Abstract: The present specification discloses video matching. In a computer-implemented method, a plurality of feature vectors of a target video is obtained. A candidate video similar to the target video is retrieved from a video database based on the plurality of feature vectors of the target video. A time domain similarity matrix feature map is constructed between the target video and the candidate video based on the target video and the candidate video. Using the time domain similarity matrix feature map as an input into a deep learning detection model, a video segment matching the target video in the candidate video and a corresponding similarity is output.

Abstract: Disclosed is a decision method of condition-based maintenance to a power grid risk. The method includes: calculating a contribution of each device to be maintained of a plurality of devices to be maintained to the power grid risk in a current operation mode of a power grid, and determining the contribution of the each device to be maintained to the power grid risk as a set value corresponding to the each device to be maintained; determining a maintenance decision order of the devices to be maintained according to a descending order of set values corresponding to the devices to be maintained; and sequentially making maintenance decisions on the devices to be maintained according to the determined maintenance decision order.