A historical building data processing method and system based on reinforcement learning

Abstract

The embodiment of the application belongs to the field of artificial intelligence, and relates to a history building data processing method based on reinforcement learning, comprising the following steps: obtaining measured operation and maintenance data of a history building and a pre-constructed digital twin model of the history building; inputting the measured operation and maintenance data and a current parameter state of the digital twin model into a pre-trained reinforcement learning model to obtain first adjustment information; updating the digital twin model according to the first adjustment information and obtaining a first parameter state of the updated digital twin model; and generating second adjustment information based on the first parameter state through the reinforcement learning model, wherein the second adjustment information is used to instruct to update and maintain the history building. The application also provides a history building data processing device based on reinforcement learning, a computer device and a storage medium. The application improves the scientificity and accuracy of history building operation and maintenance control.

Images