Design and Implementation of a Rural Social Security System Based on Deep Learning

Abstract

After the reform and opening up, my country’s economic level and total national strength have achieved unprecedented growth. The building of a well-off society in an all-round way is moving towards a harmonious society. The development of social security is also an important part of the development and improvement of a socialist harmonious society. This article is aimed at designing a rural social security system based on deep learning algorithms, using sample collection and statistical analysis methods, collecting samples, simplifying the algorithm, and establishing a new rural social security system. The data collected by the system shows that the proportion of farmers who choose very satisfied, satisfied, average, dissatisfied, and very dissatisfied with the satisfaction of the new rural insurance is 8.94%, 45.53%, 34.96%, 8.13%, and 2.44%. It can be seen that the proportion of farmers who choose to be satisfied is the largest, and more than 10.0% of farmers choose to be dissatisfied or very dissatisfied. Investigate the factors that farmers worry about participating in the new rural insurance, and the questionnaire options can also be set to multiple choices. The survey results show that 29.27% of the farmers think that the individual payment for participating in the new rural insurance is higher; 26.02% of the farmers believe that they do not understand the new rural insurance system; 9.76% of the farmers believe that it is unnecessary to pay for the new rural insurance; 22.76% of farmers choose to rely on themselves or their children in the future; 27.64% of farmers think that the system is unstable. It has basically realized the design of a brand new rural social security system starting from the deep learning of semantic computing.

Defect detection algorithm for cigarette outer packaging based on deep learning

“…Qu et al [16] proposed an improved SSD network and a pyramid convolution-based cigarette appearance defect detection model with an mAP of 90.26%. Zhao [17] achieved an mAP of 97.64% by improving NMS on YOLOv5 with CIoU loss instead of IoU loss. Lu et al focused on the defect detection of the pulling thread on the transparent plastic outer packaging of tobacco rods.…”