1403 results about "Artificial Intelligence System" patented technology

The embodiment of the invention discloses an animation image driving method based on artificial intelligence. The method comprises the following steps: collecting media data of facial expression changes when a speaker speaks voice, determining a first expression base of a first animation image corresponding to the speaker, and reflecting different expressions of the first animation image through the first expression base. After target text information used for driving the second animation image is determined, acoustic features and target expression parameters corresponding to the target text information are determined according to the target text information, the collected media data and the first expression base. Acoustic features and target expression parameters are used. A second animation image with a second expression base can be driven. According to the method and the device, the second animation image can give out the sound of the target text information spoken by the speaker through acoustic feature simulation, and the facial expression conforming to the due expression of the speaker is made in the sounding process, so that vivid substitution feeling and immersion feeling are brought to the user. The interaction experience of the user and the animation image is improved.