Currently, the challenge lies in the traditional intelligent algorithm’s ability to effectively address the e-hailing repositioning issue. Accurately identifying the underlying characteristics in extensive traffic data within a limited timeframe is difficult, ultimately preventing the achievement of the most optimal solution. This paper suggests a hybrid computing architecture involving reinforcement learning and quantum annealing based on intuitive reasoning. Intuitive reasoning aims to enhance performance in scenarios with poor system robustness, complex tasks, and diverse goals. A deep learning model is constructed, trained to extract scene features, and combined with expert knowledge, then transformed into a quantum annealable form. The final strategy is obtained using a D-wave quantum computer with quantum tunneling effect, which helps in finding optimal solutions by jumping out of local suboptimal solutions. Based on 400000 real data, four algorithms are compared: minimum-cost flow, sequential markov decision process, hot-dot strategy, and driver-prefer strategy. The average total revenue increases by about 10% and vehicle utilization by about 15% in various scenarios. In summary, the proposed architecture effectively solves the e-hailing reposition problem, offering new directions for robust artificial intelligence in big data decision problems.