The invention discloses an intelligent service device capable of simulating human interactions and a method. User sex and age are identified according to the image information of a user, and user voice information is textualized to obtain text information, and semantic analysis is performed on the text information and user questions are extracted; similar question query and answer recommendation are performed on the extracted user questions by means of database; finally the recommended answers are converted into voice answers which are played for the user and preset figure actions matched with the recommended answers or the voice answers are presented to the user, wherein the voice answers are of the voice types selected in accordance with the user sex and age. According to the device and method of the invention, there is no need to store large video data in advance so as to save memory space and reduce cost; big data analysis is used for realizing intelligent service and the user experience is improved.