Devices and systems for voice over internet protocol for identifying network traffic

1. A voice over Internet protocol (VoIP) device for identifying network traffic, comprising:

a media monitor to identify a media protocol from the network traffic;

a signal monitor to identify a signaling protocol from the network traffic; and

an artificial intelligence (AI) engine configured to:

receive signaling protocol sample data to train a signal artificial intelligence (AI) model;

process the signaling protocol identified by the signal monitor in the signal artificial intelligence (AI) model to identify the network traffic in response to the training of the signal artificial intelligence (AI) model improving at least a minimum threshold value in an error rate or probability in identifying a plurality of randomly selected signal protocol bit patterns;

receive media protocol sample data to train a media artificial intelligence (AI) model; and

process the media protocol identified by the media monitor in the media artificial intelligence (AI) model to identify the network traffic in response to the training of the signal artificial intelligence (AI) model improving less than the minimum threshold value in the error rate and probability in identifying the plurality of randomly selected signal protocol bit patterns.

2. The device of claim 1 , wherein the signal AI model identifies the network traffic as media or non-media.

3. The device of claim 2 , wherein increased quality of service (QoS) is provided in response to the signal AI model identifying the network traffic as media.

4. The device of claim 2 , wherein media includes audio or video data.

5. The device of claim 1 , wherein the AI engine is configured to process the media protocol identified by the media monitor in response to the signaling protocol being unavailable.

6. An edge device for identifying network traffic, comprising:

a media monitor to identify a media protocol from the network traffic; and

an artificial intelligence engine configured to:

receive media protocol sample data to train a media artificial intelligence (AI) model; and

process the media protocol identified by the media monitor in the media artificial intelligence (AI) model to identify the network traffic in response to training of a signal artificial intelligence (AI) model improving less than a minimum threshold value in an error rate or probability in identifying a plurality of randomly selected signal protocol bit patterns.

7. The device of claim 6 , wherein training the media AI model includes using a logistic regression machine.

8. The device of claim 6 , wherein the media AI model identifies the network traffic based on bit pattern of the media protocol.

9. The device of claim 8 , wherein the bit pattern can include a payload.

10. The device of claim 6 , wherein the media protocol sample data includes a plurality of randomly selected media protocol bit patterns.

11. The device of claim 10 , wherein training of the media AI model is complete in response to the media AI model receiving a lowest error and highest probability in identifying the plurality of randomly selected media protocol bit patterns as media.

12. The device of claim 6 , wherein the media AI model is retrained in response to receiving new media protocol data.

13. The device of claim 6 , wherein the media AI model identifies the network traffic as media or non-media.

14. The device of claim 6 , wherein increased quality of service (QoS) is provided in response to the media AI model identifying the network traffic as media.

15. A system for identifying network traffic, comprising:

a network interface configured to capture the network traffic and send a payload from the network traffic;

a signal artificial intelligence (AI) engine configured to receive signaling protocol sample data to train a signal artificial intelligence (AI) model, receive the payload, and identify the network traffic; and

a media artificial intelligence (AI) engine configured to receive the payload and identify the network traffic in response to training of the signal AI model improving less than a minimum threshold value in an error rate or probability in identifying a plurality of randomly selected signal protocol bit patterns.

16. The system of claim 15 , wherein the media AI engine is further configured to extract Internet protocol (IP) or port information.

17. The system of claim 16 , wherein the network interface is further configured to send the IP or port information to a Quality of Service (QoS) enforcer.

18. The system of claim 15 , wherein the signal AI engine calculates a probability that the signal AI engine correctly identified the network traffic.

19. The system of claim 18 , wherein the network traffic is identified as media in response to the probability exceeding a threshold.

20. The system of claim 18 , wherein the network traffic is identified as non-media in response to the probability failing to exceed a threshold.