Research On Optimization Of O2O Takeout Crowdsourcing Delivery Route

With the rapid development of the Internet and e-commerce,O2O takeout has gradually become the mainstream diet consumption model.The market of O2O takeout platforms is increasingly large,the O2O takeout orders volume are often overwhelmed during the peak hour,which brings greater distribution pressure to O2O takeout platforms.The O2O takeout crowdsourcing distribution model can make full use of the idle labor force in the society.When the self-deliverer is short of capacity in peak hours,the O2O takeout crowdsourcing distribution model can quickly relieve the distribution pressure at a lower cost and improve the delivery efficiency.Thus,it has become one of the main distribution models of O2O takeout distribution.The pace of life is accelerating in modern society,and customers' requirements on the timeliness of delivery on O2O takeout platform are constantly improving.In addition,the distinct characteristics such as the large number of takeout orders in the peak period,different order picking and delivery locations,etc.Which all bring great challenges to the crowdsourcing delivery of O2O takeout platform.Reasonably optimize the crowdsourcing distribution of a large number of takeout orders is the key issue to improve the delivery efficiency of O2O takeout platform,reduce the delivery cost,and thus improve the customer satisfaction of the platform.It is also an important operational management issue that needs to be optimized for the long-term and stable development of O2O takeout platform.Therefore,based on the data analysis method,this paper conducts cluster analysis on the pickup and delivery locations of a large number of takeout orders respectively,and proposes to merge delivery orders with similar pickup locations or delivery locations.Based on the Vehicle Routing Problem with Pick-up and Deliveries model,an O2O takeout crowdsourcing distribution route optimization mathematical model considering merge delivery orders is established,and a heuristic algorithm is designed for effective solution.Firstly,the research is carried out based on the optimization goal of minimizing the total cost of crowdsourcing distribution on the O2O takeout platform.In response to O2O takeout platforms' peak orders and high timeliness requirements for delivery,the O2O takeout crowdsourcing distribution network does not have a fixed distribution center,and the delivery location of different O2O takeout orders is different.The kmeans algorithm is used to deal with a large number of O2O takeout orders.Cluster analysis is performed on the delivery locations of orders,and orders are merged according to the principle of similar delivery locations.With the optimization goal of minimizing the total delivery cost of the O2O takeout platform,establish a mathematical model for the optimization of O2O takeout orders combined with crowdsourcing delivery routes with soft-time,design an improved Genetic Algorithm solution model.The numerical simulation results showed that the model is of feasibility and the algorithm is of validity.Secondly,on the basis of the above research,considering the different time sensitivities of different customers on O2O takeout platforms,in order to improve the customer satisfaction of O2O takeout platforms,the time sensitivity coefficient of customers is introduced to establish an O2O takeout crowdsourcing delivery route optimization model with the objective function of maximizing the time satisfaction of customers on the delivery platforms.Aiming at the high timeliness,large number of takeout orders in peak periods,different pickup locations of takeout orders,and no fixed distribution center of takeout crowdsourcing distribution model,a two-stage algorithm is designed to solve the O2O takeout crowdsourcing distribution path optimization model.In the first stage of the algorithm,Hierarchical clustering algorithm is used to perform cluster analysis on the pickup locations of a large number of takeout orders,and a large number of takeout orders are clustered according to the principle of similar pickup locations.In the second stage,the improved Genetic Algorithm is to solve the O2O takeout crowdsourcing distribution path optimization model.Numerical simulation is used to verify the model and two-stage solution algorithm,and the impact of time sensitivity on customer time satisfaction is also analyzed.The research enriches the O2O takeout crowdsourcing distribution path optimization theory,and the idea of merge delivery orders based on data analysis has a good reference significance for O2O takeout platforms to relieve the delivery pressure in peak periods and improve the customer satisfaction.