Intelligent commodity recommendation method and system based on closed-loop control

The invention provides an intelligent commodity recommendation method and system based on closed-loop control. The method comprises the following steps: in each small promotion period, selecting a group of keywords capable of achieving an expected optimal promotion effect and an optimal quotation of each keyword from a candidate keyword set of a commodity; according to the method, historical promotion effect data is captured, the promotion effect coped with the quotation of each keyword in the next small promotion period is predicted, and promotion strategy self-adaptive adjustment is performed as closed-loop negative feedback. According to the application, the promotion strategy can be dynamically adjusted according to the historical promotion record of each commodity, the dynamic change of the system state, the variables continuously introduced in the promotion and the effect change of the detection actual promotion are also considered, and the closed-loop negative feedback is formed with the strategy adjus