The existing ship domain models are mostly based on the navigation behavior of open water vessels, and they are not practicable to directly apply to inland rivers. Therefore, it is necessary to establish an inland ship safety domain model based on the ship traffic characteristic therein. Based on the AIS data in the Yangtze River, this paper establishes the functional relationship between these data through multiple regression analysis using data such as ship spacing, ship length, ship speed, and heading angle. Based on this, the safety distance between ships of different lengths in different situations and other ships is determined, so as to establish a dynamic ship domain model. At the same time, this paper explores the geographical relationship between ship and channel boundary and incorporates it into the ship domain model. Finally, a quantitative approach for ship collision risk is proposed, and the collision threat degree is calculated according to the relative heading of the ship and the position in the dynamic ship domain model. Two case studies, including crossing and overtaking situations, are performed to validate the proposed model.