The present invention relates to a method of calculating voice and facial emotion values, and an output method of an artificial intelligence speaker using the same. According to an embodiment of the present invention, a method for outputting an artificial intelligence speaker based on a voice and an emotion value calculated from a facial face includes the steps of collecting a facial face and a voice from a device, and converting the collected facial face and voice into an image or data. And calculating a first analysis value by recognizing the emotion of the data-generated voice; calculating a second analysis value by recognizing the emotion of the imaged facial face; and the first analysis value and the second analysis value. And calculating a final emotion value by calculating a weight index table on the analyzed value. Accordingly, according to an embodiment of the present invention, the user's facial facial image or voice voice data collected from the device is not separately stored in the server, and the final emotion value calculated through the algorithm is stored in the server and converted into big data. It is structured and has the effect of preventing users from infringing on human rights.
展开▼