Commodity recommendation method and device

The invention provides a commodity recommendation method and device, and relates to the field of electronic commerce. The method comprises the steps: obtaining the current state information of a target object; inputting the state information into a pre-trained recommendation model to obtain an action value corresponding to the state information; determining a probability identifier corresponding to each to-be-recommended commodity according to the action value; and according to each probability identifier, selecting a preset number of to-be-recommended commodities and recommending the to-be-recommended commodities to the target object. By applying the commodity recommendation method provided by the invention, the commodity can be recommended to the user according to the current state information of the target object, the demand of the user can be comprehensively perceived, and the shopping experience of the user is improved. 本发明提供了一种商品推荐方法及装置，涉及电子商务领域，该商品推荐方法，包括：获取目标对象当前的状态信息；将所述状态信息输入至预先训练的推荐模型中，得到与所述状态信息对应的