Online Ad Placement Based On User Metrics For Hosted Media

• US 20100242060A1
• Filed: 03/19/2009
• Published: 09/23/2010
• Est. Priority Date: 03/19/2009
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Liu, Matthew Cheng-Yu, Goldman, Jonathan Leigh, Rajaraman, Shivakumar Littoo
• Granted Patent: US 8,572,647 B2
• Time in Patent Office: Days
• US Class Current: 725/9
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising

Abstract

The present invention provides methods for determining which ads to present to a user. An embodiment of the method comprises identifying one or more ads, at least one of the identified ads associated with a video. For each identified ad, a first score is calculated. The first score for the identified ad associated with the video is calculated based on one or more metrics representing user interactions associated with viewing the video. In one embodiment, the score for the ad associated with the video will be better (e.g., higher) the more viewers of the video hosting service interact with the associated video, since such interactions thereby indicate a higher over level of viewer interest in the video. One or more of the identified ads are selected to be presented to the user based at least in part on the first score of each of the identified ads. The one or more selected ads are transmitted to a device for presenting to the user.

Claims

1. A computer implemented method for determining which ads to present to a user, the method comprising:

identifying one or more ads, at least one identified ad associated with a video;

for each identified ad, calculating a first score for the ad, the first score for the identified ad associated with the video calculated based at least in part on one or more metrics representing user interactions associated with viewing the video;

selecting one or more of the identified ads to present to the user based at least in part on the calculated first score of each of the identified ads; and

transmitting the selected one or more ads to a device for presenting to the user.

2. The computer implemented method of claim 1, wherein identifying one or more ads comprises:

monitoring user interactions with a video hosting service for an event; and

responsive to detecting the event, identifying the one or more ads based upon the detected event.

3. The computer implemented method of claim 2, wherein the event being monitored for is receiving a search query from the user.

4. The computer implemented method of claim 2, wherein the event being monitored for is receiving a request from the user to access a video.

5. The computer implemented method of claim 2, wherein the event being monitored for is receiving a request from the user to access a specific type of webpage.

6. The computer implemented method of claim 2, wherein identifying the one or more ads based upon the detected event comprises:

identifying one or more search terms based at least in part on the detected event; and

identifying the one or more ads based at least in part on the one or more search terms.

7. The computer implemented method of claim 6, wherein responsive to detecting the event of receiving a request from the user to access a video, identifying one or more search terms comprises:

scanning metadata of the requested video; and

identifying the one or more search terms from words appearing in the metadata of the requested video.

8. The computer implemented method of claim 7, wherein the identified one or more search terms are a set number of words appearing frequently in the metadata of the requested video.

9. The computer implemented method of claim 7, wherein the identified one or more search terms are one or more words having a high relevance within the metadata of the requested video.

10. The computer implemented method of claim 6, wherein responsive to detecting the event of receiving a request from the user to access a specific type of webpage, identifying one or more search terms comprises:

scanning content of the requested webpage; and

identifying the one or more search terms from words appearing in the webpage.

11. The computer implemented method of claim 10, wherein the identified one or more search terms are a set number of words appearing the frequently in the webpage.

12. The computer implemented method of claim 10, wherein the identified one or more search terms are one or more words having a high relevance in the webpage.

13. The computer implemented method of claim 1, wherein calculating the first score for the identified ad associated with the video comprises:

calculating one or more interest scores for the video, each interest score calculated based at least in part on one or more access metrics determined for an instance of access to the video by a viewer;

calculating a net interest score based at least in part on the one or more interest scores, the net interest score representing the overall interest of viewers who have accessed the video; and

calculating the first score for the ad based at least in part on the net interest score.

14. The computer implemented method of claim 13, further comprising:

responsive to a viewer accessing the video, collecting interaction data on interactions between the viewer and an entity presenting the video;

determining based at least in part on the collected data, one or more access metrics for the instance of access to the video; and

calculating a interest score based at least in part on the one or more access metrics.

15. The computer implemented method of claim 14, wherein the interaction data collected is data on selections made and information entered by the viewer in the entity presenting the video.

16. The computer implemented method of claim 14, wherein the entity presenting the video is a webpage.

17. The computer implemented method of claim 14, wherein the entity presenting the video is a video player.

18. The computer implemented method of claim 13, wherein an access metric is an amount of time the video was watched by the viewer.

19. The computer implemented method of claim 13, wherein an access metric is a percentage of the video watched by the viewer.

20. The computer implemented method of claim 13, wherein an access metric is based on whether a specific percentage of the video was watched by the viewer.

21. The computer implemented method of claim 13, wherein an access metric is a number of times the video was watched by the viewer.

22. The computer implemented method of claim 13, wherein an access metric is a rating given to the video by the viewer.

23. The computer implemented method of claim 13, wherein an access metric is based on whether the video was added as a favorite by the viewer.

24. The computer implemented method of claim 13, wherein an access metric is based on whether the video was shared on a webpage or with another viewer.

25. The computer implemented method of claim 13, wherein an access metric is based on whether a comment was provided by the viewer on the video.

26. The computer implemented method of claim 13, wherein an access metric is based on whether a comment provided by the viewer was a positive comment.

27. The computer implemented method of claim 13, wherein an access metric is based on whether a comment provided by the viewer was a neutral comment.

28. The computer implemented method of claim 13, wherein a access metric is based on whether a comment provided by the viewer was a negative comment.

29. The computer implemented method of claim 13, wherein the net interest score is a weighted combination of the one or more interest scores.

30. The computer implemented method of claim 13, wherein the net interest score is an average combination of the one or more interest scores.

31. The computer implemented method of claim 1, wherein calculating the first score for the identified ad associated with the video comprises:

periodically updating a net interest score based at least in part on one or more aggregate access metrics, each aggregate access metric an ongoing measurement of user interactions associated with viewing the video; and

calculating the first score for the ad based at least in part on the net interest score.

32. The computer implemented method of claim 31, wherein updating the net interest score comprises:

responsive to a viewer accessing the video, collecting interaction data on interactions between the viewer and an entity presenting the video;

updating the one or more aggregate access metrics based at least in part on the collected data, and

updating the net interest score based at least in part on the updated one or more aggregate access metrics.

33. The computer implemented method of claim 32, wherein the interaction data collected is data on selections made and information entered by the viewer in the entity presenting the video.

34. The computer implemented method of claim 32, the entity presenting the video is a webpage.

35. The computer implemented method of claim 32, wherein the entity presenting the video is a video player.

36. The computer implemented method of claim 31, wherein an aggregate access metric is an average amount of time the video is watched by viewers.

37. The computer implemented method of claim 31, wherein an aggregate access metric is based on an average percentage of the video watched by viewers.

38. The computer implemented method of claim 30, wherein an aggregate access metric is based on the number of times that a specific percentage of the video was watched by viewers.

39. The computer implemented method of claim 31, wherein an aggregate access metric is based on a total number of times the video has been watched by viewers.

40. The computer implemented method of claim 31, wherein an aggregate access metric is based on an average rating given to the video by viewers.

41. The computer implemented method of claim 31, wherein an aggregate access metric is based on a total number of times the video was added as a favorite by viewers.

42. The computer implemented method of claim 31, wherein an aggregate access metric is based on the total number of times the video has been shared by viewers on webpages or with other viewers.

43. The computer implemented method of claim 31, wherein an aggregate access metric is based on the total number of comments the video has received from viewers.

44. The computer implemented method of claim 31, wherein an aggregate access metric is based on the total number of positive comments the video has received from viewers.

45. The computer implemented method of claim 31, wherein an aggregate access metric is based on the total number of neutral comments the video has received from viewers.

46. The computer implemented method of claim 31, wherein an aggregate access metric is based on the total number of negative comments the video has received from viewers.

47. The computer implemented method of claim 1, wherein the first score calculated for the ad is an estimated cost per mille (eCPM) and wherein calculating the eCPM comprises:

calculating a predicted click through rate (pCTR) for the ad based at least in part on or more ad metrics; and

calculating the eCPM based at least in part on the calculated pCTR and a cost per click (CPC) value associated with the ad.

48. The computer implemented method of claim 47, wherein an ad metric used in calculating the pCTR is the total number of times the ad has been clicked on by viewers.

49. The computer implemented method of claim 47, wherein an ad access metric used in calculating the pCTR is the total number of times the ad has been presented to viewers.

50. The computer implemented method of claim 47, wherein responsive to the ad being the ad associated with the video, the pCTR is a function of the one or more ad metrics and a net interest score representing the overall interest of viewers who have viewed the video.

51. The computer implemented method of claim 47, wherein responsive to the ad being the ad associated with the video, the pCTR is a function of the one or more ad metrics, a net interest score representing the overall interest of viewers who have viewed the video, and a net comparison measurement representing the similarity between the video and videos the user has viewed and uploaded.

52. The computer implemented method of claim 1, wherein a number of identified ads having the highest first scores are selected to be presented to the user.

53. The computer implemented method of claim 1, wherein identified ads having a first score above a threshold are selected to be presented to the user.