CN114970923A - Distribution order package-combining and distribution method and device and electronic equipment - Google Patents

Distribution order package-combining and distribution method and device and electronic equipment Download PDF

Info

Publication number
CN114970923A
CN114970923A CN202110206523.1A CN202110206523A CN114970923A CN 114970923 A CN114970923 A CN 114970923A CN 202110206523 A CN202110206523 A CN 202110206523A CN 114970923 A CN114970923 A CN 114970923A
Authority
CN
China
Prior art keywords
combination
order
orders
delivery
dispatching
Prior art date
Legal status (The legal status 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 status listed.)
Pending
Application number
CN202110206523.1A
Other languages
Chinese (zh)
Inventor
潘基泽
任昊
李冬辉
司徒陈麒
于洋
王圣尧
郝丛薇
夏梦煜
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Sankuai Online Technology Co Ltd
Original Assignee
Beijing Sankuai Online Technology Co Ltd
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 Beijing Sankuai Online Technology Co Ltd filed Critical Beijing Sankuai Online Technology Co Ltd
Priority to CN202110206523.1A priority Critical patent/CN114970923A/en
Publication of CN114970923A publication Critical patent/CN114970923A/en
Pending legal-status Critical Current

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
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
    • G06Q10/06311—Scheduling, planning or task assignment for a person or group
    • 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
    • G06Q10/0838—Historical data
    • 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
    • G06Q30/00—Commerce
    • G06Q30/06—Buying, selling or leasing transactions
    • G06Q30/0601—Electronic shopping [e-shopping]
    • G06Q30/0633—Lists, e.g. purchase orders, compilation or processing
    • G06Q30/0635—Processing of requisition or of purchase orders

Landscapes

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Economics (AREA)
  • Human Resources & Organizations (AREA)
  • Theoretical Computer Science (AREA)
  • Strategic Management (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Marketing (AREA)
  • General Business, Economics & Management (AREA)
  • Development Economics (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • Game Theory and Decision Science (AREA)
  • Finance (AREA)
  • Accounting & Taxation (AREA)
  • Software Systems (AREA)
  • Evolutionary Computation (AREA)
  • Medical Informatics (AREA)
  • Data Mining & Analysis (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Mathematical Physics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Artificial Intelligence (AREA)
  • Educational Administration (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The application discloses a delivery order group-combining and dispatching method, belongs to the technical field of computers, and is beneficial to improving the overall order dispatching efficiency of a delivery system. The delivery order form packing and dispatching method disclosed by the embodiment of the application comprises the following steps: acquiring a to-be-dispatched relation between each to-be-dispatched order and a delivery person, wherein the individual dispatching relation is established in an individual dispatching manner; aiming at maximizing a preset system performance index, taking meeting a preset distribution timeliness condition as a constraint, solving the combination of the orders to be dispatched, and determining the combined package dispatching information matched with the combination; and executing the co-package dispatching of the delivery order according to the co-package dispatching information. According to the delivery order package combining and dispatching method, the package combining operation is moved backwards, the delivery personnel information can be obtained during package combining, so that the package combining is carried out by referring to the delivery personnel information in the package combining process, the rejection rate of receiving the package combining orders by the delivery personnel is effectively reduced, and the order dispatching efficiency of the whole delivery system is improved.

Description

Distribution order package-combining and distribution method and device and electronic equipment
Technical Field
The embodiment of the application relates to the technical field of computers, in particular to a distribution order package-combining and dispatching method, a distribution order package-combining and dispatching device, electronic equipment and a computer-readable storage medium.
Background
In a delivery scheduling scene, delivery orders and delivery personnel need to be matched as efficiently as possible, so that delivery efficiency is improved, and user experience is improved. Consolidated dispatch of delivery orders is one means to increase delivery efficiency. The overall delivery efficiency of delivery orders can be effectively improved by distributing the delivery orders on the way to a delivery person. In the prior art, when distribution orders are packed and distributed, distribution cost and distribution efficiency are comprehensively considered, firstly, distribution orders are merged by taking the minimization of the distribution cost as a target, and then, the combined distribution orders are combined to distribute orders in a unit of combination. In the delivery order combination and dispatch method in the prior art, when delivery tasks are combined, delivery personnel information is not combined, and delivery personnel order receiving willingness to delivery order combinations is not referred to, so that the delivery order combination and dispatch success rate is possibly reduced, and the order dispatch efficiency is reduced.
In summary, the delivery order package dispatching method in the prior art needs to be improved.
Disclosure of Invention
The embodiment of the application provides a delivery order group-combining and dispatching method which is beneficial to improving order dispatching efficiency.
In a first aspect, an embodiment of the present application provides a delivery order co-package dispatching method, including:
acquiring a to-be-dispatched relation between each to-be-dispatched order and a delivery person, wherein the individual dispatching relation is established in an individual dispatching manner;
aiming at maximizing a preset system performance index, taking meeting a preset distribution timeliness condition as a constraint, solving the combination of the orders to be dispatched, and determining the combined package dispatching information matched with the combination;
and executing the co-package dispatching of the delivery order according to the co-package dispatching information.
In a second aspect, an embodiment of the present application provides a delivery order group distribution device, including:
the system comprises a dispatching relation acquisition module, a dispatching relation acquisition module and a dispatching relation calculation module, wherein the dispatching relation acquisition module is used for acquiring the dispatching relation between each order to be dispatched and a dispatching person, and the individual dispatching relation is established in an individual dispatching mode;
the package combination optimization module is used for solving the combination of the orders to be dispatched by taking the maximization of a preset system performance index as a target and meeting a preset distribution timeliness condition as a constraint, and determining package combination dispatching information matched with the combination;
and the package combining and dispatching module is used for executing the package combining and dispatching of the dispatching orders according to the package combining and dispatching information.
In a third aspect, an embodiment of the present application further discloses an electronic device, which includes a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor implements the delivery order co-package dispatching method described in the embodiment of the present application when executing the computer program.
In a fourth aspect, the present application provides a computer-readable storage medium, on which a computer program is stored, where the computer program is executed by a processor to perform the steps of the delivery order co-package dispatching method disclosed in the present application.
The delivery order package-combining and dispatching method disclosed by the embodiment of the application obtains the to-be-dispatched relation between each to-be-dispatched order and a delivery person, wherein the individual dispatching relation is established in an individual dispatching mode; aiming at maximizing a preset system performance index, taking meeting a preset distribution timeliness condition as a constraint, solving the combination of the orders to be dispatched, and determining the combined package dispatching information matched with the combination; and executing the co-package dispatching of the delivery order according to the co-package dispatching information, thereby being beneficial to improving the overall order dispatching efficiency of the delivery system.
The above description is only an overview of the technical solutions of the present application, and the present application may be implemented in accordance with the content of the description so as to make the technical means of the present application more clearly understood, and the detailed description of the present application will be given below in order to make the above and other objects, features, and advantages of the present application more clearly understood.
Drawings
In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some embodiments of the present application, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
FIG. 1 is a flowchart of a delivery order package dispatching method according to an embodiment of the present application;
FIG. 2 is a schematic diagram of a proposed distribution relationship according to an embodiment of the present application;
FIG. 3 is a schematic structural diagram of a probability of taking a bill as a predictive model according to a first embodiment of the present application;
fig. 4 is a schematic structural diagram of a second delivery order group delivery apparatus according to a second embodiment of the present application;
FIG. 5 schematically shows a block diagram of an electronic device for performing a method according to the present application; and
fig. 6 schematically shows a storage unit for holding or carrying program code implementing a method according to the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some, but not all, embodiments of the present application. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments in the present application without making any creative effort belong to the protection scope of the present application.
Example one
The delivery order form group-combining and dispatching method disclosed in the embodiment of the application is shown in fig. 1, and the method includes: step 110 to step 130.
Step 110, obtaining the to-be-dispatched relation between each order to be dispatched and the dispatching personnel; wherein the relation to be served is established by a separate serving manner.
The method and the device are applied to the order dispatching scene, the dispatching orders are combined and dispatched according to the appointed dispatching personnel set and the appointed order set to be dispatched, and on the premise that the dispatching timeliness is met, the condition that the dispatching personnel refuse to receive orders is reduced, so that the overall dispatching efficiency of the order dispatching system is improved. The appointed distribution personnel set refers to a set of distribution personnel capable of receiving orders to be distributed in the current time slice, and the appointed order set refers to a set of orders to be distributed in the current time slice.
In the embodiment of the application, firstly, an order dispatching method (such as greedy method) in the prior art is adopted to simulate and dispatch each to-be-dispatched order in a specified to-be-dispatched order set to one or more dispatching personnel in the specified dispatching personnel set one by one, and a dispatching relationship between each to-be-dispatched order and one or more dispatching personnel is established through the mode that each to-be-dispatched order is dispatched independently.
The relationship between each order to be dispatched and the dispatch of the dispatching personnel is shown graphically and may be as shown in FIG. 2. In fig. 2 are shown the to-be-dispensed orders a1 to a4, B1 to B6, C1 to C4, and D1 and D2, in relation to the intended dispatch of the distribution personnel 1 to 4, namely: the orders to be delivered currently to the delivery personnel 1 comprise: a1 to a 4; the orders to be distributed currently intended for the distributor 2 comprise: b1 to B6; the orders to be delivered currently to the delivery personnel 3 comprise: c1 to C4; the orders to be delivered currently to the delivery personnel 4 comprise: d1 and D2.
And step 120, aiming at maximizing a preset system performance index and meeting a preset distribution timeliness condition as a constraint, solving the combination of the orders to be dispatched, and determining the combined package dispatching information matched with the combination.
Next, for each delivery person, the combined delivery effect evaluation is performed on the to-be-delivered orders to be delivered to the delivery person, and the to-be-delivered orders to be delivered to each delivery person are adjusted, so that the adjusted to-be-delivered orders to be delivered to each delivery person can be formally delivered in a combined manner, and therefore the order delivery cost is saved, and the order delivery efficiency is improved.
In some embodiments of the present application, aiming at maximizing a preset system performance index, and satisfying a preset delivery timeliness condition as a constraint, solving a combination of the orders to be delivered, and determining a combined package delivery information matched with the combination, includes: and with the maximization of the preset system performance index as a target and the satisfaction of a preset distribution timeliness condition as a constraint, executing a solution combination optimization algorithm of destruction-reconstruction, solving the combination of the orders to be dispatched, and determining the combined package dispatching information matched with the combination.
The order dispatching efficiency can be improved by carrying out package-combining distribution on the orders to be distributed. For example, by solving the optimal order package combination situation, performing package combination dispatching on the optimal package combination order (such as an on-road order), and performing distribution by the same distributor, the order receiving probability of the package combination order can be improved, and the order dispatching efficiency of the distribution system can be improved. On the other hand, the order-by-route package is dispatched to a delivery person, which is helpful for improving the order delivery efficiency of the delivery person and the delivery system.
However, the delivery system also needs to take into account user experience issues. For example, delivery timeliness. The order to be delivered is subjected to group delivery, and when the same delivery personnel delivers the order, whether the delivery personnel can complete the delivery task of carrying the order within the appointed delivery time in the process of delivering the order needs to be considered. In an actual order delivery scenario, the delivery system needs to solve the balance between user experience, delivery efficiency, and delivery cost. For example, in a specific order delivery service, due to different service scenarios, different requirements for user experience and delivery efficiency and cost on the delivery system side often need to be replaced. In the scene of distribution by a stationing point, the requirement for saving the system cost is stronger. Taking the distribution task in severe weather as an example, the user experience demand can be stronger.
In summary, the package combination problem of the orders to be delivered in the delivery system can be described as a combinatorial optimization problem, that is, the overall package combination within the whole time slice results in a cost optimization problem. The optimization target is that the preset system performance index is maximized, and the constraint is the user experience index, namely the distribution timeliness condition. In some embodiments of the present application, the preset system performance index may be an overall delivery cost saving value, may also levy delivery order quantity, and may also be a performance measurement index for other delivery systems. For example, the preset system performance index is calculated according to the product of the order taking probability of the combination of the orders to be dispatched and the resource saving value. In some embodiments of the present application, the distribution aging condition may include, for example: the average distribution time length is less than or equal to a preset time length threshold value; the user experience indexes that the average bad rating rate or the complaint rate is lower than a preset number threshold value and the like can also be taken as the user experience indexes.
In some embodiments of the present application, one description of the problem of combining packages of orders to be delivered in a delivery system may be expressed as:
max sigma delivery personnel willingness to deliver tariff reduction value
The average distribution time length of s.t. sigma delta is not more than C
Wherein, the order-receiving will of the delivery personnel is assigned to the order-receiving will of the combination of orders to be delivered (namely the combined orders to be delivered) of the delivery personnel under the condition of the appointed delivery charge reduction value; for a combination of specified orders to be delivered, the delivery charge reduction value is determined according to a preset strategy according to the original delivery charge of the combination (for example, the delivery charge reduction value may be 90%, 80% of the total delivery charge of each order to be delivered in the combination, etc.); the average delivery duration C is the average delivery duration of all orders to be delivered carried on the back by the delivery person after the delivery person receives the combined delivery task.
In some embodiments of the present application, the targeting that the preset system performance index is maximized and satisfying the preset distribution timeliness condition as a constraint, executing a destructive-reconstruction solution combination optimization algorithm, solving a combination of the orders to be dispatched, and determining the combined package dispatching information matched by the combination includes: determining an order combination formed by at least two orders to be dispatched to the same dispatching personnel and an order taking probability of each order combination based on the dispatching relationship; taking the order combination with the order receiving probability meeting the preset unpacking condition as an order combination to be destroyed; determining one or more candidate delivery personnel for the pending orders that make up the combination of orders to be destroyed, wherein the candidate delivery personnel are selected from the delivery personnel; reconstructing a combination of orders to be dispatched for the orders currently to be dispatched by the candidate dispatching personnel and the orders to be dispatched which form the combination of the orders to be destroyed; different resource saving values are given to the reconstructed combination, the maximization of a preset system performance index is taken as a target, a preset distribution timeliness condition is met as a constraint, and the reconstructed combination of the orders to be dispatched is solved; and determining the combined package dispatching information matched with the combination according to the candidate delivery personnel of the combination of the reconstructed orders to be dispatched obtained by solving and the given resource saving value.
The optimization process of the combination of the orders to be delivered can be understood as unpacking the combination with a low order receiving probability for each delivery person who delivers the orders to be delivered in a round of combination, then dispatching the orders to be delivered obtained after unpacking to other delivery persons, and combining the orders to be delivered by the other delivery persons, and calculating whether the delivery results of the corresponding delivery persons to the orders to be piggybacked and the orders to be piggybacked meet the preset delivery timeliness condition (for example, whether the average delivery duration is less than the preset duration threshold) after the orders to be delivered combined and received are received. And then, under the constraint that whether the corresponding distribution personnel meet the preset distribution timeliness condition on the distribution results of the piggyback orders and the piggyback orders, searching a combined distribution mode which enables the performance index of the preset system to be maximized.
Specifically, the process of combinatorial optimization is divided into two steps: and an unpacking step and a rebuilding step, wherein the unpacking step and the rebuilding step are executed circularly under the given constraint, so that a packing scheme meeting the optimization target is determined. The package combination scheme described in the embodiments of the present application includes two layers: in the first layer, which orders are combined to form a combination of orders to be delivered; and on the second layer, who is the candidate delivery personnel of the combination of the orders to be delivered obtained after the combination.
The following describes, by way of example, a solution-combination optimization algorithm for performing destruction-reconstruction, with reference to the relation to be served shown in fig. 2, to solve the specific combination scheme of the order to be served.
First, it needs to determine the order to be delivered that is not suitable for package delivery in the current dispatching relationship.
For each delivery person, one or more orders to be delivered have been scheduled for delivery. As can be seen from the foregoing description, when the delivery order is to be dispatched, order package delivery is not considered, so that, among the orders to be dispatched to a delivery person, some orders are suitable for package delivery and some orders are not suitable for package delivery. The order which is not suitable for the group delivery for a certain delivery person may be suitable for the order to be dispatched by other delivery persons for the group delivery. Therefore, the order to be delivered, which is not suitable for contract delivery, needs to be determined according to the current dispatch relationship, that is, the corresponding relationship between the delivery personnel and the order to be delivered.
In some embodiments of the present application, for an order to be delivered to a delivery person, the order to be delivered may be grouped by using a method in the prior art, and an order receiving probability of the group to be delivered, obtained by grouping, may be estimated. For example, for the distribution staff 2, the orders to be distributed B1 to B6 to be distributed to the distribution staff 2 are subjected to bag combination processing in the prior art, and the order taking probability of each order combination to be distributed obtained after the bag combination processing by the distribution staff 2 is estimated by using the estimation method of the order taking probability in the prior art.
And then, determining the order combination to be delivered, of which the order receiving probability is smaller than a preset order receiving probability threshold value, as an unreasonable package combination. Taking the example that the order taking probability of the combination obtained by the to-be-distributed orders B5 and B6 by the distribution staff 2 is smaller than the preset order taking probability threshold value, it may be determined that the to-be-distributed orders B5 and B6 are not suitable for being distributed to the distribution staff 2, that is, it is determined that the to-be-distributed orders B5 and B6 meet the preset unpacking conditions, and the to-be-distributed orders B5 and B6 are used as the to-be-destroyed order combination, and need to be re-proposed for the to-be-distributed orders B5 and B6.
Second, candidate dispatchers for orders to be delivered that are not suitable for package delivery need to be determined.
Next, it is necessary to further determine to which delivery person the orders to be delivered B5 and B6, respectively, are suitable for delivery to delivery person 2 for unsuitable packages. In some embodiments of the present application, determining one or more candidate dispatchers of the order to be dispatched that constitutes the combination of orders to be destroyed includes one or more of: determining candidate delivery personnel of the to-be-delivered order in the to-be-destroyed order combination according to the distance between the real-time position of the delivery personnel and the order taking address or the delivery address of the to-be-delivered order of the to-be-destroyed order combination; determining candidate delivery personnel of the order to be delivered in the order combination to be destroyed according to the number of delivery orders carried by the delivery personnel currently; and determining candidate delivery personnel of the to-be-delivered order in the to-be-destroyed order combination according to the forward degree of the delivery order carried by the delivery personnel currently and the to-be-delivered order of the to-be-destroyed order combination.
Taking the to-be-distributed order B5 unsuitable for being dispatched by a subcontract as an example, if the distributor 1 is on the way of the to-be-distributed order B5, the distributor 1 can be determined as a candidate for the to-be-distributed order B5; if the number of orders currently piggybacked by the delivery person 3 is smaller than the preset number threshold and the real-time position of the delivery person 3 is smaller than the order taking address of the order B5 to be delivered by the preset distance threshold, the delivery person 3 may be determined as a candidate for the order B5 to be delivered. In other embodiments of the present application, the candidate delivery personnel for the order to be delivered may also be determined in other manners, which are not illustrated in the embodiments of the present application.
Candidate delivery personnel of the orders to be delivered are determined according to a preset strategy, and then subsequent combined reconstruction of the orders with delivery is carried out, so that the range of the candidate delivery personnel can be effectively reduced, the number of the reconstructed combinations is reduced, and the combined solving speed is improved.
After that, combined reconstruction is performed.
Taking the example that the candidate delivery persons of order to be delivered B5 include delivery person 1 and delivery person 3, then a combination of orders to be delivered may be established in the form of a polynomial such as KM on the basis of the orders to be delivered currently to delivery person 1 and delivery person 3, for example, a possible combination of the orders to be delivered currently to delivery person 1 and order to be delivered B5 is determined, and a possible combination of the orders to be delivered currently to delivery person 3 and order to be delivered B5 is determined. Then, the order taking probability of the established combination of the orders to be delivered is estimated, and the corresponding relation between the combination of the orders to be delivered, of which the order taking probability is greater than a preset probability threshold value, and the candidate delivery personnel is determined.
Taking as an example that the to-be-delivered order B5 and the to-be-delivered orders a2 and A3 currently to be dispatched to the dispatching personnel 1 are respectively bundled to form two combinations of the to-be-delivered orders, the order taking probabilities of the two combinations are both greater than the preset probability threshold, and the to-be-delivered order B5 and the to-be-delivered order C2 currently to be dispatched to the dispatching personnel 3 are bundled to form one combination of the to-be-delivered orders, the order taking probability is also greater than the preset probability threshold, the reconstructed combination of the to-be-delivered orders can be expressed as: { delivery person 1, to-be-delivered order a2, to-be-delivered order B5}, { delivery person 1, to-be-delivered order A3, to-be-delivered order B5}, and { delivery person 3, to-be-delivered order C2, to-be-delivered order B5 }.
It should be understood by those skilled in the art that in practical applications, the number of candidate dispatchers and orders to be delivered is large, and the number of combinations of orders to be delivered obtained by reconstruction is also very large, and the combinations illustrated in this embodiment are only specific examples for facilitating the understanding of the schemes of combination reconstruction, and should not be taken as a limitation to this application.
And finally, solving the optimal combination.
And for the combination of the orders to be distributed obtained after reconstruction, further solving the optimal combination according to the constraint conditions and the target of the combination optimization problem.
In some embodiments of the present application, different resource saving values are given to the reconstructed combinations, the preset system performance index is maximized as a target, and a preset delivery timeliness condition is satisfied as a constraint, and solving the reconstructed combinations of the orders to be dispatched includes: the order taking probability of each combination of the orders to be dispatched, which are reconstructed by the candidate dispatching personnel, is estimated when the resource saving values are given differently by executing a pre-trained order taking probability estimation model; estimating the average delivery time length of each candidate delivery person after receiving the combination of the re-delivered orders to be delivered; determining the combination of the orders to be dispatched, which enables the preset system performance index to be maximum, under the condition that the average distribution time length is less than or equal to the preset time length threshold value; and the preset system performance index is obtained by calculation according to the product of the order taking probability of the combination of the orders to be dispatched and the resource saving value.
For example, for each combination of orders to be delivered obtained after reconstruction (for example, the candidate delivery person is the combination of orders to be delivered a2 and B5 of the delivery person 1), it is first determined that, in the case of performing group-by-group delivery by using the combination, the average delivery duration of the orders to be delivered by the delivery person 1 (including the orders to be delivered already piggybacked and the orders to be delivered to the delivery person 1) is determined, and if the average delivery duration does not satisfy the aforementioned constraint, the current reconstruction combination is abandoned, and the other combination cases are continuously traversed. If the average distribution time length meets the constraint, the preset system performance index of the distribution system under the current reconstruction combination condition is further calculated.
Through traversing the multiple reconstructed combination conditions, preset system performance index values under multiple different combination conditions can be obtained, and the reconstruction combination condition with the maximum preset system performance index value is selected as the basis for finally performing group-combining distribution.
The combination obtained after the reconstruction and obtained by the solution is the combination of the matching designated candidate delivery personnel and the designated resource saving value, and further, according to the designated candidate delivery personnel matched with the combination obtained after the reconstruction and obtained by the solution, the combination delivery information of the combination obtained after the reconstruction and obtained by the solution, the delivery personnel and the resource saving value can be determined. For example, after determining that the combination of orders to be served A2 and B5 is a combination that satisfies the constraints and optimization objectives described above, the combination of distributor 1 and orders to be served A2 and B5 may be determined to serve information for the optimal portfolio at a delivery resource reduction value of 0.55 dollars. The order is dispatched according to the contract dispatching information, so that the order receiving probability can be improved, and the distribution cost of a distribution system can be saved.
In some embodiments of the present application, the average delivery duration may be estimated according to the portrait information and piggybacked order information of the delivery personnel by a method in the prior art, which is not described in detail in the embodiments of the present application.
In some embodiments of the present application, the delivery person's combined pick-up probability of the order to be delivered is estimated through a pre-trained pick-up probability estimation model.
In some embodiments of the present application, the order taking probability prediction model may adopt a network structure as shown in fig. 3. As shown in fig. 3, the pre-estimation model of the order taking probability includes: the multi-head self-attention network 320 is used for performing order-independent feature mapping on combination information (for example, vectors obtained after order attribute information such as a picking and delivering position and a placing time of each order) of an order combination of the input value network to obtain combined order features; the fully-connected layer 330 is configured to perform fusion mapping on the vectors input to the layer to obtain a single-join probability corresponding to the model input.
The model input of the order taking probability pre-estimation model comprises three parts: the information of the resource, the combination information of the combination of the orders to be delivered, and the information of the candidate delivery personnel. In some embodiments of the present application, training samples may be constructed according to historical package-closing distribution data to train the single-connect probability estimation model. Wherein the sample data of the training samples comprises: the method comprises the steps of obtaining resource information of a package combination order, combination information of the package combination order, information of a distributor dispatched by the package combination order, and order taking probability of the distributor based on a sample label of a training sample. The specific meanings of the resource information, the combination information and the information of the distribution personnel, which are input as the model in the sample data, are referred to in the following description of the order taking probability prediction stage, and are not described herein again.
The training process of the order taking probability prediction model refers to the training process of a neural network model in the prior art, and is not repeated in the embodiment of the application.
In some embodiments of the present application, the pre-estimating, by executing a pre-trained order taking probability pre-estimation model, an order taking probability of each of the combinations of orders to be dispatched of the reconstruction of the candidate dispatchers at different times of giving the resource saving value includes: for each of the combinations of the orders to be dispatched of the rebuilt of each of the candidate delivery personnel, respectively performing the following order taking probability estimation operations: determining a model input at which the combination of orders to be served corresponds to each of the resource savings values, the model input comprising: the combined resource information, the combined information of the combination, and the information of the candidate delivery personnel; wherein the resource information includes: the combined resource consumption information, the current resource saving value information; the combination information includes: preset order attribute information of each order to be dispatched in the combination, and/or associated location information of the order to be dispatched in the combination; the information of the candidate delivery personnel comprises: image information of the candidate delivery personnel and/or order information carried by the candidate delivery personnel currently; executing the pre-trained order taking probability pre-estimation model, and performing order taking probability pre-estimation respectively based on the model input when the combination of the orders to be dispatched corresponds to each resource saving value to obtain the order taking probability of the combination of the orders to be dispatched, wherein the combination of the orders to be dispatched is matched with different resource saving values by the candidate delivery personnel.
For example, for the delivery person 1, the combination of orders to be delivered obtained after reconstruction includes: the combination of orders to be delivered A2 and B5, and the combination of orders to be delivered A3 and B5, then the order taking probability of delivery person 1 to the combination of orders to be delivered A2 and B5, and the order taking probability of delivery person 1 to the combination of orders to be delivered A3 and B5, respectively, need to be estimated.
Taking the pre-estimated delivery probability of the delivery person 1 for the combination of the orders to be delivered A2 and B5 through the trained pre-estimated delivery probability model as an example, the following describes the technical scheme of the delivery person for the combination of the orders to be delivered specified at different given resource saving values.
First, the model input is determined based on the information of the combination of orders to be delivered A2 and B5, and the information of delivery person 1.
For the combination of orders to be delivered A2 and B5, the model input section includes the resource information and combination information for the combination.
Further, the resource information includes resource consumption information (such as total delivery cost) of the orders a2 and B5 to be delivered in the combination, and resource saving value information (such as delivery cost reduction value caused by contract). Wherein, different resource saving values are determined according to a preset strategy. Taking the resource saving value as the delivery charge reduction value as an example, in some embodiments of the present application, different delivery charge reduction values (i.e., resource saving values) of the combination may be determined according to different reduction ratios of the total delivery charge amount of each to-be-delivered order in the combination. Taking the delivery charge of to-be-delivered order a2 as 5 yuan, the delivery charge of to-be-delivered order B5 as 6 yuan, and the total delivery charge of the combination of to-be-delivered orders a2 and B5 as 11, the delivery charge reduction value of the combination of to-be-delivered orders a2 and B5 may be: 0.55, 1.1, 2.2, or other delivery cost reduction value. Then, a set of model inputs is constructed with each delivery tariff reduction value and the combined delivery tariff sum, respectively.
Wherein the combination information may include: preset order attribute information of the orders to be dispatched A2 and B5 respectively; alternatively, the combination information may include: the preset order attribute information of the orders to be dispatched A2 and B5, and the associated delivery point information and the pick-up point information of the orders to be dispatched A2 and B5.
In some embodiments of the present application, the model input further comprises: information of the delivery person of the combination of orders to be delivered, such as the information of the delivery person 1. Further, the information of the candidate delivery personnel may include one or more of the age, the working age and the grade of the delivery personnel 1, and the order information currently carried by the delivery personnel 1 (such as the number of delivery orders currently carried by the delivery personnel 1, the order taking address and the delivery address of each delivery order, etc.).
After the model input is determined, inputting the model input into the order taking probability pre-estimation model, executing program codes of the pre-trained order taking probability pre-estimation model, and performing order taking probability pre-estimation based on the model input to obtain the order taking probability of the distributor 1 at a specified distribution expense reduction value (such as 0.55 yuan) when the to-be-distributed orders A2 and B5 are combined.
According to the method, the order taking probability of each candidate delivery person for the reconstructed combination of each order to be delivered at different delivery charge reduction values can be determined.
In some embodiments of the present application, the pre-estimation model of the order taking probability comprises: the multi-head self-attention network, wherein the executing of the pre-trained order taking probability pre-estimation model respectively performs order taking probability pre-estimation based on the model input when the combination of the orders to be dispatched corresponds to each resource saving value, and comprises the following steps: performing sequence-independent feature mapping on the combined information of the combination of the orders to be dispatched in the model input by executing the multi-head self-attention network to obtain combined order features; and performing fusion mapping on the combined order characteristic, the resource characteristic obtained by performing characteristic mapping on the combined resource information and the distribution personnel characteristic obtained by performing characteristic mapping on the information of the candidate distribution personnel to obtain the order taking probability corresponding to the model input.
When executing the program code of the order taking probability pre-estimation model, the program code firstly encodes data of different parts in the model input to obtain corresponding feature vectors, for example, encodes resource information such as the combined distribution tariff total and the distribution tariff reduction value to obtain resource features; the distribution personnel characteristics are obtained after the image information, the piggyback order information and the like of the candidate distribution personnel are subjected to characteristic mapping; and coding order attribute information such as the price, the distance, the delivery address and the like of each order to be delivered in the combination to obtain order characteristics of each order. And then, executing the program codes of the multi-head self-attention network, and performing sequence-independent feature mapping on the order features of each order to obtain combined order features. And finally, executing program codes of a full connection layer, and performing fusion mapping on the resource characteristics, the distribution personnel characteristics and the combined order characteristics output by the network module to obtain the order receiving probability corresponding to the input of the current model.
And step 130, executing the combined package dispatching of the delivery order according to the combined package dispatching information.
The group-combining distribution information in the embodiment of the application comprises: order information to be distributed, distribution personnel information and package resource saving value information of the package are combined.
After the combination optimization solution is carried out through the steps, the combination of the orders to be distributed which meets the constraint conditions and the optimization targets, the corresponding relation between the corresponding resource saving values and the distribution personnel when the combination of the orders to be distributed meets the optimization targets and the constraints are used as the reference for the co-package distribution, and the subsequent order distribution is executed.
Still taking the reconstructed orders to be delivered a2 and B5 determined in the foregoing steps as an example, if the combination of the orders to be delivered a2 and B5 meets the above constraint conditions and optimization goal at a delivery cost reduction value of 0.55 yuan, the order to be delivered a2 and B5 bundles may be delivered to the delivery person 1 according to the determined bundle delivery information, and the delivery cost reduction value is set to 0.55 yuan.
The delivery order package-combining and dispatching method disclosed by the embodiment of the application obtains the to-be-dispatched relation between each to-be-dispatched order and a delivery person, wherein the individual dispatching relation is established in an individual dispatching mode; aiming at maximizing a preset system performance index, taking meeting a preset distribution timeliness condition as a constraint, solving the combination of the orders to be dispatched, and determining the combined package dispatching information matched with the combination; and executing the package-combining dispatching of the delivery orders according to the package-combining dispatching information, thereby being beneficial to improving the overall order dispatching efficiency of the delivery system.
According to the delivery order package combining and dispatching method disclosed by the embodiment of the application, the package combining operation is moved backwards, and the delivery personnel information can be obtained during package combining, so that the package combining is carried out by referring to the delivery personnel information in the package combining process, the rejection rate of receiving the package combining orders by the delivery personnel is effectively reduced, and the order dispatching efficiency of the whole delivery system is improved.
On the other hand, a combined solving algorithm of operation and planning optimization is introduced in the package combining process, the preset system performance index and the distribution timeliness of the distribution system are balanced and adjusted, the user experience and the operation cost of the distribution system are comprehensively considered under the condition that the order distribution efficiency of the distribution system is improved, and the overall improvement of the business objective is achieved.
Furthermore, the machine learning model is introduced to learn and predict the combined order taking probability, the probability information of the combined order taking is learned from various historical order data, the accuracy of the estimation of the order taking probability is improved, and therefore the accuracy of the solution of the combined order is improved.
Example two
The delivery order group distribution device disclosed in the embodiment of the present application, as shown in fig. 4, the device includes:
a dispatch relation obtaining module 410, configured to obtain a dispatch relation between each to-be-dispatched order and a dispatching person, where the individual dispatch relation is established in an individual dispatch manner;
the package combination optimization module 420 is configured to, with a goal of maximizing a preset system performance index and satisfying a preset distribution timeliness condition as a constraint, solve a combination of the orders to be dispatched, and determine package combination dispatching information matched with the combination;
and a group-combining dispatching module 430, configured to execute group-combining dispatching of the delivery order according to the group-combining dispatching information.
In some embodiments of the application, the package combining optimization module 420 is further configured to:
and with the aim of maximizing the preset system performance index and meeting the preset distribution timeliness condition as the constraint, executing a destructive-reestablishment solution combined optimization algorithm, solving the combination of the orders to be distributed, and determining the combined package distribution information matched with the combination.
In some embodiments of the present application, the targeting that the preset system performance index is maximized and satisfying the preset distribution timeliness condition as a constraint, executing a destructive-reconstruction solution combination optimization algorithm, solving a combination of the orders to be dispatched, and determining the combined package dispatching information matched by the combination includes:
determining an order combination formed by at least two orders to be dispatched to the same delivery person and the order taking probability of each order combination based on the dispatching relation;
taking the order combination with the order receiving probability meeting the preset unpacking condition as an order combination to be destroyed;
determining one or more candidate delivery personnel for the pending orders that make up the combination of orders to be destroyed, wherein the candidate delivery personnel are selected from the delivery personnel;
reconstructing a combination of orders to be dispatched for the orders currently to be dispatched by the candidate dispatching personnel and the orders to be dispatched which form the combination of the orders to be destroyed;
different resource saving values are given to the reconstructed combination, the maximization of a preset system performance index is taken as a target, a preset distribution timeliness condition is met as a constraint, and the reconstructed combination of the orders to be dispatched is solved;
and determining the combined package dispatching information matched with the combination according to the candidate delivery personnel of the combination of the reconstructed orders to be dispatched obtained by solving and the given resource saving value.
In some embodiments of the subject application, determining one or more candidate dispatchers of the orders to be dispatched that constitute the combination of orders to be destroyed includes any one or more of:
determining candidate delivery personnel of the orders to be dispatched in the order combination to be destroyed according to the distance between the real-time position of the delivery personnel and the order taking address or the delivery address of the orders to be dispatched of the order combination to be destroyed;
determining candidate delivery personnel of the order to be delivered in the order combination to be destroyed according to the number of delivery orders carried by the delivery personnel currently;
and determining candidate delivery personnel of the to-be-delivered order in the to-be-destroyed order combination according to the forward degree of the delivery order carried by the delivery personnel currently and the to-be-delivered order of the to-be-destroyed order combination.
In some embodiments of the present application, the preset delivery timeliness condition includes that the average delivery duration is less than or equal to a preset duration threshold, different resource saving values are given to the reconstructed combination, a preset system performance index is maximized as a target, the preset delivery timeliness condition is satisfied as a constraint, and the solution of the reconstructed combination of the orders to be dispatched includes:
the order taking probability of each combination of the orders to be dispatched, which are reconstructed by the candidate dispatching personnel, is estimated when the resource saving values are given differently by executing a pre-trained order taking probability estimation model; estimating the average delivery time length of each candidate delivery person after receiving the combination of the re-delivered orders to be delivered;
determining the combination of the orders to be dispatched, which enables the preset system performance index to be maximum, under the condition that the average distribution time length is less than or equal to the preset time length threshold value; and the preset system performance index is obtained by calculation according to the product of the order taking probability of the combination of the orders to be dispatched and the resource saving value.
In some embodiments of the present application, the pre-estimating, by executing a pre-trained order taking probability pre-estimation model, an order taking probability of each of the combinations of orders to be dispatched of the reconstruction of the candidate dispatchers at different times of giving the resource saving value includes:
for each of the combinations of the orders to be dispatched of the rebuilt of each of the candidate delivery personnel, respectively performing the following order taking probability estimation operations:
determining a model input at which the combination of orders to be served corresponds to each of the resource savings values, the model input comprising: the combined resource information, the combined information of the combination, and the information of the candidate delivery personnel; wherein the resource information includes: the combined resource consumption information, the current resource saving value information; the combination information includes: preset order attribute information of each order to be dispatched in the combination, and/or associated location information of the order to be dispatched in the combination; the information of the candidate delivery personnel comprises: image information of the candidate delivery personnel and/or order information carried by the candidate delivery personnel currently;
executing the pre-trained order taking probability pre-estimation model, and performing order taking probability pre-estimation respectively based on the model input when the combination of the orders to be dispatched corresponds to each resource saving value to obtain the order taking probability of the combination of the orders to be dispatched, wherein the combination of the orders to be dispatched is matched with different resource saving values by the candidate delivery personnel.
In some embodiments of the present application, the pre-estimation model of the order taking probability comprises: the multi-head self-attention network, wherein the executing of the pre-trained order taking probability pre-estimation model respectively performs order taking probability pre-estimation based on the model input when the combination of the orders to be dispatched corresponds to each resource saving value, and comprises the following steps:
performing sequence-independent feature mapping on the combined information of the combination of the orders to be dispatched in the model input by executing the multi-head self-attention network to obtain combined order features;
and performing fusion mapping on the combined order features, the resource features obtained by performing feature mapping on the combined resource information, and the distribution personnel features obtained by performing feature mapping on the information of the candidate distribution personnel to obtain the order receiving probability corresponding to the model input.
The delivery order group dispatching device disclosed in the embodiment of the present application is used to implement the delivery order group dispatching method described in the first embodiment of the present application, and specific implementation manners of each module of the device are not described again, and reference may be made to specific implementation manners of corresponding steps in the method embodiment.
The delivery order group-combining and dispatching device disclosed by the embodiment of the application acquires the to-be-dispatched relation between each to-be-dispatched order and a delivery person, wherein the individual dispatching relation is established in an individual dispatching manner; aiming at maximizing a preset system performance index, taking meeting a preset distribution timeliness condition as a constraint, solving the combination of the orders to be dispatched, and determining the combined package dispatching information matched with the combination; and executing the package-combining dispatching of the delivery orders according to the package-combining dispatching information, thereby being beneficial to improving the overall order dispatching efficiency of the delivery system.
The delivery order closes a packet dispatching device that this application embodiment discloses through closing a packet operation retrusion, can acquire delivery personnel information when closing a packet to close a packet in-process reference delivery personnel information and close a packet, effectively reduced delivery personnel to the refusal rate of receiving orders that closes a packet of orders, thereby promoted whole delivery system's order dispatch efficiency.
On the other hand, a combined solving algorithm of operation and planning optimization is introduced in the package combining process, the preset system performance index and the distribution timeliness of the distribution system are balanced and adjusted, the user experience and the operation cost of the distribution system are comprehensively considered under the condition that the order distribution efficiency of the distribution system is improved, and the overall improvement of the business objective is achieved.
Furthermore, the machine learning model is introduced to learn and predict the combined order taking probability, the probability information of the combined order taking is learned from various historical order data, the accuracy of the estimation of the order taking probability is improved, and therefore the accuracy of the solution of the combined order is improved.
The embodiments in the present specification are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. For the apparatus embodiment, since it is substantially similar to the method embodiment, the description is relatively simple, and reference may be made to the partial description of the method embodiment for relevant points.
The above detailed description is given to the delivery order form-pooling dispatching method and device provided by the present application, and specific examples are applied herein to explain the principle and implementation manner of the present application, and the description of the above embodiments is only used to help understand the method and a core idea of the present application; meanwhile, for a person skilled in the art, according to the idea of the present application, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present application.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
The various component embodiments of the present application may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art will appreciate that a microprocessor or Digital Signal Processor (DSP) may be used in practice to implement some or all of the functionality of some or all of the components in an electronic device according to embodiments of the present application. The present application may also be embodied as apparatus or device programs (e.g., computer programs and computer program products) for performing a portion or all of the methods described herein. Such programs implementing the present application may be stored on a computer readable medium or may be in the form of one or more signals. Such a signal may be downloaded from an internet website or provided on a carrier signal or in any other form.
For example, fig. 5 shows an electronic device that may implement a method according to the present application. The electronic device can be a PC, a mobile terminal, a personal digital assistant, a tablet computer and the like. The electronic device conventionally comprises a processor 510 and a memory 520, and program code 530 stored on said memory 520 and executable on the processor 510, said processor 510 implementing the method described in the above embodiments when executing said program code 530. The memory 520 may be a computer program product or a computer readable medium. The memory 520 may be an electronic memory such as a flash memory, an EEPROM (electrically erasable programmable read only memory), an EPROM, a hard disk, or a ROM. The memory 520 has a storage space 5201 for program code 530 of the computer program for performing any of the method steps of the above-described method. For example, the storage space 5201 for the program code 530 may include respective computer programs for implementing the respective steps in the above methods. The program code 530 is computer readable code. The computer programs may be read from or written to one or more computer program products. These computer program products comprise a program code carrier such as a hard disk, a Compact Disc (CD), a memory card or a floppy disk. The computer program comprises computer readable code which, when run on an electronic device, causes the electronic device to perform the method according to the above embodiments.
The embodiment of the present application further discloses a computer-readable storage medium, on which a computer program is stored, which when executed by a processor, implements the steps of the delivery order co-package distribution method according to the foregoing embodiment of the present application.
Such a computer program product may be a computer-readable storage medium that may have memory segments, memory spaces, etc. arranged similarly to the memory 520 in the electronic device shown in fig. 5. The program code may be stored in a computer readable storage medium, for example, compressed in a suitable form. The computer readable storage medium is typically a portable or fixed storage unit as described with reference to fig. 6. Typically, the storage unit comprises computer readable code 530 ', said computer readable code 530' being code read by a processor, which when executed by the processor, performs the steps of the method described above.
Reference herein to "one embodiment," "an embodiment," or "one or more embodiments" means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the present application. Moreover, it is noted that instances of the word "in one embodiment" are not necessarily all referring to the same embodiment.
In the description provided herein, numerous specific details are set forth. However, it is understood that embodiments of the application may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.
In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The application may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means can be embodied by one and the same item of hardware. The usage of the words first, second and third, etcetera do not indicate any ordering. These words may be interpreted as names.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, and not to limit the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions in the embodiments of the present application.

Claims (10)

1. A delivery order co-packing and dispatching method is characterized by comprising the following steps:
acquiring a to-be-dispatched relation between each to-be-dispatched order and a delivery person, wherein the individual dispatching relation is established in an individual dispatching manner;
aiming at maximizing a preset system performance index, solving the combination of the orders to be dispatched by taking the preset distribution timeliness condition as a constraint, and determining the combined package dispatching information matched with the combination;
and executing the co-package dispatching of the delivery order according to the co-package dispatching information.
2. The method according to claim 1, wherein the step of solving the combination of the orders to be dispatched and determining the combined package dispatching information matched with the combination with the target of maximizing the preset system performance index and the constraint of satisfying the preset dispatching aging condition comprises:
and with the maximization of the preset system performance index as a target and the satisfaction of a preset distribution timeliness condition as a constraint, executing a solution combination optimization algorithm of destruction-reconstruction, solving the combination of the orders to be dispatched, and determining the combined package dispatching information matched with the combination.
3. The method according to claim 2, wherein the step of executing a destructive-reconstruction solution-combination optimization algorithm with the target of maximizing the preset system performance index and the constraint of satisfying the preset distribution time-efficiency condition, solving the combination of the orders to be dispatched, and determining the combined package dispatching information matched with the combination comprises:
determining an order combination formed by at least two orders to be dispatched to the same delivery person and the order taking probability of each order combination based on the dispatching relation;
taking the order combination with the order receiving probability meeting the preset unpacking condition as an order combination to be destroyed;
determining one or more candidate delivery personnel for the pending orders that make up the combination of orders to be destroyed, wherein the candidate delivery personnel are selected from the delivery personnel;
reconstructing a combination of orders to be dispatched for the orders currently to be dispatched by the candidate dispatching personnel and the orders to be dispatched which form the combination of the orders to be destroyed;
different resource saving values are given to the reconstructed combination, the maximization of a preset system performance index is taken as a target, a preset distribution time effect condition is met as a constraint, and the reconstructed combination of orders to be dispatched is solved;
and determining the combined package dispatching information matched with the combination according to the candidate delivery personnel of the combination of the reconstructed orders to be dispatched obtained by solving and the given resource saving value.
4. The method according to claim 3, wherein the preset delivery timeliness condition includes that the average delivery duration is less than or equal to a preset duration threshold, and the step of solving the combination of the reconstructed orders to be dispatched by giving different resource saving values to the combination of the reconstruction, targeting the maximization of the preset system performance index, and satisfying the preset delivery timeliness condition as a constraint comprises:
the order receiving probability of each combination of the orders to be dispatched, which are rebuilt by the candidate dispatching personnel, is estimated when the resource saving values are given differently through executing a pre-trained order receiving probability estimation model; estimating the average delivery time length of each candidate delivery person after receiving the combination of the re-delivered orders to be delivered;
determining the combination of the orders to be dispatched, which enables the preset system performance index to be maximum, under the condition that the average distribution time length is less than or equal to the preset time length threshold value; and the preset system performance index is obtained by calculation according to the product of the order taking probability of the combination of the orders to be dispatched and the resource saving value.
5. The method of claim 4, wherein said step of predicting the pick-up probability of each said combination of orders to be dispatched for each said candidate dispatch personnel's rebuild at different given said resource savings value by executing a pre-trained pick-up probability prediction model comprises:
for each of the combinations of the orders to be dispatched of the rebuilt of each of the candidate delivery personnel, respectively performing the following order taking probability estimation operations:
determining a model input at which the combination of orders to be served corresponds to each of the resource savings values, the model input comprising: the combined resource information, the combined information of the combination, and the information of the candidate delivery personnel; wherein the resource information includes: the combined resource consumption information, the current resource saving value information; the combination information includes: preset order attribute information of each order to be dispatched in the combination, and/or associated location information of the order to be dispatched in the combination; the information of the candidate delivery personnel comprises: image information of the candidate delivery personnel and/or order information carried by the candidate delivery personnel currently;
executing the pre-trained order taking probability pre-estimation model, and performing order taking probability pre-estimation respectively based on the model input when the combination of the orders to be dispatched corresponds to each resource saving value to obtain the order taking probability of the combination of the orders to be dispatched by the candidate dispatching personnel when the combination of the orders to be dispatched matches different resource saving values.
6. The method of claim 5, wherein the pre-estimation of probability of pickup model comprises: the multi-head self-attention network, wherein the step of executing the pre-trained order taking probability pre-estimation model respectively performs order taking probability pre-estimation based on the model input when the combination of the orders to be dispatched corresponds to each resource saving value, comprises the following steps:
performing sequence-independent feature mapping on the combined information of the combination of the orders to be dispatched in the model input by executing the multi-head self-attention network to obtain combined order features;
and performing fusion mapping on the combined order characteristic, the resource characteristic obtained by performing characteristic mapping on the combined resource information and the distribution personnel characteristic obtained by performing characteristic mapping on the information of the candidate distribution personnel to obtain the order taking probability corresponding to the model input.
7. The method of claim 3, wherein the step of determining one or more candidate dispatchers of the order to be dispatched that constitutes the combination of orders to be destroyed comprises any one or more of:
determining candidate delivery personnel of the orders to be dispatched in the order combination to be destroyed according to the distance between the real-time position of the delivery personnel and the order taking address or the delivery address of the orders to be dispatched of the order combination to be destroyed;
determining candidate delivery personnel of the orders to be delivered in the order combination to be destroyed according to the number of delivery orders carried by the delivery personnel currently;
and determining candidate delivery personnel of the to-be-delivered order in the to-be-destroyed order combination according to the forward degree of the delivery order carried by the delivery personnel currently and the to-be-delivered order of the to-be-destroyed order combination.
8. A delivery order group delivery device, comprising:
the system comprises a dispatching relation acquisition module, a dispatching relation acquisition module and a dispatching management module, wherein the dispatching relation acquisition module is used for acquiring the dispatching relation between each order to be dispatched and a dispatching person, and the individual dispatching relation is established in an individual dispatching mode;
the combined package optimization module is used for solving the combination of the orders to be dispatched by taking the maximization of a preset system performance index as a target and meeting a preset distribution timeliness condition as a constraint, and determining combined package dispatching information matched with the combination;
and the group-combining dispatching module is used for executing group-combining dispatching of the distribution orders according to the group-combining dispatching information.
9. An electronic device comprising a memory, a processor, and program code stored on the memory and executable on the processor, wherein the processor implements the delivery order portfolio dispatch method of any one of claims 1 through 7 when executing the program code.
10. A computer-readable storage medium having stored thereon program code, wherein the program code when executed by a processor implements the steps of the delivery order portfolio serving method of any of claims 1 through 7.
CN202110206523.1A 2021-02-24 2021-02-24 Distribution order package-combining and distribution method and device and electronic equipment Pending CN114970923A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110206523.1A CN114970923A (en) 2021-02-24 2021-02-24 Distribution order package-combining and distribution method and device and electronic equipment

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110206523.1A CN114970923A (en) 2021-02-24 2021-02-24 Distribution order package-combining and distribution method and device and electronic equipment

Publications (1)

Publication Number Publication Date
CN114970923A true CN114970923A (en) 2022-08-30

Family

ID=82973155

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110206523.1A Pending CN114970923A (en) 2021-02-24 2021-02-24 Distribution order package-combining and distribution method and device and electronic equipment

Country Status (1)

Country Link
CN (1) CN114970923A (en)

Similar Documents

Publication Publication Date Title
WO2021017609A1 (en) Determination of estimated time of arrival
CN104779680B (en) Electric automobile reservation charging control method and device
US20140188748A1 (en) Methods and systems for determining estimated package delivery/pick-up times
CN109615201A (en) Order allocation method, device, electronic equipment and storage medium
Mesa-Arango et al. Benefits of in-vehicle consolidation in less than truckload freight transportation operations
CN109598368B (en) Path decision evaluation and order distribution method and device, electronic equipment and medium
CN110674979A (en) Risk prediction model training method, prediction device, medium and equipment
CN103732471A (en) Resource management plan creation device, method thereof, and program
CN109816128B (en) Method, device and equipment for processing network taxi appointment orders and readable storage medium
CN109636482B (en) Data processing method and system based on similarity model
CN109214732A (en) Method, device and equipment for selecting logistics objects and determining logistics line overload
CN111967793B (en) Logistics timeliness evaluation method and device, electronic equipment and storage medium
CN112183943A (en) Order distribution method and device and electronic equipment
CN113379445A (en) Vehicle price prediction method and device
Simoni et al. Crowdsourced on-demand food delivery: An order batching and assignment algorithm
CN111062774A (en) Activity delivery method and device, electronic equipment and computer readable medium
CN114970923A (en) Distribution order package-combining and distribution method and device and electronic equipment
CN111753386B (en) Data processing method and device
CN106251103A (en) Automobile logistics freight charges computational methods and system
CN111582408B (en) Data processing method, data processing device, storage medium and electronic equipment
CN116187889A (en) Full-chain molten iron intermodal transportation scheme system and evaluation method
CN111047354A (en) Time-sharing pricing implementation method and device, electronic equipment and storage medium
Ramos-Carrasco et al. Artificial neural networks to estimate the forecast of tourism demand in Peru
CN114048978A (en) Supply and demand scheduling strategy fusion application based on machine learning model
CN106251104A (en) Features of Railway Logistics freight charges computational methods and system

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication