Live video streaming services

Abstract

In some implementations, a system may include an interactive video broadcasting service, implemented on a server, configured to enable a plurality of source devices to broadcast live feed video streams, over a network, to a plurality of viewing devices. The interactive video broadcasting service includes a multi-perspective video sharing engine configured to determine that at least two of the live feed video streams relate to a same event. The multi-perspective video sharing engine provides a multi-perspective display, over the network, to at least one of the plurality of viewing devices in which the multi-perspective display concurrently streams the live feed video streams determined as related to the same event.

What is claimed is: 
     
         1 . A computer-implemented method comprising:
 enabling first and second source devices to broadcast respectively first and second live feed video streams, over a network, to a plurality of viewing devices;   receiving user engagements with the second video stream from the plurality of viewing devices;   identifying portions of the second video stream that are associated with user engagements;   automatically creating, based on the identification of portions of the second video stream that are associated with user engagements, a replay from the second video stream, the replay being a segment of the broadcasted video stream;   determining that the first live feed video stream and the replay are relating to a single event; and   providing a multi-perspective display, over the network, to at least one of the plurality of viewing devices, the multi-perspective display including the first live feed video stream and the replay.   
     
     
         2 . The method of  claim 1 , further comprising:
 automatically creating the replay to have two or more video clips relating to portions of the broadcasted video stream having a level of user engagements equal to or above a threshold level.   
     
     
         3 . The method of  claim 1 , further comprising:
 determining that the first live feed video stream and the replay are relating to the single event by computing a score for the first live feed video stream and the replay using a weighted scoring algorithm that can dynamically adjust weights applied to a plurality of signals.   
     
     
         4 . The method of  claim 1 , further comprising:
 determining that the first live feed video stream and the replay are relating to the single event by computing a score for each live feed video stream with another live feed video stream based on a combination of signals; and   determining that a particular live feed video stream is correlated with the another stream when the corresponding score is above or equal to a threshold value.   
     
     
         5 . The method of  claim 1 , further comprising:
 determining that the first live feed video stream and the replay are relating to the single event by computing a score for each live feed video stream that indicates a level of similarity to another live feed video stream or the single event using a weighted scoring algorithm that applies weights to a plurality of signals; and   determining that a particular live feed video stream is correlated with another stream or the single event when the corresponding score is above or equal to a threshold value.   
     
     
         6 . The method of  claim 1 , further comprising:
 analyzing video of the live feed video streams using a video analyzer; and   determining that the first and second live feed video streams relate to the same event based on results of the video analyzer.   
     
     
         7 . The method of  claim 6 , further comprising:
 recognizing, using the video analyzer, people and/or objects in the live feed video streams.   
     
     
         8 . The method of  claim 1 , further comprising:
 analyzing audio of the live feed video streams using an audio analyzer; and   determining that the live feed video streams relate to the same event based on results of the audio analyzer.   
     
     
         9 . A non-transitory computer readable medium storing executable instructions that when executed by at least one processor cause the at least one processor to:
 enable first and second source devices to broadcast respectively first and second live feed video streams, over a network, to a plurality of viewing devices;   receive user engagements with the second video stream from the plurality of viewing devices;   identify portions of the second video stream that are associated with user engagements;   automatically create, based on the identification of portions of the second video stream that are associated with user engagements, a replay from the second video stream, the replay being a segment of the broadcasted video stream;   determine that the first live feed video stream and the replay are relating to a single event; and   provide a multi-perspective display, over the network, to at least one of the plurality of viewing devices, the multi-perspective display including the first live feed video stream and the replay.   
     
     
         10 . The non-transitory computer readable medium of  claim 9 , further comprising:
 automatically create the replay to have two or more video clips relating to portions of the broadcasted video stream having a level of user engagements equal to or above a threshold level.   
     
     
         11 . The non-transitory computer readable medium of  claim 9 , further comprising:
 determine that the first live feed video stream and the replay are relating to the single event by computing a score for the first live feed video stream and the replay using a weighted scoring algorithm that can dynamically adjust weights applied to a plurality of signals.   
     
     
         12 . The non-transitory computer readable medium of  claim 9 , further comprising:
 determine that the first live feed video stream and the replay are relating to the single event by computing a score for each live feed video stream with another live feed video stream based on a combination of signals; and   determine that a particular live feed video stream is correlated with another stream when the corresponding score is above or equal to a threshold value.   
     
     
         13 . The non-transitory computer readable medium of  claim 9 , further comprising:
 determine that the first live feed video stream and the replay are relating to the single event by computing a score for each live feed video stream that indicates a level of similarity to another live feed video stream or the single event using a weighted scoring algorithm that applies weights to a plurality of signals; and   determine that a particular live feed video stream is correlated with another stream or the single event when the corresponding score is above or equal to a threshold value.   
     
     
         14 . The non-transitory computer readable medium of  claim 9 , further comprising:
 analyze video of the live feed video streams using a video analyzer;   determine that the first and second live feed video streams relate to the same event based on results of the video analyzer; and   recognize, using the video analyzer, people and/or objects in the live feed video streams.   
     
     
         15 . A computing device comprising:
 at least one processor; and   a non-transitory computer-readable medium storing executable instructions that when executed by the at least one processor cause the at least one processor to:
 enable first and second source devices to broadcast respectively first and second live feed video streams, over a network, to a plurality of viewing devices; 
 receive user engagements with the second video stream from the plurality of viewing devices; 
 identify portions of the second video stream that are associated with user engagements; 
 automatically create, based on the identification of portions of the second video stream that are associated with user engagements, a replay from the second video stream, the replay being a segment of the broadcasted video stream; 
 determine that the first live feed video stream and the replay are relating to a single event; and 
 provide a multi-perspective display, over the network, to at least one of the plurality of viewing devices, the multi-perspective display including the first live feed video stream and the replay. 
   
     
     
         16 . The computing device of  claim 15 , further comprising:
 a video analyzer configured to analyze video of the live feed video streams, the computing apparatus being configured to determine that the first and second live feed video streams relate to the same event based on results of the video analyzer.   
     
     
         17 . The computing device of  claim 16 , wherein the video analyzer is configured to recognize people and/or objects in the live feed video streams. 
     
     
         18 . The computing device of  claim 15 , further comprising:
 an audio analyzer configured to analyze audio of the live feed video streams, the computing device configured to determine that the live feed video streams relate to the same event based on results of the audio analyzer.   
     
     
         19 . The computing device of  claim 15 , wherein the computing device is configured to automatically create the replay to have two or more video clips relating to portions of the broadcasted video stream having a level of user engagements equal to or above a threshold level. 
     
     
         20 . The computing device of  claim 15 , wherein the computing device is configured to determine that the first live feed video stream and the replay are relating to a single event by computing a score for at least one of the live feed video stream and the replay using a weighted scoring algorithm that can dynamically adjust weights applied to a plurality of signals.