Replenishment task generation method, configuration device, electronic device, and storage medium

Abstract

The present disclosure provides a replenishment task generation method and device, electronic equipment and computer readable storage medium, relating to the technical field of warehouse logistics. Among them, the replenishment task generation method comprises: predicting the quantity of goods to be shipped out in a target period based on the category and corresponding quantity of goods in historical shipping-out orders; calculating the replenishment state value of the goods in the picking position, and determining the first group of goods in the replenishment state and the second group of goods in the adjacent replenishment state based on the replenishment grading rule; determining the to-be-associated goods in the second group of goods that enter the replenishment state in the target period based on the quantity of goods to be shipped out; identifying the associated goods having an association relationship with the first group of goods from the to-be-associated goods based on an associated goods identification model; and associating the first group of goods and the associated goods to generate a replenishment task. Through the technical scheme of the present disclosure, the goods shipping-out efficiency can be improved, and the probability of order waiting caused by goods shortage can be reduced.

Description

Technical Field

[0001] This disclosure relates to the field of warehousing and logistics technology, and in particular to a replenishment task generation method, a replenishment task generation device, an electronic device, and a computer-readable storage medium. Background Technology

[0002] With the rapid development of e-commerce and modern logistics, online shopping has gradually become mainstream. After the order system receives an online shopping order, it will send the relevant item information to the warehouse management system for processing to facilitate the subsequent picking process.

[0003] However, current warehouse management systems have problems such as fixed replenishment intervals, time stagnation during the replenishment process, and order waiting when items are out of stock.

[0004] It should be noted that the information disclosed in the background section above is only used to enhance the understanding of the background of this disclosure, and therefore may include information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0005] The purpose of this disclosure is to provide a replenishment task generation method, replenishment task generation device, electronic device, and storage medium, which can at least to some extent improve the problem of low replenishment efficiency of items in related technologies.

[0006] Other features and advantages of this disclosure will become apparent from the following detailed description, or may be learned in part from practice of this disclosure.

[0007] According to one aspect of this disclosure, a method for generating replenishment tasks is provided, comprising: predicting the quantity of items to be shipped out during a target time period based on the types and corresponding quantities of items in historical outbound orders; calculating the replenishment status value of items at picking locations, and determining a first group of items in a replenishment status and a second group of items in an imminent replenishment status based on replenishment grading rules; determining, based on the quantity of items to be shipped out, items in the second group of items that will enter the replenishment status during the target time period to be associated; identifying associated items among the items to be associated that have a relationship with the first group of items based on an associated item identification model; associating the first group of items and the associated items to generate a replenishment task.

[0008] In one embodiment, predicting the quantity of items to be shipped in a target time period based on the types and corresponding quantities of items in historical outbound orders includes: statistically analyzing outbound data for multiple time periods based on the types and corresponding quantities of the items; extracting a predetermined number of individual item outbound data from the outbound data of a single time period; calculating the expected outbound data for a single time period based on the individual item outbound data; and predicting the quantity of items to be shipped in the corresponding target time period based on the expected outbound data.

[0009] In one embodiment, calculating the expected outbound data for a single time period based on the individual product outbound data includes: for the single time period, determining the interval between the collection time of the individual product outbound data and the current time; configuring a weighting coefficient for each individual product outbound data based on the negative correlation with the interval; calculating a weighted average based on the weighting coefficient and each individual product outbound data, and determining the weighted average as the expected outbound data for the single time period.

[0010] In one embodiment, predicting the quantity of goods to be shipped for the target time period based on the expected outbound data includes: constructing a Gaussian distribution of the quantity of goods to be shipped for the target time period, and predicting the quantity of goods to be shipped for the target time period based on the Gaussian distribution.

[0011] In one embodiment, calculating the replenishment status value of items at the picking location and determining a first group of items in a replenishment status and a second group of items in a near-replenishment status based on replenishment grading rules includes: calculating the replenishment status value of the items based on the quantity of items at the picking location; obtaining a first replenishment threshold and a second replenishment threshold configured based on the replenishment grading rules, wherein the first replenishment threshold is greater than the second replenishment threshold; determining the items whose replenishment status value is greater than or equal to the first replenishment threshold as the first group of items in the replenishment status; and determining the items whose replenishment status value is less than the first replenishment threshold and greater than the second replenishment threshold as the second group of items in the near-replenishment status.

[0012] In one embodiment, determining the items to be associated in the second group of items that enter the replenishment state during the target time period based on the quantity of the items to be shipped includes: for a single type of item in the second group of items, obtaining a replenishment status update value for the single type of item based on the quantity of the single type of item located at the picking location and the quantity to be shipped; if the replenishment status update value is greater than or equal to the first replenishment threshold, determining the single type of item as the item to be associated.

[0013] In one embodiment, before identifying associated items among the items to be associated that are associated with the first group of items based on the associated item identification model, the method further includes:

[0014] An item association matrix is ​​constructed based on historical outbound orders; a model training operation is performed based on the Markov chain and the association matrix to obtain the associated item recognition model.

[0015] In one embodiment, constructing an item association matrix based on historical outbound orders includes: detecting item associations based on the historical outbound orders; constructing item sequences for multiple items based on the associations; calculating the outbound rates for each of the multiple items; and constructing the item association matrix based on the item sequences and the corresponding outbound rates.

[0016] In one embodiment, constructing the item association matrix based on the item sequence and the corresponding outbound rate includes: constructing multiple randomly initialized collaborative filtering matrices based on the item sequence; generating a prior probability matrix based on the exponential processing of the outbound rates of the multiple items; and determining the multiple collaborative filtering matrices and the prior probability matrix as the item association matrix.

[0017] In one embodiment, the step of performing model training based on the Markov chain and the association matrix to obtain the associated item recognition model includes: configuring a neural network for each of the collaborative filtering matrices and initializing the network parameters of each neural network; extracting a predicted subsequence of the item sequence with the highest association probability based on the Markov chain, the collaborative filtering matrix, and the prior probability matrix; and performing model training based on the relationship between the predicted subsequence and the actual subsequence to iteratively update the network parameters until the extracted predicted subsequence is detected to satisfy the loss function, thereby obtaining the associated item recognition model.

[0018] In one embodiment, extracting the predicted subsequence with the highest association probability from the item sequence based on the Markov chain, the collaborative filtering matrix, and the prior probability matrix includes: calculating the transition probabilities of associated items in the item sequence based on the Markov chain and the prior probability matrix; and inputting the transition probabilities and the collaborative filtering matrix into the neural network to extract the predicted subsequence with the highest association probability from the item sequence.

[0019] In one embodiment, the method further includes: constructing the loss function based on the Markov chain.

[0020] In one embodiment, identifying associated items among the items to be associated that are related to the first group of items based on the associated item identification model includes: constructing a sequence to be identified based on the first group of items and the items to be associated; inputting the sequence to be identified into the associated item identification model to output a target association sequence including the first group of items and the associated items based on the maximum association probability.

[0021] According to another aspect of this disclosure, a replenishment task generation apparatus is provided, comprising: a prediction module, configured to predict the quantity of items to be shipped out during a target time period based on the types and corresponding quantities of items in historical outbound orders; a calculation module, configured to calculate the replenishment status value of items at picking locations, and determine a first group of items in a replenishment status and a second group of items in a near-replenishment status based on replenishment grading rules; a determination module, configured to determine, based on the quantity of items to be shipped out, items in the second group of items that will enter the replenishment status during the target time period to be associated; an identification module, configured to identify associated items among the items to be associated that have an association relationship with the first group of items based on an associated item identification model; and a generation module, configured to associate the first group of items and the associated items to generate a replenishment task.

[0022] According to another aspect of this disclosure, an electronic device is provided, comprising: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to perform a replenishment task generation method of any of the above by executing the executable instructions.

[0023] According to another aspect of this disclosure, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the replenishment task generation method of any of the above.

[0024] The replenishment task generation scheme provided in the embodiments of this disclosure obtains historical outbound order data and predicts the quantity of a certain item to be shipped within a specified time period based on the item type and quantity recorded in the historical outbound order data. This allows the scheme to determine which items need to be replenished based on the quantity to be shipped. In addition, by calculating the replenishment status value of the items at the picking location, the replenishment status of the items at the picking location is classified, resulting in a first group of items in the replenishment status and a second group of items in the near-replenishment status. Combined with the predicted quantity to be shipped, the scheme can determine the items in the second group that will become replenished within the specified time period as items to be associated. Furthermore, the scheme uses an associated item identification model to identify the items to be associated that have a high degree of correlation with the current first group of items, i.e., items that can often be grouped into the same order to generate replenishment tasks together. Based on the prediction of the replenishment operation of associated items, the scheme can execute replenishment operations for more items based on a single replenishment task order, which helps to reduce the number of replenishment tasks generated and issued, improve the efficiency of item outbound shipment, and reduce the probability of order waiting due to item shortages.

[0025] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0026] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure. It is obvious that the drawings described below are merely some embodiments of this disclosure, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort.

[0027] Figure 1 This diagram illustrates the structure of a replenishment task generation system according to an embodiment of the present disclosure.

[0028] Figure 2 A schematic diagram of a replenishment task generation method according to an embodiment of this disclosure is shown;

[0029] Figure 3 A schematic diagram illustrating another method for generating replenishment tasks in an embodiment of this disclosure is shown;

[0030] Figure 4 A schematic diagram illustrating another method for generating replenishment tasks in an embodiment of this disclosure is shown;

[0031] Figure 5 A schematic diagram illustrating yet another method for generating replenishment tasks according to an embodiment of this disclosure is shown;

[0032] Figure 6 A schematic diagram illustrating yet another method for generating replenishment tasks according to an embodiment of this disclosure is shown;

[0033] Figure 7 A schematic diagram illustrating yet another method for generating replenishment tasks according to an embodiment of this disclosure is shown;

[0034] Figure 8 This diagram illustrates a replenishment task generation apparatus according to an embodiment of the present disclosure;

[0035] Figure 9 This diagram illustrates a replenishment task generation apparatus according to an embodiment of the present disclosure;

[0036] Figure 10 A schematic diagram of an electronic device according to an embodiment of the present disclosure is shown. Detailed Implementation

[0037] Exemplary embodiments will now be described more fully with reference to the accompanying drawings. However, these exemplary embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, they are provided so that this disclosure will be more comprehensive and complete, and will fully convey the concept of the exemplary embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.

[0038] Furthermore, the accompanying drawings are merely illustrative of this disclosure and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and therefore repeated descriptions of them will be omitted. Some block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities may be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor devices and / or microcontroller devices.

[0039] The solution provided in this application obtains historical outbound order data and predicts the quantity of a certain item to be outbound within a specified time period based on the item type and quantity recorded in the historical outbound order data. This allows for the determination of which items need replenishment based on the quantity to be outbound. Furthermore, by calculating the replenishment status value of items at the picking location, the replenishment status of these items is categorized, resulting in a first group of items in a replenishment state and a second group of items in a near-replenishment state. Combined with the predicted quantity to be outbound, items in the second group that will become replenished within the specified time period are identified as items to be associated. A related item identification model is then used to identify items in the second group that have a high correlation with the current first group of items, meaning they can frequently be grouped into the same order to generate replenishment tasks together. Based on the prediction of replenishment operations for related items, more items can be replenished under a single replenishment task, reducing the generation and issuance of replenishment tasks, improving outbound efficiency, and decreasing the probability of order waiting due to item shortages.

[0040] To facilitate understanding, the following is an explanation of several terms used in this application.

[0041] In a warehouse, items are typically divided into storage locations and picking locations. Storage locations are solely responsible for storing goods, while picking locations are where items are located and picked during outbound operations.

[0042] During the warehousing and picking process, there are often situations where the picking location is out of stock, requiring the generation of replenishment tasks on a regular or emergency basis to transfer items from the storage location to the picking location.

[0043] Figure 1 The diagram shows a structural schematic of a replenishment task generation system according to an embodiment of the present disclosure, including multiple terminals 120 and a server cluster 140.

[0044] Terminal 120 can be a mobile terminal such as a mobile phone, game console, tablet computer, e-book reader, smart glasses, MP4 (Moving Picture Experts Group Audio Layer IV) player, smart home device, AR (Augmented Reality) device, VR (Virtual Reality) device, etc. Alternatively, terminal 120 can also be a personal computer (PC), such as a laptop computer and a desktop computer, etc.

[0045] The terminal 120 may contain an application for generating replenishment tasks.

[0046] Terminal 120 is connected to server cluster 140 via a communication network. Optionally, the communication network can be a wired network or a wireless network.

[0047] Server cluster 140 may be a single server, a combination of several servers, a virtualization platform, or a cloud computing service center. Server cluster 140 provides background services for applications that generate replenishment tasks. Optionally, server cluster 140 undertakes the primary computing work, and terminal 120 undertakes secondary computing work; or, server cluster 140 undertakes secondary computing work, and terminal 120 undertakes the primary computing work; or, terminal 120 and server cluster 140 collaborate on computing using a distributed computing architecture.

[0048] In some optional embodiments, server cluster 140 is used to store replenishment task generation models, etc.

[0049] Optionally, the application clients installed on different terminals 120 may be the same, or the application clients installed on two terminals 120 may be clients of the same type of application on different control system platforms. Depending on the terminal platform, the specific form of the application client may also differ; for example, the application client may be a mobile client, a PC client, or a World Wide Web (WWW) client.

[0050] Those skilled in the art will understand that the number of terminals 120 described above can be more or less. For example, there may be only one terminal, or there may be dozens or hundreds of terminals, or even more. This application does not limit the number of terminals or the type of device.

[0051] Optionally, the system may also include a management device ( Figure 1 (Not shown), the management device is connected to the server cluster 140 via a communication network. Optionally, the communication network can be a wired network or a wireless network.

[0052] Optionally, the aforementioned wireless or wired networks use standard communication technologies and / or protocols. The network is typically the Internet, but can also be any network, including but not limited to Local Area Networks (LANs), Metropolitan Area Networks (MANs), Wide Area Networks (WANs), mobile, wired or wireless networks, private networks, or any combination of virtual private networks. In some embodiments, technologies and / or formats including Hyper Text Markup Language (HTML), Extensible Markup Language (XML), etc., are used to represent data exchanged over the network. Furthermore, conventional encryption technologies such as Secure Socket Layer (SSL), Transport Layer Security (TLS), Virtual Private Networks (VPNs), and Internet Protocol Security (IPsec) can be used to encrypt all or some links. In other embodiments, custom and / or dedicated data communication technologies can be used to replace or supplement the aforementioned data communication technologies.

[0053] The replenishment task generation method, mobile terminal, writing device, and processing method in this exemplary embodiment will now be described in more detail with reference to the accompanying drawings and embodiments.

[0054] like Figure 2 As shown, a replenishment task generation method according to an embodiment of this disclosure includes:

[0055] Step S202: Based on the types and quantities of items in historical outbound orders, predict the quantity of items to be outbound during the target time period.

[0056] Among them, the historical outbound order quantity can be the historical outbound order quantity of various items within a specified number of days from the current moment. Furthermore, it can be divided into multiple time periods in days. For a target time period, the quantity of a certain item to be outbound in the target time period can be predicted based on the order quantity of each target time period within the specified number of days.

[0057] Step S204: Calculate the replenishment status value of the items at the picking location, and determine the first group of items in the replenishment status and the second group of items in the near-replenishment status based on the replenishment classification rules.

[0058] The replenishment classification rule is a rule for detecting whether a certain type of item needs replenishment, is close to replenishment, or does not need replenishment. Through the classification rule, the current item can be divided into a replenishment state, a close to replenishment state, or a no-replenishment state. The first replenishment state is the replenishment state, and the second replenishment state is the close to replenishment state.

[0059] Step S206: Based on the quantity of items to be shipped out, determine the items to be associated in the second group of items that will enter the replenishment state during the target time period.

[0060] Step S208: Identify related items among the items to be associated that have a relationship with the first group of items based on the related item identification model.

[0061] Among them, by training the associated item recognition model, the associated item recognition model can identify the items in the second group of items that are related to the first group of physical items, i.e., associated items. Associated physical items can be understood as items that are related in terms of sale or use.

[0062] Step S210: Associate the first group of items with related items to generate a replenishment task.

[0063] Specifically, generating a replenishment task based on the first group of items and related items includes: completing the replenishment operation of multiple items, including the first group of items and related items, in one replenishment task.

[0064] In this embodiment, by acquiring historical outbound order data, the quantity of a certain item to be outbound within a specified time period is predicted based on the item type and quantity recorded in the historical outbound order data. This allows for the determination of which items need to be replenished based on the quantity to be outbound. In addition, by calculating the replenishment status value of the items at the picking location, the replenishment status of the items at the picking location is classified, resulting in a first group of items in the replenishment status and a second group of items in the near-replenishment status. Combined with the predicted quantity to be outbound, the items in the second group that will become replenished within the specified time period can be identified as items to be associated. Furthermore, the associated item identification model is used to identify the items to be associated that have a high degree of correlation with the current first group of items, i.e., items that can frequently be grouped into the same order to generate replenishment tasks together. Based on the prediction of the replenishment operation of associated items, more replenishment operations can be performed based on a single replenishment task order, which helps to reduce the generation and issuance of replenishment tasks, improve the efficiency of item outbound, and reduce the probability of order waiting due to item shortages.

[0065] like Figure 3 As shown, in one embodiment, based on the types and corresponding quantities of items in historical outbound orders, the quantity of items to be outbound during a target time period is predicted, including:

[0066] Step S302: Statistically analyze the outbound data of items for multiple time periods based on the type and quantity of the items.

[0067] This involves dividing a day into multiple time periods, constructing the outbound quantity of items for each time period, and combining this with warehousing attributes, operational attributes, etc., to predict the outbound quantity for the same time period on the next day.

[0068] For example, a certain historical time period (first time range) can be the number of outbound orders in the most recent month or three months; the time interval (second time range) can be the interval between waves in the warehouse, such as 15 minutes. The number of outbound orders in one day is divided into 96 time periods according to the above 15 minutes. For simplicity, we will label the above 96 time periods as Time Period 1 (0:00-0:15), Time Period 2 (0:15-0:30), ... Time Period 96 (23:45-24:00).

[0069] Furthermore, the sample characteristic data may include statistical characteristic data, which may include one or more of the following: for example, the mean, first quantile, median, standard deviation, and maximum value of historical data. The first quantile can be flexibly set, for example, the 80th percentile or the 95th percentile.

[0070] Step S304: Extract a predetermined number of individual item outbound data from the item outbound data of a single time period.

[0071] In one embodiment, extracting a predetermined number of individual item outbound data from the item outbound data of a single time period includes:

[0072] A predetermined number of individual item outbound data are extracted based on random operations; or a predetermined number of individual item outbound data are extracted from the item outbound data of a single time period based on a preset ratio.

[0073] For example, assuming the historical outbound orders are orders from the past 30 days, the outbound quantity of 10 days is randomly selected from the outbound data of the target period in the past 30 days.

[0074] Step S306: Calculate the expected outbound data for a single time period based on the individual product outbound data.

[0075] The expected outbound data is obtained by averaging the outbound data of a predetermined number of individual items.

[0076] Step S308: Predict the quantity of goods to be shipped out for the corresponding target time period based on the expected outbound data.

[0077] In this embodiment, the expected outbound data for a single time period is calculated to further obtain the quantity to be outbound based on the expected outbound quantity, thereby enabling the determination of which items are about to move from the first replenishment state to the second replenishment state based on the quantity to be outbound.

[0078] In one embodiment, calculating the expected outbound data for a single time period based on individual item outbound data includes:

[0079] For a single time period, determine the interval between the collection time of the individual product outbound data and the current time.

[0080] The weighting coefficient for each item's outbound data is configured based on the negative correlation with the interval length.

[0081] The weighting coefficients can be determined based on the reciprocal of the time interval from the current time, or arranged in descending order according to the time interval from the current time, and each item's outbound data can be assigned a different weighting coefficient according to exponential decay or linear decay.

[0082] The weighted average is calculated based on the weighting coefficients and the outbound data of each individual item, and the weighted average is determined as the expected outbound data for a single period.

[0083] like Figure 4 As shown, a method for determining the quantity to be shipped according to an embodiment of this disclosure includes:

[0084] Step 402: Obtain single-item outbound data for the same time period over multiple days.

[0085] Step 404: Randomly select N items from multiple item outbound data or select N items outbound data at a preset ratio.

[0086] Step 406: Sort the data in descending order from newest to oldest, and assign different weights to the N individual product outbound data.

[0087] Step 408: Obtain the expected outbound data for this period based on different weights and the corresponding single-item outbound data.

[0088] Step 410: Using the expected outbound data as the mean of a Gaussian distribution, construct a Gaussian distribution model for the outbound quantity during this period. Based on the random output data of the model, obtain the quantity to be outbound.

[0089] In one embodiment, predicting the quantity of goods to be shipped for a corresponding target time period based on expected outbound data includes: constructing a Gaussian distribution of the quantity of goods to be shipped for the target time period, so as to predict the quantity of goods to be shipped for the target time period based on the Gaussian distribution.

[0090] In this embodiment, the quantity of goods to be shipped out in the next time period is determined based on the Gaussian distribution model to ensure the reliability of the quantity forecast.

[0091] In one embodiment, calculating the replenishment status value of items at the picking location and determining a first group of items in the replenishment status and a second group of items in the near-replenishment status based on replenishment grading rules includes: calculating the replenishment status value of items based on the quantity of items at the picking location; obtaining a first replenishment threshold and a second replenishment threshold configured based on replenishment grading rules, wherein the first replenishment threshold is greater than the second replenishment threshold; determining items with replenishment status values ​​greater than or equal to the first replenishment threshold as the first group of items in the replenishment status; and determining items with replenishment status values ​​less than the first replenishment threshold and greater than the second replenishment threshold as the second group of items in the near-replenishment status.

[0092] When calculating the replenishment status value, the current quantity of items at the picking location is used as the calculation object. The quantity of items at the picking location and the replenishment threshold set by the system are mapped from continuous values ​​to enumerated values ​​to determine the replenishment status value of each item, which can be replenished, near replenishment, or no replenishment required.

[0093] Based on the current quantity of items at the picking location, determine the replenishment status value for each item, which can be a value between 0 and 1. Based on the predicted outbound quantity for the next time period obtained from value 1, determine the replenishment status value for each item.

[0094] For example, specifically, the replenishment status classification can be divided into:

[0095] Replenishment required (first replenishment status): This means that the stock shortage has reached the threshold set by the system, and is marked as Status-1.

[0096] Nearing replenishment status (second replenishment status): The stock shortage level reaches 80%-100% of the system's set threshold, and is marked as Status-2.

[0097] No restocking required: When the stock shortage level is below 80% of the system's set threshold, it is marked as Status-3.

[0098] In one embodiment, determining the items to be associated in the second group of items that will enter the replenishment status during the target period based on the quantity of items to be shipped includes:

[0099] For a single item in the second group of items, the replenishment status update value of the single item is obtained based on the number of single items located at the picking location and the number of items to be shipped.

[0100] If the replenishment status update value is greater than or equal to the first replenishment threshold, the single item will be identified as an item to be associated.

[0101] In this embodiment, for the second group of items that are in the near-replenishment state, the predicted quantity to be shipped can be used to detect whether the items in the second group will switch from the pending replenishment state to the replenishment state in the next target time period. If the items will switch from the pending replenishment state to the replenishment state, they can be identified as items to be associated, so as to obtain the associated replenishment task based on the association operation.

[0102] In one embodiment, before identifying associated items among the items to be associated that are related to the first group of items based on the associated item identification model, the method further includes:

[0103] Construct an item association matrix based on historical outbound orders.

[0104] A model for identifying associated items is obtained by performing model training operations based on Markov chains and association matrices.

[0105] In this context, a Markov chain is a stochastic process in a state space that transitions from one state to another. Based on the principle that the probability of a state transition at a certain moment in a Markov chain depends only on its previous state, the dependency of state transitions is applied to the dependency solving process of correlation.

[0106] In this embodiment, the conditional probability of multiple items appearing simultaneously is modeled by combining historical outbound orders and Markov chains. The maximum association probability is determined based on the solution of the maximum probability. The model training operation is performed based on the above processing to obtain the associated item recognition model, so as to ensure the accuracy of associated item recognition.

[0107] In one embodiment, constructing an item association matrix based on historical outbound orders includes: detecting item associations based on historical outbound orders; constructing item sequences for multiple items based on the associations; calculating the outbound rates for each of the multiple items; and constructing the item association matrix based on the item sequences and their corresponding outbound rates.

[0108] Specifically, the probability of each item leaving the warehouse is calculated by dividing the quantity of each item leaving the warehouse over a historical period (such as 1 month, 3 months, etc.) by the total quantity leaving the warehouse. This probability is the prior probability. As shown in equation (1).

[0109] (1)

[0110] The warehouse contains a vast number (tens of thousands) of different items, each with a very small prior probability. To make the probability of each item more distinguishable, [the following steps are taken]. As the final prior probability.

[0111] In one embodiment, constructing an item association matrix based on an item sequence and its corresponding outbound rate includes: constructing multiple randomly initialized collaborative filtering matrices based on the item sequence; generating a prior probability matrix based on the exponentialization of the outbound rates of multiple items; and determining the multiple collaborative filtering matrices and the prior probability matrix as the item association matrix.

[0112] In one embodiment, a model training operation is performed based on a Markov chain and an association matrix to obtain an associated item recognition model, including:

[0113] Configure a neural network for each collaborative filtering matrix and initialize the network parameters for each neural network.

[0114] like Figure 5 As shown, based on the collaborative filtering matrix obtained by the above random initialization, the neural network to be trained is configured accordingly, and the network parameters of the neural network are randomly initialized.

[0115] After initializing the network parameters of each neural network, the predicted subsequence of the item sequence with the highest association probability is extracted based on the Markov chain, collaborative filtering matrix, and prior probability matrix.

[0116] After obtaining the predicted subsequence, the model training operation is performed based on the relationship between the predicted subsequence and the actual subsequence to iteratively update the network parameters until the extracted predicted subsequence is detected to satisfy the loss function, so as to obtain the associated item recognition model.

[0117] like Figure 6 As shown, a method for generating an associated item identification model according to an embodiment of this disclosure includes:

[0118] Step S602: Obtain the prior probability of each item in the warehouse.

[0119] Step S604: Construct an item association matrix based on prior probabilities and item sequences, assign a neural network to each item association matrix, and initialize the network parameters of the neural network.

[0120] Step S606: Use the association matrix as input to the neural network and output the item sequence with the highest predicted association probability.

[0121] Step S608: Calculate the loss function based on the output item sequence and the actual physical sequence, iterate the correlation matrix in reverse based on the calculation result, and train the neural network.

[0122] Step S610: The extracted item sequence is detected to satisfy the loss function maximization, and the trained associated item recognition model is obtained.

[0123] In one embodiment, extracting a predicted subsequence of an item sequence with the highest association probability based on a Markov chain, a collaborative filtering matrix, and a prior probability matrix includes: calculating the transition probabilities of associated items in the item sequence based on the Markov chain and the prior probability matrix; and inputting the transition probabilities and the collaborative filtering matrix into a neural network to extract the predicted subsequence with the highest association probability from the item sequence.

[0124] In one embodiment, it further includes: constructing a loss function based on a Markov chain.

[0125] In one embodiment, identifying associated items among the items to be associated that are related to the first group of items based on the associated item identification model includes: constructing a sequence to be identified based on the first group of items and the items to be associated; inputting the sequence to be identified into the associated item identification model to output a target associated sequence including the first group of items and the associated items based on the maximum association probability.

[0126] like Figure 7 As shown, a replenishment task generation method according to another embodiment of this disclosure includes:

[0127] Step S702: Predict the quantity of different types of items to be shipped out.

[0128] This involves obtaining the number of outbound orders for various items within a certain historical time period (first time range), dividing each day of the above time period into multiple time ranges according to a certain time interval (second time range), and obtaining classification results for multiple time periods.

[0129] The first time frame is the historical outbound order quantity over a certain period of time, which can be the number of outbound orders in the most recent month or three months. The second time frame is the interval between waves in the warehouse, such as 15 minutes. The outbound order quantity of one day is divided into 96 time periods according to the above 15 minutes. For simplicity, the above 96 time periods are labeled as Time Period 1 (0:00-0:15), Time Period 2 (0:15-0:30), ... Time Period 96 (23:45-24:00).

[0130] Furthermore, the sample characteristic data may include statistical characteristic data, which may include one or more of the following: the mean, first quantile value, median, standard deviation, and maximum value of historical data. The first quantile value can be flexibly set, for example, the 80th percentile value or the 95th percentile value.

[0131] Specifically, N items are randomly selected from the classification results, or the outbound quantity data of each item within each time period is selected according to a certain probability (e.g., 50%, 100%). For simplicity, the above data is referred to as the item outbound quantity set data.

[0132] First, calculate the average outbound quantity for item s, and preferably calculate the expected outbound data for item s. As shown in equation (2).

[0133] (2)

[0134] Among them, considering the past The weighted average of daily sales, { ≥0} represents a decreasing sequence, and t represents the current time point. It is the reciprocal of the distance from the current time, that is, the closer to the current time. The larger the value.

[0135] Specifically, another implementation is as follows: the set of item outbound quantities obtained above can be sorted in descending order by time, and the elements in the set can be assigned different weights according to exponential decay or linear decay, with the sum of the element weights being 1, to obtain the item outbound quantity for each item in each time period. The specific weight exponential decay formula is shown in equation (3).

[0136]

[0137] (3)

[0138] Finally, the expected outbound quantity for the obtained time period will be... The expected value μ of the Gaussian distribution has the variance as... Construct N(μ, The outbound quantity is obtained by randomly selecting values ​​from the Gaussian distribution above, thus obtaining the outbound quantity for a specified time period. .

[0139] Step S704: By calculating the replenishment status value of each type of item, different types of items are divided into replenishment status, near-replenishment status, and no-replenishment status.

[0140] Establish a tiered system for the replenishment status of warehouse items.

[0141] Step 706: Obtain the second group of items that are currently in the near-replenishment state. Based on the predicted quantity to be shipped out at the next moment, obtain the set of items to be associated that will be in the replenishment state at the next moment.

[0142] Step S708: Obtain the first group of items that are currently in a replenishment state, and identify the associated item with the highest association probability in the set of items to be associated based on the associated item identification model.

[0143] Step S710: Based on the first group of items and related items, generate and issue a replenishment task.

[0144] Based on Markov chains, association matrices, and multiple neural networks, the items that form the order are highly related.

[0145] We use Markov transition probabilities to model the conditional probability of multiple items occurring simultaneously.

[0146] For example, in warehouse outbound orders, due to consumer purchasing habits and item associations, the appearance of each item depends on other items. For instance, buying a mobile phone or tablet often necessitates purchasing accessories like phone cases and screen protectors, while buying baby formula usually involves purchasing tissues. Therefore, the appearance of items within the same order actually reflects the associations between SKUs. That is, the appearance of item A has a high probability of being associated with the appearance of item B.

[0147] Specifically, suppose S = [ , , ……, [This refers to the sorting sequence corresponding to the items (the meaning of sorting is...)] The item with the highest correlation is The correlation probability corresponding to this sequence is shown in equation (4).

[0148] (4)

[0149] in, It is the probability that item si and item si+1 appear at the same time.

[0150] Then, for a known sorted sequence S consisting of one or more items, S = [ , , ……, In the given set of items {x1, x2, x3, ..., xn}, select the item sequence that maximizes the above probability Ps, as shown in equation (5).

[0151] (5)

[0152] To simplify the complexity of the above model, we can utilize the Markov chain-like dependencies among some items, such as mobile phone -> screen protector, etc. Dynamic programming can then be used to solve the problem.

[0153] because:

[0154] (6)

[0155] Therefore, the sequence that maximizes Ps must contain the sequence that maximizes Ps.

[0156] (7)

[0157] The subsequence with the highest probability The probability of being a subsequence.

[0158] The above Ps can be solved using the Viterbi algorithm.

[0159] Finally, we can find the most likely subsequent sequence of the currently known item sequence S = [s1, s2, ..., sn]. For example, if the current items are sku-1 and sku-2, and the given item combination is {sku-11, sku-22, sku-99, sku-88}, after the above solution, the item sequence with the highest probability is [sku-1, sku-2, sku-99, sku-22].

[0160] The probability of each item leaving the warehouse (i.e., prior probability) is calculated by the ratio of the number of various items leaving the warehouse over a historical period (such as 1 month, 3 months, etc.) to the total number of items leaving the warehouse, as shown in Equation (1).

[0161] (1)

[0162] The warehouse contains a vast number (tens of thousands) of different items, each with a very small prior probability. To improve the distinguishability of the probabilities of each item, [the following is used:] As the final prior probabilities, we obtain Table 1.

[0163] Table 1

[0164]

[0165] In addition, the randomly initialized collaborative filtering matrix is ​​shown in Table 2.

[0166] Table 2

[0167]

[0168] Based on the correlation matrix obtained from the above random initialization, randomly initialize the parameters of N (N is a finite number, which can be a single item to be restocked, or N items with high correlation) neural network. The model structure is as follows. Figure 5 As shown.

[0169] Specifically, in the case of p( | Before learning, you can use the relationships between items, such as the collaborative filtering matrix between warehouse items, to perform probability normalization as the initialization matrix, which will help you learn the transition matrix faster.

[0170] Multiple neural network task loss functions are used, with sigmoid / ReLU functions as activation functions, and the neural network is optimized using stochastic gradient descent (specifically Adam, SGD, etc.).

[0171] Select the item set of multiple historically combined orders to obtain the item sequence [S1, S2, ..., Sn]. Use the following maximum likelihood function as the loss function, as shown in Equation (8).

[0172] (8)

[0173] Train the neural network to obtain the network parameter values ​​of N neural networks.

[0174] For example, based on the prior probability matrix above, sku-1: 0.38, sku-2: 0.23, sku-3: 0.43, sku-4: 0.13; combined with the initial correlation matrix, p(sku-2|sku-1) = 0.4, p(sku-3|sku-2) = 0.55, p(sku-4|sku-3) = 0.75, p(sku-3|sku-1) = 0.6. The subsequence with the highest probability can be calculated:

[0175] SKU-1->SKU-2->SKU-3: 0.38 (0.4 0.23) (0.55 0.43)=0.00826804

[0176] SKU-1->SKU-3->SKU-4: 0.38 (0.6 0.43) (0.75 0.13)=0.0095589

[0177] Since the subsequence with the highest probability is sku-1->sku-3->sku-4, the prediction result is the sku sequence of sku-1->sku-3->sku-4. By comparing it with the real sku sequence (i.e. the sequence of items that make up the historical order), the conditional probabilities between each sku are iterated in reverse, that is, the collaborative filtering matrix (association matrix) of the sku is updated. This process is repeated until the final association matrix and associated item recognition model are obtained.

[0178] The collaborative filtering matrix after neural network training is shown in Table 3:

[0179] Table 3

[0180]

[0181] Retrieve one item (skui) whose status is replenished (Status-1), and retrieve the set of items currently in the near-replenishment status (Status-2), denoted as S = [ , , ……, ].

[0182] Based on the obtained quantity to be shipped ,calculate The set of items that will change from Status-2 to Status-1 in the next time step is denoted as . .

[0183] Furthermore, based on the associated item recognition model, using skui as the first element of the sequence, from... The sequence with the highest probability (N elements) is denoted as S. The N items in S are then combined to form a replenishment task, and the replenishment is issued.

[0184] like Figure 8 As shown, a replenishment task generation apparatus 800 according to an embodiment of the present disclosure includes:

[0185] Configure module 802 to set basic configuration information;

[0186] Data acquisition module 804: Used to collect historical data from the warehouse management system.

[0187] Replenishment task construction module 806: Sample data processing, picking status classification, and correlation matrix construction.

[0188] Replenishment Module 808: Calculates various indicators and determines the replenishment method based on constraints.

[0189] It should be noted that the above figures are merely illustrative of the processes included in the method according to exemplary embodiments of the present invention, and are not intended to be limiting. It is readily understood that the processes shown in the above figures do not indicate or limit the temporal order of these processes. Furthermore, it is readily understood that these processes may, for example, be executed synchronously or asynchronously in multiple modules.

[0190] Those skilled in the art will understand that various aspects of the present invention can be implemented as systems, methods, or program products. Therefore, various aspects of the present invention can be specifically implemented in the following forms: entirely in hardware, entirely in software (including firmware, microcode, etc.), or in a combination of hardware and software, collectively referred to herein as “circuit,” “module,” or “system.”

[0191] The following reference Figure 9 This describes a replenishment task generation apparatus 900 according to this embodiment of the invention. Figure 9 The replenishment task generation device 900 shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of the present invention.

[0192] The replenishment task generation device 900 is manifested in the form of hardware modules. Components of the replenishment task generation device 900 may include, but are not limited to: a prediction module 902, used to predict the quantity of items to be shipped out during a target time period based on the types and corresponding quantities of items in historical outbound orders; a calculation module 904, used to calculate the replenishment status value of items at the picking location, and determine the first group of items in the replenishment status and the second group of items in the near-replenishment status based on replenishment grading rules; a determination module 906, used to determine the items to be associated in the second group of items that will enter the replenishment status during the target time period based on the quantity of items to be shipped out; an identification module 908, used to identify associated items among the items to be associated that have a relationship with the first group of items based on an associated item identification model; and a generation module 910, used to associate the first group of items and associated items to generate a replenishment task.

[0193] The following reference Figure 10 To describe an electronic device 1000 according to this embodiment of the present invention. Figure 10 The electronic device 1000 shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of the present invention.

[0194] like Figure 10As shown, the electronic device 1000 is manifested in the form of a general-purpose computing device. The components of the electronic device 1000 may include, but are not limited to: at least one processing unit 1010, at least one storage unit 1020, and a bus 1030 connecting different system components (including storage unit 1020 and processing unit 1010).

[0195] The storage unit stores program code, which can be executed by the processing unit 1010 to perform the steps described in the "Exemplary Methods" section of this specification according to various exemplary embodiments of the present invention. For example, the processing unit 1010 can perform, as follows: Figure 2 Steps S202 to S208 shown, and other steps defined in the replenishment task generation method of this disclosure.

[0196] Storage unit 1020 may include readable media in the form of volatile storage units, such as random access memory (RAM) 10201 and / or cache memory 10202, and may further include read-only memory (ROM) 10203.

[0197] Storage unit 1020 may also include a program / utility 10204 having a set (at least one) program module 10205, such program module 10205 including but not limited to: operating system, one or more application programs, other program modules and program data, each or some combination of these examples may include an implementation of a network environment.

[0198] Bus 1030 can represent one or more of several types of bus structures, including a memory cell bus or memory cell controller, a peripheral bus, a graphics acceleration port, a processing unit, or a local bus using any of the multiple bus structures.

[0199] Electronic device 1000 can also communicate with one or more external devices 1060 (e.g., keyboard, pointing device, Bluetooth device, etc.), one or more devices that enable a user to interact with the electronic device, and / or any device that enables the electronic device 1000 to communicate with one or more other computing devices (e.g., router, modem, etc.). This communication can be performed via input / output (I / O) interface 1040. Furthermore, electronic device 1000 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 1050. As shown, network adapter 1050 communicates with other modules of electronic device 1000 via bus 1030. It should be understood that, although not shown in the figures, other hardware and / or software modules can be used in conjunction with the electronic device, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0200] From the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solutions according to the embodiments of this disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, external hard drive, etc.) or on a network, including several instructions to cause a computing device (such as a personal computer, server, terminal device, or network device, etc.) to execute the methods according to the embodiments of this disclosure.

[0201] In exemplary embodiments of this disclosure, a computer-readable storage medium is also provided, on which a program product capable of implementing the methods described above is stored. In some possible embodiments, various aspects of the present invention may also be implemented as a program product comprising program code that, when the program product is run on a terminal device, causes the terminal device to perform the steps of the various exemplary embodiments of the present invention described in the "Exemplary Methods" section above.

[0202] According to embodiments of the present invention, a program product for implementing the above-described method may employ a portable compact disc read-only memory (CD-ROM) and include program code, and may run on a terminal device, such as a personal computer. However, the program product of the present invention is not limited thereto. In this document, a readable storage medium may be any tangible medium containing or storing a program that may be used by or in conjunction with an instruction execution system, apparatus, or device.

[0203] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A readable signal medium may also be any readable medium other than a readable storage medium, capable of sending, propagating, or transmitting programs for use by or in conjunction with an instruction execution system, apparatus, or device.

[0204] The program code contained on the readable medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical fiber, RF, etc., or any suitable combination thereof.

[0205] Program code for performing the operations of this invention can be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java and C++, and conventional procedural programming languages ​​such as C or similar languages. The program code can execute entirely on the user's computing device, partially on the user's device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0206] It should be noted that although several modules or units for the device used to perform actions have been mentioned in the detailed description above, this division is not mandatory. In fact, according to embodiments of this disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.

[0207] Furthermore, although the steps of the method in this disclosure are described in a specific order in the accompanying drawings, this does not require or imply that the steps must be performed in that specific order, or that all the steps shown must be performed to achieve the desired result. Additional or alternative steps may be omitted, multiple steps may be combined into one step, and / or a step may be broken down into multiple steps.

[0208] From the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solutions according to the embodiments of this disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, external hard drive, etc.) or on a network, including several instructions to cause a computing device (such as a personal computer, server, mobile terminal, or network device, etc.) to execute the methods according to the embodiments of this disclosure.

[0209] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the appended claims.

Claims

1. A method for generating replenishment tasks, characterized in that, include: Based on the types and quantities of items in historical outbound orders, predict the quantity of the items to be outbound during the target time period; Calculate the replenishment status value of items at the picking location, and determine the first group of items in the replenishment status and the second group of items in the near-replenishment status based on the replenishment classification rules; Based on the quantity of the items to be shipped out, determine the items in the second group of items that will enter the replenishment state during the target time period to be associated; The system detects item associations based on the historical outbound orders; constructs item sequences for various items based on the associations; calculates the outbound rates for each of the various items; constructs an item association matrix based on the item sequences and the corresponding outbound rates; and performs model training operations based on a Markov chain and the association matrix to obtain an associated item recognition model. Based on the associated item identification model, identify the associated items among the items to be associated that have a relationship with the first group of items; Associate the first group of items with the associated items to generate a replenishment task.

2. The replenishment task generation method according to claim 1, characterized in that, Based on the types and quantities of items in historical outbound orders, predict the quantity of the items to be shipped during the target time period, including: The outbound data of the items are statistically divided into multiple time periods based on the type and quantity of the items. Extract a predetermined number of individual item outbound data from the outbound data of the items in a single time period; Calculate the expected outbound data for a single time period based on the individual product outbound data; Based on the expected outbound data, predict the quantity of goods to be outbound for the corresponding target time period.

3. The replenishment task generation method according to claim 2, characterized in that, Calculate the expected outbound data for a single time period based on the individual product outbound data, including: For the single time period, determine the interval between the collection time of the single item outbound data and the current time; Configure the weighting coefficient of each item's outbound data based on the negative correlation with the interval duration; A weighted average is calculated based on the weighting coefficients and the outbound data of each individual item, and the weighted average is determined as the expected outbound data for the single time period.

4. The replenishment task generation method according to claim 2, characterized in that, Based on the expected outbound data, predict the quantity of goods to be shipped for the corresponding target time period, including: A Gaussian distribution of the quantity to be shipped out is constructed based on the quantity to be shipped out during the target time period, and the quantity to be shipped out during the target time period is predicted based on the Gaussian distribution.

5. The replenishment task generation method according to claim 1, characterized in that, Calculate the replenishment status value of items at the picking location, and determine the first group of items in the replenishment status and the second group of items in the near-replenishment status based on the replenishment grading rules, including: The replenishment status value of the item is calculated based on the quantity of the item located at the picking location; Obtain a first replenishment threshold and a second replenishment threshold configured based on the replenishment grading rules, wherein the first replenishment threshold is greater than the second replenishment threshold; The items whose replenishment status value is greater than or equal to the first replenishment threshold are identified as the first group of items in the replenishment status; The items whose replenishment status value is less than the first replenishment threshold and greater than the second replenishment threshold are identified as the second group of items in the near-replenishment status.

6. The replenishment task generation method according to claim 5, characterized in that, Based on the quantity of the items to be shipped, determine the items in the second group of items that will enter the replenishment status during the target time period, including: For a single type of item in the second group of items, the replenishment status update value of the single type of item is obtained based on the number of the single type of item located at the picking location and the number of items to be shipped out. If the replenishment status update value is greater than or equal to the first replenishment threshold, the single item is identified as the item to be associated.

7. The replenishment task generation method according to claim 1, characterized in that, Construct an item association matrix based on the item sequence and the corresponding outbound rate, including: Construct multiple randomly initialized collaborative filtering matrices based on the item sequence; Based on the exponentialization of the outbound rates of the various items, a prior probability matrix is ​​generated. The plurality of collaborative filtering matrices and the prior probability matrix are determined as the item association matrix.

8. The replenishment task generation method according to claim 7, characterized in that, Based on the Markov chain and the association matrix, a model training operation is performed to obtain an associated item recognition model, including: Configure a neural network for each of the collaborative filtering matrices and initialize the network parameters of each neural network; Based on the Markov chain, the collaborative filtering matrix, and the prior probability matrix, a predicted subsequence of the item sequence with the highest association probability is extracted; Based on the relationship between the predicted subsequence and the actual subsequence, a model training operation is performed to iteratively update the network parameters until the extracted predicted subsequence is detected to satisfy the loss function, so as to obtain the associated item recognition model.

9. The replenishment task generation method according to claim 8, characterized in that, Based on the Markov chain, the collaborative filtering matrix, and the prior probability matrix, a predicted subsequence of the item sequence with the highest association probability is extracted, including: The transition probabilities of associated items in the item sequence are calculated based on the Markov chain and the prior probability matrix. The transition probability and the collaborative filtering matrix are input into the neural network to extract the predicted subsequence with the highest association probability from the item sequence.

10. The replenishment task generation method according to claim 8, characterized in that, Also includes: The loss function is constructed based on the Markov chain.

11. The replenishment task generation method according to any one of claims 1 to 10, characterized in that, The step of identifying associated items among the items to be associated that are related to the first group of items based on the associated item identification model includes: A sequence to be identified is constructed based on the first group of items and the items to be associated; The sequence to be identified is input into the associated item identification model to output a target associated sequence including the first group of items and the associated items based on the maximum association probability.

12. A replenishment task generation device, characterized in that, include: The prediction module is used to predict the quantity of the items to be shipped out during the target time period based on the types and corresponding quantities of items in historical outbound orders. The calculation module calculates the replenishment status value of items at the picking location and determines the first group of items in the replenishment status and the second group of items in the near-replenishment status based on the replenishment classification rules. The determination module is used to determine, based on the quantity of the items to be shipped out, the items to be associated in the second group of items that will enter the replenishment state during the target time period; The model training module is used to detect item associations based on the historical outbound orders; construct item sequences of various items based on the associations; calculate the outbound rates of the various items respectively; construct an item association matrix based on the item sequences and the corresponding outbound rates; and perform model training operations based on the Markov chain and the association matrix to obtain an associated item recognition model. The identification module is used to identify, based on the associated item identification model, associated items among the items to be associated that have an association relationship with the first group of items; The generation module is used to associate the first group of items with the associated items to generate a replenishment task.

13. An electronic device, characterized in that, include: processor; as well as Memory for storing the executable instructions of the processor; The processor is configured to execute the replenishment task generation method according to any one of claims 1 to 11 by executing the executable instructions.

14. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the replenishment task generation method according to any one of claims 1 to 11.

Images