The invention discloses an accurate facial paralysis degree evaluation method and device based on H-B grading under CV. The method comprises the following steps: establishing a facial paralysis key point detection model; acquiring to-be-detected data and processing the to-be-detected data; sequentially inputting an expression-free natural state static image, a sequence image I, a sequence image II, a sequence image III and a sequence image IV into the facial paralysis key point detection model to output a plurality of corresponding groups of face shapes, and updating the plurality of groups offace shapes; evaluating the facial paralysis degree of the to-be-detected user; calculating theta1, theta2, theta3, theta4, theta5, theta6, theta7, theta8, theta9, theta10 and theta11 and comparing the theta1, theta2, theta3, theta4, theta5, theta6, theta7, theta8, theta9, theta10 and theta11 with thresholds; and judging the facial paralysis degree of the to-be-detected user through the comparison result, and calculating a facial paralysis index. According to the invention, the detection model has high detection positioning precision, the precision and accuracy of comprehensive evaluation anddetection of the facial paralysis degree of the to-be-detected user are greatly improved, and a powerful support is provided for prevention, discovery and treatment of facial paralysis patients.