of the candidate video content segment being played and computed based on a number of video plays and one or more of a number of video replays, a number of video maximizes, and a number of link activations;

receiving, by the processor, a bid for each candidate video content segment;

generating, by the processor, for each of the candidate video content segments, a rank equal to the length factor (LF) times the interestingness factor (IF) times the bid;

identifying, by the processor, one or more candidate sets of candidate video content segments, where, for each candidate set, the candidate video content segments in the candidate set collectively satisfy the one or more playback features, and

selecting, by the processor, in response to the request, one of the candidate sets whose cumulative scores are higher than at least one other candidate set.

2. The method of claim 1, wherein the video content segments are video advertisements.

3. The method of claim 2, further comprising:

computing interestingness factor (IF) for each of the video advertisements, comprising;

receiving data indicative of one or more user interactions with a video advertisement;

computing a weighted score for each of the one or more user interactions; and

summing the weighted scores.

4. The method of claim 3, wherein the user interactions comprising pauses/stops, played length, replays, viewing screen maximizing, volume mute, and activating a link.

5. The method of claim 2, wherein the playback features further include an audio noise level and a contrast.

6. The method of claim 2, wherein the bid is one of a base bid plus one or more bid increments, and a maximum bid.

7. A method, executed on a processor, for maximizing revenue from video advertisements served at an Internet Web site, comprising:

receiving, by the processor, a request for a video advertisement to serve at a web page, the video advertisement having playback features;

selecting, by the processor, an initial set of candidate video advertisements responsive to the request based on content information derived from the Web page;

ranking, by the processor, each candidate video advertisement in the initial set of candidate video advertisements, comprising;

receiving a length factor (LF) for each candidate video advertisement based on a length of the candidate video advertisement, a higher length factor (LF) corresponding to a shorter duration,

receiving an interestingness factor (IF) for each candidate video advertisement the interestingness factor (IF) representing the probability of the candidate video content segment being played and computed based on a number of video plays and one or more of a number of video replays, a number of video maximizes, and a number of link activations,

receiving a bid for one or more of the candidate video advertisements, and

computing RANK=LF×

IF×

bid for each of the one or more candidate video advertisements for which a bid was received; and

selecting, by the processor, one or more of the ranked candidate video advertisements to serve at the Web page.

8. The method of claim 7, wherein receiving the interestingness factor (IF) comprises computing the interestingness factor by:

receiving, by the processor, one or more metrics values based on data recorded from user interactions while watching a video advertisement;

applying, by the processor, a weighting factor to each of the received metrics values;

computing, by the processor, an interim interestingness factor based on the weighted metrics values; and

normalizing, by the processor, the interim interestingness factor to produce the interestingness factor (IF).

9. The method of claim 8, wherein the processor received the metrics values from a browser displaying the video advertisement, and wherein the metrics values relate to one or more of pauses/stops, played length, replays, viewing screen maximizing, volume mute, and activating a link.

10. The method of claim 7, further comprising:

receiving a nose factor (NF) for each candidate video advertisement based on noisiness of the candidate video advertisement; and

computing RANK=(NF+LF)×

IF×

bid.

11. The method of claim 7, wherein selecting, by the processor, an initial set of candidate video advertisements based on content information derived from the Web page comprises matching topical keywords associated with content of the Web page to topical keywords derived from each of the video advertisements.

12. The method of claim 11, wherein the content of the Web page comprises content of a video program provided on the Web page.

13. A system for maximizing revenue from video advertisements served at an Internet Web site, comprising:

a processor; and

a non-transitory computer-readable storage medium comprising a program of instructions for selecting and serving the video advertisements, wherein the processor executes the program of instructions to;

receive a request for a video advertisement to serve at a Web page, the video advertisement having playback features;

select an initial set of candidate video advertisements responsive to the request based on content information derived from the Web page;

rank each candidate video advertisement in the initial set of candidate video advertisements, comprising;

receive a length factor (LF) for each candidate video advertisement, a higher length factor (LF) corresponding to a shorter duration

receive an interestingness factor(IF) for each candidate video advertisement, the interestingness factor (IF) representing the probability of the candidate video content segment being played and computed based on a number of video plays and one or more of a number of video replays, a number of video maximizes, and a number of link activations,

receive a bid for one or more of the candidate video advertisements, and

compute RANK=LF×

IF×

bid for each of the one or more candidate video advertisements for which a bid was received;

and

select one or more of the ranked candidate video advertisements to serve on the

Web page.

14. The system of claim 13, wherein to receive the interestingness factor (IF), the processor:

receives on or more metrics values based on data recorded from user interactions while watching a video advertisement;

combines the metrics values to produce a normalized value of the interestingness factor (IF).

15. The system of claim 14, wherein the processor receives the metrics values from a browser displaying the video advertisement, and wherein the metrics values relate to one or more of pauses/stops, played length, replays, viewing screen maximizing, volume mute, and activating a link.

16. The system of claim 13, wherein the processor:

receives a noise factor (NF) for each candidate video advertisement based on noisiness of the candidate video advertisement; and

computing RANK as a combination of NF, LF, IF, and bid.

17. The system of claim 13, wherein the processor selects the set of candidate video advertisements based on content information derived from the Web page matching content information derived from each of the video advertisements.

18. The system of claim 17, wherein the content of the Web page comprises content of a video program provided on the Web page.