A method and device for predicting solvent residue of cigarette paper and an electronic device

Abstract

The application discloses a cigarette paper solvent residue prediction method and device and electronic equipment. The method comprises the following steps: obtaining a historical multidimensional data set of a target cigarette paper; performing feature extraction on the historical multidimensional data set according to a principal component analysis method to obtain a historical data feature vector set; constructing a cigarette paper solvent residue prediction model corresponding to a historical model training data set based on a multilayer neural network and a gradient boosting decision tree; and finally, determining a target solvent residue prediction result corresponding to any target multidimensional data of the target cigarette paper according to the cigarette paper solvent residue prediction model. Through the above prediction steps, the quality control mode is fundamentally changed from "post-test" to "prevention", the detection efficiency is significantly improved, the resource allocation is optimized, and the accuracy of solvent residue prediction is significantly improved by fusing multi-source data and advanced algorithm models.

Images