ETC customer identification model construction method and device based on supervised learning

Abstract

The invention discloses an ETC customer identification model construction method and device based on supervised learning, belonging to the technical field of artificial intelligence. The method comprises the steps of collecting original ETC customer training data and test data; according to target feature information in the original ETC customer training data, deriving new attribute feature information according to a preset derivation rule, and transplanting the new attribute feature information derived based on the target feature information to the original ETC customer test data; and training the ETC customer identification model according to the original ETC customer training data and the transplanted ETC customer test data. According to the method, the new attribute feature information is derived based on the target feature information, the new attribute feature information is transplanted to the ETC customer test data, and then the transplanted ETC customer test data is utilized to train the TC customer identification model. The target feature information is introduced into transplanted ETC customer test data, so the training effect of an ETC customer identification model can be improved.

Description

technical field [0001] The invention relates to the technical field of artificial intelligence, in particular to a method and device for constructing an ETC customer identification model based on supervised learning. Background technique [0002] This section is intended to provide a background or context to embodiments of the invention that are recited in the claims. The descriptions herein are not admitted to be prior art by inclusion in this section. [0003] Use samples with known certain or certain characteristics as the training set to establish a mathematical model (such as the discriminant model in pattern recognition, the weight model in artificial neural network method, etc.), and then use the established model to predict unknown samples , this method is called supervised learning and is the most common machine learning method. For the algorithm model of supervised learning, the currently widely used feature processing schemes, such as principal component analysi...

AI Technical Summary

Problems solved by technology

For the algorithm model of supervised learning, the currently widely used feature processing schemes, such as principal component analysis, missing value completion, attribute feature cross-derived new attribute feature information, are all limited by the input of the ETC customer identification model based on supervised learning (attribute features), so that the data set for model training discards a lot of meaningful information, resulting in the final training effect of the algorithm model is not very good

Images