Article storage method and device

Abstract

The invention discloses an article storage method and device, and relates to the technical field of intelligent logistics. A specific embodiment of the method comprises the steps of obtaining a storage condition of each storage category in a target warehouse in a historical time period; according to the category information of each storage category and the storage condition, determining floor information corresponding to each floor in the target warehouse and association degree information between every two storage categories; wherein the category information comprises weight information; inputting the floor information, the category information and the association degree information into a preset article storage model, and outputting to obtain a target floor corresponding to each storage category; wherein the object storage model takes the maximum correlation degree between every two storage categories and the minimum total weight loss of each floor as an objective function. According to the implementation mode, in the article storage process, it is guaranteed that the related articles are stacked in a classified mode so as to improve the delivery efficiency of the articles, meanwhile, it is guaranteed that the articles are stacked by floors according to the weight, and potential safety hazards are avoided.

Description

Technical Field

[0001] The present invention relates to the field of smart logistics technology, and in particular to a method and device for storing items. Background Art

[0002] The storage of items in the warehouse is an important part of logistics management. How to store items will directly affect the warehouse's operating efficiency and cost. At present, there are optimization solutions for the storage of warehouse items based on item categories and picking paths, which mainly place items reasonably based on the convenience of picking and the efficiency of item outbound delivery.

[0003] However, this optimization solution can only be applied to flat warehouses with a single floor. When there are many floors in the warehouse, considering the unclear upper limit of the load-bearing capacity of the warehouse floors themselves, we can only place large items on the lower floors as much as possible based on manual experience to avoid safety hazards such as floor collapse, and it is impossible to effectively optimize the items as a whole. Summary of the invention

[0004] In view of this, the embodiment of the present invention provides an optimization method and device for article storage. Based on the category information of each storage category and the storage status of each storage category in the warehouse, the correlation information between the storage categories can be calculated first, and the correlation information, floor information, and category information including weight information are used as the input of the article storage model, and the objective function including both the correlation and the floor weight is calculated, and finally the target floor corresponding to each storage category is output. In the process of article storage, it is achieved that the related articles are classified and stacked to improve the efficiency of the articles leaving the warehouse, and the articles are stacked on different floors according to their weight, avoiding safety hazards.

[0005] To achieve the above objective, according to one aspect of an embodiment of the present invention, a method for storing items is provided.

[0006] A method for storing items in an embodiment of the present invention includes: obtaining the storage status of each storage category in a target warehouse within a historical time period; determining the floor information corresponding to each floor in the target warehouse and the correlation information between every two storage categories based on the category information of each storage category and the storage status; wherein the category information includes weight information; inputting the floor information, the category information and the correlation information into a preset item storage model, and outputting the target floor corresponding to each storage category; wherein the item storage model uses the maximum correlation between every two storage categories and the minimum total weight loss on each floor as the objective function.

[0007] Optionally, the floor information includes: the upper limit of the floor's production capacity, the upper limit of the floor's load-bearing capacity, the upper limit of the floor's energy storage capacity, and the upper limit of the number of categories on the floor; the floor information corresponding to each floor in the target warehouse is determined according to the category information of each of the storage categories and the storage situation, including: determining the production capacity, load-bearing capacity, energy storage capacity, and number of categories corresponding to each floor in the target warehouse per unit time period according to the category information and the storage situation of the target warehouse in the historical time period; and taking the maximum values ​​of the production capacity, load-bearing capacity, energy storage capacity, and number of categories in the unit time period as the upper limit of the floor's production capacity, the upper limit of the floor's load-bearing capacity, the upper limit of the floor's energy storage capacity, and the upper limit of the number of categories on the floor.

[0008] Optionally, after obtaining the storage status of each storage category in the target warehouse within the historical time period, it also includes: obtaining multiple item categories belonging to different brands under each storage category; determining the historical weight information corresponding to the storage category within multiple unit time periods based on the unit weight of each of the item categories and the storage status; and based on a preset weight prediction model, predicting the weight information corresponding to the storage category based on the multiple historical weight information.

[0009] Optionally, the storage situation includes the storage quantity; the historical weight information corresponding to the storage category in multiple unit time periods is determined according to the unit weight of each of the item categories and the storage situation, including: determining the total weight of each of the item categories in multiple unit time periods according to the weight and storage quantity of each of the item categories; determining the total weight corresponding to the storage category in multiple unit time periods according to the total weight; and taking the average of multiple total weights to obtain the historical weight information.

[0010] Optionally, determining the correlation information between every two of the storage categories includes: obtaining historical outbound order data corresponding to the warehousing situation; and determining the correlation information between every two of the storage categories based on the number of times each two of the storage categories appear at the same time in the historical outbound order data.

[0011] Optionally, the item storage model is solved using gurobi or cplex as a solver.

[0012] Optionally, the constraints of the item storage model include at least one of the following: each of the storage categories is stored on only one floor, the total weight of the storage categories in the target warehouse does not exceed the total load-bearing capacity of the target warehouse, two categories with opposite category attributes cannot be stored on the same floor, and the total storage energy, total production capacity and total volume of each storage category in the target warehouse do not exceed the corresponding energy storage upper limit, production capacity upper limit and volume upper limit.

[0013] To achieve the above objective, according to another aspect of an embodiment of the present invention, a device for storing items is provided.

[0014] An article storage device according to an embodiment of the present invention includes:

[0015] The acquisition module is used to obtain the storage status of each storage category in the target warehouse within the historical time period;

[0016] A determination module, configured to determine the floor information corresponding to each floor in the target warehouse and the correlation information between every two storage categories according to the category information of each storage category and the storage situation;

[0017] A model calculation module, used to input the floor information, the storage category information and the correlation information into a preset item storage model, and output a target floor corresponding to each storage category;

[0018] The category information includes weight information, and the object storage model takes the maximum correlation between every two storage categories and the minimum total weight loss on each floor as the objective function.

[0019] To achieve the above objective, according to another aspect of an embodiment of the present invention, an electronic device for storing items is provided.

[0020] An electronic device for storing items according to an embodiment of the present invention comprises: one or more processors; a storage device for storing one or more programs, and when the one or more programs are executed by the one or more processors, the one or more processors implement a method for storing items according to an embodiment of the present invention.

[0021] To achieve the above objective, according to another aspect of an embodiment of the present invention, a computer-readable storage medium is provided.

[0022] A computer-readable storage medium according to an embodiment of the present invention stores a computer program, which, when executed by a processor, implements a method for storing items according to an embodiment of the present invention.

[0023] One embodiment of the above invention has the following advantages or beneficial effects: based on the category information of each storage category and the storage conditions of each storage category in the warehouse, the correlation information between the storage categories can be calculated first, and the correlation information, floor information, and category information including weight information are used as inputs of the item storage model, and the target function including both the correlation and the floor weight is calculated, and finally the target floor corresponding to each storage category is output. In the process of item storage, it is achieved that the related items are classified and stacked to improve the efficiency of the items leaving the warehouse, and the items are stacked by weight on different floors to avoid safety hazards.

[0024] The further effects of the above-mentioned non-conventional optional manner will be described below in conjunction with the specific implementation manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] The accompanying drawings are used to better understand the present invention and do not constitute an improper limitation of the present invention.

[0026] Figure 1 is a schematic diagram of the main flow of the method for storing items according to an embodiment of the present invention;

[0027] Figure 2 is a schematic diagram of the overall process of the method for storing items according to an embodiment of the present invention;

[0028] Figure 3 This is a schematic diagram of a main process of obtaining floor information according to an embodiment of the present invention;

[0029] Figure 4 is another main flow chart of obtaining floor information according to an embodiment of the present invention;

[0030] Figure 5 is a schematic diagram of a main process of determining historical weight information according to an embodiment of the present invention;

[0031] Figure 6 is a comparison result of the number of storage categories on each floor before and after the item storage method is scheduled according to an embodiment of the present invention;

[0032] Figure 7 is a comparison result of the total weight of items on each floor before and after scheduling by the item storage method according to an embodiment of the present invention;

[0033] Figure 8 is a schematic diagram of main modules of an apparatus for storing items according to an embodiment of the present invention;

[0034] Fig. 9 is an exemplary system architecture diagram to which embodiments of the present invention may be applied;

[0035] Fig.10 It is a schematic diagram of the structure of a computer system of a terminal device or a server suitable for implementing an embodiment of the present invention. DETAILED DESCRIPTION

[0036] The following is a description of exemplary embodiments of the present invention in conjunction with the accompanying drawings, including various details of the embodiments of the present invention to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present invention. Similarly, for clarity and conciseness, the description of well-known functions and structures is omitted in the following description.

[0037] It should be pointed out that the embodiments of the present invention and the technical features therein may be combined with each other without conflict.

[0038] It should be noted that the collection, collection, updating, analysis, processing, use, transmission, storage and other aspects of user personal information involved in the technical solution of this disclosure are in compliance with the provisions of relevant laws and regulations, are used for legitimate purposes, and do not violate public order and good morals. Necessary measures are taken for user personal information to prevent illegal access to user personal information data and maintain the security of user personal information, network security and national security.

[0039] Figure 1 It is a schematic diagram of main steps of a method for storing items according to an embodiment of the present invention.

[0040] like Figure 1 As shown, the method for storing items in the embodiment of the present invention mainly includes the following steps:

[0041] Step S101: Obtain the storage status of each storage category in the target warehouse within a historical period;

[0042] Step S102: According to the category information and storage status of each storage category, determine the floor information corresponding to each floor in the target warehouse and the correlation information between every two storage categories; wherein the category information includes weight information;

[0043] Step S103: Input the floor information, category information and correlation information into a preset item storage model, and output the target floor corresponding to each storage category; wherein the item storage model takes the maximum correlation between every two storage categories and the minimum total weight loss on each floor as the objective function.

[0044] In the embodiment of the present invention, the target warehouse can be understood as a warehouse that needs to optimize the storage of items. Since the embodiment of the present invention is mainly aimed at a warehouse with multiple floors, the target warehouse includes at least two floors, and each floor stores items of different storage categories. In addition, the storage category in one case refers to a variety of items belonging to a certain category, such as 500ml mineral water of different brands. Under the sku dimension, 500ml mineral water of brand A, 500ml mineral water of brand B and 500ml mineral water of brand C are three different skus, but the storage categories they belong to are all bottled mineral water. For the storage situation of each storage category in step S101, it can be understood as the current storage location and storage quantity of 500ml mineral water of brand A, 500ml mineral water of brand B and 500ml mineral water of brand C in the target warehouse respectively.

[0045] In the embodiment of the present invention, the optimization of item storage based on the storage category dimension can ensure that items of the same storage category are stacked together as much as possible, which is convenient for the outbound personnel to quickly search by area during the outbound process, and there will be no situation where 500ml mineral water of brand A, 500ml mineral water of brand B, and 500ml mineral water of brand C are stored on the first floor, second floor, and third floor of the target warehouse respectively. At the same time, using the storage category as the dimension of storage optimization can effectively reduce the amount of calculation of the item storage model in the calculation process, and facilitate rapid solution to obtain the optimal solution. When the computing power and operation speed of the item storage model can be achieved, it can also be optimized directly based on the sku dimension, that is, step S101 is to obtain the storage status of each minimum inventory unit in the target warehouse during the historical time period, and in the subsequent step S103, the category information is replaced with the item information of the minimum inventory unit to solve the model, so as to output the target floor corresponding to each minimum inventory unit.

[0046] It is understandable that it is necessary to first obtain the floor information corresponding to each floor according to the storage situation of each storage category in the target warehouse in the historical time period. Specifically, the floor information includes: the upper limit of the production capacity of the floor, the upper limit of the load-bearing capacity of the floor, the upper limit of the energy storage capacity of the floor, and the upper limit of the number of categories of the floor. Since there is no clear upper limit of production capacity, upper limit of load-bearing capacity, upper limit of energy storage capacity and upper limit of the number of categories for each floor of the target warehouse, it is necessary to estimate the floor information according to the storage situation in the historical time period to ensure that after the storage of items is optimized, it will not exceed the upper limit that the floor can bear in all aspects. Therefore, in an optional embodiment, the process of determining the floor information in step S102 includes: determining the production capacity, load-bearing capacity, energy storage capacity, and number of categories corresponding to each floor in the target warehouse per unit time period according to the category information and the storage situation of the target warehouse in the historical time period; and taking the maximum values ​​of the production capacity, load-bearing capacity, energy storage capacity, and number of categories in the unit time period as the upper limit of the production capacity of the floor, the upper limit of the load-bearing capacity of the floor, the upper limit of the energy storage capacity of the floor, and the upper limit of the number of categories of the floor.

[0047] Specifically, the above process can be Figure 2 The overall process is shown in the figure. Figure 2 In the process, firstly, based on the storage situation of each storage category in the target warehouse during the historical period and the item information corresponding to each specific item in the storage category, the category information including weight information, various floor information, and correlation information are determined. Then, the calculated floor information, category information, and correlation information are input into the item storage model for solution, and finally the item storage adjustment plan is output.

[0048] The process of obtaining floor information is described below with a specific embodiment. Figure 3 As shown, including:

[0049] Step S301: determining a plurality of unit time periods from the historical time periods;

[0050] Step S302: Obtain the storage location and storage quantity of each minimum inventory unit in the target warehouse within each unit time period;

[0051] Step S303: summing up the storage locations and storage quantities corresponding to the minimum inventory units of the same storage category to obtain the storage location and storage quantity of each storage category within a unit time period;

[0052] For each unit time period, execute step S304 to step S305;

[0053] Step S304: determining multiple target storage categories stored on the same floor according to the storage locations;

[0054] Step S305: for multiple target storage categories corresponding to the same floor: determine the capacity, energy storage, quantity of stored categories and weight corresponding to the floor according to the capacity information, energy storage information, weight information and quantity information in the category information;

[0055] Step S306: Taking the maximum values ​​of production capacity, load-bearing capacity, energy storage capacity, and number of categories in multiple unit time periods as the upper limit of production capacity, the upper limit of load-bearing capacity, the upper limit of energy storage capacity, and the upper limit of number of categories on the floor.

[0056] Among them, the warehouse storage scheduling is usually based on days, so the historical time period in the embodiment of the present invention can be understood as a historical month or historical N days, and the unit time period can be every day. According to the storage location and storage quantity of each sku or each storage category in the target warehouse every day, the production capacity, energy storage, number of stored categories and weight corresponding to each floor can be calculated respectively on each day, and the maximum value in the historical time period is used as the upper limit value, so as to obtain the upper limit of the production capacity of the floor, the upper limit of the load-bearing capacity of the floor, the upper limit of the energy storage capacity of the floor, and the upper limit of the number of categories of the floor.

[0057] In an optional embodiment, since the storage quantities corresponding to the item categories of different brands under each storage category are constantly changing in each unit time period within the historical time period, and the embodiment of the present invention optimizes the storage of items based on the storage category as a dimension, it is different from the sku dimension which has a standard weight. Therefore, it is necessary to first integrate the weight information corresponding to the storage category according to the historical weight information corresponding to the storage category in each unit time period, so as to ensure the accuracy of the floor information in the process of determining the floor information. Therefore, after step S101, it is necessary to first determine the weight information corresponding to each storage category, that is, in an optional embodiment, the process of determining the floor information corresponding to each floor in step S102 can also be as follows: Figure 4 As shown, including:

[0058] Step S401: determining a plurality of unit time periods from the historical time periods;

[0059] Step S402: obtaining multiple categories of items belonging to different brands under each storage category in each unit time period;

[0060] Step S403: determining historical weight information corresponding to the storage categories within multiple unit time periods according to the unit weight and storage status of each item category;

[0061] Step S404: Based on a preset weight prediction model, weight information corresponding to the storage category is predicted according to a plurality of historical weight information;

[0062] For each unit time period, execute step S405 to step S406;

[0063] Step S405: determining multiple target storage categories stored on the same floor according to the storage locations;

[0064] Step S406: for multiple target storage categories corresponding to the same floor: determine the production capacity, energy storage, quantity of stored categories and weight corresponding to the floor according to the production capacity information, energy storage information, weight information and quantity information in the category information;

[0065] Step S407: Taking the maximum values ​​of production capacity, load-bearing capacity, energy storage capacity, and number of categories in multiple unit time periods as the upper limit of production capacity, the upper limit of load-bearing capacity, the upper limit of energy storage capacity, and the upper limit of number of categories on the floor.

[0066] Among them, the preset weight prediction model can adopt common machine learning models, such as linear regression, decision tree, random forest and support vector machine, etc., preferably an XGBoost model. The present invention is not limited to this, and it can achieve the prediction of weight information for a period of time in the future based on historical weight information.

[0067] Specifically, for the process of obtaining historical weight information corresponding to storage categories within multiple unit time periods in step S403, in an optional embodiment, the following can be performed: Figure 5 As shown, including:

[0068] Step S501: determining the total weight of each item category within a plurality of unit time periods according to the weight and storage quantity of each item category;

[0069] Step S502: determining the total weights of the storage categories corresponding to the multiple unit time periods according to the total weights;

[0070] Step S503: taking an average of multiple total weights to obtain historical weight information.

[0071] For example, in unit time period 1, the storage category of bottled mineral water includes 500 pieces of 500ml mineral water of brand A and 500 pieces of 500ml mineral water of brand B, where, due to the different outer packaging styles of brand A and brand B, the weight of each piece of brand A mineral water is a, and the weight of each piece of brand B mineral water is b, so in unit time period 1, the total weight corresponding to the storage category of bottled mineral water is 500a+500b. In unit time period 2, the storage category of bottled mineral water includes 400 pieces of 500ml mineral water of brand A and 600 pieces of 500ml mineral water of brand B, so in unit time period 2, the total weight corresponding to the storage category of bottled mineral water is 400a+600b. Although the total number of bottled mineral water storage categories in unit time period 1 and unit time period 2 is 1,000 pieces, due to the difference in weight and storage quantity of each item category, the total weight of the same storage category in unit time period 1 and unit time period 2 is different, so the average value of the total weight corresponding to multiple unit time periods can be used as the historical weight information. It can be understood that taking the average value is only one way to determine the historical weight information, and other calculation rules can also be used, which is not limited by the present invention.

[0072] For the process of determining the association information between every two storage categories in step S102, an optional embodiment may include: obtaining historical outbound order data corresponding to the storage situation; determining the association information between every two storage categories according to the number of times every two storage categories appear at the same time in the historical outbound order data. Exemplarily, in the same historical outbound order, every time two storage categories appear at the same time, the association corresponding to the two storage categories is added by 1, so that the association information between any two storage categories can be calculated based on all the historical outbound order data, thereby determining whether there is a strong association between the storage categories, so as to place them close to each other in the subsequent item scheduling.

[0073] After determining the floor information, category information and correlation information, the process of step S103 can be executed to obtain the target floor corresponding to each storage category by solving the objective function of the item storage model. The specific construction process and solution process of the item storage model are described in detail below:

[0074] Model construction: Parameters, sets, decision variables, and objective functions are constructed based on category information, floor information, and correlation information, as shown below:

[0075] gather

[0076] I Category Collection J Floor Collection <![CDATA[T nor ]]> Month Collection

[0077] parameter

[0078]

[0079] Decision variables

[0080]

[0081] Objective Function

[0082]

[0083] Among them, the first Represents the correlation information between every two storage categories. Specifically, Represents the correlation information, the second term ∑ j a j ∑ i x ij w i q i It represents the total weight loss of multiple floors of the target warehouse, where the storage capacity can be taken as the maximum value of the energy storage in the monthly set, that is, Since the overall objective function is to solve the maximum value, the coefficient of the first term is 1 and the coefficient of the second term is -1. Therefore, the objective function is to maximize the correlation between every two storage categories and minimize the total weight loss on each floor.

[0084] In an optional embodiment, the objective function of the present invention also takes into account the number of floors in use. Since the rental and equipment costs of each floor are usually more considerable than the operating costs, the objective function of the item storage model in the embodiment of the present invention is further shown as follows:

[0085]

[0086] The second term is the total number of floors used, and the coefficient By assigning a larger coefficient 4cof to the second item, the value of the second item can be made much larger than the first and third items, thereby increasing the priority of the second item. Furthermore, since the coefficient of the second item is -4cof, through the objective function of the above formula (2), the correlation between every two storage categories can be maximized and the total weight loss of each floor can be minimized while ensuring the minimum number of floors used.

[0087] Furthermore, in the process of solving the objective function, multiple constraints need to be set to solve the optimal solution under the constraint conditions, so as to obtain a better item scheduling solution. In an optional embodiment, the constraint conditions of the item storage model include at least one of the following: each of the storage categories is stored on only one floor, the total weight of each storage category in the target warehouse does not exceed the total load-bearing capacity of the target warehouse, two categories with relative category attributes cannot be stored on the same floor, and the total storage energy, total production capacity and total volume of each storage category in the target warehouse do not exceed the corresponding storage energy upper limit, production capacity upper limit and volume upper limit.

[0088] The constraints are described in detail below, as shown in formula (3) to formula (13):

[0089]

[0090] ∑ i x ij ≥M(u j -1)+1 formula (4)

[0091] ∑ i x ij ≤Mu j Formula (5)

[0092]

[0093]

[0094] Among them, formula (3) can ensure that each storage category is stored on only one floor, avoiding the problem of a single storage category being stored on multiple floors, which affects the efficiency of outbound delivery; formulas (4) and (5) indicate whether a floor is used and whether there is an association between the storage categories on the floor, where M is a sufficiently large integer, such as 99999. When a floor is used, the left side of inequality (5) is a number greater than 0, so the right side u j It needs to be 1, and inequality (4) also holds. When the floor is not in use, the left side of inequality (5) is equal to 0, and the right side u j It needs to be 0 so that inequalities (4) and (5) hold simultaneously. Formula (6) represents the relationship between the correlation variable and the storage category placement variable. For example, for a specific floor If categories i1 and i2 are both on this floor, then In this case, Since the item related to this variable in the objective function takes the maximum value, On the contrary, when When one of them is 0, Formula (7) represents the load-bearing limit of each floor. When the building is completed, the developer will provide the maximum weighing limit W of multiple floors (i.e. the entire target warehouse) j Formulas (8)-(11) respectively represent the restrictions on floor energy storage, production capacity, number of categories and volume. The left side of the inequality is the sum of the specific information of each storage category in terms of energy storage, production capacity, number of categories and volume. The right side of the inequality is the upper limit of each dimension of the floor. Since the number of categories, production capacity and volume may fluctuate over time, the upper limit requirements need to be met in each time period. Formula (12) represents the constraints on the relationship between storage categories with relative category attributes, that is, it means that storage categories i1 and i2 with relative category attributes cannot be stored on the same floor. For example, flammable and explosive storage categories cannot be placed on the same floor with fast-burning storage categories, and should be placed on the same floor with non-flammable storage categories as much as possible. Formula (13) represents the issue of floor priority. Usually, the floors are used from the bottom right to the top, that is, the lower floors have a higher priority.

[0095] In a further optional embodiment, the item storage model provided by the embodiment of the present invention can use gurobi or cplex as a solver to solve the optimal solution according to the above-mentioned multiple constraints and objective functions.

[0096] According to the method for storing items in an embodiment of the present invention, based on the category information of each storage category and the storage conditions of each storage category in the warehouse, the correlation information between the storage categories can be calculated first, and the correlation information, floor information, and category information including weight information are used as inputs of the item storage model, and the target function including both the correlation and the floor weight is calculated, and finally the target floor corresponding to each storage category is output. In the process of item storage, it is achieved that the related items are classified and stacked to improve the efficiency of the items leaving the warehouse, and the items are stacked by weight on different floors to avoid safety hazards.

[0097] The embodiment of the present invention uses the above-mentioned method for storing items to perform item storage scheduling on a target warehouse that actually contains three floors, and obtains the following: Figure 6 The comparison results of the number of storage categories on each floor before and after scheduling are shown in the figure. Figure 7 The comparison results of the total weight of items on each floor before and after scheduling are shown in the figure. Figure 6 The blue bar graph in the figure shows the number of storage categories on each floor before optimization, and the red bar graph shows the number of storage categories on each floor after optimization. Figure 6It can be seen that after the item storage method of the embodiment of the present invention is adjusted, most of the goods of the same category are on the same warehouse floor, and the storage of the same category is more concentrated, which is convenient for warehouse operation and management. And because highly related items are placed on the same floor, the splitting rate of outbound orders is greatly reduced. When the average daily outbound volume of the warehouse is 22,000 orders, the number of split orders that can be reduced each year is about 56,000, and the splitting rate can be reduced by 0.7%, which greatly reduces the cost of packaging and transportation. Figure 7 In the figure, the green bar graph is the result of optimizing items based on the conventional item scheduling model in the prior art, which does not consider the weight information in the category information and the weight factor of each floor in the item storage model. The blue bar graph represents the total weight of the storage categories stored on each floor before optimization, and the red bar graph represents the total weight of the storage categories stored on each floor after optimization. Figure 7 It can be seen that after optimization of the item storage method in the embodiment of the present invention, the total weight of items stored on high floors has been significantly reduced, and the total weight of items stored on low floors has been significantly increased. Compared with the optimization scheme of the prior art, the safety hazard of floor collapse caused by heavy top and light bottom has been greatly reduced.

[0098] Figure 8 Schematic diagram of main modules of an apparatus for storing items according to an embodiment of the present invention.

[0099] like Figure 8 As shown, the device 800 for storing items according to the embodiment of the present invention includes:

[0100] The acquisition module 801 is used to acquire the storage status of each storage category in the target warehouse within a historical period;

[0101] A determination module 802 is used to determine the floor information corresponding to each floor in the target warehouse and the correlation information between every two storage categories according to the category information of each storage category and the storage situation;

[0102] The model calculation module 803 is used to input the floor information, the storage category information and the correlation information into a preset item storage model, and output a target floor corresponding to each storage category;

[0103] The category information includes weight information, and the object storage model takes the maximum correlation between every two storage categories and the minimum total weight loss on each floor as the objective function.

[0104] In an optional embodiment of the present invention, the floor information includes: the upper limit of the floor's production capacity, the upper limit of the floor's load-bearing capacity, the upper limit of the floor's energy storage capacity, and the upper limit of the number of categories on the floor; the determination module 802 is also used to determine the production capacity, load-bearing capacity, energy storage capacity, and number of categories corresponding to each floor in the target warehouse per unit time period based on the category information and the storage status of the target warehouse in the historical time period; and the maximum values ​​of the production capacity, load-bearing capacity, energy storage capacity, and number of categories in the unit time period are used as the upper limit of the floor's production capacity, the upper limit of the floor's load-bearing capacity, the upper limit of the floor's energy storage capacity, and the upper limit of the number of categories on the floor.

[0105] In an optional embodiment of the present invention, the determination module 802 is further used to, after obtaining the storage status of each storage category in the target warehouse within the historical time period, obtain multiple item categories belonging to different brands under each storage category; determine the historical weight information corresponding to the storage category within multiple unit time periods based on the unit weight of each of the item categories and the storage status; and based on a preset weight prediction model, predict the weight information corresponding to the storage category based on the multiple historical weight information.

[0106] In an optional embodiment of the present invention, the storage situation includes the storage quantity; the determination module 802 is also used to determine the total weight of each of the item categories in multiple unit time periods based on the weight and storage quantity of each of the item categories; determine the total weight corresponding to the storage categories in multiple unit time periods based on the total weight; and take the average of the multiple total weights to obtain the historical weight information.

[0107] In an optional embodiment of the present invention, the determination module 802 is also used to obtain historical outbound order data corresponding to the warehousing situation; and determine the correlation information between each two of the warehousing categories based on the number of times each two of the warehousing categories appear at the same time in the historical outbound order data.

[0108] In an optional embodiment of the present invention, the item storage model is solved using gurobi or cplex as a solver.

[0109] In an optional embodiment of the present invention, the constraints of the item storage model include at least one of the following: each of the storage categories is stored on only one floor, the total weight of the storage categories in the target warehouse does not exceed the total load-bearing capacity of the target warehouse, two categories with opposite category attributes cannot be stored on the same floor, and the total storage energy, total production capacity and total volume of each storage category in the target warehouse do not exceed the corresponding energy storage upper limit, production capacity upper limit and volume upper limit.

[0110] According to the device for storing items in the embodiment of the present invention, based on the category information of each storage category and the storage conditions of each storage category in the warehouse, the correlation information between the storage categories can be calculated first, and the correlation information, floor information, and category information including weight information are used as the input of the item storage model, and the target function including both the correlation and the floor weight is calculated, and finally the target floor corresponding to each storage category is output. In the process of item storage, it is achieved that the related items are classified and stacked to improve the efficiency of the outbound delivery of the items, and the items are stacked by weight on different floors to avoid safety hazards.

[0111] Fig. 9 An exemplary system architecture 900 is shown to which the method for storing items or the apparatus for storing items according to the embodiments of the present invention may be applied.

[0112] like Fig. 9 As shown, system architecture 900 may include terminal devices 901, 902, 903, network 904 and server 905. Network 904 is used to provide a medium for communication links between terminal devices 901, 902, 903 and server 905. Network 904 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0113] The user can use the terminal devices 901, 902, 903 to interact with the server 905 through the network 904 to receive or send data, etc. Various communication client applications can be installed on the terminal devices 901, 902, 903, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social platform software, etc.

[0114] The terminal devices 901 , 902 , and 903 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers, and desktop computers, etc.

[0115] Server 905 can be a server that provides various services, such as a background management server that provides support for item storage scheduling requests sent by users using terminal devices 901, 902, and 903. That is, the item storage method provided by the present invention is based on the item storage scheduling request sent by the user using terminals 901, 902, and 903. After execution, the background management server integrates the target floor corresponding to each storage category into an item storage result and feeds it back to terminals 901, 902, and 903.

[0116] It should be noted that the method for storing items provided in the embodiment of the present invention is generally executed by the server 905 , and accordingly, the device for storing items is generally set in the server 905 .

[0117] It should be understood that Fig. 9 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0118] Reference below Fig.10 , which shows a schematic diagram of the structure of a computer system 1000 of a terminal device suitable for implementing an embodiment of the present invention. Fig.10 The terminal device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0119] like Fig.10 As shown, the computer system 1000 includes a central processing unit (CPU) 1001, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1002 or a program loaded from a storage part 1008 into a random access memory (RAM) 1003. In the RAM 1003, various programs and data required for the operation of the system 1000 are also stored. The CPU 1001, the ROM 1002, and the RAM 1003 are connected to each other through a bus 1004. An input / output (I / O) first interface 1005 is also connected to the bus 1004.

[0120] The following components are connected to the I / O first interface 1005: an input section 1006 including a keyboard, a mouse, etc.; an output section 1007 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 1008 including a hard disk, etc.; and a communication section 1009 including a network first interface card such as a LAN card, a modem, etc. The communication section 1009 performs communication processing via a network such as the Internet. A drive 1010 is also connected to the I / O first interface 1005 as needed. A removable medium 1011, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 1010 as needed, so that a computer program read therefrom is installed into the storage section 1008 as needed.

[0121] In particular, according to the embodiments disclosed in the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present invention include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 1009, and / or installed from the removable medium 1011. When the computer program is executed by the central processing unit (CPU) 1001, the above-mentioned functions defined in the system of the present invention are executed.

[0122] It should be noted that the computer-readable medium shown in the present invention may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present invention, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0123] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present invention. In this regard, each box in the flow chart or block diagram can represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flow chart, and the combination of the boxes in the block diagram or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0124] The modules involved in the embodiments of the present invention may be implemented by software or hardware. The modules described may also be set in a processor, for example, they may be described as: a processor includes an acquisition module, a determination module, and a model calculation module. The names of these modules do not constitute a limitation on the modules themselves in some cases. For example, the acquisition module may also be described as a "module for acquiring the storage status of each storage category in the target warehouse within a historical time period."

[0125] As another aspect, the present invention also provides a computer-readable medium, which may be included in the device described in the above embodiment; or it may exist independently and not be assembled into the device. The above computer-readable medium carries one or more programs, and when the above one or more programs are executed by a device, the device includes: obtaining the storage status of each storage category in the target warehouse within a historical time period; determining the floor information corresponding to each floor in the target warehouse and the correlation information between every two storage categories according to the category information and the storage status of each storage category; wherein the category information includes weight information; inputting the floor information, the category information and the correlation information into a preset item storage model, and outputting the target floor corresponding to each storage category; wherein the item storage model takes the maximum correlation between every two storage categories and the minimum total weight loss of each floor as the objective function.

[0126] According to the technical solution of the embodiment of the present invention, based on the category information of each storage category and the storage situation of each storage category in the warehouse, the correlation information between the storage categories can be calculated first, and the correlation information, floor information, and category information including weight information are used as the input of the item storage model, and the target function including both the correlation and the floor weight is calculated, and finally the target floor corresponding to each storage category is output. In the process of item storage, it is achieved that the related items are classified and stacked to improve the efficiency of the outbound delivery of the items, and the items are stacked by weight on different floors to avoid safety hazards.

[0127] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may occur depending on design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for storing items, characterized in that: include: Obtain the storage status of each storage category in the target warehouse during the historical period; According to the category information of each of the storage categories and the storage situation, determine the floor information corresponding to each floor in the target warehouse and the correlation information between every two of the storage categories; wherein the category information includes weight information; Input the floor information, the category information and the correlation information into a preset item storage model, and output the target floor corresponding to each storage category; The object storage model takes the maximum correlation between every two storage categories and the minimum total weight loss on each floor as the objective function.

2. The method according to claim 1, characterized in that The floor information includes: the upper limit of the floor's production capacity, the upper limit of the floor's load-bearing capacity, the upper limit of the floor's energy storage capacity, and the upper limit of the number of categories on the floor; the floor information corresponding to each floor in the target warehouse is determined according to the category information of each of the storage categories and the storage conditions, including: Determine the production capacity, load-bearing capacity, energy storage capacity, and number of categories corresponding to each floor per unit time period in the target warehouse according to the category information and the storage status of the target warehouse in the historical time period; The maximum values ​​of the production capacity, load-bearing capacity, energy storage capacity and number of categories within the unit time period are respectively used as the upper limit of the production capacity of the floor, the upper limit of the load-bearing capacity of the floor, the upper limit of the energy storage capacity of the floor, and the upper limit of the number of categories of the floor.

3. The method according to claim 1, characterized in that After obtaining the storage status of each storage category in the target warehouse during the historical time period, the following step is also included: Get multiple categories of items belonging to different brands under each warehouse category; Determine the historical weight information corresponding to the storage category within multiple unit time periods according to the unit weight of each of the item categories and the storage situation; Based on a preset weight prediction model, the weight information corresponding to the storage category is predicted according to the multiple historical weight information.

4. The method according to claim 3, characterized in that The storage situation includes the storage quantity; the historical weight information corresponding to the storage category in multiple unit time periods is determined according to the unit weight of each of the item categories and the storage situation, including: Determine the total weight of each of the item categories within a plurality of unit time periods according to the weight and storage quantity of each of the item categories; Determine the total weight of the storage category corresponding to each of the plurality of unit time periods according to the total weight; An average value is taken for a plurality of the total weights to obtain the historical weight information.

5. The method according to claim 1, characterized in that The determining of the association information between every two storage categories includes: Obtaining historical outbound order data corresponding to the warehousing situation; According to the number of times that every two of the storage categories appear at the same time in the historical delivery order data, the correlation information between the every two storage categories is determined.

6. The method according to claim 1, characterized in that: The item storage model is solved using gurobi or cplex as a solver.

7. The method according to claim 1, characterized in that The constraint conditions of the item storage model include at least one of the following: Each of the storage categories is only stored on one floor, the total weight of each storage category in the target warehouse does not exceed the total load-bearing capacity of the target warehouse, two categories with opposite category attributes cannot be stored on the same floor, and the total storage energy, total production capacity and total volume of each storage category in the target warehouse do not exceed the corresponding energy storage upper limit, production capacity upper limit and volume upper limit.

8. A device for storing items, characterized in that: include: The acquisition module is used to obtain the storage status of each storage category in the target warehouse within the historical time period; A determination module, configured to determine the floor information corresponding to each floor in the target warehouse and the correlation information between every two storage categories according to the category information of each storage category and the storage situation; A model calculation module, used to input the floor information, the storage category information and the correlation information into a preset item storage model, and output a target floor corresponding to each storage category; The category information includes weight information, and the object storage model takes the maximum correlation between every two storage categories and the minimum total weight loss on each floor as the objective function.

9. An electronic device for storing items, characterized in that: include: one or more processors; a storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 7.

10. A computer readable medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

11. A computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the computer program implements the method according to any one of claims 1 to 7.

Images