The invention relates to a power distribution network reconstruction measure and load loss index correlation mining method and device. The method comprises the following steps of: obtaining sample data of a corresponding relationship between the configurable resource transformation measure of the active power distribution network and the corresponding load loss index; secondly, training the BP neural network by using the sample data as a training sample by using the nonlinear mapping capability of the BP neural network, and constructing direct mapping between a power distribution network transformation measure and a power distribution network load loss amount to obtain a power distribution network load loss amount evaluation model under different transformation measures based on the BP neural network. The method and the device are beneficial to discovering the potential correlation between the power distribution network transformation measure and the power distribution network load loss index, and the calculation efficiency is improved.