Method and apparatus for providing video stream based on machine learning
A method of providing a video stream based on machine learning in an electronic device according to various example embodiments may include receiving a source video stream which is streamed from a first device to at least one other device, confirming whether an event is detected on the source video stream using a learning model trained through machine learning on the basis of at least one frame of the source video stream, and determining whether to restrict streaming of the source video stream from the first device on the basis of the event detection. In addition to the method, other example embodiments are possible.
1 . A method, comprising:
receiving a source video stream from a first device;
confirming whether an event is detected on the source video stream using a learning model that provides a probability value on the basis of at least one frame of the source video stream; and
determining whether to restrict streaming of the source video stream on the basis of information acquired from one or more external devices, at least in part based on a first threshold value and a second threshold value greater than the first threshold value, the determining including
restricting the streaming of the source video stream, at least in part on the basis of a determination that the probability value is greater than or equal to a specified the second threshold value;
transmitting information related to the source video stream to a first external device of the external devices, at least in part on the basis of a determination that the probability value is greater than or equal to the first threshold value and is less than the second threshold value; and
transmitting the information related to the source video stream to more than one of the external devices, at least in part on the basis of a determination that the probability value is less than the first threshold value.
2 . The method of claim 1 , further comprising:
interrupting the confirming for a specified time, when the probability value is greater than or equal to the second threshold value.
3 . The method of claim 1 , wherein the learning model is trained at least in part on the basis of information acquired from the one or more external devices.
4 . The method of claim 1 , wherein at least one of the first threshold value or the second threshold value is determined on the basis of user identification (ID) information corresponding to the first device.
5 . The method of claim 1 , wherein the information includes information on a first frame corresponding to the event detection, on a second frame before the first frame, and on a third frame after the first frame.
6 . The method of claim 1 , wherein the learning model was trained through machine learning.
7 . An electronic device, comprising:
a memory that stores a series of commands or predetermined data; and
a processor that accesses the series of commands or predetermined data to
receive a source video stream from a first device,
confirm whether an event is detected on the source video stream using a learning model that provides a probability value on the basis of at least one frame of the source video stream, and
perform a determination whether to restrict streaming of the source video stream on the basis of information acquired from one or more external devices, at least in part based on a first threshold value and a second threshold value greater than the first threshold value, the determination including
restrict the streaming of the source video stream, at least in part on the basis of a determination that the probability value is greater than or equal to the second threshold value,
transmit information related to the source video stream to a first external device of the external devices, at least in part on the basis of a determination that the probability value is greater than or equal to the first threshold value and is less than the second threshold value, and
transmit the information related to the source video stream to more than one of the external devices, at least in part on the basis of a determination that the probability value is less than the first threshold value.
8 . The electronic device of claim 7 , wherein the processor further accesses the series of commands or predetermined data to interrupt the confirming for a specified time, when the probability value is greater than or equal to the second threshold value.
9 . The electronic device of claim 7 , wherein the learning model is trained at least in part on the basis of information acquired from the one or more external devices.
10 . The electronic device of claim 7 , wherein at least one of the first threshold value or the second threshold value is determined on the basis of user identification (ID) information corresponding to the first device.
11 . The electronic device of claim 7 , wherein the information includes information on a first frame corresponding to the event detection, on a second frame before the first frame, and on a third frame after the first frame.
12 . The electronic device of claim 7 , wherein the learning model was trained through machine learning.
13 . A non-transitory, computer-readable recording medium for recording a program for executing a method of providing a video stream on an electronic device, wherein the method comprises:
receiving a source video stream from a first device;
confirming whether an event is detected on the source video stream using a learning model that provides a probability value on the basis of at least one frame of the source video stream; and
determining whether to restrict streaming of the source video stream on the basis of information acquired from one or more external devices, at least in part based on a first threshold value and a second threshold value greater than the first threshold value, the determining including
restricting the streaming of the source video stream, at least in part on the basis of a determination that the probability value is greater than or equal to the second threshold value;
transmitting information related to the source video stream to a first external device of the external devices, at least in part on the basis of a determination that the probability value is greater than or equal to the first threshold value and is less than the second threshold value; and
transmitting the information related to the source video stream to more than one of the external devices, at least in part on the basis of a determination that the probability value is less than the first threshold value.
14 . The recording medium of claim 13 , the method further comprising:
interrupting the confirming for a specified time, when the probability value is greater than or equal to the second threshold value.
15 . The recording medium of claim 13 , wherein at least one of the first threshold value or the second threshold value is determined on the basis of user identification (ID) information corresponding to the first device.
16 . The recording medium of claim 13 , wherein the information includes information on a first frame corresponding to the event detection, on a second frame before the first frame, and on a third frame after the first frame.
17 . The recording medium of claim 13 ,
wherein the learning model was trained through machine learning.