Video transcoding task scheduling

An electronic device, comprising:

• at least one processor;
• and
• a memory communicatively connected to the at least one processor;
• wherein
• the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform operations of:
• determining an input video to be transcoded, wherein the input video comprises at least one image frame;
• performing an image analysis on the at least one image frame to obtain an image feature of the input video;
• determining a target transcoding parameter for a transcoded target video;
• predicting, based on the image feature of the input video and the target transcoding parameter, a resource occupancy required for a transcoding task of the input video and an acceptable memory usage for the transcoding task, wherein the acceptable memory usage for the transcoding task is a maximum memory usage without stuttering during the transcoding task;
• scheduling, based on the predicted resource occupancy and memory usage, a computational resource for the transcoding task,
• wherein predicting, based on the image feature of the input video and the target transcoding parameter, the resource occupancy and the memory usage comprises:
• processing the image feature of the input video and the target transcoding parameter using a trained machine learning model to output the resource occupancy and the memory usage,
• wherein the input video to be transcoded is a live stream video, and the machine learning model is a regression model or a classification model,
• wherein the machine learning model is trained by:
• determining a sample dataset, wherein the sample dataset comprises a plurality of sample videos to be transcoded;
• for each sample video in the sample dataset,
• performing an image analysis on an image frame in the sample video to determine a sample image feature of the sample video;
• determining a target transcoding parameter corresponding to the sample video;
• transcoding the sample video according to the target transcoding parameter;
• marking a ground truth resource occupancy required for a transcoding process of the sample video and an acceptable ground truth memory usage for the transcoding process, wherein the acceptable ground truth memory usage for the transcoding task is a maximum ground truth memory usage without stuttering during the transcoding task;
• inputting the sample image feature into the machine learning model to obtain a predicted resource occupancy and a predicted memory usage;
• adjusting a parameter of the machine learning model based on a first difference between the predicted resource occupancy and the ground truth resource occupancy and a second difference between the predicted memory usage and the ground truth memory usage.

A non-transient computer-readable storage medium storing computer instructions, wherein the computer instructions are used to enable the computer to perform operations of:

• determining an input video to be transcoded, wherein the input video comprises at least one image frame;
• performing an image analysis on the at least one image frame to obtain an image feature of the input video;
• determining a target transcoding parameter for a transcoded target video;
• predicting, based on the image feature of the input video and the target transcoding parameter, a resource occupancy required for a transcoding task of the input video and an acceptable memory usage for the transcoding task, wherein the acceptable memory usage for the transcoding task is a maximum memory usage without stuttering during the transcoding task;
• scheduling, based on the predicted resource occupancy and memory usage, a computational resource for the transcoding task,
• wherein predicting, based on the image feature of the input video and the target transcoding parameter, the resource occupancy and the memory usage comprises:
• processing the image feature of the input video and the target transcoding parameter using a trained machine learning model to output the resource occupancy and the memory usage,
• wherein the input video to be transcoded is a live stream video, and the machine learning model is a regression model or a classification model,
• wherein the machine learning model is trained by:
• determining a sample dataset, wherein the sample dataset comprises a plurality of sample videos to be transcoded;
• for each sample video in the sample dataset,
• performing an image analysis on an image frame in the sample video to determine a sample image feature of the sample video;
• determining a target transcoding parameter corresponding to the sample video;
• transcoding the sample video according to the target transcoding parameter;
• marking a ground truth resource occupancy required for a transcoding process of the sample video and an acceptable ground truth memory usage for the transcoding process, wherein the acceptable ground truth memory usage for the transcoding task is a maximum ground truth memory usage without stuttering during the transcoding task;
• inputting the sample image feature into the machine learning model to obtain a predicted resource occupancy and a predicted memory usage;
• adjusting a parameter of the machine learning model based on a first difference between the predicted resource occupancy and the ground truth resource occupancy and a second difference between the predicted memory usage and the ground truth memory usage.