Abstract: The present disclosure relates to a method and system for human-machine interaction. The method may include receiving input information. The input information may include scene information and a user input from a user. The method may also include determining an avatar based on the scene information, and determining user intention information based on the user input. The method may include determining output information based on the user intention information. The output information may include interaction information between the avatar and a user. The method may further include presenting the avatar based on the output information.