I. Introduction
Artificial intelligence has received more and more attention in the computer field. And it has been applied in robots, economic and political [1] decision-making, control systems, and simulation systems. The famous Stanford University Artificial Intelligence Research Center Professor Nelson defined artificial intelligence [2] as follows: "Artificial intelligence is the discipline of knowledge - the science of how to represent knowledge and how to acquire and use knowledge." [3] Time series data themselves have very different characteristics, eg, long-term, medium-term, short-term, etc. In practical applications, models that describe short-term correlation cannot be applied to long-term correlation time series data [4].