WO2023082782A1 - 物流路由网络确定方法和装置 - Google Patents

物流路由网络确定方法和装置 Download PDF

Info

Publication number
WO2023082782A1
WO2023082782A1 PCT/CN2022/115788 CN2022115788W WO2023082782A1 WO 2023082782 A1 WO2023082782 A1 WO 2023082782A1 CN 2022115788 W CN2022115788 W CN 2022115788W WO 2023082782 A1 WO2023082782 A1 WO 2023082782A1
Authority
WO
WIPO (PCT)
Prior art keywords
route
optimized
transportation cost
loading
line
Prior art date
Application number
PCT/CN2022/115788
Other languages
English (en)
French (fr)
Inventor
蒋晶
苏小龙
严良
庄晓天
吴盛楠
Original Assignee
北京京东振世信息技术有限公司
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 北京京东振世信息技术有限公司 filed Critical 北京京东振世信息技术有限公司
Publication of WO2023082782A1 publication Critical patent/WO2023082782A1/zh

Links

Images

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"
    • 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
    • G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
    • G06Q10/083—Shipping
    • 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
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
    • G16Y10/00—Economic sectors
    • G16Y10/40—Transportation

Definitions

  • the present application relates to the field of computer technology, in particular to the field of logistics technology, and in particular to a method and device for determining a logistics routing network.
  • the stowage optimization decision-making of routing network under the consideration of data fluctuation mainly includes the method based on the coefficient of variation to screen the stable load, and the method based on the mean value.
  • Embodiments of the present application provide a method, device, equipment, and storage medium for determining a logistics routing network.
  • an embodiment of the present application provides a method for determining a logistics routing network, the method comprising: acquiring route data of routes to be optimized and corresponding stowage data of routes to be optimized within a historical preset time period, and a set of associated lines corresponding to the loading to be optimized, the line to be optimized is determined according to business requirements; according to the line data of the line to be optimized, the corresponding loading data of the loading to be optimized, and the set of associated lines, construct a historical preset The routing sub-network to be optimized at each moment in the time period;
  • the target route in the routing sub-network to be optimized at a specified time within the historical preset time period is screened out, and then the target logistics routing network is determined.
  • an embodiment of the present application provides an apparatus for determining a logistics routing network, which includes: an acquisition module configured to acquire the route data of the route to be optimized and the corresponding route data to be optimized within a historical preset time period; The loading data on the load, and the associated line set corresponding to the loading to be optimized, the line to be optimized is determined according to the business requirements; the building module is configured to be based on the line data of the line to be optimized and the corresponding allocation Carrying data, and the set of associated routes, constructing routing sub-networks to be optimized at each moment in the historical preset time period; the screening module is configured to filter out the specified routes in the historical preset time period based on the target transportation cost and sampling probability Time the target route in the route sub-network to be optimized, and then determine the target logistics routing network.
  • an embodiment of the present application provides an electronic device, the electronic device includes one or more processors; a storage device, on which one or more programs are stored, when the one or more programs are Multiple processors are executed, so that one or more processors implement the method described in any implementation manner of the first aspect.
  • an embodiment of the present application provides a computer-readable medium, on which a computer program is stored, and when the program is executed by a processor, the method described in any implementation manner of the first aspect is implemented.
  • FIG. 1 is an exemplary system architecture diagram to which the present application can be applied;
  • Fig. 2 is a flow chart of an embodiment of a method for determining a logistics routing network according to the present application
  • FIG. 3 is a schematic diagram of an application scenario of a method for determining a logistics routing network according to the present application
  • Fig. 4 is a flow chart of another embodiment of the method for determining a logistics routing network according to the present application.
  • Fig. 5 is a schematic diagram of an embodiment of a device for determining a logistics routing network according to the present application
  • FIG. 6 is a schematic structural diagram of a computer system suitable for implementing the server of the embodiment of the present application.
  • FIG. 1 shows an exemplary system architecture 100 to which an embodiment of the model training method of the present application can be applied.
  • a system architecture 100 may include terminal devices 101 , 102 , 103 , a network 104 and a server 105 .
  • the network 104 is used as a medium for providing communication links between the terminal devices 101 , 102 , 103 and the server 105 .
  • Network 104 may include various connection types, such as wires, wireless communication links, or fiber optic cables, among others.
  • the terminal devices 101, 102, 103 interact with the server 105 via the network 104 to receive or send messages and the like.
  • Various communication client applications such as communication applications, can be installed on the terminal devices 101, 102, and 103.
  • the terminal devices 101, 102, and 103 may be hardware or software.
  • the terminal devices 101, 102, 103 When the terminal devices 101, 102, 103 are hardware, they may be various electronic devices with display screens, including but not limited to mobile phones and notebook computers.
  • the terminal devices 101, 102, 103 When the terminal devices 101, 102, 103 are software, they can be installed in the electronic devices listed above. It can be implemented as a plurality of software or software modules (for example, to provide logistics routing network determination services), and can also be implemented as a single software or software module. No specific limitation is made here.
  • the server 105 may be a server that provides various services, for example, obtains the line data of the line to be optimized and the corresponding loading data of the loading to be optimized within the historical preset time period, and the set of associated lines corresponding to the loading to be optimized ; According to the line data of the line to be optimized and the corresponding loading data to be optimized, as well as the set of associated lines, construct the routing sub-network to be optimized at each moment in the historical preset time period; based on the target transportation cost and sampling probability , to filter out the target route in the routing sub-network to be optimized at a specified time within the historical preset time period, and then determine the target logistics routing network.
  • the server 105 may be hardware or software.
  • the server 105 can be implemented as a distributed server cluster composed of multiple servers, or as a single server.
  • the server is software, it can be implemented as a plurality of software or software modules (for example, to provide logistics routing network determination services), or can be implemented as a single software or software module. No specific limitation is made here.
  • model training method can be executed by the server 105, can also be executed by the terminal devices 101, 102, 103, and can also be executed by the server 105 and the terminal devices 101, 102, 103 in cooperation with each other .
  • each part (such as each unit, subunit, module, submodule) included in the logistics routing network determination device can be set in the server 105, or can be set in the terminal equipment 101, 102, 103, or can be respectively Set in the server 105 and the terminal devices 101, 102, 103.
  • terminal devices, networks and servers in Fig. 1 are only illustrative. According to the implementation needs, there can be any number of terminal devices, networks and servers.
  • FIG. 2 shows a schematic flowchart 200 of an embodiment of a method for determining a logistics routing network that can be applied to the present application.
  • the method for determining the logistics routing network includes the following steps:
  • Step 201 acquiring the line data of the line to be optimized and the corresponding loading data of the loading to be optimized within the historical preset time period, as well as the associated line set corresponding to the loading to be optimized.
  • the execution subject (server 105 or terminal equipment 101, 102, 103 as shown in FIG. 1) can obtain the line data of the line to be optimized and the corresponding line to be optimized at each time within the historical preset time period.
  • the length of the historical preset time period can be set according to actual needs, for example, 10 days, 30 days, 90 days, etc., which is not limited in this application.
  • the route to be optimized at each moment within the historical preset time period may be determined according to business requirements.
  • Business requirements include information on the origin and destination of the goods to be transported, total transportation cost requirements, timeliness requirements, and other information, and may also include some special requirements, for example: the business party wants to optimize the loading of leftover cargo.
  • the logistics network database can match the routes that meet the requirements, and then determine the routes to be optimized.
  • the line may be a section of the line in the transportation path formed from the first sorting center to the last sorting center.
  • the path from a sorting center in Guangzhou (the first sorting center) to a sorting center in Shanghai (the last sorting center) is: transfer from a sorting center in Guangzhou to a sorting center in Suzhou, and then from the transfer station
  • the corresponding sorting center to Shanghai, and the line from a sorting center in Guangzhou to a sorting center in Suzhou can be a high-speed line, a national highway line, or a part of a high-speed line + a part of a national road line. Therefore, in the case of a certain path, there will be multiple matching lines.
  • the route data may include acquiring mileage information, capacity mode information, cargo quantity information, remaining capacity information and transportation cost information of the route to be optimized.
  • the mileage information of the route to be optimized may include the route code and route mileage.
  • each route is provided with a corresponding route code and route mileage.
  • the capacity mode information may include information such as the mode of transport capacity, the number of vehicles used on the route, and the load on the route.
  • the mode of transport capacity may include the type of transport and the type of means of transport. For example, the mode of transport capacity is land transport and a 9.6m large transport vehicle.
  • the cargo volume may be the cumulative sum of the volumes of the cargo.
  • the remaining load capacity information may be the difference between the volume of the corresponding stowage on the route to be optimized and the volume of the current cargo.
  • the transportation cost information may include less-than-truckload mean square quantity transportation costs of routes, vehicle transportation costs of different vehicle types, and the less-than-truckload mean square quantity transportation costs may be the transportation costs per square meter of less-than-truckload goods.
  • the above line data can be obtained through the database.
  • the line data obtained here can be used in the subsequent process of determining the routing subnetwork.
  • the loading to be optimized is determined.
  • the loading on the line is determined, that is, for the entire logistics network, there is a corresponding loading for each line in its database, and the line and the loading are corresponding to each other.
  • the route data and load data of the route to be optimized can be directly read from the database of the logistics network. It can also be generated online by using the existing logistics network generation system.
  • the stowage data may include the stowage quantity information and the stowage shift information of different sorting centers; wherein, the stowage quantity information may be the stowage quantity data, and the stowage shift information may include the first Line code and loading shift; the stowage shift is the departure time and arrival time of the stowage, and the stowage volume data of different sorting centers can be the volume of goods flowing up the corresponding line of stowage, for example, when If there are multiple lines with the loading, the loading data includes the volume of the loading in each line flow.
  • the above line data can be obtained through the database.
  • the executive body can use a series engine in the logistics field to determine the associated route.
  • the series engine can be a series relationship table established according to each sorting center. Load code, shift and other information. In the case of fewer routes to be optimized, manual selection can also be performed to set associated routes. Furthermore, an associated line set is determined according to the associated route.
  • the method for the execution subject to determine the set of associated lines according to the associated route may include: if the associated route is determined according to the original route corresponding to the loading to be optimized, then the associated line set may be determined according to the original line set corresponding to the original route to be optimized ; If the associated route is determined according to the alternative route corresponding to the loading to be optimized, then the set of associated lines can be determined according to the set of alternative lines corresponding to the alternative route to be optimized; If the route and the original route are determined, the set of associated lines can be determined according to the set of candidate lines corresponding to the candidate route to be optimized and the set of original lines corresponding to the original route.
  • obtaining the associated line set to be optimized for loading includes: determining the corresponding original line set according to the original route to be optimized for loading; Select a line set; determine the associated line set according to the original line set and the candidate line set.
  • the executive body can determine the corresponding original line set according to the original route to be optimized; it can use all the lines contained in the original route as the original line set; it can also filter the lines in the original route, Select one or several lines included in the route as the original line set.
  • the candidate route to be optimized for loading determine the corresponding candidate line set; all the lines contained in the candidate route can be used as the candidate line set; the lines in the candidate route can also be screened and selected
  • the lines contained in one or more candidate routes are used as a set of candidate lines, which is not limited in this application.
  • the execution subject can use the original line set and the candidate line set together as the associated line set, the original line set and part of the candidate line sets together as the associated line set, or part of the original line set and all or part of the candidate lines.
  • the set of lines together serves as an associated route, which is not limited in this application.
  • the aforementioned part of the original line set or part of the candidate line set can be obtained by screening according to different screening rules.
  • the alternative routes to be optimized are obtained in the following manner: according to the original route to be optimized, the alternative routes to be optimized are screened, so that the alternative routes can reach The service time limit of the site is not lower than the corresponding service time limit of the original route.
  • the original route is the unoptimized stowage route, which can be obtained from the logistics network database or from the routing serial engine.
  • the original route includes the original route of goods to be optimized for stowage and the data including line code sequence, shift and so on. Compared with the route, the route carries more information, such as line code sequence and loading shift and other information.
  • a logistics network is a transportation network formed by a large number of routes connected in series.
  • the alternative routes are screened by the route cascading engine or the greedy algorithm, so that the service timeliness of the loading and arriving sites of the alternative routes is not lower than the corresponding service timeliness of the original route. Similar to the original route, the alternative route also includes information such as the alternative route and its line code sequence and shift.
  • the objective function can be set to have the lowest transportation cost from the origin to the destination, or can be set to have the least transfers from the origin to the destination, or can be set to have the least number of transportation vehicles from the origin to the destination, depending on the needs Set, this embodiment is not limited to this;
  • the constraint condition can be that the service timeliness of the stowage arrival site of the alternative route is not lower than the corresponding service timeliness of the original route, and multiple constraint conditions can also be set, for example, the cost No increase, no increase in time, etc.; just set a greedy strategy.
  • One or more alternative routes can be screened, which is not limited in this application.
  • step 202 according to the line data of the line to be optimized, the corresponding load data of the load to be optimized, and the set of associated lines, construct a route sub-network to be optimized at each moment in the historical preset time period.
  • the executive body may directly form a line subnetwork to be optimized from the set of associated lines, or may filter lines in the set of associated lines to form a line subnetwork to be optimized, which is not limited in this application.
  • the execution subject adds the corresponding line data and loading data to the sub-network of the line to be optimized, and obtains the historical The routing sub-network to be optimized at a corresponding moment within a preset time period.
  • loading data including the volume data of each loading in different sorting centers, if there are multiple lines flowing to the loading, it includes the volume of the loading on the flow of each line, and the first line of loading Information such as codes and loading shifts;
  • line data can include line codes, line mileage, line types (such as trunk lines, branch lines, etc.), transportation types (such as road less-than-truckload, road vehicle, etc.), the number of vehicles on the line, and the cargo party. The amount, remaining load capacity, LTL transportation cost of the line, the transportation cost of different types of vehicles, the loading on the line, etc.
  • routing sub-network to be optimized is constructed on the basis of the original routing network, and the loading adjustment will only affect the line cargo volume on the routing sub-network to be optimized.
  • the line capability of the routing subnetwork to be optimized can be analyzed. Firstly, all the lines of the route sub-network to be optimized are divided into two categories: the line set of candidate lines to be optimized (referred to as the set of candidate lines), and the set of lines included in all candidate routes (referred to as the set of candidate lines). Since this example aims to reduce the cost by adjusting the loading, it is to reduce the less-than-truckload or reduce the vehicle type by reducing the amount of tail cargo on the candidate line, and at the same time, the remaining load capacity on the candidate line can cover the stowage party as much as possible. quantity. For the above analysis, the focus is on: the cargo volume of the candidate lines and the remaining carrying capacity of the candidate lines, so as to determine the capacity of the lines in the sub-network.
  • Step 203 based on the target transportation cost and the sampling probability, select the target route in the routing sub-network to be optimized at a specified time within the historical preset time period, and then determine the target logistics routing network.
  • the execution subject can construct the objective function according to the sampling probability and the target transportation cost, set constraints according to the actual demand, and filter out the target route in the routing sub-network to be optimized, and then determine the target logistics routing network.
  • the target transportation cost can be determined according to the original transportation cost of the route to be optimized and the transportation cost of any route in the routing subnetwork to be optimized, and the sampling probability and the target transportation cost are related to time.
  • the sampling probability is used to indicate the importance of the target transportation cost at a given moment. It should be pointed out that if the daily data within the preset time period is considered to be equally important, the sampling probability can be set to 1/T, where T represents the length of the preset time period.
  • the target route in the routing sub-network to be optimized at a specified moment in the historical preset time period is filtered out, including: calculating the route to be optimized at a specified moment in the historical preset time period The target transportation cost of any route in the subnetwork; select a route corresponding to the maximum value of the product of sampling probability and target transportation cost as the target route.
  • the execution subject can calculate the target transportation cost of any route in the routing sub-network to be optimized at the specified time within the preset time period; and then select a route corresponding to the maximum value of the product of the sampling probability and the target transportation cost as the target routing.
  • the product of the sampling probability and the target transportation cost is tied for the largest number of times, it can be randomly selected or selected according to other conditions, for example, the product with the largest product and the least leftover goods can be selected.
  • the calculation of the target transportation cost of any route in the route subnetwork to be optimized at a specified moment in the historical preset time period includes: determining the original transportation of the route to be optimized at the specified moment in the historical preset time period Cost and the transportation cost type of any route in the routing subnetwork to be optimized; according to the transportation cost type, the transportation costs corresponding to all transportation cost types are summed to obtain the transportation cost of the route; based on the original transportation cost and the route’s Shipping Cost, to determine the target shipping cost for this route.
  • the execution subject may first determine the original transportation cost of the route to be optimized at a specified moment and the transportation cost type of any route in the route subnetwork to be optimized.
  • the transportation cost type includes the less-than-truckload cost of the less-than-truckload line on the original route in the route, the vehicle cost of the vehicle line on the original route in the route, and the increased less-than-truckload cost of the alternate route after the load adjustment in the route.
  • the execution subject can sum the transportation costs corresponding to all transportation cost types to obtain the transportation cost of the route.
  • the transportation cost corresponding to the transportation cost type is determined based on at least one of the cubic quantity of the route to be optimized, the stowage cubic quantity of the route to be optimized, and the remaining loading capacity of the vehicle.
  • the original transportation cost, the volume of the route to be optimized, the volume of loading on the route to be optimized, and the remaining loading capacity of the vehicle are associated with time.
  • the original transportation cost, the volume of the route to be optimized, the stowage volume of the route to be optimized, and the remaining loading capacity of the vehicle are related to the vehicle type, the volume of the tail cargo, the stowage volume, and the remaining loading capacity of the line, while the tail
  • the types of trucks, the volume of tail cargo, the volume of stowage and the remaining loading capacity of the line have great fluctuations over time.
  • the influence of tail-car models, tail-cargo volume, and stowage volume on cost is mainly reflected in the cost reduction of the original route: the stowage is adjusted from the original route to the alternative route, and the original
  • the reduction in the volume of goods on the routing line, the reduction in the number of tail trucks on the line or the reduction in the type of tail trucks lead to a reduction in the transportation cost of the original routing line.
  • the cost of the original route is determined by the original tail truck type
  • the adjusted route cost is determined by the adjusted tail truck type
  • the adjusted tail truck type is determined by the remaining cargo volume
  • the adjusted remaining cargo volume is It is determined by the cargo volume of the original route and the cargo volume to be adjusted.
  • the remaining loading capacity of the line has an impact on the cost, which is mainly reflected in the increase in the transportation cost of the alternative route: the loading is adjusted from the original route to the alternative route to make full use of the remaining capacity of the alternative route. loading capacity. If the remaining loading capacity is not enough, it is necessary to add additional LTL or vehicle cost to meet the distribution demand. The increased cost is related to the overflow volume, and the overflow volume is determined by the remaining loading capacity and stowage volume of the alternative route.
  • the target transportation cost of the route is determined.
  • a mixed integer linear programming model can be constructed to optimize the loading and obtain the maximum value of the target transportation cost.
  • the aim is to make full use of the remaining load capacity of the alternative line, and by adjusting the loading, the volume of goods on the line to be optimized can be reduced.
  • a mixed integer linear programming model is constructed.
  • the objective of the model can be set to maximize the product of the target transportation cost and the sampling probability.
  • the target transportation cost is the difference between the original transportation cost and the transportation cost.
  • the transportation cost is mainly composed of three parts: 1) the LTL cost of the original LTL line; 2) the vehicle cost of the original vehicle line; 3) the adjusted loading reserve Less-than-truckload costs increased by route selection.
  • the mixed integer linear programming model of the objective function is as follows:
  • a 1 represents the set of alternative lines, A 2 represents the set of less-than-truckload lines to be optimized, and A 3 represents the set of vehicle lines to be optimized;
  • K(o) represents the same as o A collection of nodes in the sorting center but with different shifts;
  • n represents the alternative routing index, n ⁇ N od , N od represents the set of alternative routing indices corresponding to (o,d) lines; (i, j) represents the line code; the shifts are different , the encoding is different;
  • C t represents the original transportation cost of the route to be optimized; Indicates the volume of less-than-truckload and vehicle lines to be optimized; Indicates the remaining loading capacity of the alternative line; Indicates the volume of cargo corresponding to d on the route to be optimized (i,j);
  • the vehicle cost of each type of vehicle with a distance of d ij ; l ij represents the route type of the route (i, j), and l ij ⁇ ⁇ 0,1 ⁇ can be set.
  • ⁇ odn (i,j) ⁇ 0,1 ⁇ indicates whether the nth candidate route of route (o,d) contains line (i,j), and the value can be set to 1 when it is included, otherwise the value is 0 ;
  • ⁇ okd (i,j) ⁇ 0,1 ⁇ indicates whether the original route corresponding to d on the (o,k) line contains the line (i,j), and the value can be set to 1, otherwise the
  • the value is 0;
  • V1, V2, V3, V4, and V5 represent the load capacity of the 1st, 2nd, 3rd, 4th, and 5th vehicle types, for example, the 5 types of vehicles are 5.2m, 7.6m, 9.6m, and 14.5m , 17.5m box truck.
  • the types of vehicles in this embodiment can also be set correspondingly according to the actual situation, and can be more or less than 5 types, and can also be set as vehicles of the same model or different models, which is not limited in this application.
  • decision variables which are described in detail as follows: Indicates the quantity of undistributed goods remaining on the route (i,j) to be optimized; Indicates the quantity of goods allocated on the alternative line (i,j); y id ⁇ ⁇ 0,1 ⁇ indicates whether the loading d on the sorting center i is diverted to the alternative line.
  • the value is 0; ⁇ odn ⁇ ⁇ 0,1 ⁇ indicates whether the sorting center o stowage d chooses the n ⁇ N od alternative route, and the value can be set to include 1, otherwise the value is 0; Indicates the vehicle cost of the vehicle route (i, j) to be optimized after the loading adjustment; Indicates the amount of cargo that needs to be delivered as part-load if the remaining load on the alternative route (i, j) is not enough; Indicates the remaining load on the alternative line (i, j) due to the original load transfer.
  • the direct decision variables in this model are y id , ⁇ odn , the former determines whether a certain loading of the sorting center should be adjusted, and the latter determines which route to adjust to after the loading adjustment.
  • the remaining decision variables are indirect decision variables.
  • the model does not affect the random parameters C t .
  • the main reasons for fitting analysis are two points: 1) The parameters are not independent, so it is unreasonable to conduct fitting analysis alone; 2) The fitting effect is not good if the amount of data is too small, but too much data will lead to deviation from the current Historical data far away in time affects the distribution of data, and it is unreasonable to use this distribution as the future distribution.
  • the current plan considers that the transportation method cannot be adjusted for the unloaded goods on the route to be optimized.
  • the cost calculation of the vehicle transportation method is related to the model and mileage
  • the cost calculation of the less-than-truckload transportation method is related to the volume and mileage.
  • the whole vehicle mode is adjusted to the zero-truckload mode, which can be realized by modifying constraint (12).
  • the following variables can be added: Whether to choose the less-than-truckload mode of transportation, Whether to choose the vehicle transportation method of model k ⁇ 1,...,5 ⁇ (for example, 5 models correspond to 5 common models such as 5.2 meters, 7.6 meters, 9.6 meters, 14.5 meters, and 17.5 meters), Less-than-truckload quantities.
  • Constraint (13-14) is the type of variable; Constraint (15) is the cost calculation formula after adjusting the loading of the original route, where c 0 represents the unilateral cost of less-than-truckload, c k , k ⁇ 1,...,5 ⁇ is the cost of five types of vehicles; Constraint (16) restricts the use of less-than-truckload transportation or a certain vehicle model; Constraint (17) restricts the amount of LTL cargo to be greater than zero only after the LTL transportation method is selected; Constraint (18 -19) means that the cargo volume should be within the transportation capacity of the selected model.
  • this embodiment can also be extended to consider scenarios such as the route to be optimized and the vehicle model of the alternative route that can be adjusted.
  • a mixed integer linear programming solver can be used to solve it, such as the pyscipopt solver.
  • the mixed integer linear programming problem is an NP problem
  • the network scale will not be too large after optimizing the constructed routing sub-network according to business requirements.
  • the required optimization time is about 30 minutes, and the optimization time is less.
  • the output results mainly include the following information: 1) Loading adjustment plan: loading information (including name, square quantity, single quantity, etc.), 3) Information on routed routes after adjustment (including route cargo volume, adjusted route cargo volume, route cost, adjusted route cost, etc.).
  • the final optimization result of 687 stowages is: cost savings of 8,000 yuan/day, optimized stowage quantity of 89, and total optimized stowage volume of 204 square meters.
  • FIG. 3 is a schematic diagram of an application scenario of the method for determining a logistics routing network according to this embodiment.
  • the execution subject 301 acquires the line data 302 of the line to be optimized within the historical preset time period, the corresponding loading data 303 of the loading to be optimized, and the associated line set corresponding to the loading to be optimized 304; According to the line data of the line to be optimized and the corresponding loading data of the loading to be optimized, and the set of associated lines, construct the routing sub-network 305 to be optimized at each moment in the historical preset time period; based on the target transportation cost and The sampling probability screens out the target route 306 in the routing sub-network to be optimized at a specified time within the historical preset time period, and then determines the target logistics routing network.
  • the method for determining the logistics routing network of this application obtains the route data of the route to be optimized within the historical preset time period, the corresponding stowage data of the stowage to be optimized, and the set of associated routes corresponding to the stowage to be optimized;
  • the line data of the line and the corresponding loading data to be optimized, as well as the set of associated lines construct the routing sub-network to be optimized at each time within the historical preset time period; based on the target transportation cost and sampling probability, filter out the historical
  • FIG. 4 it shows a flow 400 of another embodiment of a method for determining a logistics routing network.
  • the process 400 of the method for determining the logistics routing network of this embodiment may include the following steps:
  • Step 401 acquiring the route data of the routes to be optimized and the corresponding load data of the loads to be optimized within the historical preset time period, as well as the set of associated routes corresponding to the loads to be optimized.
  • step 401 for implementation details and technical effects of step 401, reference may be made to the description of step 201, and details are not repeated here.
  • Step 402 according to the line data of the line to be optimized, the corresponding loading data of the loading to be optimized, and the set of associated lines, construct the routing sub-network to be optimized at each moment in the historical preset time period.
  • step 402 for implementation details and technical effects of step 402, reference may be made to the description of step 202, which will not be repeated here.
  • Step 403 based on the transportation cost, sampling probability and the weight of the sampling probability, select the target route in the routing sub-network to be optimized at a specified time within the historical preset time period, and then determine the target logistics routing network.
  • the execution subject can construct the objective function according to the sampling probability, the weight of the sampling probability, and the target transportation cost, and set constraints according to actual needs, and select the target in the routing subnetwork to be optimized by maximizing the target transportation cost Routing, and then determine the target logistics routing network.
  • the target transportation cost is used to indicate the difference between the original transportation cost and the transportation cost, and the sampling probability and the target transportation cost are associated with time.
  • the weight of the sampling probability can be determined according to the distance between the execution time and the current time. For example, the closer the specified time is to the current time, the greater the weight, and the farther the specified time is from the current time, the farther the weight is. The closer the specified time is to the current time, the more important the data at the specified time will be, and the greater the impact will be.
  • the process 400 of the method for determining the logistics routing network in this embodiment reflects the selection of historical presets based on the target transportation cost, sampling probability and the weight of the sampling probability.
  • the target route in the routing sub-network to be optimized is specified at the specified moment within the time period, and then the target logistics routing network is determined, which further improves the accuracy of the determined target logistics routing network.
  • the present application provides an embodiment of determining a logistics routing network.
  • the device embodiment corresponds to the method embodiment shown in FIG. 2 , and the device specifically It can be applied to various electronic devices.
  • the logistics routing network determination device 500 of this embodiment includes: an acquisition module 501, a construction module 502 and a screening module 503.
  • the acquiring module 501 can be configured to acquire the line data of the lines to be optimized and the corresponding loading data of the loading to be optimized within the historical preset time period, as well as the set of associated lines corresponding to the loading to be optimized.
  • the construction module 502 can be configured to construct the route to be optimized at each moment in the historical preset time period according to the route data of the route to be optimized and the corresponding load data of the load to be optimized, as well as the set of associated routes. network.
  • the screening module 503 can be configured to filter out the target route in the route sub-network to be optimized at a specified time within the historical preset time period based on the target transportation cost and sampling probability, and then determine the target logistics routing network.
  • the screening module is further configured to: based on the target transportation cost, the sampling probability, and the weight of the sampling probability, filter out the routing subnetwork to be optimized at a specified time within a historical preset time period destination route.
  • the screening module further includes: a calculation unit configured to calculate the target transportation cost of any route in the routing sub-network to be optimized at a specified time within the historical preset time period; select The unit is configured to select a route corresponding to the maximum value of the product of the sampling probability and the target transportation cost as the target route.
  • the calculation unit is further configured to: determine the original transportation cost of the route to be optimized and the transportation cost of any route in the route sub-network to be optimized at a specified time within the historical preset time period Type, according to the transportation cost type, sum the transportation costs corresponding to all transportation cost types to obtain the transportation cost of the route. Based on the original transportation cost and the transportation cost of the route, determine the target transportation cost of the route.
  • the acquisition module is further configured to: determine the corresponding original line set according to the original route to be optimized for loading; determine the corresponding alternative route according to the candidate route for optimized loading.
  • a line set determine an associated line set according to the original line set and the candidate line set.
  • the alternate routes to be optimized are obtained in the following manner: according to the original route to be optimized, the alternate routes to be optimized are screened, so that the alternate routes The service time limit of the stowage arrival site is not lower than the corresponding service time limit of the original route.
  • the present application also provides an electronic device and a readable storage medium.
  • FIG. 6 it is a block diagram of an electronic device according to a method for determining a logistics routing network according to an embodiment of the present application.
  • Electronic device 600 is a block diagram of an electronic device according to a method for determining a logistics routing network according to an embodiment of the present application.
  • Electronic device is intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other suitable computers.
  • Electronic devices may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smart phones, wearable devices, and other similar computing devices.
  • the components shown herein, their connections and relationships, and their functions, are by way of example only, and are not intended to limit implementations of the applications described and/or claimed herein.
  • the electronic device includes: one or more processors 601, a memory 602, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces.
  • the various components are interconnected using different buses and can be mounted on a common motherboard or otherwise as desired.
  • the processor may process instructions executed within the electronic device, including instructions stored in or on the memory, to display graphical information of a GUI on an external input/output device such as a display device coupled to an interface.
  • multiple processors and/or multiple buses may be used with multiple memories and multiple memories, if desired.
  • multiple electronic devices may be connected, with each device providing some of the necessary operations (eg, as a server array, a set of blade servers, or a multi-processor system).
  • a processor 601 is taken as an example.
  • the memory 602 is the non-transitory computer-readable storage medium provided in this application.
  • the memory stores instructions executable by at least one processor, so that the at least one processor executes the method for determining a logistics routing network provided in the present application.
  • the non-transitory computer-readable storage medium of the present application stores computer instructions, and the computer instructions are used to cause the computer to execute the method for determining the logistics routing network provided in the present application.
  • the memory 602 as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs, non-transitory computer-executable programs and modules, such as program instructions/modules corresponding to the logistics routing network determination method in the embodiment of the present application (eg , acquisition module 501, construction module 502 and screening module 503 shown in accompanying drawing 5).
  • the processor 601 executes various functional applications and data processing of the server by running non-transitory software programs, instructions and modules stored in the memory 602, that is, implements the method for determining the logistics routing network in the above method embodiments.
  • the memory 602 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and an application program required by at least one function; the data storage area may store data created by the use of electronic equipment determined by the logistics routing network, etc. .
  • the memory 602 may include a high-speed random access memory, and may also include a non-transitory memory, such as at least one magnetic disk storage device, a flash memory device, or other non-transitory solid-state storage devices.
  • the storage 602 may optionally include storages that are remotely located relative to the processor 601, and these remote storages may be connected to electronic devices determined by the logistics routing network through a network. Examples of the aforementioned networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.
  • the electronic equipment of the method for determining the logistics routing network may further include: an input device 603 and an output device 604 .
  • the processor 601, the memory 602, the input device 603, and the output device 604 may be connected through a bus or in other ways. In FIG. 6, connection through a bus is taken as an example.
  • the input device 603 can receive input digital or character information, such as a touch screen, a keypad, a mouse, a trackpad, a touchpad, a pointing stick, one or more mouse buttons, a trackball, a joystick and other input devices.
  • the output device 604 may include a display device, an auxiliary lighting device (eg, LED), a tactile feedback device (eg, a vibration motor), and the like.
  • the display device may include, but is not limited to, a liquid crystal display (LCD), a light emitting diode (LED) display, and a plasma display. In some implementations, the display device may be a touch screen.
  • Various implementations of the systems and techniques described herein can be implemented in digital electronic circuitry, integrated circuit systems, application specific ASICs (application specific integrated circuits), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include being implemented in one or more computer programs executable and/or interpreted on a programmable system including at least one programmable processor, the programmable processor Can be special-purpose or general-purpose programmable processor, can receive data and instruction from storage system, at least one input device, and at least one output device, and transmit data and instruction to this storage system, this at least one input device, and this at least one output device an output device.
  • machine-readable medium and “computer-readable medium” refer to any computer program product, apparatus, and/or means for providing machine instructions and/or data to a programmable processor ( For example, magnetic disks, optical disks, memories, programmable logic devices (PLDs), including machine-readable media that receive machine instructions as machine-readable signals.
  • machine-readable signal refers to any signal used to provide machine instructions and/or data to a programmable processor.
  • the systems and techniques described herein can be implemented on a computer having a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user. ); and a keyboard and pointing device (eg, a mouse or a trackball) through which a user can provide input to the computer.
  • a display device e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor
  • a keyboard and pointing device eg, a mouse or a trackball
  • Other kinds of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and can be in any form (including Acoustic input, speech input or, tactile input) to receive input from the user.
  • the systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., as a a user computer having a graphical user interface or web browser through which a user can interact with embodiments of the systems and techniques described herein), or including such backend components, middleware components, Or any combination of front-end components in a computing system.
  • the components of the system can be interconnected by any form or medium of digital data communication, eg, a communication network. Examples of communication networks include: Local Area Network (LAN), Wide Area Network (WAN) and the Internet.
  • a computer system may include clients and servers.
  • Clients and servers are generally remote from each other and typically interact through a communication network.
  • the relationship of client and server arises by computer programs running on the respective computers and having a client-server relationship to each other.
  • the volatility of data is fully considered, and the accuracy of the determined target logistics routing network is effectively improved.

Landscapes

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

Abstract

本申请公开了物流路由网络确定方法和装置，涉及物流技术领域。方法的一具体实施方式包括：获取历史预设时间段内的待优化线路的线路数据及所对应的待优化配载的配载数据，以及待优化配载对应的关联线路集合（201）；根据待优化线路的线路数据及所对应的待优化配载的配载数据，以及关联线路集合，构建历史预设时间段内的各时刻的待优化路由子网络（202）；基于目标运输成本和抽样概率，筛选出历史预设时间段内指定时刻待优化路由子网络中的目标路由，进而确定目标物流路由网络（203）。实施方式充分考虑了数据的波动性，有效提升了确定出的目标物流路由网络的准确性。

Description

物流路由网络确定方法和装置
相关申请的交叉引用
本专利申请要求于2021年11月9日提交的、申请号为202111319703.7的中国专利申请，以及2022年1月4日提交的、申请号为202210000520.7的中国专利申请的优先权，上述申请的全文以引用的方式并入本申请中。
技术领域
本申请涉及计算机技术领域，具体涉及物流技术领域，尤其涉及一种物流路由网络确定方法和装置。
背景技术
目前，考虑数据波动下的路由网络配载优化决策中主要有基于变异系数筛选稳定配载、以及基于均值的方法等。
发明内容
本申请实施例提供了一种物流路由网络确定方法、装置、设备以及存储介质。
根据第一方面，本申请实施例提供了一种物流路由网络确定方法，该方法包括：获取历史预设时间段内的待优化线路的线路数据及所对应的待优化配载的配载数据，以及待优化配载对应的关联线路集合，所述待优化线路根据业务需求确定；根据待优化线路的线路数据及所对应的待优化配载的配载数据，以及关联线路集合，构建历史预设时间段内的各时刻的待优化路由子网络；
基于目标运输成本和抽样概率，筛选出历史预设时间段内指定时刻待优化路由子网络中的目标路由，进而确定目标物流路由网络。
根据第二方面，本申请实施例提供了一种物流路由网络确定装置，该装置包括：获取模块，被配置成获取历史预设时间段内的待优化线路的线路数据及所对应的待优化配载的配载数据，以及待优化配载对 应的关联线路集合，所述待优化线路根据业务需求确定；构建模块，被配置成根据待优化线路的线路数据及所对应的待优化配载的配载数据，以及所述关联线路集合，构建历史预设时间段内的各时刻的待优化路由子网络；筛选模块，被配置成基于目标运输成本和抽样概率，筛选出历史预设时间段内指定时刻所述待优化路由子网络中的目标路由，进而确定目标物流路由网络。
根据第三方面，本申请实施例提供了一种电子设备，该电子设备包括一个或多个处理器；存储装置，其上存储有一个或多个程序，当一个或多个程序被该一个或多个处理器执行，使得一个或多个处理器实现如第一方面中任一实现方式描述的方法。
根据第四方面，本申请实施例提供了一种计算机可读介质，其上存储有计算机程序，该程序被处理器执行时实现如第一方面中任一实现方式描述的方法。
关键或重要特征，也不用于限制本申请的范围。本申请的其他特征将通过以下的说明书而变得容易理解。
附图说明
图1是本申请可以应用于其中的示例性系统架构图；
图2是根据本申请的物流路由网络确定方法的一个实施例的流程图；
图3是根据本申请的物流路由网络确定方法的一个应用场景的示意图；
图4是根据本申请的物流路由网络确定方法的又一个实施例的流程图；
图5是根据本申请的物流路由网络确定装置的一个实施例的示意图；
图6是适于用来实现本申请实施例的服务器的计算机系统的结构示意图。
具体实施方式
以下结合附图对本申请的示范性实施例做出说明，其中包括本申请实施例的各种细节以助于理解，应当将它们认为仅仅是示范性的。因此，本领域普通技术人员应当认识到，可以对这里描述的实施例做出各种改变和修改，而不会背离本申请的范围和精神。同样，为了清楚和简明，以下的描述中省略了对公知功能和结构的描述。
需要说明的是，在不冲突的情况下，本申请中的实施例及实施例中的特征可以相互组合。下面将参考附图并结合实施例来详细说明本申请。
图1示出了可以应用本申请的模型训练方法的实施例的示例性系统架构100。
如图1所示，系统架构100可以包括终端设备101、102、103，网络104和服务器105。网络104用以在终端设备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。
终端设备101、102、103通过网络104与服务器105交互，以接收或发送消息等。终端设备101、102、103上可以安装有各种通讯客户端应用，例如，通讯类应用等。
终端设备101、102、103可以是硬件，也可以是软件。当终端设备101、102、103为硬件时，可以是具有显示屏的各种电子设备，包括但不限于手机和笔记本电脑。当终端设备101、102、103为软件时，可以安装在上述所列举的电子设备中。其可以实现成多个软件或软件模块(例如用来提供物流路由网络确定服务)，也可以实现成单个软件或软件模块。在此不做具体限定。
服务器105可以是提供各种服务的服务器，例如，获取历史预设时间段内的待优化线路的线路数据及所对应的待优化配载的配载数据，以及待优化配载对应的关联线路集合；根据待优化线路的线路数据及所对应的待优化配载的配载数据，以及关联线路集合，构建历史预设时间段内的各时刻的待优化路由子网络；基于目标运输成本和抽样概率，筛选出历史预设时间段内指定时刻待优化路由子网络中的目标路由，进而确定目标物流路由网络。
需要说明的是，服务器105可以是硬件，也可以是软件。当服务器105为硬件时，可以实现成多个服务器组成的分布式服务器集群，也可以实现成单个服务器。当服务器为软件时，可以实现成多个软件或软件模块(例如用来提供物流路由网络确定服务)，也可以实现成单个软件或软件模块。在此不做具体限定。
需要指出的是，本申请的实施例所提供的模型训练方法可以由服务器105执行，也可以由终端设备101、102、103执行，还可以由服务器105和终端设备101、102、103彼此配合执行。相应地，物流路由网络确定装置包括的各个部分(例如各个单元、子单元、模块、子模块)可以全部设置于服务器105中，也可以全部设置于终端设备101、102、103中，还可以分别设置于服务器105和终端设备101、102、103中。
应该理解，图1中的终端设备、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设备、网络和服务器。
图2示出了可以应用于本申请的物流路由网络确定方法的实施例的流程示意图200。在本实施例中，物流路由网络确定方法包括以下步骤：
步骤201，获取历史预设时间段内的待优化线路的线路数据及所对应的待优化配载的配载数据，以及待优化配载对应的关联线路集合。
在本实施例中，执行主体(如图1中所示的服务器105或终端设备101、102、103)可以获取历史预设时间段内的各时刻的待优化线路的线路数据及所对应的待优化配载的配载数据，以及待优化配载对应的关联线路集合。
其中，历史预设时间段的长度可根据实际需求设定，例如，10天、30天、90天等等，本申请对此不作限定。
这里，历史预设时间段内的各时刻的待优化线路可根据业务需求确定。业务需求中包括待运输货物的起点信息和终点信息、运输总费用要求、时效要求等信息，还可以包括一些特殊需求，例如：业务方希望针对尾货进行配载优化。针对以上业务需求中的待运输货物的起 点信息和终点信息、运输总费用要求、时效要求等信息，物流网络数据库可以匹配出符合要求的路由，进而确定待优化线路。
其中，线路可以是首分拣中心到末分拣中心形成的运输路径中的一段线路。例如，从广州某分拣中心(首分拣中心)到上海某分拣中心(末分拣中心)的路径为：从广州某分拣中心到苏州某分拣中心进行中转，再从该中转站到上海对应分拣中心，而从广州某分拣中心到苏州某分拣中心的线路可以是高速线路，也可以是国道线路，还可以是部分高速线路+部分国道线路。因此，在路径确定的情况下，会出现多条匹配线路。
这里，线路数据可以包括获取待优化线路的里程信息、运力方式信息、货物方量信息、剩余载容信息和运输成本信息。待优化线路的里程信息可以包括线路编码和线路里程，在物流网络中，每条线路都设置有对应的线路编码和线路里程，在线路确定后该数据可以直接从系统读取获得。运力方式信息可以包括运力方式、线路上车辆使用数量和线路上的配载等信息，运力方式可以包括运输类型和运输工具类型，例如，运力方式为陆运和9.6m大型运输车。货物方量可以是货物的体积累计之和。剩余载容信息可以是待优化线路上对应配载的方量与当前货物方量之差。运输成本信息可以包括线路的零担均方量运输成本、不同车辆类型的整车运输成本，零担均方量运输成本可以是零担货物的每方量的运输成本。还可以获取线路类型，例如干线、支线等；还可以获取运输类型，例如公路整车、公路零担等。以上的线路数据均可以通过数据库获取。此处获取的线路数据可以在后续的路由子网络确定过程中使用。
进一步地，根据待优化线路以及线路与配载的匹配关系，确定待优化配载。对于物流网络来讲，线路上的配载是确定的，即对于整个物流网络来讲，在其数据库中对于每条线路均匹配有相应的配载，线路与配载是相互对应的。在确定了待优化线路和待优化配载之后，待优化线路的线路数据和配载数据可以从物流网络的数据库中直接读取获得。也可以采用现有的物流网络生成系统进行在线生成。
这里，配载数据可以包括不同分拣中心的配载方量信息和配载班次信息；其中，配载方量信息可以是配载的方量数据，配载班次信息可以包括配载的第一条线路编码和配载的班次；配载的班次也就是配载的发车 时间和到达时间，不同分拣中心的配载方量数据可以是配载对应线路流向上的货物方量，例如，当有多个线路流向上有该配载，则该配载数据包含每个线路流向上的该配载的方量。以上的线路数据均可以通过数据库获取。
进一步地，执行主体可以采用物流领域的串联引擎确定关联路由，串联引擎可以是根据各个分拣中心建立的串联关系表，该关系表中可以包括各分拣中心组成的路径及其配载、配载编码、班次等信息。在待优化线路较少的情况下，也可以进行人工选择设置关联路由。进而，根据关联路由确定关联线路集合。
这里，执行主体根据关联路由，确定关联线路集合的方式可以包括：若关联路由根据待优化配载对应的原路由确定，则可根据待优化配载的原路由对应的原线路集合确定关联线路集合；若关联路由根据待优化配载对应的备选路由确定，则可根据待优化配载的备选路由对应的备选线路集合确定关联线路集合；若关联路由根据待优化配载对应的备选路由和原路由确定，则可根据待优化配载的备选路由对应的备选线路集合和原路由对应的原线路集合确定关联线路集合。
在一些可选的方式中，获取待优化配载的关联线路集合，包括：根据待优化配载的原路由，确定对应的原线路集合；根据待优化配载的备选路由，确定对应的备选线路集合；根据原线路集合和备选线路集合，确定所述关联线路集合。
在本实现方式中，执行主体可以根据待优化配载的原路由，确定对应的原线路集合；可以将原路由中包含的所有线路作为原线路集合；也可以对原路由中的线路进行筛选，选取一条或若干条路由包含的线路作为原线路集合。
进一步地，根据待优化配载的备选路由，确定对应的备选线路集合；可以将备选路由中包含的所有线路作为备选线路集合；也可以对备选路由中的线路进行筛选，选取一条或若干条备选路由包含的线路作为备选线路集合，本申请对此不作限定。
最后，执行主体可以根据原线路集合和备选线路集合共同作为关联线路集合，可以将原线路集合与部分备选线路集合共同作为关联线 路集合，还可以将部分原线路集合与全部或部分备选线路集合共同作为关联路由，本申请对此不作限定。
其中，上述部分原线路集合或部分备选线路集合可以根据不同的筛选规则进行筛选获得。
在一些可选的方式中，待优化配载的备选路由通过以下方式得到：根据待优化配载的原路由，筛选得到待优化配载的备选路由，以使备选路由的配载到达站点的服务时效不低于所述原路由的相应服务时效。
在本实现方式中，原路由为未优化前的配载路由，其可以从物流网络数据库获取，也可以从路由串联引擎获取。原路由包括待优化配载的原走货路径及其包含的线路编码序列、班次等数据。与路径相比，路由携带更多信息，如线路编码序列和配载班次等信息。物流网络就是由大量路由串联形成的运输网络。备选路由通过路由串联引擎或者贪心算法筛选得到，以使备选路由的配载到达站点的服务时效不低于原路由的相应服务时效。与原路由相似，备选路由也包括备选路径及其包含的线路编码序列、班次等信息。
举例而言，采用贪心算法筛选备选路由，目标函数可以设置为起点到终点的运输成本最低，也可以设置为起点到终点的中转最少，也可以设置为起点到终点的运输车次最少，根据需要进行设置，本实施例对此不做限定；约束条件可以为备选路由的配载到达站点的服务时效不低于所述原路由的相应服务时效，也可以设置多个约束条件，例如，成本不增加、时间不增加等；再设置贪心策略即可。可以筛选一个或多个备选路由，本申请对此不作限定。
步骤202，根据待优化线路的线路数据及所对应的待优化配载的配载数据，以及关联线路集合，构建历史预设时间段内的各时刻的待优化路由子网络。
在本实施例中，执行主体可以由关联线路集合直接形成待优化线路子网络，也可以对关联线路集合中的线路进行筛选形成待优化线路子网络，本申请对此不作限定。
进一步地，执行主体根据历史预设时间段内各时刻对应的待优化 线路的线路数据和待优化配载的配载数据，对待优化线路子网络中添加相应的线路数据和配载数据，得到历史预设时间段内的相应时刻的待优化路由子网络。
其中，配载数据：包括不同分拣中心各配载的方量数据，如果有多个线路流向有该配载，则包括各线路流向上该配载的方量、配载的第一条线路编码、配载的班次等信息；线路数据可以包括线路编码、线路里程、线路类型(如干线、支线等)、运输类型(如公路零担、公路整车等)、线路上车辆使用数、货物方量、剩余载容、线路的零担单均方量运输成本、不同类型整车运输费用、线路上的配载等。
以上的待优化路由子网络和原路由网络的关系是：待优化路由子网络是在原路由网络的基础上构建的，并且配载调整只会影响待优化路由子网络上的线路货量。
此外，可以对待优化路由子网络的线路能力进行分析。首先，将待优化路由子网络的所有线路分成两类：待优化的候选线路的线路集合(简称候选线路集合)，以及所有备选路由包括的线路集合(简称备选线路集合)。由于本示例旨在通过调整配载降低成本，则是通过减少候选线路上的尾货方量，来减少零担或者降低尾货车型，同时备选线路上的剩余载容能尽可能覆盖配载方量。针对以上分析，重点在于：候选线路的货物方量和备选线路的剩余载容，以此确定子网络中线路的能力。
步骤203，基于目标运输成本和抽样概率，筛选出历史预设时间段内指定时刻待优化路由子网络中的目标路由，进而确定目标物流路由网络。
在本实施例中，执行主体可以根据抽样概率和目标运输成本构建目标函数，并根据实际需求设置约束条件，筛选出待优化路由子网络中的目标路由，进而确定目标物流路由网络。
其中，目标运输成本可以根据待优化线路的原运输成本与待优化路由子网络中任一路由的运输成本确定，抽样概率和目标运输成本与时间相关联。
这里，抽样概率用于指示指定时刻的目标运输成本的重要性。需 要指出的是，若认为预设时间段内每天的数据同样重要，则可设置抽样概率为1/T，其中T表示预设时间段的长度。
在一些可选的方式中，基于目标运输成本和抽样概率，筛选出历史预设时间段内指定时刻待优化路由子网络中的目标路由，包括：计算历史预设时间段内指定时刻待优化路由子网络中的任意一条路由的目标运输成本；选取抽样概率与目标运输成本乘积的最大值对应的一条路由作为目标路由。
在本实现方式中，执行主体可以计算预设时间段内指定时刻待优化路由子网络中的任意一条路由的目标运输成本；进而选取抽样概率与目标运输成本乘积的最大值对应的一条路由作为目标路由。
这里，若抽样概率与目标运输成本乘积出现多个并列最大，则可以随机选取或根据其他条件进行相应选取，例如，选择乘积最大且尾货最少的。
在一些可选的方式中，计算历史预设时间段内指定时刻待优化路由子网络中的任意一条路由的目标运输成本，包括：确定历史预设时间段内指定时刻的待优化线路的原运输成本和待优化路由子网络中的任意一条路由的运输成本类型；根据运输成本类型，将所有运输成本类型对应的运输成本进行求和，得到该路由的运输成本；基于原运输成本和该路由的运输成本，确定该路由的目标运输成本。
在本实现方式中，执行主体可以首先确定指定时刻的待优化线路的原运输成本和待优化路由子网络中的任意一条路由的运输成本类型。
其中，运输成本类型包括该路由中原路由上的零担线路的零担成本、该路由中原路由上的整车线路的整车成本和该路由中配载调整后的备选线路增加的零担成本。
然后，执行主体可以根据运输成本类型，将所有运输成本类型对应的运输成本进行求和，得到该路由的运输成本。
其中，运输成本类型对应的运输成本基于待优化线路的方量、待优化线路的配载方量和车辆剩余装载能力中的至少一项确定。
这里，原运输成本、待优化线路的方量、待优化线路的配载方量和车辆剩余装载能力与时间相关联。
其中，原运输成本、待优化线路的方量、待优化线路的配载方量和车辆剩余装载能力与尾货车型、尾货货量、配载方量及线路剩余装载能力相关联，而尾货车型、尾货货量、配载方量及线路剩余装载能力随时间发展具有较大的波动性。
这里，尾货车型、尾货货量、配载方量在线路优化过程中，对成本的影响主要体现在原路由线路的成本的降低：配载从原路由线路调整至备选路由线路上，原路由线路货量降低，线路上尾货车辆数减少或者尾货车型降低导致原路由线路的运输成本降低。原路由线路成本由原尾货车型决定，调整后的线路成本由调整后的尾货车型决定，调整后的尾货车型则由剩下的货物方量决定，而调整后剩下的货物方量则由原路由线路货量、待调整的配载货物方量决定。
线路剩余装载能力在线路优化过程中，对成本的影响主要体现在备选路由线路的运输成本的增加：配载从原路由线路调整至备选路由线路上，以充分利用备选路由线路的剩余装载能力。如果剩余装载能力不够，则需要增加额外的零担或者整车成本来满足配送需求。增加的成本与溢出的货量有关，而溢出的货量则由备选路由线路剩余装载能力及配载方量决定。
最后，基于原运输成本和该路由的运输成本，确定该路由的目标运输成本。
具体地，基于待优化路由子网络，可以通过构建混合整数线性规划模型以优化配载，求解目标运输成本的最大值。旨在充分利用备选线路的剩余载容，通过调整配载，能减少待优化线路上的货量。
首先，构造混合整数线性规划模型。可以将该模型的目标设为最大化目标运输成本与抽样概率的乘积。其中，目标运输成本为原运输成本与运输成本的差值运输成本主要由三部分组成：1)原零担线路的零担成本；2)原整车线路的整车成本；3)调整配载后备选线路增加的零担成本。
可选地，目标函数的混合整数线性规划模型如下：
Figure PCTCN2022115788-appb-000001
Figure PCTCN2022115788-appb-000002
Figure PCTCN2022115788-appb-000003
Figure PCTCN2022115788-appb-000004
Figure PCTCN2022115788-appb-000005
d∈D,t∈T od             ⑷
y od＝y o′d,
Figure PCTCN2022115788-appb-000006
o∈O,d∈D             ⑸
Figure PCTCN2022115788-appb-000007
d∈D                     ⑹
Figure PCTCN2022115788-appb-000008
Figure PCTCN2022115788-appb-000009
Figure PCTCN2022115788-appb-000010
y id∈{0,1},
Figure PCTCN2022115788-appb-000011
d∈D                   ⑽
λ odn∈{0,1},
Figure PCTCN2022115788-appb-000012
Figure PCTCN2022115788-appb-000013
参数说明：O表示待优化线路的首分拣中心集合，o表示集合O中的一个首分拣中心；o′表示不同于o的首分拣中心；D表示待优化线路的末分拣中心集合，d表示集合D中的一个末分拣中心；A 1表示备选线路集合，A 2表示待优化的零担线路集合，A 3表示待优化的整车线路集合；K(o)表示与o同一分拣中心但班次不同的节点集合；n表示备选路由索引，n∈N od，N od表示(o,d)线路对应的备选路由索引集合；(i,j)表示线路编码；班次不同，则编码不同；t表示时间；T od表示(o,d)线路对应的时间集合。C t表示待优化线路原运输成本；
Figure PCTCN2022115788-appb-000014
表示待优化的零担、整车线路的方量；
Figure PCTCN2022115788-appb-000015
表示备选线路剩余装载能力；
Figure PCTCN2022115788-appb-000016
表示待优化线路(i,j)上与d对应配载的货物方量；c ij表示待优化线路(i,j)上的每方量的零担成本；f(k,d ij)表示第k种车型距离为d ij的整车成本；l ij表示线路(i,j)的线路类型，可以设置l ij∈{0,1}，l ij＝1时，表示线路为干线，l ij＝0 时，表示线路为支线。θ odn(i,j)∈{0,1}表示路由(o,d)的第n条备选路由是否包含线路(i,j)，可以设置包含时该值取1，否则该值取0；η okd(i,j)∈{0,1}表示(o,k)线路上与d对应的配载的原路由是否包含线路(i,j)，可以设置包含该值取1，否则该值取0；V1、V2、V3、V4、V5分别表示第1、2、3、4、5种车型的载容，例如，5种车辆类型分别为5.2m、7.6m、9.6m、14.5m、17.5m的箱式货车。本实施例的车辆类型也可以根据实际情况进行相应设定，可以多于或少于5种，也可以设置为同型号或不同型号的车辆，本申请对此不作限定。
以上公式的参数中，还有一部分为决策变量，具体说明如下：
Figure PCTCN2022115788-appb-000017
表示待优化线路(i,j)上未被分流所剩下的货物方量；
Figure PCTCN2022115788-appb-000018
表示备选线路(i,j)上被分配的货物方量；y id∈{0,1}表示分拣中心i上的配载d是否分流至备选线路可以设置是该值取1，否则该值取0；λ odn∈{0,1}表示分拣中心o配载d是否选择第n∈N od条备选路由，可以设置包含该值取1，否则该值取0；
Figure PCTCN2022115788-appb-000019
表示调整配载后待优化的整车线路(i,j)的整车成本；
Figure PCTCN2022115788-appb-000020
表示备选线路(i,j)上剩余载量不够需要发零担的货物方量；
Figure PCTCN2022115788-appb-000021
表示备选线路(i,j)上由于原有配载调走而增加的剩余载量。需要说明的是，该模型中的直接决策变量为y id,λ odn，前者决定分拣中心的某配载是否进行调整，后者决定配载调整后调整至哪一个路由。其余决策变量为间接决策变量。
这里，模型并未对随机参数C t、
Figure PCTCN2022115788-appb-000022
的分布进行拟合分析，主要原因在于两点：1)参数之间并不独立，单独进行拟合分析不合理；2)数据量太小拟合效果不好，但是数据量太大会导致离当前时刻很远的历史数据影响数据的分布，用该分布作为未来的分布不合理。
以上模型中的约束说明：约束(1)、(3):备选线路由于剩余载量不够需要发零担的货物方量(根据业务需求确定)；约束(2):原走货路径上线路(i,j)上待优化配载的方量；约束(4):每个配载至多选择一条备选路由(业务约束)；约束(5):每个班次、每天的调整配载方案相同(业务约束)；约束(6):统计分拣中心针对不同的配载待调走的方量；约束(7):备选线路上被分配的货物方量计算方式；约束(8-9):待优化的零担、整车线路上未被调走的货物方量的计算 逻辑，保证其非负性；约束(10-11):变量类型约束；约束(12):待优化的整车线路上货量需要使用的车型所对应的整车成本约束。
进一步地，目前该方案考虑待优化线路尾货不能调整运输方式，整车运输方式成本计算与车型、里程有关，零担运输方式成本计算与货量、里程有关，如果考虑待优化线路尾货可以从整车方式调整至零担方式，可通过对约束(12)进行修改实现。
具体地，可增加如下变量：
Figure PCTCN2022115788-appb-000023
是否选择零担运输方式，
Figure PCTCN2022115788-appb-000024
是否选择车型k∈{1,…,5}的整车运输方式(例如，5种车型分别对应5.2米,7.6米,9.6米,14.5米,17.5米等5种常用车型)，
Figure PCTCN2022115788-appb-000025
零担的货量。
Figure PCTCN2022115788-appb-000026
Figure PCTCN2022115788-appb-000027
Figure PCTCN2022115788-appb-000028
Figure PCTCN2022115788-appb-000029
Figure PCTCN2022115788-appb-000030
Figure PCTCN2022115788-appb-000031
Figure PCTCN2022115788-appb-000032
约束说明：约束(13-14)为变量的类型；约束(15)为原路由线路调整配载后成本计算公式，其中c 0表示零担的单方成本，c k，k∈{1,…,5}为5种车型的成本；约束(16)限制尾货最多使用零担运输方式或者某种整车车型；约束(17)限制只有选择了零担运输方式后零担货量才能为大于零；约束(18-19)则表示货量要在所选择车型的运输能力范围内。
进一步地，该实施例也可扩展至考虑待优化线路、备选线路均可以调整车型等场景。
对于上述线性规划模型，可以使用混合整数线性规划的求解器进行求解，例如pyscipopt求解器。虽然混合整数线性规划问题为NP问题，但是在针对业务需求对构建的路由子网络进行优化后，网络规模不会太大。当待优化配载为687个时，所需要的优化时间为30分钟左右，优化耗时较少。
最后，对于上述线性规划模型，输出的结果主要包括如下信息：1)配载调整方案：配载信息(包括名称、方量、单量等)，2)配载原路由线路信息(包括线路货量、调整后线路货量、线路成本、调整后线路成本等)，3)调整后路由线路信息(包括线路货量、调整后线路货量、线路成本、调整后线路成本等)。
具体地，最终得到687个配载的优化结果为：成本节约8000元/天，优化的配载数量为89个，总优化的配载方量为204方。
继续参见图3，图3是根据本实施例的物流路由网络确定方法的应用场景的一个示意图。
在图3的应用场景中，执行主体301获取历史预设时间段内的待优化线路的线路数据302及所对应的待优化配载的配载数据303，以及待优化配载对应的关联线路集合304；根据待优化线路的线路数据及所对应的待优化配载的配载数据，以及关联线路集合，构建历史预设时间段内的各时刻的待优化路由子网络305；基于目标运输成本和抽样概率，筛选出历史预设时间段内指定时刻待优化路由子网络中的目标路由306，进而确定目标物流路由网络。
本申请物流路由网络确定方法，通过获取历史预设时间段内的待优化线路的线路数据及所对应的待优化配载的配载数据，以及待优化配载对应的关联线路集合；根据待优化线路的线路数据及所对应的待优化配载的配载数据，以及关联线路集合，构建历史预设时间段内的各时刻的待优化路由子网络；基于目标运输成本和抽样概率，筛选出历史预设时间段内指定时刻待优化路由子网络中的目标路由，进而确定目标物流路由网络，充分考虑了数据的波动性，有效提升了确定出的目标物流路由网络的准确性。
进一步参考图4，其示出了物流路由网络确定方法的又一个实施例的流程400。在本实施例中，本实施例的物流路由网络确定方法的流程400，可包括以下步骤：
步骤401，获取历史预设时间段内的待优化线路的线路数据及所对应的待优化配载的配载数据，以及待优化配载对应的关联线路集合。
在本实施例中，步骤401的实现细节和技术效果，可以参考对步骤201的描述，在此不再赘述。
步骤402，根据待优化线路的线路数据及所对应的待优化配载的配载数据，以及关联线路集合，构建历史预设时间段内的各时刻的待优化路由子网络。
在本实施例中，步骤402的实现细节和技术效果，可以参考对步骤202的描述，在此不再赘述。
步骤403，基于运输成本、抽样概率及抽样概率的权重，筛选出历史预设时间段内指定时刻待优化路由子网络中的目标路由，进而确定目标物流路由网络。
在本实施例中，执行主体可以根据抽样概率、抽样概率的权重和目标运输成本构建目标函数，并根据实际需求设置约束条件，通过最大化目标运输成本，筛选出待优化路由子网络中的目标路由，进而确定目标物流路由网络。
其中，目标运输成本用于指示原运输成本与运输成本的差值，抽样概率和目标运输成本与时间相关联。
这里，抽样概率的权重可以根据执行时刻距离当前时刻的远近确定，例如，可设定指定时刻距离当前时刻越近，则权重越大，指定时刻距离当前时刻越远，则权重越远，即认为指定时刻距离当前时刻越近，则指定时刻的数据越重要，影响越大。
本申请的上述实施例，与图2对应的实施例相比，本实施例中的物流路由网络确定方法的流程400体现了基于目标运输成本、抽样概率及抽样概率的权重，筛选出历史预设时间段内指定时刻所述待优化路由子网络中的目标路由，进而确定目标物流路由网络，进一步提升了确定出的目标物流路由网络的准确性。
进一步参考图5，作为对上述各图所示方法的实现，本申请提供了一种物流路由网络确定的一个实施例，该装置实施例与图2所示的方法实施例相对应，该装置具体可以应用于各种电子设备中。
如图5所示，本实施例的物流路由网络确定装置500包括：获取 模块501、构建模块502和筛选模块503。
其中，获取模块501，可被配置成获取历史预设时间段内的待优化线路的线路数据及所对应的待优化配载的配载数据，以及待优化配载对应的关联线路集合。
构建模块502，可被配置成根据待优化线路的线路数据及所对应的待优化配载的配载数据，以及所述关联线路集合，构建历史预设时间段内的各时刻的待优化路由子网络。
筛选模块503，可被配置成基于目标运输成本和抽样概率，筛选出历史预设时间段内指定时刻所述待优化路由子网络中的目标路由，进而确定目标物流路由网络。
在本实施例的一些可选的方式中，筛选模块进一步被配置成：基于目标运输成本、抽样概率及抽样概率的权重，筛选出历史预设时间段内指定时刻所述待优化路由子网络中的目标路由。
在本实施例的一些可选的方式中，筛选模块进一步包括：计算单元，被配置成计算所述历史预设时间段内指定时刻待优化路由子网络中的任意一条路由的目标运输成本；选取单元，被配置成选取抽样概率与目标运输成本乘积的最大值对应的一条路由作为目标路由。
在本实施例的一些可选的方式中，计算单元进一步被配置成：确定历史预设时间段内指定时刻的待优化线路的原运输成本和待优化路由子网络中的任意一条路由的运输成本类型，根据运输成本类型，将所有运输成本类型对应的运输成本进行求和，得到该路由的运输成本基于原运输成本和该路由的运输成本，确定该路由的目标运输成本。
在本实施例的一些可选的方式中，获取模块进一步被配置成：根据待优化配载的原路由，确定对应的原线路集合；根据待优化配载的备选路由，确定对应的备选线路集合；根据原线路集合和所述备选线路集合，确定关联线路集合。
在本实施例的一些可选的方式中，待优化配载的备选路由通过以下方式得到：根据待优化配载的原路由，筛选得到待优化配载的备选路由，以使备选路由的配载到达站点的服务时效不低于所述原路由的相应服务时效。
根据本申请的实施例，本申请还提供了一种电子设备和一种可读存储介质。
如图6所示，是根据本申请实施例的物流路由网络确定方法的电子设备的框图。
600是根据本申请实施例的物流路由网络确定方法的电子设备的框图。电子设备旨在表示各种形式的数字计算机，诸如，膝上型计算机、台式计算机、工作台、个人数字助理、服务器、刀片式服务器、大型计算机、和其它适合的计算机。电子设备还可以表示各种形式的移动装置，诸如，个人数字处理、蜂窝电话、智能电话、可穿戴设备和其它类似的计算装置。本文所示的部件、它们的连接和关系、以及它们的功能仅仅作为示例，并且不意在限制本文中描述的和/或者要求的本申请的实现。
如图6所示，该电子设备包括：一个或多个处理器601、存储器602，以及用于连接各部件的接口，包括高速接口和低速接口。各个部件利用不同的总线互相连接，并且可以被安装在公共主板上或者根据需要以其它方式安装。处理器可以对在电子设备内执行的指令进行处理，包括存储在存储器中或者存储器上以在外部输入/输出装置(诸如，耦合至接口的显示设备)上显示GUI的图形信息的指令。在其它实施方式中，若需要，可以将多个处理器和/或多条总线与多个存储器和多个存储器一起使用。同样，可以连接多个电子设备，各个设备提供部分必要的操作(例如，作为服务器阵列、一组刀片式服务器、或者多处理器系统)。图6中以一个处理器601为例。
存储器602即为本申请所提供的非瞬时计算机可读存储介质。其中，所述存储器存储有可由至少一个处理器执行的指令，以使所述至少一个处理器执行本申请所提供的物流路由网络确定方法。本申请的非瞬时计算机可读存储介质存储计算机指令，该计算机指令用于使计算机执行本申请所提供的物流路由网络确定方法。
存储器602作为一种非瞬时计算机可读存储介质，可用于存储非瞬时软件程序、非瞬时计算机可执行程序以及模块，如本申请实施例 中的物流路由网络确定方法对应的程序指令/模块(例如，附图5所示的获取模块501、构建模块502和筛选模块503)。处理器601通过运行存储在存储器602中的非瞬时软件程序、指令以及模块，从而执行服务器的各种功能应用以及数据处理，即实现上述方法实施例中的物流路由网络确定方法。
存储器602可以包括存储程序区和存储数据区，其中，存储程序区可存储操作系统、至少一个功能所需要的应用程序；存储数据区可存储物流路由网络确定的电子设备的使用所创建的数据等。此外，存储器602可以包括高速随机存取存储器，还可以包括非瞬时存储器，例如至少一个磁盘存储器件、闪存器件、或其他非瞬时固态存储器件。在一些实施例中，存储器602可选包括相对于处理器601远程设置的存储器，这些远程存储器可以通过网络连接至物流路由网络确定的电子设备。上述网络的实例包括但不限于互联网、企业内部网、局域网、移动通信网及其组合。
物流路由网络确定方法的电子设备还可以包括：输入装置603和输出装置604。处理器601、存储器602、输入装置603和输出装置604可以通过总线或者其他方式连接，图6中以通过总线连接为例。
输入装置603可接收输入的数字或字符信息，例如触摸屏、小键盘、鼠标、轨迹板、触摸板、指示杆、一个或者多个鼠标按钮、轨迹球、操纵杆等输入装置。输出装置604可以包括显示设备、辅助照明装置(例如，LED)和触觉反馈装置(例如，振动电机)等。该显示设备可以包括但不限于，液晶显示器(LCD)、发光二极管(LED)显示器和等离子体显示器。在一些实施方式中，显示设备可以是触摸屏。
此处描述的系统和技术的各种实施方式可以在数字电子电路系统、集成电路系统、专用ASIC(专用集成电路)、计算机硬件、固件、软件、和/或它们的组合中实现。这些各种实施方式可以包括：实施在一个或者多个计算机程序中，该一个或者多个计算机程序可在包括至少一个可编程处理器的可编程系统上执行和/或解释，该可编程处理器可以是专用或者通用可编程处理器，可以从存储系统、至少一个输入装置、和至少一个输出装置接收数据和指令，并且将数据和指令传输至 该存储系统、该至少一个输入装置、和该至少一个输出装置。
这些计算程序(也称作程序、软件、软件应用、或者代码)包括可编程处理器的机器指令，并且可以利用高级过程和/或面向对象的编程语言、和/或汇编/机器语言来实施这些计算程序。如本文使用的，术语“机器可读介质”和“计算机可读介质”指的是用于将机器指令和/或数据提供给可编程处理器的任何计算机程序产品、设备、和/或装置(例如，磁盘、光盘、存储器、可编程逻辑装置(PLD))，包括，接收作为机器可读信号的机器指令的机器可读介质。术语“机器可读信号”指的是用于将机器指令和/或数据提供给可编程处理器的任何信号。
为了提供与用户的交互，可以在计算机上实施此处描述的系统和技术，该计算机具有：用于向用户显示信息的显示装置(例如，CRT(阴极射线管)或者LCD(液晶显示器)监视器)；以及键盘和指向装置(例如，鼠标或者轨迹球)，用户可以通过该键盘和该指向装置来将输入提供给计算机。其它种类的装置还可以用于提供与用户的交互；例如，提供给用户的反馈可以是任何形式的传感反馈(例如，视觉反馈、听觉反馈、或者触觉反馈)；并且可以用任何形式(包括声输入、语音输入或者、触觉输入)来接收来自用户的输入。
可以将此处描述的系统和技术实施在包括后台部件的计算系统(例如，作为数据服务器)、或者包括中间件部件的计算系统(例如，应用服务器)、或者包括前端部件的计算系统(例如，具有图形用户界面或者网络浏览器的用户计算机，用户可以通过该图形用户界面或者该网络浏览器来与此处描述的系统和技术的实施方式交互)、或者包括这种后台部件、中间件部件、或者前端部件的任何组合的计算系统中。可以通过任何形式或者介质的数字数据通信(例如，通信网络)来将系统的部件相互连接。通信网络的示例包括：局域网(LAN)、广域网(WAN)和互联网。
计算机系统可以包括客户端和服务器。客户端和服务器一般远离彼此并且通常通过通信网络进行交互。通过在相应的计算机上运行并且彼此具有客户端-服务器关系的计算机程序来产生客户端和服务器的关系。
根据本申请实施例的技术方案，充分考虑了数据的波动性，有效提升了确定出的目标物流路由网络的准确性。
应该理解，可以使用上面所示的各种形式的流程，重新排序、增加或删除步骤。例如，本发申请中记载的各步骤可以并行地执行也可以顺序地执行也可以不同的次序执行，只要能够实现本申请公开的技术方案所期望的结果，本文在此不进行限制。
上述具体实施方式，并不构成对本申请保护范围的限制。本领域技术人员应该明白的是，根据设计要求和其他因素，可以进行各种修改、组合、子组合和替代。任何在本申请的精神和原则之内所作的修改、等同替换和改进等，均应包含在本申请保护范围之内。

Claims (14)

  1. 一种物流路由网络确定方法，所述方法包括：
    获取历史预设时间段内的待优化线路的线路数据及所对应的待优化配载的配载数据，以及所述待优化配载对应的关联线路集合，所述待优化线路根据业务需求确定；
    根据所述待优化线路的线路数据及所对应的待优化配载的配载数据，以及所述关联线路集合，构建历史预设时间段内的各时刻的待优化路由子网络；
    基于目标运输成本和抽样概率，筛选出历史预设时间段内指定时刻所述待优化路由子网络中的目标路由，进而确定目标物流路由网络。
  2. 根据权利要求1所述的方法，其中，所述基于目标运输成本和抽样概率，筛选出历史预设时间段内指定时刻所述待优化路由子网络中的目标路由，包括：
    基于目标运输成本、抽样概率及抽样概率的权重，筛选出历史预设时间段内指定时刻所述待优化路由子网络中的目标路由。
  3. 根据权利要求1所述的方法，其中，所述基于目标运输成本和抽样概率，筛选出历史预设时间段内指定时刻所述待优化路由子网络中的目标路由，包括：
    计算所述历史预设时间段内指定时刻待优化路由子网络中的任意一条路由的目标运输成本；
    选取抽样概率与目标运输成本乘积的最大值对应的一条路由作为目标路由。
  4. 根据权利要求3所述的方法，其中，所述计算历史预设时间段内指定时刻待优化路由子网络中的任意一条路由的目标运输成本，包括：
    确定所述历史预设时间段内指定时刻的待优化线路的原运输成本 和待优化路由子网络中的任意一条路由的运输成本类型，其中，所述运输成本类型包括该路由中原路由上的零担线路的零担成本、该路由中原路由上的整车线路的整车成本和该路由中配载调整后的备选线路增加的零担成本，所述原运输成本与时间相关联；
    根据所述运输成本类型，将所有运输成本类型对应的运输成本进行求和，得到该路由的运输成本，其中，所述运输成本类型对应的运输成本基于待优化线路的方量、待优化线路的配载方量和车辆剩余装载能力中的至少一项确定，所述待优化线路的方量、所述待优化线路的配载方量和所述车辆剩余装载能力与时间相关联；
    基于所述原运输成本和所述该路由的运输成本，确定该路由的目标运输成本。
  5. 根据权利要求1所述的方法，其中，所述获取待优化配载对应的关联线路集合，包括：
    根据所述待优化配载的原路由，确定对应的原线路集合；
    根据所述待优化配载的备选路由，确定对应的备选线路集合；
    根据所述原线路集合和所述备选线路集合，确定关联线路集合。
  6. 根据权利要求5所述的方法，其中，所述待优化配载的备选路由通过以下方式得到：
    根据所述待优化配载的原路由，筛选得到所述待优化配载的备选路由，以使备选路由的配载到达站点的服务时效不低于所述原路由的相应服务时效。
  7. 一种物流路由网络确定装置，包括：
    获取模块，被配置成获取历史预设时间段内的待优化线路的线路数据及所对应的待优化配载的配载数据，以及所述待优化配载对应的关联线路集合，所述待优化线路根据业务需求确定；
    构建模块，被配置成根据所述待优化线路的线路数据及所对应的待优化配载的配载数据，以及所述关联线路集合，构建历史预设时间 段内的各时刻的待优化路由子网络；
    筛选模块，被配置成基于目标运输成本和抽样概率，筛选出历史预设时间段内指定时刻所述待优化路由子网络中的目标路由，进而确定目标物流路由网络。
  8. 根据权利要求7所述的装置，其中，所述筛选模块进一步被配置成：
    基于目标运输成本、抽样概率及抽样概率的权重，筛选出历史预设时间段内指定时刻所述待优化路由子网络中的目标路由。
  9. 根据权利要求7所述的装置，其中，所述筛选模块进一步包括：
    计算单元，被配置成计算所述历史预设时间段内指定时刻待优化路由子网络中的任意一条路由的目标运输成本；选取单元，被配置成选取抽样概率与目标运输成本乘积的最大值对应的一条路由作为目标路由。
  10. 根据权利要求9所述的装置，其中，所述计算单元进一步被配置成：
    确定所述历史预设时间段内指定时刻的待优化线路的原运输成本和待优化路由子网络中的任意一条路由的运输成本类型，其中，所述运输成本类型包括该路由中原路由上的零担线路的零担成本、该路由中原路由上的整车线路的整车成本和该路由中配载调整后的备选线路增加的零担成本，所述原运输成本与时间相关联；
    根据所述运输成本类型，将所有运输成本类型对应的运输成本进行求和，得到该路由的运输成本，其中，所述运输成本类型对应的运输成本基于待优化线路的方量、待优化线路的配载方量和车辆剩余装载能力中的至少一项确定，所述待优化线路的方量、所述待优化线路的配载方量和所述车辆剩余装载能力与时间相关联；
    基于所述原运输成本和所述该路由的运输成本，确定该路由的目标运输成本。
  11. 根据权利要求7所述的装置，其中，所述获取模块进一步被配置成：
    根据所述待优化配载的原路由，确定对应的原线路集合；
    根据所述待优化配载的备选路由，确定对应的备选线路集合；
    根据所述原线路集合和所述备选线路集合，确定关联线路集合。
  12. 根据权利要求11所述的装置，其中，所述待优化配载的备选路由通过以下方式得到：
    根据所述待优化配载的原路由，筛选得到所述待优化配载的备选路由，以使备选路由的配载到达站点的服务时效不低于所述原路由的相应服务时效。
  13. 一种电子设备，其特征在于，包括：
    至少一个处理器；以及
    与所述至少一个处理器通信连接的存储器；其中，
    所述存储器存储有可被所述至少一个处理器执行，以使所述至少一个处理器能够执行权利要求1-6中任一项所述的方法。
  14. 一种存储有计算机指令的非瞬时计算机可读存储介质，其特征在于，所述计算机指令用于使所述计算机执行权利要求1-6中任一项所述的方法。
PCT/CN2022/115788 2021-11-09 2022-08-30 物流路由网络确定方法和装置 WO2023082782A1 (zh)

Applications Claiming Priority (4)

Application Number Priority Date Filing Date Title
CN202111319703.7 2021-11-09
CN202111319703 2021-11-09
CN202210000520.7 2022-01-04
CN202210000520.7A CN114240001B (zh) 2021-11-09 2022-01-04 物流路由网络确定方法和装置

Publications (1)

Publication Number Publication Date
WO2023082782A1 true WO2023082782A1 (zh) 2023-05-19

Family

ID=80745581

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/115788 WO2023082782A1 (zh) 2021-11-09 2022-08-30 物流路由网络确定方法和装置

Country Status (2)

Country Link
CN (1) CN114240001B (zh)
WO (1) WO2023082782A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117114560A (zh) * 2023-10-25 2023-11-24 中科云谷科技有限公司 用于确定物品运输路径的方法、装置、存储介质及处理器

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114240001B (zh) * 2021-11-09 2024-06-18 北京京东振世信息技术有限公司 物流路由网络确定方法和装置
CN115660244B (zh) * 2022-12-27 2023-09-01 北京京东振世信息技术有限公司 路线信息生成方法、装置、设备和介质

Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101673382A (zh) * 2009-10-21 2010-03-17 北京交通大学 一种农资连锁经营物流配送配载组合优化方法
CN106600180A (zh) * 2016-11-04 2017-04-26 中联物流（中国）有限公司 物流管理系统的运输路径优化方法和系统
CN110826951A (zh) * 2018-08-10 2020-02-21 北京京东尚科信息技术有限公司 运输线路配载方法、装置、电子设备及计算机可读介质
US20200327497A1 (en) * 2019-04-11 2020-10-15 Federal Express Corporation System and method for linehaul optimization
CN113077103A (zh) * 2021-04-16 2021-07-06 北京京东振世信息技术有限公司 运输网络规划方法和装置
CN113255950A (zh) * 2020-02-11 2021-08-13 北京京东振世信息技术有限公司 一种优化物流网络的方法和装置
CN113379102A (zh) * 2021-05-20 2021-09-10 浙江百世技术有限公司 一种多网干线运输优化方法、计算机设备及存储介质
CN113408775A (zh) * 2020-07-31 2021-09-17 上海中通吉网络技术有限公司 基于物流网络的路由规划方法、装置、设备和存储介质
CN113408836A (zh) * 2020-03-16 2021-09-17 北京京东振世信息技术有限公司 物流路由评估方法及装置、存储介质、电子设备
CN114240001A (zh) * 2021-11-09 2022-03-25 北京京东振世信息技术有限公司 物流路由网络确定方法和装置

Family Cites Families (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8886453B2 (en) * 2008-12-11 2014-11-11 Telogis, Inc. System and method for efficient routing on a network in the presence of multiple-edge restrictions and other constraints
KR20110052054A (ko) * 2009-11-12 2011-05-18 부산대학교 산학협력단 운송 물류 네트워크 관리 시스템 및 그 방법
KR20120100601A (ko) * 2011-03-04 2012-09-12 주식회사 한국무역정보통신 스마트 물류네트워크의 최적화시스템
CN103854072B (zh) * 2014-03-17 2017-12-12 湖南工学院 用于路径选择的处理方法及系统
US20160048802A1 (en) * 2014-08-13 2016-02-18 Tianyu Luwang Transportation planning for a regional logistics network
CN108921362B (zh) * 2018-08-02 2021-02-19 顺丰科技有限公司 一种医药干线优化方法、系统、设备及存储介质
CN109816147B (zh) * 2018-12-26 2023-01-03 深圳市北斗智能科技有限公司 一种航空货运路由规划方法、装置、设备和存储介质
CN111340318B (zh) * 2020-05-22 2020-11-17 深圳市城市交通规划设计研究中心股份有限公司 一种车辆动态调度方法、装置及终端设备
CN112288232B (zh) * 2020-09-29 2024-03-29 深圳市跨越新科技有限公司 干线网点的货物运输批次规划方法及系统

Patent Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101673382A (zh) * 2009-10-21 2010-03-17 北京交通大学 一种农资连锁经营物流配送配载组合优化方法
CN106600180A (zh) * 2016-11-04 2017-04-26 中联物流（中国）有限公司 物流管理系统的运输路径优化方法和系统
CN110826951A (zh) * 2018-08-10 2020-02-21 北京京东尚科信息技术有限公司 运输线路配载方法、装置、电子设备及计算机可读介质
US20200327497A1 (en) * 2019-04-11 2020-10-15 Federal Express Corporation System and method for linehaul optimization
CN113255950A (zh) * 2020-02-11 2021-08-13 北京京东振世信息技术有限公司 一种优化物流网络的方法和装置
CN113408836A (zh) * 2020-03-16 2021-09-17 北京京东振世信息技术有限公司 物流路由评估方法及装置、存储介质、电子设备
CN113408775A (zh) * 2020-07-31 2021-09-17 上海中通吉网络技术有限公司 基于物流网络的路由规划方法、装置、设备和存储介质
CN113077103A (zh) * 2021-04-16 2021-07-06 北京京东振世信息技术有限公司 运输网络规划方法和装置
CN113379102A (zh) * 2021-05-20 2021-09-10 浙江百世技术有限公司 一种多网干线运输优化方法、计算机设备及存储介质
CN114240001A (zh) * 2021-11-09 2022-03-25 北京京东振世信息技术有限公司 物流路由网络确定方法和装置

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117114560A (zh) * 2023-10-25 2023-11-24 中科云谷科技有限公司 用于确定物品运输路径的方法、装置、存储介质及处理器
CN117114560B (zh) * 2023-10-25 2024-01-05 中科云谷科技有限公司 用于确定物品运输路径的方法、装置、存储介质及处理器

Also Published As

Publication number Publication date
CN114240001B (zh) 2024-06-18
CN114240001A (zh) 2022-03-25

Similar Documents

Publication Publication Date Title
WO2023082782A1 (zh) 物流路由网络确定方法和装置
CN110555640B (zh) 路由规划的方法和装置
CN105630984A (zh) 一种运价搜索系统
CN113988720B (zh) 分流路径生成方法、装置、电子设备和计算机可读介质
US20210239486A1 (en) Method and apparatus for predicting destination, electronic device and storage medium
CN113259144B (zh) 一种仓储网络规划方法和装置
CN110737849B (zh) 出行方案的推荐方法、装置、设备及存储介质
CN104426767A (zh) 基于路由距离和容量的路由选择的方法和系统
CN113240175B (zh) 配送路线的生成方法、设备、存储介质和程序产品
Cheng et al. The impacts of port governance reform on port competition in China
WO2023082724A1 (zh) 物流路由网络确定方法及装置、电子设备
CN114428907A (zh) 信息搜索方法、装置、电子设备及存储介质
Qian et al. Region division in logistics distribution with a two-stage optimization algorithm
CN113255950B (zh) 一种优化物流网络的方法和装置
CN113408836B (zh) 物流路由评估方法及装置、存储介质、电子设备
US9111213B2 (en) Method for constructing a tree of linear classifiers to predict a quantitative variable
CN117455188A (zh) 货运平台供需匹配方法、装置及电子设备
CN113128820A (zh) 评估仓库调整计划的方法、装置、设备和计算机可读介质
CN115412401B (zh) 训练虚拟网络嵌入模型及虚拟网络嵌入的方法和装置
CN115660244A (zh) 路线信息生成方法、装置、设备和介质
CN112116120A (zh) 物流路径规划方法和装置
CN113077199A (zh) 一种确定配送路线的方法和装置
Yi et al. Evaluation of information service in smart scenic area based on “SEM-ANP” synthetic evaluation mode
CN117609341B (zh) 一种电网的数字孪生系统
CN114440918B (zh) 一种充电桩导航方法、装置、电子设备及自动驾驶车辆

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: 22891587

Country of ref document: EP

Kind code of ref document: A1