Order combining method, medium, computer equipment and program product
By detecting logistics order update events and combining orders based on the promised delivery time and expected warehouse time, the problem of combining orders across time windows is solved, and more efficient logistics order mergers are achieved, and the opportunity to combine orders and combination effects are increased.
Patent Information
- Application Number
- CN202510198903.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-02-21
- Publication Date
- 2025-07-22
AI Technical Summary
In the prior art, the traditional combination of orders cannot realize combination of orders across logistics orders across different time windows, resulting in loss of combination of orders and poor combination of orders.
By detecting logistics order update events, the logistics order set is divided into several logistics order groups based on preset order combination conditions, and merged when the expected delivery time is reached. The order combination conditions are determined using the promised delivery time and the expected arrival time of the logistics order, and the order combination decision is dynamically triggered.
On the premise of ensuring the delivery time of logistics orders, the opportunity to combine orders is increased, the effect of combining orders is improved, the waiting time of logistics orders is reduced, and the efficiency of combining orders is improved.
Smart Images
Figure CN120355485A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of logistics technologies, and in particular, to a method for combining orders, a medium, a computer device, and a program product. Background Art
[0002] In recent years, e-commerce has flourished both at home and abroad, providing consumers with a richer supply of goods, and the corresponding logistics supply chain has become increasingly perfect. In the e-commerce scenario, after a consumer places an order on the platform side, the goods will be packed and shipped out of the warehouse, and may go through multiple possible logistics stages such as sorting, trunk line, customs clearance (for cross-border scenarios), and last-mile delivery, and finally reach the consumer. The relatively long fulfillment path of the logistics order corresponds to a relatively high fulfillment cost. How to reduce the fulfillment cost of the logistics order has a profound impact on increasing the economic benefits of the supply chain.
[0003] By combining and shipping multiple logistics orders that meet certain constraint conditions, the fulfillment cost can be effectively reduced. Traditional order combination methods usually adopt a time window algorithm, that is, combining logistics orders that meet the constraint conditions within the same time window. However, the above method cannot combine logistics orders across different time windows, resulting in a certain loss of order combination opportunities and a poor order combination effect. Summary of the Invention
[0004] In a first aspect, an embodiment of the present application provides an order combination method, the method including: detecting a logistics order update event; in response to the detected logistics order update event, obtaining a set of logistics orders in a logistics order system; dividing each logistics order in the set of logistics orders into several logistics order groups based on a preset order combination condition; any one of the logistics order groups includes one or more logistics orders; if the current time reaches the estimated delivery time of any one of the logistics order groups, combining each logistics order in the logistics order group, and deleting each logistics order in the logistics order group from the set of logistics orders; otherwise, returning to the step of detecting the logistics order update event; where the estimated delivery time of the logistics order group is the minimum value of the estimated delivery times of each logistics order in the logistics order group, and the estimated delivery time of the logistics order is determined based on the promised delivery time of the logistics order.
[0005] In a second aspect, an embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the method described in any embodiment of the present application is implemented.
[0006] In a third aspect, an embodiment of the present application provides a computer device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, and when the processor executes the computer program, the method described in any embodiment of the present application is implemented.
[0007] Fourthly, an embodiment of the present application provides a computer program product, including a computer program which, when executed by a processor, implements the method described in any embodiment of the present application.
[0008] In the embodiment of the present application, the order consolidation operation is triggered by a logistics order update event. Each time an order consolidation is performed, an order consolidation decision is made for each logistics order in the logistics order set of the logistics order system, and several logistics order groups are obtained. The estimated delivery time of the logistics order is determined based on the promised delivery time of the logistics order, and the minimum value of the estimated delivery times of each logistics order in the same logistics order group is determined as the estimated delivery time of the logistics order group. If the current time reaches the estimated delivery time of any logistics order group, the logistics orders in the logistics order group are merged; otherwise, wait for the next logistics order update event and trigger a new order consolidation operation. In this way, the present application can consolidate as many logistics orders as possible on the basis of meeting the promised delivery time of the logistics orders, increasing the order consolidation opportunities and improving the order consolidation effect.
[0009] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and do not limit the present application. BRIEF DESCRIPTION OF THE DRAWINGS
[0010] The drawings here are incorporated into the specification and constitute a part of the present application. These drawings show embodiments consistent with the present application and, together with the specification, are used to illustrate the technical solutions of the present application.
[0011] Figure 1 is a schematic diagram of the system architecture of an embodiment of the present application.
[0012] Figure 2 is a schematic diagram of the order consolidation method in the related art.
[0013] Figure 3 is a flowchart of the order consolidation method of an embodiment of the present application.
[0014] Figure 4 is a schematic diagram of the training framework of the in-warehouse time estimation model of the logistics order of an embodiment of the present application.
[0015] Figure 5 is a schematic diagram of the overall decision-making process of an embodiment of the present application.
[0016] Figure 6 is a flowchart of the decision-making process based on timeliness of an embodiment of the present application.
[0017] Figure 7 is a block diagram of the order consolidation device of an embodiment of the present application.
[0018] Figure 8It is a schematic diagram of the computer device according to an embodiment of the present application. Detailed implementation manners
[0019] Here, exemplary embodiments will be described in detail, and examples thereof are shown in the drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The implementation manners described in the following exemplary embodiments do not represent all implementation manners consistent with the present application. On the contrary, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.
[0020] The terms used in the present application are only for the purpose of describing specific embodiments and are not intended to limit the present application. The singular forms "a", "the", and "said" used in the present application and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term "and / or" as used herein refers to and includes any or all possible combinations of one or more of the associated listed items. In addition, the term "at least one" as used herein means any one of a plurality or any combination of at least two of a plurality.
[0021] It should be understood that although the terms first, second, third, etc. may be used in the present application to describe various information, such information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of the present application, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the word "if" as used herein may be interpreted as "when" or "while" or "in response to determining".
[0022] In order to enable those skilled in the art to better understand the technical solutions in the embodiments of the present application and make the above-mentioned objects, features, and advantages of the embodiments of the present application more obvious and understandable, the technical solutions in the embodiments of the present application will be further described in detail below with reference to the drawings.
[0023] Logistics order fulfillment refers to the full-link logistics order transfer process from the consumer placing an order to the completion of the transaction. It is one of the important links in the supply chain, including many links such as order placement and payment, logistics order processing, goods out-of-warehouse, and distribution, which are closely related to the consumer experience and fulfillment cost. Figure 1 A schematic diagram showing the system architecture of the logistics order fulfillment process is shown. As Figure 1As shown, the shipping modes of logistics orders can be roughly divided into two types. In the first shipping mode (also known as the warehouse shipping mode), the goods will be pre-shipped from the stock preparation warehouse to the consolidation warehouse before the logistics order is issued. In the second shipping mode (also known as the JIT mode, JIT stands for Just-In-Time, and the Chinese name is Just-In-Time production), after the consumer places an order, the e-commerce platform issues a logistics order to the merchant. After receiving the logistics order, the merchant ships the goods to the JIT warehouse, and then the JIT warehouse ships the goods to the consolidation warehouse. The consolidation warehouse can perform order consolidation processing on the logistics orders and pack and ship the goods to the distribution and main line for transportation based on the order consolidation result. Order consolidation processing means packing and shipping the logistics orders placed by the consumer within a certain period of time together. In addition, for some logistics orders that do not require order consolidation, the goods required by these logistics orders can also be directly shipped to the distribution and main line through the JIT warehouse or the stock preparation warehouse.
[0024] It should be noted that the above system architecture is only for exemplary illustration and is not used to limit this application. The solution of this application can be applied not only to the above system architecture but also to other system architectures. Moreover, the solution of this application can also be applicable to other shipping modes.
[0025] In the related art, the time window algorithm is usually used for order consolidation processing. Among them, the time window algorithm includes the fixed time window algorithm (that is, a time window with a fixed length) and the dynamic time window algorithm (that is, a time window with a variable length). Taking the fixed time window algorithm as an example below, and combined with Figure 2 , an example of the order consolidation method based on the time window algorithm will be given.
[0026] In the fixed time window algorithm, the time will be sliced into fixed-length segments. The logistics orders received within the same time slice will be uniformly made an order consolidation decision when reaching the processing time node corresponding to that time slice. As Figure 2 shown, assuming that a 30-minute time slice is used, in the first time slice, the logistics order system successively receives logistics order A1 and logistics order A2. Then, when reaching the processing time node T1 corresponding to the first time, a unified order consolidation decision will be made for logistics order A1 and logistics order A2, and logistics order A1 and logistics order A2 will be removed from the logistics order system. In the case of not reaching the processing time node T1 corresponding to the first time, logistics order A1 and logistics order A2 will wait in the logistics order system. Similarly, in the second time slice, the logistics order system successively receives logistics order A3, logistics order A4, and logistics order A5. When reaching the processing time node T2 corresponding to the second time, a unified order consolidation decision will be made for logistics order A3, logistics order A4, and logistics order A5, and logistics order A3, logistics order A4, and logistics order A5 will be removed from the logistics order system.
[0027] The above decision-making method has a simple logic. However, the above method cannot achieve order consolidation among logistics orders across different time windows, resulting in a certain loss of order consolidation opportunities and a poor order consolidation effect. For example, the same user may successively issue logistics order A2, logistics order A3, and logistics order A4 with the same destination address within a short period of time. These logistics orders originally meet the order consolidation conditions, but because logistics order A2 is generated in a different time window from logistics order A3 and logistics order A4, logistics order A2, logistics order A3, and logistics order A4 cannot be consolidated into the same logistics order.
[0028] Based on this, the present application provides an order consolidation method. See Figure 3 , the method includes:
[0029] Step S12: Detect a logistics order update event;
[0030] Step S14: In response to the detected logistics order update event, obtain the set of logistics orders in the logistics order system;
[0031] Step S16: Divide each logistics order in the set of logistics orders into several logistics order groups based on preset order consolidation conditions; any logistics order group includes one or more logistics orders;
[0032] Step S18: If the current time reaches the estimated delivery time of any logistics order group, merge each logistics order in the logistics order group and delete each logistics order in the logistics order group from the set of logistics orders; otherwise, return to the step of detecting a logistics order update event; wherein, the estimated delivery time of the logistics order group is the minimum value of the estimated delivery times of each logistics order in the logistics order group, and the estimated delivery time of the logistics order is determined based on the promised delivery time of the logistics order.
[0033] In the embodiments of the present application, the order consolidation method originally triggered by a time window is improved to an order consolidation method triggered by a logistics order update event. Different from the method in the related art where order consolidation decisions are uniformly made for all received logistics orders only when a certain time node is reached, the present application adopts a streaming decision-making method. Each time a logistics order update event occurs, a process of making order consolidation decisions for the logistics orders in the logistics order set is triggered, obtaining several groups of logistics orders, and calculating the estimated delivery time of the groups of logistics orders. Then, based on the estimated delivery time of the groups of logistics orders and the current time, it is determined whether to wait for the next logistics order update event or generate the final logistics order consolidation result, and the consolidated logistics orders are deleted from the logistics order set. That is to say, the groups of logistics orders in the present application are equivalent to the intermediate order consolidation results after a logistics order update event occurs. After obtaining this intermediate order consolidation result, it is not directly used as the final order consolidation result, but continues to wait. During the waiting process, if a new logistics order update event occurs, the order consolidation operation will be re-triggered to generate a new intermediate order consolidation result until the current time reaches the estimated delivery time of the groups of logistics orders. In this way, on the premise of ensuring the delivery timeliness of logistics orders, as many logistics orders meeting the order consolidation conditions as possible can be consolidated, thereby increasing the order consolidation opportunity and improving the order consolidation effect. The implementation details of the embodiments of the present application will be illustrated by examples with reference to the accompanying drawings.
[0034] In step S12, a logistics order update event can be detected. Among them, a logistics order is the smallest granularity participating in order consolidation, such as a piece of goods or a JIT package, and a logistics order can also be called an order consolidation unit. A logistics order update event refers to an event in which the status of a logistics order changes, which can be a logistics order generation event, a logistics order cancellation event, a logistics order logistics status change event, or a logistics order physical element change event. A logistics order generation event refers to an event in which a new logistics order is received by the logistics order system; a logistics order cancellation event refers to an event in which one or more generated logistics orders in the logistics order system are cancelled; a logistics order logistics status change event refers to an event in which the logistics status of a logistics order is updated, and the logistics status includes but is not limited to statuses such as the merchant has shipped the goods and the JIT warehouse has received the goods; a logistics order physical element change event refers to an event in which the information of one or more physical elements of the goods in a logistics order changes, where the physical elements include but are not limited to the size and / or weight of the goods.
[0035] In step S14, in response to detecting any one of the logistics order update events, a logistics order set of the logistics order system can be obtained. The above-mentioned logistics order system can be deployed in Figure 1In the consolidation warehouse in the system architecture shown, it is used to process logistics orders. The logistics order set is used to record the set of each logistics order currently received by the logistics order system. The number of logistics orders in the logistics order set may be greater than or equal to 0. For example, after a logistics order generation event occurs, the logistics order set includes at least one logistics order; after a logistics order cancellation event occurs, the number of logistics orders in the logistics order set may be greater than or equal to 0.
[0036] In some embodiments, each logistics order in the logistics order set is a logistics order of the same user, and the destination addresses of the logistics orders are the same. That is to say, only the logistics orders of the same user with the same destination address will be added to the same logistics order set and participate in the subsequent order consolidation decision. If two logistics orders are logistics orders of different users, or the destination addresses of the two logistics orders are different, then the two logistics orders do not participate in the subsequent order consolidation decision.
[0037] It can be understood that the above conditions are only an optional means for screening mergeable logistics orders, rather than a necessary means. For example, each logistics order in the logistics order set may also include logistics orders of different users sent to the same address, or include logistics orders of different users sent within the same geographical area (such as the same community or the same building). The specific order consolidation conditions can be set according to actual needs.
[0038] In step S16, if the number of logistics orders in the logistics order set is greater than 0, then each logistics order in the logistics order set can be divided into several logistics order groups. The logistics orders in the same logistics order group are logistics orders that meet the order consolidation conditions, that is, the logistics orders in the same logistics order group can be merged; the logistics orders in different logistics order groups are logistics orders that do not meet the order consolidation conditions, that is, the logistics orders in different logistics order groups cannot be merged. Each logistics order group can include one or more logistics orders.
[0039] In some embodiments, the order consolidation condition includes a condition determined based on the estimated delivery time of the previous logistics order and the estimated arrival time at the warehouse of the subsequent logistics order in the set of logistics orders, and this condition is also referred to as the timeliness condition. Herein, the previous logistics order refers to the logistics order that the logistics order system receives first, and the subsequent logistics order refers to the logistics order that the logistics order system receives later. That is to say, the time when the logistics order system receives the previous logistics order is earlier than the time when the logistics order system receives the subsequent logistics order. To ensure that the subsequent logistics order can catch up with the estimated delivery time of the previous logistics order, the estimated arrival time at the warehouse of the subsequent logistics order should be earlier than the estimated delivery time of the previous logistics order. Therefore, if the estimated arrival time at the warehouse in the subsequent logistics order is not later than the estimated delivery time of the previous logistics order, the previous logistics order and the subsequent logistics order are added to the same logistics order group. If the estimated arrival time at the warehouse in the subsequent logistics order is later than the estimated delivery time of the previous logistics order, the previous logistics order and the subsequent logistics order are added to different logistics order groups.
[0040] For example, assume that the estimated delivery time of the previous logistics order is the 5th day after receiving the order, and the estimated arrival time at the warehouse of the subsequent logistics order is the 3rd day after receiving the order. Then, the estimated arrival time at the warehouse of the subsequent logistics order is earlier than the estimated delivery time of the previous logistics order. Therefore, the subsequent logistics order and the previous logistics order can be added to the same logistics order group. Assume that the estimated delivery time of the previous logistics order is the 2nd day after receiving the order, and the estimated arrival time at the warehouse of the subsequent logistics order is the 3rd day after receiving the order. Then, the estimated arrival time at the warehouse of the subsequent logistics order is later than the estimated delivery time of the previous logistics order. Therefore, the subsequent logistics order and the previous logistics order can be added to different logistics order groups.
[0041] In the related art, the time window algorithm is used for order consolidation decision-making. Generally speaking, the time span of the time window is relatively small, and thus the impact on the delivery timeliness is also relatively small. That is to say, even if the order consolidation decision for the logistics orders received within the time window is uniformly made after the end of the time window, it usually will not cause the logistics orders to fail to be delivered according to the estimated delivery time. Therefore, in the order consolidation decision-making method based on the time window, the order consolidation decision is usually not made based on the timeliness condition. In this application, in order to consolidate as many logistics orders as possible, the constraint of the time window is removed, which may cause a logistics order to wait indefinitely for merging with other logistics orders, resulting in the failure of the logistics order to be delivered in time. To solve the above problems, this application sets the timeliness condition. Through the above setting, only when the estimated arrival time at the warehouse in the subsequent logistics order is not later than the estimated delivery time of the previous logistics order, the subsequent logistics order and the previous logistics order will be added to the same logistics order group. In this way, the situation where the previous logistics order waits indefinitely for the subsequent logistics order is avoided, thereby improving the delivery timeliness of the logistics order.
[0042] In the above example, the estimated delivery time of the logistics order refers to the time when the logistics order is expected to be delivered, and the estimated delivery time of the logistics order is not later than the latest delivery time of the logistics order (i.e., the last time limit for delivering the logistics order). The latest delivery time of the logistics order can be determined based on the promised delivery time of the logistics order. For example, in order to improve customer satisfaction and enhance market competitiveness, e-commerce platforms usually promise to deliver goods to consumers within a certain specified period (such as 3 days, 5 days, etc.) after receiving the order. In addition, the delivery destination of the logistics order can be obtained according to the logistics order information, and the delivery duration of the logistics order can be estimated based on the delivery destination of the logistics order and the shipping location. The latest delivery time of the logistics order can be determined based on the delivery duration of the logistics order and the promised delivery time of the logistics order. For example, assuming that the promised delivery time of the logistics order is the 5th day after receiving the order, and the estimated delivery duration of the logistics order is 2 days, then the logistics order needs to be delivered at the latest on the 3rd day after receiving the order, that is, the latest delivery time of the logistics order is the 3rd day after receiving the order, so the estimated delivery time of the logistics order is not later than the 3rd day after receiving the order.
[0043] The estimated arrival time of the logistics order at the warehouse refers to the estimated time when the goods in the logistics order arrive at the warehouse (such as Figure 1 the consolidation warehouse shown). If the shipping mode of the logistics order is the warehouse shipping mode in the foregoing embodiments, the goods required for the logistics order will be pre-shipped to the warehouse before the logistics order is generated. Therefore, the generation time of the logistics order can be directly used as the estimated arrival time of the logistics order at the warehouse. If the shipping mode of the logistics order is the JIT mode in the foregoing embodiments, the goods required for the logistics order will be shipped to the warehouse after the logistics order is generated. Therefore, the estimated arrival time of the logistics order can be estimated based on the information of the merchant who receives the logistics order. Among them, the information of the merchant includes, but is not limited to, the ID of the merchant and the shipping location of the merchant. Further, the estimated arrival time of the logistics order can be jointly estimated based on the information of the merchant and the information of the receiving warehouse (such as the location of the receiving warehouse). The following is an example of the specific method for determining the estimated arrival time of the logistics order in the JIT mode.
[0044] In some embodiments, refer to Figure 4, the estimated arrival time of a logistics order can be estimated through an arrival time prediction model. Optionally, the arrival time prediction model can be a probability model such as a Bayesian network. The arrival time prediction model can be trained based on the arrival time of the merchant's historical logistics orders and the merchant's information. Specifically, the arrival time prediction model can predict the arrival time of the merchant's historical logistics orders based on the merchant's information, and the arrival time prediction model can be offline-trained according to the difference between the arrival time predicted by the arrival time prediction model and the arrival time of the merchant's historical logistics orders. After the offline training is completed, the merchant's information for receiving the logistics order can be processed through the arrival time prediction model, so as to predict the probability distribution of the arrival time of the merchant's logistics order. For example, the probability that the merchant's logistics order arrives on the 1st day after receiving the order is 5%, the probability that the merchant's logistics order arrives on the 2nd day after receiving the order is 10%, and the probability that the merchant's logistics order arrives on the 3rd day after receiving the order is 85%, and so on. The above probability distribution can be used to estimate the estimated arrival time of the merchant's logistics order during the online processing. A preset probability can be selected in advance, and the estimated arrival time of the logistics order can be determined based on the preset probability and the probability distribution predicted by the arrival time prediction model. Continuing with the previous example, assuming the preset probability is 85%, the arrival duration corresponding to this preset probability can be obtained, that is, the 3rd day after receiving the order, so as to determine that the 3rd day after receiving the order is the estimated arrival time of the logistics order. The above preset probability can be used as a model parameter and adjusted according to actual needs.
[0045] Furthermore, the arrival time prediction model can also be updated regularly. Each time it is updated, the arrival time of the historical logistics orders within the most recent preset period (the preset period can be set according to actual needs) is used as sample data to retrain the arrival time prediction model. Through the above method, the arrival time prediction model can be adapted to the real change trend of the arrival time, so that the prediction result is more accurate.
[0046] It can be understood that the above method is only an optional implementation method. In other examples, other methods can also be used to estimate the estimated arrival time of the logistics order. For example, the average arrival time of the merchant's logistics orders within a period of time can be determined as the estimated arrival time of the merchant's logistics order.
[0047] In some embodiments, goods with certain attributes are not suitable for transportation together with other goods. For example, liquid goods are not suitable for transportation together with charged goods, or goods that are too large in size, too heavy in weight, too high in price, or of a specific category need to be transported separately. Therefore, the order consolidation conditions can include conditions determined based on the attributes of the goods in the logistics order, which are also referred to as physical attribute conditions. Based on this, logistics orders whose goods' attributes meet the preset conditions can be grouped into the same logistics order group, while logistics orders whose goods' attributes do not meet the preset conditions are grouped into different logistics order groups from those whose goods' attributes meet the preset conditions. When the attributes of the goods include size, the preset conditions can include that the size of the goods is within a preset size range (for example, the size of the goods is greater than the preset size upper limit), where the size can include the single side length of the goods and / or the sum of the three side lengths (i.e., the sum of length, width, and height). When the attributes of the goods include weight, the preset conditions can include that the weight of the goods is within a preset weight range (for example, the weight of the goods is greater than the preset weight upper limit). When the attributes of the goods include price, the preset conditions can include that the price of the goods is within a preset price range (for example, the price of the goods is greater than the preset price upper limit). When the attributes of the goods include category, the preset conditions can include that the category of the goods matches the preset combinable categories.
[0048] It can be understood that the above is only an exemplary illustration. In other examples, the preset conditions can be other conditions, and the attributes of the goods can also include other attributes.
[0049] In some embodiments, the order consolidation conditions include conditions determined based on service rules, which are also referred to as service rule conditions. Optionally, the service rule can be that logistics orders of a target category are not consolidated with logistics orders of other categories. Among them, the category of the logistics order can be determined based on information such as the tariff payment method, preferential rules, payment method, and / or logistics distribution requirements of the logistics order. Correspondingly, by setting the above order consolidation conditions, it can be ensured that logistics orders with specific tariff payment methods, specific preferential rules, specific payment methods, and / or specific logistics distribution requirements are not consolidated with other logistics orders. According to actual needs, the service rule can also be other rules, which will not be listed here.
[0050] In some embodiments, the order consolidation conditions can also include at least two of the above conditions, and can also include other conditions. After determining the order consolidation conditions, a preset solution method can be used to solve the optimal logistics order grouping method, and the solved logistics order grouping is applied to subsequent processes.
[0051] In step S18, the estimated delivery time of each logistics order group can be determined. Among them, the estimated delivery time of a logistics order group is the minimum value of the estimated delivery times of the individual logistics orders in the logistics order group. For example, assume that the logistics order group S includes logistics orders A1, A2, and A3. Among them, the estimated delivery time of logistics order A1 is T1, the estimated delivery time of logistics order A2 is T2, and the estimated delivery time of logistics order A3 is T3, and T1 is earlier than T2, and T2 is earlier than T3. Then the estimated delivery time of this logistics order group S is T1. The estimated delivery time of a logistics order can be determined based on the promised delivery time of the logistics order. The specific determination method is as described in the foregoing embodiments and will not be elaborated here.
[0052] After determining the estimated delivery time of each logistics order group, the following judgment can be made for each logistics order group: whether the current time has reached the estimated delivery time of the logistics order group. If so, in order to ensure the timeliness of the logistics order, the individual logistics orders in the logistics order group can be merged. The merged logistics orders can be packed and shipped together. In addition, the individual logistics orders in the logistics order group can also be deleted from the logistics order set. Continuing with the previous example, assume that the current time reaches T1. Then the individual logistics orders in the logistics order group S can be merged, and logistics orders A1, A2, and A3 can be deleted from the logistics order set.
[0053] If the above judgment result is no, then step S12 can be returned, so as to continue waiting for possible new order combination opportunities without affecting the timeliness of the logistics order and achieve as many order combinations as possible.
[0054] The following uses an example to illustrate the order combination process.
[0055] Assume that the initial logistics order set is empty. On the Tth day, logistics order A1 is received (i.e., a logistics order generation event occurs), and the estimated delivery time of logistics order A1 is the 5th day after receiving the order. At this time, the logistics order set includes logistics order A1, and a logistics order group including logistics order A1 is obtained. The estimated delivery time of this logistics order group is the 5th day after receiving the order (i.e., the (T + 5)th day). Since the current time is earlier than the estimated delivery time of the logistics order group, the logistics order update event is continuously detected.
[0056] Suppose that on the (T + 1)-th day, a logistics order A2 is received, and the estimated delivery time of the logistics order A2 is the 3rd day after receiving the order (i.e., the (T + 4)-th day). Suppose that the logistics order A1 and the logistics order A2 meet the preset order combination conditions and are combined into the same logistics order group. At this time, the logistics order set includes the logistics order A1 and the logistics order A2, and the estimated delivery time of this logistics order group is the earlier one of the estimated delivery time of the logistics order A1 and the estimated delivery time of the logistics order A2, that is, the (T + 4)-th day. Since the current time is earlier than the estimated delivery time of the logistics order group, the logistics order update event is continuously detected.
[0057] Suppose that on the (T + 2)-th day, a logistics order A3 is received, and the estimated delivery time of the logistics order A3 is the 0th day after receiving the order (i.e., the (T + 2)-th day). Suppose that the logistics order A1, the logistics order A2, and the logistics order A3 meet the preset order combination conditions and are combined into the same logistics order group. At this time, the logistics order set includes the logistics order A1, the logistics order A2, and the logistics order A3, and the estimated delivery time of this logistics order group is the earliest one of the estimated delivery time of the logistics order A1, the estimated delivery time of the logistics order A2, and the estimated delivery time of the logistics order A3, that is, the (T + 2)-th day. Since the current time has reached the estimated delivery time of the logistics order group, the logistics orders in the logistics order group (i.e., the logistics order A1, the logistics order A2, and the logistics order A3) are combined, and the logistics order A1, the logistics order A2, and the logistics order A3 are deleted from the logistics order set.
[0058] When other logistics order update events occur, the processing method is similar to the above process and will not be described one by one here.
[0059] Figure 5 The overall process of the embodiment of the present application is shown.
[0060] In step S22, the order combination operation is triggered by a decision event. Among them, the decision event is the logistics order update event in the foregoing embodiment. Each time a decision event occurs, an order combination decision is triggered, and the order combination decision result (i.e., the logistics order group) is updated for actual operation execution.
[0061] In step S24, the order combination decision range is determined. Each time a decision is triggered, the decision range includes all logistics orders that meet the combinable conditions (such as the same consumer, the same delivery address, not shipped from the consolidation warehouse, etc.) to ensure that all eligible orders are combined. A complete decision includes three parts of modules: a decision module based on service rules, a decision module based on time limit conditions, and a decision module based on physical attribute conditions.
[0062] In step S26, a decision is made through a decision-making module based on service rules. This module splits the logistics orders participating in the decision according to service rules, and mutually exclusive logistics orders that cannot be combined will be divided into different logistics order groups for the next decision-making.
[0063] In step S28, a decision is made through a decision-making module based on timeliness conditions. This module makes a decision on whether different logistics orders can be combined from the timeliness dimension, and adds the logistics orders that cannot be combined in terms of timeliness dimension to different logistics order groups. The decision-making framework of this module is as Figure 6 shown.
[0064] The combined order decision needs to match the promised delivery time of the logistics order to the consumer. Therefore, each logistics order has an estimated delivery time (which can also be other similar time points, and this application does not limit it). Each time a decision is made, first, based on the physical trajectory nodes and time trajectory node information of the logistics before this decision for the logistics order, the estimated arrival time at the warehouse of the logistics order is estimated (which can also be other similar time points, and this application does not limit it). Then, by solving a classic set partitioning problem, the optimal logistics order grouping is obtained.
[0065] Step S282: Estimate the estimated arrival time at the warehouse of the logistics order
[0066] For the logistics orders in the JIT mode, a pre-trained Bayesian network can be used to obtain the probability distribution of the estimated arrival time at the warehouse. The obtained estimated arrival time at the warehouse can be consumed by step S284, and the result data is fed back as the training set for the next training to realize the continuous iterative update of the model. This application does not limit the training method, and any other model can be used for training.
[0067] Step S284: Solve the logistics order grouping
[0068] Input: The estimated delivery time of the logistics order, the probability distribution of the estimated arrival time at the warehouse obtained in step S282.
[0069] Output: Logistics order grouping.
[0070] Objective: Minimize the number of logistics order groupings.
[0071] Constraint: The estimated arrival time at the warehouse of the logistics orders within the same logistics order grouping is not later than the minimum value of the estimated delivery times of each logistics order within this logistics order grouping.
[0072] This is a typical Set Partition problem; define the current moment as T, and a combined order unit is The information included is the estimated time point for warehousing in the consolidation warehouse (Obtained by selecting the X - quantile of the predicted time - limit distribution, where X is determined by historical simulation to obtain the optimal parameters), the predicted off - shelf time point of the consolidation warehouse Define G as a group, G set is the set of groups, that is, G ∈ G set .
[0073] Decision variable
[0074] x oG : Whether the consolidation unit o goes to the group G
[0075] Objective function
[0076] Minimize the number of sets: min|G set |.
[0077] Constraint
[0078] Indicates that a consolidation unit appears in only one group;
[0079] Indicates that the time - limit condition is satisfied.
[0080] This application does not limit the solution method. Small - scale DFS exact search and large - scale meta - heuristic search methods can be used to solve the problem.
[0081] Step S30: Make a decision through a decision - making module based on physical - property conditions. This module makes a decision on whether logistics orders can be consolidated from the dimension of physical elements, divides the logistics orders that do not meet the physical - property conditions into different logistics - order groups, and finally obtains the consolidation result of a single consolidation decision. Some of the considered physical - element constraints include, but are not limited to, the following: single - side length limit of goods, sum of three - side lengths limit of goods, goods - category limit, goods - weight limit, goods - amount (i.e., price) limit, etc.
[0082] This problem can be modeled as a classic three - dimensional bin - packing problem. When the constraints related to the placement position, such as the single - side length and the sum of three - side lengths, do not need to be considered, this problem degenerates into a knapsack problem. This application does not limit the solution method, and a tree model based on beam search can be used to solve the problem.
[0083] The consolidation method proposed in this application considers various constraint conditions, realizes dynamic real - time consolidation, changes the fixed / dynamic time - window consolidation algorithm to a dynamic real - time multiple - chasing consolidation decision algorithm, and realizes the maximum approximation to the theoretical consolidation upper limit.
[0084] See Figure 7 , this application also provides a consolidation device, and the device includes:
[0085] A detection module 202, configured to detect a logistics order update event;
[0086] An acquisition module 204, configured to acquire a set of logistics orders of a logistics order system in response to the detected logistics order update event;
[0087] A grouping module 206, configured to divide each logistics order in the set of logistics orders into a plurality of logistics order groups based on a preset order combination condition; any one of the logistics order groups includes one or more logistics orders;
[0088] An order combination module 208, configured to, if the current time reaches the estimated delivery time of any one of the logistics order groups, combine each logistics order in the logistics order group, and delete each logistics order in the logistics order group from the set of logistics orders; otherwise, return to the step of detecting a logistics order update event; wherein, the estimated delivery time of the logistics order group is the minimum value of the estimated delivery times of each logistics order in the logistics order group, and the estimated delivery time of the logistics order is determined based on the promised delivery time of the logistics order.
[0089] An embodiment of the present application further provides a computer device, which at least includes a memory, a processor, and a computer program stored on the memory and executable on the processor. Wherein, when the processor executes the program, the method described in any one of the foregoing embodiments is implemented.
[0090] Figure 8 FIG. shows a more specific schematic diagram of the hardware structure of a computer device provided by an embodiment of the present application. The device may include: a processor 302, a memory 304, an input / output interface 306, a communication interface 308, and a bus 310. Wherein, the processor 302, the memory 304, the input / output interface 306, and the communication interface 308 are communicatively connected to each other inside the device through the bus 310.
[0091] The processor 302 may be implemented in a general-purpose central processing unit (CPU), a microprocessor, an application specific integrated circuit (ASIC), or one or more integrated circuits, etc., and is configured to execute relevant programs to implement the technical solution provided by the embodiment of the present application. The processor 302 may further include a graphics card, and the graphics card may be an Nvidia titan X graphics card or a 1080Ti graphics card, etc.
[0092] The memory 304 may be implemented in the form of a Read Only Memory (ROM), a Random Access Memory (RAM), a static storage device, a dynamic storage device, etc. The memory 304 may store an operating system and other application programs. When implementing the technical solutions provided in the embodiments of the present application through software or firmware, the relevant program codes are stored in the memory 304 and called and executed by the processor 302.
[0093] The input / output interface 306 is used to connect to the input / output module to implement information input and output. The input / output module may be configured as a component in the device (not shown in the figure) or externally connected to the device to provide corresponding functions. Among them, the input device may include a keyboard, a mouse, a touch screen, a microphone, various sensors, etc., and the output device may include a display, a speaker, a vibrator, an indicator light, etc.
[0094] The communication interface 308 is used to connect to a communication module (not shown in the figure) to implement communication and interaction between this device and other devices. Among them, the communication module may implement communication in a wired manner (such as USB, network cable, etc.) or in a wireless manner (such as mobile network, Wi-Fi, Bluetooth, etc.).
[0095] The bus 310 includes a path for transmitting information between various components of the device (such as the processor 302, the memory 304, the input / output interface 306, and the communication interface 308).
[0096] It should be noted that although the above device only shows the processor 302, the memory 304, the input / output interface 306, the communication interface 308, and the bus 310, in the specific implementation process, this device may also include other components necessary for normal operation. In addition, those skilled in the art can understand that the above device may also only include the components necessary for implementing the solutions of the embodiments of the present application and not necessarily include all the components shown in the figure.
[0097] The embodiments of the present application provide a computer program product, including a computer program, which when executed by a processor implements the method described in any embodiment of the present application.
[0098] The embodiments of the present application also provide a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, it implements the method described in any of the foregoing embodiments.
[0099] A computer-readable medium includes both permanent and non-permanent, removable and non-removable media that can implement information storage by any method or technology. The information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassette tapes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transitory medium that can be used to store information accessible by a computer device. As defined herein, a computer-readable medium does not include transitory computer-readable media, such as modulated data signals and carrier waves.
[0100] Each embodiment in this application is described in a progressive manner. For the same or similar parts among the embodiments, reference can be made to each other. Each embodiment focuses on the differences from other embodiments. In particular, for the device embodiments, since they are basically similar to the method embodiments, the description is relatively simple. For the relevant parts, reference can be made to the description of the method embodiments. The device embodiments described above are merely illustrative. The modules described as separate components may or may not be physically separated. When implementing the solution of the embodiments of this application, the functions of the modules can be implemented in the same or multiple software and / or hardware. It is also possible to select some or all of the modules according to actual needs to achieve the purpose of the solution of this embodiment. A person of ordinary skill in the art can understand and implement it without creative efforts.
[0101] The above is only the specific implementation manner of the embodiments of this application. It should be noted that for those of ordinary skill in the art in the technical field, without departing from the principle of the embodiments of this application, several improvements and refinements can be made, and these improvements and refinements should also be regarded as the protection scope of the embodiments of this application.
Claims
1. A consolidation method, the method comprising: Detecting a logistics order update event; In response to the detected logistics order update event, obtaining a set of logistics orders of the logistics order system; Dividing each logistics order in the set of logistics orders into several logistics order groups based on preset consolidation conditions; Any one of the logistics order groups includes one or more logistics orders; If the current time reaches the estimated delivery time of any one of the logistics order groups, merging each logistics order in the logistics order group and deleting each logistics order in the logistics order group from the set of logistics orders; otherwise, returning to the step of detecting the logistics order update event; wherein, the estimated delivery time of the logistics order group is the minimum value of the estimated delivery times of each logistics order in the logistics order group, and the estimated delivery time of the logistics order is determined based on the promised delivery time of the logistics order.
2. The method according to claim 1, wherein the logistics order update event includes any one of the following events: A logistics order generation event; A logistics order cancellation event; A logistics status change event of the logistics order; A physical element change event of the logistics order.
3. The method according to claim 1, wherein the preset consolidation conditions include conditions determined based on the estimated delivery time of the previous logistics order and the estimated arrival time at the warehouse of the subsequent logistics order in the set of logistics orders, the time when the logistics order system receives the previous logistics order is earlier than the time when the logistics order system receives the subsequent logistics order, and the estimated arrival time at the warehouse of the logistics order is the estimated time when the goods in the logistics order are delivered to the warehouse; the dividing each logistics order in the set of logistics orders into several logistics order groups based on the preset consolidation conditions includes: If the estimated arrival time at the warehouse in the subsequent logistics order is not later than the estimated delivery time of the previous logistics order, adding the previous logistics order and the subsequent logistics order to the same logistics order group.
4. The method according to claim 3, wherein the delivery mode of the logistics order includes a first delivery mode in which the goods are pre-delivered to the warehouse before the logistics order is issued, and the estimated arrival time at the warehouse of the logistics order in the first delivery mode is the generation time of the logistics order.
5. The method according to claim 3, wherein the delivery mode of the logistics order includes a second delivery mode in which the goods are sent to the warehouse after the logistics order is issued, and the estimated arrival time at the warehouse of the logistics order in the second delivery mode is estimated based on the information of the merchant who accepts the logistics order.
6. The method according to claim 5, the method further comprising: Obtaining the probability distribution of the arrival time at the warehouse of the logistics order of the merchant predicted by the arrival time estimation model based on the information of the merchant; The arrival time estimation model is trained based on the arrival time at the warehouse of the historical logistics order of the merchant and the information of the merchant; Determining the estimated arrival time at the warehouse of the logistics order in the second delivery mode based on a preset probability and the probability distribution.
7. The method according to any one of claims 1 to 6, wherein the preset order consolidation condition includes a condition determined based on the attributes of the goods in the logistics order; dividing each logistics order in the logistics order set into several logistics order groups based on the preset order consolidation condition includes: Adding logistics orders whose goods attributes meet the preset conditions to the same logistics order group.
8. The method according to claim 7, The attribute includes size, and the preset condition includes that the size of the goods is within a preset size range; and / or The attribute includes weight, and the preset condition includes that the weight of the goods is within a preset weight range; and / or The attribute includes price, and the preset condition includes that the price of the goods is within a preset price range; and / or The attribute includes category, and the preset condition includes that the category of the goods hits a preset combinable category.
9. The method according to any one of claims 1 to 6, wherein the preset order consolidation condition includes a condition determined based on service rules, and the service rules are used to indicate target logistics order categories that cannot be consolidated; dividing each logistics order in the logistics order set into several logistics order groups based on the preset order consolidation condition includes: Adding logistics orders of other categories except the target logistics order category to the same logistics order group.
10. The method according to claim 1, wherein each of the logistics orders is a logistics order of the same user, and the destination addresses of each of the logistics orders are the same.
11. A computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the method according to any one of claims 1 to 10 is implemented.
12. A computer device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, and when the processor executes the computer program, the method according to any one of claims 1 to 10 is implemented.
13. A computer program product, including a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 10 is implemented.