Building performance prediction method and device, equipment and medium

The invention relates to the technical field of artificial intelligence, and provides a building performance prediction method, device, equipment and medium, which can obtain a multi-task building energy prediction model based on a multi-task learning model of a double-end input and four-task output architecture and existing building data training in a specified longitude and latitude range. Therefore, simultaneous prediction of various building performance indexes is realized, and the prediction efficiency is improved. And inputting the target building characteristics and the target meteorological parameters of the target building into the multi-task building energy prediction model to obtain predicted building energy consumption intensity, predicted roof photovoltaic power generation capacity, predicted south facade photovoltaic power generation capacity and predicted east-west facade photovoltaic power generation capacity of the target building. And a target building performance prediction result of the ta