Order processing method, device, electronic device and storage medium

Abstract

The embodiment of the present application discloses an order processing method, device, electronic device and storage medium, the method comprising: according to the order identifier of the received order, performing project decomposition on the order associated with the order identifier to obtain one or more projects; respectively determining the order combination results of one or more projects with other orders within a preset time period; in response to the order combination result being orderable, placing the project and order identifier corresponding to the order combination result into a project order combination queue; in response to the project satisfying the order issuance condition in the project order combination queue, obtaining the project and the total quantity corresponding to the project from the project order combination queue. The embodiment of the present application realizes the determination of the order combination result of the project within a preset time period, and no longer relies on manual order combination decision-making, so that when the order volume is large, the order combination result can be quickly determined and the order combination processing can be performed, thereby reducing the order processing time and improving the order processing efficiency.

Description

Technical Field

[0001] The present application relates to the field of Internet technology, and in particular to an order processing method, device, electronic device and storage medium. Background Art

[0002] At present, the food delivery logic of catering businesses is that the chef determines whether multiple dishes can be combined into one order based on the printed food order. If feasible, the dishes will be directly combined and served together. If the dishes cannot be combined, the dishes will be served in chronological order.

[0003] The existing catering business's food delivery methods are constrained by the capabilities of the kitchen system. During peak order periods, the order volume increases, and food delivery decisions based on chef experience will lead to reduced food delivery capabilities, prolonged order processing time, and low order processing efficiency, which seriously affects the user experience. Summary of the Invention

[0004] The embodiments of the present application provide an order processing method, device, electronic device, and storage medium to reduce order processing time and improve order processing efficiency.

[0005] To solve the above problems, in a first aspect, embodiments of the present application provide an order processing method, comprising:

[0006] According to the order identifier of the received order, the order associated with the order identifier is decomposed into projects to obtain one or more projects;

[0007] Determining the order combination results of the one or more items with other orders within a preset time period;

[0008] In response to the order combining result being that the order can be combined, placing the project corresponding to the order combining result and the order identifier into a project order combining queue;

[0009] In response to the item satisfying an order condition in the item order queue, the item and the total quantity corresponding to the item are obtained from the item order queue.

[0010] Optionally, determining the order combination results of the one or more items with other orders within a preset time period includes:

[0011] Based on historical order data, estimate the order results of the one or more items and other orders within a preset time period.

[0012] Optionally, estimating, based on historical order data, the order consolidation results of the one or more items with other orders within a preset time period includes:

[0013] Traversing the one or more items to determine a current decision item;

[0014] Extracting input features of the current decision item based on the historical order data;

[0015] The input features are input into an order closing decision model to obtain an order closing result of the current decision item, where the order closing decision model is a machine learning model.

[0016] Optionally, extracting the input features of the current decision item based on the historical order data includes:

[0017] Determine, based on historical order data, the maximum number of orders and the quantile of the number of orders for the current decision item within a preset time period, and determine the maximum number of items, the minimum number of items, and the quantile of items in orders containing the current decision item within the preset time period, and determine item relevance information for the current decision item;

[0018] The maximum number of orders, the quantile of the number of orders, the maximum number of items, the minimum number of items, the quantile of items and the item correlation information are used as the input features.

[0019] Optionally, estimating, based on historical order data, the order consolidation results of the one or more items with other orders within a preset time period includes:

[0020] Based on historical order data, estimate the probability of combining the one or more items with other orders within a preset time period;

[0021] According to the probability of combining the one or more items with other orders within the preset time period, the result of combining the one or more items with other orders within the preset time period is determined.

[0022] Optionally, determining the result of combining the one or more items with other orders within the preset time period according to the probability of combining the one or more items with other orders within the preset time period includes:

[0023] In response to a probability that a project is combined with other orders within a preset time period being greater than or equal to a preset threshold, determining that a result of combining the project with other orders within the preset time period is possible;

[0024] In response to a probability that a project can be combined with other orders within a preset time period being less than a preset threshold, it is determined that a result of combining the project with other orders within the preset time period is uncombinable.

[0025] Optionally, after respectively estimating the order consolidation results of the one or more items with other orders within a preset time period, the method further includes:

[0026] In response to the order combining result being that the order cannot be combined, the project corresponding to the order combining result is placed in a project order issuing queue.

[0027] Optionally, after obtaining the project and the total quantity corresponding to the project from the project order queue, the method further includes:

[0028] The project and the total quantity are passed into the project order queue.

[0029] Optionally, the order placement condition is that the length of time the project has been placed in the project order queue reaches a preset time period, or that the total number of projects in the project order queue reaches a preset number.

[0030] In a second aspect, an embodiment of the present application provides an order processing device, comprising:

[0031] A project decomposition module is used to decompose the order associated with the received order identifier into projects according to the order identifier of the received order to obtain one or more projects;

[0032] A combined order determination module, configured to determine the combined order results of the one or more items with other orders within a preset time period;

[0033] an item cache module, configured to, in response to the order combining result being an order-combinable item, place the item corresponding to the order combining result and the order identifier into an item combining queue;

[0034] The order issuing module is used to obtain the project and the total quantity corresponding to the project from the project order queue in response to the project meeting the order issuing condition in the project order queue.

[0035] Optionally, the combined order determination module is specifically configured to:

[0036] Based on historical order data, estimate the order results of the one or more items and other orders within a preset time period.

[0037] Optionally, the combined order determination module includes:

[0038] a current item determining unit, configured to traverse the one or more items and determine a current decision item;

[0039] An input feature extraction unit, configured to extract input features of the current decision item based on the historical order data;

[0040] The order closing prediction unit is used to input the input features into the order closing decision model to obtain the order closing result of the current decision project, and the order closing decision model is a machine learning model.

[0041] Optionally, the input feature extraction unit is specifically used to:

[0042] Determine, based on historical order data, the maximum number of orders and the quantile of the number of orders for the current decision item within a preset time period, and determine the maximum number of items, the minimum number of items, and the quantile of items in orders containing the current decision item within the preset time period, and determine item relevance information for the current decision item;

[0043] The maximum number of orders, the quantile of the number of orders, the maximum number of items, the minimum number of items, the quantile of items and the item correlation information are used as the input features.

[0044] Optionally, the combined order determination module includes:

[0045] A combination probability estimation unit, configured to estimate, based on historical order data, the probability of combining the one or more items with other orders within a preset time period;

[0046] The order combination decision unit is used to determine the order combination results of the one or more items with other orders within a preset time period based on the probability of combining the one or more items with other orders within a preset time period.

[0047] Optionally, the order combination decision unit is specifically configured to:

[0048] In response to a probability that a project is combined with other orders within a preset time period being greater than or equal to a preset threshold, determining that a result of combining the project with other orders within the preset time period is possible;

[0049] In response to a probability that a project can be combined with other orders within a preset time period being less than a preset threshold, it is determined that a result of combining the project with other orders within the preset time period is uncombinable.

[0050] Optionally, the device further includes:

[0051] The direct order placement module is used to place the project corresponding to the order combination result into the project order placement queue in response to the order combination result being uncombinable.

[0052] Optionally, the device further includes:

[0053] The combined order issuing module is used to transfer the items and the total quantity into the item order issuing queue.

[0054] Optionally, the order placement condition is that the length of time the project has been placed in the project order queue reaches a preset time period, or that the total number of projects in the project order queue reaches a preset number.

[0055] In a third aspect, an embodiment of the present application further discloses an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the order processing method described in the embodiment of the present application when executing the computer program.

[0056] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the steps of the order processing method disclosed in the embodiment of the present application are performed.

[0057] The order processing method, device, electronic device and storage medium disclosed in the embodiments of the present application decompose the order associated with the order identifier of the received order into projects to obtain one or more projects, and respectively determine the order combination results of the one or more projects with other orders within a preset time period. In response to the order combination result being that the order can be combined, the project corresponding to the order combination result and the order identifier are placed in a project order combination queue. In response to the project meeting the order issuance condition in the project order combination queue, the project and the total quantity corresponding to the project are obtained from the project order combination queue, thereby realizing the determination of the order combination result of the project within the preset time period, and no longer relying on manual order combination decision-making. Therefore, when the order volume is large, the order combination result can be quickly determined and the order combination processing can be performed, thereby reducing the order processing time and improving the order processing efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following briefly introduces the drawings required for use in the embodiments or descriptions of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0059] Figure 1 This is a flowchart of the order processing method of Example 1 of the present application;

[0060] Figure 2 It is a structural diagram of the order processing device of Example 2 of the present application. DETAILED DESCRIPTION

[0061] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0062] Example 1

[0063] This embodiment discloses an order processing method, which is suitable for processing orders during peak periods, such as Figure 1 As shown, the method includes: steps 110 to 140.

[0064] Step 110 : Based on the order ID of the received order, the order associated with the order ID is decomposed into items to obtain one or more items.

[0065] When a merchant receives an order, the order is decomposed into items based on the order identifier, resulting in one or more items corresponding to the order identifier. For example, in the catering industry, the items are dishes. When an order is received, the order is decomposed into dishes, that is, each dish is separated, and the one or more dishes corresponding to the order identifier are obtained. In the online shopping industry, the items are commodities. When an order is received, the order is decomposed into commodities, that is, each commodity is separated, and the one or more commodities are obtained.

[0066] Step 120: Determine the order combination results of the one or more items with other orders within a preset time period.

[0067] The preset time period may be determined based on historical order data, human experience, or other requirements.

[0068] After decomposing the order into items to obtain one or more items, determine the results of combining the one or more items with other orders within a preset time period before the current time, or determine the results of combining the one or more items with other orders within a preset time period in the future, or use the current time as a time point within the preset time period, that is, determine the results of combining the one or more items with other orders within the preset time period.

[0069] In one embodiment of the present application, respectively determining the results of combining the one or more items with other orders within a preset time period includes: respectively estimating the results of combining the one or more items with other orders within a preset time period based on historical order data.

[0070] The historical order data may be order data within a specific time period, that is, order data during peak order periods, such as order data from 11:00 am to 2:00 pm and order data from 6:00 pm to 8:00 pm every day.

[0071] Obtain historical order data, analyze the historical order data, and estimate whether the one or more projects can be combined with projects in other orders within a preset time period in the future, and obtain the results of combining the one or more projects with other orders within the preset time period, thereby realizing the estimation of the results of combining the projects within the preset time period.

[0072] In one embodiment of the present application, estimating, based on historical order data, the order consolidation results of the one or more items with other orders within a preset time period includes:

[0073] Traversing the one or more items to determine a current decision item;

[0074] Extracting input features of the current decision item based on the historical order data;

[0075] The input features are input into an order closing decision model to obtain an order closing result of the current decision item, where the order closing decision model is a machine learning model.

[0076] The order combination decision model is a machine learning model trained based on historical order data. The input is the input features of a project, and the output is the order combination result of a project with other orders within a preset time period. The input features include but are not limited to: the maximum number of orders and the quantile of the number of orders for the current decision project within the preset time period, the maximum number of items, the minimum number of items, and the quantile of items in the orders containing the current decision project within the preset time period, and the project relevance information of the current decision project. The historical order data includes the historical order data of the current merchant and the historical order data of other merchants in the business district where the current merchant is located. The other merchants and the current merchant are in the same industry.

[0077] From the one or more projects, one project is selected as the current decision project. Based on the historical order data, historical order data related to the current decision project is extracted. Based on this historical order data, input features of the current decision project are determined. These input features are then input into the order consolidation decision model to obtain the order consolidation result for the current decision project. Using the order consolidation decision model, the accuracy of the order consolidation result estimates can be improved by estimating the order consolidation results for each project relative to other orders within a preset time period.

[0078] In one embodiment of the present application, extracting the input features of the current decision item based on the historical order data includes:

[0079] Determine, based on historical order data, the maximum number of orders and the quantile of the number of orders for the current decision item within a preset time period, and determine the maximum number of items, the minimum number of items, and the quantile of items in orders containing the current decision item within the preset time period, and determine item relevance information for the current decision item;

[0080] The maximum number of orders, the quantile of the number of orders, the maximum number of items, the minimum number of items, the quantile of items and the item correlation information are used as the input features.

[0081] Extract historical order data including the current decision project from historical order data, and based on the historical order data, count the maximum number of orders and the quantile of the number of orders for the current decision project within a preset time period, and count the maximum number of items, the minimum number of items, and the quantile of items included in the orders containing the current decision project within the preset time period, and determine the project correlation information of the current decision project based on the historical order data and the attributes of the current decision project, thereby obtaining the input features of the current decision project.

[0082] In the catering industry, when the item is a dish, the attribute can be the ingredients, and the item relevance information can be determined based on the ingredients used in the dish. For example, scrambled eggs with tomatoes and scrambled eggs with green peppers, both of these dishes include eggs as an ingredient, so the two dishes are related. The relevance information of dishes represents the substitutability of the dishes, that is, two related dishes can replace each other, that is, if a user orders one of the multiple related dishes, other users are likely to order another of the multiple related dishes, so the probability of combining the related dishes into one order is relatively small. Therefore, the item relevance information has a certain impact on the probability of combining the dishes.

[0083] It should be noted that, in addition to the aforementioned maximum number of orders and the quantile of the number of orders for the current decision item within the preset time period, the maximum number of items, the minimum number of items and the quantile of the items in the orders containing the current decision item within the preset time period, and the item relevance information of the current decision item, the input features may also include other information, such as merchant user information, business district information, etc.

[0084] In another embodiment of the present application, estimating, based on historical order data, the order consolidation results of the one or more items with other orders within a preset time period includes:

[0085] Based on historical order data, estimate the probability of combining the one or more items with other orders within a preset time period;

[0086] According to the probability of combining the one or more items with other orders within the preset time period, the result of combining the one or more items with other orders within the preset time period is determined.

[0087] In one embodiment of the present application, determining the result of combining the one or more items with other orders within the preset time period based on the probability of combining the one or more items with other orders within the preset time period includes:

[0088] In response to a probability that a project is combined with other orders within a preset time period being greater than or equal to a preset threshold, determining that a result of combining the project with other orders within the preset time period is possible;

[0089] In response to a probability that a project can be combined with other orders within a preset time period being less than a preset threshold, it is determined that a result of combining the project with other orders within the preset time period is uncombinable.

[0090] Based on historical order data, the probability of one or more projects being combined with other orders within a preset time period can be estimated. Projects with a combination probability greater than or equal to a preset threshold are determined to be possible to be combined with other orders within the preset time period, and projects with a combination probability less than a preset threshold are determined to be impossible to be combined with other orders within the preset time period. When estimating the probability of a project being combined with other orders within a preset time period based on historical order data, the estimation can be made based on the above-mentioned combination decision model, that is, after inputting the input features of a project into the combination decision model, the output of the combination decision model is obtained to obtain the probability of the project being combined with other orders within the preset time period, thereby determining the result of combining the project with other orders within the preset time period based on the combination probability.

[0091] Step 130: In response to the order combining result being that the order can be combined, the project corresponding to the order combining result and the order identifier are placed in an item combining queue.

[0092] The project consolidation queue is used to temporarily save projects that have been consolidable.

[0093] If it is determined that a project can be combined with other orders within the preset time period, the project and the corresponding order ID will be placed in the project combination queue and wait for combination.

[0094] Step 140: In response to the item in the item order queue satisfying an order condition, the item and the total quantity corresponding to the item are obtained from the item order queue.

[0095] The order placement condition is that the item has been in the item order queue for a preset period of time, or the total number of items in the item order queue has reached a preset number. When estimating the results of combining an item with other orders within a preset period of time, for sectors with high time requirements, the length of time an item has been in the item order queue for a preset period of time can be used as an order placement condition, such as in the catering sector. This order placement condition can prevent users from waiting too long.

[0096] If an item in the item order consolidation queue meets the order placement criteria, the item is retrieved from the consolidation queue, along with the corresponding order ID. The quantity of the item in each order ID is determined and summed up to obtain the total quantity. This allows the item to be consolidated and placed. For example, in the restaurant industry, if a dish is scrambled eggs with tomatoes and meets the order placement criteria, the item is retrieved from the consolidation queue, and the total quantity is calculated to be 4. This allows the item to be consolidated and given to the chef, allowing him to make four servings of scrambled eggs with tomatoes.

[0097] Taking the catering industry as an example, when an order is received, the order is broken down into its individual dishes, separating each dish to obtain one or more dishes corresponding to the order ID. For each dish, a consolidation decision model is used to estimate the probability of consolidating the dish with the same dish in other orders within a preset time period. If the consolidation probability exceeds a preset threshold, the dish is deemed consolidable with other orders within the preset time period and is added to the project consolidation queue. After the dish is added to the project consolidation queue, any other orders receiving the same dish within the preset time period will also be added to the project consolidation queue. If the time period for the first order to be added to the project consolidation queue reaches the preset time period, the quantity of the dish in the corresponding order is determined based on the order ID and accumulated to obtain the total quantity of the dish. The dish and total quantity are then transferred to the project ordering queue, where they await ordering, i.e., waiting for the chef to process the dish. By processing the same dish from multiple orders simultaneously, processing speed can be accelerated.

[0098] Taking the online shopping field as an example, when an order is received, the order is decomposed into products, that is, each product is separated to obtain one or more products and the corresponding quantity of each product. For each product, the order combination result with the same product in other orders within a preset time period is estimated. If the order combination result is that the order can be combined, the product and the corresponding order ID are added to the project order combination queue. If the time the project has been in the project order combination queue reaches the preset time or the corresponding quantity of the product reaches the preset quantity, the total quantity of the product is determined, and the product and the corresponding total quantity are added to the project order queue, waiting for the order to be placed.

[0099] The order processing method disclosed in the embodiment of the present application decomposes the order associated with the order identifier of the received order into projects to obtain one or more projects, and determines the order combination results of the one or more projects with other orders within a preset time period. In response to the order combination result being that the order can be combined, the project corresponding to the order combination result and the order identifier are placed in a project order combination queue. In response to the project meeting the order issuance condition in the project order combination queue, the project and the total quantity corresponding to the project are obtained from the project order combination queue, thereby realizing the determination of the order combination result of the project within the preset time period, and no longer relying on manual order combination decision-making. Therefore, when the order volume is large, the order combination result can be quickly determined and the order combination processing can be performed, thereby reducing the order processing time and improving the order processing efficiency.

[0100] Based on the above technical solution, after respectively estimating the results of combining the one or more projects with other orders within a preset time period, the method further includes:

[0101] In response to the order combining result being that the order cannot be combined, the project corresponding to the order combining result is placed in a project order issuing queue.

[0102] Among them, the project order queue is used to temporarily save projects to be ordered.

[0103] If it is determined that a project cannot be combined with other orders within the preset time period, the project will be directly placed in the project order queue and wait for order placement, so that orders can be placed in a timely manner for projects that are estimated to be uncombinable.

[0104] On the basis of the above technical solution, after obtaining the project and the total quantity corresponding to the project from the project combined order queue, the method further includes:

[0105] The project and the total quantity are passed into the project order queue.

[0106] The item order queue is used to temporarily store items to be ordered and the corresponding total quantity.

[0107] After obtaining the project and the corresponding total quantity from the project order consolidation queue, the project and the corresponding total quantity are placed in the project order issuance queue, waiting for issuance, so that the combined projects can be issued together.

[0108] Example 2

[0109] This embodiment discloses an order processing device, such as Figure 2 As shown, the order processing device 200 includes:

[0110] The project decomposition module 210 is configured to decompose the order associated with the received order identifier into projects according to the order identifier of the received order to obtain one or more projects;

[0111] The order combination determination module 220 is used to respectively determine the order combination results of the one or more items with other orders within a preset time period;

[0112] The item cache module 230 is configured to, in response to the order combining result being that the order can be combined, place the item corresponding to the order combining result and the order identifier into an item combining queue;

[0113] The order issuing module 240 is configured to obtain the item and the total quantity corresponding to the item from the item ordering queue in response to the item satisfying an order issuing condition in the item ordering queue.

[0114] Optionally, the combined order determination module is specifically configured to:

[0115] Based on historical order data, estimate the order results of the one or more items and other orders within a preset time period.

[0116] Optionally, the combined order determination module includes:

[0117] a current item determining unit, configured to traverse the one or more items and determine a current decision item;

[0118] An input feature extraction unit, configured to extract input features of the current decision item based on the historical order data;

[0119] The order closing prediction unit is used to input the input features into the order closing decision model to obtain the order closing result of the current decision project, and the order closing decision model is a machine learning model.

[0120] Optionally, the input feature extraction unit is specifically used to:

[0121] Determine, based on historical order data, the maximum number of orders and the quantile of the number of orders for the current decision item within a preset time period, and determine the maximum number of items, the minimum number of items, and the quantile of items in orders containing the current decision item within the preset time period, and determine item relevance information for the current decision item;

[0122] The maximum number of orders, the quantile of the number of orders, the maximum number of items, the minimum number of items, the quantile of items and the item correlation information are used as the input features.

[0123] Optionally, the combined order determination module includes:

[0124] A combination probability estimation unit, configured to estimate, based on historical order data, the probability of combining the one or more items with other orders within a preset time period;

[0125] The order combination decision unit is used to determine the order combination results of the one or more items with other orders within a preset time period based on the probability of combining the one or more items with other orders within a preset time period.

[0126] Optionally, the order combination decision unit is specifically configured to:

[0127] In response to a probability that a project is combined with other orders within a preset time period being greater than or equal to a preset threshold, determining that a result of combining the project with other orders within the preset time period is possible;

[0128] In response to a probability that a project can be combined with other orders within a preset time period being less than a preset threshold, it is determined that a result of combining the project with other orders within the preset time period is uncombinable.

[0129] Optionally, the device further includes:

[0130] The direct order placement module is used to place the project corresponding to the order combination result into the project order placement queue in response to the order combination result being uncombinable.

[0131] Optionally, the device further includes:

[0132] The combined order issuing module is used to transfer the items and the total quantity into the item order issuing queue.

[0133] Optionally, the order placement condition is that the length of time the project has been placed in the project order queue reaches a preset time period, or that the total number of projects in the project order queue reaches a preset number.

[0134] The order processing device provided in the embodiment of the present application is used to implement the various steps of the order processing method described in Example 1 of the present application. The specific implementation methods of each module of the device can be found in the corresponding steps and will not be repeated here.

[0135] The order processing device disclosed in the embodiment of the present application performs project decomposition on the order associated with the received order identifier according to the order identifier of the order, and obtains one or more projects. The order combination determination module determines the order combination results of the one or more projects with other orders within a preset time period respectively. The project cache module responds to the order combination result as being combinable and puts the project corresponding to the order combination result and the order identifier into the project order combination queue. The order issuance module responds to the project meeting the order issuance condition in the project order combination queue and obtains the project and the total quantity corresponding to the project from the project order combination queue, thereby realizing the determination of the order combination result of the project within the preset time period, and no longer relying on manual order combination decision-making. Therefore, when the order volume is large, the order combination result can be quickly determined and the order combination processing can be performed, thereby reducing the order processing time and improving the order processing efficiency.

[0136] Accordingly, an embodiment of the present application further discloses an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the order processing method described in the first embodiment of the present application is implemented. The electronic device may be a server, a PC, a mobile terminal, a personal digital assistant, a tablet computer, or the like.

[0137] An embodiment of the present application further discloses a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the steps of the order processing method described in the first embodiment of the present application are implemented.

[0138] Each embodiment in this specification is described in a progressive manner, with each embodiment focusing on the differences from other embodiments. Similar or identical parts between the various embodiments can be referred to in conjunction with each other. For the device embodiments, since they are generally similar to the method embodiments, their description is relatively simple, and for relevant parts, reference can be made to the description of the method embodiments.

[0139] The above is a detailed introduction to an order processing method, device, electronic device and storage medium provided in the embodiments of the present application. Specific examples are used herein to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea. At the same time, for those skilled in the art, according to the ideas of the present application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

[0140] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, and of course can also be implemented by hardware. Based on this understanding, the essence of the above technical solution or the part that contributes to the existing technology can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or certain parts of the embodiments.

Claims

1. An order processing method, comprising: According to the order identifier of the received order, the order associated with the order identifier is decomposed into projects to obtain one or more projects; Determining the order combination results of the one or more items with other orders within a preset time period; In response to the order combining result being that the order can be combined, placing the project corresponding to the order combining result and the order identifier into a project order combining queue; In response to the item meeting the order issuance condition in the item order queue, obtaining the item and the total quantity corresponding to the item from the item order queue; The step of respectively determining the result of combining the one or more items with other orders within a preset time period includes: Based on the historical order data, traverse the one or more items to determine the input features of the current decision item; Inputting the input features into an order closing decision model to obtain an order closing result for the current decision item, wherein the order closing decision model is a machine learning model; Determine, based on historical order data, the maximum number of orders and the quantile of the number of orders for the current decision item within a preset time period, and determine the maximum number of items, the minimum number of items, and the quantile of items in orders containing the current decision item within the preset time period, and determine the item relevance information of the current decision item; The maximum number of orders, the quantile of the number of orders, the maximum number of items, the minimum number of items, the quantile of items and the item correlation information are used as the input features.

2. The method according to claim 1, further comprising: after determining the results of combining the one or more items with other orders within a preset time period; In response to the order combining result being that the order cannot be combined, the project corresponding to the order combining result is placed in a project order issuing queue.

3. The method according to claim 1, after obtaining the project and the total quantity corresponding to the project from the project order queue, further comprising: The project and the total quantity are passed into the project order queue.

4. According to the method described in any one of claims 1 to 3, the order placement condition is that the length of time that the project is placed in the project order queue reaches a preset time period, or the total number of projects in the project order queue reaches a preset number.

5. An order processing device comprising: A project decomposition module is used to decompose the order associated with the received order identifier into projects according to the order identifier of the received order to obtain one or more projects; A combined order determination module, configured to determine the combined order results of the one or more items with other orders within a preset time period; an item cache module, configured to, in response to the order combining result being an order-combinable item, place the item corresponding to the order combining result and the order identifier into an item combining queue; an order issuing module, configured to obtain the item and the total quantity corresponding to the item from the item order queue in response to the item satisfying an order issuing condition in the item order queue; The combined order determination module is specifically configured to: Based on historical order data, estimate the order results of the one or more items with other orders within a preset time period; The combined order determination module includes: a current item determining unit, configured to traverse the one or more items and determine a current decision item; An input feature extraction unit, configured to extract input features of the current decision item based on the historical order data; an order closing prediction unit, configured to input the input features into an order closing decision model to obtain an order closing result for the current decision item, wherein the order closing decision model is a machine learning model; The input feature extraction unit is specifically used for: Determine, based on historical order data, the maximum number of orders and the quantile of the number of orders for the current decision item within a preset time period, and determine the maximum number of items, the minimum number of items, and the quantile of items in orders containing the current decision item within the preset time period, and determine the item relevance information of the current decision item; The maximum number of orders, the quantile of the number of orders, the maximum number of items, the minimum number of items, the quantile of items and the item correlation information are used as the input features.

6. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the order processing method according to any one of claims 1 to 4 when executing the computer program.

7. A computer-readable storage medium having a computer program stored thereon, wherein when the program is executed by a processor, the steps of the order processing method according to any one of claims 1 to 4 are implemented.

Images