Service processing method for CDN platform and CDN system

Abstract

The embodiment of the invention relates to the technical field of communication. The invention discloses a service processing method for a CDN platform. The method comprises the following steps: obtaining a service request initiated by terminal equipment, wherein the service request comprises a requested machine learning model, a CDN calculation identifier and / or to-be-processed data, and if it isdetermined that calculation is needed according to the CDN calculation identifier, by the requested machine learning model, calculating the to-be-processed data, returning the calculation result to aterminal device, and if it is determined that calculation is not needed according to the CDN calculation identifier, returning the requested machine learning model to the terminal device. The embodiment of the invention further provides a CDN system. According to the service processing method for the CDN platform and the CDN system provided by the embodiment of the invention, the artificial intelligence level of low-computing-power terminal equipment and the flexibility of model application of high-computing-power terminal equipment can be improved.

Description

technical field [0001] The invention relates to the field of communication technology, in particular to a service processing method for a CDN platform and a CDN system. Background technique [0002] With the continuous development of technology and the arrival of the 5G era, the application of artificial intelligence based on machine learning is becoming more and more extensive. [0003] However, for some low-computing terminal devices (such as cameras, audio, etc.), due to their limited computing power, it is difficult to apply artificial intelligence applications to analyze, calculate and further control terminal device data, and the level of artificial intelligence is relatively low. Low; and for some high-computing terminal devices, because the machine learning models used are all customized by the manufacturer, machine learning models other than those customized by the manufacturer cannot be applied, and the flexibility of model application is low. Contents of the inv...

AI Technical Summary

Problems solved by technology

[0003] However, for some low-computing terminal devices (such as cameras, audio, etc.), due to their limited computing power, it is difficult to apply artificial intelligence applications to analyze, calculate and further control terminal device data, and the level of artificial intelligence is relatively low. Low; for some high-computing terminal devices, because the machine learning models used are all customized by the manufacturer, machine learning models other than those customized by the manufacturer cannot be applied, and the flexibility of model application is low.

Images