Method, device and computer-readable storage medium for storing goods in a warehouse

Abstract

The present disclosure relates to a method, device and computer-readable storage medium for storing goods in a warehouse, and relates to the field of automated warehousing technology. The method disclosed in the present disclosure includes: obtaining the available volume and capacity interval of each storage area, as well as the inventory volume and average outbound quantity in unit measurement of each classification of goods in a preset historical time period; the capacity interval is the average outbound quantity interval in unit measurement of the storage area; for each storage area, determining the classification of goods stored in the storage area from the corresponding set of candidate goods according to constraint conditions; wherein the constraint conditions include: the sum of the inventory volume of goods stored in the storage area does not exceed the available volume of the storage area, and the sum of the average outbound quantity in unit measurement is within the capacity interval of the storage area; according to the determined classification of goods stored in each storage area, storing each classification of goods in the corresponding storage area.

Description

Technical Field

[0001] The present disclosure relates to the field of automated warehousing technology, and in particular to a method, device and computer-readable storage medium for storing goods in a warehouse. Background Art

[0002] With the development of science and technology, large warehouses are becoming more and more automated. In automated warehouses, robots and other automated equipment are used to replace manual labor in the handling and picking of goods, greatly improving the efficiency of goods out of the warehouse and in the warehouse.

[0003] As the business scale expands, the automated warehouses also continue to expand. In order to cope with the decline in picking efficiency in large-scale warehouses, the overall warehouse is generally divided into multiple storage areas, and order picking and warehousing operations are carried out in each area.

[0004] At present, for each storage area, the selection of which categories of goods to store is mostly based on manual experience, using a trial and correction method. First, some categories of goods are selected based on experience to verify whether the constraints are met. If not, the categories are adjusted. Summary of the invention

[0005] The inventors found that the existing solution of manually determining the category of goods for each storage area is very inefficient and may result in very low outbound volume in some areas, wasting resources, or excessive outbound volume exceeding the production capacity limit of the area, resulting in the inability to ship goods out in time.

[0006] A technical problem to be solved by the present disclosure is: how to determine the category of goods stored in each storage area, improve the determination efficiency and meet the production capacity requirements.

[0007] According to some embodiments of the present disclosure, a method for storing goods in a warehouse is provided, comprising: obtaining the available capacity and production capacity interval of each storage area, as well as the inventory volume of each classification of goods and the average outbound quantity in unit measurement within a preset historical time period; the production capacity interval is the average outbound quantity interval in unit measurement of the storage area; for each storage area, determining the classification of goods stored in the storage area from the corresponding set of candidate goods according to constraints; wherein the constraints include: the sum of the inventory volumes of goods stored in the storage area does not exceed the available capacity of the storage area, and the sum of the average outbound quantity in unit measurement is within the production capacity interval of the storage area; according to the determined classification of goods stored in each storage area, storing the goods of each classification in the corresponding storage area.

[0008] In some embodiments, for each storage area, determining the classification of goods to be stored in the storage area from the corresponding set of candidate goods according to constraints includes: for each storage area, determining the classification of goods to be stored in the storage area from the corresponding set of candidate goods according to each goods selection model and constraint conditions, and obtaining multiple storage schemes corresponding to the storage area; using test data to determine at least one of the order confluence ratio, number of goods types, capacity utilization and volume utilization of each storage scheme; wherein the test data includes: information of each order in another historical time period different from the preset historical time period; selecting a storage scheme based on at least one of the determined order confluence ratio, number of goods types, capacity utilization and volume utilization of each storage scheme, and determining the classification of goods to be stored in the storage area based on the selected storage scheme.

[0009] In some embodiments, the unit measurement includes: unit time or unit wave; when the unit measurement is unit time, for each storage area, the capacity interval is determined based on the number of workstations in the storage area, the working hours and the number of picks per unit time at each workstation; when the unit measurement is unit wave, for each storage area, the capacity interval is determined based on the number of workstations in the storage area and the number of picks per unit wave at each workstation.

[0010] In some embodiments, the classification of goods is determined based on at least one of the types of goods and the correlation between each type of goods; the correlation between any two types of goods is determined based on the number of orders containing the two types of goods within a preset time period and the total number of orders within the preset time period.

[0011] In some embodiments, for each category of goods, the inventory volume is determined based on the upper limit days for replenishment of the category of goods, the average outbound quantity per unit time, the minimum inventory quantity and the volume of a single piece of goods.

[0012] In some embodiments, when the cargo selection model includes a first cargo selection model, determining the classification of cargo to be stored in the storage area from the corresponding set of candidate cargoes according to each cargo selection model and constraints includes: determining the ratio of quantity to volume of cargo of each classification in the corresponding set of candidate cargoes in the first cargo selection model; sorting each classification in descending order of the ratio of quantity to volume; and selecting the classification in order from front to back until the cargo of the selected classification meets the constraints.

[0013] In some embodiments, when the cargo selection model includes a second cargo selection model, determining the classification of cargo stored in the storage area from the corresponding candidate cargo set according to each cargo selection model and the constraint condition includes: determining a similarity matrix between each classification in the corresponding candidate cargo set in the second cargo selection model; determining a Laplace matrix according to the similarity matrix; determining the classification of cargo stored in the storage area according to the first objective function and the constraint condition; wherein the first objective function is expressed by the following formula:

[0014] minx T Lx

[0015] Among them, x represents the classification selection vector, and the element x in x i =1 means that category i is selected and stored in this storage area, x i =0 indicates that category i is not selected to be stored in the storage area, and L indicates the Laplace matrix.

[0016] In some embodiments, the similarity matrix between the various categories is determined according to the following formula:

[0017]

[0018] Among them, W ij Represents the element in the i-th row and j-th column of the similarity matrix, K ij is the order set containing category i and category j, k is the order number in the order set, W ii =0; or, the similarity matrix between each category is determined according to the following formula:

[0019]

[0020] Among them, W ij represents the element in the i-th row and j-th column of the similarity matrix, |P k | represents the number of types of goods in order k, W ii =0; or, the similarity matrix between each category is determined according to the following formula:

[0021] W ij =Z ij -minZ ij

[0022] Among them, W ij Represents the element in the i-th row and j-th column of the similarity matrix, Z ij Represents the element in the i-th row and j-th column of the matrix Z. The matrix Z is the covariance matrix of the order matrix F, F∈R M×N , where M is the order quantity, N is the number of categories of goods in the corresponding alternative goods set, and F mn=1 indicates the element in the mth row and nth column of F, which means that order m contains goods of category n. mn =0 means that order m does not contain goods of category n.

[0023] In some embodiments, when the cargo selection model includes a third cargo selection model, determining the classification of cargo stored in the storage area from the corresponding candidate cargo set according to each cargo selection model and the constraint condition includes: in the third cargo selection model, reducing the dimension of the order matrix, wherein the order matrix F∈R M×N , where M is the order quantity, N is the number of categories of goods in the corresponding alternative goods set, and F mn =1 indicates the element in the mth row and nth column of F, which means that order m contains goods of category n. mn =0 means that order m does not contain goods of category n; spectral clustering is performed on the order matrix after dimensionality reduction; a cluster is selected from each cluster after spectral clustering according to the second objective function and the constraint condition, and the classification of the goods in the selected cluster is determined as the classification of the goods stored in the storage area; wherein the second objective function represents a function that minimizes the number of types of selected goods.

[0024] In some embodiments, when the cargo selection model includes a fourth cargo selection model, determining the classification of cargo stored in the storage area from the corresponding candidate cargo set according to each cargo selection model and the constraint condition includes: in the fourth cargo selection model, uniformly sampling the order matrix to obtain a sampled matrix, wherein the order matrix F∈R M×N , where M is the order quantity, N is the number of categories of goods in the corresponding alternative goods set, and F mn =1 indicates the element in the mth row and nth column of F, which means that order m contains goods of category n. mn =0 means that order m does not contain goods of category n; according to the third objective function and the constraint conditions, the category of goods stored in the storage area is determined; wherein the third objective function is expressed by the following formula:

[0025] max(N X -‖b-Ax‖0)+(N X -‖bA(ex)‖0)

[0026] Among them, N X Represents the number of rows of the sampled matrix A, b = Ae, e = [1,1,…,1] T ,x represents the classification selection vector, and the element x in x i =1 means that category i is selected and stored in this storage area, x i =0 means that category i is not selected to be stored in this storage area.

[0027] In some embodiments, selecting a storage scheme based on at least one of the determined order confluence ratio, number of goods types, capacity utilization and volume utilization of each storage scheme includes: for each storage scheme, determining a first parameter based on the ratio of the difference between the order confluence ratio of the storage scheme and the minimum value of the order confluence ratio of each storage scheme to the difference between the maximum value and the minimum value of the order confluence ratio of each storage scheme; determining a second parameter based on the ratio of the difference between the number of goods types of the storage scheme and the minimum value of the number of goods types of each storage scheme to the difference between the maximum value and the minimum value of the number of goods types of each storage scheme; determining a third parameter based on the ratio of the difference between the capacity utilization of the storage scheme and the minimum value of the capacity utilization of each storage scheme to the difference between the maximum value and the minimum value of the capacity utilization of each storage scheme; determining a fourth parameter based on the ratio of the difference between the volume utilization of the storage scheme and the minimum value of the volume utilization of each storage scheme to the difference between the maximum value and the minimum value of the volume utilization of each storage scheme; weighting the first parameter, the second parameter, the third parameter and the fourth parameter corresponding to the storage scheme, and selecting a storage scheme with the largest corresponding weighted value.

[0028] In some embodiments, for each storage plan, the ratio of the number of merged orders in the test data to the total number of orders is used as the order merge ratio, wherein some of the goods in the merged orders belong to the category of goods corresponding to the storage plan, and some of the goods do not belong to the category of goods corresponding to the storage plan; or, for each storage plan, the goods belonging to the category corresponding to the storage plan are used as reference goods, and the ratio of the average outbound quantity in unit measurement of the reference goods to the upper limit of the production capacity range of the storage area is determined according to the test data as the capacity utilization rate; or, for each storage plan, the goods belonging to the category of goods corresponding to the storage plan are used as reference goods, and the ratio of the inventory volume of the reference goods to the available volume of the storage area is determined according to the test data as the volume utilization rate.

[0029] According to other embodiments of the present disclosure, a device for storing goods in a warehouse is provided, comprising: an acquisition module, used to acquire the available capacity and production capacity interval of each storage area, as well as the inventory volume and average outbound quantity in unit measurement of goods of each classification within a preset historical time period; the production capacity interval is the average outbound quantity interval in unit measurement of the storage area; a determination module, used to determine, for each storage area, the classification of goods stored in the storage area from the corresponding set of candidate goods according to constraints; wherein the constraints include: the sum of the inventory volumes of goods stored in the storage area does not exceed the available capacity of the storage area, and the sum of the average outbound quantity in unit measurement is within the production capacity interval of the storage area; a storage module, used to store the goods of each classification in the corresponding storage area according to the determined classification of the goods stored in each storage area.

[0030] In some embodiments, the determination module is used to determine, for each storage area, the classification of goods to be stored in the storage area from the corresponding set of alternative goods according to each goods selection model and constraint conditions, and obtain multiple storage schemes corresponding to the storage area; use test data to determine at least one of the order confluence ratio, the number of goods types, the capacity utilization rate and the volume utilization rate of each storage scheme; wherein the test data includes: information on each order in another historical time period different from the preset historical time period; select a storage scheme based on at least one of the order confluence ratio, the number of goods types, the capacity utilization rate and the volume utilization rate of each determined storage scheme, and determine the classification of goods to be stored in the storage area based on the selected storage scheme.

[0031] In some embodiments, the unit measurement includes: unit time or unit wave; when the unit measurement is unit time, for each storage area, the capacity interval is determined based on the number of workstations in the storage area, the working hours and the number of picks per unit time at each workstation; when the unit measurement is unit wave, for each storage area, the capacity interval is determined based on the number of workstations in the storage area and the number of picks per unit wave at each workstation.

[0032] In some embodiments, the classification of goods is determined based on at least one of the types of goods and the correlation between each type of goods; the correlation between any two types of goods is determined based on the number of orders containing the two types of goods within a preset time period and the total number of orders within the preset time period.

[0033] In some embodiments, for each category of goods, the inventory volume is determined based on the upper limit days for replenishment of the category of goods, the average outbound quantity per unit time, the minimum inventory quantity and the volume of a single piece of goods.

[0034] In some embodiments, when the cargo selection model includes a first cargo selection model, the determination module is used to determine, in the first cargo selection model, the ratio of the quantity to the volume of cargo in each category in the corresponding set of candidate cargoes; sort the categories in order of the ratio of quantity to volume from large to small; and select the categories in order from front to back until the cargo in the selected category meets the constraint conditions.

[0035] In some embodiments, when the cargo selection model includes a second cargo selection model, the determination module is used to determine, in the second cargo selection model, a similarity matrix between each classification in the corresponding candidate cargo set; determine a Laplace matrix according to the similarity matrix; and determine the classification of the cargo stored in the storage area according to the first objective function and the constraint condition; wherein the first objective function is expressed by the following formula:

[0036] minx T Lx

[0037] Among them, x represents the classification selection vector, and the element x in x i =1 means that category i is selected and stored in this storage area, x i =0 indicates that category i is not selected to be stored in the storage area, and L indicates the Laplace matrix.

[0038] In some embodiments, the similarity matrix between the various categories is determined according to the following formula:

[0039]

[0040] Among them, W ij Represents the element in the i-th row and j-th column of the similarity matrix, K ij is the order set containing category i and category j, k is the order number in the order set, W ii =0; or, the similarity matrix between each category is determined according to the following formula:

[0041]

[0042] Among them, W ij represents the element in the i-th row and j-th column of the similarity matrix, |P k | represents the number of types of goods in order k, W ii =0; or, the similarity matrix between each category is determined according to the following formula:

[0043] W ij =Z ij -minZ ij

[0044] Among them, W ijRepresents the element in the i-th row and j-th column of the similarity matrix, Z ij Represents the element in the i-th row and j-th column of the matrix Z. The matrix Z is the covariance matrix of the order matrix F, F∈R M×N , where M is the order quantity, N is the number of categories of goods in the corresponding alternative goods set, and F mn =1 indicates the element in the mth row and nth column of F, which means that order m contains goods of category n. mn =0 means that order m does not contain goods of category n.

[0045] In some embodiments, the determination module is used to reduce the dimension of the order matrix in the third product selection model, where the order matrix F∈R M×N , where M is the order quantity, N is the number of categories of goods in the corresponding alternative goods set, and F mn =1 indicates the element in the mth row and nth column of F, which means that order m contains goods of category n. mn =0 means that order m does not contain goods of category n; spectral clustering is performed on the order matrix after dimensionality reduction; a cluster is selected from each cluster after spectral clustering according to the second objective function and the constraint condition, and the classification of the goods in the selected cluster is determined as the classification of the goods stored in the storage area; wherein the second objective function represents a function that minimizes the number of types of selected goods.

[0046] In some embodiments, when the product selection model includes a fourth product selection model, the determination module is used to uniformly sample the order matrix in the fourth product selection model to obtain a sampled matrix, wherein the order matrix F∈R M×N , where M is the order quantity, N is the number of categories of goods in the corresponding alternative goods set, and F mn =1 indicates the element in the mth row and nth column of F, which means that order m contains goods of category n. mn =0 means that order m does not contain goods of category n; according to the third objective function and the constraint conditions, the category of goods stored in the storage area is determined; wherein the third objective function is expressed by the following formula:

[0047] max(N X -‖b-Ax‖0)+(N X -‖bA(ex)‖0)

[0048] Among them, N X Represents the number of rows of the sampled matrix A, b = Ae, e = [1,1,…,1] T ,x represents the classification selection vector, and the element x in x i =1 means that category i is selected and stored in this storage area, x i=0 means that category i is not selected to be stored in this storage area.

[0049] In some embodiments, the determination module is used to determine, for each storage scheme, a first parameter according to the ratio of the difference between the order confluence ratio of the storage scheme and the minimum value of the order confluence ratio of each storage scheme to the difference between the maximum value and the minimum value of the order confluence ratio of each storage scheme; determine a second parameter according to the ratio of the difference between the number of types of goods of the storage scheme and the minimum value of the number of types of goods of each storage scheme to the difference between the maximum value and the minimum value of the number of types of goods of each storage scheme; determine a third parameter according to the ratio of the difference between the capacity utilization of the storage scheme and the minimum value of the capacity utilization of each storage scheme to the difference between the maximum value and the minimum value of the capacity utilization of each storage scheme; determine a fourth parameter according to the ratio of the difference between the volume utilization of the storage scheme and the minimum value of the volume utilization of each storage scheme to the difference between the maximum value and the minimum value of the volume utilization of each storage scheme; weight the first parameter, the second parameter, the third parameter, and the fourth parameter corresponding to the storage scheme, and select a storage scheme with the largest corresponding weighted value.

[0050] In some embodiments, for each storage plan, the ratio of the number of merged orders in the test data to the total number of orders is used as the order merge ratio, wherein some of the goods in the merged orders belong to the category of goods corresponding to the storage plan, and some of the goods do not belong to the category of goods corresponding to the storage plan; or, for each storage plan, the goods belonging to the category corresponding to the storage plan are used as reference goods, and the ratio of the average outbound quantity in unit measurement of the reference goods to the upper limit of the production capacity range of the storage area is determined according to the test data as the capacity utilization rate; or, for each storage plan, the goods belonging to the category of goods corresponding to the storage plan are used as reference goods, and the ratio of the inventory volume of the reference goods to the available volume of the storage area is determined according to the test data as the volume utilization rate.

[0051] According to some other embodiments of the present disclosure, a device for storing cargo in a warehouse is provided, comprising: a processor; and a memory coupled to the processor, for storing instructions, which, when executed by the processor, causes the processor to execute a method for storing cargo in a warehouse as described in any of the aforementioned embodiments.

[0052] According to some further embodiments of the present disclosure, a non-transitory computer-readable storage medium is provided, on which a computer program is stored, wherein when the program is executed by a processor, the steps of the method for storing goods in a warehouse of any of the aforementioned embodiments are implemented.

[0053] The present disclosure sets a constraint that the sum of the inventory volumes of the goods stored in the storage area does not exceed the available volume of the storage area and the sum of the average outbound volume in the unit measurement is within the capacity range of the storage area. Based on the constraint, the available volume and capacity range of each storage area, and the inventory volume and average outbound volume in the unit measurement of each classification of goods in a preset historical time period, the classification of the goods stored in each storage area is determined, so that goods of different classifications are stored in the corresponding storage area. The present disclosure automatically determines the classification of goods stored in each storage area based on historical data, meets the constraints of the available volume and capacity range in the storage area, improves the determination efficiency and meets the capacity requirements.

[0054] Other features and advantages of the present disclosure will become apparent from the following detailed description of exemplary embodiments of the present disclosure with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] In order to more clearly illustrate the embodiments of the present disclosure or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0056] Figure 1 A schematic diagram showing a flow chart of a method for storing goods in a warehouse according to some embodiments of the present disclosure.

[0057] Figure 2 A schematic diagram showing a flow chart of a method for storing goods in a warehouse according to other embodiments of the present disclosure.

[0058] Figure 3 A schematic diagram showing the structure of a cargo storage device in a warehouse according to some embodiments of the present disclosure.

[0059] Figure 4 A schematic structural diagram of a cargo storage device in a warehouse according to some other embodiments of the present disclosure is shown.

[0060] Figure 5 A schematic structural diagram of a cargo storage device in a warehouse according to some other embodiments of the present disclosure is shown. DETAILED DESCRIPTION

[0061] The technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only part of the embodiments of the present disclosure, rather than all of the embodiments. The following description of at least one exemplary embodiment is actually only illustrative and is by no means intended to limit the present disclosure and its application or use. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present disclosure.

[0062] The present invention proposes a method for storing goods in a warehouse. Figure 1 Give a description.

[0063] Figure 1 Flowcharts of some embodiments of the method for storing goods in a warehouse disclosed in the present invention. Figure 1 As shown, the method of this embodiment includes: steps S102 to S106.

[0064] In step S102, the available capacity and capacity interval of each storage area, as well as the inventory volume and average outbound quantity in unit measurement of each classification of goods in a preset historical time period are obtained.

[0065] For each storage area, the available capacity can be determined based on the product of the available capacity (taking into account the gaps and reservations, the capacity is not 100% utilized) and the quantity of the storage units (e.g., pallets, shelves, etc.) planned in the storage area. The capacity interval is the interval of the outbound volume within the unit measurement of the storage area. For example, the unit measurement includes: unit time or unit wave; for example, each wave can be composed of a preset number of orders. When the unit measurement is unit time, for each storage area, the capacity interval is determined based on the number of workstations in the storage area, the working hours, and the number of picks per unit time at each workstation. For example, the upper and lower limits of the capacity for each storage area are C and C respectively. u and C l If it is an automated storage area, the upper capacity limit is the product of the number of workstations in the area, the working hours, and the average number of picks per unit time of the automatic picking device at each workstation. If the storage area uses manual picking, the upper capacity limit is the product of the number of pickers in the area (usually one picker is assigned to one workstation), the working hours, and the average number of picks per unit time of the picker at each workstation. The ratio of the lower capacity limit to the upper capacity limit of the storage area can be configured to a preset ratio, such as 0.5.

[0066] When the unit measurement is unit wave, for each storage area, the capacity interval is determined based on the number of workstations in the storage area and the number of picks within the unit wave of each workstation.

[0067] In some embodiments, the classification of goods is determined based on at least one of the types of goods and the correlation between each type of goods; the correlation between any two types of goods is determined based on the number of orders containing the two types of goods within a preset time period and the total number of orders within the preset time period.

[0068] For example, the type of goods can be directly used as the classification of goods, or the classification of goods can be determined only based on the correlation between goods of various types. Alternatively, when the type of goods exceeds the type threshold, the classification of goods is determined based on the correlation between goods of various types, and when the type of goods is lower than the type threshold, the type of goods is directly used as the classification of goods. The classification method can also adopt other methods according to actual needs.

[0069] For example, the correlation between any two types of goods is the ratio of the number of orders containing the two types of goods within a preset time period to the total number of orders within the preset time period. Based on the orders within a preset time period (e.g., the past month), the correlation between any two goods i and j can be determined according to the following formula.

[0070] g ij =O ij / O Q (1)

[0071] Among them, O ij is the order quantity that contains both goods, O Q is the total number of orders. Further, the following formula can be used to standardize the correlation.

[0072]

[0073] Among them, Ming ij Indicates that all g ij The minimum value in ij Indicates that all g ij The maximum value in . The correlation degree after standardized processing in formula (2) can be used as the correlation degree between the two goods, or the correlation degree calculated in formula (1) can be directly used as the correlation degree between the two goods.

[0074] Furthermore, multiple types of goods whose association exceeds the association threshold can be determined as the same category. For example, (1) initialize a new category set J; (2) select a category from the unclassified goods and add it to set J; (3) select a category from the unclassified goods whose association with at least one of the goods in set J exceeds the association threshold g. θ Add the goods to set J and repeat the above step (3) until no goods that have not been classified are found whose correlation with at least one of the goods in set: exceeds the correlation threshold g.θ The process returns to step (1) and continues until all goods have been sorted.

[0075] The above method classifies goods according to their relevance. Goods of the same category have a higher probability of appearing in the same order, so storing them in the same storage area can improve outbound efficiency.

[0076] In some embodiments, for each category of goods, the inventory volume is determined based on the upper limit of replenishment days for the goods of the category, the average outbound quantity per unit time, the minimum inventory quantity, and the volume of a single piece of goods. For example, the average outbound quantity per unit time of each category of goods s in a preset historical time period is calculated. s ; Inventory volume of each category i Where S i is the set of goods under category i, M s is the minimum number of pieces in stock of item s (for example, some slow-moving items need to have a minimum number of pieces in stock, otherwise the product of the average outbound quantity per unit time and the upper limit of replenishment days may be less than 1 piece), v s is the volume of a single piece of cargo s;

[0077] In some embodiments, for goods of category i, the average outbound quantity per unit time (for example, per day) is Or, for each category of goods, the average outbound quantity per wave (for example, each wave) is Among them, o′ s It represents the average outbound quantity of goods of type s under category i within a unit wave.

[0078] In step S104, for each storage area, the classification of goods to be stored in the storage area is determined from the corresponding candidate goods set according to the constraint conditions.

[0079] For each storage area, a set of candidate goods can be determined, and the set of candidate goods can be determined based on the characteristics (size, load-bearing capacity, etc.) of the storage containers (pallets, turnover boxes, multi-layer shelves, etc.) planned for this storage area and other restrictions (storage of valuable goods in separate areas, etc.). The order of each storage area can be determined according to actual needs, and the classification of goods stored in each storage area can be determined in sequence. The set of candidate goods for each storage area is determined from the remaining unselected goods.

[0080] Constraints include, for example: the sum of the inventory volumes of goods stored in the storage area does not exceed the available volume of the storage area, and the sum of the average outbound volumes in a unit of measurement is within the capacity range of the storage area.

[0081] In some embodiments, an objective function may be set according to actual needs, and the classification of goods stored in the storage area may be determined from the corresponding candidate goods set in combination with constraint conditions. The objective function may be set, for example, to minimize the number of types of goods stored, or minimize the order confluence ratio, or maximize the capacity utilization rate, or maximize the volume utilization rate, etc. The classification of goods stored in the storage area is solved according to the objective function under the constraint conditions.

[0082] In some embodiments, Figure 2 As shown, for each storage area, the following method (steps S202 to S206) can be used to determine the classification of goods stored in the storage area from the corresponding candidate goods set according to the constraint conditions.

[0083] In step S202, for each storage area, the classification of goods to be stored in the storage area is determined from the corresponding candidate goods set according to each goods selection model and constraint conditions, and multiple storage solutions corresponding to the storage area are obtained.

[0084] Different cargo selection models may use different methods to determine the classification of cargo to be stored in the storage area, and the resulting storage solutions are also different. Some embodiments of the cargo selection model will be described later.

[0085] In step S204, at least one of the order confluence ratio, the number of goods types, the capacity utilization rate and the volume utilization rate of each storage solution is determined using the test data.

[0086] The test data includes, for example, information about each order in another historical time period different from the preset historical time period. The information about each order in the preset historical time period (for example, the first 20 days of September 2019) is used as training data for each cargo selection model to determine each storage plan. The information about each order in another historical time period (for example, the last 10 days of September 2019) is used as test data to test indicators such as the order confluence ratio, the number of cargo types, the capacity utilization rate and / or the volume utilization rate of each storage plan.

[0087] In some embodiments, for each storage solution, the ratio of the number of merged orders in the test data to the total number of orders is used as the order merge ratio. For example, for a storage area, the order merge ratio of each storage solution is Among them, C his the number of merged orders in the test data, and C is the total number of orders in the test data. A merged order is an order in which some of the goods belong to the category of goods corresponding to the storage solution, and some of the goods do not belong to the category of goods corresponding to the storage solution. If the goods required in an order are stored in different areas, the order will be split, and the merge operation will be performed after picking is completed in different storage areas. Therefore, the higher the proportion of merged orders, the lower the outbound efficiency and the higher the cost of picking and distribution. The number of types of goods stored in the storage area determined by each storage solution can be expressed as N s .

[0088] For each storage solution, the goods belonging to the classification corresponding to the storage solution are used as reference goods. The ratio of the average outbound quantity in the unit measurement of the reference goods to the upper limit of the capacity range of the storage area is determined according to the test data as the capacity utilization rate. For example, the capacity utilization rate of each storage solution is Among them, C r The average outbound quantity in units of measurement of the classified goods stored in the storage area determined for the storage plan, C u The upper limit of the storage area's capacity.

[0089] For each storage solution, the goods belonging to the category of goods corresponding to the storage solution are used as reference goods, and the ratio of the inventory volume of the reference goods to the available volume of the storage area is determined according to the test data as the volume utilization rate. For example, the volume utilization rate of each storage solution is Among them, V r The total inventory volume of the goods stored in the storage area determined for the storage solution may be determined according to the aforementioned embodiment.

[0090] In step S206, a storage plan is selected based on the order confluence ratio, the number of goods types, at least one of the capacity utilization rate and the volume utilization rate of each determined storage plan, and the classification of the goods stored in the storage area is determined based on the selected storage plan.

[0091] In some embodiments, for each storage scheme, a first parameter is determined based on the ratio of the difference between the order confluence ratio of the storage scheme and the minimum value of the order confluence ratio of each storage scheme to the difference between the maximum value and the minimum value of the order confluence ratio of each storage scheme; a second parameter is determined based on the ratio of the difference between the number of types of goods of the storage scheme and the minimum value of the number of types of goods of each storage scheme to the difference between the maximum value and the minimum value of the number of types of goods of each storage scheme; a third parameter is determined based on the ratio of the difference between the capacity utilization of the storage scheme and the minimum value of the capacity utilization of each storage scheme to the difference between the maximum value and the minimum value of the capacity utilization of each storage scheme; a fourth parameter is determined based on the ratio of the difference between the volume utilization of the storage scheme and the minimum value of the volume utilization of each storage scheme to the difference between the maximum value and the minimum value of the volume utilization of each storage scheme; the first parameter, the second parameter, the third parameter, and the fourth parameter corresponding to the storage scheme are weighted, and a storage scheme with the largest corresponding weighted value is selected.

[0092] Of course, you can also select a storage solution based on any one of the order confluence ratio, the number of goods types, the capacity utilization rate, and the volume utilization rate, such as the storage solution with the smallest order confluence ratio. You can also select a storage solution by combining any two or three of them, for example, weighting the second parameter and the third parameter corresponding to each storage solution, and selecting the storage solution with the largest corresponding weighted value.

[0093] For example, for each storage solution, the score of each storage solution can be obtained based on the order confluence ratio, the number of goods types, the capacity utilization rate and the volume utilization rate. s ,E c ,E v ), select the solution with the highest score. Scoring function f(H,N s ,E c ,E v )=α1h1(H)+α2h2(N s )+α3h3(E c )+P4h4(E v ). i ≥0 is the weight. The larger the value, the more attention is paid to a certain evaluation item. 0 means no attention is paid to this item. i (·) can take different functions.

[0094] For example, the first parameter Among them, minH represents the minimum value of the order confluence ratio of each storage solution, and similarly maxH represents the maximum value of the order confluence ratio of each storage solution.

[0095] For example, the second parameter, when the business planning goal is to store as many types of goods as possible in the storage area, When the business planning goal is to store as few types of goods as possible in the storage area,

[0096] For example, when the business planning goal is to achieve the highest possible capacity utilization,

[0097] For example, when the business planning goal is to set the volume utilization rate as high as possible, When the business planning goal is to store as many types of goods as possible in the storage area,

[0098] The method of the above embodiment selects a storage scheme with reference to one or more of the order confluence ratio, the number of goods types, the capacity utilization rate and the volume utilization rate for multiple storage schemes. If the storage scheme is selected with reference to the order confluence ratio, the order confluence ratio can be reduced, the probability of goods in the order being stored in different areas can be reduced, and the efficiency of outbound delivery can be improved. If the number of goods types is referenced, the number of goods types in the same storage area can meet actual demand. If the capacity utilization rate is referenced, the capacity utilization rate of the storage area can be improved, reducing the waste of resources. If the volume utilization is referenced, the waste of space in the storage area can be reduced.

[0099] In step S106, according to the determined classification of the goods to be stored in each storage area, the goods of each classification are stored in the corresponding storage area.

[0100] In the above embodiment, the constraint condition that the sum of the inventory volume of the goods stored in the storage area does not exceed the available volume of the storage area and the sum of the average outbound quantity in the unit measurement is within the capacity interval of the storage area is set. According to the constraint condition, the available volume and capacity interval of each storage area, and the inventory volume and average outbound quantity in the unit measurement of each classification of goods in a preset historical time period, the classification of the goods stored in each storage area is determined, so that goods of different classifications are stored in the corresponding storage area. The above embodiment automatically determines the classification of goods stored in each storage area based on historical data, satisfies the constraints of the available volume and capacity interval in the storage area, improves the determination efficiency and meets the capacity requirements.

[0101] Several embodiments of the cargo selection model are described in detail below.

[0102] In some embodiments, when the cargo selection model includes a first cargo selection model, in the first cargo selection model, the ratio of the quantity to volume of cargo of each category in the corresponding candidate cargo set is determined; the categories are sorted in descending order of the ratio of quantity to volume; the categories are selected in the order from front to back until the cargo of the selected category meets the constraint condition. If both constraints cannot be met, "No feasible solution found" is returned.

[0103] In some embodiments, when the cargo selection model includes a second cargo selection model, in the second cargo selection model, a similarity matrix between each classification in the corresponding candidate cargo set is determined; a Laplace matrix is ​​determined based on the similarity matrix; and a classification of the cargo stored in the storage area is determined based on the first objective function and the constraint condition. The first objective function can be expressed by the following formula.

[0104] minx T Lx (3)

[0105] x represents the classification selection vector, and the elements x in x i =1 means that category i is selected and stored in this storage area, x i =0 indicates that category i is not selected to be stored in the storage area, and L indicates the Laplace matrix.

[0106] For example, the similarity matrix between each category is determined according to the following formula.

[0107]

[0108] Among them, W ij Represents the element in the i-th row and j-th column of the similarity matrix, K ij is the order set containing category i and category j (the order set within the preset historical time period), k is the order number in the order set, W ii =0.

[0109] For another example, the similarity matrix between each category is determined according to the following formula.

[0110]

[0111] Among them, W ij represents the element in the i-th row and j-th column of the similarity matrix, |P k | represents the number of types of goods in order k, W ii =0;

[0112] For another example, the similarity matrix between each category is determined according to the following formula.

[0113] W ij =Zij -minZ ij (6)

[0114] Among them, W ij Represents the element in the i-th row and j-th column of the similarity matrix, Z ij Represents the element in the i-th row and j-th column of the matrix Z. The matrix Z is the covariance matrix of the order matrix F, F∈R M×N , where M is the number of orders in the preset historical time period (which can be orders classified in the candidate goods set), N is the number of categories of goods in the corresponding candidate goods set, and F mn =1 indicates the element in the mth row and nth column of F, which means that order m contains goods of category n. mn =0 means that order m does not contain goods of category n.

[0115] Furthermore, the Laplacian matrix can be expressed by the following formula.

[0116] L=DW (7)

[0117] Among them, the element D in D ii =∑ j W ij , D ij =0; W is the similarity matrix between each category.

[0118] According to the above formulas (3) to (7), it can be determined that the meaning of formula (3) is to classify goods with great similarity into the same storage area as much as possible.

[0119] The constraint condition can be expressed, for example, by the following formula.

[0120] ∑ i V i ·x i ≤V (8)

[0121] Among them, V i represents the inventory volume of goods of category i, x i =1 means that category i is selected and stored in this storage area, x i =0 indicates that category i is not selected to be stored in the storage area, and V indicates the available capacity of the storage area.

[0122] ∑ i O i ·x i ≤C u (9)

[0123] ∑ i O i ·x i ≥C l (10)

[0124] Among them, C i represents the average outbound quantity in unit measure of goods of category i, x i =1 means that category i is selected and stored in this storage area, x i =0 means that category i is not selected to be stored in this storage area, C u Indicates the upper limit of the storage area’s capacity, C l Indicates the lower limit of the storage area's capacity.

[0125] In some embodiments, when the product selection model includes a third product selection model, in the third product selection model, the order matrix is ​​reduced in dimension, wherein the order matrix F∈R M×n , where M is the number of orders in the preset historical time period (which can be orders classified in the candidate goods set), N is the number of categories of goods in the corresponding candidate goods set, and F mn =1 indicates the element in the mth row and nth column of F, which means that order m contains goods of category n. mn =0 means that order m does not contain goods of category n; perform spectral clustering on the order matrix after dimensionality reduction; select a cluster from each cluster after spectral clustering according to the second objective function and constraint conditions, and determine the classification of goods in the selected cluster as the classification of goods stored in the storage area; wherein the second objective function represents a function with the minimum number of types of selected goods. The second objective function and constraint conditions can form a 0-1 integer linear programming model, and solving the model can obtain the classification of goods stored in the storage area.

[0126] In some embodiments, when the product selection model includes a fourth product selection model, in the fourth product selection model, the order matrix is ​​uniformly sampled to obtain a sampled matrix, wherein the order matrix F∈R M×N , where M is the number of orders in the preset historical time period (which can be orders classified in the candidate goods set), N is the number of categories of goods in the corresponding candidate goods set, and F mn =1 indicates the element in the mth row and nth column of F, which means that order m contains goods of category n. mn =0 means that order m does not contain goods of category n; according to the third objective function and the constraint conditions, the category of goods stored in the storage area is determined. The third objective function can be expressed by the following formula.

[0127] max(N X -‖b-Ax‖0)+(N X -‖bA(ex)‖0) (11)

[0128] Among them, N XRepresents the number of rows of the sampled matrix A, b = Ae, e = [1,1,…,1] T ,x represents the classification selection vector, and the element x in x i =1 means that category i is selected and stored in this storage area, x i =0 means that category i is not selected to be stored in the storage area. The third objective function represents maximizing the number of non-merging orders. Since the L0 norm involved in the third objective function is difficult to solve directly, it can be classified as a 0-1 integer linear programming by introducing a slack variable.

[0129] min∑ i y i +∑ i z i (12)

[0130] Furthermore, in addition to being expressed by formulas (8) to (10), the constraint conditions may also include the following formula.

[0131]

[0132]

[0133]

[0134] Among them, Q is a large positive number, which is larger than the number of categories.

[0135] The present disclosure also provides a cargo storage device in a warehouse. Figure 3 Give a description.

[0136] Figure 3 Figure 1 is a structural diagram of some embodiments of the in-warehouse cargo storage device disclosed in the present invention. Figure 3 As shown, the device 30 of this embodiment includes: an acquisition module 310 , a determination module 320 , and a storage module 330 .

[0137] The acquisition module 310 is used to obtain the available capacity and capacity interval of each storage area, as well as the inventory volume of each category of goods and the average outbound quantity in unit measurement within a preset historical time period; the capacity interval is the average outbound quantity interval in unit measurement of the storage area.

[0138] In some embodiments, the unit measurement includes: unit time or unit wave; when the unit measurement is unit time, for each storage area, the capacity interval is determined based on the number of workstations in the storage area, the working hours and the number of picks per unit time at each workstation; when the unit measurement is unit wave, for each storage area, the capacity interval is determined based on the number of workstations in the storage area and the number of picks per unit wave at each workstation.

[0139] In some embodiments, the classification of goods is determined based on at least one of the types of goods and the correlation between each type of goods; the correlation between any two types of goods is determined based on the number of orders containing the two types of goods within a preset time period and the total number of orders within the preset time period.

[0140] In some embodiments, for each category of goods, the inventory volume is determined based on the upper limit days for replenishment of the category of goods, the average outbound quantity per unit time, the minimum inventory quantity and the volume of a single piece of goods.

[0141] The determination module 320 is used to determine, for each storage area, the classification of goods stored in the storage area from the corresponding set of candidate goods according to the constraints; wherein the constraints include: the sum of the inventory volumes of the goods stored in the storage area does not exceed the available volume of the storage area, and the sum of the average outbound quantities in unit measurement is within the production capacity range of the storage area.

[0142] In some embodiments, the determination module 320 is used to determine, for each storage area, the classification of goods to be stored in the storage area from the corresponding set of alternative goods according to each goods selection model and constraint conditions, and obtain multiple storage schemes corresponding to the storage area; use test data to determine at least one of the order confluence ratio, the number of goods types, the capacity utilization rate and the volume utilization rate of each storage scheme; wherein the test data includes: information on each order in another historical time period different from the preset historical time period; select a storage scheme based on at least one of the order confluence ratio, the number of goods types, the capacity utilization rate and the volume utilization rate of each storage scheme, and determine the classification of goods to be stored in the storage area based on the selected storage scheme.

[0143] In some embodiments, when the cargo selection model includes a first cargo selection model, the determination module 320 is used to determine, in the first cargo selection model, the ratio of the quantity to the volume of cargo in each category in the corresponding set of candidate cargoes; sort the categories in order of the ratio of quantity to volume from large to small; and select the categories in order from front to back until the cargo in the selected category meets the constraint conditions.

[0144] In some embodiments, when the cargo selection model includes a second cargo selection model, the determination module 320 is used to determine, in the second cargo selection model, a similarity matrix between each classification in the corresponding candidate cargo set; determine a Laplace matrix according to the similarity matrix; and determine the classification of the cargo stored in the storage area according to the first objective function and the constraint condition; wherein the first objective function is expressed by the following formula:

[0145] minxT Lx

[0146] Among them, x represents the classification selection vector, and the element x in x i =1 means that category i is selected and stored in this storage area, x i =0 indicates that category i is not selected to be stored in the storage area, and L indicates the Laplace matrix.

[0147] In some embodiments, the similarity matrix between the various categories is determined according to the following formula:

[0148]

[0149] Among them, W ij Represents the element in the i-th row and j-th column of the similarity matrix, K ij is the order set containing category i and category j, k is the order number in the order set, W ii =0; or, the similarity matrix between each category is determined according to the following formula:

[0150]

[0151] Among them, W ij represents the element in the i-th row and j-th column of the similarity matrix, |P k | represents the number of types of goods in order k, W ii =0; or, the similarity matrix between each category is determined according to the following formula:

[0152] W ij =Z ij -minZ ij

[0153] Among them, W ij Represents the element in the i-th row and j-th column of the similarity matrix, Z ij Represents the element in the i-th row and j-th column of the matrix Z. The matrix Z is the covariance matrix of the order matrix F, F∈R M×N , where M is the order quantity, N is the number of categories of goods in the corresponding alternative goods set, and F mn =1 indicates the element in the mth row and nth column of F, which means that order m contains goods of category n. mn =0 means that order m does not contain goods of category n.

[0154] In some embodiments, the determination module 320 is used to reduce the dimension of the order matrix in the third product selection model, where the order matrix F∈R M×N , where M is the order quantity, N is the number of categories of goods in the corresponding alternative goods set, and F mn=1 indicates the element in the mth row and nth column of F, which means that order m contains goods of category n. mn =0 means that order m does not contain goods of category n; spectral clustering is performed on the order matrix after dimensionality reduction; a cluster is selected from each cluster after spectral clustering according to the second objective function and the constraint condition, and the classification of the goods in the selected cluster is determined as the classification of the goods stored in the storage area; wherein the second objective function represents a function that minimizes the number of types of selected goods.

[0155] In some embodiments, when the product selection model includes the fourth product selection model, the determination module 320 is used to uniformly sample the order matrix in the fourth product selection model to obtain a sampled matrix, wherein the order matrix F∈R M×N , where M is the order quantity, N is the number of categories of goods in the corresponding alternative goods set, and F mn =1 indicates the element in the mth row and nth column of F, which means that order m contains goods of category n. mn =0 means that order m does not contain goods of category n; according to the third objective function and the constraint conditions, the category of goods stored in the storage area is determined; wherein the third objective function is expressed by the following formula:

[0156] max(N X -‖b-Ax‖0)+(N X -‖bA(ex)‖0)

[0157] Among them, N X Represents the number of rows of the sampled matrix A, b = Ae, e = [1,1,…,1] T ,x represents the classification selection vector, and the element x in x i =1 means that category i is selected and stored in this storage area, x i =0 means that category i is not selected to be stored in this storage area.

[0158] In some embodiments, the determination module 320 is used to determine, for each storage scheme, a first parameter according to the ratio of the difference between the order confluence ratio of the storage scheme and the minimum value of the order confluence ratio of each storage scheme to the difference between the maximum value and the minimum value of the order confluence ratio of each storage scheme; determine a second parameter according to the ratio of the difference between the number of types of goods of the storage scheme and the minimum value of the number of types of goods of each storage scheme to the difference between the maximum value and the minimum value of the number of types of goods of each storage scheme; determine a third parameter according to the ratio of the difference between the capacity utilization of the storage scheme and the minimum value of the capacity utilization of each storage scheme to the difference between the maximum value and the minimum value of the capacity utilization of each storage scheme; determine a fourth parameter according to the ratio of the difference between the volume utilization of the storage scheme and the minimum value of the volume utilization of each storage scheme to the difference between the maximum value and the minimum value of the volume utilization of each storage scheme; weight the first parameter, the second parameter, the third parameter, and the fourth parameter corresponding to the storage scheme, and select a storage scheme with the largest corresponding weighted value.

[0159] In some embodiments, for each storage plan, the ratio of the number of merged orders in the test data to the total number of orders is used as the order merge ratio, wherein some of the goods in the merged orders belong to the category of goods corresponding to the storage plan, and some of the goods do not belong to the category of goods corresponding to the storage plan; or, for each storage plan, the goods belonging to the category corresponding to the storage plan are used as reference goods, and the ratio of the average outbound quantity in unit measurement of the reference goods to the upper limit of the production capacity range of the storage area is determined according to the test data as the capacity utilization rate; or, for each storage plan, the goods belonging to the category of goods corresponding to the storage plan are used as reference goods, and the ratio of the inventory volume of the reference goods to the available volume of the storage area is determined according to the test data as the volume utilization rate.

[0160] The storage module 330 is used to store the goods of each category into the corresponding storage area according to the determined categories of the goods to be stored in each storage area.

[0161] The in-warehouse cargo storage device in the embodiments of the present disclosure can be implemented by various computing devices or computer systems. Figure 4 as well as Figure 5 Give a description.

[0162] Figure 4 Figure 1 is a structural diagram of some embodiments of the in-warehouse cargo storage device disclosed in the present invention. Figure 4 As shown, the device 40 of this embodiment includes: a memory 410 and a processor 420 coupled to the memory 410, and the processor 420 is configured to execute the in-warehouse cargo storage method in any of some embodiments of the present disclosure based on the instructions stored in the memory 410.

[0163] The memory 410 may include, for example, a system memory, a fixed non-volatile storage medium, etc. The system memory may store, for example, an operating system, an application program, a boot loader, a database, and other programs.

[0164] Figure 5 FIG. 1 is a structural diagram of some other embodiments of the in-warehouse cargo storage device disclosed in the present invention. Figure 5 As shown, the device 50 of this embodiment includes: a memory 510 and a processor 520, which are similar to the memory 410 and the processor 420 respectively. It can also include an input and output interface 530, a network interface 540, a storage interface 550, etc. These interfaces 530, 540, 550 and the memory 510 and the processor 520 can be connected, for example, through a bus 560. Among them, the input and output interface 530 provides a connection interface for input and output devices such as a display, a mouse, a keyboard, and a touch screen. The network interface 540 provides a connection interface for various networked devices, for example, it can be connected to a database server or a cloud storage server. The storage interface 550 provides a connection interface for external storage devices such as SD cards and USB flash drives.

[0165] Those skilled in the art will appreciate that the embodiments of the present disclosure may be provided as methods, systems, or computer program products. Therefore, the present disclosure may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present disclosure may take the form of a computer program product implemented on one or more computer-usable non-transient storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0166] The present disclosure 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 disclosure. 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.

[0167] 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.

[0168] 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 A step that specifies a function in one or more boxes.

[0169] The above description is only a preferred embodiment of the present disclosure and is not intended to limit the present disclosure. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present disclosure should be included in the protection scope of the present disclosure.

Claims

1. A method for storing goods in a warehouse, comprising: Obtain the available capacity and capacity range of each storage area, as well as the inventory volume and average outbound quantity of each category of goods in a preset historical time period; The capacity interval is the average outbound volume interval within the unit measurement of the storage area; For each storage area, the classification of goods stored in the storage area is determined from the corresponding set of candidate goods according to each goods selection model and constraint conditions, and multiple storage schemes corresponding to the storage area are obtained. The order confluence ratio, the number of goods types, at least one of the capacity utilization rate and the volume utilization rate of each storage scheme are determined by using test data, wherein the test data includes: information of each order in another historical time period different from the preset historical time period, according to the determined order confluence ratio, the number of goods types, at least one of the capacity utilization rate and the volume utilization rate of each storage scheme, a storage scheme is selected, and the classification of goods stored in the storage area is determined according to the selected storage scheme, wherein the constraint conditions include: the total inventory volume of the goods stored in the storage area does not exceed the available volume of the storage area, the unit is The sum of the average outbound quantity in the quantity is within the capacity range of the storage area. For each storage plan, the ratio of the number of merged orders in the test data to the total number of orders is used as the order merge ratio, wherein some of the goods in the merged order belong to the category of goods corresponding to the storage plan, and some of the goods do not belong to the category of goods corresponding to the storage plan. Alternatively, for each storage plan, the goods belonging to the category corresponding to the storage plan are used as reference goods, and the ratio of the average outbound quantity in the unit measurement of the reference goods to the upper limit of the capacity range of the storage area is determined according to the test data as the capacity utilization rate. Alternatively, for each storage plan, the goods belonging to the category of goods corresponding to the storage plan are used as reference goods, and the ratio of the inventory volume of the reference goods to the available volume of the storage area is determined according to the test data as the volume utilization rate. According to the determined classification of goods to be stored in each storage area, each classified goods are stored in the corresponding storage area.

2. The method for storing goods in a warehouse according to claim 1, wherein: The unit measurement includes: unit time or unit wave; In the case where the unit measurement is unit time, for each storage area, the capacity interval is determined according to the number of workstations in the storage area, the working hours and the number of picks per unit time at each workstation; When the unit measurement is a unit wave, for each storage area, the capacity interval is determined according to the number of workstations in the storage area and the number of picks in the unit wave of each workstation.

3. The method for storing goods in a warehouse according to claim 1, wherein: The classification of goods is determined based on at least one of the types of goods and the degree of association between goods of each type; The degree of association between any two types of goods is determined based on the number of orders containing the two types of goods within a preset time period and the total number of orders within the preset time period.

4. The method for storing goods in a warehouse according to claim 1, wherein: For each category of goods, the inventory volume is determined based on the upper limit of replenishment days for the category of goods, the average outbound volume per unit time, the minimum inventory quantity and the volume of a single piece of goods.

5. The method for storing goods in a warehouse according to claim 1, wherein: In the case where the cargo selection model includes a first cargo selection model, the step of determining the classification of cargo to be stored in the storage area from the corresponding candidate cargo set according to each cargo selection model and constraint conditions includes: In the first cargo selection model, determining the ratio of the quantity to volume of cargo of each category in the corresponding candidate cargo set; Sort the categories in descending order of the ratio of the quantity to the volume; The categories are selected in order from front to back until the goods in the selected categories meet the constraints.

6. The method for storing goods in a warehouse according to claim 1, wherein: In the case where the cargo selection model includes a second cargo selection model, the step of determining the classification of cargo to be stored in the storage area from the corresponding candidate cargo set according to each cargo selection model and constraint conditions includes: In the second goods selection model, determining a similarity matrix between each category in the corresponding candidate goods set; Determine a Laplacian matrix according to the similarity matrix; Determining the classification of goods stored in the storage area according to the first objective function and the constraint conditions; The first objective function is expressed by the following formula: min x T Lx Among them, x represents the classification selection vector, and the element x in x i =1 means that category i is selected and stored in this storage area, x i =0 indicates that category i is not selected to be stored in the storage area, and L indicates the Laplace matrix.

7. The method for storing goods in a warehouse according to claim 6, wherein: The similarity matrix between the various categories is determined according to the following formula: Among them, W ij Represents the element in the i-th row and j-th column of the similarity matrix, K ij is the order set containing category i and category j, k is the order number in the order set, W ii =0; Alternatively, the similarity matrix between the various categories is determined according to the following formula: Among them, W ij represents the element in the i-th row and j-th column of the similarity matrix, |P k | represents the number of types of goods in order k, W ii =0; Alternatively, the similarity matrix between the various categories is determined according to the following formula: IN ij =Z ij -min Z ij Among them, W ij Represents the element in the i-th row and j-th column of the similarity matrix, Z ij Represents the element in the i-th row and j-th column of the matrix Z. The matrix Z is the covariance matrix of the order matrix F, F∈R M×W , where M is the order quantity, N is the number of categories of goods in the corresponding alternative goods set, and F mn =1 indicates the element in the mth row and nth column of F, which means that order m contains goods of category n. mn =0 means that order m does not contain goods of category n.

8. The method for storing goods in a warehouse according to claim 1, wherein: In the case where the cargo selection model includes a third cargo selection model, the step of determining the classification of cargo to be stored in the storage area from the corresponding candidate cargo set according to each cargo selection model and constraint conditions includes: In the third product selection model, the order matrix is ​​reduced in dimension, where the order matrix F∈R M×N , where M is the order quantity, N is the number of categories of goods in the corresponding alternative goods set, and F mn =1 indicates the element in the mth row and nth column of F, which means that order m contains goods of category n. mn =0 means that order m does not contain goods of category n; Perform spectral clustering on the order matrix after dimension reduction; According to the second objective function and the constraint condition, a cluster is selected from each cluster after spectral clustering, and the classification of the goods in the selected cluster is determined as the classification of the goods stored in the storage area; wherein the second objective function represents a function with the smallest number of types of selected goods.

9. The method for storing goods in a warehouse according to claim 1, wherein: In the case where the cargo selection model includes the fourth cargo selection model, the determining the classification of the cargo to be stored in the storage area from the corresponding candidate cargo set according to each cargo selection model and the constraint condition includes: In the fourth product selection model, the order matrix is ​​uniformly sampled to obtain a sampled matrix, where the order matrix F∈R M×N , where M is the order quantity, N is the number of categories of goods in the corresponding alternative goods set, and F mn =1 indicates the element in the mth row and nth column of F, which means that order m contains goods of category n. mn =0 means that order m does not contain goods of category n; Determining the classification of goods stored in the storage area according to the third objective function and the constraint conditions; The third objective function is expressed by the following formula: max(N X -‖b-Ax‖0)+(N X -‖b-A(e-x)‖0) Among them, N X Represents the number of rows of the sampled matrix A, b = Ae, e = [1,1,…,1] T ,x represents the classification selection vector, and the element x in x i =1 means that category i is selected and stored in this storage area, x i =0 means that category i is not selected to be stored in this storage area.

10. The method for storing goods in a warehouse according to claim 1, wherein: The selecting a storage plan according to at least one of the order confluence ratio, the number of goods types, the capacity utilization rate and the volume utilization rate of each storage plan determined includes: For each storage scheme, determine the first parameter according to the ratio of the difference between the order confluence ratio of the storage scheme and the minimum value of the order confluence ratio of each storage scheme to the difference between the maximum value and the minimum value of the order confluence ratio of each storage scheme; Determine the second parameter according to the ratio of the difference between the number of goods types in the storage scheme and the minimum number of goods types in each storage scheme and the difference between the maximum value and the minimum value of the number of goods types in each storage scheme; Determine a third parameter according to a ratio of a difference between the capacity utilization rate of the storage scheme and the minimum value of the capacity utilization rates of various storage schemes to a difference between a maximum value and a minimum value of the capacity utilization rates of various storage schemes; Determine a fourth parameter according to a ratio of a difference between the volume utilization rate of the storage scheme and the minimum value of the volume utilization rates of various storage schemes to a difference between a maximum value and a minimum value of the volume utilization rates of various storage schemes; The first parameter, the second parameter, the third parameter, and the fourth parameter corresponding to the storage scheme are weighted, and a storage scheme with the largest corresponding weighted value is selected.

11. A cargo storage device in a warehouse, comprising: An acquisition module, used to acquire the available capacity and capacity interval of each storage area, as well as the inventory volume and average outbound quantity in unit measurement of each classification of goods in a preset historical time period; the capacity interval is the average outbound quantity interval in unit measurement of the storage area; A determination module is used to determine, for each storage area, the classification of goods stored in the storage area from the corresponding set of candidate goods according to each goods selection model and constraint conditions, obtain multiple storage schemes corresponding to the storage area, and use test data to determine the order confluence ratio, the number of goods types, and at least one of the capacity utilization rate and volume utilization rate of each storage scheme, wherein the test data includes: information of each order in another historical time period different from the preset historical time period, and select a storage scheme according to at least one of the order confluence ratio, the number of goods types, the capacity utilization rate and the volume utilization rate of each storage scheme determined, and determine the classification of goods stored in the storage area according to the selected storage scheme, wherein the constraint condition includes: the sum of the inventory volume of the goods stored in the storage area does not exceed the available volume of the storage area , the sum of the average outgoing quantity in the unit measurement is within the capacity range of the storage area. For each storage scheme, the ratio of the number of merged orders in the test data to the total number of orders is used as the order merge ratio, wherein some of the goods in the merged order belong to the category of goods corresponding to the storage scheme, and some of the goods do not belong to the category of goods corresponding to the storage scheme, or, for each storage scheme, the goods belonging to the category corresponding to the storage scheme are used as reference goods, and the ratio of the average outgoing quantity in the unit measurement of the reference goods to the upper limit of the capacity range of the storage area is determined according to the test data as the capacity utilization rate, or, for each storage scheme, the goods belonging to the category of goods corresponding to the storage scheme are used as reference goods, and the ratio of the inventory volume of the reference goods to the available volume of the storage area is determined according to the test data as the volume utilization rate; The storage module is used to store the goods of each category in the corresponding storage area according to the determined categories of the goods to be stored in each storage area.

12. A cargo storage device in a warehouse, comprising: processor; as well as A memory coupled to the processor is used to store instructions, and when the instructions are executed by the processor, the processor executes the method for storing goods in a warehouse as described in any one of claims 1-10.

13. A non-transitory computer-readable storage medium having a computer program stored thereon, wherein: When the program is executed by a processor, the steps of the method for storing goods in a warehouse as described in claims 1-10 are implemented.

Images