Abstract: As a key element of the new infrastructure strategy of China, the charging facilities of electric vehicles have developed rapidly in recent years. However, the development of charging facilities faces the problem of imbalance between supply and demand. Therefore, it is necessary to analyze the user demands and behavior characteristics through real data and build an effective public charging facility planning system to serve the development of electric vehicles. To provide a feasible framework for the planning of real-world charging stations, by taking Shanghai as a practical case, this paper carries out practical big data mining analysis, which integrates multi-source real-world data such as service vehicle trajectory data, charging station data, passenger vehicle travel statistical data, traffic road condition data, and interest point retrieval data. From the macro-perspective, the correlation between the traveling-charging behavior of vehicle users and the city temporal-spatial characteristics is analyzed. From the micro-perspective, the behavioral preferences of individual vehicle users are modeled, where the user charging demand is predicted by the decision tree model, and the user’s charging station selection behavior is described by the Huff attraction model.On this basis, the massive user behavior is reconstructed and simulated, and a simulation framework of the urban integrated energytraffic network is established. The construction of existing charging facilities is evaluated from multiple dimensions such as the overall supply and demand and the individual service quality. Finally, a future charging facility expansion planning framework considering multiple objectives is proposed, which provides data support and decision-making basis for the charging facility planning of electric vehicles.