Abstract: The traditional identification of household transformer relationships mainly relies on manual investigation, which has problems such as low efficiency and poor accuracy, and is difficult to meet the needs of modern intelligent management of distribution networks. To this end, this article proposes a household change relationship recognition method based on symbol aggregation approximation method and improved K-means clustering algorithm. The voltage data collected by the intelligent measurement system for substation users is studied. Firstly, the voltage time series is segmented and aggregated for approximation processing, significantly reducing the dimensionality of the data; subsequently, the reduced voltage data was transformed into a string sequence through symbolic conversion, effectively eliminating redundant information; on this basis, the similarity between string sequences is calculated based on the edit distance metric, and a similarity matrix is constructed accordingly. Finally, the improved K-means clustering algorithm is used to perform clustering analysis on the matrix, thereby achieving accurate identification of household variable relationships.