Based on the Narrow Band Internet of Things (NB-IoT) and Machine Learning Support Vector Machine (SVM) algorithm, this paper proposes a new intelligent station recognition technology. Firstly, the voltage data is uploaded to the host computer by NB-IoT communication module. Through the analysis, it is found that the voltage data of the electric energy acquisition equipment in the same area have temporal and spatial correlation. On this basis, the voltage time correlation and spatial correlation are taken as the characteristic factors, and the SVM classification method is used to judge the attribution relationship of the acquisition equipment to be identified. The identification technology can provide real and accurate user stations, and achieve fine management of the stations.