User change relation identification method and system based on current sequence similarity

The invention provides a user-transformer relation identification method and system based on current sequence similarity, and the method comprises the steps: obtaining transformer current time sequence data and corresponding user meter box current time sequence data, carrying out the preprocessing of the obtained time sequence data, and obtaining a data set of the current time sequence data, the data set of the current time sequence data at least comprises user meter box current segment data and transformer current segment data at a corresponding moment; inputting the data set of the current time sequence data as an input item into a pre-trained neural network discrimination model, and classifying a single current fragment sample to obtain a classification result; and counting the proportion of each single current segment sample according to the classification result, and selecting the connection relationship represented by the data group with the highest proportion value as a final identification result. Acc