A method of controlling a marine product transportation environment is disclosed. A method of controlling a marine product transportation environment according to an embodiment is a method of controlling a transportation environment of aquatic products based on artificial intelligence, wherein aquatic product detection cameras in a water tank for transportation capture an image for each segment for 2 minutes, and manage water quality The sensor acquires the water quality status data, the embedded computer in the transportation tank acquires the vehicle operation information, and based on the imaging result, the water quality status data acquisition result, and the autonomous operation information acquisition result, the embedded computer generates the first input signal. The embedded computer inputs the first input signal into the convolutional neural network of the blockchain network including the embedded computer, the embedded computer acquires the first output signal from the convolutional neural network, and based on the first output signal, the embedded computer Control the liquid oxygen regulator and water quality controller, and control Based on the re-acquisition of images for each segment, water quality status data, and vehicle operation information at 2-minute intervals, and based on the re-acquisition results, the embedded computer updates the first input signal and detects abnormal marine products in the first input signal Based on the result data, the embedded computer generates a first learning signal, and based on the result of generating the first learning signal, the embedded computer may apply the first learning signal to the convolutional neural network to learn.수산물 운송 환경을 제어하는 방법이 개시된다. 일실시예에 따른 수산물 운송 환경을 제어하는 방법은 인공지능을 기반으로 수산물의 운송 환경을 제어하는 방법에 있어서, 운송용 수조 내의 수산물 감지 영상 카메라들이 각 분할 별 영상을 2분 간 촬영하고, 수질 관리 센서가 수질 상태 데이터를 획득하고, 운송용 수조의 임베디드 컴퓨터가 자동차 조작 정보를 획득하고, 영상 촬영 결과, 수질 상태 데이터 획득 결과 및 자동자 조작 정보 획득 결과에 기초하여, 임베디드 컴퓨터가 제1 입력 신호를 생성하고, 임베디드 컴퓨터가
