Method and system for automatic learning of parameters for automatic video and photo editing based on user's satisfaction

• US 9,734,869 B2
• Filed: 03/11/2015
• Issued: 08/15/2017
• Est. Priority Date: 03/11/2014
• Status: Active Grant

• Current Assignee: Vimeo, Inc. (Match Group, Inc.)
• Original Assignee: Magisto Ltd. (Match Group, Inc.)
• Inventors: Rav-Acha, Alexander, Boiman, Oren
• Primary Examiner(s): Shibru, Helen
• Application Number:
  US14/644,350
• Publication Number:
  US 20150262615A1
• Time in Patent Office: 888 Days
• Field of Search: 386281, 386248, 386282
• CPC Class Codes: G11B 27/031 Electronic editing of digitised analogue information signals, e.g. audio or video signals
• CPC Class Codes: H04N 1/00167 Processing or editing H04N1/00196 - H04N1/00201 take precedence
• CPC Class Codes: H04N 21/25891 being end-user preferences retrieval of video data in a video database based on user preferences G06F16/739; arrangements for recognizing users' preferences H04H60/46; user profiles in network data switching protocols H04L67/306; processing of user preferences or user profiles in wireless networks H04W8/18
• CPC Class Codes: H04N 21/2665 Gathering content from different sources, e.g. Internet and satellite
• CPC Class Codes: H04N 21/4223 Cameras H04N23/00 takes precedence
• CPC Class Codes: H04N 21/431 Generation of visual interfaces for content selection or interaction; Content or additional data rendering
• CPC Class Codes: H04N 21/854 Content authoring

Abstract

A method and system for modifying video editing parameters based on users satisfaction. The method may include the following steps: maintaining a plurality of video editing parameters; obtaining from a plurality of users, a plurality of footage sets each set comprising at least one of: a video sequence, and a still image; editing the plurality of footage sets, based on the plurality of video editing parameters, to yield respective edited videos; deriving user-satisfaction indicators from the plurality of users, responsive to viewing the respective edited videos; and automatically modifying at least one of the video editing parameters, based on the user-satisfaction indicators, to yield modified video editing parameters.

Claims

1. A method for modifying video editing parameters comprising:

maintaining a plurality of video editing parameters;

obtaining from at least one user, a plurality of footage sets each set comprising at least one of;

a video sequence, and still image;

editing the plurality of footage sets, based on the plurality of video editing parameters, to yield respective edited videos;

deriving user-satisfaction indicators from the at least one user, responsive to viewing the respective edited videos, wherein the user satisfaction indicates an emotional reaction of a user to viewing the respective edited videos; and

automatically modifying at least one of the video editing parameters, based on the user-satisfaction indicators, to yield modified video editing parameters.

2. The method according to claim 1, wherein the user satisfaction is based on a rating of the edited video as provided explicitly by the user.

3. The method according to claim 1, wherein the user satisfaction is automatically derived from actions and behaviors of the respective users.

4. The method according to claim 3, wherein the actions of the respective users include at least one of:

viewing beyond a predefined portion of the edited video, sharing, buying, becoming a premium user, saving, commenting, and deleting.

5. The method according to claim 1, wherein the user satisfaction is based on a choice of a user out of multiple edited videos.

6. The method according to claim 1, wherein the user satisfaction is based on priority made by a user relative to multiple edited videos.

7. The method according to claim 1, wherein the user-satisfaction is based on capturing the face of the user during or immediately after viewing the edited movie, analyzing the facial expression of the captured face;

and automatically deriving the user-satisfaction.

8. The method according to claim 1, wherein the user-satisfaction is based on capturing auditory signals during or immediately after viewing the edited movie by the user;

analyzing the captured auditory signals; and

automatically deriving the user-satisfaction.

9. The method according to claim 1, wherein the maintained video editing parameters are stored on a data-structure that associates user attributes with at least a subset of video editing parameters, and wherein the modified video editing parameters are associated with at least one attribute of users.

10. The method according to claim 1, wherein the video editing parameters comprise at least one of:

editing style;

tempo; and

theme.

11. The method according to claim 1, wherein the video editing parameters comprise an importance level of at least one of:

scene representation;

speech;

activity, class of objects; and

a specific object.

12. The method according to claim 1, wherein the modifying of the video editing parameters utilizes at least one of A-B testing;

regression, and annealing.

13. The method according to claim 1, wherein the modifying is carried out for a plurality of users at the same time.

14. The method according to claim 9, wherein the user attribute comprises at least of one of gender;

age; and

country.

15. The method according to claim 1, wherein the modifying at least one of video editing parameters is performed only in a case that the user-satisfaction indicators meet certain statistical significance criteria.

16. The method according to claim 1, wherein the maintained video editing parameters are stored on a data-structure that associates attributes of footage sets with at least a subset of video editing parameters;

and wherein the modified video editing parameters are associated with at least one attribute of the footage sets being viewed by the plurality of users.

17. The method according to claim 16, wherein the attributes of the footage sets comprise at least one of:

type of media that constitute the footage;

length of the footage;

number of faces being detected within the footage.

18. A system for modifying video editing parameters comprising:

a server associated with a computer processor and a database configured to maintain a plurality of video editing parameters;

a plurality of communication devices being in communication with the server and configured to obtain a plurality of footage sets each set comprising at least one of;

a video sequence, and a still image;

an editing module, executed by the computer processor and configured to edit the plurality of footage sets, based on the plurality of video editing parameters, to yield respective edited videos; and

a learning module, executed by the computer processor and configured to derive user-satisfaction indicators from the plurality of users, responsive to viewing the respective edited videos, wherein the user satisfaction indicates an emotional reaction of a user to viewing the respective edited videos,

wherein the computer processor is further configured to automatically modify at least one of the video editing parameters, based on the user-satisfaction indicators, to yield modified video editing parameters.

19. The system according to claim 18, wherein the communication devices are configured to capture the face of the user during or immediately after viewing the edited movie, and wherein the user-satisfaction is based on analyzing the facial expression of the captured face;

and automatically deriving the user-satisfaction.

20. The system according to claim 18, wherein the communication devices are configured to capture auditory signals during or immediately after viewing the edited movie by the user, and wherein the user-satisfaction is based on analyzing the captured auditory signals, and automatically deriving the user-satisfaction.