Video recommendation text generation method, model training method and related device

The invention relates to a video recommendation text generation method, a model training method and a related device, the video recommendation text generation method comprises the following steps: obtaining text information corresponding to a target video, the text information comprising description information associated with the target video and at least one piece of label information; inputting the description information and the at least one piece of label information into a pre-trained text generation model to obtain a recommended text of the target video; wherein the text generation model is used for acquiring context representation of the description information and the at least one piece of label information, and determining text content corresponding to each text position in sequence according to the context representation to obtain a recommended text. Thus, context representation can be performed on the description information of the target video and the at least one piece of label information throu