The planning of electric vehicle (EV) charging stations with a comprehensive consideration of the multi-type charging demands and the acceptance capacities of the distribution network is of great significance to the development of EVs and the transformation of the distribution network. At present, most studies determine EV charging needs based on user travel paths, but they have not taken the behavior uncertainty of EV owners and the diversity of their demands into account. The probability statistics on the massive data of EV travels can help excavating the travel and charging rules of the EVs. Based on user travel data, the Markov chain and the roulette method are used to simulates EV charging requirements in three scenarios considering various uncertain factors, and then a K-means clustering algorithm is used to obtain charging requirements in three scenarios. On this basis, a bi-level planning model of charging station with maximum annual profit of construction and operation and minimum comprehensive charging cost of EVs as multi-objective function is proposed. This model also considers many constraints, such as cooperative service of multi-type charging piles, acceptance capacity of distribution network and so on. The upper model takes the location and capacity of charging station planning as control variables. The lower model was established to minimize the comprehensive charging cost of EVs. The upper and lower models interact and couple with each other. The solution process of bi-level planning model was designed through using firefly algorithm. Finally, taking the urban area of a city in China as the planning area, and the transportation network coupled with the IEEE 69 node distribution network as an example, the validity and correctness of the proposed model are verified.