(EN) The embodiment of the invention provides a recommendation reason generation method and device, equipment and a storage medium. The method comprises the steps: acquiring content information of a to-be-recommended object, and generating a recommendation reason of the to-be-recommended object according to a pre-trained recommendation reason generation model and the content information, wherein the training data used by the recommendation reason generation model comprises question and answer data and content information of a plurality of objects. In the technical scheme, the training of the recommendation reason generation model combines the question and answer data with the content information of a plurality of objects, and the most interested commodity of the user is mined through the question and answer data, so that the recommendation reason generated by the method can accurately locate the user demand, and the user experience is improved.
(ZH) 本申请实施例提供一种推荐理由生成方法、装置、设备及存储介质，通过获取待推荐对象的内容信息，并根据预先训练好的推荐理由生成模型和内容信息，生成待推荐对象的推荐理由，其中，推荐理由生成模型使用的训练数据包括多个对象的问答数据和内容信息。该技术方案中，由于推荐理由生成模型的训练是结合多个对象的问答数据和内容信息，通过问答数据挖掘用户最在意的商品，因此，通过本方案生成的推荐理由可准确定位用户需求，提高了用户的体验。
