Vehicle scheduling and path optimization method and system under background of double-channel distribution center

Abstract

The invention provides a vehicle scheduling and route optimization method and system under the background of a double-channel distribution center, and belongs to the field of transportation management and logistics distribution, and the method comprises the steps: S1, setting constraint conditions, and building a vehicle scheduling and route optimization model; s2, obtaining the day demands of the online customers and the offline customers respectively, carrying out the classified statistics of order information, and solving the vehicle scheduling and route optimization model when the demand scale is small, so as to obtain a vehicle scheduling and transportation plan for the day demands; when the demand scale is relatively large, preprocessing the data to obtain a feasible initial solution, and turning to step S3; and S3, based on the vehicle scheduling and route optimization model, a heuristic algorithm is used to solve a vehicle scheduling and transportation plan for the demand of the day based on the initial solution. According to the method, from the perspective of a double-channel distribution center, vehicle scheduling and transportation schemes of online and offline customers are optimized.

Description

Technical Field

[0001] The present invention belongs to the field of transportation management and logistics distribution, and in particular relates to a vehicle scheduling and path optimization method and system under the background of a dual-channel distribution center. Background Art

[0002] With the booming development of e-commerce, manufacturers are building a warehousing and distribution system shared by both online and offline channels based on traditional distribution channels, and continuously improving their warehousing and distribution capabilities. In the new context, distribution centers play multiple functions in urban areas. Distribution centers need to distribute products to offline specialty stores, department stores and other terminal stores every day according to relatively fixed inventory and replenishment plans, and also need to deliver goods to individual consumers who placed orders online the day before.

[0003] The vehicle dispatching and distribution management of dual-channel distribution centers have the following problems: 1. The vehicle dispatch plan is unreasonable, the transportation plan is unscientific, and there are delays in delivery.

[0004] When formulating vehicle scheduling and transportation plans, it is necessary to consider a variety of information such as customer type, geographic location, time window, quantity of products required, and vehicle transportation capacity. Especially when customer demand is large and transportation capacity is insufficient, it is difficult for distribution centers to formulate scientific and reasonable vehicle scheduling and transportation plans, resulting in insufficient use of vehicle capacity, delayed product delivery, driver overtime, and reduced customer satisfaction.

[0005] 2. The coordination efficiency between online and offline customer demands is low, and the vehicle transportation efficiency is not high.

[0006] The distribution center serves both online and offline customers at the same time. If it manages the vehicle dispatch for the two types of customers as two independent modules separately, it will require more transport vehicles and drivers, resulting in high transportation costs. For the distribution center that manages the needs of the two types of customers in a collaborative manner, the vehicle and transportation management is chaotic, resulting in low transportation efficiency due to the lack of effective management methods. Summary of the invention

[0007] In order to solve the above technical problems, the present invention provides a vehicle scheduling and path optimization method in the context of a dual-channel distribution center, comprising the following steps: Step S1: Set constraints; establish a vehicle scheduling and route optimization model with the goal of minimizing the sum of vehicle fixed costs, transportation costs, penalty costs for delayed delivery to online and offline customers, and driver overtime costs; Step S2: Obtain the daily demands of online and offline customers respectively, and classify and count the order information, including the order quantity, product quantity, order delivery location and time window; when the demand scale is small, solve the vehicle scheduling and route optimization model to obtain the vehicle scheduling and transportation plan for the daily demand; when the demand scale is large, pre-process the data to obtain a feasible initial solution, and then go to step S3; Step S3: Using a heuristic algorithm, based on the vehicle scheduling and route optimization model and the initial solution, solve the vehicle scheduling and transportation plan for the day's demand, including: multiple routes consisting of online or offline customers, matching of vehicles and routes, vehicle journey readiness time, journey departure time, vehicle arrival time at the customer, customer service start time, customer goods delayed delivery time, and vehicle overtime.

[0008] Beneficial effects: The present invention provides a vehicle scheduling and route optimization method in the context of a dual-channel distribution center. From the perspective of the dual-channel distribution center, a vehicle scheduling and route optimization method facing both online and offline customers is proposed; the method enables the distribution center to strengthen the management of transport vehicles, improve the collaborative service capabilities for both online and offline customers, optimize vehicle scheduling and transportation plans, reduce the delayed delivery rate of goods, reduce distribution costs, and improve customer satisfaction. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] Figure 1 A schematic flow chart of a vehicle scheduling and path optimization method in the context of a dual-channel distribution center according to the present invention; Figure 2 Examples for vehicle scheduling and transportation planning; Figure 3 It is a structural block diagram of a vehicle scheduling and path optimization system in the context of a dual-channel distribution center of the present invention. DETAILED DESCRIPTION

[0010] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention. In addition, the technical features involved in the various embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.

[0011] In the following embodiments of the present invention, the offline customer group of the dual-channel distribution center is relatively fixed, has signed a long-term cooperation plan, has a relatively fixed batch inventory and replenishment plan, and requires the distribution center to deliver its fixed batch demand as soon as possible during working hours. The online customer group is random, and when individual consumers purchase a single quantity of goods online, they will select the delivery time window of the goods; the time, location and quantity of individual consumer orders are uncertain, but due to the adoption of the next-day delivery strategy, at the beginning of a specific delivery date, the information of individual customers is known and certain.

[0012] Embodiment 1 like Figure 1 As shown, a vehicle scheduling and path optimization method in a dual-channel distribution center context provided by an embodiment of the present invention includes the following steps: Step S1: Set constraints; establish a vehicle scheduling and route optimization model with the goal of minimizing the sum of vehicle fixed costs, transportation costs, penalty costs for delayed delivery to online and offline customers, and driver overtime costs; Step S2: Obtain the daily demands of online and offline customers respectively, and classify and count the order information, including the order quantity, product quantity, order delivery location and time window; when the demand scale is small, solve the vehicle scheduling and route optimization model to obtain the vehicle scheduling and transportation plan for the daily demand; when the demand scale is large, pre-process the data to obtain a feasible initial solution, and then go to step S3; Step S3: Using the heuristic fire algorithm, based on the vehicle scheduling and route optimization model and the initial solution, solve the vehicle scheduling and transportation plan for the day's demand, including: multiple routes consisting of online or offline customers, matching of vehicles and routes, vehicle journey readiness time, journey departure time, vehicle arrival time at the customer, customer service start time, customer goods delayed delivery time, and vehicle overtime.

[0013] In one embodiment, the above step S1: setting constraints; establishing a vehicle scheduling and route optimization model with the goal of minimizing the sum of vehicle fixed costs, transportation costs, penalty costs for delayed delivery to online and offline customers, and overtime costs for drivers, specifically includes: Step S11: define various parameters and variables as follows: 1) Collection: is a collection of transport nodes; For offline customers’ collection; A collection of offline customers and distribution centers; A collection of online and offline customers; For the collection of vehicles; Implementing the collection of journeys for vehicles; 2) Parameters: is the capacity of the vehicle; is the travel time from transport node i to transport node j; The service time required by customer i; is the delivery time window requested by customer i; is a fixed sufficiently large integer; 3) Variables: is a 0-1 variable. If the product of customer i is delivered by vehicle k on its g-th trip, then ,otherwise, ; is a 0-1 variable. If the product of customer i is delivered after the product of customer j, then ,otherwise ; is the readiness time of vehicle k for the g-th trip; is the departure time of vehicle k’s g-th trip; represents the arrival time of the vehicle providing service to customer i; represents the time when the service for customer i starts; The delayed delivery time of the goods for customer i; The time it takes for vehicle k to complete all trips and return to the distribution center;

[0014] is the overtime time of vehicle k;

[0015] To eliminate auxiliary variables of sub-loops; Step S12: Offline customers’ demands are in batches, so the transportation plan for offline customers needs to meet the following constraints: Since offline customers require the distribution center to deliver their fixed needs as soon as possible during working hours, the distribution center dispatches vehicles to deliver goods to offline customers after working hours start: (1) Since offline customers’ demands are in batches and the capacity of vehicles is limited, one vehicle only serves one offline customer: (2) The vehicles that provide services to offline customers depart from the distribution center and drive directly to the offline customers they serve. After completing the service, they return directly to the distribution center: (3) Step S13: The demand of online customers is a single quantity. A vehicle can provide services to multiple online customers during a trip, so the order of visiting these customers needs to be planned; the transportation plan of online customers needs to meet the following constraints: Every online customer needs to be served: (4) A vehicle cannot carry more merchandise than it can carry in one trip: (5) For each online customer, a car will drive in and out of the customer's location, satisfying the following constraints (6) and (7): (6) (7) If a vehicle serves two customers on the same journey, then the vehicle can drive from the distribution center to at most one of the two customers and can also return to the distribution center from at most one of the two customers, that is, it satisfies the following constraints (8) and (9): (8) (9) If a customer is served immediately before or after another customer, then the two customers must be on the same trip in the same vehicle, i.e., the following constraints (10) and (11) are satisfied: (10) (11) It is necessary to eliminate the sub-loop by formula (12): (12) Step S14: Both offline customers and online customers need to meet the following constraints: There are significant differences between online and offline customers in terms of demand quantity and delivery time windows, so a car will not serve both online and offline customers in one trip: (13) The previous trip of a vehicle's active trip must not be empty: (14) Step S15: The delivery time window for online and offline customers, and a vehicle needs to provide multiple trips within a working day, so time constraints need to be added: The departure time of a trip shall not be earlier than the vehicle readiness time for the trip plus the service at the departure point, that is, the loading time: (15) The time of arrival at the first customer of a trip is no earlier than the departure time of the trip plus the travel time from the departure point to the customer: (16) The time of arrival of a non-first customer in a trip is no earlier than the service end time of the previous customer plus the travel time between the two customers: (17) The vehicle's readiness time for the next trip is no less than the end time of service for the last customer of the current trip plus the time to return to the starting point: (18) If the vehicle arrives at the customer earlier than the earliest service time, the customer needs to wait until the earliest service time before starting to serve the customer. Otherwise, the service can start as soon as the vehicle arrives at the customer: and (19) Formula (20) is used to obtain the deviation between the time when the vehicle arrives at the customer and the customer's latest service time, which is used to calculate the penalty cost for delayed arrival: (20) The deviation between the time when the vehicle returns to the starting point after completing all journeys and the latest working time at the starting point is calculated by formulas (21) and (22) to calculate the overtime cost: (twenty one) (twenty two) Step S16: Taking the minimum total cost as the objective function, a vehicle scheduling and route optimization model is constructed, which includes the vehicle travel cost, the vehicle fixed cost, the delayed delivery cost of the two types of customers, and the overtime cost beyond working hours: (twenty three) in, and They are the cost coefficients of vehicle travel cost, vehicle fixed cost, delayed delivery cost for two types of customers, and overtime cost beyond working hours.

[0016] In one embodiment, the above step S2: respectively obtain the daily demands of online customers and offline customers, classify and count the order information, including the order quantity, product quantity, order delivery location and time window; when the demand scale is small, solve the vehicle scheduling and route optimization model to obtain the vehicle scheduling and transportation plan for the daily demand; when the demand scale is large, pre-process the data to obtain a feasible initial solution, and go to step S3, which specifically includes: Step S21: Count the number of online and offline orders, the number of products required for each order, the delivery location and time window of the order, the number of vehicles, and the fixed cost of the vehicles; Step S22: if the demand scale of the day is relatively small, directly solve the vehicle scheduling and route optimization model to obtain the vehicle scheduling and transportation plan for the demand of the day; In this step, a solver, such as cplex, can be used to directly solve the vehicle scheduling and route optimization model to obtain the vehicle scheduling and transportation plan for the day's demand.

[0017] Step S23: If the demand scale of the day is large, pre-process the data obtained in step S21 to obtain a feasible initial solution. , then go to step S3.

[0018] For example, a feasible initial solution can be obtained by: First, the orders of offline customers are assigned to the first journey of a vehicle. If the number of offline customer orders is greater than the number of vehicles, the remaining orders are assigned to the second journey of the vehicle that returns to the warehouse earliest. The orders of online customers are sorted from small to large according to the delivery time window of the order and the distance from the delivery location to the warehouse, and the online customers are assigned to vehicles according to the journey rounds. Each assignment ensures that the vehicle that is idle first or returns to the warehouse earliest is fully loaded.

[0019] Considering that this vehicle scheduling and route optimization model is an NP-hard problem involving multiple decision variables, it can be solved by a heuristic algorithm (such as a genetic algorithm, a taboo search algorithm, etc.); the specific solution method can be implemented by conventional techniques, and the present invention uses a heuristic simulated annealing algorithm to solve the problem. The simulated annealing algorithm is a widely used random search algorithm that simulates the solid physics annealing process. There is a certain probability of accepting inferior solutions during the iteration process, which can effectively avoid falling into the local optimum, thereby obtaining a high-quality solution. The simulated annealing algorithm and its hybrid algorithm are often used to solve combinatorial optimization problems, such as production scheduling problems and vehicle routing problems.

[0020] In one embodiment, the above step S3: using a heuristic algorithm, based on the vehicle scheduling and route optimization model and the initial solution, solves the vehicle scheduling and transportation plan for the day's demand, including: multiple routes consisting of online or offline customers, matching of vehicles and routes, vehicle journey readiness time, journey departure time, vehicle arrival time at the customer, customer service start time, customer goods delayed delivery time and vehicle overtime, specifically including: Step S31: Setting the initial temperature , termination temperature , step length , temperature reduction coefficient and inferior solution acceptance criteria; let the current temperature , let the current solution and the current optimal solution be ; The inferior solution acceptance criterion is based on the cost difference between the inferior solution and the current solution and the current temperature. Specifically, if , then accept the inferior solution as the current solution; otherwise, discard the inferior solution; Step S32: If , execute steps S33-S38; Step S33: If , execute steps S34-S37; Step S34: Randomly select one from the following neighborhood structures: (1) Randomly disrupt the order of order access within a trip; this neighborhood structure is only for trips that provide services to online customers; (2) Randomly swap the positions of the two trips; this neighborhood structure can be used for trips that serve two types of customers; (3) Randomly swap the positions of two orders; the two orders selected by this neighborhood structure in one iteration belong to the same type of customers; (4) Randomly select a trip and insert it into another location; this neighborhood structure can be used for trips that serve two types of customers; (5) Randomly select an order and insert it into another position in an existing journey; this neighborhood structure can only select orders belonging to online customers and journeys belonging to online customers; (6) Randomly select a vehicle to add a trip to deliver a randomly selected order; this neighborhood structure can only select orders belonging to online customers; Generate a new solution based on the current solution and the selected neighborhood structure; Step S35: If the objective function value of the new solution is lower than the objective function value of the current solution, the new solution is accepted as the current solution; otherwise, the new solution that is inferior to the current solution is accepted as the current solution with a certain probability; Step S36: If the objective function value of the new solution is lower than the objective function value of the current optimal solution, the new solution is accepted as the current optimal solution; Step S37: ; Step S38: ; Step S39: Output the current optimal solution as the optimal solution.

[0021] Figure 2 It shows an example of a simple vehicle scheduling and transportation plan based on the following daily demand: there are two offline customers (numbered 1 and 2), both with a delivery time window of [8, 10]; there are 14 online customers (numbered 3-16), among which the delivery time window for online customers 3-8 is [8, 10], the delivery time window for online customers 9-10 is [10, 12], the delivery time window for online customers 11-12 is [12, 14], the delivery time window for online customers 13-14 is [14, 16], and the delivery time window for online customers 15-16 is [16, 18]. Figure 2 In the figure, the dots show the time when the vehicle departs from the warehouse and returns to the warehouse, and the triangles show the time when the vehicle arrives at the customer. Based on experience, this example belongs to a case where the demand scale is large, so the total cost of the initial solution obtained by the initial solution proposed in step S2 of the embodiment of the present invention is 141.67, of which the travel cost of the vehicle is 93.42, the fixed cost of the vehicle is 28, the delayed delivery cost of offline customers is 0, the delayed delivery cost of offline customers is 9.35, and the overtime cost beyond working hours is 10.90. Secondly, the total cost of the optimized solution obtained by the simulated annealing algorithm proposed in step S3 of the embodiment of the present invention is 109.20, of which the travel cost of the vehicle is 74.41, the fixed cost of the vehicle is 28, the delayed delivery cost of offline customers is 0, the delayed delivery cost of offline customers is 6.65, and the overtime cost beyond working hours is 0.14.

[0022] Embodiment 2 like Figure 3 As shown, the embodiment of the present invention provides a vehicle scheduling and path optimization system in the context of a dual-channel distribution center, including the following modules: Constructing a model module 41 for setting constraints; establishing a vehicle scheduling and route optimization model with the goal of minimizing the sum of vehicle fixed costs, transportation costs, penalty costs for delayed delivery to online and offline customers, and overtime costs for drivers; The initial solution module 42 is used to obtain the daily demands of online customers and offline customers respectively, and classify and count the order information, including the order quantity, the product quantity, the delivery location and the time window of the order; when the demand scale is small, the vehicle scheduling and route optimization model is solved to obtain the vehicle scheduling and transportation plan for the daily demand; when the demand scale is large, the data is pre-processed to obtain a feasible initial solution, and then transferred to the optimal solution acquisition module; The optimal solution acquisition module 43 is used to use a heuristic algorithm to solve the vehicle scheduling and transportation plan for the day's demand based on the vehicle scheduling and route optimization model and the initial solution, including: multiple routes composed of online or offline customers, matching of vehicles and routes, vehicle journey readiness time, journey departure time, vehicle arrival time at the customer, customer service start time, customer goods delayed delivery time and vehicle overtime.

[0023] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above embodiments can be implemented by software, or by means of software plus necessary general hardware platforms. Based on such understanding, the technical solutions of the above embodiments can be embodied in the form of software products, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.), including several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods of various embodiments of the present invention.

[0024] Technical personnel in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the system can be divided into different functional modules to complete all or part of the functions described above.

[0025] The above is only a preferred specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed in the present invention should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A vehicle scheduling and path optimization method in the context of a dual-channel distribution center, characterized in that: include: Step S1: setting constraints; Establish a vehicle scheduling and route optimization model with the goal of minimizing the sum of vehicle fixed costs, transportation costs, penalty costs for delayed delivery to online and offline customers, and driver overtime costs; Step S2: Obtain the daily demands of online customers and offline customers respectively, and classify and count the order information, including the order quantity, product quantity, order delivery location and time window; When the demand scale is small, the vehicle scheduling and route optimization model is solved to obtain the vehicle scheduling and transportation plan for the day's demand; when the demand scale is large, the data is preprocessed to obtain a feasible initial solution and then go to step S3; Step S3: Using a heuristic algorithm, based on the vehicle scheduling and route optimization model and the initial solution, solve the vehicle scheduling and transportation plan for the day's demand, including: multiple routes consisting of online or offline customers, matching of vehicles and routes, vehicle journey readiness time, journey departure time, vehicle arrival time at the customer, customer service start time, customer goods delayed delivery time, and vehicle overtime.

2. The vehicle scheduling and route optimization method in the context of a dual-channel distribution center according to claim 1 is characterized in that: Step S1: setting constraints; establishing a vehicle scheduling and route optimization model with the goal of minimizing the sum of vehicle fixed costs, transportation costs, penalty costs for delayed delivery to online and offline customers, and driver overtime costs, specifically including: Step S11: define various parameters and variables as follows: 1) Collection: is a collection of transport nodes; For offline customers’ collection; A collection of offline customers and distribution centers; A collection of online and offline customers; For the collection of vehicles; Implementing the collection of journeys for vehicles; 2) Parameters: is the capacity of the vehicle; is the travel time from transport node i to transport node j; The service time required for customer i; is the delivery time window requested by customer i; is a fixed sufficiently large integer; 3) Variables: is a 0-1 variable. If the product of customer i is delivered by vehicle k on its g-th trip, then ,otherwise, ; is a 0-1 variable. If the product of customer i is delivered after the product of customer j, then ,otherwise ; is the readiness time of vehicle k for the g-th trip; is the departure time of vehicle k’s g-th trip; represents the arrival time of the vehicle providing service to customer i; represents the time when the service for customer i starts; The delayed delivery time of the goods for customer i; The time it takes for vehicle k to complete all trips and return to the distribution center; is the overtime time of vehicle k; To eliminate auxiliary variables of sub-loops; Step S12: Offline customers’ demands are in batches, so the transportation plan for offline customers needs to meet the following constraints: Since offline customers require the distribution center to deliver their fixed needs as soon as possible during working hours, the distribution center dispatches vehicles to deliver goods to offline customers after working hours start: (1) Since offline customers’ demands are in batches and the capacity of vehicles is limited, one vehicle only serves one offline customer: (2) The vehicles that provide services to offline customers depart from the distribution center and drive directly to the offline customers they serve. After completing the service, they return directly to the distribution center: (3) Step S13: The demand of online customers is a single quantity. A vehicle can provide services to multiple online customers during a trip, so the order of visiting these customers needs to be planned; the transportation plan of online customers needs to meet the following constraints: Every online customer needs to be served: (4) A vehicle cannot carry more merchandise than it can carry in one trip: (5) For each online customer, a car will drive in and out of the customer's location, satisfying the following constraints (6) and (7): (6) (7) If a vehicle serves two customers on the same journey, then the vehicle can drive from the distribution center to at most one of the two customers and can also return to the distribution center from at most one of the two customers, that is, it satisfies the following constraints (8) and (9): (8) (9) If a customer is served immediately before or after another customer, then the two customers must be on the same trip in the same vehicle, i.e., the following constraints (10) and (11) are satisfied: (10) (11) It is necessary to eliminate the sub-loop by formula (12): (12) Step S14: Both offline customers and online customers need to meet the following constraints: There are significant differences between online and offline customers in terms of demand quantity and delivery time windows, so a car will not serve both online and offline customers in one trip: (13) The previous trip of a vehicle's active trip must not be empty: (14) Step S15: The delivery time window for online and offline customers, and a vehicle needs to provide multiple trips within a working day, so time constraints need to be added: The departure time of a trip shall not be earlier than the vehicle readiness time for the trip plus the service at the departure point, that is, the loading time: (15) The time of arrival at the first customer of a trip is no earlier than the departure time of the trip plus the travel time from the departure point to the customer: (16) The time of arrival of a non-first customer in a trip is no earlier than the service end time of the previous customer plus the travel time between the two customers: (17) The vehicle's readiness time for the next trip is no less than the end time of service for the last customer of the current trip plus the time to return to the starting point: (18) If the vehicle arrives at the customer earlier than the earliest service time, the customer needs to wait until the earliest service time before starting to serve the customer. Otherwise, the service can start as soon as the vehicle arrives at the customer: and (19) Formula (20) is used to obtain the deviation between the time when the vehicle arrives at the customer and the customer's latest service time, which is used to calculate the penalty cost for delayed arrival: (20) The deviation between the time when the vehicle returns to the starting point after completing all journeys and the latest working time at the starting point is calculated by formulas (21) and (22) to calculate the overtime cost: (21) (22) Step S16: Taking the minimum total cost as the objective function, a vehicle scheduling and route optimization model is constructed, which includes the vehicle travel cost, the vehicle fixed cost, the delayed delivery cost of the two types of customers, and the overtime cost beyond working hours: (23) in, and They are the cost coefficients of vehicle travel cost, vehicle fixed cost, delayed delivery cost for two types of customers, and overtime cost beyond working hours.

3. A vehicle dispatching and routing optimization system in the context of a dual-channel distribution center, characterized in that: Includes the following modules: Build a model module to set constraints; establish a vehicle scheduling and route optimization model with the goal of minimizing the sum of vehicle fixed costs, transportation costs, penalty costs for delayed delivery to online and offline customers, and driver overtime costs; The initial solution module is used to obtain the daily demands of online and offline customers respectively, classify and count the order information, including the order quantity, product quantity, order delivery location and time window, pre-process the data, and obtain a feasible initial solution; The optimal solution acquisition module is used to use the simulated annealing algorithm to solve the vehicle scheduling and transportation plan for the day's demand based on the vehicle scheduling and route optimization model and the initial solution, including: multiple routes composed of online or offline customers, matching of vehicles and routes, vehicle journey readiness time, journey departure time, vehicle arrival time at the customer, customer service start time, customer goods delayed delivery time and vehicle overtime.

Images