Method, processor and machine-readable storage medium for shelf hit

Abstract

The present application discloses a method, processor and machine-readable storage medium for shelf hit, belonging to the field of intelligent warehousing technology, the method comprising: obtaining order information of an order to be picked and inventory information of a current cargo warehouse; encoding and generating multiple individuals according to preset encoding rules based on the order information and inventory information to obtain an initial population, the number of chromosomes of each individual equals the number of cargo types of the order to be picked, and the number of gene bits of each chromosome equals the total number of cargo compartments in the current cargo warehouse; based on a multi-objective genetic algorithm, determining a target individual according to the initial population and a pre-constructed fitness function, the fitness function is constructed according to a preset evaluation dimension; determining the hit result corresponding to the target individual as the target hit result of the order to be picked. The present application adopts a multi-objective genetic algorithm to determine the target hit result of the order to be picked, and encodes according to the cargo type of the order to be picked and the total number of cargo compartments in the cargo warehouse, with high flexibility.

Description

Technical Field

[0001] The present application relates to the field of intelligent warehousing technology, and in particular to a method, a processor, and a machine-readable storage medium for shelf matching. Background Art

[0002] In an automated warehousing system, picking is a key link to ensure that orders are accurate and delivered in a timely manner. The automated picking system can significantly improve processing speed, reduce picking errors, reduce labor intensity, and optimize warehouse space utilization, ultimately improving the efficiency of the entire supply chain. The "hitting the shelf" link refers to calculating the set of shelves that need to be called based on the goods information and shelf inventory information required by the order, and then the automated equipment is responsible for moving the shelves in the warehouse to the picking warehouse for picking. The order-hitting-shelf method used in the prior art is mainly aimed at the static order picking mode, that is, for a single order, while for a group wave order, it needs to be decomposed into individual orders and solved one by one, which has low flexibility. Therefore, the order-hitting-shelf method used in the prior art for picking goods has the problem of low flexibility. Summary of the invention

[0003] The purpose of the embodiments of the present application is to provide a method, processor and machine-readable storage medium for shelf matching, so as to solve the problem that the method for matching orders to shelves used in the prior art has a small scope of application.

[0004] In order to achieve the above-mentioned purpose, the first aspect of the embodiment of the present application provides a method for shelf hit, the method comprising:

[0005] Get the order information of the order to be picked and the inventory information of the current goods warehouse. The order information includes the type and picking quantity of each order to be picked, and the inventory information includes the shelf number, shelf number, type and inventory quantity of the goods in the shelf.

[0006] According to the order information and inventory information, multiple individuals are encoded according to the preset encoding rules to obtain the initial population. Each individual corresponds to a hit result. The number of chromosomes of each individual is equal to the number of types of goods in the order to be picked, and the number of gene bits of each chromosome is equal to the total number of cargo compartments in the current cargo warehouse;

[0007] Based on the multi-objective genetic algorithm, the target individual is determined according to the initial population and the pre-constructed fitness function, and the fitness function is constructed according to the preset evaluation dimensions;

[0008] The hit result corresponding to the target individual is determined as the target hit result of the order to be picked, and the target hit result includes the target shelf number and the target cargo compartment number.

[0009] In an embodiment of the present application, the preset evaluation dimension includes a hit shelf number dimension, and the hit shelf number dimension includes the number of hit shelves corresponding to each individual.

[0010] In the embodiment of the present application, the preset evaluation dimension includes an validity period dimension, and the validity period dimension includes the average validity period of the inventory goods of each individual hit.

[0011] In the embodiment of the present application, the preset evaluation dimension includes a shelf distance dimension, which is the sum of the distances from each shelf hit by each individual to the picking workstation.

[0012] In an embodiment of the present application, when the number of preset evaluation dimensions is at least two, the construction of the fitness function includes: constructing the fitness function according to each preset evaluation dimension and a preset weight value corresponding to each preset evaluation dimension.

[0013] In an embodiment of the present application, a chromosome of each individual corresponds to a cargo type of an order to be picked, and the gene bits of each chromosome correspond one-to-one to the cargo grids in the cargo warehouse. According to the order information and inventory information, encoding is performed according to preset encoding rules to generate multiple individuals, including: based on binary encoding, each chromosome is initialized according to the inventory information, the gene bits corresponding to the hit cargo grids are initialized to 1, and the gene bits corresponding to the remaining cargo grids are initialized to 0, and the hit cargo grids are cargo grids whose cargo types of the inventory goods are the same as the cargo types corresponding to each chromosome; real number encoding is performed on the gene bits encoded as 1 in each initialized chromosome to generate random numbers to obtain individuals; multiple individuals are generated by performing real number encoding on each initialized chromosome multiple times.

[0014] In an embodiment of the present application, multiple individuals are encoded according to preset coding rules based on order information and inventory information to obtain an initial population, including: out-of-stock detection is performed based on the order information and inventory information to determine whether there is a shortage of goods; if there is no shortage of goods, multiple individuals are encoded according to preset coding rules based on the order information and inventory information to obtain an initial population.

[0015] In an embodiment of the present application, the order information also includes an order number, and the method also includes: when there is a shortage of goods, outputting the order number of the order to be picked and a reminder of the shortage of goods.

[0016] In an embodiment of the present application, out-of-stock detection is performed based on order information and inventory information to determine whether there is a shortage of goods, including: determining, based on the inventory information, the total inventory quantity of inventory goods in the goods warehouse that are the same type as the goods corresponding to the goods to be picked in the order information; comparing the picking quantity of each goods to be picked with the corresponding total inventory quantity; if the picking quantity of any goods to be picked is greater than the corresponding total inventory quantity, determining that there is a shortage of goods; if the picking quantity of each goods to be picked is less than or equal to the corresponding total inventory quantity, determining that there is no shortage of goods.

[0017] In an embodiment of the present application, a method for determining a hit result corresponding to an individual includes: according to order information, inventory information, and the encoding size of the gene position of each chromosome of the individual, sequentially hitting the cargo cells corresponding to the gene positions in a preset order until the number of hit goods meets the requirements of the order to be picked, so as to obtain multiple hit cargo cells; determining a hit shelf according to the inventory information and multiple hit cargo cells, so as to obtain a hit result corresponding to the individual.

[0018] A second aspect of an embodiment of the present application provides a processor configured to execute the above-mentioned method for shelf hitting.

[0019] A third aspect of an embodiment of the present application provides a machine-readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, the above-mentioned method for shelf hit is implemented.

[0020] The above technical scheme obtains the order information of the order to be picked and the inventory information of the current cargo warehouse, the order information includes the cargo type and picking quantity of each cargo to be picked, and the inventory information includes the shelf number, the compartment number, the cargo type of the inventory cargo in the compartment, and the inventory quantity, and then encodes multiple individuals according to the preset encoding rules based on the order information and the inventory information to obtain an initial population, each individual corresponds to a hit result, the number of chromosomes of each individual is equal to the number of cargo types of the order to be picked, and the number of gene bits of each chromosome is equal to the total number of compartments in the current cargo warehouse, and further, based on the multi-objective genetic algorithm, the target individual is determined according to the initial population and the pre-constructed fitness function, and the fitness function is constructed according to the preset evaluation dimension, and finally, the hit result corresponding to the target individual is determined as the target hit result of the order to be picked, and the target hit result includes the target shelf number and the target compartment number. The present application adopts a multi-objective genetic algorithm to determine the target hit results of the orders to be picked, and encodes them according to the cargo type of the orders to be picked and the total number of cargo compartments in the cargo warehouse, which has high flexibility. Since the target hit results finally obtained by the present application include the target shelf number and the target cargo compartment number, the present application can implement the optimal cargo picking strategy with fine-grained specificity to the shelves and cargo compartments for cargo picking tasks.

[0021] 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

[0022] 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:

[0023] Figure 1 A flowchart of a method for shelf hitting provided in an embodiment of the present application;

[0024] Figure 2 A flowchart of a method for order matching to shelves based on a multi-objective optimization algorithm provided in a specific embodiment of the present application;

[0025] Figure 3 A structural block diagram of a device for shelf hit provided in an embodiment of the present application. DETAILED DESCRIPTION

[0026] 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.

[0027] 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.

[0028] 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.

[0029] Figure 1 A flowchart of a method for shelf targeting provided in an embodiment of the present application is shown below. Figure 1 As shown, an embodiment of the present application provides a method for shelf hit, which is described by taking the method applied to a processor as an example. The method may include the following steps.

[0030] Step S101, obtaining order information of orders to be picked and inventory information of the current goods warehouse, the order information includes the type and picking quantity of each order to be picked, and the inventory information includes the shelf number, the shelf number, the type and inventory quantity of the goods in the shelf.

[0031] In an embodiment of the present application, for the convenience of calculation, both the order information and the inventory information can be stored in a table. For example, the order information can be an order information table, and each table item in the order information table includes the type of goods to be picked and the picking quantity, wherein the picking quantity is the required quantity of the goods. In one example, the inventory information can be an inventory information table, and each table item in the inventory information table includes a shelf number, a compartment number, the type of goods in stock in the compartment, and the inventory quantity. In another example, the inventory information may include a shelf status table and multiple shelf inventory information tables, wherein, to facilitate the determination of the status of each shelf, each table item in the shelf status table may include a shelf number and a shelf status. The shelf inventory information table may include the compartment number of each compartment in the shelf, the type of goods in stock in the compartment, and the inventory quantity. In this way, a data basis is provided for subsequent shelf hits.

[0032] Step S102: Based on the order information and inventory information, multiple individuals are encoded according to preset encoding rules to obtain an initial population. Each individual corresponds to a hit result. The number of chromosomes of each individual is equal to the number of cargo types of the order to be picked, and the number of gene bits of each chromosome is equal to the total number of cargo compartments in the current cargo warehouse.

[0033] In the embodiment of the present application, in order to quickly determine the target hit shelf of the order to be picked, the embodiment of the present application adopts a genetic algorithm for solving. Specifically, according to the order information and the inventory information, encoding is performed according to the preset encoding rules to generate multiple individuals, thereby obtaining an initial population. Among them, the preset encoding rules can be binary encoding rules and real number encoding rules. For the convenience of solving, when encoding, the goods to be picked of each type of goods in the order to be picked are encoded corresponding to a chromosome, that is, the number of chromosomes contained in the generated individual is equal to the number of goods types contained in the order to be picked. At the same time, considering that there may be shelves of various specifications in the goods warehouse, when encoding, the gene length of the chromosome is set to the total number of cargo grids in the current goods warehouse, that is, the sum of the cargo grids contained in all shelves. In addition, the gene position in the chromosome is matched one by one with the cargo grid in the warehouse, that is, one gene position can locate a piece of inventory data, including the shelf number, the cargo grid number, the cargo type and the inventory quantity of the goods in the cargo grid. It can be understood that each individual corresponds to a hit result, that is, a potential solution. Among them, the hit result corresponding to each individual includes a hit shelf and a hit cargo grid.

[0034] Step S103: Based on a multi-objective genetic algorithm, a target individual is determined according to the initial population and a pre-constructed fitness function, wherein the fitness function is constructed according to a preset evaluation dimension.

[0035] In the embodiment of the present application, in order to optimize the order hit result, the embodiment of the present application adopts a multi-objective genetic algorithm for solving. After obtaining the initial population, the target individual can be determined based on the multi-objective genetic algorithm and the pre-constructed fitness function. Among them, the fitness function can be constructed according to the preset evaluation dimension, and the preset evaluation dimension can include at least one of the hit shelf number dimension, the validity period dimension, and the shelf distance dimension.

[0036] Specifically, based on the multi-objective genetic algorithm, the individuals of the initial population are used as the mother to perform operations such as gene crossover and gene mutation, and multiple offspring can be obtained. Non-dominated sorting and crowding calculation are performed on each offspring, and the fitness value of each offspring is calculated according to the fitness function. Then, excellent individuals are retained according to the fitness value and gene selection strategy to obtain a new population. Iterate multiple times until the algorithm converges. In one example, a preset number of iterations can be set. After reaching the preset number of iterations, the individual with the maximum fitness value in the offspring is determined as the target individual. In another example, a preset fitness value can be set. After the fitness value of any offspring exceeds the preset fitness value, the iteration is stopped, and the individual with the maximum fitness value in the offspring and exceeding the preset fitness value is determined as the target individual. In another example, after iterating the preset number of iterations according to the multi-objective genetic algorithm or reaching the preset termination condition, a set of Pareto optimal solution sets is obtained, and then the target solution is selected in the Pareto optimal solution set according to the preset evaluation dimension and the fitness function. The individual for which the target solution is the target individual. In this way, the target individual, i.e., the target solution, can be quickly determined while considering the preset evaluation dimension. In addition, encoding based on the order information and inventory information of the orders to be picked is more flexible and can be applied to various types of orders and shelves of different specifications.

[0037] Step S104: determine the hit result corresponding to the target individual as the target hit result of the order to be picked, and the target hit result includes the target shelf number and the target cargo compartment number.

[0038] In the embodiment of the present application, after the target individual is determined, the hit result corresponding to the target individual is the target hit result of the order to be picked. The target hit result includes the target shelf number of the target hit shelf and the target compartment number of the target hit compartment in the target hit shelf.

[0039] The above technical scheme obtains the order information of the order to be picked and the inventory information of the current cargo warehouse, the order information includes the cargo type and picking quantity of each cargo to be picked, and the inventory information includes the shelf number, the compartment number, the cargo type of the inventory cargo in the compartment, and the inventory quantity, and then encodes multiple individuals according to the preset encoding rules based on the order information and the inventory information to obtain an initial population, each individual corresponds to a hit result, the number of chromosomes of each individual is equal to the number of cargo types of the order to be picked, and the number of gene bits of each chromosome is equal to the total number of compartments in the current cargo warehouse, and further, based on the multi-objective genetic algorithm, the target individual is determined according to the initial population and the pre-constructed fitness function, and the fitness function is constructed according to the preset evaluation dimension, and finally, the hit result corresponding to the target individual is determined as the target hit result of the order to be picked, and the target hit result includes the target shelf number and the target compartment number. The present application adopts a multi-objective genetic algorithm to determine the target hit results of the orders to be picked, and encodes them according to the cargo type of the orders to be picked and the total number of cargo compartments in the cargo warehouse, which has high flexibility. Since the target hit results finally obtained by the present application include the target shelf number and the target cargo compartment number, the present application can implement the optimal cargo picking strategy with fine-grained specificity to the shelves and cargo compartments for cargo picking tasks.

[0040] In an embodiment of the present application, the preset evaluation dimension includes a hit shelf number dimension, and the hit shelf number dimension includes the number of hit shelves corresponding to each individual.

[0041] Specifically, in the process of picking goods, after the hit link is completed, the target hit shelf needs to be transported to the corresponding workstation by the transport robot so that the goods can be picked. In order to reduce the scheduling pressure of the transport robot and reduce the risk of congestion during the movement of the transport robot, the preset evaluation dimension in the embodiment of the present application may include a shelf hit number dimension, that is, a fitness function is constructed based on the shelf hit number dimension. Among them, the shelf hit number dimension includes the number of hit shelves corresponding to each individual, that is, according to the shelf number of the hit shelf in the hit result corresponding to the individual, the number of hit shelves of the individual can be obtained through deduplication processing. In this way, considering optimizing the number of hit shelves, reducing the scheduling pressure of the transport robot, and at the same time improving the efficiency of subsequent picking.

[0042] In the embodiment of the present application, the preset evaluation dimension includes an validity period dimension, and the validity period dimension includes the average validity period of the inventory goods of each individual hit.

[0043] It can be understood that the first-in-first-out (FIFO) principle is crucial in inventory management, especially when dealing with perishable goods or items with a shelf life. In order to reduce losses, the preset evaluation dimension of the embodiment of the present application may include an expiration date dimension, that is, a fitness function is constructed based on the expiration date. Among them, the expiration date refers to the average expiration date of the inventory goods of all the shelves hit in the individual hit results. In one example, the inventory information may also include the shelf expiration date of each shelf, and the shelf expiration date is the average expiration date of the inventory goods in the shelf. Preferably, the operating scenario of the present application is that the goods are stored in batches in the shelving link, and the goods of the same type and the same month of production date are one batch. According to the rule of "one product, one place", goods of different batches do not support mixing. For the same batch of inventory goods stored in each shelf, for the convenience of calculation, the shelf expiration date can be the difference between the shelf expiration month and the current month of the inventory goods stored in the shelf.

[0044] In this way, by constructing a fitness function based on the validity period, we can prioritize goods with a near validity period according to the first-in-first-out principle, ensuring that the goods that were put on the shelves first are picked first, which can not only reduce expiration losses, but also improve picking efficiency. By giving priority to the FIFO principle when hitting the shelves, we can effectively optimize the picking process and reduce losses caused by expired goods.

[0045] In the embodiment of the present application, the preset evaluation dimension includes a shelf distance dimension, which is the sum of the distances from each shelf hit by each individual to the picking workstation.

[0046] It can be understood that the transport distance of the transport robot to transport the shelf is also an important factor affecting the efficiency of cargo picking. In order to optimize the transport distance of the shelf, the preset evaluation dimension in the embodiment of the present application may include the shelf transport distance dimension, that is, a fitness function is constructed according to the shelf transport distance dimension. Among them, the shelf distance dimension includes the sum of the distances from each cargo compartment hit by each individual to the picking workstation. In this way, by constructing a fitness function through the shelf distance, the shelves can be reasonably arranged, and the moving distance of the AMR between the shelves can be shortened, which is conducive to improving the picking speed and reducing the possibility of traffic jams. By optimizing the arrangement and layout of the shelves, combined with the intelligent scheduling system, more efficient picking operations can be achieved to ensure smooth logistics operations under high demand conditions.

[0047] In an embodiment of the present application, when the number of preset evaluation dimensions is at least two, the construction of the fitness function includes: constructing the fitness function according to each preset evaluation dimension and a preset weight value corresponding to each preset evaluation dimension.

[0048] Specifically, in order to optimize the shelf hit result, multiple influencing factors are considered, and the preset evaluation dimensions can be multiple, for example, the hit shelf number dimension and / or the validity period dimension and / or the shelf distance dimension. When the number of preset evaluation dimensions is at least two, a fitness function can be constructed according to each preset evaluation dimension and the preset weight value corresponding to each preset evaluation dimension. In one example, the fitness function can be constructed by weighted summing each preset evaluation dimension.

[0049] In one example, the preset weight values ​​corresponding to the preset evaluation dimensions can be set according to the needs of the user, and the processor can adjust the preset weight values ​​corresponding to the preset evaluation dimensions in response to the user's input. In this way, the fitness function can be adjusted according to the actual application scenario, and the target hit result corresponding to the scenario can be output, which is more flexible and conducive to improving the user experience.

[0050] In an embodiment of the present application, a chromosome of each individual corresponds to a cargo type of an order to be picked, and the gene bits of each chromosome correspond one-to-one to the cargo grids in the cargo warehouse. According to the order information and inventory information, encoding is performed according to preset encoding rules to generate multiple individuals, including: based on binary encoding, each chromosome is initialized according to the inventory information, the gene bits corresponding to the hit cargo grids are initialized to 1, and the gene bits corresponding to the remaining cargo grids are initialized to 0, and the hit cargo grids are cargo grids whose cargo types of the inventory goods are the same as the cargo types corresponding to each chromosome; real number encoding is performed on the gene bits encoded as 1 in each initialized chromosome to generate random numbers to obtain individuals; multiple individuals are generated by performing real number encoding on each initialized chromosome multiple times.

[0051] It can be understood that, for the convenience of calculation, the embodiment of the present application adopts a combination of binary coding and real number coding to obtain the initial population. In the embodiment of the present application, the number of chromosomes of each individual is the same as the number of types of goods in the order to be picked, the gene length of each chromosome is the same as the total number of cargo compartments in the cargo warehouse, and each gene position of the chromosome corresponds to the cargo compartment in the cargo warehouse. Specifically, taking the chromosome z corresponding to the cargo type z as an example, for chromosome z, it is first initialized based on binary coding, and the gene corresponding to the cargo compartment of the stored inventory goods of the cargo type z is initialized to 1, and the remaining gene positions are initialized to 0. Then, the gene position encoded as 1 in the initialized chromosome is generated by the real number coding method to obtain the chromosome z after the encoding is completed. At this time, the gene of the cargo compartment corresponding to the cargo type z of the inventory goods in the chromosome z is encoded as a random real number, and the rest is 0. Similarly, the encoding of all chromosomes is completed, that is, an individual is obtained. The above encoding method is used to randomly generate multiple groups of random numbers, that is, multiple individuals are obtained to form an initial population. The encoding method adopted in the embodiment of the present application can be applied to shelves of different specifications, with high flexibility.

[0052] In an embodiment of the present application, a method for determining a hit result corresponding to an individual includes: according to order information, inventory information, and the encoding size of the gene position of each chromosome of the individual, sequentially hitting the cargo cells corresponding to the gene positions in a preset order until the number of hit goods meets the requirements of the order to be picked, so as to obtain multiple hit cargo cells; determining a hit shelf according to the inventory information and multiple hit cargo cells, so as to obtain a hit result corresponding to the individual.

[0053] It can be understood that each individual is a potential solution. In the application scenario of the present application, each individual corresponds to a hit result, and the hit result is the solution corresponding to the individual. Since the embodiment of the present application is applied to the shelf hitting link in the cargo picking scenario, the purpose is to hit the shelves and cargo grids. Specifically, for each individual, the cargo grids corresponding to the gene positions can be hit in sequence according to the encoding size of the genes of each chromosome in a preset order. The preset order can include a descending order or an ascending order. In this way, the cargo grids are hit in sequence until the needs of the order to be picked are met.

[0054] Since one chromosome of an individual in the embodiment of the present application corresponds to a type of goods to be picked, a hit can be performed in units of one type of goods. For example, taking the goods to be picked z of the goods type z in the order to be picked as an example, the corresponding chromosome z hits the cargo grid corresponding to the gene position in sequence according to the order of gene coding from small to large, and at the same time calculates the total inventory number of the hit according to the inventory quantity of the inventory goods z corresponding to the cargo grid. When the total inventory number of the hit is greater than or equal to the picking quantity of the goods z to be picked, the hit is stopped to obtain multiple hit cargo grids. Similarly, the hit cargo grids of each to-be-picked goods in the order to be picked can be determined, thereby obtaining the hit cargo grid set of the order to be picked. Further, based on the inventory information, the corresponding hit shelf is determined according to the cargo grid number of each hit cargo grid in the hit cargo grid set, thereby obtaining the hit result corresponding to the individual. In this way, the hit result corresponding to each individual can be quickly determined.

[0055] In the embodiment of the present application, for any individual, the number of hit shelves, average effectiveness, and total shelf distance corresponding to the individual can be calculated based on the hit result of the individual, that is, the corresponding hit shelf number dimension, validity period dimension, and shelf distance dimension. Further, according to the fitness function, the fitness value of the individual can be determined based on the hit result of the individual, and then used to evaluate the pros and cons of the individual. Provide a data basis for the subsequent determination of the target hit result of the order to be picked.

[0056] In an embodiment of the present application, multiple individuals are encoded according to preset coding rules based on order information and inventory information to obtain an initial population, including: out-of-stock detection is performed based on the order information and inventory information to determine whether there is a shortage of goods; if there is no shortage of goods, multiple individuals are encoded according to preset coding rules based on the order information and inventory information to obtain an initial population.

[0057] It is understandable that, considering the limited inventory of goods in the goods warehouse, there may be a shortage of goods. In order to prevent invalid calculations, before encoding and generating multiple individuals according to the preset encoding rules based on the order information and inventory information, the processor can perform a shortage detection based on the order information of the order to be picked and the inventory information of the current goods warehouse to determine whether there is a shortage of goods for the order to be picked. If the shortage detection is satisfied, that is, there is no shortage of goods, the operation of encoding and generating multiple individuals according to the preset encoding rules based on the order information and inventory information is continued.

[0058] In an embodiment of the present application, the order information also includes an order number, and the method also includes: when there is a shortage of goods, outputting the order number of the order to be picked and a reminder of the shortage of goods.

[0059] It is understood that the order information also includes the order number of the order to be picked. If the out-of-stock detection is not met, that is, the goods are out of stock, in order to avoid invalid calculations, the system can directly output the order number of the order to be picked and the out-of-stock reminder of the goods. This reminds the staff to replenish the goods in time or remove the out-of-stock goods.

[0060] In an embodiment of the present application, out-of-stock detection is performed based on order information and inventory information to determine whether there is a shortage of goods, including: determining, based on the inventory information, the total inventory quantity of inventory goods in the goods warehouse that are the same type as the goods corresponding to the goods to be picked in the order information; comparing the picking quantity of each goods to be picked with the corresponding total inventory quantity; if the picking quantity of any goods to be picked is greater than the corresponding total inventory quantity, determining that there is a shortage of goods; if the picking quantity of each goods to be picked is less than or equal to the corresponding total inventory quantity, determining that there is no shortage of goods.

[0061] Specifically, when the processor performs out-of-stock detection, it can determine the total inventory quantity of each to-be-picked goods in the to-be-picked order in the current goods warehouse based on the same goods type and inventory information, and then compare the picking quantity of each to-be-picked goods with the corresponding total inventory quantity. If the picking quantity of the to-be-picked goods in the to-be-picked order is greater than the total inventory quantity, it means that the to-be-picked goods are out of stock, that is, it is determined that there is a shortage of goods. If the picking quantity of each to-be-picked goods in the to-be-picked order is less than or equal to the total inventory quantity, it means that the inventory in the current goods warehouse can meet the needs of the to-be-picked order, and it is determined that there is no shortage of goods.

[0062] In a specific embodiment of the present application, after an order is assigned to the current workstation, the operator will perform the box binding operation, and the warehouse execution system (WES) will automatically schedule the application shelf. A shelf has two sides, A / B. The shelf that has been hit but not picked is called an in-transit shelf. Only one side of the shelf can be picked at one entry. The in-transit shelf can be hit by one or two sides. If both sides of the shelf are hit, it is necessary to pick one side and then go around in front of the workstation and queue up to pick the other side. The shelf that is about to return to the warehouse or on the way back to the warehouse after picking is called the return shelf. The coordinates of the return shelf and the in-transit shelf are transmitted to the WES system in real time by the fusion interaction system (RCS). Figure 2 A flowchart of a method for order matching to a shelf based on a multi-objective optimization algorithm is provided in a specific embodiment of the present application. Figure 2 As shown, a specific embodiment of the present application provides a method for order matching shelves based on a multi-objective optimization algorithm, and the method may include the following steps:

[0063] S1. The workstation sends a request for a shelf.

[0064] S2. The picking-hitting-shelf algorithm is started and receives input data, including workstation information, shelf inventory information table, shelf status table, and order information table.

[0065] Specifically, for a system including multiple workstations, the workstation information includes the workstation location and the workstation number. Each entry in the shelf inventory information table includes the shelf number, the shelf number, the type of goods in the shelf, and the inventory quantity. Each entry in the shelf status table includes the shelf number and the shelf status, where the shelf status includes the in-transit status and the in-stock status. Each entry in the order information table includes the type of goods to be picked and the picking quantity.

[0066] S3, out-of-stock detection, determine whether there is a stock out of stock situation, if so, go to S12, otherwise go to S4.

[0067] S4. Calculate the hit area of ​​the in-transit shelves.

[0068] It can be understood that according to the shelf status table, it can be determined whether there is an in-transit shelf with a shelf status of in-transit. In order to reduce the number of shelf transfers, the in-transit shelves can be given priority. The in-transit shelf hit surface is calculated according to the order information table and the shelf inventory information table, and the cargo grid in the in-transit shelf is hit. After the hit, the shelf information table and order information table corresponding to the in-transit shelf are updated.

[0069] S5. Build mathematical models for the non-hit surfaces of in-transit shelves and in-stock shelves.

[0070] S6. Generate individuals through real number coding and binary coding and initialize the population.

[0071] S7, crossover operation, mutation operation.

[0072] S8, non-dominated sorting, congestion calculation.

[0073] S9. Calculation of adaptation value (number of hit shelves, validity period, shelf distance).

[0074] S10. Gene selection strategy retains excellent individuals.

[0075] S11, determine whether the iteration is finished, if so, go to S12, otherwise go to S7.

[0076] S12. Output the target hit result (including the actual hit result and the out-of-stock miss result).

[0077] It can be understood that a specific embodiment of the present application provides a method for order-to-shelf matching based on a multi-objective optimization algorithm. The aim is to transport the least number of shelves to meet the order to be picked, while considering the validity period obtained on the shelf and the total shelf distance of the hit shelf to construct a mathematical model, and use a multi-objective genetic algorithm (NSGA-II) to solve it. The real number coding and binary coding coding methods are used, which are more flexible and convenient for crossover and mutation operations. At the same time, it can be applied to shelves of different sizes for solving, and finally the optimal set of transported shelves is found. The method includes the following steps:

[0078] Step 1: Data preprocessing

[0079] The data input for the shelf picking process mainly includes: order information table of orders to be picked, workstation information, shelf inventory information table and shelf status information table.

[0080] According to the order information table of the order to be picked, an order dictionary sku_dict={sku i :num i}; Among them, sku i is the type of goods to be picked, num i The picking quantity corresponding to the goods to be picked of this type of goods.

[0081] In this operation scenario, goods are stored in batches during the shelf-loading process. Goods of the same type and with the same production date and month are considered one batch. According to the "one product, one place" rule, goods from different batches cannot be mixed. For ease of calculation, the validity period of a batch of inventory goods stored in each shelf is valid_time It is the difference between the goods expiration month and the current month.

[0082] Step 2: Out-of-stock detection

[0083] SKU of goods type in the recurring order dictionary i and picking quantity num i , filter the total inventory quantity of the same type of inventory stored in the inventory information table, and compare the total inventory quantity with the picking quantity num of the goods to be picked of the goods type i Compare to determine whether it is out of stock. If it is not out of stock, the order hits the shelf module. If it is out of stock, the prompt of out-of-stock goods and out-of-stock quantity is returned.

[0084] Step 3: Prioritize in-transit shelves

[0085] It can be understood that when the workstation is just opened, there is no in-transit shelf. As the order picking progresses, the shelf is hit by the previous order and becomes an in-transit shelf. When a new order is assigned to the workstation, in order to improve the picking efficiency, the inventory goods in the in-transit shelf can be hit first. If the in-transit shelf can meet the needs of the new order to be picked, the corresponding in-transit shelf will be directly used as the target hit shelf. If the in-transit shelf cannot fully meet the needs of the new order to be picked, it is necessary to enter the next step to hit the in-stock shelves, select the optimal shelf set, and update the shelf inventory information table of each target hit shelf and the order information table of the order to be picked.

[0086] Step 4: Build a mathematical model

[0087] Assume the total number of shelves is I, the shelf number is i, and each shelf has Suppose an order or a batch of orders has Z types of goods.

[0088] The mathematical model is constructed with the minimum number of hit shelves, the minimum average shelf life, and the shortest shelf distance as the objective function. Among them, the number of hit shelves refers to the number of shelves hit for the order to be picked, the average shelf life refers to the mean of the shelf life of the hit shelves, the shelf life refers to the mean of the shelf life of the goods hit on the shelves, and the shelf distance refers to the sum of the distances from each target hit shelf to the workstation. Specifically:

[0089] Number of hit shelves satisfy:

[0090] ;

[0091] Where P is the order i Total number of shelves available; i Whether to select shelf p, 。

[0092] Validity satisfy:

[0093] ;

[0094] in, represents minimization, is the shelf shelf life corresponding to the hit shelf, S is the set of the target hit shelves, S={ … }.

[0095] Shelf distance Can satisfy:

[0096] ;

[0097] in, are the coordinates of the workstation, are the coordinates of the shelf.

[0098] Step 5: Use multi-objective genetic algorithm to solve

[0099] The multi-objective genetic algorithm (NSGA-II) is a genetic algorithm based on the Pareto optimal concept. Compared with the weighted algorithm, NSGA-II can effectively handle nonlinear and non-convex multi-objective optimization problems and has strong global search capabilities.

[0100] 1. Individual encoding and decoding methods

[0101] According to the order-hitting-shelf model, let the total number of shelves be I, the shelf number be i, and each shelf has Suppose an order or a batch of orders has Z types of goods, then an individual has Z chromosomes, and the number of goods type z required is ,Gene The ij gene position of the zth chromosome corresponds to the jth slot in the shelf numbered i. The total length of the gene is J 1+ J 2+… J I, that is, the total length of the gene is equal to the sum of the cargo spaces of all shelves in the current cargo warehouse, that is, the total number of cargo spaces in the cargo warehouse, and the gene positions correspond to the cargo spaces one by one. Furthermore, binary coding is used to set the value of each gene to 0 or 1, that is, =0 or =1, 0 means that the cargo box corresponding to this gene position cannot be hit, 1 means that the inventory goods in the cargo box corresponding to this gene position can be hit, and the quantity of goods is Then, the gene bits with the encoding value of 1 in the initialized chromosome are coded by real numbers to generate random numbers. The initial population is obtained according to the above coding rules.

[0102] 2. Constructing fitness function

[0103] The fitness function is used to evaluate and compare the quality of individual solutions. The embodiment of the present application mainly considers the number of shelves hit, the average shelf life of goods, and the shelf distance to formulate the fitness function, with the minimization of the number of shelves hit, the priority of the approaching date, and the shortest shelf distance as the optimization goals, including:

[0104] (1) Minimize the number of shelves hit

[0105] ;

[0106] in: .

[0107] (2) Priority is given to those with a closer date

[0108] .

[0109] (3) The shelf is closest

[0110] The coordinates of the workstation are , Shelves i The coordinates of , Shelves i The distance to the workstation is satisfy:

[0111] ;

[0112] .

[0113] Constraints for hitting the shelf:

[0114] , z = {0 1…Z}; indicates that the quantity of item z hits needs to satisfy the quantity required for the order of item z.

[0115] Indicates shelf iWhether it was hit.

[0116] Decision variables For goods z shelf i The cargo space j Whether it was hit.

[0117] The fitness function can be constructed by weighted summation based on the above considerations.

[0118] 3. Generate initial solution

[0119] For each chromosome of each individual, sort the corresponding cells in ascending order of the gene bit values ​​until the constraint condition is met. , that is, if the number of hits of goods z in the order is greater than or equal to the order quantity, the remaining gene positions will no longer be hit, and the actual number of hits of the last hit gene position is the number to be picked minus the number that has been hit, but when establishing the mathematical model, all quantities are still used for calculation. Therefore, for the last shelf, when other conditions are the same, the shelf closer to the order quantity will be hit first, which can improve the utilization rate of the shelf and prevent the goods from being too dispersed due to picking.

[0120] 4. Solution process of multi-objective genetic algorithm

[0121] First, for the initial population, determine the hit results corresponding to each individual in the initial population, and then calculate the fitness of each individual through the fitness function based on the hit results. Then, perform crossover and mutation operations on the chromosomes z of the two individuals. Use the double-point crossover method to randomly select two crossover points, cut the chromosomes of the two parent individuals at these two points, and then exchange the cut fragments to generate two offspring individuals. Then use exchange mutation to randomly select two gene positions in a chromosome for exchange to generate new chromosomes and individuals.

[0122] The fitness value of the individual is calculated according to the fitness function, and then the new individuals in the population are stratified by non-dominated sorting with the individuals of the previous generation, and the individuals in the population are stratified according to the Pareto dominance relationship to form different frontiers. For the individuals in each frontier, their crowding distances on each target are calculated. For each target, the difference between the target values ​​of the adjacent individuals on the target is calculated, and then these differences are normalized. Finally, the normalized distances of all targets are added to obtain the total crowding distance of the individual. As shown below.

[0123] For each individual (j=1 2 … K), which in each target (i = 1 2 3) Crowding distance The calculation formula is:

[0124] ;

[0125] in, is on target The target value of the jth individual after sorting; and The targets are The minimum and maximum values ​​of , whose comprehensive crowding distance is the sum of the crowding distances on all targets: .

[0126] The crowding distance of some extreme values ​​(such as the maximum and minimum target values) is set to infinity. The elite strategy is used to select individuals with better fitness and larger crowding distance as the new population, and iterate until the algorithm converges to obtain a set of Pareto optimal solutions. Then, the optimal individual is selected from the Pareto optimal solution set based on the shelf satisfaction rate, validity period, and distance from the shelf to the workstation.

[0127] Step 6: Output results

[0128] The chromosome gene of the optimal individual calculated above is decoded. The last gene hit in the above iteration process will be marked, and the actual hit quantity is the quantity required for the order minus the number of goods in the cargo compartment that have been hit. The hit shelf number, the cargo compartment number in the shelf, and the specific hit quantity are sorted and sent to the WES system.

[0129] In summary, this method can be applied to both static order picking mode (single order) and dynamic order picking mode (group wave order). It uses a multi-objective genetic algorithm to solve the problem. The combination of binary coding and real number coding is more flexible and can be applied to shelves with different specifications.

[0130] An embodiment of the present application also provides a processor configured to execute the method for shelf hitting in the above-mentioned implementation.

[0131] Figure 3 The present invention also provides a device 300 for shelf hit, and the device 300 includes:

[0132] The data acquisition module 310 is used to obtain the order information of the orders to be picked and the inventory information of the current goods warehouse. The order information includes the type and picking quantity of each order to be picked, and the inventory information includes the shelf number, the shelf number, the type and inventory quantity of the goods in the shelf.

[0133] The population generation module 320 is used to encode and generate multiple individuals according to the order information and inventory information in accordance with the preset encoding rules to obtain an initial population. Each individual corresponds to a hit result. The number of chromosomes of each individual is equal to the number of cargo types of the order to be picked, and the number of gene bits of each chromosome is equal to the total number of cargo compartments in the current cargo warehouse.

[0134] The first determination module 330 is used to determine the target individual based on the multi-objective genetic algorithm according to the initial population and a pre-constructed fitness function, where the fitness function is constructed according to a preset evaluation dimension.

[0135] The second determination module 340 is used to determine the hit result corresponding to the target individual as the target hit result of the order to be picked, and the target hit result includes a target shelf number and a target cargo compartment number.

[0136] The above-mentioned device 300 for shelf hitting obtains the order information of the order to be picked and the inventory information of the current cargo warehouse, the order information includes the cargo type and picking quantity of each cargo to be picked, and the inventory information includes the shelf number, the compartment number, the cargo type of the cargo in the compartment, and the inventory quantity, and then encodes multiple individuals according to the order information and the inventory information according to the preset encoding rules to obtain an initial population, each individual corresponds to a hit result, the number of chromosomes of each individual is equal to the number of cargo types of the order to be picked, and the number of gene bits of each chromosome is equal to the total number of compartments in the current cargo warehouse. Furthermore, based on the multi-objective genetic algorithm, the target individual is determined according to the initial population and the pre-constructed fitness function, and the fitness function is constructed according to the preset evaluation dimension. Finally, the hit result corresponding to the target individual is determined as the target hit result of the order to be picked, and the target hit result includes the target shelf number and the target compartment number. The present application adopts a multi-objective genetic algorithm to determine the target hit results of the orders to be picked, and encodes them according to the cargo type of the orders to be picked and the total number of cargo compartments in the cargo warehouse, which has high flexibility. Since the target hit results finally obtained by the present application include the target shelf number and the target cargo compartment number, the present application can implement the optimal cargo picking strategy with fine-grained specificity to the shelves and cargo compartments for cargo picking tasks.

[0137] In one embodiment, the preset evaluation dimension includes a hit shelf number dimension, and the hit shelf number dimension includes the number of hit shelves corresponding to each individual.

[0138] In one embodiment, the preset evaluation dimension includes an expiration date dimension, and the expiration date dimension includes an average expiration date of each individual hit of the inventory goods.

[0139] In one embodiment, the preset evaluation dimension includes a shelf distance dimension, which is the sum of the distances from each shelf hit by each individual to the picking workstation.

[0140] In one embodiment, when the number of preset evaluation dimensions is at least two, constructing the fitness function includes: constructing the fitness function according to each preset evaluation dimension and a preset weight value corresponding to each preset evaluation dimension.

[0141] In one embodiment, a chromosome of each individual corresponds to a cargo type of an order to be picked, and the gene bits of each chromosome correspond one-to-one to the cargo boxes in the cargo warehouse. The population generation module 320 is also used to: initialize each chromosome based on binary coding according to inventory information, initialize the gene bits corresponding to the hit cargo boxes to 1, and initialize the gene bits corresponding to the remaining cargo boxes to 0, and the hit cargo boxes are cargo boxes whose cargo types of the inventory goods are the same as the cargo types corresponding to each chromosome; perform real number encoding on the gene bits encoded as 1 in each initialized chromosome to generate random numbers to obtain individuals; and generate multiple individuals by performing real number encoding on each initialized chromosome multiple times.

[0142] In one embodiment, the population generation module 320 is also used to: perform out-of-stock detection based on order information and inventory information to determine whether there is a shortage of goods; if there is no shortage of goods, encode and generate multiple individuals according to the order information and inventory information according to preset encoding rules to obtain an initial population.

[0143] In one embodiment, the order information also includes an order number, and the population generation module 320 is further used to: when there is a shortage of goods, output the order number of the order to be picked and a reminder of the shortage of goods.

[0144] In one embodiment, the population generation module 320 is also used to: determine the total inventory quantity of inventory goods of the same type as the goods corresponding to the goods to be picked in the order information in the goods warehouse based on the inventory information; compare the picking quantity of each goods to be picked with the corresponding total inventory quantity; if the picking quantity of any goods to be picked is greater than the corresponding total inventory quantity, determine that there is a shortage of goods; if the picking quantity of each goods to be picked is less than or equal to the corresponding total inventory quantity, determine that there is no shortage of goods.

[0145] In one embodiment, the population generation module 320 is also used to: hit the cargo cells corresponding to the gene positions in sequence according to the order information, inventory information and the coding size of the gene positions of each chromosome of the individual in a preset order until the number of hit goods meets the needs of the order to be picked, so as to obtain multiple hit cargo cells; determine the hit shelf according to the inventory information and the multiple hit cargo cells, so as to obtain the hit result corresponding to the individual.

[0146] An embodiment of the present application also provides a machine-readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, the method for shelf hit in the above-mentioned embodiment is implemented.

[0147] 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.

[0148] 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 box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes 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.

[0149] 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.

[0150] 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.

[0151] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0152] 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.

[0153] 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 tape 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.

[0154] 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.

[0155] 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. A method for shelf targeting, characterized in that: The method comprises: Obtain order information of the order to be picked and inventory information of the current goods warehouse, wherein the order information includes the type and quantity of each item to be picked, and the inventory information includes the shelf number, the shelf number, the type and quantity of the goods in stock in the shelf; According to the order information and the inventory information, multiple individuals are encoded according to a preset encoding rule to obtain an initial population, each of the individuals corresponds to a hit result, the number of chromosomes of each individual is equal to the number of types of goods in the order to be picked, and the number of gene bits of each chromosome is equal to the total number of cargo compartments in the current cargo warehouse; Based on a multi-objective genetic algorithm, a target individual is determined according to the initial population and a pre-constructed fitness function, wherein the fitness function is constructed according to a preset evaluation dimension, wherein the preset evaluation dimension includes at least one of a hit shelf number dimension, an expiration date dimension, and a shelf distance dimension; Determine the hit result corresponding to the target individual as the target hit result of the order to be picked, wherein the target hit result includes a target shelf number and a target cargo compartment number; Among them, one chromosome of each individual corresponds to a type of goods of the order to be picked, and the gene position of each chromosome corresponds one-to-one to the cargo compartment in the cargo warehouse. The encoding is performed according to the order information and the inventory information according to the preset encoding rules to generate multiple individuals, including: Based on binary coding, each of the chromosomes is initialized according to the inventory information, the gene bit corresponding to the hittable cargo compartment is initialized to 1, and the gene bit corresponding to the remaining cargo compartment is initialized to 0, and the hittable cargo compartment is the cargo compartment whose cargo type of the inventory cargo is the same as the cargo type corresponding to each of the chromosomes; Performing real number encoding on the gene bits coded as 1 in each of the initialized chromosomes to generate random numbers to obtain the individual; Generate a plurality of individuals by performing real number encoding on each of the initialized chromosomes multiple times; The method for determining the hit result corresponding to the individual includes: According to the order information, the inventory information and the coding size of the gene position of each chromosome of the individual, the cargo cells corresponding to the gene positions are hit in sequence according to a preset order until the number of hit goods meets the requirements of the order to be picked, so as to obtain multiple hit cargo cells; The hit shelf is determined according to the inventory information and the multiple hit shelves to obtain the hit result corresponding to the individual.

2. The method according to claim 1, characterized in that The preset evaluation dimension includes a hit shelf number dimension, and the hit shelf number dimension includes the number of hit shelves corresponding to each of the individuals.

3. The method according to claim 1, characterized in that The preset evaluation dimension includes an expiration date dimension, and the expiration date dimension includes an average expiration date of each of the individual hit inventory goods.

4. The method according to claim 1, characterized in that: The preset evaluation dimension includes a shelf distance dimension, and the shelf distance dimension is the sum of the distances from each shelf hit by each individual to the picking workstation.

5. The method according to claim 1, characterized in that When the number of the preset evaluation dimensions is at least two, the construction of the fitness function includes: The fitness function is constructed according to each of the preset evaluation dimensions and the preset weight value corresponding to each of the preset evaluation dimensions.

6. The method according to claim 1, characterized in that The step of encoding the order information and the inventory information according to a preset encoding rule to generate a plurality of individuals to obtain an initial population includes: Perform out-of-stock detection based on the order information and the inventory information to determine whether there is a shortage of goods; In the case that there is no shortage of goods, multiple individuals are encoded according to the order information and the inventory information in accordance with a preset encoding rule to obtain the initial population.

7. The method according to claim 6, characterized in that The order information also includes an order number, and the method further includes: In the case that the goods are out of stock, the order number of the order to be picked and a reminder of the goods being out of stock are output.

8. The method according to claim 6, characterized in that The out-of-stock detection is performed according to the order information and the inventory information to determine whether there is a shortage of goods, including: Determine, based on the inventory information, the total inventory quantity of the same type of inventory goods in the goods warehouse as the goods corresponding to the goods to be picked in the order information; Compare the picking quantity of each of the goods to be picked with the corresponding total inventory quantity; When the picking quantity of any of the goods to be picked is greater than the corresponding total inventory quantity, it is determined that the goods are out of stock; When the picking quantity of each of the to-be-picked goods is less than or equal to the corresponding total inventory quantity, it is determined that the goods are not out of stock.

9. A processor, characterized in that: The method is configured to execute the method for shelf hitting according to any one of claims 1 to 8.

10. A machine-readable storage medium storing a program or an instruction, characterized in that: When the program or the instruction is executed by a processor, the method for shelf hit according to any one of claims 1 to 8 is implemented.

Images