WO2024011844A1

WO2024011844A1 - Aggregate order optimization processing method and apparatus, and storage medium

Info

Publication number: WO2024011844A1
Application number: PCT/CN2022/138932
Authority: WO
Inventors: 夏春浩; 李双双; 肖贺
Original assignee: 北京京东振世信息技术有限公司; 北京京东乾石科技有限公司
Priority date: 2022-07-11
Filing date: 2022-12-14
Publication date: 2024-01-18
Also published as: CN117436559A

Abstract

Provided in the present disclosure are an aggregate order optimization processing method and apparatus, and a storage medium. The aggregate order optimization processing method comprises: generating, at a preset period, a plurality of candidate aggregate orders by using all orders in an order pool; and when an i-th candidate aggregate order among the plurality of candidate aggregate orders does not meet a preset constraint condition, moving all orders in the i-th candidate aggregate order into the order pool, wherein 1 ≤ i ≤ N, and N is the total number of candidate aggregate orders.

Description

Collection order optimization processing method, device and storage medium

Cross-references to related applications

This application is based on the application with CN application number 202210808972.8 and the filing date is July 11, 2022, and claims its priority. The disclosure content of the CN application is hereby incorporated into this application as a whole.

Technical field

The present disclosure relates to the field of information processing, and in particular to a method and device for optimizing processing of collective orders, and a storage medium.

Background technique

Currently in the urban delivery process, before orders are issued and processed, they are combined into a collective order based on the user's expected delivery time and whether the road area is the same, and then picking is carried out according to the collective order and according to the route planned by the collective order. Delivery.

Contents of the invention

According to a first aspect of an embodiment of the present disclosure, a method for optimizing collection orders is provided, including: using all orders in an order pool to generate multiple candidate collection orders in a preset cycle; If the i-th candidate set order does not meet the preset constraints, all orders in the i-th candidate set order will be moved into the order pool, 1≤i≤N, and N is the total number of candidate set orders.

In some embodiments, before moving all orders in the i-th candidate set order into the order pool, it is determined whether the difference between the latest release time of the i-th candidate set order and the current time is greater than Preset time threshold; if the difference is greater than the preset time threshold, move all orders in the i-th candidate set order into the order pool.

In some embodiments, if the difference is not greater than the preset time threshold, the i-th candidate set order is issued.

In some embodiments, when the i-th candidate set order satisfies preset constraints, the i-th candidate set order is issued.

In some embodiments, the preset constraints include: the earliest production time of the i-th candidate set order is greater than the sum of the current time and preset parameters, where the earliest production time is the i-th candidate set order The earliest time among the production times of each order in the order; and the total number of orders in the i-th candidate set order is less than the preset upper limit.

In some embodiments, the preset constraints also include: when the i-th candidate set order is divided into a catering order set and a non-catering order set, any catering order in the catering order set The delivery time of is earlier than the delivery time of any non-catering order in the non-catering order set.

In some embodiments, generating multiple candidate set orders using all orders in the order pool includes: using a first algorithm to process all orders in the order pool to generate multiple candidate set orders; wherein, The first algorithm includes: randomly selecting an order from the order pool; in the case where there are already candidate set orders, if a matching position can be found in the existing candidate set orders using a preset strategy, then a random selection will be made Insert the order into the matching position; if the matching position cannot be found in the existing candidate collection order, or there is currently no candidate collection order, insert the randomly selected order into the new candidate collection order; repeat the selection from the order pool An order is randomly selected from the order pool until there is no order left in the order pool.

In some embodiments, generating multiple candidate set orders using all orders in the order pool includes: using a second algorithm to process all orders in the target set to generate multiple candidate set orders; wherein, The second algorithm includes: dividing the orders in the order pool into seed orders and non-seed orders according to preset rules; randomly selecting a seed order from the plurality of seed orders as a basic order; using the preset strategy to select Output seed orders and non-seed orders that can be placed in the same collective order with the basic order to generate a collective order; repeatedly select a seed order randomly from the multiple seed orders as the basic order until the multiple seeds are Until the order is processed.

In some embodiments, the preset rules include: in the order pool, the order whose difference between the issuance time and the current time is less than the time difference threshold is used as a seed order, and the order pool except the seed order is Outside orders are treated as non-seed orders.

In some embodiments, after the plurality of seed orders are processed, if there are remaining orders in the order pool, the first algorithm is used to process all remaining orders in the order pool.

In some embodiments, a first optimization process is performed on the plurality of candidate collection orders; wherein the first optimization process includes: randomly selecting a predetermined number of candidate collection orders as the first collection orders to be processed; in each th From a set of pending orders, move at least one order into the order pool; use the first algorithm to process all orders in the order pool.

In some embodiments, after the first optimization process, a second optimization process is performed on the plurality of candidate set orders; wherein the second optimization process includes: generating random numbers at a preset frequency; if the If the random number is greater than the preset disturbance value, check whether there is an independent seed order, where the independent seed order is a seed order that does not form a candidate set order with other orders; if there is an independent seed order, move the independent seed order into all the order pool; randomly select a predetermined number of candidate collection orders that meet preset conditions as second pending collection orders; move all orders in each second pending collection order into the order pool; use the second algorithm Process all orders in the order pool.

In some embodiments, the preset condition includes: the total number of orders in the second set of pending orders is less than a preset quantity threshold.

According to a second aspect of an embodiment of the present disclosure, a device for optimizing collection orders is provided, including: a first processing module configured to generate multiple candidate collection orders using all orders in the order pool in a preset cycle; second A processing module configured to move all orders in the i-th candidate set order into the order pool if the i-th candidate set order among the plurality of candidate set orders does not meet the preset constraint conditions. , 1≤i≤N, N is the total number of candidate set orders.

According to a third aspect of an embodiment of the present disclosure, there is provided a set order optimization processing device, including: a memory configured to store instructions; a processor coupled to the memory, and the processor is configured to execute the instructions based on the instructions stored in the memory to implement the above The method described in any embodiment.

According to a fourth aspect of an embodiment of the present disclosure, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and when the instructions are executed by a processor, the method as described in any of the above embodiments is implemented.

Other features and advantages of the present disclosure will become apparent from the following detailed description of exemplary embodiments of the present disclosure with reference to the accompanying drawings.

Description of drawings

In order to explain the embodiments of the present disclosure or the technical solutions in the prior art more clearly, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings in the following description are only These are some embodiments of the present disclosure. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without exerting any creative effort.

Figure 1 is a schematic flow chart of a collection order optimization processing method according to an embodiment of the present disclosure;

Figures 2A and 2B are schematic diagrams of collective orders according to some embodiments of the present disclosure;

Figures 3A and 3B are schematic diagrams of collective orders according to other embodiments of the present disclosure;

Figure 4 is a schematic structural diagram of a collection order optimization processing device according to an embodiment of the present disclosure;

Figure 5 is a schematic structural diagram of a collection order optimization processing device according to another embodiment of the present disclosure;

Figure 6 is a schematic diagram of a collection order according to another embodiment of the present disclosure.

Detailed ways

The technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only some of the embodiments of the present disclosure, rather than all of the embodiments. The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the disclosure, its application or uses. Based on the embodiments in this disclosure, all other embodiments obtained by those of ordinary skill in the art without making creative efforts fall within the scope of protection of this disclosure.

The relative arrangement of components and steps, numerical expressions, and numerical values set forth in these examples do not limit the scope of the disclosure unless otherwise specifically stated.

At the same time, it should be understood that, for convenience of description, the dimensions of various parts shown in the drawings are not drawn according to actual proportional relationships.

Techniques, methods and devices known to those of ordinary skill in the relevant art may not be discussed in detail, but where appropriate, such techniques, methods and devices should be considered part of the authorized specification.

In all examples shown and discussed herein, any specific values are to be construed as illustrative only and not as limiting. Accordingly, other examples of the exemplary embodiments may have different values.

It should be noted that similar reference numerals and letters refer to similar items in the following figures, so that once an item is defined in one figure, it does not need further discussion in subsequent figures.

The inventor noticed that in the related technology, the two processes of collection order generation and distribution are independent of each other, so the generated collection order cannot achieve global optimization.

Accordingly, the present disclosure provides a method for optimizing collection orders, which can achieve global optimization of collection orders.

Figure 1 is a schematic flowchart of a collection order optimization processing method according to an embodiment of the present disclosure. In some embodiments, the following collective order optimization processing method is executed by the collective order optimization processing device.

In step 101, multiple candidate set orders are generated using all orders in the order pool in a preset period.

For example, the preset period is 1 minute.

In some embodiments, the following first algorithm or second algorithm may be used to process all orders in the order pool to generate multiple candidate set orders.

The first algorithm can also be called the greedy algorithm. The specific content is as follows:

1) Randomly select an order from the order pool.

2) When there are already candidate set orders, if a matching position can be found in the existing candidate set orders using the preset strategy, a randomly selected order will be inserted into the matching position.

For example, the collective order generation problem can be converted into a VRP (Vehicle Routing Problem, vehicle route planning problem) for processing, so as to minimize the delivery distance of each courier.

For example, the order pool includes 3 orders, and the corresponding order numbers are {11, 24, 33}.

There are currently two collection orders, specifically: collection order one: 1-3-14-26, collection order two: 5-2-7.

Randomly extract an order from the order pool, that is, order 11, and then determine whether there is a position in set order one and set order two that satisfies the constraints of VRP and minimizes the increase in the VRP objective function value. If such a position exists, Then insert order 11 at this position.

It should be noted that since VRP is not the inventive point of the present disclosure, it will not be described here.

3) If a matching position cannot be found in the existing candidate collection order, or there is currently no candidate collection order, the randomly selected order will be inserted into the new candidate collection order.

For example, in the above embodiment, if it is determined that there is no position in set order one and set order two that satisfies the constraints of VRP and minimizes the increase in the VRP objective function value, then order 11 is inserted into a new set order.

4) Repeatedly randomly selecting an order from the order pool until there is no order in the order pool.

The second algorithm can also be called the seed order adsorption algorithm. The specific content is as follows:

1) According to the preset rules, the orders in the order pool are divided into seed orders and non-seed orders.

In some embodiments, the preset rules include: in the order pool, orders whose difference between the issuance time and the current time is less than the time difference threshold are regarded as seed orders, and orders in the order pool other than seed orders are regarded as non-seed orders.

That is, the order that is about to arrive at the release time is used as a seed order.

2) Randomly select a seed order from multiple seed orders as the base order.

3) Use the preset strategy to select seed orders and non-seed orders that can be placed in the same set order with the basic order to generate a set order.

In some embodiments, on the basis of the basic order, other orders are adsorbed with a strategy that minimizes the increase in VRP objective function value to generate a collective order.

4) Repeatedly randomly selecting a seed order from multiple seed orders as the base order until multiple seed orders are processed.

5) After multiple seed orders are processed, if there are remaining orders in the order pool, use the above-mentioned first algorithm to process all remaining orders in the order pool.

In some embodiments, after using the first algorithm or the second algorithm to generate multiple candidate collective orders, a first optimization process is performed on the multiple candidate collective orders to obtain optimized collective orders.

For example, the first optimization process includes: first randomly selecting a predetermined number of candidate collection orders as the first collection orders to be processed, and then moving at least one order into the order pool in each first collection order to be processed, and then using the above The first algorithm processes all orders in the order pool.

It should be noted that in order to ensure the stability of optimization processing, if there are only two orders in a certain set order, the set order will be selected.

In the above-mentioned first optimization process, by reorganizing the orders included in the collective order, an optimized collective order can be obtained.

As shown in Figure 2A, there are currently 3 collection orders. The set order 21 includes 5 orders, the set order 22 includes 2 orders, and the set order 23 includes 3 orders.

As shown in FIG. 2B , through the above-described first optimization process, the orders included in the

collective orders

21 and 22 are reorganized. In this case, the set order 21 includes 4 orders, the set order 22 includes 3 orders, and the set order 23 remains unchanged.

In some embodiments, after the first optimization process, a second optimization process may also be performed on multiple candidate collective orders to perform random optimization on the collective orders.

For example, the second optimization process includes: generating random numbers at a preset frequency, and if the random numbers are greater than the preset disturbance value, checking whether there is an independent seed order, where an independent seed order is a seed order that does not form a candidate set order with other orders.

If there is an independent seed order, the independent seed order will be moved into the order pool, and a predetermined number of candidate collective orders that meet the preset conditions will be randomly selected as the second pending collective order.

For example, the preset conditions include: the total number of orders in the second pending collection order is less than the preset quantity threshold. That is, the collection order with a smaller order quantity is selected as the second pending collection order.

Next, all orders in each second pending collection order are moved into the order pool. Finally, the second algorithm is used to process all orders in the order pool.

As shown in Figure 3A, there are currently 3 collection orders. The collective order 31 includes 5 orders, the collective order 32 includes 2 orders, and the collective order 33 includes 3 orders. In addition, there is a seed order 30 that is not combined with other orders to form a collective order.

As shown in FIG. 3B , through the second optimization process, the seed order 30 forms a collective order 33 with an order originally included in the collective order 31 and an order originally included in the collective order 32 . This effectively improves the overall order collection rate.

It should be noted that in Figure 3B, through the second optimization process, one order in the original set order 32 does not form a set order with other orders. Since the order is a non-seed order, the order can be returned to the order pool to participate in the next collective order generation, thereby increasing the probability of the overall order combination being successful.

Return to Figure 1. In step 102, when the i-th candidate set order among the multiple candidate set orders does not meet the preset constraint conditions, all orders in the i-th candidate set order are moved into the order pool, 1≤i≤N, N is the total number of candidate collection orders.

It should be noted that during the optimization process, in addition to paying attention to whether each courier's delivery distance is the shortest, it is also necessary to consider the order collection rate of the store throughout the day. The order collection rate directly affects the delivery efficiency of the courier.

Since store order volume is not fixed, it will fluctuate over time. In order to optimize the store's order collection rate, constraints need to be set on the objective function.

In some embodiments, the preset constraints include: the earliest production time of the i-th candidate set order is greater than the sum of the current time and the preset parameters, where the earliest production time is the production time of each order in the i-th candidate set order. The earliest time in; and the total number of orders in the i-th candidate set order is less than the preset upper limit.

In addition, it should be noted that due to the particularity of catering orders, catering orders need to be delivered earlier, so further constraints need to be set on the objective function.

In some embodiments, the preset constraints also include: when the i-th candidate set order is divided into a catering order set and a non-catering order set, the delivery time of any catering order in the catering order set is earlier than that of the non-catering order set. The delivery time of any non-catering order in the catering order collection.

In some embodiments, before moving all orders in the i-th candidate set order into the order pool, it is determined whether the difference between the latest issuance time of the i-th candidate set order and the current time is greater than a preset time threshold. When the difference is greater than the preset time threshold, all orders in the i-th candidate set order are moved into the order pool.

That is to say, if the i-th candidate set order is not globally optimal, but the latest release time of the i-th candidate set order has not yet reached, in this case, the i-th candidate set order will be All orders here are moved into the order pool so that these orders can participate in the next collective order optimization process.

In some implementations, when the difference is not greater than a preset time threshold, the i-th candidate set order is issued.

That is to say, if the i-th candidate set order is not globally optimal, but the latest release time of the i-th candidate set order is coming, in this case, the i-th candidate set order will be Release processing is performed so that the processing of the i-th candidate collection order can be completed on time.

In some embodiments, when the i-th candidate set order satisfies the preset constraint conditions, the i-th candidate set order is issued.

That is, if the i-th candidate set order is globally optimal, there is no need to process the i-th candidate set order, and the i-th candidate set order is directly issued for processing.

In the collection order optimization processing method provided by the above embodiments of the present disclosure, not only the delivery distance of each courier is the shortest, but also the order collection rate of the store throughout the day, so that the generated collection order is globally optimal.

Figure 4 is a schematic structural diagram of a collection order optimization processing device according to an embodiment of the present disclosure. As shown in FIG. 4 , the assembly order optimization processing device includes a first processing module 41 and a second processing module 42 .

The first processing module 41 is configured to generate a plurality of candidate set orders using all orders in the order pool in a preset cycle.

For example, the preset period is 1 minute.

In some embodiments, the above-mentioned first algorithm or second algorithm may be used to process all orders in the order pool to generate multiple candidate set orders.

The second processing module 42 is configured to move all orders in the i-th candidate set order into the order pool when the i-th candidate set order among the plurality of candidate set orders does not meet the preset constraint conditions, 1≤i ≤N, N is the total number of candidate set orders.

In some embodiments, before moving all orders in the i-th candidate set order into the order pool, the second processing module 42 determines whether the difference between the latest release time of the i-th candidate set order and the current time is greater than the predetermined time. Set time threshold. If the difference is greater than the preset time threshold, the second processing module 42 moves all orders in the i-th candidate set order into the order pool.

That is to say, if the i-th candidate set order is not globally optimal, but the latest issuance time of the i-th candidate set order has not yet arrived, in this case, the second processing module 42 will All orders of the i-th candidate collection order are moved into the order pool so that these orders can participate in the next collection order optimization process.

In some implementations, when the difference is not greater than the preset time threshold, the second processing module 42 issues the i-th candidate set order.

That is to say, if the i-th candidate set order is not globally optimal, but the latest release time of the i-th candidate set order is coming, in this case, the second processing module 42 will The i candidate collection order is issued for processing so that the processing of the i-th candidate collection order can be completed on time.

In some embodiments, when the i-th candidate collection order satisfies the preset constraint conditions, the second processing module 42 issues the i-th candidate collection order.

In the collection order optimization processing device provided by the above embodiments of the present disclosure, not only the delivery distance of each courier is the shortest, but also the order collection rate of the store throughout the day, so that the generated collection order is globally optimal.

FIG. 5 is a schematic structural diagram of a collection order optimization processing device according to another embodiment of the present disclosure. As shown in FIG. 5 , the assembly order optimization processing device includes a memory 51 and a processor 52 .

The memory 51 is used to store instructions, and the processor 52 is coupled to the memory 51 . The processor 52 is configured to execute the method involved in any embodiment in FIG. 1 based on the instructions stored in the memory.

As shown in Figure 5, the collective order optimization processing device also includes a communication interface 53 for information interaction with other devices. At the same time, the collective order optimization processing device also includes a bus 54, through which the processor 52, the communication interface 53, and the memory 51 complete communication with each other.

The memory 51 may include high-speed RAM memory, or may also include non-volatile memory (non-volatile memory), such as at least one disk memory. The memory 51 may also be a memory array. The memory 51 may also be divided into blocks, and the blocks may be combined into virtual volumes according to certain rules.

Additionally, processor 52 may be a central processing unit (CPU), or may be an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement embodiments of the present disclosure.

The present disclosure also relates to a computer-readable storage medium, wherein the computer-readable storage medium stores computer instructions. When the instructions are executed by a processor, the method related to any embodiment in Figure 1 is implemented.

By implementing the above embodiments of the present disclosure, attention is not only paid to whether the delivery distance of each courier is the shortest, but also to the order collection rate of the store throughout the day, thereby making the generated collection orders globally optimal.

As shown in Table 1, the traditional collective order generation method is used in the first time period (for example, November 29, 2021-December 5, 2021), and in the second time period (for example, December 13, 2021 Use the solution provided by this disclosure within the period from 19th to December 19th, 2021. It can be seen from Table 1 that by using the solution provided by the present disclosure, various indicators have been significantly improved.

Table 1

For example, there are 15 orders in the order pool. By adopting the solution adopted in this disclosure, 3 optimal collective orders are obtained. As shown in Figure 6, the collective order in the upper left is 6-9-12-5-13. The collective order on the upper right is 8-4-2-3-15, and the collective order on the lower right is 7-1-11-14-10. In Figure 6, the number marked between two orders represents the travel time of the delivery person from the delivery point of the previous order to the delivery point of the next order. On this basis, the delivery person can complete the order delivery efficiently.

In some embodiments, the functional unit modules described above can be implemented as a general-purpose processor, a programmable logic controller (PLC), a digital signal processor (PLC) for performing the functions described in this disclosure. Digital Signal Processor (DSP for short), Application Specific Integrated Circuit (ASIC for short), Field-Programmable Gate Array (FPGA for short) or other programmable logic devices, discrete gates or transistors logic devices, discrete hardware components, or any appropriate combination thereof.

Those of ordinary skill in the art can understand that all or part of the steps to implement the above embodiments can be completed by hardware, or can be completed by instructing relevant hardware through a program. The program can be stored in a computer-readable storage medium. The above-mentioned The storage media mentioned can be read-only memory, magnetic disks or optical disks, etc.

The description of the present disclosure has been presented for the purposes of illustration and description, and is not intended to be exhaustive or to limit the disclosure to the form disclosed. Many modifications and variations will be apparent to those of ordinary skill in the art. The embodiment was chosen and described in order to best explain the principles of the disclosure and the practical application, and to enable others of ordinary skill in the art to understand the disclosure and design various embodiments with various modifications as are suited to the particular use contemplated.

Claims

A method for optimizing collection order processing, including:

In a preset period, use all orders in the order pool to generate multiple candidate set orders;

When the i-th candidate set order among the plurality of candidate set orders does not meet the preset constraint conditions, all orders in the i-th candidate set order are moved into the order pool, 1≤i≤N , N is the total number of candidate set orders.
The method of claim 1, further comprising:

Before moving all orders in the i-th candidate set order into the order pool, determine whether the difference between the latest issuance time of the i-th candidate set order and the current time is greater than a preset time threshold;

If the difference is greater than the preset time threshold, all orders in the i-th candidate set order are moved into the order pool.
The method of claim 2, further comprising:

If the difference is not greater than the preset time threshold, the i-th candidate set order is issued.
The method of claim 1, further comprising:

When the i-th candidate collection order satisfies the preset constraint conditions, the i-th candidate collection order is issued.
The method of claim 1, wherein,

The preset constraints include:

The earliest production time of the i-th candidate set order is greater than the sum of the current time and preset parameters, wherein the earliest production time is the earliest time among the production times of each order in the i-th candidate set order; and

The total number of orders in the i-th candidate set order is less than the preset upper limit.
The method of claim 5, wherein,

The preset constraints also include:

When the i-th candidate set order is divided into a catering order set and a non-catering order set, the delivery time of any catering order in the catering order set is earlier than that of any catering order set in the non-catering order set Delivery times for non-catering orders.
The method according to any one of claims 1-6, wherein generating multiple candidate set orders using all orders in the order pool includes:

Use the first algorithm to process all orders in the order pool to generate multiple candidate set orders;

Wherein, the first algorithm includes:

Randomly select an order from said order pool;

In the case where there are already candidate set orders, if a matching position can be found in the existing candidate set orders using a preset strategy, a randomly selected order will be inserted into the matching position;

If a matching position cannot be found in the existing candidate collection order, or there is currently no candidate collection order, the randomly selected order will be inserted into the new candidate collection order;

Repeatedly selecting an order at random from the order pool until there are no orders left in the order pool.
The method according to claim 7, wherein generating multiple candidate set orders using all orders in the order pool includes:

Using a second algorithm to process all orders in the target set to generate multiple candidate set orders;

Wherein, the second algorithm includes:

Divide the orders in the order pool into seed orders and non-seed orders according to preset rules;

Randomly select one seed order from the plurality of seed orders as the base order;

Use the preset strategy to select seed orders and non-seed orders that can be placed in the same collective order as the basic order to generate a collective order;

Repeatedly selecting one seed order randomly from the plurality of seed orders as the base order until the plurality of seed orders are processed.
The method of claim 8, further comprising:

The preset rules include: in the order pool, the order whose difference between the issuance time and the current time is less than the time difference threshold is regarded as a seed order, and the orders in the order pool other than the seed order are regarded as non-seed orders. Order.
The method of claim 8, further comprising:

After the plurality of seed orders are processed, if there are remaining orders in the order pool, the first algorithm is used to process all remaining orders in the order pool.
The method of claim 10, further comprising:

Perform first optimization processing on the plurality of candidate set orders;

Wherein, the first optimization process includes:

Randomly select a predetermined number of candidate collection orders as the first pending collection orders;

In each first pending collection order, move at least one order into the order pool;

The first algorithm is used to process all orders in the order pool.
The method of claim 11, further comprising:

After the first optimization process, perform a second optimization process on the plurality of candidate collection orders;

Wherein, the second optimization process includes:

Generate random numbers at a preset frequency;

If the random number is greater than the preset disturbance value, check whether there is an independent seed order, where the independent seed order is a seed order that does not form a candidate set order with other orders;

If there is an independent seed order, move the independent seed order into the order pool;

Randomly select a predetermined number of candidate collection orders that meet the preset conditions as the second pending collection orders;

Move all orders in each second pending collection order into the order pool;

Use the second algorithm to process all orders in the order pool.
The method of claim 12, wherein:

The preset conditions include: the total number of orders in the second set of pending orders is less than a preset quantity threshold.
A device for optimizing and processing collective orders, including:

The first processing module is configured to use all orders in the order pool to generate multiple candidate set orders in a preset cycle;

The second processing module is configured to move all orders in the i-th candidate set order into the Order pool, 1≤i≤N, N is the total number of candidate set orders.
A device for optimizing and processing collective orders, including:

memory configured to store instructions;

A processor, coupled to the memory, configured to execute the method according to any one of claims 1-13 based on instructions stored in the memory.
A computer-readable storage medium, wherein the computer-readable storage medium stores computer instructions, and when the instructions are executed by a processor, the method according to any one of claims 1-13 is implemented.