In order to alleviate urban traffic congestion and avoid the traffic accident, the route selection in urban road networks has been a hot research topic. With the development of edge computing and vehicle intelligent terminal technology, driving vehicles in urban road network are transiting from self-organizing network to Internet of vehicles (IoV) paradigm, which makes the route selection of vehicles change the computation based on static historic traffic data to real-time traffic information. In the current research on the route selection in urban road networks, many scholars focus on how to improve the efficiency of travel, reduce travel time, etc. Nevertheless, these studies do not consider the possible risk on the selected route. Based on the above issues, this study constructs a real-time road risk assessment model based on edge computing (R³A-EC) for the first time. Besides, it proposes a real-time route selection method based on risk assessment (R²S-RA). The R³A-EC model makes full use of the characteristics of low latency and high reliability of the edge computing technology to assess the risk on the urban road in real time, and uses the minimum risk Bayes decision making to validate whether there is a risk. Finally, based on the real-time risk assessment model, the route selection of urban road network is optimized to realize the real-time dynamic and low-risk route selection method. Compared with the traditional shortest path method Dijkstra and the shortest time method based on VANET, the dynamic path planning algorithm based on MEC and the bidirectional A* shortest path optimization algorithm, the proposed R²S-RA method can better choose the optimal route that takes road risk and travel time into account, so as to reduce the occurrence of traffic congestion and traffic accidents.