17955444. SYSTEM AND METHOD FOR ULTRA LOW LATENCY LIVE STREAMING BASED ON USER DATAGRAM PROTOCOL simplified abstract (SAMSUNG ELECTRONICS CO., LTD.)

SYSTEM AND METHOD FOR ULTRA LOW LATENCY LIVE STREAMING BASED ON USER DATAGRAM PROTOCOL

Organization Name

SAMSUNG ELECTRONICS CO., LTD.

Inventor(s)

Luckraj Shrawan Kumar of Bengaluru, Karnataka (IN)

Gopinath Chennakeswaran of Bangalore (IN)

Renuka Varry of Bangalore (IN)

Divyanshu Chuchra of Bengaluru (IN)

Umang Bhatia of Gurgaon (IN)

Utkarsh Mohan of Patna, Bihar (IN)

Aalok Kumar Gupta of Koderma, Jharkhand (IN)

SYSTEM AND METHOD FOR ULTRA LOW LATENCY LIVE STREAMING BASED ON USER DATAGRAM PROTOCOL - A simplified explanation of the abstract

This abstract first appeared for US patent application 17955444 titled 'SYSTEM AND METHOD FOR ULTRA LOW LATENCY LIVE STREAMING BASED ON USER DATAGRAM PROTOCOL

Simplified Explanation

The abstract describes a method for enhancing video streaming by using neural networks. Here are the key points:

• The method involves training a client-side neural network (NN) in a client device using a client-side environment parameter.
• The client-side encoding bit rate is determined based on the training result and transmitted to a server-side neural network (NN) in a server device.
• The server-side NN is trained using the client-side encoding bit rate and a server-side environment parameter.
• The server-side encoding bit rate is determined based on the training result, and the encoding bit rate of the video stream is adjusted accordingly.

Potential Applications

This technology can be applied in various video streaming scenarios, including:

• Online video platforms: Enhancing the video streaming experience for users by optimizing encoding bit rates based on client and server environments.
• Video conferencing: Improving the quality and stability of video calls by dynamically adjusting encoding bit rates.
• Live streaming: Optimizing video quality and reducing buffering issues during live broadcasts.

Problems Solved

The method addresses the following problems in video streaming:

• Inconsistent video quality: By training neural networks based on client and server environments, the method ensures that the encoding bit rate is optimized for the specific conditions, resulting in a more consistent video quality.
• Bandwidth optimization: By adjusting the encoding bit rate based on the determined server-side encoding bit rate, the method helps optimize bandwidth usage and reduce buffering issues.
• Real-time adaptation: The method allows for real-time adjustments to the encoding bit rate, ensuring a smooth video streaming experience even in changing network conditions.

Benefits

The use of neural networks in video streaming offers several benefits:

• Improved video quality: By training neural networks based on client and server environments, the method can enhance video quality by optimizing the encoding bit rate.
• Enhanced user experience: The real-time adjustments to the encoding bit rate help provide a smoother and more stable video streaming experience for users.
• Bandwidth efficiency: By dynamically adjusting the encoding bit rate, the method helps optimize bandwidth usage and reduce data consumption without compromising video quality.

Original Abstract Submitted

An example method includes for enhancing video streaming includes inputting a client-side environment parameter to a client-side neural network (NN) implemented in a client device and then training the client-side NN based on the inputted client-side environment parameter. Thereafter, a client-side encoding bit rate is determined based on a result of the training of the client-side NN and then transmitting the determined client-side encoding bit rate as an input to a server-side neural network (NN) implemented in a server device. The method further includes training the server-side NN based on the inputted client-side encoding bit rate and a server-side environment parameter. Then, a server-side encoding bit rate is determined based on a result of the training of the server-side NN and thereafter, an encoding bit rate of an encoder for the video stream is adjusted based on the determination of the server-side encoding bit rate, and the server-side environment parameter.