The present application relates to the technical field of natural language processing. Particularly disclosed are a question-answer method and question-answer apparatus based on a Transformer model, and a storage apparatus. The question-answer method comprises: acquiring question text input by a user, and processing the question text to obtain a question sequence; decoding the question sequence to obtain a plurality of candidate answers related to the question sequence; splicing the question sequence with each candidate answer; and scoring each splicing result, and selecting the candidate answer corresponding to the highest score to be the optimal answer for the question sequence. By means of the above method, the present application can solve the problems of question answering intention recognition not being sufficiently accurate, answers not being sufficiently humanized, and a context connection during a dialogue process not being sufficiently close.
展开▼