Model integration method and apparatus

Abstract

A model integration method and apparatus are disclosed. The model integration method comprises: determining at least two to-be-integrated independent models, wherein each independent model has one output value; acquiring event data sets from historical event records; generating integrated model training samples according to the acquired event data sets; and using a supervised learning algorithm totrain the samples to obtain an integrated model.

Description

technical field [0001] The embodiments of this specification relate to the technical field of data processing, and in particular to a model integration method and device. Background technique [0002] The essence of intelligent or automatic processing is a process in which a computer obtains corresponding output information after calculation based on given input information, and a model is a kind of information used to describe the above-mentioned input-output relationship. Simple models can be established according to artificial rules. In the data age, data modeling based on big data and machine learning technology has become the mainstream. At present, in various application fields, big data modeling has been widely used to achieve various intelligence However, as the number of models increases, problems such as difficulty in management and excessive resource consumption also arise. [0003] Taking the risk control system as an example, the model-driven risk control strat...

AI Technical Summary

Problems solved by technology

However, while the risk prediction coverage is constantly improving, the number of models also increases. Over time, the overall risk control system will become larger and larger. Not only will the management and maintenance costs become uncontrollable, but also due to the frequent existence of different models Redundancy actually causes unnecessary consumption of system processing resources

Images