School of Economics and Trade Management, Yibin Vocational and Technical College, Yibin 644003, China.
School of Management, Guangzhou Xinhua University, Dongguan 523133, China.
Comput Intell Neurosci. 2022 Sep 16;2022:1823762. doi: 10.1155/2022/1823762. eCollection 2022.
In order to carry out practical innovation of the intelligent logistics system and promote the practicality of the intelligent logistics system and supply chain management process, this study aims to optimize the design of the intelligent logistics system and supply chain management under edge computing (EC) and the Internet of Things (IoT). The flower pollination algorithm performs the positioning function in the intelligent logistics system and supply chain management. Based on the research on the design of the intelligent logistics system and supply chain management under the EC and IoT, this thesis analyzes the positioning of intelligent logistics systems and supply chain management through the flower pollination algorithm. The eXtreme Gradient Boosting (XGBoost) model is used to predict user information in the system of supply chain management information. Finally, the operation of intelligent logistics and supply chain management systems, the prediction model of supply chain management under XGBoost, and the change of supply chain management and material flow are analyzed. The results show that with the increase in the number of iterations, the optimized algorithm improves the comparison distance error by 53.57%, which has high accuracy and can meet the requirements of positioning and tracking of the intelligent logistics system and logistics status query in supply chain management. The waiting time of the intelligent logistics system is shorter than that of the supply chain management system, and the average waiting time of the system increases by 121.252 ms. The XGBoost model can well predict user information under supply chain management. After discussing the changes of the intelligent logistics system from 2018 to 2020, it is found that the operation efficiency of the supply management system is higher with the increase of the system operation days. The intelligent logistics system has a significant impact on the development of the logistics industry. This research gives a reference for establishing the intelligent logistics system and supply chain management system.
为了实现智能物流系统的实际创新，提高智能物流系统和供应链管理过程的实用性，本研究旨在优化边缘计算（EC）和物联网（IoT）下的智能物流系统和供应链管理设计。花授粉算法在智能物流系统和供应链管理中执行定位功能。基于对 EC 和 IoT 下智能物流系统和供应链管理设计的研究，本文通过花授粉算法分析了智能物流系统和供应链管理的定位。使用极端梯度提升（XGBoost）模型预测供应链管理系统中的用户信息。最后，分析了智能物流和供应链管理系统的运行、XGBoost 下的供应链管理预测模型以及供应链管理和物流的变化。结果表明，随着迭代次数的增加，优化算法将比较距离误差提高了 53.57%，具有很高的准确性，可以满足智能物流系统的定位和跟踪以及供应链管理中物流状态查询的要求。智能物流系统的等待时间短于供应链管理系统，系统的平均等待时间增加了 121.252ms。XGBoost 模型可以很好地预测供应链管理下的用户信息。讨论了 2018 年至 2020 年智能物流系统的变化后，发现随着系统运行天数的增加，供应管理系统的运行效率更高。智能物流系统对物流行业的发展具有重大影响。本研究为建立智能物流系统和供应链管理系统提供了参考。
