<p>The development of Internet of Vehicles technology (IOV), which uses mobile internet and the Global Positioning System (GPS), has been accelerated by the growing number of autonomous and intelligent transportation systems (ITS), which deliver real-time traffic data to maximize efficiency. The Internet of Vehicles (IoV), a highly interactive network, continuously monitors a vehicle’s location, speed, route, and other characteristics. The widespread adoption of GPS-equipped vehicles has generated massive amounts of location and trajectory data, driving the development of numerous trajectory mining techniques. However, many existing methods often overlook users’ privacy concerns. To address this, the present study proposes a novel privacy-preserving approach for stay point mining in vehicle trajectory data. Wuhan City, one of the largest central logistics hubs in Hubei Province, is chosen as the case study to validate the proposed model. The integration of privacy protection mechanisms based on differential intelligent transportation systems and privacy technology comes after the initial identification of the stay points within trajectories using density clustering techniques in Spatio-temporal density-based spatial clustering of applications with noise (ST-DBSCAN). For testing, validation, and privacy protection, a heavy-duty truck trajectory dataset is employed to train the proposed unsupervised machine learning model, DBSCAN. The study also explores open research challenges and highlights the importance of vehicle trajectory similarity evaluation. The proposed method not only accurately identifies stay points with 96% precision but also effectively protects users’ private information from potential disclosure.</p>