The invention discloses a module Gamma adjustment method based on an LSTM neural network. The method comprises the following steps: obtaining a trained LSTM neural network, wherein the input binding point queue of the LSTM neural network comprises a plurality of binding point initial vectors, and the binding point initial vectors comprise input binding points and Gamma adjustment values thereof, the output binding point queue of the LSTM neural network comprises one or more output binding point prediction vectors, and the output binding point prediction vectors comprise output binding points and Gamma adjustment prediction initial values thereof; obtaining a current input binding point queue of a to-be-modulated module, obtaining a current output binding point queue of the to-be-modulatedmodule by utilizing the trained LSTM neural network; carrying out Gamma adjustment on the current output binding point of the to-be-modulated module by utilizing the Gamma adjustment prediction initial value of the current output binding point, and obtaining the Gamma adjustment prediction initial value by utilizing the LSTM neural network. The precision of the Gamma adjustment prediction initialvalue is improved.