In view of the current situation that anti-theft technology is often analyzed by a single algorithm, which results in unsatisfactory anti-theft effect, a recognition method for low-voltage users is proposed. First of all, the technical line loss part of the line loss in the area is separated. Then, k-means clustering algorithm is adopted to analyze the processed line loss data, identify the platform area where the line loss rate fluctuates abnormally or is continuously high, and define the time dispersion according to the clustering result to measure the suspected degree of power theft. Then it analyzes the users under the abnormal station area, and studies the possible relationship between the change of single user"s electricity quantity and the change of line loss rate in the station area through the correlation analysis. The outlier algorithm and K-means clustering algorithm are used to analyze the daily electricity data of users, judge the suspected electricity theft of a single user, and determine the specific electricity theft behavior. The research results show that this method can identify the low-voltage users" power stealing more effectively, which provides a new way for power stealing identification and remediation.