CN111768132A

CN111768132A - Cargo storage adjusting method and device applied to unmanned warehouse

Info

Publication number: CN111768132A
Application number: CN201910257195.0A
Authority: CN
Inventors: 祝捷; 加梦奕; 陆继任; 赵芮; 彭先铁; 林世洪; 翟思让
Original assignee: Beijing Wodong Tianjun Information Technology Co Ltd
Current assignee: Beijing Wodong Tianjun Information Technology Co Ltd
Priority date: 2019-04-01
Filing date: 2019-04-01
Publication date: 2020-10-13

Abstract

The embodiment of the application discloses a cargo storage adjusting method and device applied to an unmanned warehouse. One embodiment of the method comprises: acquiring a simulation order set, wherein the simulation order set is generated according to scene information related to orders; importing the simulation order set into a pre-established stock adjustment model to generate a simulation result, wherein the stock adjustment model is used for representing the corresponding relation between the order set and the simulation result, and the simulation result is used for indicating the stock adjustment mode of the unmanned warehouse; and adjusting the stock of the unmanned bin according to the simulation result. This embodiment provides a new way of adjusting unmanned warehouse inventory.

Description

Cargo storage adjusting method and device applied to unmanned warehouse

Technical Field

The embodiment of the application relates to the field of intelligent warehousing, in particular to a goods inventory adjusting method and device applied to an unmanned warehouse.

Background

The unmanned storehouse aims at realizing unmanned operation of warehouse operation processes such as warehousing, storing, selecting, ex-warehouse and the like, and the unmanned storehouse is required to be provided with a processing center, analyzes external order data, control data and mass data sensed by numerous sensors, accurately predicts the future condition, coordinates the operation of intelligent equipment after autonomous decision, timely adjusts strategies according to information fed back by task execution, and forms closed-loop control on operation, namely, the unmanned storehouse has the characteristics of intelligent sensing, real-time analysis, accurate prediction, autonomous decision, automatic control and autonomous learning.

It will be appreciated that the order content and order volume will determine the core issues in the supply chain, such as the layout, inventory, replenishment strategy, etc. of the items in the unmanned bin.

Disclosure of Invention

The embodiment of the application provides a cargo storage adjusting method and device applied to an unmanned warehouse.

In a first aspect, an embodiment of the present application provides a method for adjusting stock of an unmanned storehouse, where the method includes: acquiring a simulation order set, wherein the simulation order set is generated according to scene information related to orders; importing the simulation order set into a pre-established stock adjustment model to generate a simulation result, wherein the stock adjustment model is used for representing the corresponding relation between the order set and the simulation result, and the simulation result is used for indicating the stock adjustment mode of the unmanned warehouse; and adjusting the stock of the unmanned bin according to the simulation result.

In some embodiments, the acquiring a simulation order set includes: receiving scene information; generating an item identification set and a first order quantity corresponding to each item identification according to the scene information; and generating the simulation order set according to the item identification set and the quantity of each first order.

In some embodiments, the generating the simulated order set according to the item identifier set and the respective first order quantities includes: acquiring pre-generated article ordering rule information, wherein the article ordering rule information can be used for indicating the rule of ordering articles by a user; and generating the simulated order set according to the item ordering rule information, the item identification set and the quantity of each first order.

In some embodiments, the article ordering rule information is generated by: acquiring a historical order set; and generating article ordering rule information according to the historical order set.

In some embodiments, the item ordering rule information includes at least one of: item transition probability, frequent item set, associated confidence, purchase quantity probability distribution within order, and shipping address probability distribution.

In some embodiments, the above term transition probability is determined by: determining the number of items of the included item identification aiming at the historical order comprising the target item identification; and determining item transfer probability among the item numbers corresponding to the target item identification according to the order number of each item number.

In some embodiments, the frequent item set is determined by: extracting the article identification included in the historical order from the order set; specifying a target article identifier from the extracted article identifiers, and executing the following steps aiming at the target article identifier: determining the object identifier which is in the same historical order as the target object identifier as a related object identifier; for each associated item identifier, determining the proportion of the historical order comprising the target item identifier and the associated item identifier in the historical order set as a support degree, and if the support degree is greater than a support degree threshold value, determining the associated item identifier and the target item identifier as frequent items; and determining the set of the determined frequent items as a frequent item set.

In some embodiments, the associated confidence level corresponding to the frequent item is determined by: and for the associated item identifier in the frequent item, determining the ratio of the historical order comprising the target item identifier and the associated item identifier in the historical order comprising the target item identifier as the associated confidence of the frequent item.

In some embodiments, the above probability distribution of purchase quantity in order is determined by: determining the purchase quantity of the target item identifier in the historical order comprising the target item identifier; and establishing probability distribution of the purchase quantity in the order corresponding to the target article identification according to the purchase quantity corresponding to each historical order.

In some embodiments, the shipping address probability distribution is determined by: for historical orders in the historical order set, extracting receiving addresses in the historical orders; generating a superior address according to the extracted delivery address; and establishing the probability distribution of the receiving address by using the generated superior address.

In some embodiments, the generating the simulated order set according to the item ordering rule information, the item identifier set, and the respective first order quantities includes: and importing the article ordering rule information, the article identification set and each first order quantity into a pre-established order generation model to obtain a simulated order set, wherein the order generation model is used for representing the corresponding relation among the article ordering rule information, the article identification set and each first order quantity and the simulated order set.

In some embodiments, the generating the simulated order set according to the item ordering rule information, the item identifier set, and the respective first order quantities includes: for each item identifier in the item identifier set, generating an order subset corresponding to the item identifier;

and generating the simulated order set according to each order subset.

In some embodiments, the subset of orders may be generated by: generating a first order with a second order quantity according to the first order quantity corresponding to the target article identifier; determining the quantity of the item identifications in each first order according to the item transfer probability corresponding to the target item identification; adding target article identifications to the first orders with the article identification number equal to 1, and adding article identifications forming frequent items with the target article identifications to the first orders with the article identification number larger than 1 according to the corresponding association confidence degrees of the target article identifications to obtain second orders; for the item identifier in each second order, adding the order quantity for the item identifier according to the probability distribution of the purchase quantity in the order of the item identifier to obtain a third order; and generating an order subset corresponding to the target item identifier according to each third order.

In some embodiments, the generating, according to each third order, an order subset corresponding to the target item identifier includes: and adding the receiving address to each third order according to the probability distribution of the receiving address to obtain a fourth order.

In some embodiments, the generating a set of item identifiers and a first order quantity corresponding to each item identifier according to the scenario information includes: determining a scene type to which the received scene information belongs according to a preset type judgment condition; determining an order quantity prediction model corresponding to the received scene information from an order quantity prediction model set according to a corresponding relation between a pre-established scene type and the order quantity prediction model, wherein the order quantity prediction model is used for representing the corresponding relation between the scene information and an item identification set and between the first order quantity and the item identification set; and importing the received scene information into the determined order quantity prediction model to generate an item identification set and a first order quantity corresponding to each item identification.

In a second aspect, an embodiment of the present application provides a stock adjustment device applied to an unmanned storehouse, the device including: the system comprises an acquisition unit, a processing unit and a display unit, wherein the acquisition unit is configured to acquire a simulation order set, and the simulation order set is generated according to scene information related to orders; the generation unit is configured to import the simulation order set into a stock adjustment model which is established in advance, and generate a simulation result, wherein the stock adjustment model is used for representing the corresponding relation between the order set and the simulation result, and the simulation result is used for indicating the stock adjustment mode of the unmanned warehouse; and the adjusting unit is configured to adjust the stock of the unmanned bin according to the simulation result.

In some embodiments, the obtaining unit is further configured to: receiving scene information; generating an item identification set and a first order quantity corresponding to each item identification according to the scene information; and generating the simulation order set according to the item identification set and the quantity of each first order.

In some embodiments, the obtaining unit is further configured to: acquiring pre-generated article ordering rule information, wherein the article ordering rule information can be used for indicating the rule of ordering articles by a user; and generating the simulated order set according to the item ordering rule information, the item identification set and the quantity of each first order.

In some embodiments, the obtaining unit is further configured to: and importing the article ordering rule information, the article identification set and each first order quantity into a pre-established order generation model to obtain a simulated order set, wherein the order generation model is used for representing the corresponding relation among the article ordering rule information, the article identification set and each first order quantity and the simulated order set.

In some embodiments, the obtaining unit is further configured to: for each item identifier in the item identifier set, generating an order subset corresponding to the item identifier; and generating the simulated order set according to each order subset.

In some embodiments, the obtaining unit is further configured to: determining a scene type to which the received scene information belongs according to a preset type judgment condition; determining an order quantity prediction model corresponding to the received scene information from an order quantity prediction model set according to a corresponding relation between a pre-established scene type and the order quantity prediction model, wherein the order quantity prediction model is used for representing the corresponding relation between the scene information and an item identification set and between the first order quantity and the item identification set; and importing the received scene information into the determined order quantity prediction model to generate an item identification set and a first order quantity corresponding to each item identification.

In a third aspect, an embodiment of the present application provides an electronic device for adjusting stock of unmanned storehouse, including: one or more processors; a storage device having one or more programs stored thereon, which when executed by the one or more processors, cause the one or more processors to implement the method of any of the embodiments as applied to the unmanned aerial vehicle cargo space adjustment method described above.

In a fourth aspect, the present application provides a stock adjustment computer-readable medium applied to an unmanned bin, on which a computer program is stored, where the program, when executed by a processor, implements the method of any one of the embodiments of the stock adjustment method applied to an unmanned bin as described above.

According to the cargo storage adjusting method and device applied to the unmanned storehouse, the simulation result is obtained by leading the simulation order set into the cargo storage adjusting model, then the cargo storage of the unmanned storehouse is adjusted according to the simulation result, here, the simulation order set is generated according to the scene information related to the order, and the technical effects at least include: provides a new unmanned warehouse goods storage adjusting mode.

Drawings

Other features, objects and advantages of the present application will become more apparent upon reading of the following detailed description of non-limiting embodiments thereof, made with reference to the accompanying drawings in which:

FIG. 1 is an exemplary system architecture diagram in which one embodiment of the present application may be applied;

FIG. 2 is a flow diagram of one embodiment of a method for inventory adjustment applied to an unmanned bin according to the present application;

FIG. 3 is a schematic diagram of an application scenario for a method of inventory adjustment for unmanned aerial vehicles according to the present application;

FIG. 4 is a flow chart of yet another embodiment of a method for inventory adjustment applied to an unmanned bin according to the present application;

FIG. 5 is a schematic diagram of an alternative implementation of step 403 according to the present application;

FIG. 6 is a schematic illustration of the manner in which an order rule for an item is generated according to the present application;

FIG. 7 is a schematic diagram of generating a simulated order set using an order generation model according to the present application;

FIG. 8 is a schematic diagram of an alternative implementation of step 4032 according to the present application;

FIG. 9 is a schematic diagram of an alternative implementation of generating a subset of orders according to the present application;

FIG. 10 is a schematic diagram of an alternative implementation of step 402 according to the present application;

FIG. 11 is a schematic diagram of an embodiment of a load leveling device applied to an unmanned aerial vehicle according to the present application;

FIG. 12 is a block diagram of a computer system suitable for use in implementing the electronic device of an embodiment of the present application.

Detailed Description

The present application will be described in further detail with reference to the following drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the relevant invention and not restrictive of the invention. It should be noted that, for convenience of description, only the portions related to the related invention are shown in the drawings.

It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict. The present application will be described in detail below with reference to the embodiments with reference to the attached drawings.

Fig. 1 illustrates an exemplary system architecture 100 to which embodiments of the stock adjustment method applied to an unmanned bin or the stock adjustment apparatus applied to an unmanned bin of embodiments of the present application may be applied.

As shown in fig. 1, system architecture 100 may include

sorting units

101, 102, 103, network 104, and server 105. Network 104 is used to provide a medium of communication links between

sorting units

101, 102, 103 and server 105. Network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, to name a few.

The sorting

units

101, 102, 103 may interact with a server 105 via a network 104 to receive or send messages or the like. For example, the sorting unit may send information to the server about the orders to be sorted, which are orders that are allocated to the sorting equipment but not sorted by the sorting equipment.

The sorting

units

101, 102, 103 may also control the sorting equipment to sort out the goods indicated by the order to be sorted. As an example, the sorting unit may comprise a robot, a truck or the like for sorting goods. In the sorting unit shown in fig. 1, the sorting

units

101 and 102 are schematic diagrams of sorting robots, and the sorting unit 103 is a schematic diagram of a transport vehicle. The cart may be a variety of vehicles including, but not limited to, an unmanned vehicle, a manned vehicle, and the like. As an example, the cart may be an AGV cart.

The server 105 may be a server that provides various services, for example, may take a set of simulation orders and analyze the set of simulation orders to generate simulation results. And the server controls the sorting unit according to the simulation result and adjusts the stock of the unmanned storehouse.

It should be noted that the stock adjustment method applied to the unmanned bin provided by the embodiment of the present application may be executed by the server 105, and accordingly, the stock adjustment device applied to the unmanned bin may be disposed in the server 105.

The server may be hardware or software. When the server is hardware, it may be implemented as a distributed server cluster formed by multiple servers, or may be implemented as a single server. When the server is software, it may be implemented as multiple pieces of software or software modules (e.g., software or software modules used to provide distributed services), or as a single piece of software or software module. And is not particularly limited herein.

It should be understood that the number of sorting units, networks and servers in fig. 1 is merely illustrative. There may be any number of sorting units, networks, and servers, as desired for an implementation. When the electronic device on which the stock adjustment method applied to the unmanned bin is operated does not need to perform data transmission with other electronic devices, the system architecture may only include the electronic device on which the stock adjustment method applied to the unmanned bin is operated.

With continued reference to fig. 2, a flow 200 of one embodiment of a method for inventory adjustment applied to an unmanned bin according to the present application is shown. The cargo storage adjusting method applied to the unmanned storehouse comprises the following steps:

step 201, a simulation order set is obtained.

In the present embodiment, an execution subject (e.g., a server shown in fig. 1) applied to the stock adjustment method of the unmanned warehouse may acquire a simulation order set.

In this embodiment, the simulation order set may be a set of simulation orders. The simulated order may be understood as: instead of a real order from a real user, a virtual order is generated by a computer that simulates the real order.

In this embodiment, the execution agent may generate the simulation order set by itself, thereby obtaining the simulation order set. The simulation order set may also be generated by other electronic devices from which the fulfillment subject may then retrieve the simulation order set.

In this embodiment, the simulated order set may be generated according to scene information related to the order.

Here, the scene information may be given by a user, or may be received by the execution main body from another electronic device.

In this embodiment, the scenario may affect the order volume or the order content. For example, a scenario may include, but is not limited to, at least one of: promotional scenarios, non-promotional scenarios, instant shipment scenarios, delayed shipment scenarios, etc. It is understood that the order related to the context information may be an order that may be generated later and may not be available when the context information is obtained.

In the present embodiment, the scene information may be used to indicate a scene. As an example, the scene information may include: item identification of the upsell item and upsell strength information. Here, the promotion strength information may be represented by a discount rate.

Step 202, importing the simulation order set into a pre-established inventory adjustment model to generate a simulation result.

In this embodiment, the executive agent may import the simulation order set into a stock adjustment model established in advance, and generate a simulation result.

Here, the simulation order set is generated according to the scene information related to the scene information order given by the user. The simulation order set generated according to the scene information related to the scene information order given by the user can better accord with the real situation.

In this embodiment, the simulation result is used to indicate the cargo storage adjustment mode of the unmanned bin.

In this embodiment, the cargo storage adjustment mode of the unmanned warehouse may include at least one of the following items, but is not limited to: the number of articles in the unmanned bin, the placing position of the articles in the unmanned bin, the number of cargos in the unmanned bin, the number of shipment in the unmanned bin and the like.

In this embodiment, the inventory adjustment model may be used to characterize the correspondence between the order set and the simulation result. The inventory adjustment model requires entry of a true-case order corresponding to the desired scenario.

In this embodiment, the inventory adjustment model may be obtained in various ways, for example, a historical order set and a corresponding historical inventory adjustment mode may be obtained; and taking the historical order set and the corresponding historical stock adjustment mode as training samples, and training an initial model to obtain a stock adjustment model. The initial model may be a variety of models or networks based on machine learning algorithms, including but not limited to random forest models, convolutional neural networks, cyclic neural networks, and the like.

It is understood that the specific type of inventory adjustment mode of the output of the inventory adjustment model is optional. In practical applications, which inventory adjustment mode is desired, the inventory adjustment model can be trained by using the corresponding historical data, and an inventory adjustment model with expected output can be obtained.

Optionally, the historical orders may also be imported into the inventory adjustment model, and thus, the inventory adjustment model is reused to obtain a simulation result. However, when the historical order is used, due to the limitation of the historical scene of the historical order, the current expected simulated scene cannot be attached, and the simulation result obtained by the method may have errors, so that the situation that the adjustment of the unmanned bin is not suitable for the future situation (the situation that the unmanned bin is required for the user to really place the order in the scene indicated by the scene information) may occur.

It will be appreciated that the simulated order set imported into the inventory adjustment model is the normal order set for the inventory adjustment model. The simulated order set cannot be distinguished from a simulated order set, and is a virtual order generated by simulating the ordering condition of a real user by a computer.

And step 203, adjusting the stock of the unmanned bin according to the simulation result.

In this embodiment, the execution body may adjust the stock of the unmanned aerial vehicle according to the simulation result.

It should be noted that the simulation result obtained by simulating the order set according to the present application can better meet the actual production, so that the adjusted stock of the unmanned warehouse can improve the shipment efficiency in the scene desired by the user.

With continued reference to fig. 3, fig. 3 is a schematic diagram of an application scenario of the stock adjustment method applied to the unmanned storehouse according to the embodiment:

first, a user can be given scene information (e.g., "running shoes 5-fold") using the terminal 301. The server 302 may generate a simulated order set based on the context information ("running shoes 5-fold"). As an example, in the simulated order set, more orders may be included for running shoes, and fewer orders may be included for running shoes; compared to home appliances, there are a few sports wear purchased with running shoes.

The server 302 may then import the simulation order set into a pre-established inventory adjustment model, generating simulation results. As an example, the simulation results may include: firstly, adjusting running shoes in an unmanned storehouse to a goods shelf with the highest shipment priority; and secondly, the sportswear in the unmanned storehouse is adjusted to the goods shelf with the highest shipment priority.

Finally, the server 302 may control the transport device 303 (e.g., unmanned vehicle) in the unmanned bin to adjust the inventory in the unmanned bin based on the simulation results. The unmanned vehicle can perform the following actions according to the control instruction given by the server 302: firstly, adjusting running shoes in an unmanned storehouse to a goods shelf with the highest shipment priority; and secondly, the sportswear in the unmanned storehouse is adjusted to the goods shelf with the highest shipment priority.

Note that the unmanned bin control system including the server 302 and the transportation device 303 may be the whole as the subject of execution of the present application.

In the method provided by the above embodiment of the present application, the simulation result is obtained by importing the simulation order set into the stock adjustment model, and then the stock of the unmanned warehouse is adjusted according to the simulation result, where the simulation order set is generated according to the scene information related to the order, and the technical effects at least include:

first, a new unmanned warehouse inventory adjustment is provided.

Secondly, the simulated order set generated according to the scene information related to the order can better meet the real situation.

Thirdly, the simulation result obtained according to the simulation order set of the application can better accord with the actual production, so that the adjusted stock of the unmanned warehouse can improve the delivery efficiency in the scene expected by the user.

With further reference to fig. 4, a flow 400 of yet another embodiment of a stock adjustment method applied to an unmanned bin is shown. The process 400 of the cargo storage adjustment method applied to the unmanned warehouse comprises the following steps:

step 401, receiving scene information.

In the present embodiment, an execution subject (e.g., a server shown in fig. 1) of the stock adjustment method applied to the unmanned warehouse may receive scene information. Here, the scene information is specified by the user.

Step 402, generating an item identification set and a first order quantity corresponding to each item identification according to the scene information.

In this embodiment, the execution subject may generate an item identifier set and a first order quantity corresponding to an item identifier in the item identifier set according to the scenario information.

As an example, the set of item identifications may include: "item A" and "item B". The first order quantity for "item a" may be 300 and the first order quantity for "item B" may be 200.

Here, the article identifier may be used to indicate an article, and in an actual application process, it may be flexibly defined as which level of the article classification the article identifier is. By way of example, the item identifier may be a Stock Keeping Unit (SKU), or may be a top-level item class identifier of a SKU. By way of example, the article identifier may be "a brand 500 g bagged milk powder", or "a brand bagged milk powder".

Here, step 402 may be implemented in various ways.

As an example, step 402 may include: and acquiring the article identification and the discount rate aimed by the scene information, and converting the discount rate into the first order quantity according to a preset discount rate order quantity conversion relation. As an example, the scenario information includes "item a, five-fold", and the discount rate order quantity conversion rate may be that the normal price corresponds to the average quantity sold on the item on the month and day, and the first order quantity is the product of the average quantity sold on the month and day and the inverse discount rate.

Step 403, generating a simulation order set according to the item identifier set and the first order quantities.

In this embodiment, the executive agent may generate the simulation order according to the item identifier set and the respective first order quantity.

Here, step 403 may be implemented in various ways.

As an example, step 403 may include: for each item identifier in the item identifier set, generating an order subset including only the first order quantity for that item identifier; and identifying the corresponding order subset for each item to serve as a simulation order set.

Step 404, importing the simulation order set into a pre-established inventory adjustment model to generate a simulation result.

In this embodiment, the execution agent may import the simulation order set into a stock adjustment model that is established in advance, and generate a simulation result.

Here, the inventory adjustment model is used to characterize the correspondence between the order set and the simulation result.

And step 405, adjusting the stock of the unmanned bin according to the simulation result.

In this embodiment, the execution body may adjust the stock of the unmanned bin according to the simulation result.

In this embodiment, details of implementation and technical effects of step 404 and step 405 may refer to step 202 and step 203 in the corresponding embodiment of fig. 2, which are not described herein again.

As can be seen from fig. 4, compared with the embodiment corresponding to fig. 2, the process 400 of the inventory adjustment method applied to the unmanned warehouse in this embodiment highlights the steps of generating the first order quantity corresponding to the item identifier of the item identifier set according to the received scenario information, and generating the simulated order set according to the item identifier set and each first order quantity, so that the technical effects of the solution described in this embodiment at least may include:

first, a simulated order generation approach is provided.

Secondly, according to the scene information, generating an item identification set and a first order quantity corresponding to each item identification, and then according to the item identification set and each first order quantity, the simulated order set generated in this way can better accord with the actual situation of the scene. The specific analysis is as follows: in an actual scenario, a plurality of real orders placed by a plurality of users may relate to a plurality of item identifiers, each real order may also relate to a plurality of item identifiers, and the simulation of such a complex scenario from what angle is an unexpected and faced technical problem in the prior art.

In some embodiments, the execution subject may generate a simulation order set according to the scenario information, for example, obtain an item identifier in the scenario information, and use a combination of the item identifier and a preset number as the simulation order set.

In some implementations, the step 403 may be implemented by a flow 403 shown in fig. 5, where the flow 403 may include:

step 4031, obtain the order rule information of the article that is produced in advance.

Here, the execution body may acquire the article ordering rule information generated in advance. Here, the item ordering rule information may be used to indicate a rule that a user orders an item. The specific content included in the article ordering rule information can be specifically set in the actual application process.

In some embodiments, the item ordering rule information may include, but is not limited to, at least one of: item transition probability, frequent item set, associated confidence, purchase quantity probability distribution within order, and shipping address probability distribution.

Here, the item transition probability, the association confidence and the in-order purchase quantity probability distribution may correspond to the item identifiers, that is, each item identifier corresponds to its own item transition probability, association confidence and in-order purchase quantity probability distribution. Here, the item transition probability, the association confidence, and the purchase quantity probability distribution in the order will be described by taking the target item identifier as an example.

Here, the item transition probability may be used to indicate a probability from including N item identifications to N +1 item identifications in an order including the target item identification. Here, N may be a natural number equal to or greater than 1.

Here, the frequent items in the frequent item set may be item identifier combinations with a frequency of simultaneous occurrence (occurrence in the same order) greater than a preset frequency threshold.

Here, the above-mentioned association confidence may be used to characterize a conditional probability that the item identifier B appears in the case where the item identifier a (target item identifier) appears in the item identifier group (item identifier a and item identifier B).

Here, the probability distribution of the purchase quantity in the order may refer to a probability distribution of the order quantity corresponding to the target item identifier in the order. As an example, for item identification A, the purchase quantity probability distribution within an order, if identified as a probability distribution graph, may have the order quantity (e.g., 1 and 2) on the abscissa and the probability (30% for 1 and 70% for 2) on the ordinate.

Here, the delivery address probability distribution may be a probability distribution of a user delivery address. As an example, for item identification a, the shipping address probability distribution if identified as a probability distribution graph, the abscissa of the probability distribution graph may be the shipping address (e.g., north and south of the river) and the ordinate may be the probability (40% for north of the river and 60% for south of the river).

Optionally, the probability distribution of the receiving address may or may not correspond to the item identifier (i.e., the probability distribution of the receiving address is common to multiple item identifiers).

Step 4032, a simulation order set is generated according to the item ordering rule information, the item identification set and the quantity of each first order.

Here, the execution agent may generate a simulation order set according to the item ordering rule information, the item identifier set, and each first order quantity.

It should be noted that, the simulated order set is generated based on the article ordering rule information, so that the generated simulated order set can meet the ordering situation of the real user in the specified scene, and the generated simulated order set has higher accuracy.

In some embodiments, the item ordering rule information may be generated by: acquiring a historical order set; and generating the article ordering rule information according to the historical order set.

Referring to fig. 6, a schematic diagram of a generation manner of the item ordering rule information is shown. In fig. 6, a set of item identifiers in the historical order, a set of corresponding purchase quantities of item identifiers in the historical order, and a set of shipping addresses in the historical order may be extracted from the historical order set.

Item transition probabilities, frequent item sets, and associated confidence levels may then be extracted from the set of item identification groups within the historical order.

Then, a probability distribution of the purchase quantity of the item in the order can be established from the purchase quantity set corresponding to the item identification in the history by using a probability distribution parameter estimation (for example, establishing an initial binomial distribution, and then fitting a probability distribution of the purchase quantity of the item in the order by adjusting the parameters of the initial binomial distribution).

The probability distribution may then be established from the collection of shipping addresses within the historical order using probability distribution parameter estimation (e.g., establishing an initial normal distribution, then adjusting the parameters of the normal distribution to fit a shipping address probability distribution).

In some embodiments, the item transition probability is determined by: determining the number of items of the included item identification aiming at the historical order comprising the target item identification; and determining the item transfer probability of the target item identifier according to the order quantity of each item number.

As an example, for a history order (e.g., history order a, history order B, and history order C) including an item identifier a, determining the number of items of the included item identifier, for example, history order a includes an item identifier a (the number of items is 1), history order B includes an item identifier a and an item identifier B (the number of items is 2), and history order C includes an item identifier a and an item identifier C (the number of items is 2); according to the order quantity of each item (the order quantity corresponding to 1 item is 1, and the order quantity corresponding to 2 items is 2), an item transition probability between the item quantities corresponding to the item identifier a is determined, for example, the item transition probability of 1 item to 2 items may be the order quantity corresponding to 2 items (2), and divided by the sum of the total order quantities (3), so as to be 67%.

As an example, the historical orders including the item identifier a are counted, and if the number of the historical orders including the item identifier a is 200, the historical orders including only the item identifier a are 100, the historical orders including the item identifier a and having the total item number of 2 are 50, and the historical orders including the item identifier a and having the total item number of 3 are 30. Item transition probabilities (i.e., probabilities of transitioning from 1 to 2 and 2 to 3) between the number of items (i.e., 1, 2, and 3) corresponding to the target item identification may be determined based on order quantity 100 of item number 1, order quantity 20 of item number 2, and order quantity 30 of item number 3.

In some embodiments, the frequent item set may be determined by: extracting an article identifier included in the historical order from the historical order set; a target article scale is designated from the extracted article identification, and the following steps are executed for the target article identification: determining the object identifier which appears in the same historical order as the target object identifier as a related object identifier; for each associated item identifier, determining the proportion of the historical order comprising the target item identifier and the associated item identifier in the historical order set as a support degree, and if the support degree is greater than a preset support degree threshold value, determining the associated item identifier and the target item identifier as frequent items; and determining the set of the determined frequent items as a frequent item set.

As an example, an item identifier included in each historical order is extracted from the historical order set, and for each item identifier, the following steps are performed (the item identifier a is taken as an example for explanation below): for an item identifier (taking the item identifier B as an example) appearing in the same order as the item identifier A, determining the ratio of the quantity of the historical orders comprising the item identifier A and the item identifier B in the historical order set as a support degree, and if the support degree is greater than a support degree threshold value, taking the item identifier A and the item identifier B as frequent items; and establishing a corresponding relation between the article identification A and the article identification B.

In some embodiments, the associated confidence level corresponding to the frequent item based on the target item identification may be determined by: and for the associated item identifier in the frequent item, determining the ratio of the historical order comprising the target item identifier and the associated item identifier in the historical order comprising the target item identifier as the association confidence of the frequent item.

As an example, the historical order including the item identifier a and the item identifier B is used as the confidence of the association between the item identifier a and the item identifier B in the occupation ratio of the historical order including the item identifier a.

It is understood that the higher the support, the more common the combination of the illustrated article identification a and article identification B; the higher the association confidence, the stronger the combined association of the item identifier a and the item identifier B.

It should be noted that the frequent items are selected with the support degree, and the frequent items are used as the content of the article ordering rule information, so that the article possibly ordered by the user with the highest probability can be found for the scene needing to be simulated, and the order condition in the real scene can be accurately simulated.

It should be noted that, by using the associated confidence as the content of the item ordering rule information, after the item identifier that needs to appear is determined, the item identifier that may appear simultaneously with the item identifier may be accurately determined, and the determined identifier that appears simultaneously conforms to the purchasing habit of the user, so as to improve the accuracy of the simulated order.

Here, a probability density distribution of the purchase quantity of the order may be established for the item identification a. In the established probability density distribution, the abscissa may be the purchase amount of the item a in the order, and the ordinate may be the purchase probability. The probability density distribution function is used for simulating the purchase quantity in the order, and the selection can be flexibly carried out in practical application. As an example, simulations can be performed with a binomial distribution or a negative binomial distribution.

In some embodiments, the shipping address probability distribution may be determined by: for historical orders in the historical order set, extracting receiving addresses in the historical orders; generating a superior address according to the extracted delivery address; and establishing the probability distribution of the receiving address by using the generated superior address.

As an example, the superior address may be a shipping address specific to a street level (which level may be flexibly determined) of the shipping address in the historical order. That is, the address specific to the house number in the historical order is not utilized, and thus, technical effects may include at least: the addresses of the specific receiving doorplate numbers are scattered, and general logistics planning (such as delivery from which warehouse) is carried out, and the specific address determination of the receiving doorplate numbers is not utilized, so that the receiving address distribution is established by utilizing superior addresses, the calculation workload can be reduced, more practical receiving address distribution can be established, and the applicability and the accuracy of subsequent application of the receiving address distribution are improved.

Referring to FIG. 7, a schematic diagram of generating a simulated order set using an order generation model is shown.

In some embodiments, step 4032 may be implemented by: and importing the article ordering rule information, the article identification set and the quantity of each first order into a pre-established order generation model to obtain a simulated order set.

Here, the order generation model is used to represent the correspondence between the item ordering rule information, the item identification set first order quantity, and the simulated order set.

Here, the simulated order model may be obtained by: establishing an initial model; and training the initial model by using a training sample set to obtain an order generation model.

Here, the initial model may be various untrained or untrained neural networks, where the neural networks may include at least one of, but are not limited to: convolutional neural networks, cyclic neural networks, long-term memory neural networks, and the like.

Here, the training samples in the training sample set include a training history order set, and an item ordering rule set, an item identification set, and an order quantity extracted from the training history order set.

It should be noted that, taking the above three (the item ordering rule information, the item identification set, and each first order quantity) as input, and using the order generation model to obtain the output simulated order set, the technical effects at least include:

first, a new simulated order generation approach is provided.

Second, a set of simulation orders can be generated quickly.

And thirdly, the article ordering rule information is used as an input, and the article ordering rule information can be flexibly adjusted, so that more accurate article ordering rule information can be obtained through multiple iterations, and a more accurate simulation order set can be obtained.

Referring to fig. 8, which shows a schematic diagram of an alternative implementation of step 4032, step 4032 may include:

step 40321, for each item identifier in the set of item identifiers, a subset of orders corresponding to the item identifier is generated.

40322, a simulation order set is generated from each order subset.

Here, the execution agent may adjust each order subset to generate a simulation order set.

As an example, in the order subset corresponding to the item identifier a, there may be an order including the item identifier B; in the order subset corresponding to the item identifier B, there may be an order including the item identifier a. After generating the respective order subsets, a third order quantity of the generated order including item identification a, and a third order quantity of the generated order including item identification B may be viewed in combination with the order subsets. If the third order quantity of the article identifier A is larger than the first order quantity, removing the article identifier A from some orders comprising the article identifier B and the article identifier A; and if the third order quantity of the item identifier B is larger than the first order quantity, removing the item identifier B from some orders comprising the item identifier B and the item identifier A.

In some embodiments, referring to fig. 9, the item identifier in the item identifier set is designated as a target item identifier, and the order subset corresponding to the target item identifier may be generated through a process 900, where the process 900 may include:

step 901, generating a first order with a second order quantity according to the first order quantity corresponding to the target article identifier.

Here, the second order quantity is smaller than the first order quantity.

Here, the first order may be a null order, and the null order may be filled with information of a predefined kind. The predefined category of information may include, but is not limited to, at least one of: the goods identification, the purchase quantity corresponding to the goods identification and the receiving address.

Optionally, different content may be added to the first order according to the predefined category.

And step 902, determining the quantity of the item identifications in each first order according to the item transfer probability corresponding to the target item identification.

By way of example, the item identification number may comprise one, two, three, or the like.

Step 903, adding a target article identifier to the first order with the article identifier number equal to 1, and adding an article identifier forming a frequent item with the target article identifier to the first order with the article identifier number greater than 1 according to the correlation confidence corresponding to the target article identifier to obtain a second order.

Adding a target article identifier to a first order with the number of article identifiers equal to 1 to obtain a second order; and adding the item identifications of the items which form frequent items with the target item identification into the first order with the item identification number larger than 1 to obtain another second order.

And 904, adding the order quantity for the item identifier according to the probability distribution of the order quantity in the order of the item identifier for the item identifier in each second order to obtain a third order.

And 905, adding the receiving address to each third order according to the probability distribution of the receiving address to obtain a fourth order.

Here, the set of fourth orders may be considered as a subset of orders corresponding to the target item identification.

In the practical application process, the content needing to be filled in the first order can be flexibly selected.

Optionally, an order subset corresponding to the target item identifier may be generated according to each second order. The set of second orders may be considered a subset of orders corresponding to the target item identification.

Optionally, an order subset corresponding to the target item identifier may be generated according to each third order. For example, the set of third orders may also be regarded as a subset of orders corresponding to the target item identification; for another example, according to the probability distribution of the receiving address, the receiving address is added to each third order to obtain a fourth order, and a set of the fourth order may be regarded as an order subset corresponding to the target item identifier.

Referring to fig. 10, the step 402 may be implemented by a process 402, where the process 402 may include:

step 4021, determining the scene type to which the received scene information belongs according to the preset type judgment condition.

Here, the type judgment condition may be used to judge the scene type of the scene information described above.

Here, the scene types may be classified into various types by using different classification angles. For example, from the perspective of whether a promotion is promoted or not, the scene types can be divided into a promotion scene and a non-promotion scene. As another example, scene types can be classified into an immediate shipment scene and a delayed shipment scene from the viewpoint of whether or not shipment is time (whether or not shipment is immediate).

Step 4022, determining an order quantity prediction model corresponding to the received scene information from the order quantity prediction model set according to the corresponding relation between the pre-established scene type and the order quantity prediction model.

Here, the correspondence between the scene type and the order quantity prediction model may be established in advance, in other words, the order quantity prediction model may be established in plurality for each scene type.

Here, the order quantity prediction model corresponding to the scene type to which the received scene information belongs may be determined as the order quantity prediction model corresponding to the received scene information.

Here, the order quantity prediction model is used to represent the correspondence between the scenario information and the item identification set and the first order quantity.

Here, the order quantity prediction model may be established by: acquiring scene information under a target scene type and a scene historical order set; determining a training article identification set and the order quantity corresponding to the training article identification from a scene placed historical order set, and taking scene information, the determined training article identification set and the order quantity as training samples; and training the initial model through at least one training sample to obtain an order quantity prediction model corresponding to the target scene type.

Here, the initial model may be an untrained or an untrained completed machine learning model. As an example, the machine learning model described above may include at least one of, but is not limited to: random forest models, convolutional neural networks, cyclic neural networks, long-term and short-term memory neural networks and the like.

Step 4023, importing the scene information into a pre-established order quantity prediction model, and generating an item identification set and a first order quantity corresponding to each item identification.

It should be noted that, by using the order quantity prediction model of each scene type, the item identifier set and the first order quantity corresponding to each item identifier can be accurately and quickly predicted for different scenes.

With further reference to fig. 11, as an implementation of the method shown in the above figures, the present application provides an embodiment of a stock adjustment device applied to an unmanned storehouse, which corresponds to the embodiment of the method shown in fig. 2, and which may include the same or corresponding features as the embodiment of the method shown in fig. 2, in addition to the features described below. The device can be applied to various electronic equipment.

As shown in fig. 11, the cargo hold adjusting apparatus 1100 applied to the unmanned storehouse of the present embodiment includes: an acquisition unit 1101, a generation unit 1102, and an adjustment unit 1103; the acquisition unit is configured to acquire a simulation order set, wherein the simulation order set is generated according to scene information related to orders; the generation unit is configured to import the simulation order set into a stock adjustment model which is established in advance, and generate a simulation result, wherein the stock adjustment model is used for representing the corresponding relation between the order set and the simulation result, and the simulation result is used for indicating the stock adjustment mode of the unmanned warehouse; and the adjusting unit is configured to adjust the stock of the unmanned bin according to the simulation result.

Referring now to FIG. 12, shown is a block diagram of a computer system 1200 suitable for use in implementing the electronic device of an embodiment of the present application. The electronic device shown in fig. 12 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present application.

As shown in fig. 12, the computer system 1200 includes a Central Processing Unit (CPU)1201, which can perform various appropriate actions and processes in accordance with a program stored in a Read Only Memory (ROM)1202 or a program loaded from a storage section 1208 into a Random Access Memory (RAM) 1203. In the RAM 1203, various programs and data necessary for the operation of the system 1200 are also stored. The CPU 1201, ROM 1202, and RAM 1203 are connected to each other by a bus 1204. An input/output (I/O) interface 1205 is also connected to bus 1204.

The following components are connected to the I/O interface 1205: an input section 1206 including a keyboard, a mouse, and the like; an output portion 1207 including a display device such as a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, and a speaker; a storage section 1208 including a hard disk and the like; and a communication section 1209 including a network interface card such as a LAN card, a modem, or the like. The communication section 1209 performs communication processing via a network such as the internet. A driver 1210 is also connected to the I/O interface 1205 as needed. A removable medium 1211, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like, is mounted on the drive 1210 as necessary, so that a computer program read out therefrom is mounted into the storage section 1208 as necessary.

In particular, according to an embodiment of the present disclosure, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method illustrated in the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network through the communication section 1209, and/or installed from the removable medium 1211. The computer program, when executed by a Central Processing Unit (CPU)1201, performs the above-described functions defined in the methods of the present application.

It should be noted that the computer readable medium mentioned above in the present application may be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, 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 disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present application, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In this application, however, a computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.

Computer program code for carrying out operations for aspects of the present application may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).

The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

The units described in the embodiments of the present application may be implemented by software or hardware. The described units may also be provided in a processor, and may be described as: a processor includes an acquisition unit, a generation unit, and an adjustment unit. Where the names of the units do not in some cases constitute a limitation on the units themselves, for example, the acquisition unit may also be described as a "unit to acquire a set of simulation orders".

As another aspect, the present application also provides a computer-readable medium, which may be contained in the electronic device described in the above embodiments; or may exist separately without being assembled into the electronic device. The computer readable medium carries one or more programs which, when executed by the electronic device, cause the electronic device to: acquiring a simulation order set, wherein the simulation order set is generated according to scene information related to orders; importing the simulation order set into a pre-established stock adjustment model to generate a simulation result, wherein the stock adjustment model is used for representing the corresponding relation between the order set and the simulation result, and the simulation result is used for indicating the stock adjustment mode of the unmanned warehouse; and adjusting the stock of the unmanned bin according to the simulation result.

The above description is only a preferred embodiment of the application and is illustrative of the principles of the technology employed. It will be appreciated by those skilled in the art that the scope of the invention herein disclosed is not limited to the particular combination of features described above, but also encompasses other arrangements formed by any combination of the above features or their equivalents without departing from the spirit of the invention. For example, the above features may be replaced with (but not limited to) features having similar functions disclosed in the present application.

Claims

1. A cargo storage adjusting method applied to an unmanned storehouse comprises the following steps:

acquiring a simulation order set, wherein the simulation order set is generated according to scene information related to orders;

importing the simulation order set into a pre-established stock adjustment model to generate a simulation result, wherein the stock adjustment model is used for representing the corresponding relation between the order set and the simulation result, and the simulation result is used for indicating the stock adjustment mode of the unmanned warehouse;

and adjusting the stock of the unmanned bin according to the simulation result.

2. The method of claim 1, wherein said obtaining a set of simulation orders comprises:

receiving scene information;

generating an item identification set and a first order number corresponding to each item identification according to the scene information;

and generating the simulated order set according to the item identification set and the quantity of each first order.

3. The method of claim 2, wherein said generating the simulated set of orders from the set of item identifications and respective first order quantities comprises:

acquiring pre-generated article ordering rule information, wherein the article ordering rule information can be used for indicating the rule of ordering articles by a user;

and generating the simulated order set according to the item ordering rule information, the item identification set and the quantity of each first order.

4. The method of claim 3, wherein the item ordering rule information is generated by:

acquiring a historical order set;

and generating article ordering rule information according to the historical order set.

5. The method of claim 4, wherein the item ordering rule information comprises at least one of: item transition probability, frequent item set, associated confidence, purchase quantity probability distribution within order, and shipping address probability distribution.

6. The method of claim 5, wherein the item transition probability is determined by:

determining the number of items of the included item identification aiming at the historical order including the target item identification;

and determining item transfer probability among the item numbers corresponding to the target item identification according to the order number of each item number.

7. The method of claim 5, wherein the frequent item set is determined by:

extracting the item identification included in the historical order from the order set;

specifying a target article identifier from the extracted article identifiers, and executing the following steps aiming at the target article identifier: determining the object identifier which is in the same historical order as the target object identifier as a related object identifier; for each associated item identifier, determining the proportion of the historical order comprising the target item identifier and the associated item identifier in the historical order set as a support degree, and if the support degree is greater than a support degree threshold value, determining the associated item identifier and the target item identifier as frequent items;

and determining the set of the determined frequent items as a frequent item set.

8. The method of claim 7, wherein the associated confidence level corresponding to the frequent item is determined by:

for the associated item identification in the frequent item, determining the proportion of the historical order comprising the target item identification and the associated item identification in the historical order comprising the target item identification as the associated confidence of the frequent item.

9. The method of claim 5, wherein the intra-order purchase quantity probability distribution is determined by:

determining the purchase quantity of the target item identifier in the historical order comprising the target item identifier;

and establishing probability distribution of the purchase quantity in the order corresponding to the target article identification according to the purchase quantity corresponding to each historical order.

10. The method of claim 5, wherein the shipping address probability distribution is determined by:

for historical orders in the historical order set, extracting receiving addresses in the historical orders;

generating a superior address according to the extracted delivery address;

and establishing the probability distribution of the receiving address by using the generated superior address.

11. The method of claim 3, wherein generating the simulated set of orders according to the item ordering rule information, the item identification set, and the respective first order quantities comprises:

and importing the article ordering rule information, the article identification set and each first order quantity into a pre-established order generation model to obtain a simulated order set, wherein the order generation model is used for representing the corresponding relation among the article ordering rule information, the article identification set and each first order quantity and the simulated order set.

12. The method of claim 3, wherein generating the simulated set of orders according to the item ordering rule information, the item identification set, and the respective first order quantities comprises:

for each item identifier in the item identifier set, generating an order subset corresponding to the item identifier;

and generating the simulated order set according to each order subset.

13. The method of claim 12, wherein the subset of orders may be generated by:

generating a first order with a second order quantity according to the first order quantity corresponding to the target article identifier;

determining the quantity of the item identifications in each first order according to the item transfer probability corresponding to the target item identification;

adding target article identifications to the first orders with the article identification number equal to 1, and adding article identifications forming frequent items with the target article identifications to the first orders with the article identification number larger than 1 according to the corresponding association confidence degrees of the target article identifications to obtain second orders;

for the item identifier in each second order, adding the order quantity for the item identifier according to the probability distribution of the purchase quantity in the order of the item identifier to obtain a third order;

and generating an order subset corresponding to the target item identifier according to each third order.

14. The method according to claim 13, wherein the generating a subset of orders corresponding to the target item identifier according to each third order comprises:

and adding the receiving address to each third order according to the probability distribution of the receiving address to obtain a fourth order.

15. The method according to claim 2, wherein the generating a set of item identifiers and a first order quantity corresponding to each item identifier according to the scenario information comprises:

determining a scene type to which the received scene information belongs according to a preset type judgment condition;

determining an order quantity prediction model corresponding to the received scene information from an order quantity prediction model set according to a corresponding relation between a pre-established scene type and the order quantity prediction model, wherein the order quantity prediction model is used for representing the corresponding relation between the scene information and an item identification set and between the first order quantity and the item identification set;

and importing the received scene information into the determined order quantity prediction model to generate an item identification set and a first order quantity corresponding to each item identification.

16. A cargo storage adjusting device applied to an unmanned storehouse comprises:

an acquisition unit configured to acquire a simulation order set, wherein the simulation order set is generated according to order-related scene information;

the generation unit is configured to import the simulation order set into a pre-established stock adjustment model and generate a simulation result, wherein the stock adjustment model is used for representing the corresponding relation between the order set and the simulation result, and the simulation result is used for indicating a stock adjustment mode of the unmanned warehouse;

an adjusting unit configured to adjust the stock of the unmanned bin according to the simulation result.

17. The apparatus of claim 16, wherein the obtaining unit is further configured to:

receiving scene information;

18. An electronic device, comprising:

one or more processors;

a storage device having one or more programs stored thereon,

when executed by the one or more processors, cause the one or more processors to implement the method of any one of claims 1-15.

19. A computer-readable medium, on which a computer program is stored, wherein the program, when executed by a processor, implements the method of any one of claims 1-15.