A human-pet interaction system includes a pet container, a display apparatus, a speaker, and a user apparatus. The pet container has a side plate. The display apparatus is disposed on the pet container, and has a display panel and a processing module connected to the display panel. The display panel is disposed on the side plate, and has a display surface facing to an interior of the pet container. The speaker is connected to the processing module. The user apparatus transmits an audio and video control signal to the processing module to control the display panel and the speaker to play audio and video data contents. Accordingly, the user apparatus plays vivid and various audio and video data contents on the display panel and/or through the speaker so as to attract pets' attention and activate pets' motions and facial expressions, thus increasing interaction between pets and keepers.
