Order allocation method and device for multiple warehousing workstations and storage medium

Abstract

The invention discloses an order allocation method and device for multiple warehousing workstations and a storage medium, and relates to the technical field of warehousing logistics. The method comprises the steps of obtaining to-be-allocated order information of a plurality of to-be-allocated orders, existing order information of existing orders of a plurality of to-be-allocated workstations and historical cargo types of historical sorting orders of the workstations; through a multi-target genetic algorithm, according to the to-be-allocated order information, the existing order information and historical cargo types, determining a target allocation relationship between the plurality of to-be-allocated workstations and the plurality of to-be-allocated orders; wherein the optimization target of the multi-target genetic algorithm comprises the minimization of the cargo quantity discrete degree value of the plurality of to-be-distributed workstations and the maximization of the correlation degree mean value of the cargo type correlation degrees corresponding to the plurality of to-be-distributed workstations. According to the method, the working efficiency of the multiple to-be-distributed workstations can be improved, and the possibility of the cargo stacking phenomenon is reduced.

Description

Technical Field

[0001] The present application relates to the technical field of warehousing and logistics, and in particular to an order distribution method and device for multiple warehousing workstations and a machine-readable storage medium thereof. Background Art

[0002] In the intelligent warehousing logistics execution system of smart warehousing, orders are sent from the order pool to the workstation, which is used to process orders and send the processed orders to the warehouse shelves or ship them to customers. In the existing workstation order allocation method, the orders in the order pool are arranged in order, and some orders in the front will be intercepted and assigned to a single workstation, or some orders will be randomly selected and assigned to a single workstation. When it is necessary to consider allocating orders to multiple workstations, the technical means often used is serial allocation, that is, after allocating orders to a single workstation, the order is allocated to the next workstation. The above-mentioned order allocation method, in the case of multiple workstations, often causes the order accumulation of the workstation, resulting in low order processing efficiency. Summary of the invention

[0003] The purpose of the embodiments of the present application is to provide an order distribution method, device and machine-readable storage medium for multiple workstations in a warehouse, so as to solve the problem of low efficiency of multi-workstation order processing in the prior art.

[0004] In order to achieve the above-mentioned object, the first aspect of the present application provides an order allocation method for multiple warehouse workstations, comprising: Obtaining order information of multiple orders to be allocated, existing order information of multiple workstations to be allocated, and historical goods types of historical picking orders of the workstations, wherein the order information to be allocated includes the order goods type and the order goods quantity, and the existing order information includes the existing goods type and the existing goods quantity; Through a multi-objective genetic algorithm, according to the information of orders to be allocated, existing order information and historical cargo types, the target allocation relationship between multiple workstations to be allocated and multiple orders to be allocated is determined; wherein, the optimization objectives of the multi-objective genetic algorithm include: minimizing the discrete degree values ​​of the cargo quantities of multiple workstations to be allocated, and maximizing the mean value of the correlation degrees of cargo types corresponding to the multiple workstations to be allocated, the discrete degree values ​​of the cargo quantities are determined according to the order cargo quantities and the existing cargo quantities, and the cargo type correlation degrees are determined according to the historical cargo types, order cargo types and existing cargo types.

[0005] In some embodiments of the present application, a multi-objective genetic algorithm is used to determine the allocation relationship between multiple workstations to be allocated and multiple orders to be allocated based on information about orders to be allocated, existing order information, and historical types of goods, including: establishing a population with multiple individuals based on multiple orders to be allocated and multiple workstations to be allocated; wherein each individual is used to represent an allocation relationship between multiple orders to be allocated and multiple workstations to be allocated; determining a discrete degree value of the quantity of goods corresponding to each individual based on the quantity of ordered goods and the quantity of existing goods corresponding to each individual; determining a mean value of the degree of association corresponding to each individual based on the historical types of goods, order types of goods, and existing types of goods corresponding to each individual; based on the optimization objective, performing a population update operation on the population based on the discrete degree value of the quantity of goods corresponding to each individual in the population and the mean value of the degree of association until a preset convergence condition is met to obtain a final population; and taking any individual in the final population as the target allocation relationship.

[0006] In some embodiments of the present application, the discrete degree value includes a standard deviation. The discrete degree value of the quantity of goods corresponding to each individual is determined based on the quantity of ordered goods and the quantity of existing goods corresponding to each individual, including: determining the mean quantity of existing goods of multiple workstations to be allocated based on the quantity of existing goods of each of the multiple workstations to be allocated; and determining the standard deviation corresponding to the individual when allocating multiple orders to be allocated to multiple workstations to be allocated based on the individual.

[0007] In some embodiments of the present application, determining the mean value of the association degree corresponding to each individual according to the historical goods types, ordered goods types and existing goods types corresponding to each individual includes: for each workstation to be assigned in each individual, determining the union of the existing goods types and ordered goods types corresponding to each workstation to be assigned in each individual, so as to obtain a set of goods types corresponding to each workstation to be assigned; determining the number of frequent goods combination subsets in each set of goods types; wherein the frequent goods combination subsets are the goods combination subsets in the set of goods types whose number of appearances in the historical picking orders is greater than a preset number threshold; determining the association degree of the goods types corresponding to the multiple workstations to be assigned in each individual according to the number of frequent goods combination subsets in each set of goods types in each individual; determining the mean value of the association degree of each individual according to the association degree of the goods types corresponding to the multiple workstations to be assigned in each individual.

[0008] In some embodiments of the present application, based on the optimization objective, a population update operation is performed on the population according to the discrete degree value and the correlation mean of the quantity of goods corresponding to each individual in the population until a preset convergence condition is met to obtain a final population, including: non-dominated sorting of the individuals in the population according to the optimization objective; selecting a target number of individuals at the front of the non-dominated sort as parents; performing crossover and mutation operations on the parents to obtain a new population; if the preset convergence condition is not met, non-dominated sorting of the individuals in the new population according to the optimization objective until the preset convergence condition is met to obtain the final population.

[0009] In some embodiments of the present application, before obtaining the to-be-allocated order information of multiple to-be-allocated orders, the method also includes: obtaining the cut-off times corresponding to multiple existing orders and the preset priorities of the multiple existing orders; determining the comprehensive priority of the multiple existing orders based on the cut-off time and the preset priority; wherein, the existing orders with earlier cut-off times have higher comprehensive priorities; and obtaining multiple to-be-allocated orders based on the comprehensive priority and the total remaining amount of allocable orders of multiple to-be-allocated workstations.

[0010] In some embodiments of the present application, multiple orders to be allocated are obtained according to the comprehensive priority and the total balance of allocatable orders of multiple workstations to be allocated, including: according to the comprehensive priority, all existing orders within the comprehensive priority are intercepted level by level from the highest comprehensive priority; in the case of intercepting all existing orders of the comprehensive priority, it is determined whether the total number of intercepted orders is greater than or equal to the total balance of allocatable orders; in the case where the total number of intercepted orders is greater than or equal to the total balance of allocatable orders, intercepting existing orders is stopped, and the multiple existing orders that have been intercepted are used as multiple orders to be allocated; in the case where the total number of intercepted orders is less than the total balance of allocatable orders, all existing orders of the next comprehensive priority are continued to be intercepted.

[0011] In some embodiments of the present application, a multi-objective genetic algorithm is used to determine the allocation relationship between multiple workstations to be allocated and multiple orders to be allocated according to the order information to be allocated, the existing order information and the historical goods types, including: establishing a population with multiple individuals according to the multiple orders to be allocated and the multiple workstations to be allocated; wherein each individual is used to represent an allocation relationship between multiple orders to be allocated and multiple workstations to be allocated; each individual has constraints: each order to be allocated is allocated to a workstation to be allocated; the number of orders to be allocated allocated to each workstation to be allocated does not exceed the remaining number of allocable orders of the workstation to be allocated; the lowest comprehensive priority level The number of pending orders that need to be allocated is the difference between the total remaining amount of allocable orders and the total number of pending orders of other comprehensive priorities; the discrete degree value of the quantity of goods corresponding to each individual is determined according to the quantity of ordered goods and the quantity of existing goods corresponding to each individual; the mean value of the correlation degree corresponding to each individual is determined according to the historical goods types, order goods types and existing goods types corresponding to each individual; based on the optimization goal, according to the discrete degree value and the mean value of the correlation degree corresponding to each individual in the population, the population update operation is performed on the population until the preset convergence condition is met to obtain the final population; any individual in the final population is used as the target allocation relationship.

[0012] In some embodiments of the present application, when a preset convergence condition is not met, individuals in a new population are non-dominated sorted according to an optimization objective until the preset convergence condition is met, including: when the number of iterations of the population does not reach a preset iteration threshold, according to the optimization objective, individuals in the new population are non-dominated sorted until the number of iterations of the population reaches a preset iteration threshold; or, when the amplitude of change in the discrete degree and / or the mean of the association degree is greater than or equal to a preset amplitude, according to the optimization objective, individuals in the new population are non-dominated sorted until the amplitude of change in the discrete degree and / or the mean of the association degree is less than a preset amplitude.

[0013] A second aspect of the present application provides an order allocation device for multiple warehousing workstations, comprising: a memory configured to store instructions; a processor configured to call instructions from the memory and to implement the order allocation method for multiple warehousing workstations provided in accordance with any one of the above embodiments when executing the instructions.

[0014] A third aspect of the present application provides a machine-readable storage medium having instructions stored thereon, the instructions being used to enable a machine to execute the order allocation method for warehousing multiple workstations provided in any one of the above-mentioned embodiments.

[0015] The order allocation method for multiple warehousing workstations provided in the embodiment of the present application sets two optimization goals: minimizing the discrete degree value of the quantity of goods at multiple workstations to be allocated, and maximizing the mean value of the correlation between the types of goods corresponding to the multiple workstations to be allocated, and cooperates with a multi-objective genetic algorithm to continuously iteratively optimize the allocation relationship between multiple workstations to be allocated and multiple orders to be allocated, so as to obtain a target allocation relationship between multiple workstations to be allocated and multiple orders to be allocated with a smaller discrete degree value and a larger mean value of the correlation degree; according to the target allocation relationship, multiple orders to be allocated are allocated to multiple workstations to be allocated, so that the quantity of goods between the multiple workstations to be allocated tends to be averaged, and the correlation degree of the types of goods at each workstation to be allocated is at a reasonable level, and the mean value of the correlation degree is maximized; thereby, the work efficiency of the multiple workstations to be allocated can be improved, and the possibility of goods accumulation can be reduced.

[0016] Other features and advantages of the embodiments of the present application will be described in detail in the subsequent specific implementation section. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the following specific implementations, they are used to explain the embodiments of the present application, but do not constitute a limitation on the embodiments of the present application. In the accompanying drawings: Figure 1 A schematic diagram of a flow chart of an order allocation method for multiple warehouse workstations according to an embodiment of the present application is shown; Figure 2 Schematically shows Figure 1 A schematic diagram of a flow chart of step S140; Figure 3 Schematically shows Figure 2 A schematic diagram of a flow chart of step S146; Figure 4 Schematically shows Figure 3 A flowchart diagram of step S1468 in FIG. DETAILED DESCRIPTION

[0018] In order to make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. It should be understood that the specific implementation methods described herein are only used to illustrate and explain the embodiments of the present application, and are not used to limit the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0019] It should be noted that if the embodiments of the present application involve directional indications (such as up, down, left, right, front, back...), such directional indications are only used to explain the relative position relationship, movement status, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication will also change accordingly.

[0020] In addition, if there are descriptions involving "first", "second", etc. in the embodiments of the present application, the descriptions of "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or suggesting their relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the technical solutions between the various embodiments can be combined with each other, but they must be based on the ability of ordinary technicians in the field to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such combination of technical solutions does not exist and is not within the scope of protection required by this application.

[0021] In the existing allocation scheme for allocating multiple orders to workstations in a warehousing environment, multiple orders are only allocated to multiple workstations one by one. Since the quantity of goods in each order is different, and the number of existing orders and the quantity of goods in each workstation are also different. Therefore, the above existing allocation scheme may cause an imbalance in the number of goods that multiple workstations actually need to process, and the number of goods that some workstations need to process is too large, while the number of goods that other workstations need to process cannot fully utilize the goods processing capacity of the workstation. The various goods in the workstation will be picked out of the workstation with a specific combination of goods types due to the need for goods to be put on the shelves of the warehouse or the need for outbound picking. Therefore, if the types of goods in the workstation are incomplete or too many, specific types of goods will pile up. Based on the above analysis, it can be seen that the imbalance of the number of goods and the unreasonable distribution of the types of goods will cause the overall inefficiency of the multi-workstation processing of the goods in the order. Based on the above observation and analysis of the prior art, the inventor proposes an order allocation method for warehousing multiple workstations that takes into account the balance of the number of goods and the reasonable distribution of the types of goods.

[0022] The order allocation method for multiple workstations in a warehousing environment provided in the embodiment of the present application can be used in two scenarios in the field of warehousing and logistics: warehousing and shelving, and outbound picking. It can be used as an allocation method for allocating orders to workstations in the WES (Warehouse Execution System) management system in smart warehousing and is executed by a processor.

[0023] Figure 1 The following schematically shows a flow chart of a method for allocating orders to multiple warehouse workstations according to an embodiment of the present application. Figure 1As shown, the order allocation method for warehousing multiple workstations provided in the embodiment of the present application may include the following steps: S120, obtaining to-be-allocated order information of multiple to-be-allocated orders, existing order information of multiple to-be-allocated workstations' existing orders, and historical goods types of historical picking orders of the workstations, wherein the to-be-allocated order information includes order goods types and order goods quantities, and the existing order information includes existing goods types and existing goods quantities; S140. Determine the target allocation relationship between multiple workstations to be allocated and multiple orders to be allocated based on the information of orders to be allocated, existing order information and historical cargo types through a multi-objective genetic algorithm; wherein the optimization objectives of the multi-objective genetic algorithm include: minimizing the discrete degree values ​​of the cargo quantities of multiple workstations to be allocated, and maximizing the mean value of the correlation degrees of cargo types corresponding to the multiple workstations to be allocated, the discrete degree values ​​of the cargo quantities are determined based on the cargo quantities in the order and the cargo quantities that are already available, and the cargo type correlation degrees are determined based on the historical cargo types, the cargo types in the order and the existing cargo types.

[0024] It can be understood that the workstation historical picking order refers to the historical order for the goods to be put on the shelf after the shelf workstation picks the goods, or refers to the historical order for the goods to be sent to the customer after the picking workstation picks the goods. The historical picking order can come from the workstation in the same warehouse or from the workstation in different warehouses. The workstation historical picking order records the combination of historical goods types of the historical picking orders. The goods type correlation corresponding to multiple workstations to be assigned respectively means that for each workstation to be assigned, the types of goods to be processed of its existing orders and the types of goods of the orders to be assigned are put together to obtain a set of goods types, and in the set of goods types, the number of sets of various goods type combination subsets with a frequency higher than a certain value in the historical picking orders. Therefore, each workstation to be assigned can obtain a set of various goods type combination subsets with a frequency higher than a certain value as the goods type correlation between the workstation to be assigned and the order to be assigned. The average of the goods type correlations of multiple workstations to be assigned is the correlation mean. The parameter representing the discrete degree value of the quantity of goods of multiple workstations to be allocated may be, for example, the range, the interquartile range, the standard deviation, the variance, the coefficient of variation, etc.

[0025] Specifically, in step S140, the multi-objective genetic algorithm determines the allocation relationship between the multiple workstations to be allocated and the multiple orders to be allocated according to the information of the orders to be allocated and the information of the workstations to be allocated, and iteratively optimizes the allocation relationship between the multiple workstations to be allocated and the multiple orders to be allocated according to the optimization target, until a target allocation relationship that meets the multi-objective genetic algorithm is obtained. The multiple orders to be allocated are then allocated to the multiple workstations to be allocated according to the target allocation relationship.

[0026] The order allocation method for warehousing multiple workstations provided in the embodiment of the present application sets two optimization goals: minimizing the discrete degree value of the quantity of goods in multiple workstations to be allocated, and maximizing the mean value of the correlation degree of the goods types corresponding to the multiple workstations to be allocated, and cooperates with a multi-objective genetic algorithm to continuously iterate and optimize the allocation relationship between multiple workstations to be allocated and multiple orders to be allocated, so as to obtain a target allocation relationship between multiple workstations to be allocated and multiple orders to be allocated with a smaller discrete degree value and a larger mean value of the correlation degree. According to the target allocation relationship, multiple orders to be allocated are allocated to multiple workstations to be allocated, so that the quantity of goods between the multiple workstations to be allocated tends to be averaged, and the correlation degree of the goods types of each workstation to be allocated is at a reasonable level, and the mean value of the correlation degree is maximized. Thereby, the work efficiency of multiple workstations to be allocated is improved, and the possibility of goods accumulation is reduced.

[0027] In some embodiments of the present application, see Figure 2 , step S140 may include: S142, establishing a population having a plurality of individuals according to the plurality of orders to be allocated and the plurality of workstations to be allocated, wherein each individual is used to represent an allocation relationship between the plurality of orders to be allocated and the plurality of workstations to be allocated; S144, determining the discrete degree value of the quantity of goods corresponding to each individual according to the quantity of ordered goods and the quantity of existing goods corresponding to each individual; S146, determining the average value of the correlation degree corresponding to each individual according to the historical goods types, ordered goods types and existing goods types corresponding to each individual; S148. Based on the optimization goal, according to the discrete degree value and the mean value of the correlation degree of the goods quantity corresponding to each individual in the population, the population update operation is performed on the population until the preset convergence condition is met to obtain the final population; S149. Take any individual in the final population as the target allocation relationship.

[0028] It can be understood that the population in step S142 is determined by a multi-objective genetic algorithm based on the number of multiple workstations to be allocated and their respective identities, combined with the number and identities of multiple orders to be allocated. Each individual in the population represents the allocation relationship between the identities of multiple workstations to be allocated and the identities of multiple orders to be allocated.

[0029] As an example, suppose there are three workstations to be assigned, and their identity vectors are and five orders to be assigned, whose identity vectors are , then select any individual, and the identity identifiers of the five orders to be allocated in the individual and the identity identifiers of the three workstations to be allocated have such a distribution relationship as follows: {( ) }.Right now to The five pending orders are allocated to to A workstation to be assigned in.

[0030] Since the number of orders to be allocated and the number of workstations to be allocated are not necessarily equal, and the available order balance of each workstation to be allocated is limited and may be different, in some embodiments of the present application, each individual may have the following constraints: Each to-be-allocated order is allocated to a to-be-allocated workstation; the number of to-be-allocated orders allocated to each to-be-allocated workstation shall not exceed the remaining allocatable orders of the to-be-allocated workstation.

[0031] As an example, under the above constraints, assuming that there are three workstations to be assigned, the identity vectors (or identity strings) of the workstations to be assigned are , which means the workstation to be assigned The available order balance is 1, and the workstation to be allocated The available order balance is 0, and the workstation to be allocated The remaining number of allocable orders is 2. Accordingly, assuming that there are five orders to be allocated, the allocation relationship between the five orders to be allocated and the three workstations to be allocated can be, for example, , that is, the first order to be assigned and the fifth order are assigned to the workstation to be assigned , the second order to be assigned is assigned to the workstation to be assigned , the third and fourth pending orders are not allocated.

[0032] In some embodiments of the present application, the dispersion value is the standard deviation, and step 144 includes: determining the mean of the existing quantity of goods in the multiple workstations to be allocated according to the existing quantity of goods in each of the multiple workstations to be allocated; and determining the standard deviation corresponding to the individuals when allocating the multiple orders to be allocated to the multiple workstations to be allocated according to the individuals.

[0033] When the discrete degree value is the standard deviation, the optimization goal will minimize the standard deviation. After iterations of the multi-objective genetic algorithm, the standard deviation of the individuals in the new population will tend to be minimized compared to the standard deviation of the individuals in the previous generation population. The reduction in standard deviation means that in each individual, after the multiple workstations to be assigned orders are assigned, the overall deviation from the mean quantity of goods is small, so the quantity of goods at each workstation to be assigned is similar and tends to the mean quantity of goods. Therefore, the final target allocation relationship can make the quantity of goods at multiple workstations to be assigned more even after the orders to be assigned are assigned, thereby reducing the possibility of goods accumulation and improving the overall efficiency of multiple workstations to be assigned.

[0034] As an example, when multiple orders to be allocated are allocated to multiple workstations to be allocated, the standard deviation corresponding to each individual is determined by the following formula:

[0035] in, is the standard deviation, is the total number of workstations to be allocated. The quantity of goods available at each workstation to be allocated. is the mean quantity of goods already available.

[0036] In some embodiments of the present application, see Figure 3 , step S146 includes: S1462. For each workstation to be assigned in each individual, determine the union of the existing goods types and the ordered goods types corresponding to each workstation to be assigned in each individual, so as to obtain a set of goods types corresponding to each workstation to be assigned; S1464, determining the number of frequent commodity combination subsets in each commodity type set; wherein the frequent commodity combination subsets are commodity combination subsets in the commodity type set whose appearance ratio in the historical picking orders of the workstation is greater than a preset appearance ratio threshold; S1466, determining the relevance of the cargo types corresponding to the multiple to-be-assigned workstations in each individual according to the number of frequent cargo combination subsets in each cargo type set in each individual; S1468. Determine the average value of the correlation degree of each individual according to the correlation degrees of the types of goods corresponding to the multiple workstations to be assigned in each individual.

[0037] It can be understood that the goods type set refers to, in an individual, the union of the existing goods type set of the workstation to be allocated and the order goods type set of the order to be allocated allocated to the workstation to be allocated according to the allocation relationship established between the workstation to be allocated and the order to be allocated. Therefore, in each individual, each workstation to be allocated corresponds to a goods type set. The preset occurrence ratio threshold can be set manually based on experience, or the preset occurrence ratio threshold can be set and adjusted based on the frequency of occurrence of a combination of certain goods types in multiple historical picking orders. If the ratio of a certain combination of goods types in multiple historical picking orders is higher than the preset occurrence ratio threshold, it means that the combination of goods types appears frequently, otherwise it does not appear frequently. The goods type set includes multiple types of goods, and each type of goods is an element in the goods type set. By selecting elements in the goods type set, a goods combination subset can be obtained. Each goods combination subset corresponds to a goods combination. For example, if the goods type set includes N types of goods, then the number of goods combination subsets of the goods type set is , that is, from N types of goods, from 1 to N types of goods are selected for combination, and there are a total of K combinations. Of course, in another example, the case of selecting only one type of goods can also be excluded.

[0038] Specifically, as an example, after selecting K number of cargo combination subsets, the frequency of the cargo combination expressed by the cargo combination subset in the historical picking order of the workstation is determined according to the cargo combination subset. If the frequency is greater than or equal to the preset occurrence ratio threshold, the cargo combination expressed by the cargo combination subset is judged to be a frequent set. The above steps are performed for each cargo combination subset to determine whether it is a frequent set. Finally, the number of frequent sets in the cargo type set can be obtained. The number of frequent sets is the cargo type association degree corresponding to any to-be-assigned workstation in the individual. Then, step S1468 is executed to sum the cargo type association degrees corresponding to multiple to-be-assigned workstations in a single individual and divide it by the number of multiple to-be-assigned workstations to obtain the mean association degree.

[0039] According to the above technical scheme, it can be determined that the order allocation method for warehousing multiple workstations provided in the embodiment of the present application can determine the correlation between the types of goods of the order to be allocated, the types of goods to be processed of the existing orders of the workstation to be allocated, and the historical types of goods of the historical picking orders of the workstation, in each individual, and thereby obtain the mean value of the individual correlation. The mean value of the correlation reflects the average level of the correlation of multiple workstations to be allocated under the distribution relationship between the workstation to be allocated and the order to be allocated expressed by the individual. Since the maximization of the mean value of the correlation is the optimization goal in this scheme, the mean value of the correlation of the individuals in the final population is the maximization result obtained by the multi-objective genetic algorithm. Thus, after the orders to be allocated are allocated to each workstation to be allocated according to the individuals in the final population, the various goods in the existing orders of the multiple workstations to be allocated are more likely to be picked out of the workstation as a whole according to the needs of a certain picking order during the subsequent work, thereby avoiding the accumulation of specific types of goods in the workstation, and thus improving the picking efficiency of the workstation.

[0040] In some embodiments of the present application, step S148 includes: performing non-dominated sorting on individuals in the population according to the optimization objective; selecting a target number of individuals that are at the front of the non-dominated sorting as parents; performing crossover and mutation operations on the parents to obtain a new population; if a preset convergence condition is not met, performing non-dominated sorting on individuals in the new population according to the optimization objective until the preset convergence condition is met to obtain a final population.

[0041] It can be understood that the non-dominated sorting can be implemented, for example, based on Pareto dominance, and the identified Pareto front can be, for example, the target number of individuals before the non-dominated sorting. The crossover operation can adopt a multi-point crossover method. The newly generated individuals are mutated to increase the diversity of the population. The mutation can be a random change. In the process of generating a new population, the crowding distance calculation can also be performed to calculate the crowding distance of individuals in the new population, and the crowding distance between each individual is kept above a certain distance to maintain the diversity of the population.

[0042] Specifically, as an example, Figure 4 An execution flow of step S148 is shown, including: S1482, obtain the current population; S1483, judging whether the current population meets the convergence condition; If the current population does not meet the convergence conditions, perform the following steps: S1484. According to the optimization goal, perform non-dominated sorting on the individuals in the current population; S1486, select the target number of individuals that are at the front in the non-dominated sort as the parent generation; S1488, performing crossover and mutation operations on the parent generation to obtain a new population; When the current population meets the convergence conditions, perform the following steps: S1489. Output the current population as the final population.

[0043] In some embodiments of the present application, the preset convergence condition may be, for example, whether the number of iterations of the population reaches a threshold, or whether the change amplitude of the discrete degree and / or the mean of the correlation degree is greater than or equal to a preset amplitude, or whether the running time of the multi-objective genetic algorithm reaches a preset time.

[0044] Specifically, when the preset convergence condition is not met, the individuals in the new population are non-dominatedly sorted according to the optimization goal until the preset convergence condition is met to obtain the final population, which may include: when the number of iterations of the population does not reach the preset iteration threshold, according to the optimization goal, the individuals in the new population are non-dominatedly sorted until the number of iterations of the population reaches the preset iteration threshold; or, when the change amplitude of the discrete degree and / or the mean of the association degree is greater than or equal to the preset amplitude, according to the optimization goal, the individuals in the new population are non-dominatedly sorted until the change amplitude of the discrete degree and / or the mean of the association degree is less than the preset amplitude.

[0045] In order to prioritize the allocation of more important orders, the order allocation method for warehouse multi-workstations provided in the embodiment of the present application may further include, before obtaining the to-be-allocated order information of the multiple to-be-allocated orders: Get the cut-off time and preset priority of multiple existing orders respectively; Determine the comprehensive priority of multiple existing orders based on the cut-off time and the preset priority; among them, the comprehensive priority of existing orders with earlier cut-off time is higher; Acquire multiple orders to be assigned according to comprehensive priorities and total remaining quantities of assignable orders of multiple workstations to be assigned.

[0046] It can be understood that the cut-off time refers to the time point or period when the existing orders need to be allocated, and the preset priority can be, for example, a priority set according to the importance of the order. In the case where the preset priorities of multiple existing orders are the same, the existing orders with earlier cut-off times have a higher comprehensive priority and are more likely to be selected as orders to be allocated. In addition, in some embodiments of the present application, among multiple existing orders with the same cut-off time, the existing orders with higher preset priorities have a higher comprehensive priority.

[0047] Specifically, according to the comprehensive priorities and the number of workstations to be allocated, obtaining multiple orders to be allocated may include: selecting the same number of comprehensive priorities as the number of workstations to be allocated, and selecting corresponding existing orders as orders to be allocated according to the selected comprehensive priorities. Of course, a certain number of comprehensive priorities may also be selected according to the number of workstations to be allocated and a preset number interval. For example, if the number of workstations to be allocated is 5, then the number of comprehensive priorities selected accordingly may be, for example, 3 to 8, and the comprehensive priorities are selected from high to low, for example, the first comprehensive priority value is the 8th comprehensive priority.

[0048] Therefore, the order allocation method for multiple warehousing workstations provided in the embodiment of the present application can achieve priority allocation of more important existing orders, and the importance of existing orders can be determined by the cut-off time and the manually set preset priority, thereby reflecting the importance of each existing order in the actual warehousing logistics process.

[0049] In some embodiments of the present application, obtaining multiple orders to be allocated according to the comprehensive priority and the total remaining amount of allocable orders of multiple workstations to be allocated includes: According to the comprehensive priority, all existing orders within the comprehensive priority level are intercepted step by step from the highest comprehensive priority level; In the case of intercepting all existing orders of comprehensive priority, determining whether the total intercepted order quantity is greater than or equal to the total remaining quantity of allocable orders; When the total number of intercepted orders is greater than or equal to the total remaining number of allocable orders, stop intercepting existing orders, and the intercepted multiple existing orders are treated as multiple orders to be allocated; When the total number of intercepted orders is less than the total remaining number of allocable orders, continue to intercept all existing orders of the next comprehensive priority level.

[0050] According to the technical solution of intercepting the orders to be allocated, in the above embodiment, if the number of orders to be allocated is exactly equal to the total remaining amount of allocable orders, then the target allocation relationship obtained by the multi-objective genetic algorithm can just allocate all the orders to be allocated to multiple workstations to be allocated. If the number of orders to be allocated is greater than the total remaining amount of allocable orders, then in the target allocation relationship, some orders to be allocated will remain unallocated, and the remaining unallocated orders to be allocated can be allocated in the subsequent allocation process. The above interception method of the orders to be allocated can also ensure that the existing orders with higher comprehensive priority can be intercepted as orders to be allocated. Therefore, the order allocation method for warehousing multiple workstations provided in the embodiment of the present application not only takes into account the selection of existing orders with higher comprehensive priority as orders to be allocated, but also takes into account the cargo quantity of each workstation to be allocated during the order allocation period, so that the cargo quantity of each workstation to be allocated is close to the average level, thereby giving priority to the allocation of existing orders with higher comprehensive priority, and improving the overall work efficiency of multiple workstations.

[0051] Based on the above-mentioned interception method of the orders to be allocated, when the number of the orders to be allocated is greater than the total remaining amount of the orders that can be allocated, in order to ensure that all the orders to be allocated with high comprehensive priority are allocated in the target allocation relationship, in some embodiments of the present application, each individual may have the following constraints: Each order to be allocated is allocated to a workstation to be allocated; The quantity of the orders to be allocated to each workstation to be allocated shall not exceed the remaining number of orders that can be allocated to the workstation to be allocated; The number of pending orders that need to be allocated within the lowest comprehensive priority level is the difference between the total remaining amount of allocable orders and the total number of pending orders of the remaining comprehensive priorities.

[0052] It can be understood that if the orders to be allocated cover M comprehensive priorities, then the total remaining amount of allocable orders is deducted from the number of orders to be allocated of (M-1) comprehensive priorities excluding the lowest comprehensive priority, and the difference in quantity is the number of orders that need to be allocated in the lowest comprehensive priority (for example, the Mth comprehensive priority).

[0053] Therefore, based on the above constraints on individuals and the above interception method of to-be-allocated orders, no matter what the target allocation relationship is, it can be guaranteed that there are a certain number of to-be-allocated workstations to receive all to-be-allocated orders except the ones with the lowest comprehensive priority, so that in the target allocation relationship, all to-be-allocated orders with higher comprehensive priorities are allocated, and only a portion of to-be-allocated orders with the lowest comprehensive priority are allocated.

[0054] The following is an example of the order allocation method for multiple warehousing workstations provided in the embodiment of the present application, combined with application scenarios.

[0055] Taking the warehousing and shelving scenario as an example, the processor executes the order allocation method for warehousing multiple workstations provided in the embodiment of the present application. First, it is necessary to clarify the selection range of the workstations to be allocated and the orders to be allocated. The processor selects and determines the warehouse number, the allocation scenario (for example, warehousing and shelving), the priority rules, and the constraint rules. Among them, the warehouse number and the allocation scenario are used to define the selection range of the workstations to be allocated and the orders to be allocated; the priority rules may include a preset priority and an order cut-off time, and the order priority is manually input and added in advance; the order cut-off time is the second priority, and orders with an earlier cut-off time are allocated first. Constraint rules include: minimizing the deviation between the current quantity of goods at the workstation to be allocated and the mean quantity of goods at all workstations to be allocated, and maximizing the correlation between the order to be allocated and the existing orders of the workstation to be allocated.

[0056] The processor also needs to obtain the original basic data related to the existing orders and workstations in the selected warehouse, including: workstation information table, order information table, and online task detail table. The workstation information table mainly includes the number, type, maximum number of operation orders, whether it is enabled, etc. of each workstation. The order information table, as shown in Table 1 below, mainly includes attribute information such as the order number, cargo type, cargo quantity, preset priority, and cut-off time. A row in the table represents a detail line of an order, corresponding to a cargo (SKU). The online task detail table is used to record the status of each detail line of the order assigned to the workstation.

[0057] Table 1 Order information table

[0058] After obtaining the warehouse number, allocation scenario, priority rules, constraint rules, and the above-mentioned original basic data, data preprocessing is performed. First, the original basic data range is preliminarily screened according to the warehouse number and allocation scenario, and the workstations, orders, and online task lists corresponding to the warehouse and corresponding scenarios are screened.

[0059] Secondly, the order information table is aggregated to generate a comprehensive order information table as shown in Table 2 below. The order number is used as the primary key to uniquely identify each order.

[0060] Table 2 Order comprehensive information table

[0061] Specifically, for each order's multiple detail lines, the SKUs involved are summarized into a list, and the corresponding quantities are also converted into a list; all detail lines of the same order share the same cut-off time and preset priority. These attributes are directly extracted from the detail lines and saved in the order comprehensive information table to ensure data consistency and accuracy.

[0062] Improve the readability and analysis efficiency of order information through data integration. After sorting the orders according to the priority rule, add the priority index identifier as the index of the comprehensive priority, and obtain the order comprehensive information table with the priority index identifier as shown in Table 3. Orders with the same priority index have the same comprehensive priority.

[0063] Table 3 Comprehensive information table of orders with priority index identification

[0064] Then, get the workstation information table A list of workstations to be assigned , initialize the key-value dictionary of workstations and allocatable order balances , read the maximum number of operable orders for each workstation , parse the online task list and obtain the number of online operation orders for each workstation , No. The number of orders to be assigned to each workstation . Online tasks for multiple orders at a single workstation include record the current load (quantity of each type of goods) of each workstation. , Representative The quantity of goods of the type.

[0065] To ensure the flexibility of warehouse operation, each workstation is independent and can be opened or closed according to the task situation. Therefore, the allocation of pending orders to pending workstations mainly includes initial allocation and ongoing supplementary allocation. During initial allocation, the number of orders allocated to a single pending workstation is the maximum number of operable orders of the pending workstation. Each time a shelf enters a workstation, it will operate (put on the shelves or pick) a variety of goods. One operation may complete a single or multiple orders. The number of workstations to be assigned each time is uncertain, and the number of orders that need to be assigned to a single workstation to be assigned varies.

[0066] Subsequently, in order to make the quantity of goods allocated to multiple workstations to be allocated more balanced and the operation more efficient, the optimization objectives are to minimize the standard deviation of the quantity of goods between multiple workstations to be allocated and to maximize the correlation between the types of goods within the workstation.

[0067] The objective function of the optimization goal is: Standard Deviation:

[0068] Mean correlation:

[0069] Standard Deviation It describes the difference between the quantity of goods in all workstations to be allocated and the mean quantity of goods after the orders to be allocated are allocated to the workstations to be allocated. The more balanced the allocation, the better. The smaller the value. is the total number of workstations to be allocated. The quantity of goods available at each workstation to be allocated. is the mean quantity of goods available, The association degree for each workstation to be assigned.

[0070] Mean correlation To calculate the association degree of each workstation to be assigned, first determine the association degree of each workstation to be assigned, then sum the association degrees of each workstation to be assigned and take the average value relative to the total number of workstations to be assigned. The association degree can be calculated by using the Apriori algorithm to perform data mining on the historical picking orders of the workstation, and the association relationship between the orders to be assigned and the types of goods in the workstations to be assigned can be analyzed by calculating the support degree to obtain the number of frequent goods combination subsets.

[0071]

[0072] Refers to the historical picking orders of the workstation The order quantity, Refers to historical picking orders Includes a subset of cargo combinations The order quantity is When the cargo combination subset is the frequent commodity combination subset, where Is a subset of cargo combinations The support of is the preset occurrence ratio threshold.

[0073] The calculation formula for the correlation between the types of goods between the workstation to be allocated and the order to be allocated to it is:

[0074] Relevance is the number of frequent cargo combination subsets to be assigned to the workstation. It is a subset of the set of goods types obtained by taking the union of the existing goods types of the workstation to be assigned and the order goods types of the order to be assigned.

[0075] The allocation relationship between the orders to be allocated and the workstations to be allocated needs to meet the following constraints: An order to be allocated Can only be assigned to one pending workstation: ; Every time a workstation to be assigned an order to be assigned, , there exists a , that is If the order Assign to workstation , the value is 1, otherwise it is 0.

[0076] A workstation to be assigned The sum of the number of pending orders and the number of online operation orders cannot exceed the maximum number of operable orders, that is, ; Then, step S140 is performed to obtain the target allocation relationship through a multi-objective genetic algorithm: Through data preprocessing , count the number of workstations and the total remaining quantity of allocable orders of all workstations to be allocated ; According to the comprehensive priority, select the set of orders to be allocated from the order comprehensive information table ,Include Orders to be allocated, including: Initialize the cumulative order quantity , priority index value .

[0077] Cycle judgment Is it greater than If satisfied, then exit the loop and proceed to the next step. If not satisfied, then the statistical priority index value is Number of orders , added to , Add 1; Determine whether it spans multiple priority index values. priority index, a set of orders to be assigned Need to include All orders with priority indexes, and the first All orders corresponding to the priority index value need to be allocated. The number of orders that can be selected in the priority index value is ; After determining the set of orders to be allocated, the target matching relationship is determined through a multi-objective genetic algorithm, including: Generate an initial population, including multiple valid individuals; Calculate the discrete degree value and the mean value of the correlation degree of the individuals in the current population, determine whether the current population meets the convergence conditions, and if so, perform decoding operations on the best individuals to obtain the target allocation relationship. Output the allocation result list according to the target allocation relationship to describe the allocation relationship between the workstations to be allocated and the orders to be allocated; If the convergence condition is not met, the current population is subjected to population operations such as selection, crossover, and mutation until the convergence condition is met.

[0078] The embodiment of the present application also provides an order allocation device for warehousing multiple workstations, comprising: a memory and a processor. The memory is configured to store instructions. The processor is configured to call the instructions from the memory and implement the order allocation method for warehousing multiple workstations provided in accordance with any of the above embodiments when executing the instructions.

[0079] An embodiment of the present application also provides a machine-readable storage medium having instructions stored thereon, the instructions being used to enable a machine to execute the above-mentioned order allocation method for warehousing multiple workstations.

[0080] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0081] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0082] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0083] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0084] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0085] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0086] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. 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 technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0087] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0088] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. An order distribution method for multiple warehouse workstations, characterized in that: include: Acquire the to-be-allocated order information of multiple to-be-allocated orders, the existing order information of multiple to-be-allocated workstations' existing orders, and the historical goods types of the workstations' historical picking orders, wherein the to-be-allocated order information includes the order goods types and order goods quantities, and the existing order information includes the existing goods types and existing goods quantities; Through a multi-objective genetic algorithm, according to the to-be-allocated order information, the existing order information and the historical goods types, the target allocation relationship between the multiple to-be-allocated workstations and the multiple to-be-allocated orders is determined; wherein the optimization objectives of the multi-objective genetic algorithm include: minimizing the discrete degree values ​​of the goods quantities of the multiple to-be-allocated workstations, and maximizing the mean values ​​of the association degrees of the goods types corresponding to the multiple to-be-allocated workstations, the goods quantity discrete degree values ​​are determined according to the order goods quantity and the existing goods quantity, and the goods type association degrees are determined according to the historical goods types, the order goods types and the existing goods types.

2. The method according to claim 1, characterized in that The method of determining the allocation relationship between the plurality of workstations to be allocated and the plurality of orders to be allocated according to the order information to be allocated, the existing order information and the historical goods types through a multi-objective genetic algorithm includes: According to the plurality of orders to be allocated and the plurality of workstations to be allocated, a population having a plurality of individuals is established; wherein each individual is used to represent an allocation relationship between the plurality of orders to be allocated and the plurality of workstations to be allocated; Determine the discrete degree value of the quantity of goods corresponding to each of the individuals according to the quantity of ordered goods and the quantity of existing goods corresponding to each of the individuals; Determine the average value of the correlation degree corresponding to each of the individuals according to the historical goods types, the ordered goods types, and the existing goods types corresponding to each of the individuals; Based on the optimization objective, according to the discrete degree value of the quantity of goods corresponding to each of the individuals in the population and the mean value of the correlation degree, the population update operation is performed on the population until a preset convergence condition is met to obtain a final population; Any individual in the final population is used as the target allocation relationship.

3. The method according to claim 2, characterized in that The dispersion degree value includes a standard deviation, and determining the dispersion degree value of the quantity of goods corresponding to each individual according to the quantity of ordered goods and the quantity of existing goods corresponding to each individual includes: Determine the average value of the quantity of goods already in the plurality of workstations to be allocated according to the quantity of goods already in each of the plurality of workstations to be allocated; According to the individuals, a standard deviation corresponding to the individuals is determined when the multiple orders to be allocated are allocated to the multiple workstations to be allocated.

4. The method according to claim 2, characterized in that: The determining the average value of the correlation degree corresponding to each of the individuals according to the historical goods types, the ordered goods types, and the existing goods types corresponding to each of the individuals includes: For each of the workstations to be allocated in each of the individuals, determine the union of the existing goods types and the ordered goods types corresponding to each of the workstations to be allocated in each of the individuals, so as to obtain a set of goods types corresponding to each of the workstations to be allocated; Determine the number of frequent commodity combination subsets in each of the commodity type sets; wherein the frequent commodity combination subsets are commodity combination subsets in the commodity type set whose number of appearances in the historical picking orders is greater than a preset number threshold; Determine the relevance of the cargo types corresponding to the multiple workstations to be assigned in each of the individuals according to the number of frequent cargo combination subsets in each of the cargo type sets in each of the individuals; According to the correlation degrees of the cargo types corresponding to a plurality of to-be-allocated workstations in each of the individuals, the average value of the correlation degree of each of the individuals is determined.

5. The method according to claim 2, characterized in that: Based on the optimization objective, according to the discrete degree value of the quantity of goods corresponding to each of the individuals in the population and the mean value of the correlation degree, the population updating operation is performed on the population until a preset convergence condition is met to obtain a final population, including: According to the optimization goal, performing non-dominated sorting on the individuals in the population; Select the target number of individuals that are at the front of the non-dominated sort as parents; Performing a crossover operation and a mutation operation on the parent generation to obtain the new population; When the preset convergence condition is not met, the individuals in the new population are non-dominatedly sorted according to the optimization target until the preset convergence condition is met to obtain a final population.

6. The method according to claim 1, characterized in that Before obtaining the to-be-allocated order information of the plurality of to-be-allocated orders, the method further comprises: Obtain cut-off times corresponding to multiple existing orders and preset priorities of the multiple existing orders; Determine the comprehensive priority of the multiple existing orders according to the cut-off time and the preset priority; wherein the comprehensive priority of the existing orders with earlier cut-off time is higher; The multiple orders to be allocated are obtained according to the comprehensive priority and the total remaining amount of allocatable orders of the multiple workstations to be allocated.

7. The method according to claim 6, characterized in that The step of obtaining the plurality of orders to be allocated according to the comprehensive priority and the total remaining amount of the orders that can be allocated to the plurality of workstations to be allocated comprises: According to the comprehensive priority, all the existing orders within the comprehensive priority level are intercepted step by step from the highest comprehensive priority level; In the case of intercepting all the existing orders of the comprehensive priority, determining whether the total quantity of the intercepted orders is greater than or equal to the total remaining quantity of allocable orders; When the total number of intercepted orders is greater than or equal to the total remaining number of allocable orders, stop intercepting existing orders, and use the intercepted multiple existing orders as the multiple orders to be allocated; When the total number of intercepted orders is less than the total remaining number of allocable orders, continue to intercept all the existing orders of the next comprehensive priority level.

8. The method according to claim 7, characterized in that The method of determining the allocation relationship between the plurality of workstations to be allocated and the plurality of orders to be allocated according to the order information to be allocated, the existing order information and the historical goods types through a multi-objective genetic algorithm includes: According to the plurality of orders to be allocated and the plurality of workstations to be allocated, a population having a plurality of individuals is established; wherein each individual is used to represent an allocation relationship between the plurality of orders to be allocated and the plurality of workstations to be allocated; Each of the individuals has constraints: each of the to-be-allocated orders is allocated to one of the to-be-allocated workstations; the number of the to-be-allocated orders allocated to each of the to-be-allocated workstations does not exceed the allocable order balance of the to-be-allocated workstation; the number of the to-be-allocated orders that need to be allocated within the lowest comprehensive priority is the difference between the total allocable order balance and the total number of the to-be-allocated orders of the remaining comprehensive priorities; Determine the discrete degree value of the quantity of goods corresponding to each of the individuals according to the quantity of ordered goods and the quantity of existing goods corresponding to each of the individuals; Determine the average value of the correlation degree corresponding to each of the individuals according to the historical goods types, the ordered goods types, and the existing goods types corresponding to each of the individuals; Based on the optimization objective, according to the discrete degree value of the quantity of goods corresponding to each of the individuals in the population and the mean value of the correlation degree, the population update operation is performed on the population until a preset convergence condition is met to obtain a final population; Any individual in the final population is used as the target allocation relationship.

9. The method according to claim 5, characterized in that In the case where the preset convergence condition is not met, performing non-dominated sorting on the individuals in the new population according to the optimization objective until the preset convergence condition is met, including: When the number of iterations of the population does not reach a preset iteration threshold, performing non-dominated sorting on the individuals in the new population according to the optimization objective until the number of iterations of the population reaches the preset iteration threshold; Alternatively, when the amplitude of change of the discrete degree and / or the mean value of the association degree is greater than or equal to a preset amplitude, the individuals in the new population are non-dominatedly sorted according to the optimization objective until the amplitude of change of the discrete degree and / or the mean value of the association degree is less than the preset amplitude.

10. An order distribution device for multiple workstations in a warehouse, characterized in that: include: a memory configured to store instructions; A processor is configured to call the instructions from the memory and implement the order allocation method for warehousing multiple workstations according to any one of claims 1 to 9 when executing the instructions.

11. A machine-readable storage medium, characterized in that: The machine-readable storage medium stores instructions for causing a machine to execute an order allocating method for warehousing multiple workstations according to any one of claims 1 to 9.

Images