A Virtual Probe Deployment Method Based on User Behavioral Feature Analysis

To address the challenge of low survival rates and limited data collection efficiency in current virtual probe deployments, which results from anomaly detection mechanisms in location-based service (LBS) applications, this paper proposes a novel virtual probe deployment method based on user behavioral feature analysis. The core idea is to circumvent LBS anomaly detection by mimicking real-user behavior patterns. First, we design an automated data extraction algorithm that recognizes graphical user interface (GUI) elements to collect spatio-temporal behavior data. Then, by analyzing the automatically collected user data, we identify normal users’ spatio-temporal patterns and extract their features such as high-activity time windows and spatial clustering characteristics. Subsequently, an anti-detection scheduling strategy is developed, integrating spatial clustering optimization, load-balanced allocation, and time window control to generate probe scheduling schemes. Additionally, a self-correction mechanism based on an exponential backoff strategy is implemented to rectify anomalous behaviors and maintain system stability. Experiments in real-world environments demonstrate that the proposed method significantly outperforms baseline methods in terms of both probe ban rate and task completion rate, while maintaining high time efficiency. This study provides a more reliable and clandestine solution for geosocial data collection and lays the foundation for building more robust virtual probe systems.