CONTENT RATED DATA STREAM FILTERING

1 . A computer implemented method comprising:

determining a content rating level to apply to streaming content of a call;

separating at least one stream out from the streaming content;

identifying, during the call, a rating level of the at least one stream by detecting, with a machine learning object classification filter, an object from an image in the at least one stream;

detecting that the rating level of the at least one stream fails to satisfy the content rating level due to the object; and

blocking, during the call, at least a portion of the at least one stream in response to the at least the portion of the at least one stream failing to satisfy the content rating level.

2 . The computer implemented method of claim 1 , wherein the streaming content is part of a call, and determining the content rating level further comprises:

identifying a call setting for the call;

identifying a participant of the call;

identifying a device default setting for the call; and

identifying a user defined setting for the call.

3 . The computer implemented method of claim 1 , wherein the streaming content comprises a video stream, and separating the at least one stream further comprises:

separating the video stream out from the streaming content as part of the at least one stream;

processing a video frame from the video stream against a machine learning object classification filter to detect an object in the video frame; and

aligning the object to the content rating level to identify a video rating level of the video stream, wherein the video rating level is compared with the content rating level to detect whether the video stream fails to satisfy the content rating level.

4 . The computer implemented method of claim 1 , wherein the streaming content comprises a video stream, and detecting that the at least one stream fails to satisfy the content rating level comprises:

determining that a video rating level of the video stream exceeds the content rating level.

5 . The computer implemented method of claim 1 , wherein the streaming content comprises a video stream, and blocking at least the portion of the at least one stream further comprises:

blocking an object detected in the video stream from the streaming content.

6 . The computer implemented method of claim 5 , wherein blocking the object obfuscates the object in a video frame of the video stream while keeping remaining portions of the video frame intact.

7 . The computer implemented method of claim 1 , wherein the streaming content comprises an audio stream, and separating the at least one stream further comprises:

separating the audio stream out from the streaming content as part of the at least one stream;

processing the audio stream against a text detection filter to detect text; and

aligning the text to the content rating level to identify an audio rating level of the audio stream, wherein the audio rating level is compared with the content rating level to detect whether the audio stream fails to satisfy the content rating level.

8 . The computer implemented method of claim 1 , wherein the streaming content comprises an audio stream, and detecting that the at least one stream fails to satisfy the content rating level comprises:

determining that an audio rating level of the audio stream exceeds the content rating level.

9 . The computer implemented method of claim 1 , wherein the streaming content comprises an audio stream, and blocking at least the portion of the at least one stream further comprises:

blocking a portion of the audio stream from the streaming content.

10 . The computer implemented method of claim 1 , wherein blocking the at least the portion of the at least one stream further comprises:

disconnecting from the streaming content.

11 . A system comprising:

a processor;

a memory;

the memory comprising an application, wherein the application executes on the processor, uses the memory, and is configured for:

determining a content rating level to apply to streaming content of a call,

separating at least one stream out from the streaming content,

identifying, during the call, a rating level of the at least one stream by detecting, with a machine learning object classification filter, an object from an image in the at least one stream;

detecting that the rating level of the at least one stream fails to satisfy the content rating level due to the object; and

blocking, during the call, at least a portion of the at least one stream in response to the at least the portion of the at least one stream failing to satisfy the content rating level.

12 . The system of claim 11 , wherein the streaming content is part of a call, and determining the content rating level further comprises:

identifying a call setting for the call;

identifying a participant of the call;

identifying a device default setting for the call; and

identifying a user defined setting for the call.

13 . The system of claim 11 , wherein the streaming content comprises a video stream, and separating the at least one stream further comprises:

separating the video stream out from the streaming content as part of the at least one stream;

processing a video frame from the video stream against a machine learning object classification filter to detect an object in the video frame; and

aligning the object to the content rating level to identify a video rating level of the video stream, wherein the video rating level is compared with the content rating level to detect whether the video stream fails to satisfy the content rating level.

14 . The system of claim 11 , wherein the streaming content comprises a video stream, and detecting that the at least one stream fails to satisfy the content rating level comprises:

determining that a video rating level of the video stream exceeds the content rating level.

15 . The system of claim 11 , wherein the streaming content comprises a video stream, and blocking at least the portion of the at least one stream further comprises:

blocking an object detected in the video stream from the streaming content.

16 . The system of claim 15 , wherein blocking the object obfuscates the object in a video frame of the video stream while keeping remaining portions of the video frame intact.

17 . The system of claim 11 , wherein the streaming content comprises an audio stream, and separating the at least one stream further comprises:

separating the audio stream out from the streaming content as part of the at least one stream;

processing the audio stream against a text detection filter to detect text; and

aligning the text to the content rating level to identify an audio rating level of the audio stream, wherein the audio rating level is compared with the content rating level to detect whether the audio stream fails to satisfy the content rating level.

18 . The system of claim 11 , wherein the streaming content comprises an audio stream, and detecting that the at least one stream fails to satisfy the content rating level comprises:

determining that an audio rating level of the audio stream exceeds the content rating level.

19 . The system of claim 11 , wherein the streaming content comprises an audio stream, and blocking at least the portion of the at least one stream further comprises:

blocking a portion of the audio stream from the streaming content.

20 . The system of claim 11 , wherein blocking the at least the portion of the at least one stream further comprises:

disconnecting from the streaming content.

21 . A set of one or more non-transitory computer readable mediums comprising computer readable program code for:

determining a content rating level to apply to streaming content of a call;

separating at least one stream out from the streaming content;

identifying, during the call, a rating level of the at least one stream by detecting, with a machine learning object classification filter, an object from an image in the at least one stream;

detecting that the rating level of the at least one stream fails to satisfy the content rating level due to the object; and

blocking, during the call, at least a portion of the at least one stream in response to the at least the portion of the at least one stream failing to satisfy the content rating level.