A method and device for updating a model

Abstract

A model updating method and apparatus, relating to the technical field of computers and used to at least solve the problem of a waste of resources caused by the poor significance or even insignificance of a later model update in two model updates triggered by two adjacent updating triggering points, due to the fact that changes between data features of newly-added data of two adjacent updating triggering points and data features of previous data are non-obvious. The method comprises: acquiring first online service data received within a window where a triggering point to be detected is located; according to the data features of the first online service data, constructing a first feature sequence; determining an association relationship between the first feature sequence and at least one representative slice, wherein the representative slice is a slice of a feature sequence constructed according to the data feature of historical service data; if the association relationship between the first feature sequence and the at least one representative slice satisfies a pre-set condition, updating the current model.

Description

technical field [0001] The invention relates to the field of computer technology, in particular to a model updating method and device. Background technique [0002] A machine learning algorithm is an algorithm that obtains a data model (hereinafter referred to as a model) by analyzing known data, and uses the model to predict unknown data; for example, use the model and the data to be received for content recommendation services, etc. . Traditional machine learning algorithms need to prepare all known data before learning, and once the model is obtained, it will not be changed. [0003] With the development of online business (such as online recommendation business, online marketing business, etc.), the scale of data continues to increase, and the rate of data change is getting faster and faster. The model obtained by using traditional machine learning algorithms cannot adapt well to the new The changing law of the increasing data reduces the accuracy of the prediction of ...

AI Technical Summary

Problems solved by technology

[0006] Embodiments of the present invention provide a model update method and device to at least solve the problem caused by the insignificant change between the data characteristics of the newly added data and the data characteristics of the previous data between two adjacent update trigger points. Among the two model updates triggered by the two adjacent update trigger points, the last model update has little meaning, or even no doubt, which causes a waste of resources

Images