In the context of the development of new power systems, the continuous increase in the proportion of intermittent new energy sources puts forward higher requirements for the flexibility of the combined electric heating system. A multi-stage robust dispatch method for electric and heating combined systems that takes into account temperature control load demand response is proposed. Firstly, a model of electric- heat combined system that considers flexible resources such as electric-heat conversion equipment and temperature control load is established, and the concept of virtual energy storage is proposed to model the temperature control load. Then, the wind power output forecast error is modeled as a box uncertainty set, and a multi-stage robust scheduling model of the combined electric and heating system is proposed. In each scheduling period, the observation value of wind power can be used to minimize the total current and subsequent moments. The maximum cost is the goal, the subsequent scheduling plan is adjusted, and the model is solved by a robust dual dynamic programming algorithm. Finally, test cases are used to verify the effectiveness of the proposed method.