Blocking node optimization method based on virus propagation model and reinforcement learning

The invention discloses a blocking node optimization method based on a virus propagation model and reinforcement learning, and belongs to the technical field of Internet of Things terminal security protection, and the method comprises the following steps: obtaining Internet of Things terminals and historical traffic information, and constructing an Internet of Things terminal network topological graph; classifying according to service types to which the terminals belong, endowing service weights according to the service types, and calculating node comprehensive importance; constructing a terminal network susceptibility model of a virus propagation angle according to the historical flow information and the alarm information; dividing a terminal subnet, and clearly blocking router deployment nodes; and finally, defining a reward function, optimizing a blocking rule through a strengthening algorithm, and determining a solution for blocking virus propagation. According to the method and the device, the problems t