Training method and device for service quality evaluation model

Abstract

The invention discloses a training method and device for a service quality evaluation model. The method comprises the following steps: acquiring machine performance data of a service node, network characteristic data and quality monitoring data according to a fixed period; based on the machine performance data and the network characteristic data, determining characteristic values; based on the quality monitoring data, determining a tag; establishing a training set by utilizing the characteristic values and the tag; and training a deep neural network model by utilizing the training set, and obtaining the service quality evaluation model. When the service quality evaluation model provided by the invention is utilized for performing service quality evaluation, evaluation accuracy can be improved, and input of data can be reduced, so that computing resources required by evaluation as well as bandwidth are greatly reduced, not only is service quality evaluation efficiency improved, but alsooperation cost is reduced.

Description

technical field [0001] The invention relates to the technical field of CDN, in particular to a method and device for training a service quality evaluation model. Background technique [0002] With the increasing popularity of CDN (Content Delivery Network, content distribution network) technology, the business of CDN is becoming more and more complex and large, and customers have higher and higher requirements on the service quality of CDN service system. In order to ensure high-quality services, the CDN service system needs to understand the quality of service provided to customers in real time, find and replace faulty nodes in time, and avoid the decline in service quality caused by machine or network reasons. [0003] At present, one way to evaluate the service quality of the CDN service system is to evaluate the service quality by analyzing the access logs of the server, such as calculating the freeze rate and other indicators. When evaluating service quality through se...

AI Technical Summary

Problems solved by technology

When evaluating service quality through server-side access logs, a large amount of computing resources are required to traverse access logs, resulting in very high equipment and bandwidth costs for internal operation and maintenance; at the same time, this method is highly coupled with business types, and the evaluation indicators for each business type are different. It is very large, and there is no way to form a unified standard, which makes internal management very difficult

Another way is to use indicators such as machine performance and network conditions to evaluate service quality. This evaluation method relies heavily on the experience of operation and maintenance personnel, and the accuracy is not high

Images