| CPC G06F 16/258 (2019.01) [G06F 16/1794 (2019.01)] | 17 Claims |
|
1. A method for processing time series data generated at a substrate treating facility, the method comprising:
dividing a first data of a first facility according to each process of substrate treating by the first facility;
dividing a second data of a second facility according to each process of substrate treating by the second facility;
converting the divided first data and the divided second data to a same size using 1D convolution, wherein the same size is a data size for input to a Siamese network;
assembling the converted first data and the converted second data into a first plane and a second plane, respectively, wherein each of the first plane and the second plane includes a 2D convolution representing an individual process of substrate treating;
combining a plurality of 2D convolutions to generate a 3D convolution, wherein each 2D convolution of the plurality of 2D convolutions represents a separate and distinct process of substrate treating; and
determining, using the Siamese network, whether the assembled first data and the assembled second data are the same.
|