Order allocation method and device, storage medium and program product

Abstract

The invention provides an order allocation method and device, a storage medium and a program product, and relates to the technical field of computers. The method comprises the following steps: obtaining order information of a to-be-allocated order, order back information of a plurality of delivery resources and delivery resource positions of the plurality of delivery resources; for each delivery resource, constructing a position relation matrix corresponding to each delivery resource based on the order information, the order information and the delivery resource position; based on the position relation matrix corresponding to each distribution resource, carrying out multiple times of cyclic taking and sending sequence solving to obtain a target taking and sending sequence corresponding to each distribution resource; and determining a target delivery resource from the plurality of delivery resources based on the target delivery sequence corresponding to the plurality of delivery resources, and allocating the to-be-allocated order to the target delivery resource. According to the method, the solution space can be effectively improved to effectively screen the local optimal solution, so that the to-be-allocated order is allocated to a more appropriate target delivery resource.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of computers, and particularly relates to an order distribution method and device, a storage medium and a program product. BACKGROUND

[0002] With the rapid development of Internet technology, there are more and more applications based on the Internet, such as take-out applications, etc. Through these applications, users can obtain the items they need without going out, which not only facilitates users but also faces the problem of order distribution.

[0003] At present, before a to-be-distributed order is distributed, a wave pursuit distribution method is used to solve the taking and sending sequence of a plurality of distribution resources respectively, to obtain the taking and sending sequence of the plurality of distribution resources, and then a suitable target distribution resource is selected from the plurality of distribution resources based on the taking and sending sequence of the plurality of distribution resources, and the to-be-distributed order is distributed to the target distribution resource.

[0004] However, when the wave pursuit distribution method is used to solve the taking and sending sequence, the size of the solution space is reduced, which may lose the local optimal solution, so that the target distribution resource distributed to the to-be-distributed order may not be a more suitable distribution resource. SUMMARY

[0005] The present application provides an order distribution method, device, storage medium and program product to solve or improve the problems in the prior art.

[0006] In a first aspect, an order distribution method is provided, which comprises: obtaining order information of a to-be-distributed order, back order information of a plurality of distribution resources, and distribution resource positions of the plurality of distribution resources; for each distribution resource, based on the order information, the back order information and the distribution resource position, constructing a position relationship matrix corresponding to each distribution resource, wherein an element in the position relationship matrix represents the relationship between two positions; based on the position relationship matrix corresponding to each distribution resource, performing multiple loop taking and sending sequence solving to obtain a target taking and sending sequence corresponding to each distribution resource; based on the target taking and sending sequence corresponding to the plurality of distribution resources, determining a target distribution resource from the plurality of distribution resources, and distributing the to-be-distributed order to the target distribution resource.

[0007] In a possible implementation, the taking and delivering sequence is solved based on the position relationship matrix corresponding to each delivery resource for multiple loops, and a target taking and delivering sequence corresponding to each delivery resource is obtained, including: generating multiple candidate taking and delivering sequences based on the position relationship matrix; after generating an Nth candidate taking and delivering sequence, evaluating the Nth candidate taking and delivering sequence to obtain a first evaluation result of the Nth candidate taking and delivering sequence, N being an integer greater than 1; determining an Nth pending taking and delivering sequence based on the first evaluation result of the Nth candidate taking and delivering sequence and a first evaluation result of an N-1th pending taking and delivering sequence; and determining the last pending taking and delivering sequence as the target taking and delivering sequence.

[0008] In a possible implementation, the multiple candidate taking and delivering sequences are generated based on the position relationship matrix, including: caching the position relationship matrix, and configuring a point index for each element in the position relationship matrix; and constructing the candidate taking and delivering sequence based on a sorting sequence of the point index.

[0009] In a possible implementation, the Nth candidate taking and delivering sequence is evaluated to obtain the first evaluation result of the Nth candidate taking and delivering sequence, including: evaluating the Nth candidate taking and delivering sequence by using a distance prediction model to obtain a target estimated distance; evaluating the Nth candidate taking and delivering sequence by using a time length prediction model to obtain a target estimated time; evaluating the Nth candidate taking and delivering sequence by using a supply and demand relationship model to obtain a target influence index, the target influence index being used to represent an influence degree of a to-be-allocated order on a delivery resource in different supply and demand scenarios; and determining the first evaluation result of the Nth candidate taking and delivering sequence based on the target estimated distance, the target estimated time, and the target influence index.

[0010] In a possible implementation, the first evaluation result of the Nth candidate taking and delivering sequence is determined based on the target estimated distance, the target estimated time, and the target influence index, including: converting the target estimated distance into a first score value; converting the target estimated time into a second score value; and determining the first evaluation result of the Nth candidate taking and delivering sequence based on the first score value, the second score value, and the target influence index.

[0011] In a possible implementation, the first evaluation result of the Nth candidate taking and delivering sequence is determined based on the first score value, the second score value, and the target influence index, including: determining a first weight corresponding to the first score value and a second weight corresponding to the second score value based on the target influence index; and performing weighted summation on the first score value and the second score value by using the first weight and the second weight to obtain the first evaluation result of the Nth candidate taking and delivering sequence.

[0012] In a possible implementation, the Nth pending pick-and-delivery sequence is determined based on the first evaluation result of the Nth candidate pick-and-delivery sequence and the first evaluation result of the (N-1)th pending pick-and-delivery sequence, including: in a case where the first evaluation result of the Nth candidate pick-and-delivery sequence is better than the first evaluation result of the (N-1)th pending pick-and-delivery sequence, determining the Nth candidate pick-and-delivery sequence as the Nth pending pick-and-delivery sequence; or in a case where the first evaluation result of the (N-1)th pending pick-and-delivery sequence is better than the first evaluation result of the Nth candidate pick-and-delivery sequence, determining the (N-1)th pending pick-and-delivery sequence as the Nth pending pick-and-delivery sequence.

[0013] In a possible implementation, the order information includes a first pickup location and a first delivery destination location, and the back note information includes at least one second pickup location and a second delivery destination location corresponding to each second pickup location; the position relationship matrix corresponding to each delivery resource is constructed based on the order information, the back note information, and the delivery resource positions, including: the position relationship matrix is constructed based on the first pickup location, the first delivery destination location, the second pickup location, the second delivery destination location, and the delivery resource positions.

[0014] In a possible implementation, the target delivery resource is determined from the plurality of delivery resources based on the target pick-and-delivery sequence corresponding to each of the plurality of delivery resources, including: a sequential evaluation model is used to evaluate the target pick-and-delivery sequence corresponding to each of the plurality of delivery resources, to obtain a second evaluation result corresponding to each of the plurality of delivery resources; the second evaluation result corresponding to each of the plurality of delivery resources is processed to obtain feature information corresponding to each of the plurality of delivery resources; and the target delivery resource is determined from the plurality of delivery resources based on the target pick-and-delivery sequence corresponding to each of the plurality of delivery resources, the second evaluation result, and the feature information.

[0015] In a second aspect, an order allocation apparatus is provided, including: an information acquisition module, configured to acquire order information of a to-be-allocated order, back note information of a plurality of delivery resources, and delivery resource positions of the plurality of delivery resources; a matrix construction module, configured to, for each delivery resource, construct a position relationship matrix corresponding to the delivery resource based on the order information, the back note information, and the delivery resource positions, an element in the position relationship matrix representing a relationship between two positions; a sequence solving module, configured to perform pick-and-delivery sequence solving in multiple loops based on the position relationship matrix corresponding to each delivery resource, to obtain a target pick-and-delivery sequence corresponding to each delivery resource; and an order allocation module, configured to determine a target delivery resource from the plurality of delivery resources based on the target pick-and-delivery sequence corresponding to each of the plurality of delivery resources, and allocate the to-be-allocated order to the target delivery resource.

[0016] In a third aspect, an electronic device is provided, including: a memory configured to store executable program code; and a processor configured to invoke and run the executable program code from the memory, so that the electronic device executes the order allocation method.

[0017] In a fourth aspect, a computer-readable storage medium is provided, which stores computer instructions. When the computer instructions are run on an electronic device, the electronic device executes the order allocation method.

[0018] In a fifth aspect, a computer program product is provided, which includes a computer program. When the computer program is run, the computer program causes a computer to execute the order allocation method.

[0019] The embodiments of the present application can construct a position relationship matrix based on order information, back order information and delivery resource positions, and then solve the taking and delivering sequence in multiple cycles based on the position relationship matrix. In this way, there is no wave constraint in the process of solving the taking and delivering sequence, which can effectively improve the solution space to effectively screen the local optimal solution, i.e., optimize the target taking and delivering sequence solved by each delivery resource, so as to allocate the to-be-allocated order to a more suitable target delivery resource. BRIEF DESCRIPTION OF DRAWINGS

[0020] Figure 1 is a schematic diagram of a taking and delivering sequence solving method provided by the related art in a wave pursuit manner; Figure 2 is a flowchart of an order allocation method provided by the embodiments of the present application; Figure 3 is an architecture diagram of a taking and delivering sequence solving method provided by the embodiments of the present application in a full back order manner; Figure 4 is a flowchart of a taking and delivering sequence solving method provided by the embodiments of the present application in a full back order manner; Figure 5 is a structural diagram of an order allocation apparatus provided by the embodiments of the present application; Figure 6 is a structural diagram of an electronic device provided by the embodiments of the present application. DETAILED DESCRIPTION

[0021] In the embodiments of the present application, the following terms “first”, “second”, and the like are only used for description purposes, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined with “first”, “second” can explicitly or implicitly include one or more of the features. In the description of the embodiments, unless otherwise specified, the meaning of “a plurality of” is two or more.

[0022] It should be noted that in the description of the embodiments of the present application, unless otherwise specified, " / " means or, for example, A / B can mean A or B; "and / or" herein only describes the association relationship of the associated objects, which means that there can be three relationships, for example, A and / or B, which can mean that A exists alone, A and B exist together, and B exists alone. In addition, in the description of the embodiments of the present application, "multiple" means two or more than two.

[0023] It should also be noted that in the embodiments of the present application, "preset", "fixed value" and the like can be realized by pre-storing corresponding codes, tables or other means that can be used to indicate related information in the electronic device, and the present application does not limit the specific implementation manner.

[0024] It should be understood that the division of the mode, case, category and embodiment in the embodiments of the present application is only for the convenience of description, and should not constitute a special limitation. The features in various modes, categories, cases and embodiments can be combined with each other without contradiction.

[0025] It should also be understood that in the description of the embodiments, unless otherwise specified, "multiple" means two or more than two. In various embodiments of the present application, the size of the serial number of each process does not mean the order of execution, and the execution order of each process should be determined by its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0026] It should be noted that in the case of the embodiments of the present application involving user information, the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the embodiments of the present application are all information and data authorized by the user or authorized by all parties, and the collection, use and processing of related data need to comply with relevant laws, regulations and standards of relevant countries and regions, and provide corresponding operation portal for user to choose authorization or refusal. In addition, the various models involved in the present application are in line with the relevant legal and standard regulations.

[0027] In order to facilitate the understanding of the technical solutions of the embodiments of the present application, some terms involved in the embodiments of the present application are simply explained below.

[0028] Delivery resource: refers to a resource used to perform a delivery task, which can be a delivery personnel (such as a rider), a delivery robot, etc.

[0029] Wave: This is a way of dividing the operation process of delivery resources. Specifically, it refers to the process from when a delivery resource is assigned at least one order until the delivery resource is empty. For example, if a target wave includes two orders, order A and order B, and the pickup and delivery sequence of a certain delivery resource is: receive order A, receive order B, pick up order A, pick up order B, deliver order B, deliver order A, then the time when the delivery resource receives order A is taken as the start time of the target wave, and the time when the delivery resource completes the delivery of order A is taken as the end time of the target wave.

[0030] With the rapid development of internet technology, there are more and more internet-based applications, such as food delivery apps. Through these apps, users can obtain the items they need without leaving home. While these apps bring convenience to users, they also face the problem of order allocation.

[0031] After a user selects a merchant and places an order, the order allocation system will assign the order to a target delivery resource. The target delivery resource can pick up the items from the order's pickup location and deliver them to the order's destination location, thus completing the order's delivery task.

[0032] Before allocating orders, it is necessary to solve the pickup and delivery order for the order information of multiple delivery resources and the orders to be allocated, and generate a better pickup and delivery order for multiple delivery resources. This will provide underlying data that is more in line with the behavior of the delivery resources to each of the multiple delivery resources. Based on the pickup and delivery order of multiple delivery resources, a suitable target delivery resource can be selected from the multiple delivery resources and the orders to be allocated can be assigned to the target delivery resource.

[0033] Solving the pickup and delivery order of delivery resources is a method for rationally planning the pickup and delivery sequence of delivery resources. Specifically, it's used to plan the actions of delivery resources in completing the pickup and delivery of items. Taking the food delivery business scenario as an example, solving the pickup and delivery order of delivery resources refers to planning the actions of delivery resources in completing the pickup of food by merchants and delivery to users. This type of pickup and delivery order solution is classified as a dynamic traveling salesman problem (TSP), which is a complex problem of non-polynomial exponentiation (on-deterministic polynomial-hard, NP-hard).

[0034] As the number of orders carried by delivery resources increases, the solution space for determining the pickup and delivery order of delivery resources grows exponentially. In the food delivery business scenario, simulating the operation of delivery resources helps the delivery resource allocation module measure the additional cost of delivery resources for orders to be allocated. The solution granularity during the lunch peak is very high, and the requirements for solution performance are extremely high.

[0035] Currently, the wave-based sorting method can be used to solve the pick-up and delivery order for multiple delivery resources separately, thus obtaining the pick-up and delivery order of multiple delivery resources.

[0036] like Figure 1 As shown, before placing an order for an order to be assigned, the original order information of multiple delivery resources must first be used to solve the order of pickup and delivery to form wave information.

[0037] For example, for a certain delivery resource, the back order information of the delivery resource includes M orders, where M is a positive integer. When solving the pick-up and delivery order of the original back order information of the delivery resource, multiple simulated assignments will be performed. The pick-up and delivery order will be solved through the chasing mode to form wave information.

[0038] Specifically, when the delivery resource is assigned the first order, a simulated assignment (e.g., simulated assignment 1) can be performed to simulate the pickup and delivery order of the first order. If the delivery resource is assigned the second order before the first order is completed, another simulated assignment (e.g., simulated assignment 2) is performed to simulate the pickup and delivery order of the first and second orders by measuring the impact of the second order on the first order. This process continues until the delivery resource is assigned the Mth order before the first M-1 orders are completed. In this case, another simulated assignment (e.g., simulated assignment M) is performed to simulate the pickup and delivery order of the first to the Mth orders by measuring the impact of the Mth order on the M-1th orders, thus forming wave information.

[0039] For example, such as Figure 1 As shown, the wave information formed may include wave 1, wave 2 and wave 3, and each of wave 1, wave 2 and wave 3 includes at least one order.

[0040] After an order to be assigned is placed, if the order is to be assigned to the delivery resource, it is necessary to rely on the wave information generated by the original order information of the delivery resource. Under the influence of the single wave constraint, the wave chasing method is used to solve the pick-up and delivery order of the original order information of the delivery resource and the order to be assigned. The obtained pick-up and delivery order includes three pick-up and delivery orders, which are the first pick-up and delivery order, the second pick-up and delivery order, and the third pick-up and delivery order as follows.

[0041] like Figure 1 As shown, the first pickup and delivery sequence is as follows: add the orders to be assigned to wave 2. In this case, the pickup and delivery sequence of the delivery resources is to first complete the pickup and delivery of the orders in wave 1, then complete the pickup and delivery of the orders in wave 2 and the orders to be assigned, and finally complete the pickup and delivery of the orders in wave 3.

[0042] The second taking and delivering sequence is that the to-be-allocated order is added to wave 3, and in this case, the taking and delivering sequence of the delivery resource is to complete the taking and delivering of the orders in wave 1 first, then complete the taking and delivering of the orders in wave 2, and finally complete the taking and delivering of the orders in wave 3 and the to-be-allocated order.

[0043] The third taking and delivering sequence is that the to-be-allocated order is taken and delivered separately from the orders in wave 1, wave 2 and wave 3, and in this case, the taking and delivering sequence of the delivery resource is to complete the taking and delivering of the orders in wave 1 first, then complete the taking and delivering of the orders in wave 2, then complete the taking and delivering of the orders in wave 3, and finally complete the taking and delivering of the to-be-allocated order.

[0044] After the taking and delivering sequence of the original back information of the delivery resource and the to-be-allocated order is solved according to the wave chasing allocation mode described above, the most suitable target taking and delivering sequence can be selected from the multiple taking and delivering sequences. Then, the taking and delivering sequence before the to-be-allocated order is placed and the target taking and delivering sequence determined after the to-be-allocated order is placed are characterized, and the degree of influence of the to-be-allocated order on the delivery resource after the to-be-allocated order is allocated to the delivery resource is solved, such as the delivery distance and / or delivery time that the delivery resource needs to increase when delivering the to-be-allocated order.

[0045] Finally, based on the target taking and delivering sequences solved by multiple delivery resources and the degree of influence of the to-be-allocated order on the multiple delivery resources, a suitable target delivery resource can be selected from the multiple delivery resources, and the to-be-allocated order can be allocated to the target delivery resource.

[0046] However, when the wave chasing allocation mode is used to solve the taking and delivering sequence, there is a wave constraint that will select a local range for solving, which will reduce the size of the solution space, and it may lose the local optimal solution, so that the target delivery resource allocated to the to-be-allocated order may not be a more suitable delivery resource.

[0047] Based on this, the embodiment of the present application provides an order allocation method, which obtains order information of a to-be-allocated order, back single information of a plurality of delivery resources and delivery resource positions of the plurality of delivery resources; for each delivery resource, constructs a position relationship matrix corresponding to each delivery resource based on the order information, the back single information and the delivery resource position, an element in the position relationship matrix representing a relationship between two positions; performs a plurality of cyclic taking and delivering sequence solving based on the position relationship matrix corresponding to each delivery resource, to obtain a target taking and delivering sequence corresponding to each delivery resource; determines a target delivery resource from the plurality of delivery resources based on the target taking and delivering sequence corresponding to the plurality of delivery resources, and allocates the to-be-allocated order to the target delivery resource. Therefore, the embodiment of the present application can construct a position relationship matrix based on order information, back single information and delivery resource positions, and then perform a plurality of cyclic taking and delivering sequence solving based on the position relationship matrix. In this way, there is no wave constraint in the process of taking and delivering sequence solving, which can effectively improve the solution space to effectively screen the local optimal solution, that is, optimize the target taking and delivering sequence solved by each delivery resource, so as to allocate the to-be-allocated order to a more suitable target delivery resource.

[0048] The technical solutions provided by the embodiments of the present application are introduced as follows, Figure 2 is a flowchart of an order allocation method provided by the embodiments of the present application. The method can be executed by a server, or executed by a client, or a part of the steps is executed by the server and the other part of the steps is executed by the client. As shown in the figure, Figure 2 The order allocation method can specifically include the following steps: S201, obtaining order information of a to-be-allocated order, back single information of a plurality of delivery resources and delivery resource positions of the plurality of delivery resources.

[0049] In some embodiments, after a user places an order on an application on a terminal device, a to-be-allocated order can be generated, and the server can obtain order information of the to-be-allocated order. For example, in the take-out business scenario, after a user places an order on a take-out application on a terminal device, a to-be-allocated order can be generated.

[0050] The order information of the to-be-allocated order can include order number, order time, first pickup location and first delivery destination location, and order payment method and the like. For example, in the take-out business scenario, the first pickup location can be the first merchant location corresponding to the to-be-allocated order, and the first delivery destination location can be the first user location corresponding to the to-be-allocated order.

[0051] The back single information of the delivery resource includes order information of an order that the delivery resource has not completed delivery currently, such as order number, order time, the second pickup location, the second delivery destination location, and order payment method.

[0052] It should be understood that, in the case that the current back single quantity of the delivery resource is M, there are M second pickup locations and M second delivery destination locations, the second pickup location and the second delivery destination location correspond to each other, any two second pickup locations can be the same or different, and any two second delivery destination locations can be the same or different. The delivery resource can be assigned with multiple orders in the delivery process, and the current back single quantity of the delivery resource represents the total number of orders that the delivery resource has not completed delivery currently at a moment.

[0053] The delivery resource location of the delivery resource is actually a geographic location where the delivery resource currently locates, and the terminal device corresponding to the delivery resource can send the delivery resource location corresponding thereto to the server.

[0054] In S202, for each delivery resource, a location relationship matrix corresponding to each delivery resource is constructed based on the order information, the back single information, and the delivery resource location, and an element in the location relationship matrix represents a relationship between two locations.

[0055] In some embodiments, for each delivery resource, the server can extract the first pickup location and the first delivery destination location from the order information of the to-be-assigned order, and extract the second pickup location and the second delivery destination location from the back single information of each delivery resource, and the second pickup location and the second delivery destination location in the back single information can be at least one.

[0056] In a possible implementation, the order information includes the first pickup location and the first delivery destination location, and the back single information includes at least one second pickup location and a second delivery destination location corresponding to each second pickup location; and S202 of “constructing a location relationship matrix corresponding to each delivery resource based on the order information, the back single information, and the delivery resource location” can specifically include the following steps: constructing the location relationship matrix based on the first pickup location, the first delivery destination location, the second pickup location, the second delivery destination location, and the delivery resource location.

[0057] In this way, for each delivery resource, the server can construct a position relationship matrix corresponding to each delivery resource based on the first pickup location, the first delivery destination location, the second pickup location, the second delivery destination location, and the delivery resource location. The position relationship matrix can be a L*L (i.e., L rows and L columns) matrix, where L is an integer greater than 1, and the specific value of L is positively correlated with the number of back-to-back orders in the back-to-back order information. In this way, the server can construct a position relationship matrix corresponding to each of the plurality of delivery resources.

[0058] For example, assume that the first pickup location in the order information is A1 location, and the first delivery destination location in the order information is A2 location. Assume that the back-to-back order information of a certain delivery resource includes two orders, the second pickup location of the first order is B1 location, the second delivery destination location of the first order is B2 location, the second pickup location of the second order is C1 location, the second delivery destination location of the second order is C2 location, and the delivery resource location is D location. The server can construct a 7*7 position relationship matrix based on A1 location, A2 location, B1 location, B2 location, C1 location, C2 location, and D location.

[0059] In the position relationship matrix, the elements can represent the relationship between any two of A1 location, A2 location, B1 location, B2 location, C1 location, C2 location, and D location.

[0060] S203, based on the position relationship matrix corresponding to each delivery resource, performing multiple looped pickup and delivery sequence solving to obtain a target pickup and delivery sequence corresponding to each delivery resource.

[0061] In some embodiments, for each delivery resource, the server can generate a plurality of different candidate pickup and delivery sequences based on the position relationship matrix, and evaluate each candidate pickup and delivery sequence after generating it. Then, based on the first evaluation result obtained by the evaluation, the server can constantly select a better candidate pickup and delivery sequence. In this way, after multiple looped pickup and delivery sequence solving, a better target pickup and delivery sequence can be obtained.

[0062] In addition, the above multiple looped pickup and delivery sequence solving is used for each delivery resource, so that the server can determine a target pickup and delivery sequence corresponding to each of the plurality of delivery resources.

[0063] S204, based on the target pickup and delivery sequence corresponding to each of the plurality of delivery resources, determining a target delivery resource from the plurality of delivery resources, and assigning the to-be-assigned order to the target delivery resource.

[0064] In some embodiments, the server can select a suitable target delivery resource from multiple delivery resources based on the target pickup and delivery order corresponding to multiple delivery resources, and assign the orders to be allocated to the target delivery resource to optimize the order allocation method.

[0065] Therefore, in addition to the necessary strong business and logical constraints, the embodiments of this application can break the wave constraint and truly rely on the optimization of the pick-up and delivery order under the current time and space. Through the overall solution approach of the entire back-to-back list, the solution space can be effectively improved. Under the same sample, experiments have shown that the quality of the target pick-up and delivery order obtained after improving the solution space is better.

[0066] In the food delivery business scenario, with frequent updates to spatiotemporal information, the order allocation decision-making process requires high instantaneous and high concurrency, and the performance requirements for solving the pickup and delivery order are extremely high. As more and more business modules are undertaken, the solution chain needs to be simplified in order to adapt to the functions of each module.

[0067] For example, such as Figure 3 As shown, before an order to be assigned is placed, for a certain delivery resource, the backing information of that delivery resource includes M orders. Therefore, this embodiment of the application can perform full planning on the backing information of that delivery resource, that is, directly construct a location relationship matrix based on the location in the backing information and the location of the delivery resource, and solve the pick-up and delivery order through multiple iterations based on the location relationship matrix. Correspondingly, after an order to be assigned is placed, for that delivery resource, this embodiment of the application can perform full planning on the backing information of that delivery resource and the orders to be assigned, that is, directly construct a location relationship matrix based on the location in the backing information, the location in the orders to be assigned, and the location of the delivery resource, and solve the pick-up and delivery order through multiple iterations based on the location relationship matrix.

[0068] In one possible implementation, the above-mentioned S203 "solving the pickup and delivery order multiple times based on the location relationship matrix corresponding to each delivery resource to obtain the target pickup and delivery order corresponding to each delivery resource" may specifically include the following steps: generating multiple candidate pickup and delivery orders sequentially based on the location relationship matrix; after generating the Nth candidate pickup and delivery order, evaluating the Nth candidate pickup and delivery order to obtain the first evaluation result of the Nth candidate pickup and delivery order, where N is an integer greater than 1; determining the Nth undetermined pickup and delivery order based on the first evaluation result of the Nth candidate pickup and delivery order and the first evaluation result of the (N-1)th undetermined pickup and delivery order; and determining the last undetermined pickup and delivery order as the target pickup and delivery order.

[0069] In this embodiment of the application, for each delivery resource, multiple candidate pickup and delivery orders can be generated sequentially based on a location relationship matrix. After each candidate pickup and delivery order is generated, it is evaluated. Each candidate pickup and delivery order is different.

[0070] Specifically, first, a first candidate pick-up and delivery sequence is generated based on the position relationship matrix. After the first candidate pick-up and delivery sequence is generated, the first candidate pick-up and delivery sequence is evaluated to obtain a first evaluation result of the first candidate pick-up and delivery sequence, and the first candidate pick-up and delivery sequence is taken as a first pending pick-up and delivery sequence. Then, a second candidate pick-up and delivery sequence is generated based on the position relationship matrix. After the second candidate pick-up and delivery sequence is generated, the second candidate pick-up and delivery sequence is evaluated to obtain a first evaluation result of the second candidate pick-up and delivery sequence. Based on the first evaluation result of the second candidate pick-up and delivery sequence and the first evaluation result of the first pending pick-up and delivery sequence, a second pending pick-up and delivery sequence is determined from the second candidate pick-up and delivery sequence and the first pending pick-up and delivery sequence. Then, a third candidate pick-up and delivery sequence is generated based on the position relationship matrix. After the third candidate pick-up and delivery sequence is generated, the third candidate pick-up and delivery sequence is evaluated to obtain a first evaluation result of the third candidate pick-up and delivery sequence. Based on the first evaluation result of the third candidate pick-up and delivery sequence and the first evaluation result of the second pending pick-up and delivery sequence, a third pending pick-up and delivery sequence is determined from the third candidate pick-up and delivery sequence and the second pending pick-up and delivery sequence. In this way, a last pending pick-up and delivery sequence is determined, and the last pending pick-up and delivery sequence is determined as the target pick-up and delivery sequence.

[0071] In a possible implementation, the above-mentioned "generating multiple candidate pick-up and delivery sequences in sequence based on the position relationship matrix" can include the following steps: caching the position relationship matrix, and configuring a point index for each element in the position relationship matrix; constructing a candidate pick-up and delivery sequence based on a sorting sequence of the point index.

[0072] The point index is associated with the candidate pick-up and delivery sequence. The point index generally represents an identifier of an element in the position relationship matrix, and the candidate pick-up and delivery sequence describes an execution sequence of the candidate pick-up and delivery operation. The change of the sorting sequence of the point index can directly reflect the change of the candidate pick-up and delivery sequence.

[0073] Taking that the server constructs the position relationship matrix based on the A1 position, the A2 position, the B1 position, the B2 position, the C1 position, the C2 position and the D position as an example, assuming that a certain candidate pick-up and delivery sequence is: the delivery resource goes to the B1 position to pick up the meal first, then goes to the C1 position to pick up the meal, then goes to the A1 position to pick up the meal, then goes to the A2 position to deliver the meal, then goes to the B2 position to deliver the meal, and finally goes to the C2 position to deliver the meal. If the point index of the D position and the B1 position is S1, the point index between the B1 position and the C1 position is S2, the point index between the C1 position and the A1 position is S3, the point index between the A1 position and the A2 position is S4, the point index between the A2 position and the B2 position is S5, and the point index between the B2 position and the C2 position is S6, then the sorting sequence of the point index is S1-S2-S3-S4-S5-S6 in turn, thereby reflecting the above-mentioned candidate pick-up and delivery sequence.

[0074] It should be noted that when caching the location relationship matrix, the elements in the matrix represent the relationship between any two locations. However, in the actual delivery process, some elements in the location relationship matrix may not be used. For example, delivery resources generally do not arrive at the destination location of an order before arriving at the pickup location; that is, the elements representing the relationship between locations A2 and A1 are generally not used. Therefore, in this embodiment, when generating multiple candidate pickup and delivery orders based on the location relationship matrix, it is necessary to filter out some elements in the location relationship matrix according to preset delivery rules, and generate multiple candidate pickup and delivery orders based on the remaining elements in the location relationship matrix.

[0075] In one possible implementation, the aforementioned "evaluating the Nth candidate pickup and delivery order to obtain the first evaluation result of the Nth candidate pickup and delivery order" may specifically include the following steps: evaluating the Nth candidate pickup and delivery order using a distance prediction model to obtain the target estimated distance; evaluating the Nth candidate pickup and delivery order using a duration prediction model to obtain the target estimated time; evaluating the Nth candidate pickup and delivery order using a supply and demand relationship model to obtain the target impact index, which is used to represent the degree of impact of the orders to be allocated on delivery resources under different supply and demand scenarios; and determining the first evaluation result of the Nth candidate pickup and delivery order based on the target estimated distance, the target estimated time, and the target impact index.

[0076] For example, such as Figure 4 As shown, under the full-backsheet framework, the main internal modules include a pickup and delivery sequence solution module and an evaluation module. The pickup and delivery sequence solution module includes a pickup and delivery sequence solution sub-module and an evaluation system. The evaluation system includes a distance layer, a task time layer, and a supply and demand relationship layer.

[0077] After the order information of the orders to be assigned, the order tracking information of the delivery resources, and the delivery resource locations are input into the pickup / delivery order solving submodule, the submodule can construct a location relationship matrix corresponding to each delivery resource based on the order information, order tracking information, and delivery resource locations, and generate multiple candidate pickup / delivery orders sequentially based on the location relationship matrix. Furthermore, after each candidate pickup / delivery order is generated, it is evaluated using the distance layer, operation time layer, and supply-demand relationship layer of the evaluation system.

[0078] Specifically, when using the distance layer to evaluate the candidate retrieval order, the distance prediction model can be called to evaluate the candidate retrieval order. That is, the candidate retrieval order is input into the distance prediction model, so that the distance prediction model can output the target estimated distance corresponding to the candidate retrieval order.

[0079] When the candidate pick-up and delivery sequence is evaluated in the operation time consumption layer, the time length prediction model can be called to evaluate the candidate pick-up and delivery sequence, that is, the candidate pick-up and delivery sequence is input into the time length prediction model, so that the time length prediction model can output the target estimated time corresponding to the candidate pick-up and delivery sequence. The target estimated time can also be referred to as the estimated time of route (ETR) of the pick-up and delivery sequence.

[0080] When the candidate pick-up and delivery sequence is evaluated in the supply and demand relationship layer, the supply and demand relationship model can be called to evaluate the candidate pick-up and delivery sequence, that is, the candidate pick-up and delivery sequence is input into the supply and demand relationship model, so that the supply and demand relationship model can output the target influence index corresponding to the candidate pick-up and delivery sequence. The target influence index is actually a specific numerical value, which is used to represent the influence degree of the to-be-allocated order on the delivery resource in different supply and demand scenarios.

[0081] After the target estimated distance, the target estimated time and the target influence index of the candidate pick-up and delivery sequence are evaluated, the first evaluation result of the candidate pick-up and delivery sequence can be determined based on the target estimated distance, the target estimated time and the target influence index.

[0082] In this way, after the first evaluation result of the Nth candidate pick-up and delivery sequence is evaluated in the above manner, the Nth pending pick-up and delivery sequence is determined from the Nth candidate pick-up and delivery sequence and the (N-1)th pending pick-up and delivery sequence based on the first evaluation result of the Nth candidate pick-up and delivery sequence and the first evaluation result of the (N-1)th pending pick-up and delivery sequence. That is, in the case where the first evaluation result of the Nth candidate pick-up and delivery sequence is better than the first evaluation result of the (N-1)th pending pick-up and delivery sequence, the pending pick-up and delivery sequence needs to be updated, and so on. The last pending pick-up and delivery sequence is determined as the target pick-up and delivery sequence.

[0083] It should be understood that the distance prediction model described above is used to estimate the total delivery distance of the candidate pick-up and delivery sequence, that is, the target estimated distance includes the total delivery distance. The time length prediction model is used to estimate the total delivery time of the candidate pick-up and delivery sequence, that is, the target estimated time includes the total delivery time. In other embodiments, the target estimated time can include the overtime length and the like in addition to the total delivery time. Specifically, the time length prediction model can first predict the riding time of the delivery resource between two locations and the waiting time of the delivery resource after reaching each pickup location, and then add up all the riding times and waiting times to obtain the total delivery time. The supply and demand relationship model is used to estimate the influence degree of the to-be-allocated order on the delivery resource in terms of delivery distance and delivery time when the delivery resource delivers according to the candidate pick-up and delivery sequence in the corresponding supply and demand scenario (such as peak period scenario or adverse weather scenario).

[0084] In the evaluation of the candidate pick-up and delivery sequence, the embodiment of the application can evaluate based on multiple target dimensions, such as the delivery distance dimension and the delivery time dimension, and the like. In this way, through the above-mentioned manner, the pick-up and delivery sequence solving module can find a local optimal solution under different scenarios and different target dimensions.

[0085] In the evaluation process, the solving quality and the solving performance can be balanced, and if necessary, the local effect can be sacrificed to exchange effective computing power to optimize the solving performance of the target pick-up and delivery sequence. Specifically, the more the number of candidate pick-up and delivery sequences evaluated, the higher the solving quality of the target pick-up and delivery sequence obtained; the fewer the number of candidate pick-up and delivery sequences evaluated, the fewer the computing resources occupied in solving the target pick-up and delivery sequence, thereby improving the solving performance of the target pick-up and delivery sequence. Therefore, the embodiment of the application can determine the number of candidate pick-up and delivery sequences that need to be evaluated based on factors such as the number of delivery resources, the solving quality and the solving performance, that is, determine the specific number of times of pick-up and delivery sequence solving in multiple cycles.

[0086] In the full back single framework, the embodiment of the application creates a simplified pick-up and delivery sequence solving link, constructs multiple feature layers such as the distance layer, the job time consumption layer and the supply and demand relationship layer, and effectively breaks through the performance bottleneck through the schemes of pre-constructing the position relationship matrix and internally establishing the index mapping mechanism.

[0087] In addition, under the full back single framework, the main module can support the configuration of the sub-module, that is, each sub-module has different configuration versions, such as the pick-up and delivery sequence solving sub-module, the evaluation system, the strategy version and the feature version, which all support corresponding configurations. For example, in the pick-up and delivery sequence solving sub-module, the elements in the position relationship matrix can represent the straight line distance relationship or the cycling route distance relationship between two positions. In order to realize high-performance computing, the features are divided into multiple levels, and the construction of the feature layer is completed through the life cycle of global variables, various static variables and dynamic variables. In this way, through the configuration development of each main module and sub-module, the business iteration and the individualized needs of the module are more flexible and less costly.

[0088] Since multiple target modules are involved in the allocation of orders, such as a pick-up and delivery sequence solving module, an evaluation module, and a downstream distribution resource allocation module, if the targets of each target module are difficult to align, there will be a loss of solving quality between each target module. Therefore, the embodiments of the present application can solve the same target problem through multiple serial module solving, avoiding the loss of solving quality between each target module due to unaligned targets. The pick-up and delivery sequence solving module and the distribution resource allocation module are closely related, and there are different targets in different supply and demand scenarios and different time periods. For example, in peak period scenarios, both efficiency and experience need to be considered, and in adverse weather scenarios, the tolerance for experience will increase, so more attention will be paid to the connection. The distribution resource allocation module is closer to the business layer and more flexible in perceiving business constraints and scenarios. Therefore, the embodiments of the present application set a supply and demand relationship layer in the pick-up and delivery sequence solving module, which can adaptively adjust the target pick-up and delivery sequence obtained by solving, so as to align the targets between multiple modules and reduce the loss of transmission effect.

[0089] In some embodiments, the above "determining a first evaluation result of the Nth candidate pick-up and delivery sequence based on the target estimated distance, the target estimated time, and the target influence index" can specifically include the following steps: converting the target estimated distance into a first score value; converting the target estimated time into a second score value; determining the first evaluation result of the Nth candidate pick-up and delivery sequence based on the first score value, the second score value, and the target influence index.

[0090] The target estimated distance can be converted into the first score value according to a first mapping rule, and the value range of the first score value can be between 0 and 1. When the target estimated distance is larger, the first score value is closer to 0; when the target estimated distance is smaller, the first score value is closer to 1.

[0091] The target estimated time can be converted into the second score value according to a second mapping rule, and the value range of the second score value can be between 0 and 1. When the target estimated time is larger, the second score value is closer to 0; when the target estimated time is smaller, the second score value is closer to 1.

[0092] Specifically, the above "determining a first evaluation result of the Nth candidate pick-up and delivery sequence based on the first score value, the second score value, and the target influence index" can include the following steps: determining a first weight corresponding to the first score value and a second weight corresponding to the second score value based on the target influence index; and performing weighted summation on the first score value and the second score value using the first weight and the second weight to obtain the first evaluation result of the Nth candidate pick-up and delivery sequence.

[0093] In different supply and demand scenarios, the target influence indicators are different, and thus the first weight and the second weight determined based on the target influence indicators are also different. For example, in a peak period scenario, both efficiency and experience problems need to be considered, and thus the impact of the to-be-allocated order on the delivery resource in terms of delivery duration is greater, and thus the second weight can be increased, so that the delivery resource delivers at a faster delivery speed; or in a bad weather scenario, the tolerance of experience problems will be greater, and thus more attention is paid to the pickup, and thus the impact of the to-be-allocated order on the delivery resource in terms of delivery duration is smaller, and thus the second weight can be reduced.

[0094] Therefore, the embodiment of the present application can adjust the first weight corresponding to the first score value and the second weight corresponding to the second score value based on the target influence indicators, calculate a first product by multiplying the first weight and the first score value, and calculate a second product by multiplying the second weight and the second score value, and determine the first evaluation result as the sum of the first product and the second product.

[0095] In a possible implementation, the above-mentioned "determining the Nth to-be-determined taking and delivering sequence based on the first evaluation result of the Nth candidate taking and delivering sequence and the first evaluation result of the (N-1)th to-be-determined taking and delivering sequence" can specifically include the following steps: in the case that the first evaluation result of the Nth candidate taking and delivering sequence is better than the first evaluation result of the (N-1)th to-be-determined taking and delivering sequence, determining the Nth candidate taking and delivering sequence as the Nth to-be-determined taking and delivering sequence; in the case that the first evaluation result of the (N-1)th to-be-determined taking and delivering sequence is better than the first evaluation result of the Nth candidate taking and delivering sequence, determining the (N-1)th to-be-determined taking and delivering sequence as the Nth to-be-determined taking and delivering sequence.

[0096] Therefore, after the first evaluation result of the Nth candidate taking and delivering sequence is obtained by weighting and summing the first score value and the second score value with the first weight and the second weight, in the case that the first evaluation result of the Nth candidate taking and delivering sequence is greater than the first evaluation result of the (N-1)th to-be-determined taking and delivering sequence, it is determined that the first evaluation result of the Nth candidate taking and delivering sequence is better than the first evaluation result of the (N-1)th to-be-determined taking and delivering sequence, and thus the Nth candidate taking and delivering sequence is determined as the Nth to-be-determined taking and delivering sequence; in the case that the first evaluation result of the (N-1)th to-be-determined taking and delivering sequence is greater than the first evaluation result of the Nth candidate taking and delivering sequence, it is determined that the first evaluation result of the (N-1)th to-be-determined taking and delivering sequence is better than the first evaluation result of the Nth candidate taking and delivering sequence, and thus the (N-1)th to-be-determined taking and delivering sequence is determined as the Nth to-be-determined taking and delivering sequence. In the case that the first evaluation result of the Nth candidate taking and delivering sequence is equal to the first evaluation result of the (N-1)th to-be-determined taking and delivering sequence, the Nth candidate taking and delivering sequence or the (N-1)th to-be-determined taking and delivering sequence can be determined as the Nth to-be-determined taking and delivering sequence.

[0097] In a possible implementation, the S204 "determining the target delivery resource from the plurality of delivery resources based on the target taking and delivering sequence corresponding to each of the plurality of delivery resources" can include the following steps: evaluating the target taking and delivering sequence corresponding to each of the plurality of delivery resources by using a sequence evaluation model to obtain a second evaluation result corresponding to each of the plurality of delivery resources; processing the second evaluation result corresponding to each of the plurality of delivery resources to obtain feature information corresponding to each of the plurality of delivery resources; and determining the target delivery resource from the plurality of delivery resources based on the target taking and delivering sequence corresponding to each of the plurality of delivery resources, the second evaluation result, and the feature information.

[0098] As shown in FIG. 13, under the full back single frame, the evaluation module is configured to evaluate the target taking and delivering sequence and characterize the target taking and delivering sequence. When evaluating the target taking and delivering sequence, the sequence evaluation model can be called to evaluate the target taking and delivering sequence corresponding to each of the plurality of delivery resources, that is, the target taking and delivering sequence corresponding to each of the plurality of delivery resources is input into the sequence evaluation model, so that the sequence evaluation model can output a second evaluation result corresponding to each of the plurality of delivery resources. Figure 4

[0099] The second evaluation result can be used to represent an estimated time length of the delivery resource from the current delivery resource position to each of the pickup locations, an order waiting time of the delivery resource at each of the pickup locations, and a delivery time of the delivery resource from each of the pickup locations to each of the delivery destination positions, and the like. Of course, in some embodiments, the second evaluation result can also be used to represent an estimated distance from the current delivery resource position to each of the pickup locations, and an estimated distance of the delivery resource from each of the pickup locations to each of the delivery destination positions, and the like.

[0100] It should be noted that the delivery distance and the delivery time length are also estimated in the taking and delivering sequence solving module, but since the taking and delivering sequence solving involves multiple candidate taking and delivering sequences in multiple loops, in order to improve the calculation performance, the delivery distance and the delivery time length are roughly estimated in the taking and delivering sequence solving module, and the sequence evaluation model is used to accurately evaluate the target taking and delivering sequence after the target taking and delivering sequence is determined.

[0101] When the second evaluation result is characterized, some feature information in the second evaluation result is summarized. For example, the feature information obtained after processing the second evaluation result corresponding to each of the plurality of delivery resources can include an order waiting time, a delivery overtime length, and the like. The delivery overtime length refers to a time length in which the delivery time exceeds a preset time.

[0102] ​Finally, after obtaining the target taking and delivering sequence, the second evaluation result and the feature information corresponding to each of the plurality of delivery resources, the target taking and delivering sequence, the second evaluation result and the feature information corresponding to each of the plurality of delivery resources can be input to a downstream delivery resource allocation module, so that the delivery resource allocation module can determine a target delivery resource from the plurality of delivery resources based on the target taking and delivering sequence, the second evaluation result and the feature information corresponding to each of the plurality of delivery resources, and allocate the order to be allocated to the target delivery resource.

[0103] It should be noted that the distance prediction model, the time length prediction model, the supply and demand relationship model and the sequence evaluation model in the embodiments of the present application are all pre-trained neural network models.

[0104] The above describes the order allocation method provided by the embodiments of the present application. Figures 2 to 4 The above describes the order allocation method provided by the embodiments of the present application.

[0105] The embodiments of the present application provide an order allocation device, Figure 5 is a structural schematic diagram of an order allocation device provided by the embodiments of the present application. As Figure 5 shown, the order allocation device 500 can include an information acquisition module 501, a matrix construction module 502, a sequence solving module 503 and an order allocation module 504.

[0106] The information acquisition module 501 is configured to acquire order information of an order to be allocated, back single information of a plurality of delivery resources and delivery resource positions of the plurality of delivery resources; the matrix construction module 502 is configured to, for each delivery resource, construct a position relationship matrix corresponding to each delivery resource based on the order information, the back single information and the delivery resource position, an element in the position relationship matrix representing a relationship between two positions; the sequence solving module 503 is configured to solve a taking and delivering sequence in multiple cycles based on the position relationship matrix corresponding to each delivery resource to obtain a target taking and delivering sequence corresponding to each delivery resource; and the order allocation module 504 is configured to determine a target delivery resource from the plurality of delivery resources based on the target taking and delivering sequence corresponding to the plurality of delivery resources, and allocate the order to be allocated to the target delivery resource.

[0107] In a possible implementation, the sequence solving module 503 is specifically configured to: generate a plurality of candidate taking and delivering sequences in sequence based on the position relationship matrix; after generating an Nth candidate taking and delivering sequence, evaluate the Nth candidate taking and delivering sequence to obtain a first evaluation result of the Nth candidate taking and delivering sequence, N being an integer greater than 1; determine an Nth pending taking and delivering sequence based on the first evaluation result of the Nth candidate taking and delivering sequence and a first evaluation result of an N-1th pending taking and delivering sequence; and determine the last pending taking and delivering sequence as the target taking and delivering sequence.

[0108] In a possible implementation, the sequence solving module 503 is specifically configured to: cache the position relationship matrix, and configure a point index for each element in the position relationship matrix; construct the candidate taking sequence based on the ordering sequence of the point index.

[0109] In a possible implementation, the sequence solving module 503 is specifically configured to: evaluate the Nth candidate taking sequence by using the distance prediction model to obtain a target estimated distance; evaluate the Nth candidate taking sequence by using the time length prediction model to obtain a target estimated time; evaluate the Nth candidate taking sequence by using the supply-demand relationship model to obtain a target influence index, the target influence index being used to represent an influence degree of the to-be-allocated order on the delivery resource in different supply-demand scenarios; and determine a first evaluation result of the Nth candidate taking sequence based on the target estimated distance, the target estimated time, and the target influence index.

[0110] In a possible implementation, the sequence solving module 503 is specifically configured to: convert the target estimated distance into a first score value; convert the target estimated time into a second score value; and determine the first evaluation result of the Nth candidate taking sequence based on the first score value, the second score value, and the target influence index.

[0111] In a possible implementation, the sequence solving module 503 is specifically configured to: determine a first weight corresponding to the first score value and a second weight corresponding to the second score value based on the target influence index; and perform weighted summation on the first score value and the second score value by using the first weight and the second weight to obtain the first evaluation result of the Nth candidate taking sequence.

[0112] In a possible implementation, the sequence solving module 503 is specifically configured to: in a case where the first evaluation result of the Nth candidate taking sequence is better than the first evaluation result of the N-1th pending taking sequence, determine the Nth candidate taking sequence as the Nth pending taking sequence; and in a case where the first evaluation result of the N-1th pending taking sequence is better than the first evaluation result of the Nth candidate taking sequence, determine the N-1th pending taking sequence as the Nth pending taking sequence.

[0113] In a possible implementation, the order information includes a first taking location and a first delivery destination location, the back order information includes at least one second taking location and a second delivery destination location corresponding to each second taking location, and the matrix constructing module 502 is specifically configured to: construct the position relationship matrix based on the first taking location, the first delivery destination location, the second taking location, the second delivery destination location, and the delivery resource location.

[0114] In a possible implementation, the order allocation module 504 is specifically configured to: evaluate the target taking and delivering sequence corresponding to each delivery resource by using a sequential evaluation model, to obtain a second evaluation result corresponding to each delivery resource; process the second evaluation result corresponding to each delivery resource, to obtain feature information corresponding to each delivery resource; and determine the target delivery resource from the plurality of delivery resources based on the target taking and delivering sequence, the second evaluation result, and the feature information corresponding to the plurality of delivery resources.

[0115] It should be noted that, when the order allocation apparatus provided in the above embodiments allocates orders, only the division of the above functional modules is used as an example for illustration, and in actual applications, the above functions can be completed by different functional modules according to needs, that is, the internal structure of the electronic device is divided into different functional modules to complete all or part of the functions described above. In addition, the order allocation apparatus and the order allocation method provided in the above embodiments belong to the same concept, and the specific implementation process is described in detail in the method embodiments, which will not be repeated here.

[0116] The electronic device provided in the embodiment of the present application also includes an order allocation apparatus, Figure 6 is a structural schematic diagram of an electronic device provided in the embodiment of the present application. As shown in the figure, Figure 6 the electronic device includes a memory 601 and a processor 602, wherein the memory 601 stores executable program code 6011, and the processor 602 is configured to invoke and execute the executable program code 6011 to execute an order allocation method.

[0117] It can be understood that, in order to implement the above functions, the electronic device contains hardware and / or software modules corresponding to each function. The algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented in the form of hardware or a combination of hardware and computer software. Whether a certain function is implemented in hardware or computer software driven hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application in combination with the embodiments, but such implementation should not be considered beyond the scope of the present application.

[0118] The embodiment can divide the functional modules of the electronic device according to the above method examples, for example, each functional module can be divided according to each function, or two or more functions can be integrated in one processing module. The integrated module can be realized in the form of hardware. It should be noted that the division of modules in the embodiment is illustrative, and is only a logical functional division. There can be another division method in actual implementation.

[0119] In the case of adopting the corresponding respective function to divide the respective function module, a possible composition schematic diagram of the electronic device involved in the above embodiment can include a display unit, a detection unit, a processing unit and the like. Wherein, the display unit, the detection unit and the processing unit cooperate with each other, can be used to support the electronic device to execute the above steps and the like, and / or for other processes of the technology described herein.

[0120] It should be noted that all relevant contents of the steps involved in the above method embodiments can be cited to the function description of the corresponding function module, which will not be repeated here.

[0121] The electronic device provided by the embodiment is used to execute the order allocation method described above, so as to achieve the same effect as the implementation method described above.

[0122] In the case of adopting the integrated unit, the electronic device can include a processing module, a storage module and a communication module. Wherein, the processing module can be used to control and manage the actions of the electronic device, for example, can be used to support the electronic device to execute the steps executed by the display unit, the detection unit and the processing unit. The storage module can be used to support the electronic device to execute the storage of program code and data and the like. The communication module can be used to support the communication between the electronic device and other devices.

[0123] Wherein, the processing module can be a processor or a controller. It can realize or execute various exemplary logical blocks, modules and circuits described in combination with the disclosure of the present application. The processor can also be a combination of computing functions, such as one or more microprocessor combinations, digital signal processing (digital signal processing, DSP) and microprocessor combinations, etc. The storage module can be a memory. The communication module can be a device for interacting with other electronic devices, such as radio frequency circuit, Bluetooth chip, Wi-Fi chip, etc.

[0124] In one embodiment, when the processing module is a processor and the storage module is a memory, the electronic device involved in the embodiment can be an electronic device with the structure as shown in the figure. Figure 6

[0125] The embodiment also provides a computer readable storage medium, which stores computer instructions, when the computer instructions run on the electronic device, make the electronic device execute the related method steps to realize the order allocation method provided by the above embodiment.

[0126] The embodiment also provides a computer program product, which includes a computer program, when the computer program is run, makes the computer execute the above related steps to realize the order allocation method provided by the above embodiment. ​

[0127] In addition, the embodiments of the present application further provide a device, which can be a chip, a component or a module, and the device can include a processor and a memory connected to each other; the memory is used to store computer-executable instructions; when the device is running, the processor can execute the computer-executable instructions stored in the memory, so that the chip executes the method in each method embodiment described above.

[0128] The electronic device, the computer-readable storage medium, the computer program product or the chip provided by the embodiments of the present application are all used to execute the corresponding method provided above, and thus the beneficial effects achieved by the electronic device, the computer-readable storage medium, the computer program product or the chip can refer to the beneficial effects of the corresponding method provided above, which will not be repeated here.

[0129] From the above description of the embodiments, those skilled in the art can understand that, for the convenience and brevity of description, only the division of the above functional modules is taken as an example for illustration, and in actual application, the above functions can be completed by different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above.

[0130] In several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, and the division of the modules or units is only a logical function division, and in actual implementation, another division mode can be adopted, for example, a plurality of units or components can be combined or integrated into another device, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some interfaces, devices or units, and can be electrical, mechanical or other forms.

[0131] The units described as separate components can or can not be physically separate, and the components shown as units can be one physical unit or multiple physical units, that is, can be located in one place or distributed in multiple different places. Some or all of the units can be selected according to actual needs to achieve the purpose of the embodiments.

[0132] In addition, each functional unit in each embodiment of the present application can be integrated in one processing unit, or each unit can exist physically independently, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software functional unit.

[0133] The integrated unit, if implemented in the form of a software function unit and sold or used as an independent product, can be stored in a readable storage medium. Based on such understanding, the technical solutions of the embodiments of the present application essentially or say the part that contributes to the prior art or the whole or part of the technical solutions can be embodied in the form of a software product. The software product is stored in a storage medium, including a plurality of instructions to make a device (which can be a single-chip microcomputer, a chip, etc.) or a processor execute all or part of the steps of the various embodiments of the method of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various media that can store program codes.

[0134] The above is only a specific embodiment of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of changes or replacements within the technical scope disclosed by the present application, which should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. An order allocation method, characterized by, The method comprises: obtaining order information of a to-be-assigned order, back single information of a plurality of delivery resources, and delivery resource positions of the plurality of delivery resources; for each of the delivery resources, based on the order information, the back single information, and the delivery resource positions, constructing a position relationship matrix corresponding to each of the delivery resources, wherein an element in the position relationship matrix represents a relationship between two positions; based on the position relationship matrix corresponding to each of the delivery resources, performing a plurality of cycles of taking and delivering sequence solving to obtain a target taking and delivering sequence corresponding to each of the delivery resources; based on the target taking and delivering sequences corresponding to the plurality of delivery resources, determining a target delivery resource from the plurality of delivery resources, and assigning the to-be-assigned order to the target delivery resource.

2. The method of claim 1, wherein, The method comprises: based on the position relationship matrix, sequentially generating a plurality of candidate taking and delivering sequences; after generating an Nth candidate taking and delivering sequence, evaluating the Nth candidate taking and delivering sequence to obtain a first evaluation result of the Nth candidate taking and delivering sequence, wherein N is an integer greater than 1; based on the first evaluation result of the Nth candidate taking and delivering sequence and a first evaluation result of an N-1th pending taking and delivering sequence, determining an Nth pending taking and delivering sequence; determining the last pending taking and delivering sequence as the target taking and delivering sequence.

3. The method of claim 2, wherein, The method comprises: caching the position relationship matrix and configuring a point index for each element in the position relationship matrix; based on a sorting sequence of the point index, constructing the candidate taking and delivering sequence.

4. The method of claim 2, wherein, The method comprises: using a distance prediction model to evaluate the Nth candidate taking and delivering sequence to obtain a target estimated distance; using a time prediction model to evaluate the Nth candidate taking and delivering sequence to obtain a target estimated time; using a supply and demand relationship model to evaluate the Nth candidate taking and delivering sequence to obtain a target impact index, wherein the target impact index is used to represent the impact of the to-be-assigned order on the delivery resource in different supply and demand scenarios; based on the target estimated distance, the target estimated time, and the target impact index, determining the first evaluation result of the Nth candidate taking and delivering sequence.

5. The method of claim 4, wherein, The method comprises: converting the target estimated distance into a first score value; converting the target estimated time into a second score value; based on the first score value, the second score value, and the target impact index, determining the first evaluation result of the Nth candidate taking and delivering sequence.

6. The method of claim 5, wherein, The method comprises: based on the first score value, the second score value, and the target impact index, determining the first evaluation result of the Nth candidate taking and delivering sequence. determine a first weight corresponding to the first score value and a second weight corresponding to the second score value based on the target influence indicator; perform weighted summation on the first score value and the second score value by using the first weight and the second weight to obtain a first evaluation result of the Nth candidate pick-and-place sequence.

7. The method of claim 2, wherein, The determining of the Nth pending pick-and-place sequence based on the first evaluation result of the Nth candidate pick-and-place sequence and the first evaluation result of the (N-1)th pending pick-and-place sequence comprises: in a case where the first evaluation result of the Nth candidate pick-and-place sequence is better than the first evaluation result of the (N-1)th pending pick-and-place sequence, determining the Nth candidate pick-and-place sequence as the Nth pending pick-and-place sequence; in a case where the first evaluation result of the (N-1)th pending pick-and-place sequence is better than the first evaluation result of the Nth candidate pick-and-place sequence, determining the (N-1)th pending pick-and-place sequence as the Nth pending pick-and-place sequence.

8. An electronic device, comprising: comprise: a memory configured to store executable program code; a processor configured to invoke and run the executable program code from the memory, so that the electronic device performs the order allocation method according to any one of claims 1 to 7.

9. A computer-readable storage medium, characterized in that, The computer readable storage medium stores computer instructions, when the computer instructions are run on an electronic device, the electronic device executes the order allocation method according to any one of claims 1 to 7.

10. A computer program product, characterised in that, comprise a computer program, when the computer program is run, the computer executes the order allocation method according to any one of claims 1 to 7.

Images