Segmentation of a video based on user engagement in respective segments of the video

Abstract

Systems and methods for segmenting a video based on user engagement in respective segments of the video are presented. In one or more aspects, a system is provided that includes an engagement component configured to receive information regarding respective engagement of a plurality of users in connection with respective segments of a video. The system further includes an analysis component configured to analyze the information and calculate user engagement scores for the respective video segments, wherein the user engagement scores reflect level of the plurality of users' interest regarding the respective video segments, and an identification component configured to identify a subset of the video segments associated with relatively higher user engagement scores in comparison to other video segments.

What is claimed is: 
     
         1 . A method, comprising:
 receiving occurrence information indicative of the number of times that each of a plurality of different types of engagement actions have been taken by a plurality of users in connection with each of a plurality of segments of a video, each of the plurality of different types of engagement actions corresponds to a user input provided via a user interface used to present the video;   determining user engagement scores for each of the plurality of video segments based on the occurrence information; and   recommending at least a group of the plurality of video segments from the video to a user based on the user engagement scores for the group of the video segments relative to user engagement scores for other groups of the video segments.   
     
     
         2 . The method of  claim 1 , further comprising:
 identifying a subset of video segments of the plurality of video segments associated with user engagement scores indicating relatively greater user interest in comparison to other video segments of the plurality of video segments; and   segmenting the video into N groups of segments based on points in the video where segments of the subset are located, wherein N is a number greater than or equal to  2 .   
     
     
         3 . The method of  claim 2 , further comprising:
 extracting the subset of segments; and   generating a new video comprising the subset of segments.   
     
     
         4 . The method of  claim 2 , further comprising generating thumbnails for the video based on images respectively associated with the subset of video segments. 
     
     
         5 . The method of  claim 1 , further comprising:
 identifying clusters of adjacent segments that are associated with user engagement scores having a defined similarity; and   segmenting the video into N groups of segments based on the clusters, wherein N is a number greater than or equal to 2.   
     
     
         6 . The method of  claim 5 , further comprising generating thumbnails for the video based on images associated with segments of each of the N groups. 
     
     
         7 . A system, comprising:
 a hardware processor that is programmed to:
 receive occurrence information indicative of the number of times that each of a plurality of different types of engagement actions have been taken by a plurality of users in connection with each of a plurality of segments of a video, each of the plurality of different types of engagement actions corresponds to a user input provided via a user interface used to present the video; 
 determine user engagement scores for each of the plurality of video segments based on the occurrence information; and 
 recommend at least a group of the plurality of video segments from the video to a user based on the user engagement scores for the group of the video segments relative to user engagement scores for other groups of the video segments. 
   
     
     
         8 . The system of  claim 7 , wherein the hardware processor is further programmed to:
 identify a subset of video segments of the plurality of video segments associated with user engagement scores indicating relatively greater user interest in comparison to other video segments of the plurality of video segments; and   segment the video into N groups of segments based on points in the video where segments of the subset are located, wherein N is a number greater than or equal to 2.   
     
     
         9 . The system of  claim 8 , wherein the hardware processor is further programmed to:
 extract the subset of segments; and   generate a new video comprising the subset of segments.   
     
     
         10 . The system of  claim 8 , wherein the hardware processor is further programmed to further generate thumbnails for the video based on images respectively associated with the subset of video segments. 
     
     
         11 . The system of  claim 7 , wherein the hardware processor is further programmed to:
 identify clusters of adjacent segments that are associated with user engagement scores having a defined similarity; and   segment the video into N groups of segments based on the clusters, wherein N is a number greater than or equal to 2.   
     
     
         12 . The wherein the hardware processor is further programmed to of  claim 11 , wherein the hardware processor is further programmed to generate thumbnails for the video based on images associated with segments of each of the N groups. 
     
     
         13 . A non-transitory computer-readable medium containing computer executable instructions that, when executed by a processor, cause the processor to perform a method, the method comprising:
 receiving occurrence information indicative of the number of times that each of a plurality of different types of engagement actions have been taken by a plurality of users in connection with each of a plurality of segments of a video, each of the plurality of different types of engagement actions corresponds to a user input provided via a user interface used to present the video;   determining user engagement scores for each of the plurality of video segments based on the occurrence information; and   recommending at least a group of the plurality of video segments from the video to a user based on the user engagement scores for the group of the video segments relative to user engagement scores for other groups of the video segments.   
     
     
         14 . The non-transitory computer-readable medium of  claim 13 , further comprising:
 identifying a subset of video segments of the plurality of video segments associated with user engagement scores indicating relatively greater user interest in comparison to other video segments of the plurality of video segments; and   segmenting the video into N groups of segments based on points in the video where segments of the subset are located, wherein N is a number greater than or equal to 2.   
     
     
         15 . The non-transitory computer-readable medium of  claim 14 , wherein the method further comprises:
 extracting the subset of segments; and   generating a new video comprising the subset of segments.   
     
     
         16 . The non-transitory computer-readable medium of  claim 14 , wherein the method further comprises generating thumbnails for the video based on images respectively associated with the subset of video segments. 
     
     
         17 . The non-transitory computer-readable medium of  claim 13 , wherein the method further comprises:
 identifying clusters of adjacent segments that are associated with user engagement scores having a defined similarity; and   segmenting the video into N groups of segments based on the clusters, wherein N is a number greater than or equal to 2.   
     
     
         18 . The non-transitory computer-readable medium of  claim 17 , wherein the method further comprises generating thumbnails for the video based on images associated with segments of each of the N groups.