Systems and methods for light weight bitrate-resolution optimization for live streaming and transcoding

1. A computer-implemented method performed by a computing medium, the computer-implemented method comprising:

ingesting at least a portion of a live media asset from a media content source;

performing, in real time, after ingesting the at least the portion of the live media asset:

determining parameters of the at least the portion of the ingested live media asset based at least in part on analyzing bitstream-level statistics ingested with the at least the portion of the ingested live media asset;

inputting the determined parameters into a machine learning model, wherein the machine learning model has been trained using training data comprising a plurality of parameters for at least respective portions of a plurality of media assets and corresponding bitrate-resolution pairs;

determining, via an output from the machine learning model, a plurality of optimal bitrate-resolution pairs for the at least the portion of the live media asset for transmission to at least one edge server;

determining a bandwidth of the computing medium and the at least one edge server, wherein the at least one edge server is different from the computing medium;

based at least in part on the bandwidth, determining a transcoding site to transcode the at least the portion of the live media asset, wherein the transcoding site corresponds to the computing medium or the at least one edge server; and

causing the at least the portion of the live media asset to be transcoded at the transcoding site based on the plurality of optimal bitrate-resolution pairs.

2. The method of claim 1 , further comprising:

generating a bitstream comprising metadata, the metadata including the plurality of optimal bitrate-resolution pairs;

wherein causing the at least the portion of the live media asset to be transcoded comprises transmitting the bitstream from a central server to the at least one edge server, wherein the at least one edge server are configured to transcode the at least the portion of the live media asset based on the plurality of optimal bitrate-resolution pairs indicated in the metadata.

3. The method of claim 2 , wherein:

the at least the portion of the live media asset is a segment of the live media asset, and the live media asset comprises a plurality of segments; and

the transmitted bitstream includes a single indication of the metadata for each respective segment of the plurality of segments.

4. The method of claim 1 , wherein:

a central server performs the ingesting of the at least the portion of the live media asset from the media content source;

causing the at least the portion of the live media asset to be transcoded based on the plurality of optimal bitrate-resolution pairs comprises the central server transcoding the at least the portion of the live media asset; and

transmitting the transcoded at least a portion of the live media asset to the at least one edge server.

5. The method of claim 1 ,

wherein the trained machine learning model is configured to accept as input the parameters of the at least the portion of the ingested live media asset and output the plurality of optimal bitrate-resolution pairs for the at least the portion of the ingested live media asset, wherein the parameters of the training data include an indication of a genre for at least the respective portions of the plurality of media assets of the training data.

6. The method of claim 1 , wherein determining parameters of the at least the portion of the live media asset comprises extracting scene and motion statistics from a bitstream corresponding to the at least the portion of the ingested live media asset.

7. The method of claim 1 , wherein:

the at least the portion of the live media asset is a segment of the live media asset, and the live media asset comprises a plurality of segments; and

determining parameters of the at least the portion of the live media asset comprises determining parameters for at least one segment of the plurality of segments, wherein the parameters include a genre of the at least the portion of the live media asset or the at least one segment thereof.

8. The method of claim 1 , wherein causing the at least the portion of the live media asset to be transcoded at the transcoding site based on the plurality of optimal bitrate-resolution pairs is performed in response to receiving a request from a client device for the at least the portion of the ingested live media asset.

9. The method of claim 1 , wherein the at least the portion of the live media asset, as ingested, is encoded.

10. The method of claim 1 , wherein the at least the portion of the live media asset, as ingested, is not encoded, and the method further comprises:

encoding the at least the portion of the ingested live media asset, wherein the parameters of the live media asset are determined based at least in part on performing the encoding.

11. A computer-implemented system comprising:

memory; and

a computing medium comprising control circuitry configured to:

ingest at least a portion of a live media asset from a media content source;

perform, in real time, after ingesting the at least the portion of the live media asset:

determine parameters of the at least the portion of the ingested live media asset based at least in part on analyzing bitstream-level statistics ingested with the at least the portion of the ingested live media asset;

input the determined parameters into a machine learning model, wherein the machine learning model has been trained using training data comprising a plurality of parameters for at least respective portions of a plurality of media assets and corresponding bitrate-resolution pairs;

determine, via an output from the machine learning model, a plurality of optimal bitrate-resolution pairs for the at least the portion of the live media asset for transmission to at least one edge server,

determine a bandwidth of the computing medium and the at least one edge server, wherein the at least one edge server is different from the computing medium;

based at least in part on the bandwidth, determine a transcoding site to transcode the at least the portion of the live media asset, wherein the transcoding site corresponds to the computing medium or the at least one edge server; and

cause the at least the portion of the live media asset to be transcoded at the transcoding site based on the plurality of optimal bitrate-resolution pairs.

12. The system of claim 11 , wherein the system further comprises a central server and the at least one edge server, and the control circuitry is further configured to:

generate a bitstream comprising metadata, the metadata including the plurality of optimal bitrate-resolution pairs; and

cause the at least the portion of the live media asset to be transcoded by transmitting the bitstream from the central server to the at least one edge server, wherein the at least one edge server are configured to transcode the at least the portion of the live media asset based on the plurality of optimal bitrate-resolution pairs indicated in the metadata.

13. The system of claim 12 , wherein:

the at least the portion of the live media asset is a segment of the live media asset, and the live media asset comprises a plurality of segments; and

the transmitted bitstream includes a single indication of the metadata for each respective segment of the plurality of segments.

14. The system of claim 11 , wherein the system further comprises a central server, and the central server is configured to:

perform the ingesting of the at least the portion of the live media asset from the media content source;

cause the at least the portion of the live media asset to be transcoded based on the plurality of optimal bitrate-resolution pairs asset; and

transmit the transcoded at least a portion of the live media asset to the at least one edge server.

15. The system of claim 11 ,

wherein the trained machine learning model is configured to accept as input the parameters of the at least the portion of the ingested live media asset and output the plurality of optimal bitrate-resolution pairs for the at least the portion of the ingested live media asset, wherein the parameters of the training data include an indication of a genre for at least the respective portions of the plurality of media assets of the training data.

16. The system of claim 11 , wherein the control circuitry is configured to determine the parameters of the at least the portion of the live media asset by extracting scene and motion statistics from a bitstream corresponding to the at least the portion of the live media asset.

17. The system of claim 11 , wherein:

the at least the portion of the live media asset is a segment of the live media asset, and the live media asset comprises a plurality of segments; and

the control circuitry is configured to determine parameters of the at least the portion of the live media asset by determining parameters for at least one segment of the plurality of segments, wherein the parameters include a genre of the at least the portion of the live media asset or the at least one segment thereof.

18. The system of claim 11 , wherein the control circuitry is configured to cause the at least the portion of the live media asset to be transcoded at the transcoding site based on the plurality of optimal bitrate-resolution pairs in response to receiving a request from a client device for the at least the portion of the live media asset.

19. The system of claim 11 , wherein the at least the portion of the live media asset, as ingested, is encoded.

20. The system of claim 11 , wherein the at least the portion of the live media asset, as ingested, is not encoded, and the control circuitry is further configured to:

encode the at least the portion of the ingested live media asset; and

determine the parameters of the at least the portion of the live media asset based at least in part on performing the encoding.

21. The method of claim 9 , wherein the determined parameters of the at least the portion of the live media asset comprise at least one of quantization parameters (QP), bits per pixel, a number of regions used for encoding the at least the portion of the live media asset, a number of reference frames used for encoding the at least the portion of the live media asset, or motion vectors used in encoding the live the at least the portion of the live media asset.

22. The system of claim 11 , wherein the determined parameters of the at least the portion of the live media asset may comprise at least one of quantization parameters (QP), bits per pixel, a number of regions used for encoding the at least the portion of the live media asset, a number of reference frames used for encoding the at least the portion of the live media asset, and motion vectors used in encoding the live the at least the portion of the live media asset.