Order assignment method, apparatus, and storage medium for warehousing multi-station

Abstract

The application discloses an order distribution method and device for warehouse multi-stations and a storage medium, and relates to the technical field of warehouse logistics. The method comprises the following steps: obtaining to-be-distributed order information of a plurality of to-be-distributed orders, existing order information of existing orders of a plurality of to-be-distributed stations and historical goods categories of historical picking orders of the stations; determining a target distribution relationship between the plurality of to-be-distributed stations and the plurality of to-be-distributed orders according to the to-be-distributed order information, the existing order information and the historical goods categories by using a multi-objective genetic algorithm; wherein, optimization targets of the multi-objective genetic algorithm comprise minimization of a goods quantity dispersion degree value of the plurality of to-be-distributed stations and maximization of an average value of correlation degrees of goods category correlation degrees corresponding to the plurality of to-be-distributed stations. The method can improve the work efficiency of the plurality of to-be-distributed stations and reduce the possibility of goods accumulation.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of warehouse logistics, in particular to an order allocation method for warehouse multi-stations, a device and a machine readable storage medium thereof. BACKGROUND

[0002] In the logistics intelligent warehouse execution system of intelligent warehouse, orders are sent from an order pool to a work station, the work station is used for processing orders, and the processed orders are sent to the shelves of the warehouse or delivered to the customer. In the existing order allocation method of the work station, the orders in the order pool are arranged in order, part of the orders in front are intercepted and allocated to a single work station, or part of the orders are randomly selected and allocated to a single work station. When considering allocating orders to multiple work stations, the technical means adopted is usually serial allocation, that is, after allocating orders to a single work station, orders are allocated to the next work station. The above-mentioned order allocation method often causes order accumulation of the work station and low order processing efficiency in the case of multiple work stations. SUMMARY

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

[0004] In order to achieve the above-mentioned purpose, the first aspect of the present application provides an order allocation method for warehouse multi-stations, comprising:

[0005] obtaining order information of a plurality of to-be-allocated orders, order information of a plurality of existing orders of a plurality of to-be-allocated work stations, and historical goods categories of historical picking orders of the work stations, wherein the order information of the to-be-allocated orders comprises order goods categories and order goods quantities, and the order information of the existing orders comprises existing goods categories and existing goods quantities;

[0006] determining a target allocation relationship between the plurality of to-be-allocated work stations and the plurality of to-be-allocated orders according to the order information of the to-be-allocated orders, the order information of the existing orders, and the historical goods categories by a multi-objective genetic algorithm; wherein the optimization objectives of the multi-objective genetic algorithm comprise minimization of a goods quantity dispersion degree value of the plurality of to-be-allocated work stations and maximization of an average value of a correlation degree of the goods categories corresponding to the plurality of to-be-allocated work stations, the goods quantity dispersion degree value is determined according to the order goods quantities and the existing goods quantities, and the correlation degree of the goods categories is determined according to the historical goods categories, the order goods categories, and the existing goods categories.

[0007] In some embodiments of the present application, the allocation relationship between the plurality of to-be-allocated workstations and the plurality of to-be-allocated orders is determined by a multi-objective genetic algorithm according to the to-be-allocated order information, the existing order information, and the historical goods categories, including: establishing a population with a plurality of individuals according to the plurality of to-be-allocated orders and the plurality of to-be-allocated workstations; wherein each individual is used to represent an allocation relationship between the plurality of to-be-allocated orders and the plurality of to-be-allocated workstations; determining a goods quantity dispersion degree value corresponding to each individual according to the order goods quantity corresponding to each individual and the existing goods quantity; determining a correlation degree mean value corresponding to each individual according to the historical goods category corresponding to each individual, the order goods category, and the existing goods category; performing a population updating operation on the population based on the optimization target, the goods quantity dispersion degree value corresponding to each individual in the population, and the correlation degree mean value corresponding to each individual, until a preset convergence condition is met, to obtain a final population; and taking any one individual in the final population as a target allocation relationship.

[0008] In some embodiments of the present application, the dispersion degree value includes a standard deviation, and the goods quantity dispersion degree value corresponding to each individual is determined according to the order goods quantity corresponding to each individual and the existing goods quantity, including: determining a mean value of the existing goods quantities of the plurality of to-be-allocated workstations according to the existing goods quantities of the plurality of to-be-allocated workstations; and determining the standard deviation corresponding to each individual when the plurality of to-be-allocated orders are allocated to the plurality of to-be-allocated workstations according to the individual.

[0009] In some embodiments of the present application, the correlation degree mean value corresponding to each individual is determined according to the historical goods category corresponding to each individual, the order goods category, and the existing goods category, including: for each to-be-allocated workstation in each individual, determining a union set of the existing goods category and the order goods category corresponding to each to-be-allocated workstation in each individual, to obtain a goods type set corresponding to each to-be-allocated workstation; determining the number of frequent goods combination subsets in each goods type set; wherein the frequent goods combination subset is a goods combination subset in the goods type set whose occurrence frequency in the historical picking order is greater than a preset frequency threshold; determining the goods category correlation degree corresponding to the plurality of to-be-allocated workstations in each individual according to the number of frequent goods combination subsets in each goods type set in each individual; and determining the correlation degree mean value of each individual according to the goods category correlation degree corresponding to the plurality of to-be-allocated workstations in each individual.

[0010] In some embodiments of the present application, based on the optimization target, the population is updated according to the discrete degree value of the corresponding goods quantity of each individual in the population and the average correlation, until the preset convergence condition is met, to obtain the final population, including: according to the optimization target, the individuals in the population are non-dominantly sorted; select the top target number of individuals in the non-dominant sorting as the parent; the parent is subjected to cross operation and mutation operation to obtain a new population; in the case that the preset convergence condition is not met, the individuals in the new population are non-dominantly sorted according to the optimization target, until the preset convergence condition is met, to obtain the final population.

[0011] In some embodiments of the present application, before obtaining the to-be-allocated order information of the plurality of to-be-allocated orders, the method further comprises: obtaining the cut-off time corresponding to each of the plurality of existing orders and the preset priority of the plurality of existing orders; determining the comprehensive priority of the plurality of existing orders according to the cut-off time and the preset priority; wherein the comprehensive priority of the existing order with earlier cut-off time is higher; and obtaining the plurality of to-be-allocated orders according to the comprehensive priority and the total remaining amount of allocatable orders of the plurality of to-be-allocated workstations.

[0012] In some embodiments of the present application, the plurality of to-be-allocated orders are obtained according to the comprehensive priority and the total remaining amount of allocatable orders of the plurality of to-be-allocated workstations, including: according to the comprehensive priority, all existing orders within the comprehensive priority are sequentially intercepted from the highest comprehensive priority; in the case that all existing orders of the comprehensive priority are intercepted, it is judged whether the total number of intercepted orders is greater than or equal to the total remaining amount of allocatable orders; in the case that the total number of intercepted orders is greater than or equal to the total remaining amount of allocatable orders, the interception of existing orders is stopped, and the plurality of existing orders that have been intercepted are taken as the plurality of to-be-allocated orders; in the case that the total number of intercepted orders is less than the total remaining amount of allocatable orders, all existing orders of the next comprehensive priority are continuously intercepted.

[0013] In some embodiments of the present application, the assignment relationship between the plurality of to-be-assigned workstations and the plurality of to-be-assigned orders is determined by a multi-objective genetic algorithm according to the to-be-assigned order information, the existing order information, and the historical goods categories, including: a population with a plurality of individuals is established according to the plurality of to-be-assigned orders and the plurality of to-be-assigned workstations; each individual represents an assignment relationship between the plurality of to-be-assigned orders and the plurality of to-be-assigned workstations; each individual has a constraint condition that each to-be-assigned order is assigned to one to-be-assigned workstation, and the number of to-be-assigned orders assigned to each to-be-assigned workstation does not exceed the assignable order balance of the to-be-assigned workstation; the number of to-be-assigned orders that need to be assigned within the lowest comprehensive priority is the number difference between the total assignable order balance and the total number of to-be-assigned orders of the remaining comprehensive priority; the goods quantity dispersion degree value corresponding to each individual is determined according to the order goods quantity corresponding to each individual and the existing goods quantity; the association degree mean value corresponding to each individual is determined according to the historical goods category corresponding to each individual, the order goods category, and the existing goods category; based on the optimization target, the population is updated according to the goods quantity dispersion degree value and the association degree mean value corresponding to each individual in the population until a preset convergence condition is met to obtain a final population; and any individual in the final population is taken as a target assignment relationship.

[0014] In some embodiments of the present application, in the case where the preset convergence condition is not met, the individuals in the new population are non-dominantly sorted according to the optimization target until the preset convergence condition is met, including: in the case where the iteration number of the population does not reach a preset iteration threshold, the individuals in the new population are non-dominantly sorted according to the optimization target until the iteration number of the population reaches the preset iteration threshold; or, in the case where the variation amplitude of the dispersion degree and / or the association degree mean value is greater than or equal to a preset amplitude, the individuals in the new population are non-dominantly sorted according to the optimization target until the variation amplitude of the dispersion degree and / or the association degree mean value is less than the preset amplitude.

[0015] The second aspect of the present application provides an order assignment device for a warehouse multi-workstation, including: a memory configured to store instructions; a processor configured to call instructions from the memory and capable of implementing the order assignment method for a warehouse multi-workstation provided by any of the above embodiments when executing the instructions.

[0016] The third aspect of the present application provides a machine-readable storage medium having instructions stored thereon for causing a machine to execute the order assignment method for a warehouse multi-workstation provided by any of the above embodiments.

[0017] The order allocation method for multiple workstations in warehousing provided in this application sets two optimization objectives: minimizing the dispersion value of the quantity of goods at multiple workstations to be allocated and maximizing the average correlation degree of the goods type correlation degree corresponding to each of the multiple workstations to be allocated. Combined with a multi-objective genetic algorithm, the allocation relationship between multiple workstations and multiple orders to be allocated is iteratively optimized to obtain a target allocation relationship between multiple workstations and multiple orders to be allocated, with a smaller dispersion value and a larger average correlation degree. Based on this target allocation relationship, multiple orders to be allocated are distributed to multiple workstations, thereby making the quantity of goods among the multiple workstations to be allocated tend to be average, and ensuring that the goods type correlation degree of each workstation is at a reasonable level, maximizing the average correlation degree. This can improve the working efficiency of multiple workstations to be allocated and reduce the possibility of goods piling up.

[0018] Other features and advantages of the embodiments of this application will be described in detail in the following detailed description section. Attached Figure Description

[0019] The accompanying drawings are provided to further illustrate the embodiments of this application and form part of the specification. They are used together with the following detailed description to explain the embodiments of this application, but do not constitute a limitation on the embodiments of this application. In the drawings:

[0020] Figure 1 The illustration shows a flowchart of an order allocation method for a multi-workstation warehouse according to an embodiment of this application;

[0021] Figure 2 Schematic illustration Figure 1 A flowchart of step S140;

[0022] Figure 3 Schematic illustration Figure 2 A flowchart illustrating step S146;

[0023] Figure 4 Schematic illustration Figure 3 A flowchart of step S1468. Detailed Implementation

[0024] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are only for illustration and explanation of the embodiments of this application and are not intended to limit the embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0025] It should be noted that if the application embodiments involve directionality indication (such as up, down, left, right, front, back, etc.), the directionality indication is only used to explain the relative position relationship, motion condition, etc. between components in a certain specific posture (as shown in the drawings), and if the specific posture changes, the directionality indication also changes accordingly.

[0026] In addition, if the application embodiments involve descriptions such as "first", "second", etc., the descriptions of "first", "second", etc. are only for description purposes and cannot be understood as indicating or implying the relative importance or implicitly indicating the number of indicated technical features. Therefore, the features limited by "first", "second" can explicitly or implicitly include at least one of the features. In addition, the technical solutions of each embodiment can be combined with each other, but it must be based on the fact that a person skilled in the art can realize it, and when the combination of technical solutions contradicts each other or cannot be realized, it should be considered that the combination of technical solutions does not exist and is not within the protection scope claimed by the present application.

[0027] In the existing allocation scheme for allocating multiple orders to workstations in a warehouse environment, multiple orders are only allocated to multiple workstations one by one. Since the number of goods of each order is different, and the number of existing orders and the number of goods of each workstation are also different. Therefore, the above-mentioned existing allocation scheme may cause the number of goods actually needed to be processed by multiple workstations to be unbalanced, and the number of goods needed to be processed by some workstations is too large, and the number of goods needed to be processed by some other workstations cannot fully utilize the goods processing capacity of the workstations. The multiple goods in the workstations will be picked out from the workstations to the outside with a specific combination of goods types due to the need of warehouse goods shelving or warehouse picking. Therefore, if the types of goods in the workstations are not complete or too many, it will cause the accumulation of goods of specific types. Based on the above analysis, it can be known that the imbalance of the number of goods and the unreasonable allocation of the types of goods will cause the low efficiency of the whole multiple workstations in processing the goods in the orders. Based on the above observation and analysis of the prior art, the inventors propose an order allocation method for multiple workstations in a warehouse, which considers the balance of the number of goods and the reasonable allocation of the types of goods.

[0028] The order allocation method for multiple workstations in a warehouse environment provided by the application embodiments can be used in two types of scenarios of warehouse-in shelving and warehouse-out picking in the warehouse logistics field, and can be used as an allocation method for the order allocation to workstations link of the WES (Warehouse Execution System) management system in intelligent warehouse, and executed by a processor.

[0029] Figure 1A flowchart of an order allocation method for a warehouse multi-station is shown schematically according to an embodiment of the present application. As shown in Figure 1 The order allocation method for a warehouse multi-station provided by the embodiment of the present application can include the following steps:

[0030] S120, obtaining order information of a plurality of to-be-allocated orders, order information of a plurality of existing orders of the to-be-allocated stations, and historical goods categories of historical picking orders of the stations, wherein the order information of the to-be-allocated orders includes order goods categories and order goods quantities, and the order information of the existing orders includes existing goods categories and existing goods quantities;

[0031] S140, determining a target allocation relationship between the plurality of to-be-allocated stations and the plurality of to-be-allocated orders according to the order information of the to-be-allocated orders, the order information of the existing orders, and the historical goods categories by using a multi-objective genetic algorithm, wherein optimization objectives of the multi-objective genetic algorithm include minimization of a goods quantity dispersion degree value of the plurality of to-be-allocated stations, and maximization of an average value of a goods category correlation degree of the plurality of to-be-allocated stations respectively, the goods quantity dispersion degree value is determined according to the order goods quantities and the existing goods quantities, and the goods category correlation degree is determined according to the historical goods categories, the order goods categories, and the existing goods categories.

[0032] It can be understood that the historical picking orders of the stations refer to historical orders for which goods are picked by the stations and then put on shelves, or refer to historical orders for which goods are picked by the stations and then sent to customers. The historical picking orders can come from stations in the same warehouse, or from stations in different warehouses. The historical picking orders of the stations record combinations of historical goods categories of historical picking orders. The goods category correlation degree of each to-be-allocated station refers to that, for each to-be-allocated station, a set of goods types is obtained by putting together the to-be-processed goods categories of the existing orders and the goods categories of the to-be-allocated orders, and a set number of various goods type combination subsets in the set of goods types, which appear in the historical picking orders with a frequency higher than a certain value. Thus, each to-be-allocated station can obtain a set number of various goods type combination subsets, which appear with a frequency higher than a certain value, as the goods category correlation degree between the to-be-allocated station and the to-be-allocated orders. The average value of the goods category correlation degrees of the plurality of to-be-allocated stations is the average value of the correlation degrees. The parameter representing the goods quantity dispersion degree value of the plurality of to-be-allocated stations can be, for example, a range, an interquartile range, a standard deviation, a variance, a coefficient of variation, etc.

[0033] Specifically, in step S140, the multi-objective genetic algorithm determines the allocation relationship between the plurality of to-be-allocated workstations and the plurality of to-be-allocated orders according to the to-be-allocated order information and the to-be-allocated workstation information, and iteratively optimizes the allocation relationship between the plurality of to-be-allocated workstations and the plurality of to-be-allocated orders according to the optimization target until a target allocation relationship meeting the multi-objective genetic algorithm is obtained. The plurality of to-be-allocated orders are then allocated to the plurality of to-be-allocated workstations according to the target allocation relationship.

[0034] The order allocation method for warehouse multi-workstations provided by the embodiments of the present application sets two optimization targets of minimizing the discrete degree value of the quantity of goods of the plurality of to-be-allocated workstations and maximizing the average of the association degrees of the association degrees of the respective goods categories corresponding to the plurality of to-be-allocated workstations, and iteratively optimizes the allocation relationship between the plurality of to-be-allocated workstations and the plurality of to-be-allocated orders by cooperating with the multi-objective genetic algorithm, so as to obtain a target allocation relationship between the plurality of to-be-allocated workstations and the plurality of to-be-allocated orders with a smaller discrete degree value and a larger average of the association degrees. According to the target allocation relationship, the plurality of to-be-allocated orders are allocated to the plurality of to-be-allocated workstations, so that the quantity of goods among the plurality of to-be-allocated workstations tends to be average, and the association degree of the goods category of each to-be-allocated workstation is at a reasonable level, and the average of the association degrees is maximized. In this way, the work efficiency of the plurality of to-be-allocated workstations is improved, and the possibility of goods accumulation is reduced.

[0035] In some embodiments of the present application, referring to Figure 2 , step S140 can include:

[0036] S142, a population with a plurality of individuals is established according to the plurality of to-be-allocated orders and the plurality of to-be-allocated workstations; wherein each individual is used to represent an allocation relationship between the plurality of to-be-allocated orders and the plurality of to-be-allocated workstations;

[0037] S144, the discrete degree value of the quantity of goods corresponding to each individual is determined according to the order goods quantity and the existing goods quantity corresponding to each individual;

[0038] S146, the average of the association degrees corresponding to each individual is determined according to the historical goods category, the order goods category and the existing goods category corresponding to each individual;

[0039] S148, based on the optimization target, the population is subjected to a population updating operation according to the discrete degree value of the quantity of goods and the average of the association degrees corresponding to each individual in the population, until a preset convergence condition is met, so as to obtain a final population;

[0040] S149, any one individual in the final population is taken as a target allocation relationship.

[0041] It can be understood that the population in step S142 is determined by the multi-objective genetic algorithm according to the number and respective identity of the plurality of to-be-assigned workstations, in combination with the number and identity of the plurality of to-be-assigned orders. Each individual in the population represents an assignment relationship of the identity of the plurality of to-be-assigned workstations and the identity of the plurality of to-be-assigned orders.

[0042] As an example, it is assumed that there are three to-be-assigned workstations, and the identity vector of the three to-be-assigned workstations is and five to-be-assigned orders, and the identity vector of the five to-be-assigned orders is , then an optional individual, the identity of the five to-be-assigned orders in the individual and the identity of the three to-be-assigned workstations, for example, exist such an assignment relationship: . That is, to five to-be-assigned orders are respectively assigned to one to-be-assigned workstation in to .

[0043] Since the number of to-be-assigned orders and the number of to-be-assigned workstations are not necessarily equal, and the assignable order surplus of each to-be-assigned workstation is limited and may be different. Therefore, in some embodiments of the present application, each individual can have the following constraint condition:

[0044] Each to-be-assigned order is assigned to one to-be-assigned workstation; the number of to-be-assigned orders assigned to each to-be-assigned workstation does not exceed the assignable order surplus of the to-be-assigned workstation.

[0045] As an example, under the constraint of the above constraint condition, it is assumed that there are three to-be-assigned workstations, and the identity vector (or identity string) of the three to-be-assigned workstations is , which means that the assignable order surplus of the to-be-assigned workstation is 1, the assignable order surplus of the to-be-assigned workstation is 0, and the assignable order surplus of the to-be-assigned workstation is 2. Accordingly, it is assumed that there are five to-be-assigned orders, and the assignment relationship of the five to-be-assigned orders and the three to-be-assigned workstations can be, for example, , that is, the first to-be-assigned order and the fifth order are assigned to the to-be-assigned workstation , the second to-be-assigned order is assigned to the to-be-assigned workstation , and the third and fourth to-be-assigned orders are not assigned.

[0046] ​In some embodiments of the present application, the discrete degree value is a standard deviation, and the step 144 comprises: determining a mean of the existing goods quantities of the plurality of to-be-assigned workstations according to the existing goods quantities of the plurality of to-be-assigned workstations; and determining the standard deviation corresponding to each individual when the plurality of to-be-assigned orders are assigned to the plurality of to-be-assigned workstations.

[0047] When the discrete degree value is a standard deviation, the optimization objective is to minimize the standard deviation, so that the standard deviation of the individuals in the new population tends to be minimized compared with the standard deviation of the individuals in the last generation population through the iteration of the multi-objective genetic algorithm. The reduction of the standard deviation means that the deviation of the plurality of to-be-assigned workstations from the mean of the goods quantities is small after the plurality of to-be-assigned workstations assign the to-be-assigned orders, so that the goods quantities of each to-be-assigned workstation are similar and tend to be the mean of the goods quantities. Thus, the final target assignment relationship can make the goods quantities of the plurality of to-be-assigned workstations more balanced after the plurality of to-be-assigned workstations assign the to-be-assigned orders, thereby reducing the possibility of goods accumulation and improving the overall efficiency of the plurality of to-be-assigned workstations.

[0048] As an example, the standard deviation corresponding to each individual when the plurality of to-be-assigned orders are assigned to the plurality of to-be-assigned workstations is determined by the following formula:

[0049]

[0050] wherein, is the standard deviation, is the total number of the plurality of to-be-assigned workstations, is the existing goods quantity of each to-be-assigned workstation, is the mean of the existing goods quantities.

[0051] In some embodiments of the present application, referring to Figure 3 , the step S146 comprises:

[0052] S1462, for each to-be-assigned workstation in each individual, determining a set of goods types corresponding to each to-be-assigned workstation in each individual by taking the union of the existing goods types and the order goods types corresponding to each to-be-assigned workstation in each individual;

[0053] S1464, determining the number of frequent goods combination subsets in each set of goods types; wherein the frequent goods combination subset is a goods combination subset in the set of goods types, and the occurrence ratio of the goods combination subset in the historical order picking at the workstations is greater than a preset occurrence times ratio threshold value;

[0054] S1466, determining the goods type correlation degree corresponding to the plurality of to-be-assigned workstations in each individual according to the number of frequent goods combination subsets in each set of goods types in each individual.

[0055] S1468、According to the relevance degree of each individual corresponding to the cargo type of each to-be-assigned workstation, determine the average relevance degree of each individual.

[0056] It can be understood that the cargo type set refers to the union of the existing cargo type set of the to-be-assigned workstation and the order cargo type set of the to-be-assigned order in the individual according to the assignment relationship between the to-be-assigned workstation and the to-be-assigned order. Thus, in each individual, each to-be-assigned workstation corresponds to a cargo type set. The preset occurrence frequency ratio threshold can be set according to experience or can be set and adjusted according to the frequency of the combination of a certain cargo type in a plurality of historical picking orders. If the ratio of the combination of a certain cargo type in a plurality of historical picking orders is higher than the preset occurrence frequency ratio threshold, it means that the combination of the cargo type frequently occurs, and vice versa. The cargo type set includes a plurality of cargos, and each cargo type is an element in the cargo type set. By selecting elements in the cargo type set, a cargo combination subset can be obtained. Each cargo combination subset corresponds to a cargo combination. For example, if the cargo type set includes N cargo types, the number of cargo combination subsets of the cargo type set is That is, from N cargo types, 1 cargo to N cargo combinations are selected, a total of K combination methods. Of course, in another example, the case of selecting only one cargo can also be excluded.

[0057] Specifically, as an example, after selecting K number of cargo combination subsets, according to the cargo combination subset, determine the frequency of the cargo combination expressed by the cargo combination subset in the historical picking order of the workstation. If the frequency is greater than or equal to the preset occurrence frequency ratio threshold, it is judged that the cargo combination expressed by the cargo combination subset is a frequent set. For each cargo combination subset, perform the above steps to determine whether it is a frequent set, and finally the number of frequent sets in the cargo type set can be obtained, and the number of frequent sets is the relevance degree of the cargo type corresponding to any to-be-assigned workstation in the individual. Then execute step S1468, sum the cargo type relevance degrees corresponding to the plurality of to-be-assigned workstations in the individual and divide by the number of the plurality of to-be-assigned workstations to obtain the average relevance degree.

[0058] According to the technical solution, the order allocation method for the warehouse multi-workstation provided by the embodiment of the application can determine the correlation degree of the goods category between each individual target order to be allocated and the existing order of the target workstation to be allocated, and obtain the average correlation degree of the individual. The average correlation degree reflects the average level of the correlation degree of the multiple target workstations to be allocated under the allocation relationship of the target workstations to be allocated and the target orders to be allocated expressed by the individual. Since the maximization of the average correlation degree is the optimization target in the solution, the average correlation degree of the individual in the final population is the maximization result obtained by the multi-objective genetic algorithm. Therefore, after the target orders to be allocated are allocated to the target workstations to be allocated according to the individual in the final population, the various goods in the existing orders of the multiple target workstations to be allocated are more likely to be picked out of the workstations according to the needs of a certain picking order during the subsequent work, thereby avoiding the accumulation of goods of a specific category in the workstations, and thus improving the picking efficiency of the workstations.

[0059] In some embodiments of the application, step S148 comprises: performing non-dominated sorting on the individuals in the population according to the optimization target; selecting a target number of individuals at the front in the non-dominated sorting as parents; performing crossover operation and mutation operation on the parents to obtain a new population; in the case that the preset convergence condition is not met, performing non-dominated sorting on the individuals in the new population according to the optimization target until the preset convergence condition is met to obtain a final population.

[0060] It can be understood that the non-dominated sorting can be implemented based on, for example, Pareto dominance, and the identified Pareto front can be, for example, the target number of individuals at the front in the non-dominated sorting. The crossover operation can adopt a multi-point crossover manner. The newly generated individuals are mutated to increase the diversity of the population. The mutation can be random change. In the process of generating the new population, the crowding distance calculation can also be performed, the crowding distance of the individuals in the new population is calculated, and the crowding distance between the individuals is kept above a certain distance to maintain the diversity of the population.

[0061] Specifically, as an example, Figure 4 An execution flow of step S148 is shown, which comprises:

[0062] S1482, obtaining the current population;

[0063] S1483, determining whether the current population meets the convergence condition;

[0064] In the case that the current population does not meet the convergence condition, the following steps are performed:

[0065] S1484, non-dominantly sorting the individuals in the current population according to the optimization target;

[0066] S1486, selecting a target number of individuals at the front in the non-dominantly sorted individuals as parents;

[0067] S1488, performing crossover operation and mutation operation on the parents to obtain a new population;

[0068] In the case that the current population meets the convergence condition, the following steps are performed:

[0069] S1489, outputting the current population as a final population.

[0070] In some embodiments of the present application, the preset convergence condition may, for example, be whether the iteration number of the population reaches a threshold, or whether the variation range of the average of the dispersion degree and / or the correlation degree is greater than or equal to a preset range, or whether the running time of the multi-objective genetic algorithm reaches a preset time.

[0071] Specifically, in the case that the preset convergence condition is not met, the individuals in the new population are non-dominantly sorted according to the optimization target until the preset convergence condition is met to obtain the final population, which may include: in the case that the iteration number of the population does not reach a preset iteration threshold, the individuals in the new population are non-dominantly sorted according to the optimization target until the iteration number of the population reaches the preset iteration threshold; or, in the case that the variation range of the average of the dispersion degree and / or the correlation degree is greater than or equal to a preset range, the individuals in the new population are non-dominantly sorted according to the optimization target until the variation range of the average of the dispersion degree and / or the correlation degree is less than the preset range.

[0072] In order to give priority to more important orders, the order allocation method for warehouse multi-stations provided by the embodiments of the present application may further include, before obtaining the to-be-allocated order information of a plurality of to-be-allocated orders, the following steps:

[0073] Obtaining the cut-off time corresponding to each of a plurality of existing orders and the preset priority of the plurality of existing orders;

[0074] Determining the comprehensive priority of the plurality of existing orders according to the cut-off time and the preset priority; wherein, the comprehensive priority of the existing order with earlier cut-off time is higher;

[0075] Obtaining the plurality of to-be-allocated orders according to the comprehensive priority and the total remaining amount of allocable orders of the plurality of to-be-allocated stations.

[0076] It can be understood that the cut-off time refers to a time point or period at which 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 overall priority of the existing order with the earlier cut-off time is higher, and the existing order is selected as the to-be-allocated order with higher priority. In addition, in some embodiments of the present application, among multiple existing orders with the same cut-off time, the overall priority of the existing order with the higher preset priority is higher.

[0077] Specifically, according to the overall priority and the number of to-be-allocated workstations, obtaining the multiple to-be-allocated orders can include: selecting the same number of overall priorities as the number of to-be-allocated workstations, and selecting the corresponding existing orders as to-be-allocated orders according to the selected overall priorities. Of course, a certain number of overall priorities can also be selected according to the number of to-be-allocated workstations and the preset number interval. For example, if the number of to-be-allocated workstations is 5, then the number of overall priorities selected can be, for example, 3 to 8, and the overall priorities are selected from high to low, for example, the first overall priority value is the eighth overall priority.

[0078] Therefore, the order allocation method for warehouse multi-workstations provided by the embodiments of the present application can realize the priority allocation of more important existing orders, and the importance of the existing orders can be determined by the cut-off time and the preset priority set by humans, thereby reflecting the importance of each existing order in the actual warehouse logistics process.

[0079] In some embodiments of the present application, according to the overall priority and the total remaining amount of allocatable orders of the multiple to-be-allocated workstations, obtaining the multiple to-be-allocated orders includes:

[0080] According to the overall priority, all existing orders within the overall priority are sequentially intercepted from the highest overall priority;

[0081] In the case of intercepting all existing orders of the overall priority, it is judged whether the total number of intercepted orders is greater than or equal to the total remaining amount of allocatable orders;

[0082] In the case where the total number of intercepted orders is greater than or equal to the total remaining amount of allocatable orders, the interception of existing orders is stopped, and the multiple existing orders intercepted are used as the multiple to-be-allocated orders;

[0083] In the case where the total number of intercepted orders is less than the total remaining amount of allocatable orders, all existing orders of the next overall priority are continuously intercepted.

[0084] According to the above technical solution of intercepting the to-be-allocated orders, in the above embodiment, if the number of the to-be-allocated orders is exactly equal to the total remaining amount of the allocatable orders, then the target allocation relationship obtained by the multi-objective genetic algorithm can exactly allocate all the to-be-allocated orders to the plurality of to-be-allocated workstations. If the number of the to-be-allocated orders is greater than the total remaining amount of the allocatable orders, then in the target allocation relationship, there will be a part of the to-be-allocated orders that are not allocated, and the remaining to-be-allocated orders that are not allocated can be allocated in the subsequent allocation process. The above interception manner of the to-be-allocated orders can also ensure that the existing orders with higher comprehensive priority can be intercepted as to-be-allocated orders. Therefore, the order allocation method for the warehouse multi-station provided in the embodiments of the present application not only considers selecting the existing orders with higher comprehensive priority as to-be-allocated orders for allocation, but also considers the goods amount conditions of each to-be-allocated workstation during the allocation of the orders, so that the goods amount of each to-be-allocated workstation tends to be average, thereby preferentially allocating the existing orders with higher comprehensive priority and improving the overall work efficiency of the plurality of workstations.

[0085] Based on the above interception method of the to-be-allocated orders, in the case where the number of the to-be-allocated orders is greater than the total remaining amount of the allocatable orders, in order to ensure that the to-be-allocated orders with high comprehensive priority are all allocated in the target allocation relationship, in some embodiments of the present application, each individual can have the following constraint condition:

[0086] Each to-be-allocated order is allocated to one to-be-allocated workstation;

[0087] The number of the to-be-allocated orders allocated to each to-be-allocated workstation does not exceed the remaining amount of the allocatable orders of the to-be-allocated workstation;

[0088] The number of the to-be-allocated orders that need to be allocated in the lowest comprehensive priority is the difference between the total remaining amount of the allocatable orders and the total number of the to-be-allocated orders of the remaining comprehensive priorities.

[0089] It can be understood that if the to-be-allocated orders cover M comprehensive priorities, then the difference obtained by subtracting the number of the to-be-allocated orders of the (M-1) comprehensive priorities other than the lowest comprehensive priority from the total remaining amount of the allocatable orders is the number of the orders that need to be allocated in the lowest comprehensive priority (for example, the Mth comprehensive priority).

[0090] Therefore, based on the above constraint condition of the individual and the above interception method of the to-be-allocated orders, regardless of the target allocation relationship, a certain number of to-be-allocated workstations can be used to receive all the to-be-allocated orders other than the lowest comprehensive priority, so that in the target allocation relationship, the to-be-allocated orders with higher comprehensive priority are all allocated, and the to-be-allocated orders of the lowest comprehensive priority are partially allocated.

[0091] The order allocation method for warehouse multi-station provided by the embodiments of the present application will be illustrated below in combination with application scenarios.

[0092] In the warehouse storage scenario, the processor executes the order allocation method for warehouse multi-station provided by the embodiments of the present application, for example, first, the selection range of the to-be-allocated workstations and the to-be-allocated orders needs to be determined. The processor selects the warehouse number, the allocation scenario (for example, warehouse storage), the priority rule, and the constraint rule. Among them, the warehouse number and the allocation scenario are used to determine the selection range of the to-be-allocated workstations and the to-be-allocated orders; the priority rule can include the preset priority, the order cut-off time, and the order priority is manually inputted in advance; the order cut-off time is the second priority, and the orders with earlier cut-off time are allocated first. The constraint rule includes: the minimum deviation of the current cargo quantity of the to-be-allocated workstations from the average cargo quantity of all to-be-allocated workstations, and the maximum correlation degree of the to-be-allocated orders and the existing orders of the to-be-allocated workstations.

[0093] The processor also needs to obtain the original basic data related to the workstations in the selected warehouse and the existing orders, including: the workstation information table, the order information table, and the online task detail table. The workstation information table mainly includes the number, type, maximum operation order number, and whether to enable state of each workstation. The order information table, as shown in Table 1 below, mainly includes the order number, cargo type, cargo quantity, preset priority, and cut-off time, and each row in the table represents a detail row of an order, corresponding to a kind of goods (Sku). The online task detail table is used to record the status of each detail row of the orders allocated to the workstations.

[0094] Table 1 Order Information Table

[0095]

[0096] After obtaining the warehouse number, the allocation scenario, the priority rule, the constraint rule, and the above-mentioned original basic data, data preprocessing is performed. First, the original basic data range is preliminarily filtered according to the warehouse number and the allocation scenario, and the workstations and orders corresponding to the warehouse and the scenario and the online task detail table are filtered.

[0097] Secondly, the order information table is aggregated to generate the order comprehensive information table as shown in Table 2 below, and the order number is used as the primary key to realize the unique identification of each order.

[0098] Table 2 Order Comprehensive Information Table

[0099]

[0100] 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 stored in the order comprehensive information table to ensure data consistency and accuracy.

[0101] Data integration improves the readability of order information and the efficiency of analysis. After sorting orders according to priority rules, a priority index is added as an index for overall priority, resulting in a comprehensive order information table with priority indexes, as shown in Table 3. Orders with the same priority index have the same overall priority.

[0102] Table 3. Order Summary Information Table with Priority Index Identifier

[0103]

[0104] Then, obtain the information from the workstation information table. List of workstations to be assigned Initialize the key-value dictionary of workstations and allocable order surplus. Read the maximum number of orders that can be processed at each workstation. The online task details table is parsed to obtain the number of online operation orders for each workstation. , No. Number of orders to be assigned to each workstation Online tasks with multiple orders on a single workstation include... Record the current load (quantity of each type of goods) at each workstation for each type of goods. , Representing the The quantity of a type of goods.

[0105] To ensure flexibility in warehouse operations, each workstation exists independently and can be turned on or off individually as needed. Therefore, the allocation of orders to workstations mainly involves initial allocation and ongoing supplementary allocation. During initial allocation, the number of orders allocated to a single workstation is equal to the maximum number of orders that workstation can handle. Each time a shelf enters a workstation, it will handle (shelving or picking) multiple items. A single operation may complete one or more orders. The number of workstations to be assigned each time is uncertain, and the number of orders to be assigned to a single workstation varies.

[0106] Subsequently, to ensure a more balanced distribution of goods among multiple workstations and improve operational efficiency, the optimization objective was defined as minimizing the standard deviation of goods quantities among the workstations and maximizing the correlation between goods types within each workstation.

[0107] Objective function of optimization target:

[0108] Standard deviation:

[0109] Average of correlation degree:

[0110] Standard deviation Describes the difference between the number of goods of all the to-be-assigned workstations and the average number of goods after the to-be-assigned orders are assigned to the to-be-assigned workstations, the more balanced the assignment is The smaller the value is. Total number of the plurality of to-be-assigned workstations, Existing number of goods of each to-be-assigned workstation, Average of existing number of goods, Correlation degree of each to-be-assigned workstation.

[0111] Average of correlation degree The calculation of the average of correlation degree first needs to determine the correlation degree of each to-be-assigned workstation, then sums the correlation degree of each to-be-assigned workstation and averages it relative to the total number of the plurality of to-be-assigned workstations. The correlation degree can be obtained by using the Apriori algorithm to perform data mining on the historical picking orders of the workstations, analyzing the correlation between the to-be-assigned orders and the goods types of the to-be-assigned workstations by calculating the support, and obtaining the number of frequent goods combination subsets.

[0112]

[0113] Refers to the number of orders of the historical picking orders of the workstations Refers to the number of orders of the historical picking orders including the goods combination subset Refers to the number of orders of the historical picking orders when The goods combination subset is a frequent goods combination subset, wherein is the support of the goods combination subset is a preset occurrence ratio threshold.

[0114] The calculation formula of the correlation degree of the goods types between the to-be-assigned workstations and the to-be-assigned orders assigned to it is:

[0115]

[0116] The correlation degree is the number of frequent goods combination subsets of the to-be-assigned workstations. The goods combination subset ​is a subset of the set of goods types obtained by taking the union of the existing goods types of the to-be-assigned workstations and the order goods types of the to-be-assigned orders.

[0117] The assignment relationship between the to-be-assigned orders and the to-be-assigned workstations needs to meet the following constraints:

[0118] One to-be-assigned order can only be assigned to one to-be-assigned workstation: ; for each to-be-assigned workstation , there exists one , that is If the order is assigned to the workstation , the value is 1, otherwise 0.

[0119] The sum of the number of to-be-assigned orders assigned to one to-be-assigned workstation and the number of online operation orders cannot exceed the maximum number of operation orders, that is ;

[0120] Then step S140 is performed to obtain the target assignment relationship by a multi-objective genetic algorithm:

[0121] Through data preprocessing, obtain , the number of workstations and the total amount of assignable orders of all to-be-assigned workstations ;

[0122] According to the comprehensive priority, select the to-be-assigned order set from the order comprehensive information table, containing to-be-assigned orders, including:

[0123] Initialize the cumulative order quantity and the priority index value .

[0124] Loop to judge whether it is greater than . If yes, jump out of the loop and proceed to the next step. If not, count the number of orders with the priority index value , and add it to , and 1;

[0125] Judge whether it crosses multiple priority index values. If it crosses priority index values, the to-be-assigned order set needs to include all orders of the priority index values, and the first All orders corresponding to one priority index value need to be allocated, and the number of optional orders in the priority index value is ; ;

[0126] After the set of orders to be allocated is determined, a target matching relationship is determined by using a multi-objective genetic algorithm, including:

[0127] An initial population is generated, including a plurality of effective individuals;

[0128] The dispersion degree value and the average correlation degree of the individuals in the current population are calculated, and it is determined whether the current population meets the convergence condition. If yes, a decoding operation is performed on the best individual to obtain a target allocation relationship, and an allocation result detail table is output according to the target allocation relationship to describe the allocation relationship between the workstations to be allocated and the orders to be allocated.

[0129] If the convergence condition is not met, a population operation is performed on the current population, and selection, crossover and mutation are performed until the convergence condition is met.

[0130] The embodiment of the present application also provides an order allocation device for a warehouse multi-station, including a memory and a processor. The memory is configured to store instructions. The processor is configured to call the instructions from the memory and can realize the order allocation method for the warehouse multi-station provided in any of the above embodiments when the instructions are executed.

[0131] The embodiment of the present application also provides a machine readable storage medium, which stores instructions for causing a machine to execute the order allocation method for the warehouse multi-station.

[0132] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system or a computer program product. Therefore, the present application can adopt a completely hardware embodiment, a completely software embodiment or an embodiment combining software and hardware aspects. Moreover, the present application can adopt a computer program product in the form of one or more computer usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer usable program codes.

[0133] The present application is described with reference to the flowcharts and / or block diagrams of the method, equipment (system), computer program product according to the embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of the flows and / or blocks in the flowcharts and / or block diagrams can be realized by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing equipment to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing equipment produce a method for realizing the functions described in the flowcharts and / or block diagrams.Figure 1 one or more processes and / or blocks Figure 1 means for performing the function specified by the block or blocks.

[0134] These computer program instructions can also be stored in a computer- readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instructions which implement the Figure 1 one or more processes and / or blocks Figure 1 means for performing the function specified by the block or blocks.

[0135] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the Figure 1 one or more processes and / or blocks Figure 1 means for performing the function specified by the block or blocks.

[0136] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0137] The memory can include non-persistent memory and / or volatile memory, such as random access memory (RAM) and / or cache memory. The memory can also include non-volatile memory, such as read-only memory (ROM), electrically programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), flash memory, or other non-volatile memory. Memory is an example of computer-readable media.

[0138] Computer-readable media includes permanent and non-permanent, removable and non-removable media implemented in any method or technology for storage of information such as 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 programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile discs (DVDs) or other optical storage, magnetic cassettes, magnetic disks storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information accessible to a computing device. According to the definition herein, computer-readable media does not include transitory media, such as modulated data signals and carrier waves.

[0139] It should also be noted that the terms "comprising", "comprises" or other variations thereof are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but can also include other elements not expressly listed or inherent to such process, method, article, or apparatus.

[0140] The above embodiments are only used to illustrate the present application, but not to limit it. Instead of the above, various modifications and changes can be made to the application by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the application shall fall into the scope of the claims of the application.

Claims

1. A method for order allocation for a warehoused multi-station, characterized by, The method comprises: obtaining to-be-assigned order information of a plurality of to-be-assigned orders, existing order information of a plurality of existing orders of a plurality of to-be-assigned workstations, and historical goods categories of historical picking orders of the workstations, wherein the to-be-assigned order information comprises order goods categories and order goods quantities, and the existing order information comprises existing goods categories and existing goods quantities; determining a target assignment relationship between the plurality of to-be-assigned workstations and the plurality of to-be-assigned orders by a multi-objective genetic algorithm according to the to-be-assigned order information, the existing order information, and the historical goods categories, wherein an optimization objective of the multi-objective genetic algorithm comprises minimization of a goods quantity dispersion degree value of the plurality of to-be-assigned workstations and maximization of an average value of correlation degrees of respective goods categories of the plurality of to-be-assigned workstations, the goods quantity dispersion degree value is determined according to the order goods quantities and the existing goods quantities, and the correlation degree of the goods category is determined according to the historical goods categories, the order goods categories, and the existing goods categories; wherein the correlation degree of the goods category refers to, for each to-be-assigned workstation, a to-be-processed goods category of an existing order of the to-be-assigned workstation and a goods category of a to-be-assigned order being placed together to obtain a goods type set, and a set number of various goods type combination subsets in the goods type set appearing in the historical picking orders of the workstations being higher than a certain value; wherein each goods category is an element in the goods type set, an element in the goods type set is selected to obtain a goods type combination subset, and each goods type combination subset corresponds to a goods category combination; the step of determining the correlation degree of the goods category comprises: determining a frequency of the goods category combination expressed by each goods type combination subset appearing in the historical picking orders of the workstations; in a case where the frequency is greater than or equal to a preset appearance frequency threshold, determining that the goods category combination expressed by the goods type combination subset is a frequent set; determining a number of the frequent set in the goods type set corresponding to the to-be-assigned workstation as the correlation degree of the goods category corresponding to the to-be-assigned workstation; wherein each to-be-assigned workstation can obtain a set number of various goods type combination subsets appearing with a frequency higher than a certain value as the correlation degree of the goods category between the to-be-assigned workstation and the to-be-assigned order; the historical picking orders of the workstations record combinations of historical goods categories of historical picking orders.

2. The method of claim 1, wherein, The step of determining the assignment relationship between the plurality of to-be-assigned workstations and the plurality of to-be-assigned orders by the multi-objective genetic algorithm according to the to-be-assigned order information, the existing order information, and the historical goods categories comprises: establishing a population with a plurality of individuals according to the plurality of to-be-assigned orders and the plurality of to-be-assigned workstations, wherein each individual is used to represent an assignment relationship between the plurality of to-be-assigned orders and the plurality of to-be-assigned workstations; determining a goods quantity dispersion degree value corresponding to each individual according to the order goods quantity and the existing goods quantity corresponding to each individual; determine the average correlation degree of each individual according to the historical goods category, the order goods category and the existing goods category corresponding to each individual; perform a population updating operation on the population according to the goods quantity dispersion degree value and the average correlation degree of each individual in the population based on the optimization target until a preset convergence condition is met to obtain a final population; take any individual in the final population as the target allocation relationship.

3. The method of claim 2, wherein, The dispersion degree value includes a standard deviation, and the determination of the goods quantity dispersion degree value of each individual according to the order goods quantity and the existing goods quantity of each individual includes: determine the average existing goods quantity of the plurality of to-be-allocated workstations according to the existing goods quantity of each of the plurality of to-be-allocated workstations; determine the standard deviation corresponding to the individual when the plurality of to-be-allocated orders are allocated to the plurality of to-be-allocated workstations according to the individual.

4. The method of claim 2, wherein, The determination of the average correlation degree of each individual according to the historical goods category, the order goods category and the existing goods category corresponding to each individual includes: for each to-be-allocated workstation in each individual, determine the union of the existing goods category and the order goods category corresponding to each to-be-allocated workstation in each individual to obtain a goods type set corresponding to each to-be-allocated workstation; determine the number of frequent goods combination subsets in each goods type set; wherein the frequent goods combination subset is a goods combination subset in the goods type set whose occurrence frequency in the historical picking order is greater than a preset frequency threshold; determine the goods category correlation degree corresponding to the plurality of to-be-allocated workstations in each individual according to the number of frequent goods combination subsets in each goods type set in each individual; determine the average correlation degree of each individual according to the goods category correlation degree corresponding to the plurality of to-be-allocated workstations in each individual.

5. The method of claim 2, wherein, The population updating operation on the population based on the optimization target according to the goods quantity dispersion degree value and the average correlation degree of each individual in the population until a preset convergence condition is met to obtain a final population includes: perform non-dominated sorting on the individuals in the population based on the optimization target; select a target number of individuals in the front of the non-dominated sorting as parents; perform crossover operation and mutation operation on the parents to obtain a new population; perform non-dominated sorting on the individuals in the new population based on the optimization target until a preset convergence condition is met to obtain a final population in the case that the preset convergence condition is not met.

6. The method of claim 1, wherein, Before the obtaining of the to-be-allocated order information of the plurality of to-be-allocated orders, the method further includes: obtain the order cancellation time corresponding to each of a plurality of existing orders and a preset priority of the plurality of existing orders; According to the cut-off time and the preset priority, a comprehensive priority of the plurality of existing orders is determined; wherein the comprehensive priority of the existing order with the earlier cut-off time is higher; According to the comprehensive priority and the total remaining amount of the plurality of distributable workstations, the plurality of to-be-distributed orders is obtained.

7. The method of claim 6, wherein, The obtaining of the plurality of to-be-distributed orders according to the comprehensive priority and the total remaining amount of the plurality of distributable workstations comprises: According to the comprehensive priority, all the existing orders within the comprehensive priority are sequentially intercepted from the highest comprehensive priority; In the case of intercepting all the existing orders of the comprehensive priority, it is judged whether the total number of intercepted orders is greater than or equal to the total remaining amount of the distributable orders; In the case that the total number of intercepted orders is greater than or equal to the total remaining amount of the distributable orders, the interception of existing orders is stopped, and the plurality of existing orders that have been intercepted are taken as the plurality of to-be-distributed orders; In the case that the total number of intercepted orders is less than the total remaining amount of the distributable orders, all the existing orders of the next comprehensive priority are continuously intercepted.

8. The method of claim 7, wherein, The determination of the allocation relationship between the plurality of to-be-distributed workstations and the plurality of to-be-distributed orders according to the to-be-distributed order information, the existing order information and the historical goods category by the multi-objective genetic algorithm comprises: According to the plurality of to-be-distributed orders and the plurality of to-be-distributed workstations, a population with a plurality of individuals is established; wherein each individual is used to represent an allocation relationship between the plurality of to-be-distributed orders and the plurality of to-be-distributed workstations; Each individual has a constraint condition: each to-be-distributed order is allocated to one to-be-distributed workstation; the number of to-be-distributed orders allocated to each to-be-distributed workstation does not exceed the remaining amount of distributable orders of the to-be-distributed workstation; the number of to-be-distributed orders that need to be allocated in the lowest comprehensive priority is the number difference between the total remaining amount of distributable orders and the total number of to-be-distributed orders of the remaining comprehensive priorities; According to the order goods quantity and the existing goods quantity corresponding to each individual, the goods quantity dispersion degree value corresponding to each individual is determined; According to the historical goods category, the order goods category and the existing goods category corresponding to each individual, the average correlation degree value corresponding to each individual is determined; Based on the optimization target, the population is subjected to a population updating operation according to the goods quantity dispersion degree value and the average correlation degree value corresponding to each individual in the population, until a preset convergence condition is met, to obtain a final population; Any individual in the final population is taken as the target allocation relationship.

9. The method of claim 5, wherein, In the case that the preset convergence condition is not met, the individuals in the new population are subjected to a non-dominated sorting according to the optimization target, until the preset convergence condition is met, comprising: In the case that the iteration number of the population does not reach a preset iteration threshold, the individuals in the new population are subjected to a non-dominated sorting according to the optimization target, until the iteration number of the population reaches the preset iteration threshold; Or, in the case that the variation range of the dispersion degree and / or the average correlation degree is greater than or equal to a preset range, the individuals in the new population are non-dominantly sorted according to the optimization target until the variation range of the dispersion degree and / or the average correlation degree is less than the preset range.

10. An order-picking device for a warehouse multi-station, characterized in that, Comprising: a memory configured to store instructions; a processor configured to call the instructions from the memory and enable the order allocation method for warehouse multi-stations according to any one of claims 1-9 when the instructions are executed.

11. A machine-readable storage medium, characterized in that, The machine readable storage medium has instructions stored thereon for causing a machine to perform the order allocation method for warehouse multi-stations according to any one of claims 1-9.

Images