摘要
针对现代物流业务不断多样化和细分化导致传统的车货匹配方法和配送方式难以满足配送需求的问题,文章提出将大件货物与应急零散货物结合进行协同配送,构建以车主收益最大为目标的两阶段车货匹配推荐模型,充分利用货物阶段性送达产生的的剩余空间,并且在模型中考虑时效、期望、激励、货损等现实因素提高模型可实施性。为了获得不同货种间协同配送的最优匹配推荐方案,提出一种改进的人工兔优化算法(ARO)进行求解,通过引入混沌反向学习、模拟退火和自适应扰乱因子提升性能,然后通过仿真实验验证模型和算法的有效性,最后基于供需双方偏好的构建车货推荐系统为其推荐配送方案。
Aiming at the problem that the traditional vehicle-cargo matching method and distribution method cannot meet the distribution demand due to the continuous diversification and subdivision of modern logistics business,it is proposed to combine large-scale cargo with emergency scattered cargo for collaborative distribution,and build a car owner's profit maximization.The two-stage vehicle-cargo matching recommendation model makes full use of the remaining space generated by the staged delivery of goods,and considers timeliness,expectations,incentives,cargo damage and other realistic factors in the model to improve the implementability of the model.In order to obtain the optimal matching recommendation scheme for collaborative delivery among different types of goods,an improved Artificial Rabbit Optimization Algorithm(ARO)is proposed to solve it,and the performance is improved by introducing chaotic anti-learning,simulated annealing and adaptive disturbance factors,and then through simulation experiments to verify the effectiveness of the model and algorithm,and finally build a vehicle and cargo recommendation system based on the preferences of both the supply and demand sides to recommend a delivery plan.
作者
张碧玉
刘毅
孙哲
徐雷
龚光富
ZHANG Biyu;LIU Yi;SUN Zhe;XU Lei;GONG Guangfu(Post Big Data Technology and Application Engineering Research Center of Jiangsu Province,Nanjing University of Posts and Telecommunications,Nanjing 210023,China;Post Industry Technology Research and Development Center of the State Posts Bureau(Internet of Things Technology),Nanjing University of Posts and Telecommunications,Nanjing 210023,China;Anhui Yougu Express Intelligent Technology Co.,Ltd.,Wuhu 241300,China)
出处
《物流科技》
2023年第20期95-104,共10页
Logistics Sci-Tech
关键词
车货匹配
两阶段
ARO
混沌映射
反向学习
模拟退火
扰乱因子
vehicle-cargo matching
two-stage
ARO
chaotic mapping
reverse learning
simulated annealing
disturbance factor
