Abnormality processing method and device, server and storage medium

Abstract

The invention provides an abnormality processing method and device, a server and a storage medium, and belongs to the technical field of machine learning. The method comprises the following steps: for any data source of a service model, detecting a first feature value of at least one feature from the data source, and determining a target feature; acquiring a second feature value of the target feature; replacing the first feature value of the target feature with the second feature value of the target feature, and inputting the feature value of at least one feature after replacement of the data source into a service model which provides a corresponding service based on the input data source. According to the technical scheme, the second feature value is used for replacing the abnormal first feature value, the difference between the second feature value and the normal value of the target feature is in the preset difference range, the influence on the accuracy rate of the service model is also in the preset accuracy rate range, the service corresponding to the service model does not need to be paused, and the service corresponding to the service model can be normally provided.

Description

technical field [0001] The present disclosure relates to the technical field of machine learning, and in particular to an exception handling method, device, server and storage medium. Background technique [0002] With the development of machine learning technology, the service model trained based on machine learning technology provides great convenience for our life. By inputting various types of data acquired based on multiple data sources into the service model, corresponding services can be provided according to the output results of the service model. For example, taking a video recommendation model as an example, by inputting data such as user viewing records, user consumption records, and user information into the video recommendation model, the video that the user is interested in can be output, so as to achieve the purpose of recommending videos for users. However, the output of the service model may be inaccurate due to the problem that the data source may not be ...

AI Technical Summary

Problems solved by technology

[0005] The present disclosure provides an exception handling method, device, server, and storage medium to at least solve the problem of directly suspending the provision of the service corresponding to the service model when the server cannot obtain data from the data source or obtains wrong data, resulting in the failure of the service corresponding to the service model. Problems with an unavailable state

Images