Expression decomposition pattern recognition method and device, electronic equipment and storage medium

Abstract

The application provides an expression decomposition mode recognition method and device, electronic equipment and a storage medium, and relates to the technical field of symbolic regression. The method comprises the following steps: obtaining target point cloud data corresponding to a to-be-recognized symbolic expression; inputting the target point cloud data into an expression decomposition model to obtain a pre-recognition result of the to-be-recognized symbolic expression output by the expression decomposition model; the expression decomposition model is obtained based on point cloud data samples and decomposition mode labels corresponding to the point cloud data samples; the pre-recognition result is used to represent the association between the target point cloud data and all decomposition modes; and based on the pre-recognition result, a decomposition mode recognition result corresponding to the to-be-recognized symbolic expression is determined. Through the pre-training mechanism, the application can reduce the consumption of CPU and memory resources, reduce the time complexity, and improve the real-time performance of the symbolic regression task.

Images