Abstract: [Objectives]. In the process of EV charging guidance, users have different preferences in selecting charging stations, resulting in different selection criteria for charging stations, which affects users' participation in optimal scheduling. Therefore, in view of the user's habit of selecting charging stations and the interest conflict between users and charging aggregators, an EV charging guidance strategy considering the choice habit of target charging stations was proposed. [Methods]. self-organizing feature mapping (SOFM) was used for user profiling, and Shapley Additive ExPlanations (SHAP) were used to determine the best profiling results. Secondly, the entropy weight method is used to determine the weight of time cost and economic cost of each type of user in the process of selecting charging stations. According to the weight results, the user's expense cost and time cost are converted into user satisfaction. Then, the user is guided to charge according to the user satisfaction. [Results]. The example shows that compared with the shortest path algorithm, this strategy significantly improves the user's satisfaction in selecting charging stations and the profit per unit time of charging piles. Simultaneously, the strategy is less affected under different traffic conditions. [Conclusions]. This strategy effectively solves the influence of user's charging decision preference on charging guidance, which is of great significance for improving users' charging benefits and reducing users' charging congestion.

Key words: electric vehicle, charging station, preferences, user profiling, guidance, satisfaction