WO2023226459A1 - 冷链物流车辆的调度方法及相关设备 - Google Patents

冷链物流车辆的调度方法及相关设备 Download PDF

Info

Publication number
WO2023226459A1
WO2023226459A1 PCT/CN2023/072706 CN2023072706W WO2023226459A1 WO 2023226459 A1 WO2023226459 A1 WO 2023226459A1 CN 2023072706 W CN2023072706 W CN 2023072706W WO 2023226459 A1 WO2023226459 A1 WO 2023226459A1
Authority
WO
WIPO (PCT)
Prior art keywords
vehicles
vehicle
delivery
goods
total
Prior art date
Application number
PCT/CN2023/072706
Other languages
English (en)
French (fr)
Other versions
WO2023226459A9 (zh
Inventor
李进之
刘洋
陈亚迷
郭明杰
Original Assignee
北京京东乾石科技有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 北京京东乾石科技有限公司 filed Critical 北京京东乾石科技有限公司
Publication of WO2023226459A1 publication Critical patent/WO2023226459A1/zh
Publication of WO2023226459A9 publication Critical patent/WO2023226459A9/zh

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G06Q10/047—Optimisation of routes or paths, e.g. travelling salesman problem
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
    • G06Q10/083—Shipping
    • G06Q10/0832—Special goods or special handling procedures, e.g. handling of hazardous or fragile goods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
    • G06Q10/083—Shipping
    • G06Q10/0835—Relationships between shipper or supplier and carriers
    • G06Q10/08355—Routing methods
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
    • Y02T10/00—Road transport of goods or passengers
    • Y02T10/10—Internal combustion engine [ICE] based vehicles
    • Y02T10/40—Engine management systems

Definitions

  • the present disclosure relates to the fields of computer and communication technologies, and specifically to dispatching methods and devices for cold chain logistics vehicles, computer-readable storage media, and electronic devices.
  • Cold chain logistics refers to a systematic project in which items are always kept in the optimal low-temperature environment specified by the product during the production, warehousing, transportation and sales process until consumption, so that food quality can be ensured and food loss can be reduced.
  • the optimization of truck collection and distribution scheduling of cold chain logistics has huge market value and research value. Problems such as vehicle and cargo matching and dispatching in the cold chain scenario have certain particularities. For example, cold chain dispatching requires a specialized dispatching center, and cold chain transportation also requires specialized vehicles. At the same time, cold chain products need to be prevented from thawing. , the requirements for timeliness are relatively high. These particularities determine that scheduling issues in cold chain scenarios cannot directly use the scheduling solutions in general scenarios.
  • Embodiments of the present disclosure provide dispatching methods and devices for cold chain logistics vehicles, computer-readable storage media, and electronic devices, which can realize efficient dispatching of cold chain logistics vehicles.
  • a dispatching method for cold chain logistics vehicles including:
  • obtaining the set of possible vehicle quantities based on the total amount of goods to be distributed, the vehicle loading rate and the maximum loading capacity of the vehicle includes: dividing the total amount of goods to be distributed by the first vehicle loading The product of the vehicle loading rate and the maximum loading capacity of the vehicle is rounded up to obtain the upper bound of the set of possible vehicle numbers; the total amount of goods to be distributed is divided by the second vehicle loading rate and the maximum loading capacity of the vehicle.
  • the product of the cargo volume, and rounded up to obtain the lower bound of the set of the number of possible vehicles; the number of used vehicles between the upper bound of the set of the number of possible vehicles and the lower bound of the set of the number of possible vehicles is composed of The set of the number of vehicles that may be used; wherein, the first vehicle loading rate is the vehicle loading rate minus the first ratio, the second vehicle loading rate is the vehicle loading rate plus the second ratio, and the third vehicle loading rate is the vehicle loading rate plus the second ratio.
  • a ratio and the second ratio are both greater than zero and less than 1.
  • the elbow method is used to determine the number of vehicles used for scheduling and the global optimum based on the sub-optimal delivery route and the shortest total delivery timeout corresponding to each number of possible vehicles in the set of possible vehicle numbers.
  • the delivery route includes: dividing the set of the number of vehicles that may be used into a first set and a second set; and dividing the number of vehicles that may be used and the corresponding shortest total delivery timeout in each of the first set and the second set, respectively.
  • Linear regression is performed to obtain a first prediction model and a second prediction model; the number of vehicles used for scheduling and the global optimal delivery route are determined according to the first prediction model and the second prediction model.
  • determining the number of vehicles and the global optimal delivery route used for scheduling according to the first prediction model and the second prediction model includes: obtaining the first set of data according to the first prediction model. The minimum root mean square difference; obtain the minimum root mean square difference of the second set according to the second prediction model; divide the combination by the first set and the second set of the possible vehicle number sets, the first The sum of the minimum root mean square difference of the set and the minimum root mean square difference of the second set is the smallest, the number of possible vehicles that divide the first set and the second set and the corresponding sub-optimal delivery route are used for scheduling. Number of vehicles and global optimal delivery route.
  • obtaining the minimum root mean square difference of the first set according to the first prediction model includes: according to the shortest total delivery timeout corresponding to the number of possible vehicles in the first set, the first The minimum root mean square difference of the first set is obtained from the predicted value of a prediction model and the number of elements in the first set of possible vehicle numbers.
  • obtaining the minimum root mean square difference of the second set according to the second prediction model includes: based on the shortest total delivery timeout corresponding to the number of possible vehicles in each of the second set, the first The minimum root-mean-square difference of the second set is obtained from the predicted value of the two prediction models and the number of elements in the second set of possible vehicle numbers.
  • determining the sub-optimal delivery route that minimizes the total delivery timeout under capacity constraints, temperature constraints and time constraints includes: The goods to be delivered are classified according to the required vehicle temperature layer requirements; each type of goods to be delivered is allocated to vehicles in the corresponding temperature layer according to the vehicle loading rate and the vehicle's maximum loading capacity; according to possible delivery routes and customer requirements Based on the shipping time and delivery time, obtain the sub-optimal delivery route that minimizes the total delivery timeout.
  • the sub-optimal delivery route that makes the shortest total delivery timeout is obtained, including: when the shortest total delivery timeout with the number of possible vehicles is equal to zero When , the delivery route with the shortest distance is selected as the sub-optimal delivery route.
  • the vehicle has N temperature layers, where N is an integer greater than or equal to 2.
  • obtaining the total amount of goods to be distributed, the vehicle loading rate and the maximum loading capacity of the vehicle includes: when the vehicle models are inconsistent, obtaining the total amount of goods to be distributed, the vehicle loading rate and the weighted maximum vehicle loading capacity Loading volume.
  • a dispatching device for cold chain logistics vehicles including: a first acquisition module configured to acquire the total amount of goods to be distributed, the vehicle loading rate, and the maximum loading capacity of the vehicle; a second acquisition module configured In order to obtain a set of possible vehicle numbers based on the total amount of goods to be distributed, the vehicle loading rate and the maximum loading capacity of the vehicle; a first determination module, for each possible vehicle in the set of possible vehicle numbers Quantity, determine the sub-optimal delivery route that minimizes the total delivery timeout under capacity constraints, temperature constraints and time constraints; the second determination module is configured to correspond to the number of possible vehicles in each of the set of possible vehicle quantities.
  • the sub-optimal delivery route and the shortest delivery total timeout are determined by using the elbow method to determine the number of vehicles used for scheduling and the global optimal delivery route.
  • an electronic device including: one or more processors; a storage device configured to store one or more programs.
  • the one or more programs are processed by the one or more
  • the processor is executed, the one or more processors are caused to implement any one of the above embodiments. the method described.
  • a computer-readable storage medium stores a computer program.
  • the computer program is executed by a processor, the method described in any one of the above embodiments is implemented.
  • the dispatching method of cold chain logistics vehicles of the present disclosure obtains a set of the number of possible vehicles to be used based on the vehicle loading rate, the maximum loading capacity of the vehicle and the total amount of goods to be distributed. Based on the set of the number of possible vehicles to be used, based on Capacity constraints, temperature constraints and time constraints obtain the number of vehicles used in scheduling and the global optimal delivery route.
  • Figure 1 shows a schematic diagram of an exemplary system architecture to which a dispatching method for cold chain logistics vehicles according to an embodiment of the present disclosure can be applied;
  • Figure 2 schematically shows a flow chart of a dispatching method for cold chain logistics vehicles according to an embodiment of the present disclosure
  • Figure 3 shows a flow chart of using the elbow method to determine the number of vehicles used for scheduling and the global optimal delivery route according to an embodiment of the present disclosure
  • Figure 4 shows another flowchart of using the elbow method to determine the number of vehicles used for scheduling and the global optimal delivery route according to an embodiment of the present disclosure
  • Figure 5 shows regression on both sides of the dividing point, and the dividing point with the smallest sum of root-mean-square differences is selected
  • Figure 6 schematically shows a block diagram of a dispatching device for cold chain logistics vehicles according to an embodiment of the present disclosure
  • Figure 7 schematically shows a block diagram of a dispatching device for a cold chain logistics vehicle according to another embodiment of the present disclosure
  • Figure 8 schematically shows a block diagram of a dispatching device for a cold chain logistics vehicle according to another embodiment of the present disclosure.
  • FIG. 9 shows a schematic structural diagram of a computer system suitable for implementing an electronic device according to an embodiment of the present disclosure.
  • Example embodiments will now be described more fully with reference to the accompanying drawings.
  • Example embodiments may, however, be embodied in various forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concepts of the example embodiments. To those skilled in the art.
  • the total quantity of goods to be delivered is the total mass or volume of goods to be delivered included in the total waybill to be dispatched within the dispatch period.
  • Vehicle loading rate is the ratio of the actual amount of cargo loaded on the vehicle to the theoretical maximum loading capacity.
  • the maximum loading capacity of a vehicle is the maximum total mass or volume of cargo that the vehicle can load.
  • Capacity constraint means that the actual amount of cargo carried by the vehicle must be less than or equal to the maximum total mass or volume of cargo that the vehicle can load.
  • Temperature layer constraint means that the temperature layer of the vehicle (refrigerated, frozen or normal temperature) must match the transportation requirements of the goods.
  • Time constraints refer to the shipping time and delivery time required by the customer in the order.
  • the total delivery timeout refers to the delivery time that exceeds the customer's request after all vehicles complete the delivery of the order. total timeout period.
  • Delivery route refers to the route traveled by the vehicle during delivery.
  • the number of vehicles that may be used refers to the number of vehicles that may be used that is used for calculation in determining the number of vehicles used for scheduling and the global optimal delivery route in this disclosure.
  • the set of possible vehicle quantities is a set consisting of all possible vehicle quantities.
  • FIG. 1 shows a schematic diagram of an exemplary system architecture 100 to which the dispatching method of cold chain logistics vehicles according to the embodiment of the present disclosure can be applied.
  • the system architecture 100 may include one or more of terminals 101, 102, 103, a network 104 and a server 105.
  • Network 104 is the medium used to provide communication links between terminals 101, 102, 103 and server 105.
  • Network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, among others.
  • the number of terminals, networks and servers in Figure 1 is only illustrative. You can have any number of endpoints, networks, and servers depending on your implementation needs.
  • the server 105 may be a server cluster composed of multiple servers.
  • the terminals 101, 102, 103 can be various electronic devices with display screens, including but not limited to smart phones, tablet computers, portable computers, desktop computers, and so on.
  • the server 105 may be a server that provides various services. For example, when a staff member sends instructions for dispatching cold chain logistics vehicles to the server 105 through the terminal 103 (it can also be the terminal 101 or 102), the server 105 can obtain the total amount of goods to be distributed, the vehicle loading rate, and the vehicle's maximum loading capacity; according to The total amount of goods to be distributed, the vehicle loading rate and the maximum loading capacity of the vehicle obtain a set of possible vehicle numbers; for each possible number of vehicles in the set of possible vehicle numbers, determine the number of possible vehicles in the capacity constraint, The sub-optimal delivery route that makes the total delivery timeout the shortest under temperature constraints and time constraints; according to the sub-optimal delivery route and the shortest total delivery timeout corresponding to the number of possible vehicles in the set of possible vehicle numbers, use manual The elbow method is used to determine the number of vehicles and the global optimal delivery route used for scheduling.
  • the server 105 can display the number of vehicles used for scheduling and the global optimal delivery route on the terminal 103 or other terminals, and then staff or other personnel (for example, users) can view the number of vehicles used for scheduling and the number of vehicles used for scheduling based on the content displayed on the terminal. Global optimal delivery route.
  • Figure 2 schematically shows a flow chart of a dispatching method for cold chain logistics vehicles according to an embodiment of the present disclosure.
  • the method steps of the embodiments of the present disclosure may be executed by a terminal or a server, or by an interaction between a terminal and a server, or by a server cluster.
  • they may be executed by the server 105 in Figure 1 , but the disclosure is not limited thereto.
  • step S210 the total amount of goods to be delivered, the vehicle loading rate and the maximum vehicle loading capacity are obtained.
  • the terminal or server obtains the vehicle loading rate, the vehicle's maximum loading capacity, and the total amount of goods to be delivered.
  • obtaining the total amount of goods to be distributed, the vehicle loading rate, and the vehicle's maximum loading capacity include:
  • data during actual use, data must first be collected during vehicle dispatch.
  • the collected data includes but is not limited to: the number of the waybill to be dispatched, the destination of the waybill, and the total volume of the goods on the waybill. , the total weight of the goods on the waybill, the start delivery time required by the waybill, the latest delivery time required by the waybill, the vehicle models that can be selected, etc.
  • the vehicle dispatching method of the present disclosure Before actually starting dispatching, the vehicle dispatching method of the present disclosure also needs to understand the average loading rate level of vehicles in historical dispatching based on business experience, understand the optimization space, and set the vehicle loading rate r accordingly.
  • step S220 a set of the number of possible vehicles is obtained based on the total amount of goods to be distributed, the vehicle loading rate and the vehicle maximum loading capacity.
  • the terminal or server obtains a set of possible vehicle numbers based on the total amount of goods to be distributed, the vehicle loading rate, and the vehicle maximum loading capacity.
  • the total amount of goods to be distributed is divided by the product of the first vehicle loading rate and the maximum loading capacity of the vehicle, and is rounded up to obtain the upper bound of the set of possible vehicle numbers;
  • the number of vehicles in use between the upper bound of the set of possible vehicle numbers and the lower bound of the set of possible vehicle numbers constitutes the set of possible vehicle numbers
  • the first vehicle loading rate is the vehicle loading rate minus a first ratio
  • the second vehicle loading rate is the vehicle loading rate plus a second ratio
  • the first ratio and the second The ratios are all greater than zero and less than 1.
  • obtaining the number set of possible vehicles to be used based on the total amount of goods to be distributed, the vehicle loading rate and the vehicle maximum loading capacity includes:
  • r is the vehicle loading rate
  • v is the maximum loading capacity of the vehicle
  • V is the total amount of goods to be distributed
  • V l is the upper bound of the number of vehicles
  • V u is the lower bound of the number of vehicles
  • the first ratio in V l is 0.1
  • V u The second ratio is also 0.1, but the disclosure is not limited thereto.
  • the first ratio and the second ratio can also have different values.
  • the approximate target level of the dispatch vehicle loading rate of the present disclosure is set to r.
  • V the total amount of goods to be delivered on that day (day)
  • v the maximum loading volume that each vehicle can load
  • v the maximum loading volume that each vehicle can load
  • the multiple vehicle models are sorted from high to low according to the historical dispatch frequency (for example, the average number of daily dispatches of each vehicle in the past three months) and are numbered 1, 2 respectively.
  • the historical dispatch frequency for example, the average number of daily dispatches of each vehicle in the past three months
  • the vehicle set corresponding to each sub-problem s can be determined as follows: with s Divide by f to get the quotient quo and the remainder rem, then the number of cars numbered i is
  • each vehicle model can be allocated to f i ⁇ quo vehicles until the remaining number of vehicles rem is less than f. At this time, priority will be given to vehicles that were more commonly used in the past (i.e., vehicles with larger fi ) until they are used up. All available credits, therefore at this stage each vehicle i should be allocated vehicles, and its upper bound is f i vehicles, and its lower bound is 0 vehicles.
  • the above method can determine the actual vehicle set K s corresponding to each sub-problem s.
  • step S230 for each possible number of vehicles in the set of possible vehicle numbers, a sub-optimal delivery route that minimizes the total delivery timeout under capacity constraints, temperature constraints and time constraints is determined.
  • the terminal or server determines the sub-optimal delivery route that minimizes the total delivery timeout under capacity constraints, temperature constraints and time constraints for each possible number of vehicles in the set of possible vehicle numbers.
  • the shortest total delivery timeout refers to the shortest length of time that exceeds the delivery time required by the customer after a possible number of vehicles is used to complete the delivery.
  • the shortest total delivery timeout is greater than or equal to zero.
  • the shortest total delivery timeout is equal to zero, which means that all The goods are delivered in advance or on time.
  • the present disclosure may use each value s in the set S of vehicle numbers to correspond to a sub-problem, that is, given the number of delivery vehicles s, find the sub-optimal vehicle that satisfies the capacity and temperature constraints. Delivery route such that the total delivery timeout is the shortest. Specifically, solve the following optimization subproblem:
  • K is the vehicle set
  • N represents the set of target delivery places for all orders
  • o represents the starting point, that is, the cold storage
  • d represents the end point of the delivery end (if there is no need to return to the unified end point, you can set The distance from d to all points is 0)
  • e i represents the agreed delivery start time point
  • f i represents the agreed delivery end time point
  • a i represents the time of arrival at delivery point i
  • w i represents the time from arrival
  • s i represents Unloading time
  • l i represents the order quantity at delivery point i
  • the constraints of the above optimization problem design include: (1)-(5) are the classic constraints of the vehicle routing problem, which respectively involve: (1) Each customer has and only one vehicle to provide service; (2) For any j ⁇ N , the car k that enters it must go out; (3) Each car k must start from o; (4) Each car k must finally return to d; (5) Eliminate sub-loops.
  • Constraint (6) is the identity of the arrival time, and (7) is the time window starting point constraint, which includes two situations: one is that you can only wait if you arrive before the agreed time, and the other is that you may need to wait in line to unload in the actual scenario; (8 ) is the truck capacity constraint; (9) is the temperature layer constraint unique to cold chain logistics; (10) is the integer constraint in integer programming.
  • determining the sub-optimal delivery route that minimizes the total delivery timeout under capacity constraints, temperature constraints and time constraints includes: The goods to be delivered are classified according to the required vehicle temperature requirements; Allocate each type of goods that need to be delivered to the corresponding temperature layer according to the vehicle loading rate and the maximum loading capacity of the vehicle; according to the possible delivery routes and the delivery time and delivery time required by the customer, obtain the total delivery time The sub-optimal delivery route with the shortest timeout.
  • the delivery route with the shortest delivery distance is selected as the sub-optimal delivery route.
  • w i is defined as max(q i ,e i -a i ), where the modeling of queuing time q i relies on the mining of past historical data.
  • each order shipping location can be classified into busy status Divide into different categories, use classical queuing theory to model each type of delivery location, assuming the arrival rate and service rate, so as to take the expected waiting time as qi;
  • the driving time t ij between two delivery target locations i, j can also be calculated based on historical experience, assuming the average driving speed of trucks u.
  • d ij represents the distance between i and j.
  • d ij can directly take the distance of the great spherical surface; while in urban distribution (same-city delivery) scenarios, Manhattan distance or other more accurate routing distances can be used.
  • the vehicle may have N temperature layers, where N is an integer greater than or equal to 2.
  • N is an integer greater than or equal to 2.
  • each vehicle k has and has only one certain temperature layer vt k , but in actual situations, a vehicle can achieve multiple refrigeration units and cargo boxes with partitions.
  • Temperature layer especially for long-distance transportation scenarios of large vehicles, customers are generally far away from each other, and customers may order different goods from multiple temperature layers at the same time.
  • using a multi-temperature layer dispatching solution for one vehicle can greatly reduce transportation costs. For example, a vehicle must deliver goods in the "refrigerated" temperature layer and goods in the "frozen” temperature layer.
  • the constraints (9) of the optimization subproblem can be adjusted accordingly.
  • the mathematical expression is: Car k has two transportable temperature layers. and Then constraint (9) is changed to
  • step S240 use the elbow method to determine the number of vehicles used for scheduling and the global optimal delivery based on the sub-optimal delivery route and the shortest total delivery timeout corresponding to each number of possible vehicles in the set of possible vehicle numbers. route.
  • the terminal or the server uses the elbow method to determine the number of vehicles used for scheduling and the global number of vehicles based on the sub-optimal delivery route and the shortest total delivery timeout corresponding to each number of possible vehicles in the set of possible vehicle numbers.
  • Optimal delivery route is the elbow method to determine the number of vehicles used for scheduling and the global number of vehicles based on the sub-optimal delivery route and the shortest total delivery timeout corresponding to each number of possible vehicles in the set of possible vehicle numbers.
  • the dispatching method of cold chain logistics vehicles of the present disclosure is based on the vehicle loading rate, the vehicle's maximum
  • the large loading volume and the total amount of goods to be distributed are obtained to obtain the number set of possible vehicles to be used, and the number of vehicles used for scheduling and the global maximum are obtained based on the set of number of possible vehicles to be used, and according to the capacity constraints, temperature constraints and time constraints of the vehicles.
  • Figure 3 shows a flow chart of using the elbow method to determine the number of vehicles used for scheduling and the global optimal delivery route according to an embodiment of the present disclosure.
  • using the elbow method to determine the number of vehicles used for scheduling and the global optimal delivery route includes:
  • step S241 the set of the number of possible vehicles is divided into a first set and a second set;
  • step S242 linear regression is performed respectively according to the number of vehicles that may be used in each of the first set and the second set and the corresponding shortest total delivery timeout to obtain the first prediction model and the second prediction model;
  • step S243 the number of vehicles used for scheduling and the global optimal delivery route are determined according to the first prediction model and the second prediction model.
  • the set of the number of possible vehicles is divided into a first set and a second set, and a linear regression is performed based on the number of possible vehicles and the corresponding shortest total delivery timeout in each of the first set and the second set.
  • Figure 4 shows another flowchart of using the elbow method to determine the number of vehicles used for scheduling and the global optimal delivery route according to an embodiment of the present disclosure.
  • determining the number of vehicles used for scheduling and the global optimal delivery route according to the first prediction model and the second prediction model includes:
  • step S2431 obtain the minimum root mean square difference of the first set according to the first prediction model
  • obtaining the minimum root mean square difference of the first set according to the first prediction model includes:
  • the first total delivery timeout corresponding to each number of possible vehicles in the first set, the predicted value of the first prediction model, and the number of elements of the number of possible vehicles in the first set are obtained.
  • the minimum root mean square difference of the set is obtained.
  • step S2432 obtain the minimum root mean square difference of the second set according to the second prediction model
  • obtaining the minimum root mean square difference of the second set according to the second prediction model includes:
  • the second set is obtained based on the shortest total delivery timeout corresponding to each number of possible vehicles in the second set, the predicted value of the second prediction model, and the number of elements of the number of possible vehicles in the second set.
  • the minimum root mean square difference of the set is obtained based on the shortest total delivery timeout corresponding to each number of possible vehicles in the second set, the predicted value of the second prediction model, and the number of elements of the number of possible vehicles in the second set.
  • step S2433 in the first set and the second set of the possible vehicle number sets, the sum of the minimum root mean square difference of the first set and the minimum root mean square difference of the second set is divided into combinations.
  • the smallest possible number of vehicles that divides the first set and the second set and the corresponding sub-optimal delivery route are used as the number of vehicles used for scheduling and the global optimal delivery route.
  • the minimum root mean square difference of the first set is obtained according to the first prediction model
  • the minimum root mean square difference of the second set is obtained according to the second prediction model
  • the first set and the second set of possible vehicle number sets are obtained.
  • the sum of the minimum root mean square difference of the first set and the minimum root mean square difference of the second set is the smallest
  • the number of possible vehicles used to divide the first set and the second set and the corresponding sub-optimal delivery route are as The number of vehicles used in scheduling and the global optimal distribution route realize the scheduling of cold chain logistics vehicles.
  • Figure 5 shows regression on both sides of the dividing point, and the dividing point with the smallest sum of root mean square differences is selected.
  • RMSE (V m ) RMSE 1 (V m ) + RMSE 2 (V m ), and traverse all the values of V m ⁇ V l +1 ,V l +2,...,V u -2 ⁇ , find the minimum value of RMSE (V m ) corresponding to RMSE * This is used as the number of dispatched vehicles, and the path planning solution solved by its corresponding sub-problem is used as the global optimal delivery route.
  • This disclosure proposes a vehicle scheduling method for logistics distribution scenarios, which is also applicable to collection scenarios.
  • the disclosed method balances the needs of the two dimensions of service quality and cost saving in terms of optimization objectives, and in terms of constraints, it not only considers the traditional truck capacity limitations, but also considers the unique temperature constraints in the cold chain scenario.
  • FIG 6 schematically shows a block diagram of a dispatching device for cold chain logistics vehicles according to an embodiment of the present disclosure.
  • the cold chain logistics vehicle dispatching device 600 provided by the embodiment of the present disclosure can be set up on the server side, or partly set up on the terminal and partly set up on the server side. For example, it can be set up on the server 105 in Figure 1, but the present disclosure It is not limited to this.
  • the dispatching device 600 for cold chain logistics vehicles may include a first acquisition module 610 , a second acquisition module 620 , a first determination module 630 and a second determination module 640 .
  • the first acquisition module 610 is configured to acquire the total amount of goods to be delivered, the vehicle loading rate and the maximum loading capacity of the vehicle;
  • the second acquisition module 620 is configured to acquire a set of the number of possible vehicles to be used based on the total amount of goods to be distributed, the vehicle loading rate and the vehicle maximum loading capacity;
  • the first determination module 630 is configured to determine, for each possible number of vehicles in the set of possible vehicle numbers, a sub-optimal delivery route that minimizes the total delivery timeout under capacity constraints, temperature constraints and time constraints;
  • the second determination module 640 is configured to use the elbow method to determine the number of vehicles used for scheduling and the global optimal number of vehicles according to the sub-optimal delivery route and the shortest total delivery timeout corresponding to each number of possible vehicles in the set of possible vehicle numbers. Optimal delivery routes.
  • the above-mentioned dispatching device 600 of cold chain logistics vehicles obtains a set of the number of possible vehicles to be used based on the vehicle loading rate, the maximum loading capacity of the vehicle and the total amount of goods to be distributed. Based on the set of the number of possible vehicles to be used, based on the capacity Constraints, temperature constraints and time constraints can obtain the number of vehicles used in scheduling and the global optimal distribution route, and can realize the scheduling of cold chain logistics vehicles. Spend.
  • the above-mentioned cold chain logistics vehicle dispatching device 600 can be used to implement the cold chain logistics vehicle dispatching method described in the embodiment of FIGS. 2 to 4 .
  • FIG. 7 schematically shows a block diagram of a dispatching device 700 for a cold chain logistics vehicle according to another embodiment of the present disclosure.
  • the dispatching device 700 of the cold chain logistics vehicle also includes Display module 710.
  • the display module 710 displays the number of vehicles used in scheduling and the global optimal delivery route to the customer or staff.
  • the display module 710 can display the number of vehicles used for scheduling and the global optimal delivery route.
  • FIG. 8 schematically shows a block diagram of a dispatching device 800 for a cold chain logistics vehicle according to another embodiment of the present disclosure.
  • the dispatching device 800 of the cold chain logistics vehicle also includes a storage Module 810.
  • the storage module 810 is used to store data during the dispatching process of cold chain logistics vehicles to facilitate subsequent call and reference.
  • the first acquisition module 610, the second acquisition module 620, the first determination module 630 and the second determination module 640, the display module 710 and the storage module 810 can be combined and implemented in one module, or any one of the modules can be is split into multiple modules. Alternatively, at least part of the functionality of one or more of these modules may be combined with at least part of the functionality of other modules and implemented in one module. According to an embodiment of the present disclosure, at least one of the first acquisition module 610 , the second acquisition module 620 , the first and second determination modules 630 and 640 , the display module 710 and the storage module 810 may be at least partially implemented as a hardware circuit.
  • At least one of the first acquisition module 610, the second acquisition module 620, the first determination module 630 and the second determination module 640, the display module 710 and the storage module 810 may be at least partially implemented as a computer program module. When run by a computer, the functions of the corresponding modules can be performed.
  • each module of the cold chain logistics vehicle dispatching device of the exemplary embodiment of the present disclosure can be used to implement the steps of the exemplary embodiment of the cold chain logistics vehicle dispatching method described above in FIGS. 2 to 4 , for the implementation of the cold chain logistics vehicle dispatching device of the present disclosure
  • the cold chain logistics vehicle dispatching device of the present disclosure For details not disclosed in the method, please refer to the implementation of the cold chain logistics vehicle dispatching method mentioned above in this disclosure.
  • each module, unit and sub-unit in the dispatching device for cold chain logistics vehicles can refer to the contents of the dispatching method for cold chain logistics vehicles mentioned above, and will not be described again here.
  • FIG. 9 shows a schematic structural diagram of a computer system suitable for implementing an electronic device according to an embodiment of the present disclosure.
  • the computer system 900 includes a central processing unit (CPU, Central Processing Unit) 901, which can be loaded into a random accessory according to a program stored in a read-only memory (ROM, Read-Only Memory) 902 or from a storage part 908. Access the program in the memory (RAM, Random Access Memory) 903 to perform various appropriate actions and processes. In RAM 903, various programs and data required for system operation are also stored.
  • CPU 901, ROM 902 and RAM 903 are connected to each other through bus 904.
  • An input/output (I/O) interface 905 is also connected to bus 904.
  • the following components are connected to the I/O interface 905: an input part 906 including a keyboard, a mouse, etc.; an output part 907 including a cathode ray tube (CRT, Cathode Ray Tube), a liquid crystal display (LCD, Liquid Crystal Display), etc., and a speaker, etc. ; a storage part 908 including a hard disk, etc.; and a communication part 909 including a network interface card such as a LAN (Local Area Network) card, a modem, etc.
  • the communication section 909 performs communication processing via a network such as the Internet.
  • Driver 910 is also connected to I/O interface 905 as needed.
  • Removable media 911 such as magnetic disks, optical disks, magneto-optical disks, semiconductor memories, etc., are installed on the drive 910 as needed, so that a computer program read therefrom is installed into the storage portion 908 as needed.
  • embodiments of the present disclosure include a computer program product including a computer program carried on a computer-readable storage medium, the computer program containing program code for performing the method illustrated in the flowchart.
  • the computer program may be downloaded and installed from the network via communication portion 909 and/or installed from removable media 911 .
  • CPU central processing unit
  • the computer-readable storage medium shown in the present disclosure may be a computer-readable signal medium or a computer-readable storage medium, or any combination of the above two.
  • the computer-readable storage medium may be, for example, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus or device, or any combination thereof.
  • Computer readable storage media may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard drive, random access memory (RAM), read only memory (ROM), removable Programmable read-only memory (EPROM (Erasable Programmable Read Only Memory, Erasable Programmable Read Only Memory) or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or the above any suitable combination.
  • a computer-readable storage medium may be any tangible medium that contains or stores a program for use by or in connection with an instruction execution system, apparatus, or device.
  • a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code therein. Such propagated data signals may take many forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above.
  • a computer-readable signal medium may also be any computer-readable storage medium other than a computer-readable storage medium that may be sent, propagated, or transmitted for use by or in connection with an instruction execution system, apparatus, or device program of.
  • Program codes contained on computer-readable storage media can be transmitted using any appropriate medium, including but not limited to: wireless, wires, optical cables, RF (Radio Frequency, radio frequency), etc., or any suitable combination of the above.
  • each block in the flowchart or block diagrams may represent a module, segment, or portion of code that contains one or more logic functions that implement the specified executable instructions.
  • the functionality selected in the box is also May occur in a different order than boxed in the figure. For example, two blocks shown one after another may actually execute substantially in parallel, or they may sometimes execute in the reverse order, depending on the functionality involved.
  • each block in the block diagram or flowchart illustration, and combinations of blocks in the block diagram or flowchart illustration can be implemented by special purpose hardware-based systems that perform the specified functions or operations, or may be implemented by special purpose hardware-based systems that perform the specified functions or operations. Achieved by a combination of specialized hardware and computer instructions.
  • modules and/or units and/or subunits described in the embodiments of the present disclosure can be implemented in software or hardware.
  • the described modules and/or units and/or subunits It can also be set in the processor.
  • the names of these modules and/or units and/or subunits do not constitute a limitation on the modules and/or units and/or subunits themselves under certain circumstances.
  • the present application also provides a computer-readable storage medium.
  • the computer-readable storage medium may be included in the electronic device described in the above embodiments; it may also exist independently without being assembled into the electronic device. in electronic equipment.
  • the computer-readable storage medium carries one or more programs. When the one or more programs are executed by an electronic device, the electronic device implements the method described in the following embodiments. For example, the electronic device can implement the steps shown in Figures 2 to 4.
  • machine learning methods for example, machine learning methods, deep learning methods, etc. can be used to schedule cold chain logistics vehicles. Different methods have different applicable scopes.
  • modules, units and sub-units of the device for action execution are mentioned in the detailed description above, this division is not mandatory. Indeed, according to embodiments of the present disclosure, the features and functions of two or more modules, units and sub-units described above may be embodied in one module, unit or sub-unit. Conversely, the features and functions of one module, unit and sub-unit described above may be further divided into being embodied by a plurality of modules, units and sub-units.
  • the example embodiments described here can be implemented by software, or can be implemented by software combined with necessary hardware. Therefore, the technical solution according to the embodiment of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, U disk, mobile hard disk, etc.) or on the network , including several instructions to cause a computing device (which may be a personal computer, a server, a touch terminal, a network device, etc.) to execute the method according to the embodiments of the present disclosure.
  • a computing device which may be a personal computer, a server, a touch terminal, a network device, etc.

Landscapes

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Human Resources & Organizations (AREA)
  • Economics (AREA)
  • Strategic Management (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Quality & Reliability (AREA)
  • Operations Research (AREA)
  • Marketing (AREA)
  • Development Economics (AREA)
  • Tourism & Hospitality (AREA)
  • Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Game Theory and Decision Science (AREA)
  • Educational Administration (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

本公开的实施方式提供了冷链物流车辆的调度方法及装置、计算机可读存储介质和电子设备，属于计算机和通信技术领域。方法包括：获取需配送货物总量、车辆装载率和车辆最大装货量；根据需配送货物总量、车辆装载率和车辆最大装货量获取可能使用车辆数量集合；对于可能使用车辆数量集合中的每一个可能使用车辆数量，确定在容量约束、温层约束和时间约束下使得配送总超时最短的子最优配送路线；根据可能使用车辆数量集合中的每一个可能使用车辆数量对应的子最优配送路线和最短配送总超时，使用手肘法确定调度所使用的车辆数量和全局最优配送路线。本公开的方法可以实现冷链物流车辆的调度。 (图2)

Description

冷链物流车辆的调度方法及相关设备
相关申请的交叉引用
本公开要求于2022年05月24日提交的申请号为202210571006.9、名称为“冷链物流车辆的调度方法及相关设备”的中国专利申请的优先权，该中国专利申请的全部内容通过引用全部并入本文。
技术领域
本公开涉及计算机和通信技术领域，具体而言，涉及冷链物流车辆的调度方法及装置、计算机可读存储介质和电子设备。
背景技术
冷链物流是指物品在生产、仓储或运输和销售过程中，一直到消费前的各个环节中始终处于产品规定的最佳低温环境下，才能保证食品质量，减少食品损耗的一项系统工程。冷链物流的货车揽货、配送调度优化具有巨大的市场价值和研究价值。冷链场景下的车货匹配和调度等问题具有一定的特殊性，例如，冷链的调度需要专门的调度中心，而冷链的运输也需要专门的车辆，同时，由于冷链产品需要防止化冻，对时效的要求比较高。这些特殊性决定了冷链场景中的调度等问题不能够直接使用通用场景下的调度方案。
需要说明的是，在上述背景技术部分公开的信息仅用于加强对本公开的背景的理解，因此可以包括不构成对本领域普通技术人员已知的现有技术的信息。
发明内容
本公开实施例提供冷链物流车辆的调度方法及装置、计算机可读存储介质和电子设备，能够实现冷链物流车辆的高效调度。
本公开的其他特性和优点将通过下面的详细描述变得显然，或部分地通过本公开的实践而习得。
根据本公开的一个方面，提供一种冷链物流车辆的调度方法，包括：
获取需配送货物总量、车辆装载率和车辆最大装货量；根据所述需配送货物总量、所述车辆装载率和所述车辆最大装货量获取可能使用车辆数量集合；对于所述可能使用车辆数量集合中的每一个可能使用车辆数量，确定在容量约束、温层约束和时间约束下使得配送总超时最短的子最优配送路线；根据所述可能使用车辆数量集合中的每一个可能使用车辆数量对应的子最优 配送路线和最短配送总超时，使用手肘法确定调度所使用的车辆数量和全局最优配送路线。
在一个实施例中，根据所述需配送货物总量、所述车辆装载率和所述车辆最大装货量获取可能使用车辆数量集合包括：将所述需配送货物总量除以第一车辆装载率和所述车辆最大装货量的乘积，并向上取整以获得所述可能使用车辆数量集合的上界；将所述需配送货物总量除以第二车辆装载率和所述车辆最大装货量的乘积，并向上取整以获得所述可能使用车辆数量集合的下界；将所述可能使用车辆数量集合的上界和所述可能使用车辆数量集合的下界之间的使用车辆数量组成所述可能使用车辆数量集合；其中，所述第一车辆装载率是所述车辆装载率减去第一比率，所述第二车辆装载率是所述车辆装载率加上第二比率，所述第一比率和所述第二比率均大于零且小于1。
在一个实施例中，根据所述可能使用车辆数量集合中的每一个可能使用车辆数量对应的子最优配送路线和最短配送总超时，使用手肘法确定调度所使用的车辆数量和全局最优配送路线，包括：将所述可能使用车辆数量集合分为第一集合和第二集合；根据所述第一集合和所述第二集合中每一个可能使用车辆数量和对应的最短配送总超时分别进行线性回归以获得第一预测模型和第二预测模型；根据所述第一预测模型和所述第二预测模型确定调度所使用的车辆数量和全局最优配送路线。
在一个实施例中，根据所述第一预测模型和所述第二预测模型确定调度所使用的车辆数量和全局最优配送路线，包括：根据所述第一预测模型获取所述第一集合的最小方均根差；根据所述第二预测模型获取所述第二集合的最小方均根差；以所述可能使用车辆数量集合的所述第一集合和所述第二集合划分组合中，所述第一集合的最小方均根差和所述第二集合的最小方均根差之和最小的、划分所述第一集合和所述第二集合的可能使用车辆数量和对应的子最优配送路线作为调度所使用的车辆数量和全局最优配送路线。
在一个实施例中，根据所述第一预测模型获取所述第一集合的最小方均根差，包括：根据所述第一集合中每一个可能使用车辆数量所对应的最短配送总超时、所述第一预测模型的预测值和所述第一集合中可能使用车辆数量的元素个数获取所述第一集合的最小方均根差。
在一个实施例中，根据所述第二预测模型获取所述第二集合的最小方均根差，包括：根据所述第二集合中每一个可能使用车辆数量所对应的最短配送总超时、所述第二预测模型的预测值和所述第二集合中可能使用车辆数量的元素个数获取所述第二集合的最小方均根差。
在一个实施例中，对于所述可能使用车辆数量集合中的每一个可能使用车辆数量，确定在容量约束、温层约束和时间约束下使得配送总超时最短的子最优配送路线，包括：将需配送货物按照需要的车辆温层要求进行分类；将分类完成的每类需配送货物根据车辆装载率和车辆最大装货量，分别分配给对应温层的车辆；按照可能的配送路线和客户要求的发货时间、送达时间，获取使得配送总超时最短的子最优配送路线。
在一个实施例中，按照可能的配送路线和客户要求的发货时间、送达时间，获取使得配送总超时最短的子最优配送路线，包括：在一个可能使用车辆数量的最短配送总超时等于零时，选择路程最短的配送路线为子最优配送路线。
在一个实施例中，车辆的温层为N个，其中N是大于等于2的整数。
在一个实施例中，获取需配送货物总量、车辆装载率和车辆最大装货量，包括：在车辆的车型不一致时，获取所述需配送货物总量、所述车辆装载率和加权车辆最大装货量。
根据本公开的一个方面，提供一种冷链物流车辆的调度装置，包括：第一获取模块，配置为获取需配送货物总量、车辆装载率和车辆最大装货量；第二获取模块，配置为根据所述需配送货物总量、所述车辆装载率和所述车辆最大装货量获取可能使用车辆数量集合；第一确定模块，对于所述可能使用车辆数量集合中的每一个可能使用车辆数量，确定在容量约束、温层约束和时间约束下使得配送总超时最短的子最优配送路线；第二确定模块，配置为根据所述可能使用车辆数量集合中的每一个可能使用车辆数量对应的子最优配送路线和最短配送总超时，使用手肘法确定调度所使用的车辆数量和全局最优配送路线。
根据本公开的一个方面，提供一种电子设备，包括：一个或多个处理器；存储装置，配置为存储一个或多个程序，当所述一个或多个程序被所述一个或多个处理器执行时，使得所述一个或多个处理器实现如上实施例中任一项 所述的方法。
根据本公开的一个方面，提供一种计算机可读存储介质，所述计算机可读存储介质存储有计算机程序，所述计算机程序被处理器执行时实现如上实施例中任一项所述的方法。
本公开的冷链物流车辆的调度方法，根据所述车辆装载率、所述车辆最大装货量和所述需配送货物总量获取可能使用车辆数量集合，基于所述可能使用车辆数量集合、根据容量约束、温层约束和时间约束获取调度所使用的车辆数量和全局最优配送路线。
应当理解的是，以上的一般描述和后文的细节描述仅是示例性和解释性的，并不能限制本公开。
附图说明
以下附图描述了本公开的某些说明性实施方式，其中相同的附图标记表示相同的元件。这些描述的实施方式将是本公开的示例性实施方式，而不是以任何方式进行限制。
图1示出了可以应用本公开实施方式的冷链物流车辆的调度方法的示例性系统架构的示意图；
图2示意性示出了根据本公开的一实施方式的冷链物流车辆的调度方法的流程图；
图3示出了本公开一个实施例的一种使用手肘法确定调度所使用的车辆数量和全局最优配送路线的流程图；
图4示出了本公开一个实施例的另一种使用手肘法确定调度所使用的车辆数量和全局最优配送路线的流程图；
图5示出了对分界点两侧分别回归，选出方均根差之和最小的分界点；
图6示意性示出了根据本公开的一实施方式的冷链物流车辆的调度装置的框图；
图7示意性示出了根据本公开的另一个实施方式的冷链物流车辆的调度装置的方框图；
图8示意性示出了根据本公开的另一个实施方式的冷链物流车辆的调度装置的方框图；以及
图9示出了适于用来实现本公开实施方式的电子设备的计算机系统的结构示意图。
具体实施方式
现在将参考附图更全面地描述示例实施方式。然而，示例实施方式能够以多种形式实施，且不应被理解为限于在此阐述的范例；相反，提供这些实施方式使得本公开将更加全面和完整，并将示例实施方式的构思全面地传达给本领域的技术人员。
此外，所描述的特征、结构或特性可以以任何合适的方式结合在一个或更多实施方式中。在下面的描述中，提供许多具体细节从而给出对本公开的实施方式的充分理解。然而，本领域技术人员将意识到，可以实践本公开的技术方案而没有特定细节中的一个或更多，或者可以采用其它的方法、组元、装置、步骤等。在其它情况下，不详细示出或描述公知方法、装置、实现或者操作以避免模糊本公开的各方面。
附图中所示的方框图仅仅是功能实体，不一定必须与物理上独立的实体相对应。即，可以采用软件形式来实现这些功能实体，或在一个或多个硬件模块或集成电路中实现这些功能实体，或在不同网络和/或处理器装置和/或微控制器装置中实现这些功能实体。
附图中所示的流程图仅是示例性说明，不是必须包括所有的内容和操作/步骤，也不是必须按所描述的顺序执行。例如，有的操作/步骤还可以分解，而有的操作/步骤可以合并或部分合并，因此实际执行的顺序有可能根据实际情况改变。
下面首先对本公开的一些术语进行说明：
需配送货物总量，是调度周期内待调度的总运单所包括的需配送货物总质量或总体积。
车辆装载率，是车辆实际装载的货物量与理论最大装货量的比值。
车辆最大装货量，是车辆能够装载的最大货物总质量或总体积。
容量约束，是指车辆的实际转载的货物量要小于等于车辆能够装载的最大货物总质量或总体积。
温层约束，是指车辆的温层(冷藏、冷冻或常温)要与货物的运送要求匹配。
时间约束，是指订单中客户要求的发货时间与送达时间等。
配送总超时，是指所有车辆完成订单的配送后，超出客户要求的送达时 间的总超时时间。
配送路线，是指车辆配送过程所行使经过的路线。
可能使用车辆数量，是指在本公开的确定调度所使用的车辆数量和全局最优配送路线中，所用于计算的可能使用车辆的数量。可能使用车辆数量集合，即由所有可能使用车辆数量组成的集合。
图1示出了可以应用本公开实施方式的冷链物流车辆的调度方法的示例性系统架构100的示意图。
如图1所示，系统架构100可以包括终端101、102、103中的一种或多种，网络104和服务器105。网络104是用以在终端101、102、103和服务器105之间提供通信链路的介质。网络104可以包括各种连接类型，例如有线、无线通信链路或者光纤电缆等等。
应该理解，图1中的终端、网络和服务器的数目仅仅是示意性的。根据实现需要，可以具有任意数目的终端、网络和服务器。比如服务器105可以是多个服务器组成的服务器集群等。
工作人员可以使用终端101、102、103通过网络104与服务器105交互，以接收或发送消息等。终端101、102、103可以是具有显示屏的各种电子设备，包括但不限于智能手机、平板电脑、便携式计算机和台式计算机等等。
服务器105可以是提供各种服务的服务器。例如工作人员通过终端103(也可以是终端101或102)向服务器105发送冷链物流车辆的调度的指令时，服务器105可以获取需配送货物总量、车辆装载率和车辆最大装货量；根据所述需配送货物总量、所述车辆装载率和所述车辆最大装货量获取可能使用车辆数量集合；对于所述可能使用车辆数量集合中的每一个可能使用车辆数量，确定在容量约束、温层约束和时间约束下使得配送总超时最短的子最优配送路线；根据所述可能使用车辆数量集合中的每一个可能使用车辆数量对应的子最优配送路线和最短配送总超时，使用手肘法确定调度所使用的车辆数量和全局最优配送路线。服务器105可以将调度所使用的车辆数量和全局最优配送路线显示于终端103或其他终端，进而工作人员或其他人员(例如，用户)可以基于终端上显示的内容查看调度所使用的车辆数量和全局最优配送路线。
物流车辆调度时，需要同时考虑减少调度车辆的数量和减少配送延迟情 况。虽然目前存在多目标优化的技术可以在一些场景下解决类似的问题，但实现起来较为复杂。同时，多目标优化一般会输出多组解，但实际运用时只能从中选取一个，但选取的标准较难定义。本公开每次固定调度可用的车辆的数量，并求解能够最小化配送延迟相关的惩罚的调度方案，通过不断增加给定调度车数量，来在每个子问题中获得不同“成本支出-最优效益”组合，最后再通过“手肘法”自动筛选出所有组合中最优调度方案。
图2示意性示出了根据本公开的一实施方式的冷链物流车辆的调度方法的流程图。本公开实施方式的方法步骤可以由终端或服务器执行，或由终端和服务器交互执行，或由服务器集群执行，例如，可以由上述图1中的服务器105执行，但本公开并不限定于此。
在步骤S210中，获取需配送货物总量、车辆装载率和车辆最大装货量。
在该步骤中，终端或服务器获取车辆装载率、车辆最大装货量和需配送货物总量。
在一个实施例中，获取需配送货物总量、车辆装载率和车辆最大装货量包括：
在车辆的车型不一致时，获取所述需配送货物总量、所述车辆装载率和加权车辆最大装货量。
在一个实施例中，在实际的使用过程中，车辆调度时首先要对数据进行收集，收集的数据包括但不限于：需要调度的运单的单号，运单的目的地，运单上货物的总体积，运单上货物的总重量，运单要求的开始配送时间，运单要求的最晚配送时间，可以选择的车型等。通过以上信息的收集可以获取需配送货物总量等信息。
在实际开始调度之前，本公开的车辆调度方法还需要根据业务经验了解到历史调度中车辆的平均装载率水平，了解优化空间并据此设定车辆装载率r。
当调度规划开始时，该调度周期内待调度的总运单不再发生变化，因此周期内需配送货物总量(质量或体积)V是确定的。但当货车不止有一种车型，即不同车k有不同最大装货量vk时，车辆数量上界Vl和车辆数量下界Vu的计算变得复杂。本公开按照各类车型的比例算出加权车辆最大装货量这里的“权”应理解为由历史数据所得的大致比例，例如假设过去三个月两种车型的日均调度次数分别为39次和11次，其最大装货量分别为v1和v2，则按照 4:1对两种车型加权平均，即加权车辆最大装货量
在步骤S220中，根据所述需配送货物总量、所述车辆装载率和所述车辆最大装货量获取可能使用车辆数量集合。
在该步骤中，终端或服务器根据所述需配送货物总量、所述车辆装载率和所述车辆最大装货量获取可能使用车辆数量集合。
在一个实施例中，将所述需配送货物总量除以第一车辆装载率和所述车辆最大装货量的乘积，并向上取整以获得所述可能使用车辆数量集合的上界；
将所述需配送货物总量除以第二车辆装载率和所述车辆最大装货量的乘积，并向上取整以获得所述可能使用车辆数量集合的下界；
将所述可能使用车辆数量集合的上界和所述可能使用车辆数量集合的下界之间的使用车辆数量组成所述可能使用车辆数量集合；
其中，所述第一车辆装载率是所述车辆装载率减去第一比率，所述第二车辆装载率是所述车辆装载率加上第二比率，所述第一比率和所述第二比率均大于零且小于1。
例如，根据所述需配送货物总量、所述车辆装载率和所述车辆最大装货量获取可能使用车辆数量集合包括：
根据以下公式获得车辆数量上界(这一符号表示对x向上取整)：
根据以下公式获得车辆数量下界：
其中，r是车辆装载率，v是车辆最大装货量，V是需配送货物总量，Vl是车辆数量上界，Vu是车辆数量下界，Vl中第一比率是0.1，Vu中第二比率也是0.1，但是本公开不以此为限，第一比率和第二比率也可以不同的数值。
在一个实施例中，设定本公开调度车辆装载率大致目标水平为r。同时已知当次(日)需配送货物总量为V，假设每辆车可装载最大装货量为v，则算出使用车辆数量下界使用车辆数量上界其代表平均装载率为第二车辆装载率(r+0.1)与第一车辆装载率(r-0.1)时分别对 应的所需车辆数。得到可能使用车辆数量的集合S＝{s|Vl≤s≤Vu,s∈N+}，即Vl与Vu之间的所有整数都是可能使用的车辆数。
在一个实施例中，车型有多种，例如m种时，将多种车型按历史调度频率(例如过去三个月每种车的日均调度次数)从高到低排序分别编号为1,2,..,m，设各类车历史调度频率比为f1:f2:...:fm，令对于本公开的不同给定车辆数的子问题集合S＝{s|Vl≤s≤Vu,s∈N+}，而每一个子问题s所对应的车辆集合确定方式可以如下：以s除以f得到商quo和余数rem，则编号为i的车数量为
本公开上述模式下，每种车型能分到fi·quo辆，直到剩下的车辆数rem小于f，这时优先分配过去更常用的车(即fi更大的车)，直到用完所有可分配的额度，因此在这一阶段每种车i应分配辆，且其上界为fi辆，下界为0辆。以上方法可以确定每个子问题s对应的实际车辆集合Ks。
在步骤S230中，对于所述可能使用车辆数量集合中的每一个可能使用车辆数量，确定在容量约束、温层约束和时间约束下使得配送总超时最短的子最优配送路线。
在该步骤中，终端或服务器对于所述可能使用车辆数量集合中的每一个可能使用车辆数量，确定在容量约束、温层约束和时间约束下使得配送总超时最短的子最优配送路线。
在一个实施例中，所述最短配送总超时是指一个可能使用车辆数量完成配送后，超出客户要求送达时间的最短时间长度，所述最短配送总超时大于等于零，最短配送总超时等于零表示所有货物提前或者按时送达。
例如，在一个实施例中，本公开可能使用车辆数量的集合S中每一个取值s对应一个子问题，即给定送货车辆数目s，求出满足容量、温层约束的子最优车辆配送路线，使得配送总超时最短。具体来说，求解如下优化子问题：

上述优化问题设计的变量包括：K是车辆集合；N表示所有订单的目标送货地集合；o表示出发地，即冷库；d表示送货结束的终点(若不需要回到统一终点，可以设d到所有点距离为0)；表示货车k经过路径(i,j)的指示变量；ei表示约定送货开始时间点；fi表示约定送货结束时间点；ai表示到达送货点i的时间；wi表示从到达送货点i直至可以开始卸货的时间，既包括排队等待时间qi，也包括先于约定收货时间到达的情况，即wi＝max(qi,ei-ai)；si表示卸货时间；tij行驶路径(i,j)所需时间；li表示送货点i处订单量；Qk表示货车k的最大容量；gti表示订单i货物的温层；vtk表示货车k的温层。
上述优化问题设计的约束包括：(1)-(5)是车辆路由问题的经典约束，分别涉及到：(1)每位顾客有且仅有一辆车提供服务；(2)对于任何j∈N，进入它的车k都要出去；(3)每辆车k都要从o出发；(4)每辆车k都要最后回到d；(5)消除子回路。约束(6)是到达时间的恒等式，(7)则是时间窗起始点约束，包含两种情形：一是先于约定时间到达只能等待，二是实际场景中卸货可能需要排队等待；(8)是货车容量约束；(9)是冷链物流中特有的温层约束；(10)是整数规划中的整数约束。
上述优化子问题可以通过各类免费或者商业优化求解器求解，也可以自行编写程序，用各类元启发式方法获得优质解，因此对每一个s对应的子问题可以得出一个近似最短配送总超时t(s)。
在一个实施例中，对于所述可能使用车辆数量集合中的每一个可能使用车辆数量，确定在容量约束、温层约束和时间约束下使得配送总超时最短的子最优配送路线，包括：将需配送货物按照需要的车辆温层要求进行分类； 将分类完成的每类需配送货物根据车辆装载率和车辆最大装货量，分别分配给对应温层的车辆；按照可能的配送路线和客户要求的发货时间、送达时间，获取使得配送总超时最短的子最优配送路线。
在一个实施例中，在一个可能使用车辆数量的最短配送总超时等于零时(即，提前或者按时送达)，选择配送路程最短的配送路线为子最优配送路线。
在一个实施例中，wi定义为max(qi,ei-ai)，其中对于排队时间qi的建模依赖于过往历史数据的挖掘，比如可以把每个订单运送地点按忙碌状态分为不同类别，对每个类型的运送地点用经典排队论建模，假设到达速率和服务速率，从而取期望等待时间作为qi；卸货时间si可以根据业务人员经验，假设一个平均卸货速度vd，计算si＝li/vd来求得；两送货目标地点i,j之间的行驶时间tij同样可以根据历史经验，假设货车的平均行驶速度u，计算来求得，其中dij表示i,j之间的距离，在不同物流场景中可以有不同的计算方式，比如在城际尤其是跨省运输中，dij可以直接取大圆球面距离；而在城配(同城配送)场景中，则可以用曼哈顿距离或者其他更精确的路由距离。
在一个实施例中，车辆的温层可以为N个，其中N是大于等于2的整数。在本公开中，假设的是每一辆车k有且只有一种确定的温层vtk，但实际情况中，一辆车可以通过多制冷机、货箱加隔板的方式实现一车多温层，尤其对于大型车辆远程运送的场景，客户之间一般距离较远，且客户可能同时订购多个温层的不同货物，此时采用一车多温层的调度方案能够大大降低运输成本。比如一辆车既要配送“冷藏”温层的货物，也要配送“冷冻”温层的货物。这时可对应调整优化子问题的约束(9)，数学化的表述为：车k有两个可运送温层和则约束(9)改为
在步骤S240中，根据所述可能使用车辆数量集合中的每一个可能使用车辆数量对应的子最优配送路线和最短配送总超时，使用手肘法确定调度所使用的车辆数量和全局最优配送路线。
在该步骤中，终端或服务器根据所述可能使用车辆数量集合中的每一个可能使用车辆数量对应的子最优配送路线和最短配送总超时，使用手肘法确定调度所使用的车辆数量和全局最优配送路线。
本公开的冷链物流车辆的调度方法，根据所述车辆装载率、所述车辆最 大装货量和所述需配送货物总量获取可能使用车辆数量集合，基于所述可能使用车辆数量集合、根据车辆的容量约束、温层约束和时间约束获取调度所使用的车辆数量和全局最优配送路线。
图3示出了本公开一个实施例的一种使用手肘法确定调度所使用的车辆数量和全局最优配送路线的流程图。
参考图3，使用手肘法确定调度所使用的车辆数量和全局最优配送路线包括：
在步骤S241中，将所述可能使用车辆数量集合分为第一集合和第二集合；
在步骤S242中，根据所述第一集合和所述第二集合中每一个可能使用车辆数量和对应的最短配送总超时分别进行线性回归以获得第一预测模型和第二预测模型；
在步骤S243中，根据所述第一预测模型和所述第二预测模型确定调度所使用的车辆数量和全局最优配送路线。
图3的实施例中，将可能使用车辆数量集合分为第一集合和第二集合，根据第一集合和第二集合中每一个可能使用车辆数量和对应的最短配送总超时分别进行线性回归以获得第一预测模型和第二预测模型，然后根据第一预测模型和第二预测模型确定调度所使用的车辆数量和全局最优配送路线，可以实现冷链物流车辆的调度。
图4示出了本公开一个实施例的另一种使用手肘法确定调度所使用的车辆数量和全局最优配送路线的流程图。
参考图4，根据所述第一预测模型和所述第二预测模型确定调度所使用的车辆数量和全局最优配送路线，包括：
在步骤S2431中，根据所述第一预测模型获取所述第一集合的最小方均根差；
在一个实施例中，根据所述第一预测模型获取所述第一集合的最小方均根差，包括：
根据所述第一集合中每一个可能使用车辆数量所对应的最短配送总超时、所述第一预测模型的预测值和所述第一集合中可能使用车辆数量的元素个数获取所述第一集合的最小方均根差。
在步骤S2432中，根据所述第二预测模型获取所述第二集合的最小方均根差；
在一个实施例中，根据所述第二预测模型获取所述第二集合的最小方均根差，包括：
根据所述第二集合中每一个可能使用车辆数量所对应的最短配送总超时、所述第二预测模型的预测值和所述第二集合中可能使用车辆数量的元素个数获取所述第二集合的最小方均根差。
在步骤S2433中，以所述可能使用车辆数量集合的所述第一集合和所述第二集合划分组合中，所述第一集合的最小方均根差和所述第二集合的最小方均根差之和最小的、划分所述第一集合和所述第二集合的可能使用车辆数量和对应的子最优配送路线作为调度所使用的车辆数量和全局最优配送路线。
图4的实施例中，根据第一预测模型获取第一集合的最小方均根差，根据第二预测模型获取第二集合的最小方均根差，然后以可能使用车辆数量集合的第一集合和第二集合划分组合中，第一集合的最小方均根差和第二集合的最小方均根差之和最小的、划分所述第一集合和所述第二集合的可能使用车辆数量和对应的子最优配送路线作为调度所使用的车辆数量和全局最优配送路线，实现了冷链物流车辆的调度。
例如，在一个实施例中，当求得每个可能使用车辆数量所对应的最短配送总超时t(s)后，将可能使用车辆数量集合S分解为第一集合S1＝{Vl,Vl+1,Vl+2,...,Vm}(其中Vm可取{Vl+1,Vl+2,...,Vu-1}中的任何数)和第二集合S2＝{Vm+1,Vm+2,...,Vu-1,Vu}，故可知S＝S1∪S2。
对第一集合S1对应的点集合{(s,t(s))|s∈S1}进行线性回归，得到第一预测模型p1(s)，并求出最小方均根差其中p1(s)是上述线性回归拟合出的第一预测模型的预测值，|S1|是S1中元素个数；
类似的，求出第二集合S2对应的点集合{(s,t(s))|s∈S2}进行线性回归，得到第一预测模型p2(s)，求出最小方均根差其中 p2(s)是上述线性回归拟合出的第二预测模型的预测值，|S2|是S2中元素个数。
图5示出了对分界点两侧分别回归，选出方均根差之和最小的分界点。
参考图5，对于每一个Vm，能求出两部分方均根差之和RMSE(Vm)＝RMSE1(Vm)+RMSE2(Vm)，遍历Vm所有取值{Vl+1,Vl+2,...,Vu-2}，求出RMSE(Vm)最小的值RMSE*所对应的以此作为调度车辆数目，并以其对应的子问题解出的路径规划方案作为全局最优配送路线。
本公开提出一种物流配送场景的车辆调度方法，对于揽收场景也适用。本公开方法在优化目标方面平衡了服务质量与成本节省两个维度的需求，而在约束条件方面不但考虑了传统的货车容量限制，还考虑了冷链场景下特有的温层约束。
图6示意性示出了根据本公开的一实施方式的冷链物流车辆的调度装置的框图。本公开实施方式提供的冷链物流车辆的调度装置600可以设置在服务器端上，或者部分设置在终端上，部分设置在服务器端上，例如，可以设置在图1中的服务器105，但本公开并不限定于此。
本公开实施方式提供的冷链物流车辆的调度装置600可以包括第一获取模块610、第二获取模块620、第一确定模块630和第二确定模块640。
其中，第一获取模块610配置为获取需配送货物总量、车辆装载率和车辆最大装货量；
第二获取模块620配置为根据所述需配送货物总量、所述车辆装载率和所述车辆最大装货量获取可能使用车辆数量集合；
第一确定模块630配置为对于所述可能使用车辆数量集合中的每一个可能使用车辆数量，确定在容量约束、温层约束和时间约束下使得配送总超时最短的子最优配送路线；
第二确定模块640配置为根据所述可能使用车辆数量集合中的每一个可能使用车辆数量对应的子最优配送路线和最短配送总超时，使用手肘法确定调度所使用的车辆数量和全局最优配送路线。
根据本公开的实施方式，上述冷链物流车辆的调度装置600根据车辆装载率、车辆最大装货量和需配送货物总量获取可能使用车辆数量集合，基于所述可能使用车辆数量集合、根据容量约束、温层约束和时间约束可以获取调度所使用的车辆数量和全局最优配送路线，可以实现冷链物流车辆的调 度。
根据本公开的实施方式，上述冷链物流车辆的调度装置600可以用于实现图2至图4的实施方式描述的冷链物流车辆的调度方法。
图7示意性示出了根据本公开的另一个实施方式的冷链物流车辆的调度装置700的方框图。
如图7所示，除了图7实施方式描述的第一获取模块610、第二获取模块620、第一确定模块630和第二确定模块640之外，该冷链物流车辆的调度装置700还包括显示模块710。
具体地，显示模块710在第二确定模块640获取调度所使用的车辆数量和全局最优配送路线后，向客户或工作人员显示调度所使用的车辆数量和全局最优配送路线。
在该冷链物流车辆的调度装置700中，通过显示模块710可以显示调度所使用的车辆数量和全局最优配送路线。
图8示意性示出了根据本公开的另一个实施方式的冷链物流车辆的调度装置800的方框图。
如图8所示，除了图6实施方式描述的第一获取模块610、第二获取模块620、第一确定模块630和第二确定模块640之外，冷链物流车辆的调度装置800还包括存储模块810。
具体地，存储模块810用于对冷链物流车辆的调度过程中的数据进行存储，以方便后续调用和参考。
可以理解的是第一获取模块610、第二获取模块620、第一确定模块630和第二确定模块640、显示模块710和存储模块810可以合并在一个模块中实现，或者其中的任意一个模块可以被拆分成多个模块。或者，这些模块中的一个或多个模块的至少部分功能可以与其他模块的至少部分功能相结合，并在一个模块中实现。根据本公开的实施方式，第一获取模块610、第二获取模块620、第一确定模块630和第二确定模块640、显示模块710和存储模块810的至少一个可以至少被部分地实现为硬件电路，例如现场可编程门阵列(FPGA)、可编程逻辑阵列(PLA)、片上系统、基板上的系统、封装上的系统、专用集成电路(ASIC)，或可以以对电路进行集成或封装的任何其他的合理方式等硬件或固件来实现，或以软件、硬件以及固件三种实 现方式的适当组合来实现。或者，第一获取模块610、第二获取模块620、第一确定模块630和第二确定模块640、显示模块710和存储模块810的至少一个可以至少被部分地实现为计算机程序模块，当该程序被计算机运行时，可以执行相应模块的功能。
由于本公开的示例实施方式的冷链物流车辆的调度装置的各个模块可以用于实现上述图2至图4描述的冷链物流车辆的调度方法的示例实施方式的步骤，因此对于本公开装置实施方式中未披露的细节，请参照本公开上述的冷链物流车辆的调度方法的实施方式。
本公开实施方式提供的冷链物流车辆的调度装置中的各个模块、单元和子单元的具体实现可以参照上述冷链物流车辆的调度方法中的内容，在此不再赘述。
图9示出了适于用来实现本公开实施方式的电子设备的计算机系统的结构示意图。
需要说明的是，图9示出的电子设备的计算机系统900仅是一个示例，不应对本公开实施方式的功能和使用范围带来任何限制。
如图9所示，计算机系统900包括中央处理单元(CPU，Central Processing Unit)901，其可以根据存储在只读存储器(ROM，Read-Only Memory)902中的程序或者从储存部分908加载到随机访问存储器(RAM，Random Access Memory)903中的程序而执行各种适当的动作和处理。在RAM 903中，还存储有系统操作所需的各种程序和数据。CPU 901、ROM 902以及RAM 903通过总线904彼此相连。输入/输出(I/O)接口905也连接至总线904。
以下部件连接至I/O接口905：包括键盘、鼠标等的输入部分906；包括诸如阴极射线管(CRT，Cathode Ray Tube)、液晶显示器(LCD，Liquid Crystal Display)等以及扬声器等的输出部分907；包括硬盘等的储存部分908；以及包括诸如LAN(Local Area Network，局域网)卡、调制解调器等的网络接口卡的通信部分909。通信部分909经由诸如因特网的网络执行通信处理。驱动器910也根据需要连接至I/O接口905。可拆卸介质911，诸如磁盘、光盘、磁光盘、半导体存储器等等，根据需要安装在驱动器910上，以便于从其上读出的计算机程序根据需要被安装入储存部分908。
特别地，根据本公开的实施方式，上文参考流程图描述的过程可以被实 现为计算机软件程序。例如，本公开的实施方式包括一种计算机程序产品，其包括承载在计算机可读存储介质上的计算机程序，该计算机程序包含用于执行流程图所示的方法的程序代码。在这样的实施方式中，该计算机程序可以通过通信部分909从网络上被下载和安装，和/或从可拆卸介质911被安装。在该计算机程序被中央处理单元(CPU)901执行时，执行本申请的方法和/或装置中限定的各种功能。
需要说明的是，本公开所示的计算机可读存储介质可以是计算机可读信号介质或者计算机可读存储介质或者是上述两者的任意组合。计算机可读存储介质例如可以是——但不限于——电、磁、光、电磁、红外线、或半导体的系统、装置或器件，或者任意以上的组合。计算机可读存储介质的更具体的例子可以包括但不限于：具有一个或多个导线的电连接、便携式计算机磁盘、硬盘、随机访问存储器(RAM)、只读存储器(ROM)、可擦式可编程只读存储器(EPROM(Erasable Programmable Read Only Memory，可擦除可编程只读存储器)或闪存)、光纤、便携式紧凑磁盘只读存储器(CD-ROM)、光存储器件、磁存储器件、或者上述的任意合适的组合。在本公开中，计算机可读存储介质可以是任何包含或存储程序的有形介质，该程序可以被指令执行系统、装置或者器件使用或者与其结合使用。而在本公开中，计算机可读的信号介质可以包括在基带中或者作为载波一部分传播的数据信号，其中承载了计算机可读的程序代码。这种传播的数据信号可以采用多种形式，包括但不限于电磁信号、光信号或上述的任意合适的组合。计算机可读的信号介质还可以是计算机可读存储介质以外的任何计算机可读存储介质，该计算机可读存储介质可以发送、传播或者传输用于由指令执行系统、装置或者器件使用或者与其结合使用的程序。计算机可读存储介质上包含的程序代码可以用任何适当的介质传输，包括但不限于：无线、电线、光缆、RF(Radio Frequency，射频)等等，或者上述的任意合适的组合。
附图中的流程图和框图，图示了按照本公开各种实施方式的方法、装置和计算机程序产品的可能实现的体系架构、功能和操作。在这点上，流程图或框图中的每个方框可以代表一个模块、程序段、或代码的一部分，上述模块、程序段、或代码的一部分包含一个或多个用于实现规定的逻辑功能的可执行指令。也应当注意，在有些作为替换的实现中，方框中所框选的功能也 可以以不同于附图中所框选的顺序发生。例如，两个接连地表示的方框实际上可以基本并行地执行，它们有时也可以按相反的顺序执行，这依所涉及的功能而定。也要注意的是，框图或流程图中的每个方框、以及框图或流程图中的方框的组合，可以用执行规定的功能或操作的专用的基于硬件的系统来实现，或者可以用专用硬件与计算机指令的组合来实现。
描述于本公开实施方式中所涉及到的模块和/或单元和/或子单元可以通过软件的方式实现，也可以通过硬件的方式来实现，所描述的模块和/或单元和/或子单元也可以设置在处理器中。其中，这些模块和/或单元和/或子单元的名称在某种情况下并不构成对该模块和/或单元和/或子单元本身的限定。
作为另一方面，本申请还提供了一种计算机可读存储介质，该计算机可读存储介质可以是上述实施方式中描述的电子设备中所包含的；也可以是单独存在，而未装配入该电子设备中。上述计算机可读存储介质承载有一个或者多个程序，当上述一个或者多个程序被一个该电子设备执行时，使得该电子设备实现如下述实施方式中所述的方法。例如，所述的电子设备可以实现如图2至图4的各个步骤。
相关技术中，例如可以采用机器学习方法、深度学习方法等进行冷链物流车辆的调度，不同方法适用的范围不同。
应当注意，尽管在上文详细描述中提及了用于动作执行的设备的若干模块、单元和子单元，但是这种划分并非强制性的。实际上，根据本公开的实施方式，上文描述的两个或更多模块、单元和子单元的特征和功能可以在一个模块、单元和子单元中具体化。反之，上文描述的一个模块、单元和子单元的特征和功能可以进一步划分为由多个模块、单元和子单元来具体化。
通过以上的实施方式的描述，本领域的技术人员易于理解，这里描述的示例实施方式可以通过软件实现，也可以通过软件结合必要的硬件的方式来实现。因此，根据本公开实施方式的技术方案可以以软件产品的形式体现出来，该软件产品可以存储在一个非易失性存储介质(可以是CD-ROM，U盘，移动硬盘等)中或网络上，包括若干指令以使得一台计算设备(可以是个人计算机、服务器、触控终端、或者网络设备等)执行根据本公开实施方式的方法。
本领域技术人员在考虑说明书及实践这里公开的发明后，将容易想到本公开的其它实施方案。本申请旨在涵盖本公开的任何变型、用途或者适应性变化，这些变型、用途或者适应性变化遵循本公开的一般性原理并包括本公开未公开的本技术领域中的公知常识或惯用技术手段。说明书和实施方式仅被视为示例性的，本公开的真正范围和精神由下面的权利要求指出。
应当理解的是，本公开并不局限于上面已经描述并在附图中示出的精确结构，并且可以在不脱离其范围进行各种修改和改变。本公开的范围仅由所附的权利要求来限制。

Claims (14)

  1. 一种冷链物流车辆的调度方法，其中，包括：
    获取需配送货物总量、车辆装载率和车辆最大装货量；
    根据所述需配送货物总量、所述车辆装载率和所述车辆最大装货量获取可能使用车辆数量集合；
    对于所述可能使用车辆数量集合中的每一个可能使用车辆数量，确定在容量约束、温层约束和时间约束下使得配送总超时最短的子最优配送路线；
    根据所述可能使用车辆数量集合中的每一个可能使用车辆数量对应的子最优配送路线和最短配送总超时，使用手肘法确定调度所使用的车辆数量和全局最优配送路线。
  2. 根据权利要求1所述的方法，其中，根据所述需配送货物总量、所述车辆装载率和所述车辆最大装货量获取可能使用车辆数量集合包括：
    将所述需配送货物总量除以第一车辆装载率和所述车辆最大装货量的乘积，并向上取整以获得所述可能使用车辆数量集合的上界；
    将所述需配送货物总量除以第二车辆装载率和所述车辆最大装货量的乘积，并向上取整以获得所述可能使用车辆数量集合的下界；
    将所述可能使用车辆数量集合的上界和所述可能使用车辆数量集合的下界之间的使用车辆数量组成所述可能使用车辆数量集合；
    其中，所述第一车辆装载率是所述车辆装载率减去第一比率，所述第二车辆装载率是所述车辆装载率加上第二比率，所述第一比率和所述第二比率均大于零且小于1。
  3. 根据权利要求1所述的方法，其中，根据所述可能使用车辆数量集合中的每一个可能使用车辆数量对应的子最优配送路线和最短配送总超时，使用手肘法确定调度所使用的车辆数量和全局最优配送路线，包括：
    将所述可能使用车辆数量集合分为第一集合和第二集合；
    根据所述第一集合和所述第二集合中每一个可能使用车辆数量和对应的最短配送总超时分别进行线性回归以获得第一预测模型和第二预测模型；
    根据所述第一预测模型和所述第二预测模型确定调度所使用的车辆数量和全局最优配送路线。
  4. 根据权利要求3所述的方法，其中，根据所述第一预测模型和所述第 二预测模型确定调度所使用的车辆数量和全局最优配送路线，包括：
    根据所述第一预测模型获取所述第一集合的最小方均根差；
    根据所述第二预测模型获取所述第二集合的最小方均根差；
    以所述可能使用车辆数量集合的所述第一集合和所述第二集合划分组合中，所述第一集合的最小方均根差和所述第二集合的最小方均根差之和最小的、划分所述第一集合和所述第二集合的可能使用车辆数量和对应的子最优配送路线作为调度所使用的车辆数量和全局最优配送路线。
  5. 根据权利要求4所述的方法，其中，根据所述第一预测模型获取所述第一集合的最小方均根差，包括：
    根据所述第一集合中每一个可能使用车辆数量所对应的最短配送总超时、所述第一预测模型的预测值和所述第一集合中可能使用车辆数量的元素个数获取所述第一集合的最小方均根差。
  6. 根据权利要求5所述的方法，其中，根据所述第二预测模型获取所述第二集合的最小方均根差，包括：
    根据所述第二集合中每一个可能使用车辆数量所对应的最短配送总超时、所述第二预测模型的预测值和所述第二集合中可能使用车辆数量的元素个数获取所述第二集合的最小方均根差。
  7. 根据权利要求1所述的方法，其中，对于所述可能使用车辆数量集合中的每一个可能使用车辆数量，确定在容量约束、温层约束和时间约束下使得配送总超时最短的子最优配送路线，包括：
    将需配送货物按照需要的车辆温层要求进行分类；
    将分类完成的每类需配送货物根据车辆装载率和车辆最大装货量，分别分配给对应温层的车辆；
    按照可能的配送路线和客户要求的发货时间、送达时间，获取使得配送总超时最短的子最优配送路线。
  8. 根据权利要求7所述的方法，其中，按照可能的配送路线和客户要求的发货时间、送达时间，获取使得配送总超时最短的子最优配送路线，包括：
    在一个可能使用车辆数量的最短配送总超时等于零时，选择路程最短的配送路线为子最优配送路线。
  9. 根据权利要求1所述的方法，其中，车辆的温层为N个，其中N是 大于等于2的整数。
  10. 根据权利要求1所述的方法，其中，获取需配送货物总量、车辆装载率和车辆最大装货量，包括：
    在车辆的车型不一致时，获取所述需配送货物总量、所述车辆装载率和加权车辆最大装货量。
  11. 一种冷链物流车辆的调度装置，其中，包括：
    第一获取模块，配置为获取需配送货物总量、车辆装载率和车辆最大装货量；
    第二获取模块，配置为根据所述需配送货物总量、所述车辆装载率和所述车辆最大装货量获取可能使用车辆数量集合；
    第一确定模块，对于所述可能使用车辆数量集合中的每一个可能使用车辆数量，确定在容量约束、温层约束和时间约束下使得配送总超时最短的子最优配送路线；
    第二确定模块，配置为根据所述可能使用车辆数量集合中的每一个可能使用车辆数量对应的子最优配送路线和最短配送总超时，使用手肘法确定调度所使用的车辆数量和全局最优配送路线。
  12. 一种电子设备，其中，包括：
    一个或多个处理器；
    存储装置，配置为存储一个或多个程序，当所述一个或多个程序被所述一个或多个处理器执行时，使得所述一个或多个处理器实现如权利要求1至10中任一项所述的方法。
  13. 一种计算机可读存储介质，所述计算机可读存储介质存储有计算机程序，其中，所述计算机程序被处理器执行时实现如权利要求1至10中任一项所述的方法。
  14. 一种计算机程序产品，包括计算机程序，所述计算机程序被处理器执行时实现权利要求1-10任一项所述的方法。
PCT/CN2023/072706 2022-05-24 2023-01-17 冷链物流车辆的调度方法及相关设备 WO2023226459A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202210571006.9 2022-05-24
CN202210571006.9A CN114862038A (zh) 2022-05-24 2022-05-24 冷链物流车辆的调度方法及相关设备

Publications (2)

Publication Number Publication Date
WO2023226459A1 true WO2023226459A1 (zh) 2023-11-30
WO2023226459A9 WO2023226459A9 (zh) 2024-02-01

Family

ID=82638777

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2023/072706 WO2023226459A1 (zh) 2022-05-24 2023-01-17 冷链物流车辆的调度方法及相关设备

Country Status (2)

Country Link
CN (1) CN114862038A (zh)
WO (1) WO2023226459A1 (zh)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114862038A (zh) * 2022-05-24 2022-08-05 北京京东乾石科技有限公司 冷链物流车辆的调度方法及相关设备

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106803136A (zh) * 2017-01-24 2017-06-06 苏州工业职业技术学院 一种基于混合遗传算法的生鲜配送实时优化方法
US20190303857A1 (en) * 2018-03-27 2019-10-03 Accenture Global Solutions Limited System for collaborative logistics using a collaborative logistics map and a knowledge graph
CN112183812A (zh) * 2020-08-25 2021-01-05 昆明理工大学 一种计及短时低成本的成品卷烟物流车辆调度方法
CN114862038A (zh) * 2022-05-24 2022-08-05 北京京东乾石科技有限公司 冷链物流车辆的调度方法及相关设备

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR100613858B1 (ko) * 2000-01-21 2006-08-17 한국전자통신연구원 물류 워크플로우용 차량 배차 방법
CN113449895A (zh) * 2020-03-25 2021-09-28 北京沃东天骏信息技术有限公司 车辆调度方法和装置
CN112270135B (zh) * 2020-11-13 2023-02-03 吉林烟草工业有限责任公司 一种物流发运调度智能配送方法、装置、设备及存储介质

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106803136A (zh) * 2017-01-24 2017-06-06 苏州工业职业技术学院 一种基于混合遗传算法的生鲜配送实时优化方法
US20190303857A1 (en) * 2018-03-27 2019-10-03 Accenture Global Solutions Limited System for collaborative logistics using a collaborative logistics map and a knowledge graph
CN112183812A (zh) * 2020-08-25 2021-01-05 昆明理工大学 一种计及短时低成本的成品卷烟物流车辆调度方法
CN114862038A (zh) * 2022-05-24 2022-08-05 北京京东乾石科技有限公司 冷链物流车辆的调度方法及相关设备

Also Published As

Publication number Publication date
WO2023226459A9 (zh) 2024-02-01
CN114862038A (zh) 2022-08-05

Similar Documents

Publication Publication Date Title
US10692039B2 (en) Cargo logistics dispatch service with integrated pricing and scheduling
US10776750B2 (en) System and method for fulfilling e-commerce orders from a hierarchy of fulfilment centres
US20230088950A1 (en) Method and system for intelligent load optimization for vehicles
Shao et al. Synchronizing e-commerce city logistics with sliding time windows
CN109272267A (zh) 一种配送路径规划方法、装置及设备、存储介质
CN109345166B (zh) 用于生成信息的方法和装置
WO2023226459A1 (zh) 冷链物流车辆的调度方法及相关设备
CN113673932A (zh) 一种物流网络规划方法和装置
CN111178810B (zh) 用于生成信息的方法和装置
Zhou et al. A scalable vehicle assignment and routing strategy for real-time on-demand ridesharing considering endogenous congestion
CN112082566A (zh) 电动汽车路径规划方法、装置、终端及存储介质
CN111582701B (zh) 订单处理方法、装置、存储介质及电子设备
Wang et al. Multi-objective optimisation of automated guided dispatching and vehicle routing system
Wang et al. The mobile production vehicle routing problem: Using 3D printing in last mile distribution
US10068192B2 (en) System and method of solving supply chain campaign planning problems involving major and minor setups
CN113469431A (zh) 物流配送路径推荐的方法、装置和计算机可读存储介质
Cai et al. An efficient multi-objective evolutionary algorithm for a practical dynamic pickup and delivery problem
US20230090740A1 (en) System and Method for Predicting Arrival Time in a Freight Delivery System
JP2008168966A (ja) 運搬ルート生成装置、運搬ルート生成方法及び物流ネットワーク最適化装置
CN111768133A (zh) 物品入库方法和装置
US20230104886A1 (en) Heavyweight quoting and associating plane types with package sizes
CN113762574B (zh) 航班推荐方法和装置以及电子设备和介质
CN115099865A (zh) 一种数据处理方法和装置
CN111144602A (zh) 一种车辆调度方法和装置
CN113256194B (zh) 确定配送中心自留库存的方法和装置

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 23810535

Country of ref document: EP

Kind code of ref document: A1