Warehouse distribution method, device and equipment and storage medium

Abstract

The invention relates to the technical field of warehouse logistics, and discloses a warehouse distribution method, device and equipment and a storage medium. The method comprises the steps of obtaining current storage data corresponding to a current operation period; determining predicted productivity data based on the current storage data and a pre-trained target productivity prediction model; determining target productivity data based on the predicted productivity data, and executing the current distribution task based on the current operation period and the target productivity data; wherein the current storage data comprises a predicted total amount and current distribution parameter data, the current distribution parameter data comprises at least one of a historical distribution amount, a distribution residual amount and a current order amount, and the predicted productivity data comprises predicted distribution amounts corresponding to at least one residual operation period; each remaining operation period comprises the current operation period. According to the embodiment of the invention, the operation efficiency of the all-day distribution task is improved.

Description

Technical Field

[0001] The present invention relates to the field of warehousing logistics technology, and in particular to a warehousing distribution method, device, equipment and storage medium. Background Art

[0002] In the warehousing and logistics scenario, a timed and quantitative management system is currently adopted for distribution tasks. That is, based on a fixed working time of a day, the total predicted quantity of pieces for the day is evenly distributed to obtain predicted capacity data. The predicted capacity data includes the average distribution quantity corresponding to each operation cycle in a day. The staff performs distribution tasks according to the predicted capacity data.

[0003] In the process of implementing the present invention, it is found that there are at least the following technical problems in the prior art:

[0004] The traditional warehouse distribution management method is to make a one-time allocation based on the predicted total quantity of pieces for the whole day. Due to the uncertainty of the predicted total quantity, in the actual execution of the distribution task, it is very easy for the actual distribution quantity of a certain operation cycle to fail to meet the average distribution quantity, resulting in an imbalance in the actual production capacity data for the whole day and low efficiency of the distribution task throughout the day. Summary of the invention

[0005] The embodiments of the present invention provide a warehouse distribution method, device, equipment and storage medium to solve the problem of unbalanced actual production capacity data in traditional warehouse distribution management methods, thereby ensuring the operating efficiency of all-day distribution tasks.

[0006] According to one embodiment of the present invention, a storage distribution method is provided, the method comprising:

[0007] Get the current storage data corresponding to the current operation cycle;

[0008] Determine predicted capacity data based on the current storage data and a pre-trained target capacity prediction model;

[0009] Based on the predicted capacity data, target capacity data is determined, and based on the current operation cycle and the target capacity data, a current seeding task is executed;

[0010] Among them, the current warehouse data includes the predicted total quantity of pieces and the current distribution parameter data, the current distribution parameter data includes at least one of the historical distribution quantity, the remaining distribution quantity and the current order quantity, and the predicted production capacity data includes the predicted distribution quantity corresponding to at least one remaining operation cycle, and each of the remaining operation cycles includes the current operation cycle.

[0011] According to another embodiment of the present invention, a storage distribution device is provided, the device comprising:

[0012] The current storage data acquisition module is used to obtain the current storage data corresponding to the current operation cycle;

[0013] A predicted capacity data determination module, used to determine the predicted capacity data based on the current storage data and a pre-trained target capacity prediction model;

[0014] A current broadcasting task execution module, used to determine target capacity data based on the predicted capacity data, and execute the current broadcasting task based on the current operation cycle and the target capacity data;

[0015] Among them, the current warehouse data includes the predicted total quantity of pieces and the current distribution parameter data, the current distribution parameter data includes at least one of the historical distribution quantity, the remaining distribution quantity and the current order quantity, and the predicted production capacity data includes the predicted distribution quantity corresponding to at least one remaining operation cycle, and each of the remaining operation cycles includes the current operation cycle.

[0016] According to another embodiment of the present invention, there is provided an electronic device, the electronic device comprising:

[0017] at least one processor; and

[0018] a memory communicatively connected to the at least one processor; wherein,

[0019] The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the warehouse distribution method described in any embodiment of the present invention.

[0020] According to another embodiment of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the warehouse distribution method described in any embodiment of the present invention when executed.

[0021] The technical solution of the embodiment of the present invention obtains the current warehouse data corresponding to the current operation cycle, adopts the pre-trained target capacity prediction model, determines the predicted capacity data based on the current warehouse data, and executes the current distribution task based on the current operation cycle and the target capacity data determined based on the predicted capacity data, wherein the current warehouse data includes the predicted total piece quantity and the current distribution parameter data, the current distribution parameter data includes at least one of the historical capacity data, the distribution remaining quantity and the current order piece quantity, the predicted capacity data includes the predicted distribution piece quantity corresponding to at least one remaining operation cycle, and each remaining operation cycle includes the current operation cycle. The embodiment of the present invention takes into account the real-time change characteristics of the warehouse data corresponding to each operation cycle in the warehouse distribution process, and distributes the distribution piece quantity of each operation cycle in real time, thereby solving the problem of uneven actual capacity data in the traditional warehouse distribution management method and ensuring the operation efficiency of the full-day distribution task.

[0022] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0024] Figure 1 A flow chart of a storage distribution method provided by one embodiment of the present invention;

[0025] Figure 2 A flowchart of another storage and distribution method provided by an embodiment of the present invention;

[0026] Figure 3 A schematic diagram of a process for determining target capacity data provided by an embodiment of the present invention;

[0027] Figure 4 A flowchart of another storage and distribution method provided by an embodiment of the present invention;

[0028] Figure 5 A flowchart of another storage and distribution method provided by an embodiment of the present invention;

[0029] Figure 6 A schematic diagram of the structure of a storage and seeding device provided by an embodiment of the present invention;

[0030] Figure 7 The present invention is a schematic structural diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0031] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0032] It should be noted that the terms "first", "second", "intermediate", "target", "reference", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0033] Figure 1 This is a flowchart of a warehouse distribution method provided by an embodiment of the present invention. This embodiment can be applied to manage the execution of order item distribution tasks in a warehouse storage system. The method can be executed by a warehouse distribution device. The warehouse distribution device can be implemented in the form of hardware and / or software. The warehouse distribution device can be configured in a terminal device. Figure 1 As shown, the method includes:

[0034] S110, obtaining current storage data corresponding to the current operation cycle.

[0035] Specifically, within the working hours of a day, the working hours can be divided into at least two operating cycles. For example, assuming that the working hours are from 8 am to 6 pm, the operating cycle within a day can be 10 operating cycles divided by 1 hour, or 5 operating cycles divided by 2 hours. Of course, the cycle intervals corresponding to each operating cycle within the working hours can also be different, such as 8 am to 9 am as operating cycle A, and 9 am to 11 am as operating cycle A. The specific division method of the operating cycle is not limited here, and users can customize the settings according to actual needs.

[0036] Specifically, the current storage data can be used to characterize factors that affect the predicted distribution quantity. In this embodiment, the current storage data includes the predicted total quantity and current distribution parameter data, and the current distribution parameter data includes at least one of the historical distribution quantity, the distribution remaining quantity, and the current order quantity.

[0037] Specifically, the predicted total piece quantity represents the total task piece quantity of the storage items that need to be distributed on that day. The predicted total piece quantity can be determined based on the actual total task piece quantity corresponding to the historical time period. For example, the historical time period can be the previous 7 days of the day or the previous month, etc. The predicted total piece quantity can be the maximum value, minimum value, median value or average value corresponding to at least one actual total task piece quantity.

[0038] Specifically, the historical distribution quantity is used to characterize the statistical value of at least one actual distribution quantity corresponding to the historical operation cycle that is the same as the current operation cycle within the historical time period. Exemplarily, the statistical value is the maximum value, the minimum value, the median value or the average value. For example, when the statistical value is the average value, assuming that the actual distribution quantity corresponding to 8 a.m. to 9 a.m. in the previous 7 days is 100 pieces, 150 pieces, 90 pieces, 120 pieces, 100 pieces, 80 pieces and 200 pieces respectively, then the historical distribution quantity corresponding to 8 a.m. to 9 a.m. in the historical production capacity data is 120 pieces.

[0039] Specifically, the remaining quantity for distribution represents the quantity of undistributed items in the previous operation cycle, and the remaining quantity for distribution is equal to the difference between the quantity of items to be distributed in the previous operation cycle and the actual quantity of items distributed. Specifically, the current order quantity represents the total quantity of orders placed on the day before the current operation cycle.

[0040] On the basis of the above embodiment, specifically, the current warehouse data also includes at least one of arrival data, order category, distribution start time, distribution end time, long-tail products and hot products.

[0041] Specifically, the arrival data includes the arrival time and / or arrival quantity of the supplier before the current operation cycle on the day. Specifically, the order category represents the category of items corresponding to the undistributed orders among all the orders received before the current operation cycle on the day. For example, the item category includes but is not limited to daily necessities, seafood, frozen products, fruits, etc.

[0042] Specifically, the distribution start time represents the time when the distribution task is first issued on the day, and the distribution end time represents the time when the distribution task is last issued.

[0043] Among them, long-tail products represent order categories with order quantity less than the first quantity threshold, and hot products represent order categories with order quantity greater than the second quantity threshold, and the first quantity threshold is less than the second quantity threshold. For example, the first quantity threshold is 10 pieces and the second quantity threshold is 500 pieces. There is no limit on the first quantity threshold and the second quantity threshold here, and users can customize the settings according to actual needs.

[0044] The advantage of this setting is that by considering more factors that can affect the predicted capacity data and using them as current warehouse data to determine the predicted capacity data, the accuracy of the subsequently obtained predicted capacity data can be further improved, and the balance of the actual capacity data can be further improved.

[0045] S120: Determine predicted capacity data based on current warehouse data and a pre-trained target capacity prediction model.

[0046] In a specific embodiment, based on current warehouse data and a pre-trained target capacity prediction model, the predicted capacity data is determined, including: inputting the current warehouse data into the pre-trained target capacity prediction model to obtain output predicted capacity data.

[0047] In another specific embodiment, based on current warehouse data and a pre-trained target capacity prediction model, predicted capacity data is determined, including: inputting current warehouse data into the pre-trained target capacity prediction model to obtain output full-day capacity data; based on at least one remaining operation cycle, screening the full-day capacity data to obtain predicted capacity data.

[0048] In this embodiment, the predicted capacity data includes the predicted distribution quantity corresponding to at least one remaining operation cycle, and each remaining operation cycle includes the current operation cycle. For example, assuming that each operation cycle of the day includes 10 operation cycles from 8 am to 6 pm, with 1 hour as the cycle interval, and the current operation cycle is from 9 am to 10 am, then each remaining operation cycle includes the other 9 operation cycles except 8 am to 9 am.

[0049] In a specific embodiment, the method also includes: obtaining training warehouse data corresponding to the training operation cycle; determining reference capacity data based on the training warehouse data and an untrained initial capacity prediction model; determining a loss function based on the reference capacity data and the standard capacity data; and adjusting the model parameters of the initial capacity prediction model based on the loss function until the loss function converges to obtain a trained target capacity prediction model.

[0050] In another specific embodiment, the method also includes: obtaining training warehouse data corresponding to the training operation cycle; determining reference capacity data based on the training warehouse data and an untrained initial capacity prediction model; determining a loss function based on the reference capacity data and the standard capacity data; and adjusting the model parameters of the initial capacity prediction model based on the loss function until the loss function converges and the peak coefficient corresponding to the reference capacity data is less than the first coefficient threshold, thereby obtaining a trained target capacity prediction model.

[0051] In the above embodiment, the training warehouse data includes the total training piece quantity and the training distribution parameter data, the training distribution parameter data includes at least one of the historical distribution piece quantity, the distribution remaining quantity and the training order piece quantity, and the reference production capacity data includes the reference distribution piece quantity corresponding to at least one remaining operation cycle, and each remaining operation cycle includes the training operation cycle.

[0052] Among them, the "training storage data" corresponds to the same or similar to the "current storage data" in the above embodiment, and this embodiment will not be repeated here.

[0053] Among them, exemplary loss functions include but are not limited to square loss function, logarithmic loss function, exponential loss function, logistic regression loss function, Huber loss function, cross entropy loss function and Kullback-Leibler divergence loss function, etc., and the loss function used here is not limited.

[0054] In the above embodiment, the peak coefficient represents the ratio between the maximum reference distribution piece quantity and the minimum reference distribution piece quantity in the reference capacity data. The maximum reference distribution piece quantity represents the largest reference distribution piece quantity in the reference capacity data, and the minimum reference distribution piece quantity represents the smallest reference distribution piece quantity in the reference capacity data. Exemplarily, assuming that the reference distribution piece quantities corresponding to the three remaining operation cycles in the reference capacity data are 100 pieces, 200 pieces, and 150 pieces, respectively, the maximum reference distribution piece quantity is 200 pieces, and the minimum reference distribution piece quantity is 100 pieces, and accordingly, the peak coefficient is 2.

[0055] Exemplarily, the first coefficient threshold may be 1.3. The first coefficient threshold is not limited here and may be customized according to actual needs.

[0056] The advantage of setting the peak coefficient is that it can constrain the output results of the target capacity prediction model, so that the target capacity prediction model has the ability to evenly predict capacity data, further ensuring the balance of the target capacity data and the efficiency of the all-day broadcasting tasks.

[0057] S130: Determine target capacity data based on the predicted capacity data, and execute the current broadcasting task based on the current operation cycle and the target capacity data.

[0058] Specifically, the target capacity data represents the target distribution quantity corresponding to at least one remaining operation cycle. In a specific embodiment, determining the target capacity data based on the predicted capacity data includes: using the predicted capacity data as the target capacity data.

[0059] Specifically, the current target distribution quantity corresponding to the current operation cycle in the target capacity data is obtained, and based on the current target distribution quantity, the current distribution task is executed. Exemplarily, the current distribution task includes but is not limited to the distribution operation of the current target distribution quantity and the distribution operation of the items.

[0060] The technical solution of this embodiment obtains the current warehouse data corresponding to the current operation cycle, adopts the pre-trained target capacity prediction model, determines the predicted capacity data based on the current warehouse data, and executes the current distribution task based on the current operation cycle and the target capacity data determined based on the predicted capacity data, wherein the current warehouse data includes the predicted total piece quantity and the current distribution parameter data, the current distribution parameter data includes at least one of the historical capacity data, the distribution remaining quantity and the current order piece quantity, the predicted capacity data includes the predicted distribution piece quantity corresponding to at least one remaining operation cycle, and each remaining operation cycle includes the current operation cycle. The embodiment of the present invention takes into account the real-time change characteristics of the warehouse data corresponding to each operation cycle in the warehouse distribution process, and distributes the distribution piece quantity of each operation cycle in real time, thereby solving the problem of imbalance of actual capacity data in traditional warehouse distribution management methods and ensuring the operation efficiency of the whole day distribution tasks.

[0061] Figure 2 This is a flow chart of another storage distribution method provided by an embodiment of the present invention. This embodiment further refines the "determining target production capacity data based on predicted production capacity data" in the above embodiment. Figure 2 As shown, the method includes:

[0062] S210, obtaining current storage data corresponding to the current operation cycle.

[0063] S220: Determine predicted capacity data based on current warehouse data and a pre-trained target capacity prediction model.

[0064] S210-S220 in this embodiment are similar to those in the above embodiment. Figure 1 S110 - S120 shown in FIG. 1 are identical or similar to each other, and will not be described in detail in this embodiment.

[0065] S230, obtaining the maximum value predicted distribution quantity in the predicted production capacity data.

[0066] In this embodiment, the maximum predicted distribution quantity represents the maximum predicted distribution quantity in the predicted capacity data. For example, assuming that the predicted distribution quantities corresponding to the three remaining operation cycles in the predicted capacity data are 100 pieces, 200 pieces, and 150 pieces, respectively, the maximum predicted distribution quantity is 200 pieces.

[0067] S240. When the maximum predicted broadcast component quantity is greater than the average broadcast component quantity and the remaining operation cycle corresponding to the maximum predicted broadcast component quantity meets the preset time range, determine the balanced broadcast component quantity based on the maximum predicted broadcast component quantity and the average broadcast component quantity.

[0068] Exemplarily, the average distribution volume can be determined based on the number of cycles corresponding to all completed operation cycles before the current operation cycle and the actual total distribution volume. For example, assuming that the operation cycles of the day include 10 operation cycles from 8 am to 6 pm, with 1 hour as the cycle interval, the current operation cycle is from 10 am to 11 am, all completed operation cycles include 2 operation cycles from 8 am to 9 am and 9 am to 10 am, and the actual distribution volume corresponding to all completed operation cycles is 100 and 200, respectively, then the average distribution volume is 150.

[0069] For example, the average broadcast quantity can also be determined based on the predicted total quantity and the total number of cycles corresponding to the operation cycles in a day. For example, assuming that the operation cycles of the day include 10 operation cycles from 8 am to 6 pm, with 1 hour as the cycle interval, and the predicted total quantity is 2,000 pieces, the average broadcast quantity is 200 pieces.

[0070] Of course, the average distribution file quantity can also be preset by the user based on actual experience. The specific value of the average distribution file quantity is not limited here.

[0071] Specifically, the preset time range represents a later working time period in a day. For example, assuming that each working cycle of the day includes 10 working cycles from 8 am to 6 pm, with 1 hour as the cycle interval, the preset time range may be 3 pm to 6 pm, or 5 pm to 6 pm.

[0072] Specifically, the remaining operation cycle satisfies the preset time range, which indicates that the preset time range includes the remaining operation cycle, and the balanced broadcast component quantity is equal to the difference between the maximum predicted broadcast component quantity and the mean broadcast component quantity.

[0073] On the basis of the above embodiments, specifically, the method also includes: when the maximum predicted distribution quantity is less than or equal to the mean distribution quantity, or when the remaining operation cycle corresponding to the maximum predicted distribution quantity does not meet the preset time range, the predicted capacity data is used as the target capacity data, and S260 is executed.

[0074] S250: Predict the quantity of distributed parts and the balanced quantity of distributed parts based on the minimum value in the predicted capacity data, and determine the target capacity data.

[0075] In a specific embodiment, target capacity data is determined based on the minimum predicted distribution piece quantity and the balanced distribution piece quantity in the predicted capacity data, including: determining the minimum predicted distribution piece quantity based on at least one minimum predicted distribution piece quantity in the predicted capacity data; adjusting the maximum predicted distribution piece quantity in the predicted capacity data to the average distribution piece quantity, and increasing the minimum predicted distribution piece quantity in the predicted capacity data by the balanced distribution piece quantity to obtain target capacity data.

[0076] For example, assuming that the remaining operating cycles corresponding to the maximum predicted broadcast quantity and the minimum predicted broadcast quantity in the predicted capacity data are 5 pm to 6 pm and 10 am to 11 am respectively, and the maximum predicted broadcast quantity and the minimum predicted broadcast quantity are 5,000 pieces and 3,000 pieces respectively, and the average broadcast quantity is 4,500 pieces, then the balanced broadcast quantity is 500 pieces, and the target broadcast quantity corresponding to 10 am to 11 am in the target capacity data is 3,500 pieces, and the target broadcast quantity corresponding to 5 pm to 6 pm is 4,500 pieces.

[0077] In another specific embodiment, the target capacity data is determined based on the minimum predicted distribution piece quantity and the balanced distribution piece quantity in the predicted capacity data, including: taking the minimum predicted distribution piece quantity corresponding to the earliest remaining operation cycle in the predicted capacity data as the intermediate predicted distribution piece quantity, and determining the target capacity data based on the intermediate predicted distribution piece quantity and the balanced distribution piece quantity. Specifically, the maximum predicted distribution piece quantity in the predicted capacity data is adjusted to the average distribution piece quantity, and the intermediate predicted distribution piece quantity in the predicted capacity data is increased by the balanced distribution piece quantity to obtain the target capacity data.

[0078] The advantage of this setting is that after adding the balanced broadcast quantity to the intermediate predicted broadcast quantity, the remaining operating cycle corresponding to the intermediate predicted broadcast quantity may become the remaining operating cycle corresponding to the maximum value target broadcast quantity in the target capacity data. Therefore, setting the intermediate predicted broadcast quantity to the minimum predicted broadcast quantity corresponding to the earliest remaining operating cycle can make the maximum value in the target capacity data appear as early as possible, avoiding the situation where the remaining operating cycle corresponding to the maximum value falls into the preset time range again, thereby improving the correction quality of peak shaving and valley filling.

[0079] In another specific embodiment, target capacity data is determined based on the minimum predicted distribution piece quantity and the balanced distribution piece quantity in the predicted capacity data, including: taking the minimum predicted distribution piece quantity corresponding to the earliest remaining operation cycle in the predicted capacity data as the intermediate predicted distribution piece quantity, and determining the intermediate capacity data based on the intermediate predicted distribution piece quantity and the balanced distribution piece quantity; when the peak coefficient corresponding to the intermediate capacity data is less than the second coefficient threshold, taking the intermediate capacity data as the target capacity data; wherein the peak coefficient represents the ratio between the maximum intermediate predicted distribution piece quantity and the minimum intermediate predicted distribution piece quantity in the intermediate capacity data.

[0080] Specifically, the maximum predicted broadcast quantity in the predicted capacity data is adjusted to the average broadcast quantity, and the intermediate predicted broadcast quantity in the predicted capacity data is increased by the balanced broadcast quantity to obtain the intermediate capacity data.

[0081] Specifically, the first coefficient threshold and the second coefficient threshold may be the same or different. For example, the second coefficient threshold is 1.3. The second coefficient threshold is not limited here.

[0082] On the basis of the above embodiment, specifically, the target capacity data is determined based on the minimum predicted distribution piece quantity and the balanced distribution piece quantity in the predicted capacity data, and the target capacity data is determined, and the following also includes: when the peak coefficient corresponding to the intermediate capacity data is greater than or equal to the second coefficient threshold, the intermediate capacity data is used as the predicted capacity data, and the maximum value predicted distribution piece quantity in the predicted capacity data is obtained; and the step of returning to execute the step of determining the balanced distribution piece quantity based on the maximum value predicted distribution piece quantity and the mean distribution piece quantity is determined.

[0083] Specifically, if the peak coefficient is less than the second coefficient threshold, it means that the balance of the intermediate capacity data is relatively high, and if the peak coefficient is greater than or equal to the second coefficient threshold, it means that the balance of the intermediate capacity data is relatively poor.

[0084] Figure 3 A schematic diagram of a process for determining target capacity data provided by an embodiment of the present invention. Specifically, Figure 3The difference between x1 and x3 is the same as the difference between x3 and x5, x2 = 0.6x1 + 0.4x3, x3 = 0.8x1, x4 = 0.5 (x3 + x5), x5 = 0.6x1, Figure 3 The horizontal solid line in indicates that the average broadcast quantity is x3 pieces, and the second coefficient threshold is 1.3.

[0085] Figure 3 The figure above represents the predicted capacity data. Among them, the remaining operation cycles corresponding to the maximum predicted broadcast quantity and the earliest minimum predicted broadcast quantity in the predicted capacity data are 5 pm to 6 pm and 10 am to 11 am, respectively, and the maximum predicted broadcast quantity and the earliest minimum predicted broadcast quantity are x1 pieces and x3 pieces, respectively, then the balanced broadcast quantity is (x1-x3) pieces, and the peak shaving and valley filling operation provided by the embodiment of the present invention can be obtained Figure 3 The middle picture in .

[0086] Figure 3 The middle graph in represents the intermediate capacity data. Among them, the remaining operating cycles of the maximum intermediate broadcast quantity and the minimum intermediate broadcast quantity in the intermediate capacity data are 10 am to 11 am and 12 noon to 1 pm respectively, and the maximum intermediate broadcast quantity and the minimum intermediate broadcast quantity are x1 pieces and x4 pieces respectively. The peak coefficient corresponding to the intermediate capacity data is 1.4, which is greater than the second coefficient threshold. At this time, the intermediate capacity data is used as the predicted capacity data, and the remaining operating cycles corresponding to the maximum predicted broadcast quantity and the earliest minimum predicted broadcast quantity in the predicted capacity data are 10 am to 11 am and 12 noon to 1 pm respectively, and the maximum predicted broadcast quantity and the earliest minimum predicted broadcast quantity are x1 pieces and x4 pieces respectively. The balanced broadcast quantity is (x1-x3) pieces, which can be obtained through the peak shaving and valley filling operation provided by the embodiment of the present invention. Figure 3 See the figure below.

[0087] Figure 3 The following figure represents the target capacity data, where the maximum value and minimum value of the target distribution quantity in the target capacity data are x2 pieces and x3 pieces respectively. The peak coefficient corresponding to the target capacity data is 1.15, which is less than the second coefficient threshold.

[0088] S260: Execute the current sowing task based on the current operation cycle and target production capacity data.

[0089] The technical solution of this embodiment is to obtain the maximum value predicted broadcast quantity in the predicted capacity data, and determine the balanced broadcast quantity based on the maximum value predicted broadcast quantity and the average broadcast quantity when the maximum value predicted broadcast quantity is greater than the average broadcast quantity and the remaining operation cycle corresponding to the maximum value predicted broadcast quantity meets the preset time range, and determine the target capacity data based on the minimum value predicted broadcast quantity and the balanced broadcast quantity in the predicted capacity data. The embodiment of the present invention provides a method for shaving peaks and filling valleys, further solves the problem of imbalance in actual capacity data in traditional warehouse distribution management methods, and further ensures the operating efficiency of all-day distribution tasks.

[0090] Figure 4 This is a flow chart of another warehouse distribution method provided by an embodiment of the present invention. This embodiment further refines the warehouse distribution method provided by the above embodiment. Figure 4 As shown, the method includes:

[0091] S310, obtaining current storage data corresponding to the current operation cycle.

[0092] S320: Determine predicted capacity data based on current warehouse data and a pre-trained target capacity prediction model.

[0093] S330. Determine target capacity data based on the predicted capacity data.

[0094] S310-S330 in this embodiment are similar to those in the above embodiment. Figure 1 S110-S130 shown in FIG. 1 correspond to the same or similar ones, or to the same ones in the above-mentioned embodiment. Figure 2 The S210 - S250 shown correspond to the same or similar ones, and are not described in detail in this embodiment.

[0095] S340, obtaining the operable distribution piece quantity corresponding to the current operation cycle and the current target distribution piece quantity corresponding to the current operation cycle in the target production capacity data.

[0096] Specifically, in a warehousing system, items usually go through three steps in sequence, namely, acceptance, picking, and distribution. Acceptance is used to indicate that the items received from suppliers are accepted and stored in the warehouse, and picking is used to indicate that the accepted items in the warehouse are located and removed from the shelves. In this embodiment, specifically, the number of operable distribution pieces is used to indicate the total number of pieces in the warehouse that have completed the picking operation but have not completed the distribution operation.

[0097] S350: When the amount of operable distribution components is less than the current target distribution component amount, determine the difference distribution component amount based on the amount of operable distribution components and the current target distribution component amount.

[0098] Specifically, the difference distribution component quantity is equal to the difference between the current target distribution component quantity and the operable distribution component quantity.

[0099] In this embodiment, the method further includes: executing S380 when the operable distribution component quantity is greater than or equal to the current target distribution component quantity.

[0100] S360: Obtain the operable picking quantity corresponding to the current operation cycle, and determine the increased picking quantity and / or increased acceptance quantity corresponding to the current operation cycle based on the operable picking quantity and the difference broadcasting quantity.

[0101] Specifically, the operable picking quantity is used to represent the total quantity of pieces that have completed the acceptance operation but have not completed the picking operation in the warehouse.

[0102] In a specific embodiment, based on the operable picking quantity and the differential broadcasting quantity, the increased picking quantity and / or increased acceptance quantity corresponding to the current operation cycle are determined, including: when the operable picking quantity is greater than or equal to the differential broadcasting quantity, the differential broadcasting quantity is used as the increased picking quantity corresponding to the current operation cycle, and / or the increased acceptance quantity corresponding to the current operation cycle is set to zero; when the operable picking quantity is less than the differential broadcasting quantity, the operable picking quantity is used as the increased picking quantity corresponding to the current operation cycle, and / or, based on the operable picking quantity and the differential broadcasting quantity, the increased acceptance quantity corresponding to the current operation cycle is determined.

[0103] Specifically, the increase in the number of accepted pieces is equal to the difference between the difference in the number of distributed pieces and the number of operable picking pieces, and the sum of the increase in the number of picked pieces, the increase in the number of accepted pieces and the number of operable distributed pieces is equal to the current target number of distributed pieces.

[0104] For example, assuming that the current target distribution quantity is 1,000 pieces and the operable distribution quantity is 800 pieces, the difference distribution quantity is 200 pieces. When the operable picking quantity is 300 pieces, the picking quantity is increased by 200 pieces and the acceptance quantity is increased by 0 pieces. When the operable picking quantity is 50 pieces, the picking quantity is increased by 50 pieces and the acceptance quantity is increased by 150 pieces.

[0105] S370: Based on the increase in the number of pieces to be picked and / or the increase in the number of pieces to be accepted, a piece quantity prompt operation is performed.

[0106] Exemplarily, the quantity prompt operation may be a text display, such as the quantity prompt information being "need to increase picking by X pieces, and increase acceptance by Y pieces".

[0107] S380: Execute the current sowing task based on the current operation cycle and target production capacity data.

[0108] S380 in this embodiment corresponds to or is similar to S130 in the above embodiment, and is not described in detail in this embodiment.

[0109] The technical solution of this embodiment is to obtain the operable distribution piece quantity corresponding to the current operation cycle and the current target distribution piece quantity corresponding to the current operation cycle in the target capacity data before executing the current distribution task based on the current operation cycle and the target capacity data. When the operable distribution piece quantity is less than the current target distribution piece quantity, the difference distribution piece quantity is determined based on the operable distribution piece quantity and the current target distribution piece quantity, the operable picking piece quantity corresponding to the current operation cycle is obtained, and the increased picking piece quantity and / or increased acceptance piece quantity corresponding to the current operation cycle are determined based on the operable picking piece quantity and the difference distribution piece quantity. Based on the increased picking piece quantity and / or increased acceptance piece quantity, the piece quantity prompt operation is performed. The embodiment of the present invention can help management personnel adjust the workload or work status of picking personnel and / or acceptance personnel according to the piece quantity prompt information to meet the piece quantity requirements in the piece quantity prompt information, solves the problem that the traditional warehouse distribution management method does not have the piece quantity prompt function, provides data support for the preliminary workload to ensure the balance of the actual capacity data, and further ensures the operation efficiency of the distribution task throughout the day.

[0110] Figure 5 This is a flow chart of another warehouse distribution method provided by an embodiment of the present invention. This embodiment further refines the warehouse distribution method provided by the above embodiment. Figure 5 As shown, the method includes:

[0111] S410, obtaining current storage data corresponding to the current operation cycle.

[0112] S420: Determine predicted capacity data based on current warehouse data and a pre-trained target capacity prediction model.

[0113] S430: Determine target capacity data based on the predicted capacity data.

[0114] S410-S430 in this embodiment are similar to those in the above embodiment. Figure 1 S110-S130 shown in FIG. 1 correspond to the same or similar ones, or to the same ones in the above-mentioned embodiment. Figure 2 The S210 - S250 shown correspond to the same or similar ones, and are not described in detail in this embodiment.

[0115] S440: Obtain the actual number of distribution pieces corresponding to the previous operation cycle.

[0116] S450: When the actual number of distributed files is less than the threshold number of distributed files, determine the previous work efficiency based on the actual number of distributed files and the previous number of employees corresponding to the previous operation cycle.

[0117] In one implementation, the distribution piece quantity threshold may be preset by the user based on actual experience. In another embodiment, the distribution piece quantity threshold is determined based on the last target distribution piece quantity corresponding to the last operation cycle in the target capacity data. Specifically, the distribution piece quantity threshold is equal to the product of the last target distribution piece quantity and a preset ratio. For example, the preset ratio may be 0.8 or 0.9. The preset ratio is not limited here.

[0118] Specifically, the previous work efficiency is equal to the ratio between the actual number of distributed pieces and the previous number of employees.

[0119] S460: Based on the previous work efficiency, perform a warning prompt operation, and based on the previous work efficiency, perform a warning prompt operation.

[0120] In a specific embodiment, the early warning prompt operation includes an efficiency prompt operation. Accordingly, based on the previous work efficiency, the early warning prompt operation is performed, including: when the previous work efficiency is less than the standard work efficiency, based on the standard work efficiency and the previous work efficiency, determining the corrected work efficiency, and performing the efficiency prompt operation based on the corrected work efficiency.

[0121] For example, the standard work efficiency may be preset by the user based on actual experience, or may be calculated based on historical work efficiency corresponding to a historical time period. The method for obtaining the standard work efficiency is not limited here.

[0122] In one embodiment, the revised work efficiency is equal to the difference between the standard work efficiency and the previous work efficiency. For example, when the standard work efficiency is 700 pieces / hour and the previous work efficiency is 500 pieces / hour, the revised work efficiency is 200 pieces / hour. For example, the efficiency prompt operation can be a text display, such as the efficiency prompt information "employee work efficiency needs to be improved by 200 / hour".

[0123] In another embodiment, based on the standard work efficiency and the previous work efficiency, the differential work efficiency is determined, and the ratio between the differential work efficiency and the standard work efficiency is used as the corrected work efficiency. For example, when the standard work efficiency is 700 pieces / hour and the previous work efficiency is 500 pieces / hour, the corrected work efficiency is 28.6%. For example, the efficiency prompt operation can be a text display, such as the efficiency prompt information "employee work efficiency needs to be improved by 28.6%".

[0124] In another specific embodiment, the early warning prompt operation includes a number of people prompt operation. Accordingly, based on the previous work efficiency, the early warning prompt operation is performed, including: when the previous work efficiency is greater than or equal to the standard work efficiency, obtaining the current target distribution quantity corresponding to the current operation cycle in the target capacity data; based on the current target distribution quantity, the standard work efficiency and the previous number of employees, determining the increased number of employees corresponding to the current operation cycle, and performing the number of employees prompt operation based on the increased number of employees.

[0125] Specifically, the number of additional employees = (current target distribution volume / standard work efficiency) - the previous number of employees. For example, if the current target distribution volume is 7,000 pieces, the standard work efficiency is 700 pieces / hour, and the previous number of employees is 8, then the number of additional employees is 10.

[0126] Exemplarily, the number of people prompt operation can be a text display, such as the number of people prompt information is "the current operation cycle needs to increase a people".

[0127] On the basis of the above embodiments, specifically, the method also includes: when the current operation cycle corresponds to the start time of distribution, based on the standard work efficiency and the current target distribution quantity corresponding to each remaining operation cycle in the target production capacity data, determining the predicted number of employees corresponding to each remaining operation cycle; using the largest predicted number of employees among the predicted numbers of employees as the reserve number of employees, and executing the number of employees configuration task based on the reserve number of employees; wherein the sum of the previous number of employees and the increased number of employees is less than the reserve number of employees.

[0128] Specifically, the predicted number of employees is equal to the ratio between the current target distribution volume and the standard work efficiency. Exemplarily, the staffing task includes but is not limited to recruiting or screening distribution personnel.

[0129] The advantage of this setting is that it ensures that during the whole day's warehousing and distribution process, especially when the number of people needs to be adjusted, there will be neither an excess nor a shortage of distribution personnel, thereby further reducing the average cost of items in the warehouse on that day.

[0130] S470: Execute the current sowing task based on the current operation cycle and target production capacity data.

[0131] S470 in this embodiment is the same as or similar to S130 in the above embodiment, and will not be described in detail in this embodiment.

[0132] The technical solution of this embodiment obtains the actual amount of distribution pieces corresponding to the previous operation cycle before executing the current distribution task based on the current operation cycle and target production capacity data. When the actual amount of distribution pieces is less than the distribution piece amount threshold, the previous work efficiency is determined based on the actual amount of distribution pieces and the previous number of employees corresponding to the previous operation cycle. Based on the previous work efficiency, an early warning prompt operation is performed. Based on the previous work efficiency, an early warning prompt operation is performed, which solves the problem that the traditional warehouse distribution management method does not have the efficiency and / or number of people prompt function, provides work efficiency and the operating capacity of the number of workers to ensure the balance of the actual production capacity data, realizes the balanced allocation of distribution personnel, and reduces the average cost of pieces in the warehouse for the whole day's distribution tasks.

[0133] Figure 6 The structure diagram of a storage and broadcasting device provided by one embodiment of the present invention is shown in FIG. Figure 6 As shown, the device includes: a current storage data acquisition module 510, a predicted capacity data determination module 520 and a current distribution task execution module 530.

[0134] Among them, the current storage data acquisition module 510 is used to obtain the current storage data corresponding to the current operation cycle;

[0135] A predicted capacity data determination module 520 is used to determine predicted capacity data based on current storage data and a pre-trained target capacity prediction model;

[0136] The current distribution task execution module 530 is used to determine the target capacity data based on the predicted capacity data, and execute the current distribution task based on the current operation cycle and the target capacity data;

[0137] Among them, the current warehouse data includes the predicted total quantity of pieces and the current distribution parameter data. The current distribution parameter data includes at least one of the historical distribution quantity, the remaining distribution quantity and the current order quantity. The predicted production capacity data includes the predicted distribution quantity corresponding to at least one remaining operation cycle, and each remaining operation cycle includes the current operation cycle.

[0138] The technical solution of this embodiment obtains the current warehouse data corresponding to the current operation cycle, adopts the pre-trained target capacity prediction model, and determines the predicted capacity data based on the current warehouse data, wherein the current warehouse data includes the predicted total piece quantity and the current distribution parameter data, the current distribution parameter data includes at least one of the historical capacity data, the distribution remaining quantity and the current order piece quantity, the predicted capacity data includes the predicted distribution piece quantity corresponding to at least one remaining operation cycle, each remaining operation cycle includes the current operation cycle, the embodiment of the present invention takes into account the real-time change characteristics of the warehouse data corresponding to each operation cycle in the warehouse distribution process, and distributes the distribution piece quantity of each operation cycle in real time, thereby solving the problem of imbalance of actual capacity data in traditional warehouse distribution management methods and ensuring the operation efficiency of the all-day distribution tasks.

[0139] Based on the above embodiment, specifically, the device further includes:

[0140] The target capacity prediction model training module is used to obtain the training storage data corresponding to the training operation cycle;

[0141] Determine reference capacity data based on the training warehouse data and the untrained initial capacity forecasting model;

[0142] Determine a loss function based on the reference capacity data and the standard capacity data;

[0143] Based on the loss function, the model parameters of the initial capacity prediction model are adjusted until the loss function converges and the peak coefficient corresponding to the reference capacity data is less than the first coefficient threshold, thereby obtaining a trained target capacity prediction model;

[0144] Among them, the training warehousing data includes the total training piece quantity and the training distribution parameter data, the training distribution parameter data includes at least one of the historical distribution piece quantity, the distribution remaining quantity and the training order piece quantity, the reference capacity data includes the reference distribution piece quantity corresponding to at least one remaining operation cycle, each remaining operation cycle includes the training operation cycle, and the peak coefficient represents the ratio between the maximum reference distribution piece quantity and the minimum reference distribution piece quantity in the reference capacity data.

[0145] Based on the above embodiment, specifically, the current broadcast task execution module 530 includes:

[0146] A maximum value predicted distribution piece quantity acquisition unit is used to acquire the maximum value predicted distribution piece quantity in the predicted production capacity data;

[0147] A balanced distribution component quantity determination unit is used to determine the balanced distribution component quantity based on the maximum value predicted distribution component quantity and the average distribution component quantity when the maximum value predicted distribution component quantity is greater than the average distribution component quantity and the remaining operation cycle corresponding to the maximum value predicted distribution component quantity meets the preset time range;

[0148] The target capacity data determination unit is used to predict the distribution quantity and the balanced distribution quantity based on the minimum value in the predicted capacity data to determine the target capacity data.

[0149] Based on the above embodiment, specifically, the target capacity data determination unit is specifically used to:

[0150] The minimum predicted distribution quantity corresponding to the earliest remaining operation cycle in the predicted capacity data is used as the intermediate predicted distribution quantity, and the intermediate capacity data is determined based on the intermediate predicted distribution quantity and the balanced distribution quantity;

[0151] When the peak coefficient corresponding to the intermediate capacity data is less than the second coefficient threshold, the intermediate capacity data is used as the target capacity data; wherein the peak coefficient represents the ratio between the maximum intermediate predicted broadcast quantity and the minimum intermediate predicted broadcast quantity in the intermediate capacity data.

[0152] Based on the above embodiment, specifically, the target capacity data determination unit is further used to:

[0153] When the peak coefficient corresponding to the intermediate capacity data is not less than the second coefficient threshold, the intermediate capacity data is used as the predicted capacity data, and the maximum value predicted distribution quantity in the predicted capacity data is obtained;

[0154] Return to execute the step of determining the balanced broadcast quantity based on the maximum predicted broadcast quantity and the average broadcast quantity.

[0155] Based on the above embodiment, specifically, the device further includes:

[0156] The piece quantity prompt operation execution module is used to obtain the operable distribution piece quantity corresponding to the current operation cycle and the current target distribution piece quantity corresponding to the current operation cycle in the target capacity data before executing the current distribution task based on the current operation cycle and the target capacity data;

[0157] When the operable distribution piece quantity is less than the current target distribution piece quantity, determining the difference distribution piece quantity based on the operable distribution piece quantity and the current target distribution piece quantity;

[0158] Obtain the operable picking quantity corresponding to the current operation cycle, and determine the increased picking quantity and / or increased acceptance quantity corresponding to the current operation cycle based on the operable picking quantity and the difference broadcasting quantity;

[0159] Based on increasing the number of pieces to be picked and / or increasing the number of pieces to be accepted, a piece quantity prompt operation is performed.

[0160] Based on the above embodiment, specifically, the quantity prompt operation execution module is specifically used to:

[0161] When the operable picking quantity is greater than or equal to the difference broadcasting quantity, the difference broadcasting quantity is used as the increased picking quantity corresponding to the current operation cycle, and / or the increased acceptance quantity corresponding to the current operation cycle is set to zero;

[0162] When the operable picking quantity is less than the differential broadcasting quantity, the operable picking quantity is used as the increased picking quantity corresponding to the current operation cycle, and / or, based on the operable picking quantity and the differential broadcasting quantity, the increased acceptance quantity corresponding to the current operation cycle is determined.

[0163] Based on the above embodiment, specifically, the device further includes:

[0164] The early warning prompt operation execution module is used to obtain the actual distribution quantity corresponding to the previous operation cycle before executing the current distribution task based on the current operation cycle and target production capacity data;

[0165] When the actual number of distributed items is less than the distribution item threshold, the previous work efficiency is determined based on the actual number of distributed items and the previous number of employees corresponding to the previous operation cycle, and based on the previous work efficiency, an early warning prompt operation is performed.

[0166] On the basis of the above embodiment, specifically, the early warning prompt operation includes an efficiency prompt operation, and accordingly, the early warning prompt operation execution module includes:

[0167] The efficiency prompt operation execution unit is used to determine the revised work efficiency based on the standard work efficiency and the previous work efficiency when the previous work efficiency is less than the standard work efficiency, and to execute the efficiency prompt operation based on the revised work efficiency.

[0168] On the basis of the above embodiment, specifically, the early warning prompt operation includes a number of people prompt operation, and accordingly, the early warning prompt operation execution module includes:

[0169] The headcount prompt operation execution unit is used to obtain the current target distribution quantity corresponding to the current operation cycle in the target capacity data when the previous work efficiency is greater than or equal to the standard work efficiency;

[0170] Based on the current target distribution volume, standard work efficiency and the previous number of employees, the number of additional employees corresponding to the current operation cycle is determined, and based on the increased number of employees, the number of employees prompt operation is performed.

[0171] Based on the above embodiment, specifically, the device further includes:

[0172] The headcount configuration task execution module is used to determine the predicted number of workers corresponding to each remaining operation cycle based on the standard work efficiency and the current target broadcasting quantity corresponding to each remaining operation cycle in the target capacity data when the current operation cycle corresponds to the broadcasting start time;

[0173] The largest predicted number of employees among the predicted numbers of employees is used as the reserve number of employees, and the staffing task is performed based on the reserve number of employees; wherein the sum of the previous number of employees and the increased number of employees is less than the reserve number of employees.

[0174] On the basis of the above embodiment, specifically, the current warehouse data includes at least two of the predicted total piece quantity, historical production capacity data, the distribution remaining quantity corresponding to the current operation cycle, and the current order piece quantity.

[0175] On the basis of the above embodiments, specifically, the current warehouse data also includes arrival data, order categories, distribution start time, distribution end time, long-tail products and hot products. Among them, long-tail products represent order categories with order quantity less than a first quantity threshold, hot products represent order categories with order quantity greater than a second quantity threshold, and the first quantity threshold is less than the second quantity threshold.

[0176] The warehouse distribution device provided in the embodiment of the present invention can execute the warehouse distribution method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0177] Figure 7 A schematic diagram of the structure of an electronic device provided for one embodiment of the present invention. The electronic device 10 is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0178] like Figure 7As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0179] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0180] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the warehouse distribution method provided in the above embodiments.

[0181] In some embodiments, the warehouse distribution method provided in the above embodiments may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps in the warehouse distribution method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to execute the warehouse distribution method in any other appropriate manner (e.g., by means of firmware).

[0182] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0183] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0184] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, 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 foregoing.

[0185] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0186] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0187] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0188] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0189] 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 can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A storage and sowing method, characterized in that: include: Get the current storage data corresponding to the current operation cycle; Determine predicted capacity data based on the current storage data and a pre-trained target capacity prediction model; Based on the predicted capacity data, target capacity data is determined, and based on the current operation cycle and the target capacity data, a current seeding task is executed; Among them, the current warehouse data includes the predicted total quantity of pieces and the current distribution parameter data, the current distribution parameter data includes at least one of the historical distribution quantity, the remaining distribution quantity and the current order quantity, and the predicted production capacity data includes the predicted distribution quantity corresponding to at least one remaining operation cycle, and each of the remaining operation cycles includes the current operation cycle.

2. The method according to claim 1, characterized in that The method further comprises: Get the training storage data corresponding to the training operation cycle; Determining reference capacity data based on the training warehouse data and the untrained initial capacity prediction model; Determining a loss function based on the reference capacity data and the standard capacity data; Based on the loss function, adjusting the model parameters of the initial capacity prediction model until the loss function converges and the peak coefficient corresponding to the reference capacity data is less than the first coefficient threshold, thereby obtaining a trained target capacity prediction model; Among them, the training warehouse data includes the total training piece quantity and the training distribution parameter data, the training distribution parameter data includes at least one of the historical distribution piece quantity, the distribution remaining quantity and the training order piece quantity, the reference production capacity data includes the reference distribution piece quantity corresponding to at least one remaining operation cycle, each of the remaining operation cycles includes the training operation cycle, and the peak coefficient represents the ratio between the maximum reference distribution piece quantity and the minimum reference distribution piece quantity in the reference production capacity data.

3. The method according to claim 1, characterized in that The step of determining target capacity data based on the predicted capacity data includes: Obtaining the maximum value predicted distribution quantity in the predicted production capacity data; When the maximum predicted distribution piece quantity is greater than the average distribution piece quantity and the remaining operation cycle corresponding to the maximum predicted distribution piece quantity meets the preset time range, the balanced distribution piece quantity is determined based on the maximum predicted distribution piece quantity and the average distribution piece quantity; The target capacity data is determined based on the minimum predicted distribution quantity and the balanced distribution quantity in the predicted capacity data.

4. The method according to claim 3, characterized in that The step of determining target capacity data based on the minimum value predicted distribution component quantity and the balanced distribution component quantity in the predicted capacity data includes: The minimum predicted distribution piece quantity corresponding to the earliest remaining operation cycle in the predicted capacity data is used as the intermediate predicted distribution piece quantity, and the intermediate capacity data is determined based on the intermediate predicted distribution piece quantity and the balanced distribution piece quantity; When the peak coefficient corresponding to the intermediate capacity data is less than the second coefficient threshold, the intermediate capacity data is used as the target capacity data; wherein the peak coefficient represents the ratio between the maximum intermediate predicted distribution quantity and the minimum intermediate predicted distribution quantity in the intermediate capacity data.

5. The method according to claim 4, characterized in that The step of determining target capacity data based on the minimum value predicted distribution component quantity and the balanced distribution component quantity in the predicted capacity data further includes: When the peak coefficient corresponding to the intermediate capacity data is greater than or equal to the second coefficient threshold, the intermediate capacity data is used as the predicted capacity data, and the maximum value predicted distribution quantity in the predicted capacity data is obtained; Return to the step of determining a balanced distribution component quantity based on the maximum predicted distribution component quantity and the average distribution component quantity.

6. The method according to any one of claims 1 to 5, characterized in that: Before executing the current sowing task based on the current operation cycle and the target capacity data, the method further includes: Acquire the operable distribution piece quantity corresponding to the current operation cycle and the current target distribution piece quantity corresponding to the current operation cycle in the target production capacity data; In the case where the operable distribution component quantity is less than the current target distribution component quantity, determining a differential distribution component quantity based on the operable distribution component quantity and the current target distribution component quantity; Obtaining the operable picking quantity corresponding to the current operation cycle, and determining the increased picking quantity and / or increased acceptance quantity corresponding to the current operation cycle based on the operable picking quantity and the difference broadcasting quantity; Based on the increase in the number of pieces to be picked and / or the increase in the number of pieces to be accepted, a piece quantity prompt operation is performed.

7. The method according to claim 6, characterized in that The determining, based on the operable picking quantity and the difference broadcasting quantity, of an increased picking quantity and / or an increased acceptance quantity corresponding to the current operation cycle includes: When the operable picking quantity is greater than or equal to the difference broadcasting quantity, the difference broadcasting quantity is used as the increased picking quantity corresponding to the current operation cycle, and / or the increased acceptance quantity corresponding to the current operation cycle is set to zero; When the operable picking quantity is less than the differential broadcasting quantity, the operable picking quantity is used as the increased picking quantity corresponding to the current operation cycle, and / or, based on the operable picking quantity and the differential broadcasting quantity, the increased acceptance quantity corresponding to the current operation cycle is determined.

8. The method according to any one of claims 1 to 5, characterized in that: Before executing the current sowing task based on the current operation cycle and the target capacity data, the method further includes: Get the actual number of distribution pieces corresponding to the previous operation cycle; When the actual number of distributed pieces is less than the distribution piece threshold, the previous work efficiency is determined based on the actual number of distributed pieces and the previous number of employees corresponding to the previous operation cycle, and an early warning prompt operation is performed based on the previous work efficiency.

9. The method according to claim 8, characterized in that The early warning prompt operation includes an efficiency prompt operation. Accordingly, the early warning prompt operation is performed based on the previous work efficiency, including: In the case that the previous work efficiency is less than the standard work efficiency, a revised work efficiency is determined based on the standard work efficiency and the previous work efficiency, and an efficiency prompt operation is performed based on the revised work efficiency.

10. The method according to claim 8, characterized in that The early warning prompt operation includes a number of people prompt operation. Accordingly, the early warning prompt operation is performed based on the previous work efficiency, including: When the previous working efficiency is greater than or equal to the standard working efficiency, obtaining the current target distribution quantity corresponding to the current operation cycle in the target production capacity data; Based on the current target distribution volume, standard work efficiency and the last number of employees, the additional number of employees corresponding to the current operation cycle is determined, and based on the additional number of employees, a number of employees prompt operation is performed.

11. The method according to claim 10, characterized in that The method further comprises: In the case where the current operation cycle corresponds to the start time of broadcasting, based on the standard work efficiency and the current target broadcasting quantity corresponding to each remaining operation cycle in the target capacity data, the predicted number of employees corresponding to each remaining operation cycle is determined; The largest predicted number of employees among the predicted numbers of employees is used as the reserve number of employees, and the staffing task is performed based on the reserve number of employees; wherein the sum of the previous number of employees and the increased number of employees is less than the reserve number of employees.

12. The method according to claim 1, characterized in that The current warehouse data also includes arrival data, order category, distribution start time, distribution end time, at least one of long-tail products and hot products, wherein the long-tail products represent order categories with an order quantity less than a first quantity threshold, and the hot products represent order categories with an order quantity greater than a second quantity threshold, and the first quantity threshold is less than the second quantity threshold.

13. A storage and sowing device, characterized in that: include: The current storage data acquisition module is used to obtain the current storage data corresponding to the current operation cycle; A predicted capacity data determination module, used to determine the predicted capacity data based on the current storage data and a pre-trained target capacity prediction model; A current broadcasting task execution module, used to determine target capacity data based on the predicted capacity data, and execute the current broadcasting task based on the current operation cycle and the target capacity data; Among them, the current warehouse data includes the predicted total quantity of pieces and the current distribution parameter data, the current distribution parameter data includes at least one of the historical distribution quantity, the remaining distribution quantity and the current order quantity, and the predicted production capacity data includes the predicted distribution quantity corresponding to at least one remaining operation cycle, and each of the remaining operation cycles includes the current operation cycle.

14. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the warehouse distribution method described in any one of claims 1-13.

15. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the warehouse distribution method described in any one of claims 1-13 when executed.

Images