Self-operation and crowdsourcing transport capacity integrated distribution method for e-commerce orders and electronic equipment

Abstract

The invention provides an e-commerce order self-operation and crowdsourcing transport capacity integrated distribution method and electronic equipment. The method comprises the steps of obtaining a to-be-allocated order set, a commodity set, inventory data, transport capacity data and time window data of an e-commerce platform; constructing a cost optimization model of the to-be-allocated order set, wherein the cost optimization model comprises a front transport capacity cost parameter, a self-operation transport capacity cost parameter and a crowdsourcing transport capacity cost parameter; determining a decision variable and a target constraint condition of the cost optimization model; based on the to-be-allocated order set, the commodity set, the inventory data, the transport capacity data and the target constraint condition, solving a decision variable of the cost optimization model to obtain a target variable value of the decision variable; and outputting a target allocation strategy of the to-be-allocated order set based on the target variable value of the decision variable. According to the invention, the overall timeliness of the order set can be improved, the overall delivery cost is reduced, and the order timeliness default problem is reduced.

Description

Technical Field

[0001] This application relates to the field of digital scheduling and processing technology, specifically to a method and electronic device for the integrated allocation of self-operated and crowdsourced transportation capacity for e-commerce orders. Background Technology

[0002] With the development of e-commerce and instant retail, sellers' demand for time-sensitive delivery services such as "same-day delivery" and "next-day delivery" continues to increase. However, e-commerce platforms experience significant fluctuations in order volume between off-peak and peak periods, making it difficult for self-operated transportation capacity to simultaneously balance off-peak costs and peak-peak delivery timeliness. This results in heavy fulfillment pressure during peak periods and idle capacity and wasted resources during off-peak periods.

[0003] In related technologies, a crowdsourced delivery model is introduced, in which self-operated and crowdsourced delivery capabilities collaborate to complete delivery services, in order to address to some extent the problems of high delivery service fulfillment pressure during peak periods and idle capacity and resource waste during off-peak periods. However, the inventors of this application discovered during the actual research and development process that, because self-operated and crowdsourced delivery capabilities in related technologies are usually allocated orders relatively independently, order data lacks unified allocation and synchronization constraints between self-operated and crowdsourced delivery capabilities, ultimately resulting in low overall timeliness of order data and high overall delivery costs. Summary of the Invention

[0004] This application provides a method and electronic device for integrating and allocating self-operated and crowdsourced delivery capacity for e-commerce orders, which can improve the overall timeliness of order sets, reduce overall delivery costs, and reduce order timeliness default issues.

[0005] In a first aspect, this application provides a method for integrating and allocating self-operated and crowdsourced delivery capacity for e-commerce orders, the method comprising:

[0006] Obtain the set of orders to be assigned, the set of goods, inventory data, transportation capacity data, and time window data from the e-commerce platform. The transportation capacity data includes the forward transportation capacity data of each forward warehouse. Data on the self-operated transportation capacity of each distribution center Hezhongbao Transportation Capacity Data The inventory data includes the inventory of each product in each forward warehouse, and the product set is the set of products involved in the set of orders to be allocated;

[0007] Construct a cost optimization model for the set of orders to be assigned, wherein the cost optimization model includes upfront transportation cost parameters, self-operated transportation cost parameters, and crowdsourced transportation cost parameters, and the crowdsourced transportation cost parameters include crowdsourced transportation cost, crowdsourced loading capacity cost, and crowdsourced time cost;

[0008] Determine the decision variables and objective constraints of the cost optimization model, wherein the decision variables include the preceding route variables. Self-operated route variables Crowdsourcing route variables Crowdsourcing membership variables Self-operated transshipment variables Crowdsourcing transfer variables Pre-set start time variable Self-operated start time variable Crowdsourcing start time variable The target constraints include time constraints based on the time window data, a first constraint on pre-positioned capacity, a second constraint on self-operated capacity, and a third constraint on crowdsourced capacity.

[0009] Based on the set of orders to be assigned, the set of goods, the inventory data, the transportation capacity data, and the target constraints, the decision variables of the cost optimization model are solved to obtain the target variable values ​​of the decision variables;

[0010] Based on the target variable value of the decision variable, the target allocation strategy of the set of orders to be allocated is output.

[0011] Secondly, this application also provides an electronic device, which includes a processor and a memory, wherein the memory stores a computer program, and when the processor calls the computer program in the memory, it executes any of the self-operated and crowdsourced delivery capacity integration and allocation methods for e-commerce orders provided in this application.

[0012] Thirdly, this application also provides a computer-readable storage medium having a computer program stored thereon, the computer program being loaded by a processor to execute the self-operated and crowdsourced transportation capacity integration and allocation method for e-commerce orders.

[0013] In this application, firstly, by simultaneously including both self-operated capacity cost parameters and crowdsourced capacity cost parameters in the same cost optimization model, self-operated capacity and crowdsourced capacity can be considered as a whole cost, and by constructing decision variables that simultaneously include prior route variables. Self-operated route variables Crowdsourcing route variables This approach allows for synchronized planning of the entire delivery chain, with upstream transportation capacity serving as transshipment and delivery resources, and self-operated and crowdsourced capacity simultaneously serving as end-of-chain delivery resources. This enables the overall planning of self-operated and crowdsourced capacity as end-of-chain delivery resources, reducing the problems of lower overall timeliness and higher overall delivery costs caused by independent planning of self-operated and crowdsourced capacity. Secondly, by constructing time window constraints using time window data, the overall delivery timeliness of the entire chain meets the service time window requirements of customer orders, reducing order timeliness breaches (such as orders not meeting the "same-day delivery" or "next-day delivery" requirements). Thirdly, by constructing cost parameters for upstream transportation capacity, self-operated capacity, and crowdsourced capacity through a cost optimization model, the costs of upstream transshipment and delivery resources and end-of-chain delivery resources can be controlled to some extent. Fourthly, by using upstream route variables... Self-operated route variables Crowdsourcing route variables Crowdsourcing membership variables Self-operated transshipment variables Crowdsourcing transfer variables Pre-set start time variable Self-operated start time variable Crowdsourcing start time variable The target variable values ​​of decision variables are used to plan the target allocation strategy, enabling the allocation of orders to be assigned to simultaneously complete the allocation of front-end warehouse inventory, front-end delivery resources and time (i.e., the allocation of loading orders and service start times for front-end transportation capacity), and last-mile delivery resources and time (i.e., the allocation of loading orders and service start times for self-operated and crowdsourced transportation capacity) as a whole. This achieves integrated planning of all tasks in the delivery chain, thereby further optimizing the overall timeliness and cost of the allocation strategy. Therefore, this application can improve the overall timeliness of order sets, reduce overall delivery costs, and mitigate order timeliness default issues. Attached Figure Description

[0014] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0015] Figure 1 This is a schematic block diagram of the structure of an electronic device provided in an embodiment of this application;

[0016] Figure 2 This is a flowchart illustrating a method for integrating and allocating self-operated and crowdsourced transportation capacity for e-commerce orders, as provided in an embodiment of this application.

[0017] Figure 3 This is an illustrative diagram of the delivery chain in an embodiment of this application;

[0018] Figure 4 This is a schematic flowchart of one embodiment of step 204 in this application;

[0019] Figure 5 This is a schematic flowchart of an embodiment of step 205 in this application;

[0020] Figure 6 This is a flowchart illustrating another embodiment of step 205 in this application. Detailed Implementation

[0021] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0022] The flowchart shown in the attached diagram is for illustrative purposes only and does not necessarily include all content and operations / steps, nor does it necessarily have to be performed in the order described. For example, some operations / steps can be broken down, combined, or partially merged, so the actual execution order may change depending on the actual situation.

[0023] In the description of the embodiments of this application, it should be understood that the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Therefore, features defined with "first" and "second" may explicitly or implicitly include one or more of the stated features. In the description of the embodiments of this application, "multiple" means two or more, unless otherwise explicitly specified.

[0024] To enable any person skilled in the art to implement and use this application, the following description is provided. In this description, details are set forth for purposes of explanation. It should be understood that those skilled in the art will recognize that this application can be implemented without using these specific details. In other instances, well-known processes will not be described in detail to avoid obscuring the description of the embodiments of this application with unnecessary detail. Therefore, this application is not intended to be limited to the embodiments shown, but is consistent with the broadest scope of the principles and features disclosed in the embodiments of this application.

[0025] This application provides a method for integrating and allocating self-operated and crowdsourced delivery capacity for e-commerce orders, an electronic device, and a computer-readable storage medium. The electronic device can be a mobile phone, computer, etc.

[0026] The following detailed description of some embodiments of this application is provided in conjunction with the accompanying drawings. Unless otherwise specified, the following embodiments and features can be combined with each other.

[0027] Figure 1 This is a schematic block diagram of the structure of an electronic device provided in an embodiment of this application.

[0028] like Figure 1 As shown, the electronic device 100 includes a processor 101 and a memory 102, which are connected by a bus 103, such as a PCIe (Peripheral Component Interconnect Express) bus.

[0029] Specifically, processor 101 provides computing and control capabilities to support the operation of the entire electronic device 100. Processor 101 can be a Central Processing Unit (CPU), but it can also be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor.

[0030] Specifically, the memory 102 can be a Flash chip, a read-only memory (ROM) disk, an optical disk, a USB flash drive, or a portable hard drive, etc.

[0031] Those skilled in the art will understand that Figure 1 The structures shown are merely block diagrams of some structures related to the embodiments of this application and do not constitute a limitation on the electronic devices to which the embodiments of this application are applied. Specific electronic devices may include more or fewer components than those shown in the figures, or combine certain components, or have different component arrangements.

[0032] The processor 101 is configured to run a computer program stored in the memory 102, and when executing the computer program, implement any of the self-operated and crowdsourced delivery capacity integration and allocation methods for e-commerce orders provided in this application embodiment. For example, the processor 101 is configured to run a computer program stored in the memory 102, and when executing the computer program, it can implement the following steps:

[0033] Obtain the set of orders to be assigned, the set of goods, inventory data, transportation capacity data, and time window data from the e-commerce platform. The transportation capacity data includes the forward transportation capacity data of each forward warehouse. Data on the self-operated transportation capacity of each distribution center Hezhongbao Transportation Capacity Data The inventory data includes the inventory of each product in each forward warehouse, and the product set is the set of products involved in the set of orders to be allocated;

[0034] Construct a cost optimization model for the set of orders to be assigned, wherein the cost optimization model includes upfront transportation cost parameters, self-operated transportation cost parameters, and crowdsourced transportation cost parameters, and the crowdsourced transportation cost parameters include crowdsourced transportation cost, crowdsourced loading capacity cost, and crowdsourced time cost;

[0035] Determine the decision variables and objective constraints of the cost optimization model, wherein the decision variables include the preceding route variables. Self-operated route variables Crowdsourcing route variables Crowdsourcing membership variables Self-operated transshipment variables Crowdsourcing transfer variables Pre-set start time variable Self-operated start time variable Crowdsourcing start time variable The target constraints include time constraints based on the time window data, a first constraint on pre-positioned capacity, a second constraint on self-operated capacity, and a third constraint on crowdsourced capacity.

[0036] Based on the set of orders to be assigned, the set of goods, the inventory data, the transportation capacity data, and the target constraints, the decision variables of the cost optimization model are solved to obtain the target variable values ​​of the decision variables;

[0037] Based on the target variable value of the decision variable, the target allocation strategy of the set of orders to be allocated is output.

[0038] It should be noted that those skilled in the art will understand that, for the sake of convenience and brevity, the specific working process of the electronic device described above can be referred to the corresponding process in the following embodiment of the self-operated and crowdsourced transportation capacity integration and allocation method for e-commerce orders, and will not be repeated here.

[0039] The following will be based on Figure 1 Taking the electronic device shown as the execution subject of the self-operated and crowdsourced transportation capacity integration and allocation method for e-commerce orders as an example, the self-operated and crowdsourced transportation capacity integration and allocation method for e-commerce orders provided in this application embodiment will be described in detail. For the sake of simplification and ease of description, the execution subject will be omitted in the subsequent method embodiments.

[0040] Please see Figure 2 , Figure 2 This is a flowchart illustrating a method for integrating and allocating self-operated and crowdsourced delivery capacity for e-commerce orders, as provided in an embodiment of this application. The method includes steps 201-205, wherein:

[0041] 201. Obtain the set of pending orders, the set of goods, inventory data, shipping capacity data, and time window data from the e-commerce platform.

[0042] To better understand the embodiments of this application, please refer to Figure 3 The following section introduces some of the names involved in the embodiments of this application:

[0043] 1. Delivery Chain: This refers to the delivery chain of an order, which sequentially passes through nodes such as a forward warehouse, a distribution center, and the customer, thus enabling the order to be delivered from the forward warehouse to the customer after it is placed (e.g., after an order is placed on an e-commerce platform). Figure 3 As shown.

[0044] 2. Front warehouse (FC): Used for storing goods and can complete the packaging of a single order.

[0045] 3. Distribution Center (DC): Used to receive orders from the forward warehouse and complete the transfer to the customer.

[0046] 4. Pre-positioning capacity (CT, also known as transshipment capacity): Capacity (such as city trucks) used to transfer orders between pre-positioning warehouses and distribution centers. Figure 3 As shown.

[0047] Pre-positioned delivery (also known as transshipment delivery): The transfer of orders between pre-positioned warehouses and distribution centers.

[0048] 5. Last-mile delivery capacity: This refers to the transportation capacity used to fulfill the task of transporting orders between the distribution center and the customer (specifically including the transportation of orders from the distribution center to customers and the delivery of orders to customers). In this embodiment, last-mile delivery includes self-operated capacity and crowdsourced capacity, such as... Figure 3 As shown.

[0049] Last-mile delivery: The transportation and delivery of orders between the distribution center and the customer.

[0050] Self-operated capacity (UV): Self-owned capacity (such as the vehicles owned by the distribution center DC) used to fulfill the task of transporting orders between the distribution center and the customer.

[0051] Crowdsourced delivery (CDP): Third-party individuals / groups of delivery personnel who undertake and complete last-mile delivery tasks on a per-order basis.

[0052] 6. EOFP-CDP (E-commerce Order Fulfillment Problem with CDPs): This refers to the problem of integrating CDPs into the self-operated fulfillment chain in the online retail scenario to collaboratively optimize order transfer, capacity allocation, and route scheduling.

[0053] 7. Involves sets:

[0054] The collection of orders awaiting delivery and allocation (denoted as...) ): This represents a collection of all orders to be shipped, where each order contains one or more product categories.

[0055] Pre-position warehouse collection (denoted as ): represents the set of all pre-positioned warehouses.

[0056] Distribution center assembly (denoted as ): This represents the collection of all distribution centers.

[0057] Pre-positioned transport capacity (denoted as) ): represents the set of all preceding transport capacity.

[0058] Self-operated operational capacity (denoted as...) ): represents the collection of all self-operated capacity.

[0059] Crowdsourced transportation capacity aggregation (denoted as ): represents the collection of all crowdsourced transportation capacity.

[0060] 8. Parameters involved:

[0061] The EOFP-CDP problem is defined in a directed network. Above, where the set of nodes is The set A of arcs contains four subsets.

[0062] A1: Represents the arc connecting FC and DC.

[0063] A2: Represents an arc connecting any two distribution centers.

[0064] A3: Represents the arc connecting the distribution center and the customer.

[0065] A4 represents the arc connecting the client.

[0066] definition and Let K represent the set of nodes and the set of arcs that vehicle K can access, respectively.

[0067] : Indicates entering the node The set of all arcs;

[0068] : Indicates leaving the node The set of all arcs.

[0069] : Indicates that vehicle k is from node To the node Transportation costs.

[0070] : Indicates that vehicle k is from node To the node The transit time. Transit time is directly proportional to transit cost.

[0071] : indicates at node The service time corresponds to the order's transit time.

[0072] : is a very large constant.

[0073] : Represents the total inventory of product p in the forward warehouse FC.

[0074] : indicates an order Required product categories A set of.

[0075] : indicates an order Chinese commodities The demand is so high that the goods in the order cannot be further broken down; it must be fulfilled by one FC and delivered by one UV or CDP.

[0076] This represents the set of all product categories p offered by an online retailer.

[0077] Indicates goods Required loading capacity per unit.

[0078] and , representing the pre-positioned capacity set and the self-operated capacity set, respectively.

[0079] This represents the set of DCs to which CDP k can belong.

[0080] and These represent the fixed costs of CT and UV, respectively.

[0081] , and These represent the loading capacity of k in CT, UV, and CDP, respectively.

[0082] Number The set of all CTs to which the FC belongs is denoted as .

[0083] DC The set of all UVs belonging to a given group is denoted as .

[0084] This represents the set of all CDPs.

[0085] 9. Decision variables:

[0086] Pre-route variables : Represents the set of preceding transportation capacity Does the preceding transport capacity k1 travel along the arc (i,j)? For example, =1 indicates that the preceding transport capacity k1 travels along the arc (i,j). =0 indicates that the preceding transport capacity k1 does not travel along the arc (i,j).

[0087] Self-operated route variables : Represents the collection of self-operated operating capacity Does the self-operated capacity k2 travel along the arc (i,j)? For example, =1 indicates that the self-operated transport capacity k2 travels along the arc (i,j). =0 indicates that the self-operated transport force k2 does not travel along the arc (i,j).

[0088] Crowdsourced route variables : Indicates the aggregation of crowdsourced transportation capacity Does the crowdsourced transportation capacity k2 travel along the arc (i,j)? For example, =1 indicates that the crowdsourced transportation capacity k3 travels along the arc (i,j). =0 indicates that the crowdsourced transportation capacity k3 does not travel along the arc (i,j).

[0089] Crowdsourcing membership variable : Indicates whether the crowdsourced delivery capacity k3 belongs to the distribution center collection. Distribution center i in the middle. For example, =1 indicates that the crowdsourced delivery capacity k3 belongs to the distribution center set. Distribution center i in the middle, =0 indicates that the crowdsourced delivery capacity k3 does not belong to the distribution center set. Distribution center i in the middle.

[0090] Self-operated forwarding variables : Indicates whether product p in order i is from the preceding transport capacity set The forward capacity k1 is transferred to the self-operated capacity pool. The self-operated capacity k2 in the system. For example, =1 indicates that item p in order i is from the previous transportation capacity set. The forward capacity k1 is transferred to the self-operated capacity pool. The self-operated capacity k2 in the middle, =0 indicates that item p in order i is not from the preceding transportation capacity set. The forward capacity k1 is transferred to the self-operated capacity pool. The self-operated capacity k2 in the middle.

[0091] Crowdsourced transfer variables : Indicates whether product p in order i is from the preceding transport capacity set The pre-positioned transportation capacity k1 is transferred to the crowdsourced transportation capacity aggregation. The crowdsourced delivery capacity k3 in the context. For example... =1 indicates that item p in order i is from the previous transportation capacity set. The pre-positioned transportation capacity k1 is transferred to the crowdsourced transportation capacity aggregation. K3, a crowdsourced delivery capacity in China =0 indicates that item p in order i is not from the preceding transportation capacity set. The pre-positioned transportation capacity k1 is transferred to the crowdsourced transportation capacity aggregation. The crowdsourced delivery capacity k3 in the middle.

[0092] Pre-start time variable : Represents the set of preceding transportation capacity The preceding capacity k1 in the process is at the service start time of node i.

[0093] Self-operated start time variable : Represents the collection of self-operated operating capacity The self-operated capacity k2 in the process starts its service at node i.

[0094] Crowdsourcing start time variable : Indicates the aggregation of crowdsourced transportation capacity The crowdsourced delivery capacity k2 in the data is at the service start time of node i.

[0095] 10. Allocation Strategy: This includes the service order set of each front-end service warehouse, the travel route of each front-end service capacity k1', the loading order set of each front-end service capacity k1', and the service start time of each front-end service capacity k1'; the travel route of each self-operated service capacity k2', the loading order set of each self-operated service capacity k2', and the service start time of each self-operated service capacity k2'; and the travel route of each crowdsourced service capacity k3', the loading order set of each crowdsourced service capacity k3', and the service start time of each crowdsourced service capacity k3'.

[0096] Among them, the forward service warehouse is a forward warehouse obtained through planning, used to serve the set of orders to be allocated. When all forward route variables... Once the variable values ​​are determined, it can be determined whether the front warehouse will be used, thus allowing the front service warehouse to be planned.

[0097] Here, the front-end service capacity k1' is the front-end capacity obtained through planning to serve the set of orders to be allocated. Front-end route variable. Once the variable values ​​are determined, it can be determined whether the front-end capacity k1 is used. In this way, the front-end service capacity k1' (i.e. the front-end capacity that needs to be used for front-end delivery) can be planned.

[0098] Among them, the self-operated service capacity k2' is the self-operated capacity obtained through planning to serve the set of orders to be allocated. Self-operated route variables. Once the variable values ​​are determined, it can be determined whether the self-operated capacity k2 is used. In this way, the self-operated service capacity k2' (i.e. the self-operated capacity required for last-mile delivery) can be planned.

[0099] Among them, the crowdsourced service capacity k3' is the crowdsourced capacity obtained through planning to serve the set of orders to be assigned. Crowdsourced route variable. Once the variable values ​​are determined, it can be determined whether the crowdsourced delivery capacity k3 will be used. In this way, the crowdsourced service delivery capacity k3' (i.e. the crowdsourced delivery capacity required for last-mile delivery) can be planned.

[0100] The capacity data includes the forward capacity data (CT) of each forward warehouse (FC), the self-operated capacity data (UV) of each distribution center (DC), and the crowdsourced capacity data. The inventory data includes the inventory of each product in each forward warehouse (FC).

[0101] The set of orders to be assigned includes multiple orders, specifically the set of all orders on the e-commerce platform that have the same delivery time requirement (e.g., the set of all orders that customers require to be delivered tomorrow).

[0102] The inventory data includes the inventory of each product in each forward warehouse (FC). For example, the inventory of product a and product b in forward warehouse 1, and the inventory of product a, product b, and product c in forward warehouse 2.

[0103] The product set refers to the set of all products involved in all orders within the order set to be assigned.

[0104] 202. Construct a cost optimization model for the set of orders to be assigned.

[0105] The cost optimization model includes upfront transportation cost parameters, self-operated transportation cost parameters, and crowdsourced transportation cost parameters. The crowdsourced transportation cost parameters include crowdsourced transportation cost, crowdsourced loading capacity cost, and crowdsourced time cost.

[0106] For example, the cost optimization model is shown in the following formula (1):

[0107] Formula (1)

[0108] In formula (1), the first two terms represent the upfront transportation cost parameters, the third and fourth terms represent the self-operated transportation cost parameters, and the fifth to seventh terms represent the crowdsourced transportation cost parameters.

[0109] 203. Determine the decision variables and objective constraints of the cost optimization model.

[0110] The decision variables include the preceding route variables. Self-operated route variables Crowdsourcing route variables Crowdsourcing membership variables Self-operated transshipment variables Crowdsourcing transfer variables Pre-set start time variable Self-operated start time variable Crowdsourcing start time variable .

[0111] The target constraints include the first constraint on pre-positioned capacity, the second constraint on self-operated capacity, and the third constraint on crowdsourced capacity.

[0112] For example, the first constraint condition for defining the forward transport capacity specifically includes, but is not limited to, defining the constraints in the following formulas (2) to (11):

[0113] Formula (2)

[0114] Formula (3)

[0115] Formula (4)

[0116] Formula (5)

[0117] Formula (6)

[0118] Formula (7)

[0119] Formula (8)

[0120] Formula (9)

[0121] Formula (10)

[0122] Formulas (2) and (3) indicate that a certain forward capacity CT is used to fulfill the service plan of the set of orders to be allocated, and it must depart from and return from its respective forward warehouse FC.

[0123] Formula (4) represents the flow balance constraint on the CT service route.

[0124] Formula (5) specifies the service start time of the node accessed by CT.

[0125] Formula (6) links the service plans for CT and UV.

[0126] Formula (7) represents the coordinated time relationship between CT and UV within the operation time window.

[0127] Formula (8) represents the coordinated time relationship between CT and CDP (if they belong to DC) within the operating time window.

[0128] Formula (9) stipulates that the quantity of goods provided by CT cannot exceed its inventory.

[0129] Formula (10) ensures that the total weight of the order items loaded by the CT when it departs from its FC does not exceed its loading capacity.

[0130] Formula (11) ensures the time window limit for CT access nodes.

[0131] For example, the second constraint on self-operated capacity is defined specifically including, but not limited to, the constraints defined by the following formulas (12) to (18):

[0132] Formula (12)

[0133] Formula (13)

[0134] Formula (14)

[0135] Formula (15)

[0136] Formula (16)

[0137] Formula (17)

[0138] Formula (18)

[0139] Formulas (12) and (13) jointly stipulate that if a self-operated capacity UV is used to fulfill the service plan of the set of orders to be allocated, it can only start from its DC and return along the same path.

[0140] Formula (14) represents the flow balance constraint of UV.

[0141] Formula (15) defines the time it takes for a UV to reach a customer node.

[0142] Formula (16) ensures that UV must begin fulfilling services within the customer’s time window.

[0143] Formula (17) describes the operational relationship of UV accessing client nodes.

[0144] Formula (18) indicates that the total weight of goods received by UV from CT cannot exceed its carrying capacity, and they observe the coordination between CT and UV in the order transfer process.

[0145] For example, the third constraint on crowdsourced capacity is defined specifically including, but not limited to, the constraints defined in formulas (19) to (28) below:

[0146] Formula (19)

[0147] Formula (20)

[0148] Formula (21)

[0149] Formula (22)

[0150] Formula (23)

[0151] Formula (24)

[0152] Formula (25)

[0153] Formula (26)

[0154] Formula (27)

[0155] Formula (28)

[0156] Formula (19) stipulates that a CDP can only participate in the order fulfillment plan if it belongs to a specific DC and receives orders from that DC.

[0157] Formulas (20) to (22) stipulate that only the selected CDP can participate in the order fulfillment service and describe the allocation relationship between CT and CDP.

[0158] Formula (23) states that a CDP’s order fulfillment service plan must begin from its own DC.

[0159] Formula (24) requires that the CDP can only provide fulfillment services for the customer's orders when the CDP visits the customer.

[0160] Formula (25) represents the traffic balancing constraint of the customer order node accessed by CDP.

[0161] Formula (26) specifies the time for the crowdsourced delivery capacity (CDP) to reach the customer node.

[0162] Formula (27) ensures that crowdsourced delivery capacity (CDP) can only provide fulfillment services within the service time window of the customer's order.

[0163] Formula (28) defines that the total weight of the order items loaded by the crowdsourced delivery capacity (CDP) when leaving the DC must not exceed its carrying capacity.

[0164] 204. Based on the set of orders to be assigned, the set of goods, the inventory data, the transportation capacity data, and the target constraints, solve the decision variables of the cost optimization model to obtain the target variable values ​​of the decision variables.

[0165] For example, such as Figure 4 As shown, Figure 4 This is a schematic flowchart of an embodiment of step 204 in this application. Step 204 may specifically include the following steps 2041 to 2043:

[0166] 2041. Perform distribution center clustering on the set of orders to be assigned to obtain the distribution center constraints of the set of orders to be assigned.

[0167] In some embodiments, firstly, each order in the set of orders to be assigned can be clustered based on spatial proximity to obtain multiple cluster sets of the set of orders to be assigned, each cluster set including multiple orders; then, each cluster set is preferentially associated with the nearest or lowest cost distribution center to obtain the associated distribution centers of each order in the set of orders to be assigned, and the associated distribution centers of each order in the set of orders to be assigned are described as distribution center constraints of the set of orders to be assigned, so that further capacity allocation processing can be performed on each order of the distribution center in the subsequent process.

[0168] 2042. Based on the distribution center constraints, the product set, the inventory data, the transportation capacity data, the time constraints, the second constraints, and the third constraints, obtain the self-operated route variables. Target variable value, crowdsourcing route variable Target variable value, crowdsourcing membership variable Target variable value, self-operated start time variable Target variable value and crowdsourcing start time variable The target variable value.

[0169] For example, using product category as the allocation basis, and prioritizing self-operated capacity to transport a single product category or a small number of product categories, self-operated capacity k2 or crowdsourced capacity k3 is allocated to each order in each set of orders to be allocated based on distribution center constraints, the product set, the inventory data, the capacity data, the second constraint, and the third constraint, thereby obtaining the self-operated route variable. Target variable value, crowdsourcing route variable Target variable value, crowdsourcing membership variable The target variable value.

[0170] Then, based on the self-operated route variables Target variable value, crowdsourcing route variable Target variable value, crowdsourcing membership variable The target variable value and the time constraint are the self-operated route variables. The target variable values ​​correspond to the self-operated capacity k2 planning departure and arrival times, and are used as crowdsourced route variables. The target variable value corresponds to the departure and arrival times of the crowdsourced transportation capacity k3 plan, thus obtaining the self-operated start time variable. Target variable value and crowdsourcing start time variable The target variable value.

[0171] 2043. Based on the aforementioned self-operated route variables The target variable value, the crowdsourcing route variable The target variable value, the crowdsourcing membership variable The target variable value, the self-operated start time variable The target variable value and the crowdsourcing start time variable Based on the target variable value and the first constraint, determine the preceding route variable. Target variable value, self-operated transit variable Target variable value, crowdsourcing transfer variable The target variable value and the preceding start time variable The target variable value.

[0172] For example, based on the self-operated route variable The target variable value, the crowdsourcing route variable The target variable value, the crowdsourcing membership variable The target variable value, the self-operated start time variable The target variable value and the crowdsourcing start time variable Based on the target variable value and the first constraint, advance transportation capacity k1 is allocated to each order in each set of orders to be assigned, thereby obtaining the advance route variable. Target variable value, self-operated transit variable Target variable value, crowdsourcing transfer variable The target variable value and the preceding start time variable The target variable value.

[0173] 205. Based on the target variable value of the decision variable, output the target allocation strategy for the set of orders to be allocated.

[0174] There are multiple ways to implement step 205, including, for example, the following methods (1) to (3).

[0175] (1) In some embodiments, the initial allocation strategy constructed based on the target variable value of the decision variable is output as the target allocation strategy. In this case, step 205 may specifically include the following steps 2051A~2052A:

[0176] 2051A. Based on the target variable value of the decision variable, determine the initial allocation strategy for the set of orders to be allocated.

[0177] The initial allocation strategy refers to the allocation strategy based on the indications corresponding to the target variable value set.

[0178] Once the self-operated route variable is determined Target variable value, crowdsourcing route variable Target variable value, crowdsourcing membership variable Target variable value, self-operated start time variable Target variable value, crowdsourcing start time variable Target variable value, preceding route variable Target variable value, self-operated transit variable Target variable value, crowdsourcing transfer variable Target variable value and preceding start time variable The target variable value is equivalent to determining the M forward paths and N terminal paths from the forward warehouse to the distribution center. Each forward path is determined by the forward route variable. The target variable value indicates (representing the use of forward transportation capacity k1 to complete the transfer from forward warehouse i to distribution center j), and the last-mile path includes two types: N1 self-operated last-mile paths and N2 crowdsourced self-operated paths. Each self-operated last-mile path is determined by the self-operated route variable. The target variable value indicates (representing the use of self-operated capacity k2 to complete transportation and delivery between the distribution center and the customer), and each crowdsourced last-mile route is determined by the self-operated route variable. The target variable value indicates (that crowdsourced transportation capacity k3 is used to complete transportation and delivery between the distribution center and the customer).

[0179] After obtaining the target variable value set through step 204, the initial allocation strategy for an order to be allocated is obtained under the guidance of the target variable value set. The initial allocation strategy includes the service order set of each front-end service warehouse, the travel route of each front-end service capacity k1', the loading order set of each front-end service capacity k1', and the service start time of each front-end service capacity k1', the travel route of each self-operated service capacity k2', the loading order set of each self-operated service capacity k2', and the service start time of each self-operated service capacity k2', as well as the travel route of each crowdsourced service capacity k3', the loading order set of each crowdsourced service capacity k3', and the service start time of each crowdsourced service capacity k3'.

[0180] Among them, self-operated service capacity k2' and crowdsourced service capacity k3' are collectively referred to as last-mile service capacity.

[0181] 2052A. Output the initial allocation strategy as the target allocation strategy.

[0182] (2) In some embodiments, the optimized allocation strategy obtained by optimizing the end-capacity of the initial allocation strategy is output as the target allocation strategy. In this case, such as... Figure 5 As shown, Figure 5 This is a schematic flowchart of an embodiment of step 205 in this application. Step 205 may specifically include the following steps 2051B to 2055B:

[0183] 2051B. Based on the target variable value of the decision variable, determine the initial allocation strategy for the set of orders to be allocated.

[0184] The implementation of step 2051B is similar to that of step 2051A. For details, please refer to the relevant explanations above. They will not be repeated here.

[0185] 2052B. Based on the initial allocation strategy, obtain the allocation strategy before this end-point optimization.

[0186] The allocation strategy prior to this last-mile optimization refers to the allocation strategy before this last-mile capacity optimization. Each last-mile optimization will change the last-mile capacity of the allocation strategy. Specifically, by removing loading orders for last-mile capacity and then re-planning the last-mile capacity of the removed orders, the last-mile capacity of the allocation strategy can be optimized, thereby improving the reliability of the allocation strategy.

[0187] In steps 2051B to 2055B, the initial allocation strategy is used before the first round of end-point optimization (where one round of optimization consists of one removal and one optimization, i.e., one round of end-point optimization is performed once). After the first round of optimization, the allocation strategy after the previous end-point optimization is used as the allocation strategy before the current end-point optimization. For example, in the first round of end-point optimization, the allocation strategy before the first end-point optimization is the initial allocation strategy, and the allocation strategy after the first end-point optimization is obtained after steps 2053B to 2054B; in the second round of end-point optimization, the allocation strategy before the second end-point optimization is the allocation strategy after the first end-point optimization, and the allocation strategy after the second end-point optimization is obtained after steps 2053B to 2054B; and so on.

[0188] 2053B. The allocation strategy before the current terminal optimization is removed to obtain the allocation strategy after the current terminal removal.

[0189] The allocation strategy after removing the last-mile delivery orders refers to the allocation strategy obtained after removing the loading orders of the last-mile delivery capacity during this last-mile capacity optimization process.

[0190] For example, step 2053B may specifically include the following steps B1 to B2:

[0191] B1. Determine the last-mile removal order for the current last-mile optimization allocation strategy.

[0192] In some embodiments, a target front-end service warehouse with the fewest service products can be determined from the front-end service warehouses indicated by the current end-to-end optimization allocation strategy; the service order corresponding to the target front-end service warehouse is taken as the current end-to-end removal order. For example, the set of orders to be assigned is order ID1, ID2, ..., ID100. The front-end service warehouses indicated by the allocation strategy before this end-point optimization are FC1, FC2, FC3, and FC4. The service order set of front-end service warehouse FC1 is {ID1, ID2, ..., ID10}, the service order set of front-end service warehouse FC2 is {ID11, ID12, ..., ID50}, the service order set of front-end service warehouse FC3 is {ID51, ID52, ..., ID70}, and the service order set of front-end service warehouse FC4 is {ID71, ID72, ..., ID100}. Assuming that each order contains one product, since the number of products corresponding to the service order set of front-end service warehouse FC1 is the smallest, front-end service warehouse FC1 can be used as the target front-end service warehouse. The loading orders ID1, ID2, ..., ID10 corresponding to front-end service warehouse FC1 are used as the orders to be removed in this end-point optimization.

[0193] In some embodiments, the target front-end service capacity with the smallest loading capacity can be determined from the front-end service capacity indicated by the current end-to-end optimization allocation strategy; the loading orders corresponding to the target front-end service capacity are used as the current end-to-end removal orders. For example, the set of orders to be allocated is order ID1, ID2, ..., ID100, and the front-end service capacity k1' indicated by the current end-to-end optimization allocation strategy includes CT1, CT2, CT3, and CT4. The loading order set of front-end service capacity CT1 is {ID1, ID2, ..., ID50}, the loading order set of CT2 is {ID51, ID52, ..., ID90}, and the loading order set of CT3 is {ID91, ID92, ..., ID100}. Assuming that each order is for one product, since the loading capacity corresponding to the loading order set of front-end service capacity CT3 is the smallest, front-end service capacity CT3 can be used as the target front-end service capacity, and the loading orders ID91, ID92, ..., ID100 corresponding to front-end service capacity CT3 are used as the current end-to-end removal orders.

[0194] In some embodiments, the target self-operated service capacity with the smallest loading capacity can be determined from the self-operated service capacity indicated by the allocation strategy before this last-mile optimization; the loading orders corresponding to the target self-operated service capacity are used as the last-mile removal orders. For example, the set of orders to be allocated is order ID1, ID2, ..., ID100, and the self-operated service capacity k2' indicated by the allocation strategy before this last-mile optimization includes UV1, UV2, and UV3. The loading order set of self-operated service capacity UV1 is {ID1, ID2, ..., ID20}, the loading order set of UV2 is {ID21, ID22, ..., ID40}, and the loading order set of UV3 is {ID41, ID42, ..., ID50}. Assuming that each order is for one product, since the loading capacity corresponding to the loading order set of self-operated service capacity UV3 is the smallest, self-operated service capacity UV3 can be used as the target self-operated service capacity, and the loading orders ID41, ID42, ..., ID50 corresponding to self-operated service capacity UV3 are used as the last-mile removal orders.

[0195] In some embodiments, self-operated service capacity can be randomly selected from the self-operated service capacity indicated by the allocation strategy before this last-mile optimization; the loading orders corresponding to the randomly selected self-operated service capacity are used as the last-mile removal orders. For example, if the set of orders to be allocated is order ID1, ID2, ..., ID100, and the self-operated service capacity k2' indicated by the allocation strategy before this last-mile optimization includes UV1, UV2, and UV3, and self-operated service capacity UV1 is randomly selected as the target self-operated service capacity, then the loading orders ID1, ID2, ..., ID20 corresponding to self-operated service capacity UV1 are used as the last-mile removal orders.

[0196] In some embodiments, crowdsourcing service capacity can be randomly selected from the crowdsourcing service capacity indicated by the allocation strategy before this last-mile optimization; the loading orders corresponding to the randomly selected crowdsourcing service capacity are used as the last-mile removal orders. For example, if the set of orders to be allocated is order ID1, ID2, ..., ID100, and the crowdsourcing service capacity k3' indicated by the allocation strategy before this last-mile optimization includes CDP1, CDP2, and CDP3, the loading order set of crowdsourcing service capacity CDP1 is {ID51, ID52, ..., ID70}, the loading order set of CDP2 is {ID71, ID72, ..., ID90}, and the loading order set of CDP3 is {ID91, ID92, ..., ID100}, and crowdsourcing service capacity CDP3 is randomly selected as the target crowdsourcing service capacity, then the loading orders ID91, ID92, ..., ID100 corresponding to crowdsourcing service capacity CDP3 are used as the last-mile removal orders.

[0197] In some embodiments, a first order cluster with a product similarity greater than a first preset similarity threshold can be obtained from the orders to be assigned; and each order in the first order cluster can be used as the final removal order in this instance.

[0198] In some embodiments, a second order cluster with spatial similarity between orders greater than a second preset similarity threshold can be obtained from the orders to be assigned; each order in the second order cluster is used as the final removal order in this instance.

[0199] B2. Based on the current end-point removal order, the allocation strategy before the current end-point optimization is removed to obtain the allocation strategy after the current end-point removal.

[0200] In some embodiments, if the last-mile removal order is a loading order for the front-end service capacity k1', then the last-mile removal order is removed from the loading order set of each front-end service capacity k1' corresponding to the previous last-mile optimization allocation strategy, thereby updating the loading order set of each front-end service capacity k1'; if the last-mile removal order is a loading order for the self-operated service capacity k2', then the last-mile removal order is removed from the loading order set of each self-operated service capacity k2' corresponding to the previous last-mile optimization allocation strategy, thereby updating the loading order set of each self-operated service capacity k2'; if the last-mile removal order is a loading order for the crowdsourced service capacity k3', then the last-mile removal order is removed from the loading order set of each crowdsourced service capacity k3' corresponding to the previous last-mile optimization allocation strategy, thereby updating the loading order set of each crowdsourced service capacity k3'. The allocation strategy before this last-mile optimization will be updated accordingly as last-mile removal orders are removed. This includes: the service order set of each front-end service warehouse, the travel path of each front-end service capacity k1', the loading order set of each front-end service capacity k1', and the service start time of each front-end service capacity k1'; the travel path of each self-operated service capacity k2', the loading order set of each self-operated service capacity k2', and the service start time of each self-operated service capacity k2'; and the travel path of each crowdsourced service capacity k3', the loading order set of each crowdsourced service capacity k3', and the service start time of each crowdsourced service capacity k3'. This will yield the allocation strategy after this last-mile removal. In this way, last-mile removal orders can be removed from the last-mile path, providing room for improvement in subsequent last-mile path optimization, thereby improving the timeliness of the allocation strategy.

[0201] 2054B. Based on the first constraint, the second constraint, and the third constraint, perform end-of-pipe optimization processing on the end-of-pipe removal allocation strategy to obtain the end-of-pipe optimized allocation strategy.

[0202] The allocation strategy after removing the last mile refers to the allocation strategy after optimizing the last mile capacity.

[0203] In some embodiments, step 2054B may specifically include: based on the second constraint and the third constraint, detecting a first end-user service capacity that minimizes the insertion cost of the current end-user removal order from the current end-user removal allocation strategy; if the current end-user removal allocation strategy contains the first end-user service capacity, then adding the current end-user removal order to the first end-user service capacity to complete the end-user optimization processing of the current end-user removal allocation strategy and obtain the current end-user optimized allocation strategy; if the current end-user removal allocation strategy does not contain the first end-user service capacity, then creating a second end-user service capacity and adding it to the current end-user optimization allocation strategy, and adding the current end-user removal order to the first end-user service capacity to complete the end-user optimization processing of the current end-user removal allocation strategy and obtain the current end-user optimized allocation strategy. In this way, one or more of the last-mile removal orders can be tried one by one to insert into the feasible last-mile service capacity with the smallest incremental cost (the incremental cost is the increase in allocation strategy cost after the last-mile removal order is inserted relative to the allocation strategy cost before insertion, and the incremental cost can be determined according to the transportation cost of the last-mile capacity), and the allocation strategy after this last-mile optimization still satisfies the second and third constraints, thereby ensuring that the allocation strategy after this last-mile optimization can provide fulfillment services within the service time window of the order.

[0204] Among them, the first last-mile service capacity refers to the last-mile service capacity that minimizes the incremental cost of the allocation strategy after loading and adding the last-mile removal order among the self-operated service capacity k2' and crowdsourced service capacity k3' of the allocation strategy after this last-mile removal.

[0205] The second-end service capacity refers to the newly created end-point capacity used to load orders added to this end-point removal order.

[0206] 2055B. The optimized allocation strategy for this terminal phase is output as the target allocation strategy.

[0207] In some embodiments, steps 2052B to 2054B are considered as one end-of-pipe optimization process. The result of one optimization can be referred to steps 2052B to 2054B. For example, the allocation strategy after the first end-of-pipe optimization can be used as the target allocation strategy output.

[0208] In some embodiments, steps 2052B to 2054B are considered as one end-point optimization process. Multiple optimizations can be performed by referring to steps 2052B to 2054B until the end-point optimization stop condition is met. The result obtained after multiple end-point optimizations, such as the allocation strategy after the n=5th end-point optimization, is output as the target allocation strategy.

[0209] (3) In some embodiments, the optimized allocation strategy obtained by optimizing the transfer capacity of the initial allocation strategy is output as the target allocation strategy. In this case, such as... Figure 6 As shown, Figure 6 This is a flowchart illustrating another embodiment of step 205 in this application. Step 205 may specifically include the following steps 2051C to 2055C:

[0210] 2051C. Based on the target variable value of the decision variable, determine the initial allocation strategy for the set of orders to be allocated.

[0211] The implementation of step 2051C is similar to that of step 2051A. For details, please refer to the relevant explanations above. They will not be repeated here.

[0212] 2052C. Based on the initial allocation strategy, obtain the allocation strategy before this transfer optimization.

[0213] The allocation strategy prior to this transshipment optimization refers to the allocation strategy before this transshipment capacity optimization. Each transshipment optimization will change the transshipment capacity of the allocation strategy. Specifically, by removing the loading orders of the transshipment capacity and then re-planning the transshipment capacity of the removed orders, the transshipment capacity of the allocation strategy is optimized, thereby improving the reliability of the allocation strategy.

[0214] In steps 2051C to 2055C, the initial allocation strategy is used before the first round of transfer optimization (where one round of optimization consists of one removal and one optimization, i.e., one execution of steps 2053C to 2054C constitutes one round of transfer optimization). After the first round of optimization, the allocation strategy after the previous transfer optimization is used as the allocation strategy before the current transfer optimization. For example, in the first round of transfer optimization, the allocation strategy before the first transfer optimization is the initial allocation strategy, and the allocation strategy after the first transfer optimization is obtained after steps 2053C to 2054C; in the second round of transfer optimization, the allocation strategy before the second transfer optimization is the allocation strategy after the first transfer optimization, and the allocation strategy after the second transfer optimization is obtained after steps 2053C to 2054C; and so on.

[0215] 2053C. The allocation strategy before the current transfer optimization is removed to obtain the current transfer removal allocation strategy.

[0216] The "transfer removal and allocation strategy" refers to the allocation strategy obtained after removing loading orders for the transfer capacity during the current transfer capacity optimization process.

[0217] In some embodiments, step 2053C may specifically include: determining the capacity to be removed from the end-service capacity indicated by the pre-optimization allocation strategy for this transit, wherein the end-service capacity includes self-operated service capacity and crowdsourced service capacity; and removing the pre-optimization allocation strategy based on the current order group of the removed capacity to obtain the post-removal allocation strategy for this transit, wherein each order in the current order group belongs to the same upstream capacity, and the total number of product categories in the current order group is less than the preset total number of categories. Thus, a "batch order" (i.e., the current order group) can be introduced as the basic unit for reconstructing the transit path upstream of the delivery chain: a group of orders fulfilled by the same UV or CDP and involving the same or limited categories of products is considered a "batch order," thereby enabling transit optimization to inherit customer time windows and loading / unloading sequence constraints. This ensures that fulfillment services are provided within the customer order's service time window, while continuously optimizing the upstream transit path of the delivery chain. The final output target strategy reduces the upstream delivery cost while providing fulfillment services within the customer order's service time window.

[0218] 2054C. Based on the first constraint, the second constraint, and the third constraint, the current transfer removal allocation strategy is optimized to obtain the optimized allocation strategy.

[0219] The "removal and allocation strategy for this transfer" refers to the allocation strategy after the optimization of the transfer capacity.

[0220] In some embodiments, step 2054C may specifically include: based on the first constraint, the second constraint, and the third constraint, detecting the first front-end service capacity that minimizes the insertion cost of the current order group from the current transfer removal and allocation strategy; if the first front-end service capacity exists in the current transfer removal and allocation strategy, then adding the current order group to the first front-end service capacity to complete the transfer optimization processing of the current transfer removal and allocation strategy, and obtaining the current transfer optimized allocation strategy; if the first front-end service capacity does not exist in the current transfer removal and allocation strategy, then creating a second front-end service capacity and adding it to the current transfer optimized allocation strategy, and adding the current order group to the first front-end service capacity to complete the transfer optimization processing of the current transfer removal and allocation strategy, and obtaining the current transfer optimized allocation strategy. In this way, one or more current order groups can be inserted one by one into the feasible front-end service capacity with the smallest incremental cost (the incremental cost is the increase in allocation strategy cost after the current order group is inserted relative to the allocation strategy cost before insertion, and the incremental cost can be determined according to the transportation cost of the front-end capacity), and the allocation strategy after the current transfer optimization still satisfies the first constraint condition, thereby ensuring that the allocation strategy after the current transfer optimization will not affect the customer time window and loading and unloading sequence of the last delivery in the downstream of the delivery chain.

[0221] Among them, the first front-end service capacity refers to the front-end service capacity k1' of the allocation strategy after the removal of this transit, which minimizes the incremental cost of the allocation strategy after being loaded into this order group.

[0222] The second forward service capacity refers to the newly created forward capacity used to load the orders added to this order group.

[0223] 2055C. The optimized allocation strategy for this transfer is output as the target allocation strategy.

[0224] In some embodiments, steps 2052C to 2054C are considered as one transfer optimization process. The results of one optimization can be obtained by referring to steps 2052C to 2054C. For example, the allocation strategy after the first transfer optimization can be used as the target allocation strategy output.

[0225] In some embodiments, steps 2052C to 2054C are considered as one transfer optimization process. Multiple optimizations can be performed by referring to steps 2052C to 2054C until the conditions for stopping transfer optimization are met. The results obtained after multiple transfer optimizations, such as the allocation strategy after the m=6th transfer optimization, are output as the target allocation strategy.

[0226] (4) In some embodiments, the terminal optimized allocation strategy is obtained by first optimizing the terminal capacity of the initial allocation strategy, and the transfer optimized allocation strategy is obtained by optimizing the transfer capacity of the terminal optimized allocation strategy. The transfer optimized allocation strategy is then output as the target allocation strategy. In this case, step 205 may specifically include the following steps 2051D~2058D:

[0227] 2051D. Based on the target variable value of the decision variable, determine the initial allocation strategy for the set of orders to be allocated.

[0228] 2052D. Based on the initial allocation strategy, obtain the allocation strategy before this end-point optimization.

[0229] 2053D. The allocation strategy before the current terminal optimization is removed to obtain the allocation strategy after the current terminal removal.

[0230] 2054D. Based on the first constraint, the second constraint, and the third constraint, the allocation strategy after end removal is optimized to obtain the optimized allocation strategy.

[0231] The implementation of steps 2051D to 2054D is similar to that of steps 2051A to 2054A. For details, please refer to the relevant explanations above, which will not be repeated here.

[0232] 2055D. Based on the optimized allocation strategy for this terminal phase, determine the pre-optimized allocation strategy for this transit phase.

[0233] In some embodiments, steps 2052D to 2054D can be considered as one end-of-pipe optimization process. The results of one optimization can be referred to steps 2052D to 2054D. For example, the allocation strategy after the first end-of-pipe optimization can be used as the allocation strategy before this transfer optimization.

[0234] In some embodiments, steps 2052D to 2054D are considered as one end-of-line optimization process. Multiple optimizations can be performed with reference to steps 2052D to 2054D until the end-of-line optimization stop condition is met. The results obtained after multiple end-of-line optimizations, such as the allocation strategy after the n=5th end-of-line optimization, are used as the allocation strategy before this transfer optimization.

[0235] 2056D. The allocation strategy before the current transfer optimization is removed to obtain the current transfer removal allocation strategy.

[0236] 2057D. Based on the first constraint, the second constraint, and the third constraint, the current transfer removal allocation strategy is optimized to obtain the optimized allocation strategy.

[0237] The implementation of steps 2056D to 2057D is similar to that of steps 2053C to 2054C. For details, please refer to the relevant explanations above. They will not be repeated here.

[0238] 2058D. Based on the optimized allocation strategy for this transfer, output the target allocation strategy.

[0239] In some embodiments, steps 2055D to 2057D are considered as one transfer optimization process. The results of one optimization can be obtained by referring to steps 2055D to 2057D. For example, the allocation strategy after the first transfer optimization can be used as the target allocation strategy output.

[0240] In some embodiments, steps 2055D to 2057D are considered as one transfer optimization process. Multiple optimizations can be performed by referring to steps 2055D to 2057D until the conditions for stopping transfer optimization are met. The results obtained after multiple transfer optimizations, such as the allocation strategy after the m=6th transfer optimization, are output as the target allocation strategy.

[0241] As can be seen from the above, the first aspect involves including both self-operated and crowdsourced transportation cost parameters in the same cost optimization model, allowing self-operated and crowdsourced transportation capacity to be considered as a whole cost. Furthermore, the decision variables are constructed to include prior route variables. Self-operated route variables Crowdsourcing route variables This approach allows for synchronized planning of the entire delivery chain, with upstream transportation capacity serving as transshipment and delivery resources, and self-operated and crowdsourced capacity simultaneously serving as end-of-chain delivery resources. This enables the overall planning of self-operated and crowdsourced capacity as end-of-chain delivery resources, reducing the problems of lower overall timeliness and higher overall delivery costs caused by independent planning of self-operated and crowdsourced capacity. Secondly, by constructing time window constraints using time window data, the overall delivery timeliness of the entire chain meets the service time window requirements of customer orders, reducing order timeliness breaches (such as orders not meeting the "same-day delivery" or "next-day delivery" requirements). Thirdly, by constructing cost parameters for upstream transportation capacity, self-operated capacity, and crowdsourced capacity through a cost optimization model, the costs of upstream transshipment and delivery resources and end-of-chain delivery resources can be controlled to some extent. Fourthly, by using upstream route variables... Self-operated route variables Crowdsourcing route variables Crowdsourcing membership variables Self-operated transshipment variables Crowdsourcing transfer variables Pre-set start time variable Self-operated start time variable Crowdsourcing start time variable The target variable values ​​of decision variables are used to plan the target allocation strategy, enabling the allocation of orders to be assigned to simultaneously complete the allocation of front-end warehouse inventory, front-end delivery resources and time (i.e., the allocation of loading orders and service start times for front-end transportation capacity), and last-mile delivery resources and time (i.e., the allocation of loading orders and service start times for self-operated and crowdsourced transportation capacity) as a whole. This achieves integrated planning of all tasks in the delivery chain, thereby further optimizing the overall timeliness and cost of the allocation strategy. Therefore, this application can improve the overall timeliness of order sets, reduce overall delivery costs, and mitigate order timeliness default issues.

[0242] Those skilled in the art will understand that all or part of the steps in the above-described method for integrating and allocating self-operated and crowdsourced transportation capacity for e-commerce orders can be accomplished by instructions, or by controlling related hardware through instructions. These instructions can be stored in a computer-readable storage medium and loaded and executed by a processor. Therefore, embodiments of this application provide a computer-readable storage medium storing multiple computer programs that can be loaded by a processor to execute any of the self-operated and crowdsourced transportation capacity integration and allocation methods for e-commerce orders provided in this application. For example, the computer program can be loaded by a processor to execute any step in the above-described method for integrating and allocating self-operated and crowdsourced transportation capacity for e-commerce orders.

[0243] The computer-readable storage medium may include: read-only memory (ROM), random access memory (RAM), disk or optical disk, etc.

[0244] In the above embodiments of the self-operated and crowdsourced transportation capacity integration and allocation method, computer-readable storage medium, and electronic device for e-commerce orders, the descriptions of each embodiment have different focuses. For parts not detailed in a particular embodiment, please refer to the relevant descriptions of other embodiments. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes and beneficial effects of the computer-readable storage medium, electronic device, and their corresponding units described above can be referred to the description of the self-operated and crowdsourced transportation capacity integration and allocation method for e-commerce orders in the above embodiments, and will not be repeated here.

[0245] The foregoing has provided a detailed description of a method for integrating and allocating self-operated and crowdsourced transportation capacity for e-commerce orders, an electronic device, and a computer-readable storage medium, as provided in the embodiments of this application. Specific examples have been used to illustrate the principles and implementation methods of this application. The descriptions of the embodiments above are only for the purpose of helping to understand the method and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A method for integrating and allocating self-operated and crowdsourced delivery capacity for e-commerce orders, characterized in that, The method includes: The system acquires the set of orders to be assigned, the set of goods, inventory data, transportation capacity data, and time window data from the e-commerce platform. The transportation capacity data includes the pre-positioned transportation capacity data of each pre-positioned warehouse, the self-operated transportation capacity data of each distribution center, and the crowdsourced transportation capacity data. The inventory data includes the inventory of each product in each pre-positioned warehouse. The set of goods is the set of goods involved in the set of orders to be assigned. Construct a cost optimization model for the set of orders to be assigned, wherein the cost optimization model includes upfront transportation cost parameters, self-operated transportation cost parameters, and crowdsourced transportation cost parameters, and the crowdsourced transportation cost parameters include crowdsourced transportation cost, crowdsourced loading capacity cost, and crowdsourced time cost; The decision variables and objective constraints of the cost optimization model are determined, wherein the decision variables include pre-route variables, self-operated route variables, crowdsourced route variables, crowdsourced affiliation variables, self-operated transfer variables, crowdsourced transfer variables, pre-start time variables, self-operated start time variables, and crowdsourced start time variables, and the objective constraints include time constraints based on the time window data, a first constraint on pre-operated capacity, a second constraint on self-operated capacity, and a third constraint on crowdsourced capacity; Based on the set of orders to be assigned, the set of goods, the inventory data, the transportation capacity data, and the target constraints, the decision variables of the cost optimization model are solved to obtain the target variable values ​​of the decision variables; Based on the target variable value of the decision variable, the target allocation strategy of the set of orders to be allocated is output.

2. The method for integrating and allocating self-operated and crowdsourced delivery capacity for e-commerce orders according to claim 1, characterized in that, The step of solving the decision variables of the cost optimization model based on the set of orders to be assigned, the set of goods, the inventory data, the transportation capacity data, and the target constraints to obtain the target variable values ​​of the decision variables includes: The distribution center clustering of the set of orders to be assigned is performed to obtain the distribution center constraints of the set of orders to be assigned. Based on the distribution center constraints, the product set, the inventory data, the transportation capacity data, the time constraints, the second constraints, and the third constraints, the target variable values ​​for the self-operated route variable, the crowdsourced route variable, the crowdsourced affiliation variable, the self-operated start time variable, and the crowdsourced start time variable are obtained. Based on the target variable values ​​of the self-operated route variable, the crowdsourced route variable, the crowdsourced affiliation variable, the self-operated start time variable, the crowdsourced start time variable, and the first constraint condition, the target variable values ​​of the preceding route variable, the self-operated transfer variable, the crowdsourced transfer variable, and the preceding start time variable are determined.

3. The method for integrating and allocating self-operated and crowdsourced delivery capacity for e-commerce orders according to claim 1, characterized in that, The step of outputting the target allocation strategy for the set of orders to be allocated based on the target variable value of the decision variable includes: Based on the target variable values ​​of the decision variables, determine the initial allocation strategy for the set of orders to be allocated; Based on the initial allocation strategy, obtain the allocation strategy before this end-point optimization; The allocation strategy before this end-point optimization is removed to obtain the allocation strategy after this end-point removal; Based on the first constraint, the second constraint, and the third constraint, the allocation strategy after end removal is optimized to obtain the optimized allocation strategy. Based on the optimized allocation strategy for this terminal, the target allocation strategy is output.

4. The method for integrating and allocating self-operated and crowdsourced delivery capacity for e-commerce orders according to claim 3, characterized in that, The step of removing the allocation strategy before the current end-point optimization to obtain the allocation strategy after end-point removal includes: The last-mile removal orders are determined based on the allocation strategy prior to this last-mile optimization. Based on the current last-mile removal order, the allocation strategy before the current last-mile optimization is removed to obtain the allocation strategy after the current last-mile removal.

5. The method for integrating and allocating self-operated and crowdsourced delivery capacity for e-commerce orders according to claim 4, characterized in that, The process of determining the last-mile removal order for the current last-mile optimization allocation strategy includes: From the front-end service warehouses indicated by the current end-point optimization allocation strategy, a target front-end service warehouse with the fewest service products is determined. The allocation strategy is used to indicate the front-end service warehouses to be allocated orders, front-end service capacity, self-operated service capacity, crowdsourced service capacity, and the service orders of the front-end service warehouses, the loading orders of the front-end service capacity, the loading orders of the self-operated service capacity, and the loading orders of the crowdsourced service capacity. The service orders corresponding to the target front-end service warehouse are used as the orders removed from the end-point process. Alternatively, from the front-end service capacity indicated by the current end-to-end optimization allocation strategy, determine the target front-end service capacity with the smallest loading capacity; and use the loading order corresponding to the target front-end service capacity as the current end-to-end removal order. Alternatively, from the self-operated service capacity indicated by the allocation strategy before this last-mile optimization, determine the target self-operated service capacity with the smallest loading capacity; and use the loading order corresponding to the target self-operated service capacity as the last-mile removal order for this time. Alternatively, from the self-operated service capacity indicated by the allocation strategy before this last-mile optimization, randomly select self-operated service capacity; and use the loading order corresponding to the randomly selected self-operated service capacity as the last-mile removal order for this time. Alternatively, randomly select crowdsourced service capacity from the crowdsourced service capacity indicated by the allocation strategy before this end-point optimization; and use the loading order corresponding to the randomly selected crowdsourced service capacity as the end-point removal order for this time. Alternatively, from the orders to be assigned, obtain a first order cluster where the similarity of goods between orders is greater than a first preset similarity threshold; and use each order in the first order cluster as the final removal order for this time. Alternatively, from the orders to be assigned, obtain a second order cluster whose spatial similarity between orders is greater than a second preset similarity threshold; and use each order in the second order cluster as the final removal order for this time.

6. The method for integrating and allocating self-operated and crowdsourced delivery capacity for e-commerce orders according to claim 4, characterized in that, The process of performing end-cap removal optimization on the current end-cap removal allocation strategy based on the first constraint, the second constraint, and the third constraint to obtain the current end-cap optimized allocation strategy includes: Based on the first constraint, the second constraint, and the third constraint, detect the first end-of-line service capacity that minimizes the insertion cost of the current end-of-line removal order from the allocation strategy after this end-of-line removal. If the first end-to-end service capacity exists in the allocation strategy after the current end-to-end removal, then the current end-to-end removal order is added to the first end-to-end service capacity to complete the end-to-end optimization processing of the allocation strategy after the current end-to-end removal, and obtain the allocation strategy after the current end-to-end optimization. Alternatively, if the first end-to-end service capacity is not present in the current end-to-end removal allocation strategy, a second end-to-end service capacity is created and added to the current end-to-end optimization allocation strategy, and the current end-to-end removal order is added to the first end-to-end service capacity to complete the end-to-end optimization processing of the current end-to-end removal allocation strategy and obtain the current end-to-end optimization allocation strategy.

7. The method for integrating and allocating self-operated and crowdsourced delivery capacity for e-commerce orders according to claim 3, characterized in that, The step of outputting the target allocation strategy based on the current optimized allocation strategy includes: Based on the optimized allocation strategy for this terminal phase, the pre-optimized allocation strategy for this transit phase is determined; The allocation strategy before the current transfer optimization is removed to obtain the allocation strategy after the current transfer is removed; Based on the first constraint, the second constraint, and the third constraint, the allocation strategy after the current transfer removal is optimized to obtain the optimized allocation strategy for this transfer. Based on the optimized allocation strategy for this transfer, the target allocation strategy is output.

8. The method for integrating and allocating self-operated and crowdsourced delivery capacity for e-commerce orders according to claim 7, characterized in that, The step of removing the allocation strategy before the current transfer optimization to obtain the allocation strategy after the current transfer removal includes: The capacity to be removed in this transaction is determined from the end-service capacity indicated by the allocation strategy before the current transfer optimization, wherein the end-service capacity includes self-operated service capacity and crowdsourced service capacity; Based on the order group of the capacity removed this time, the allocation strategy before the current transfer optimization is removed to obtain the allocation strategy after the current transfer removal. In this order group, each order belongs to the same front-end capacity, and the total number of product categories in the order group is less than the preset total number of categories.

9. The method for integrating and allocating self-operated and crowdsourced delivery capacity for e-commerce orders according to claim 8, characterized in that, The process of optimizing the allocation strategy after the removal of the current transfer based on the first constraint, the second constraint, and the third constraint yields the optimized allocation strategy, including: Based on the first constraint, the second constraint, and the third constraint, detect the first front-end service capacity that minimizes the insertion cost of the current order group from the allocation strategy after the removal of this transit; If the first front-end service capacity exists in the current transfer removal and allocation strategy, then the current order group is added to the first front-end service capacity to complete the transfer optimization processing of the current transfer removal and allocation strategy, and obtain the current transfer optimization allocation strategy.

10. An electronic device, characterized in that, It includes a processor and a memory, wherein the memory stores a computer program, and when the processor invokes the computer program in the memory, it executes the self-operated and crowdsourced transportation capacity integration and allocation method for e-commerce orders as described in any one of claims 1 to 9.

Images