Model training method, service processing method, device and equipment

Abstract

The embodiment of the invention provides a model training method, a service processing method, a device and equipment. The method comprises the following steps: acquiring at least one historical record service, wherein the historical record service corresponds to service information; determining a judgment result of the historical record service corresponding to at least one preset judgment rule according to the service information, wherein the judgment result comprises a normal service and an abnormal service; constructing at least one training sample service by utilizing the service information of the historical record service of the abnormal service in the judgment result, wherein the number of the training sample businesses is greater than that of the abnormal businesses; and trainingan abnormal service identification model based on the training sample service, wherein the abnormal service identification model is used for identifying the abnormal service. According to the method,the number of the abnormal services is expanded after the abnormal services are obtained, and the expanded training sample services are used for training the model, so that the sufficient sample sizeis ensured during model training, and the accuracy of abnormal service identification is ensured.

Description

technical field [0001] The embodiments of this specification relate to the field of computer technology, and in particular to a model training method, business processing method, device, and equipment. Background technique [0002] With the development of artificial intelligence technology, people can use computers to complete some tasks that require human intelligence, such as classifying target objects, or performing image recognition and processing. And machine learning technology is the core technology of artificial intelligence. It mainly improves the cognition of a certain thing by continuously acquiring new data. The sample data of the object is obtained, and the sample data is used for training to improve the model, so that the model can identify the object more accurately. [0003] In order to ensure the accuracy of the machine learning model, it is often necessary to use a large amount of training sample data when training the machine learning model. However, whe...

AI Technical Summary

Problems solved by technology

[0004] The purpose of the embodiments of this specification is to provide a model training method, business processing method, device and equipment to solve the problem of how to conveniently and accurately use the trained model to identify abnormal business

Images