Inventory data management method, device, equipment and storage medium

Through collaboration between multiple warehouse terminals, a more complete inventory data management model is built using machine learning models, which solves the problems of insufficient data and external influences of suppliers in inventory forecasting and replenishment decisions, and achieves a more accurate Inventory management.

CN113554401BActive Publication Date: 2024-11-12HANGZHOU PINPIANYI NETWORK TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202110898696.4
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2021-08-05
Publication Date
2024-11-12
Estimated Expiration
2041-08-05

AI Technical Summary

Technical Problem

When suppliers manage inventory data, due to the randomness of procurement quantity and insufficient training data, it is difficult to achieve inventory management based on effective predictions, especially in the multi-level distribution model, which is affected by shipments by other suppliers.

Method used

Through collaboration between multiple warehouse terminals, use machine learning models to manage inventory data, including sending training request signals, querying and feedback inventory data indexes, assisting in training center models, updating and distributing training result data, to build a more complete Inventory data management model.

Benefits of technology

A relatively complete machine learning model is implemented, which can make inventory prediction and replenishment decisions more accurately, reducing the risks due to insufficient data and external impacts.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN113554401B_ABST
    Figure CN113554401B_ABST
Patent Text Reader

Abstract

The present application discloses an inventory data management method, device, equipment and storage medium, wherein the method includes: in response to a training request signal sent by a warehouse terminal, querying the inventory data index uploaded by other store terminals related to the training request signal; feeding back the queried inventory data index to the warehouse terminal that sent the training request signal; in response to the warehouse terminal's selection operation signal for the inventory data index, sending an assisting training signal and a central model to other store terminals according to the selection operation signal; receiving training result data from other store terminals; updating the central model according to the training result data and distributing the central model to the requesting warehouse terminal. The benefit of the present application is that through the collaboration of multiple warehouse terminals in machine learning models, model training data and model-related parameters, one of the warehouse terminals has a more complete machine learning model for inventory data management.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to an inventory data management method, apparatus, device and storage medium. Background Art

[0002] In related technologies, orders from multiple stores are aggregated through an Internet platform, and then unified procurement and logistics pickup are carried out from suppliers. The carrier vehicles then deliver the goods to the corresponding stores according to the purchase orders, thereby reducing the warehousing costs of stores such as convenience stores and improving procurement flexibility.

[0003] When suppliers manage inventory data, they often need to make certain forecasts based on historical data to determine the quantity and timing of replenishment.

[0004] However, due to the randomness of the purchase quantity in the above model, which is different from the previous multi-level distribution batch regular purchase model, suppliers are often unable to make accurate predictions based on changes in their own data. Because in the above model, the supplier's shipment volume is also affected by other suppliers, and there may be a problem of insufficient training data. Therefore, there is now a situation where suppliers cannot achieve inventory management based on effective predictions based on their own data. Summary of the invention

[0005] The content of this application is used to introduce concepts in a brief form, which will be described in detail in the detailed implementation section below. The content of this application is not intended to identify the key features or essential features of the technical solution claimed for protection, nor is it intended to limit the scope of the technical solution claimed for protection.

[0006] Some embodiments of the present application propose inventory data management methods, devices, electronic devices, and computer-readable media to solve the technical problems mentioned in the above background technology section.

[0007] As a first aspect of the present application, some embodiments of the present application provide an inventory data management method, including: in response to a training request signal sent by a warehouse terminal, querying the inventory data index uploaded by other store terminals related to the training request signal; feeding back the queried inventory data index to the warehouse terminal that sends the training request signal; in response to the warehouse terminal's selection operation signal for the inventory data index, sending an assistance training signal and a central model to other store terminals that upload these inventory data indexes according to the inventory data index selected by the selection operation signal; receiving training result data obtained from other store terminals through training the central model with their own inventory data; updating the central model according to the training result data and distributing the updated central model to the warehouse terminal that sends the training request signal.

[0008] As a second aspect of the present application, some embodiments of the present application provide an inventory data management device, including: a query module, used to respond to a training request signal sent by a warehouse terminal, and query the inventory data index uploaded by other store terminals related to the training request signal; a feedback module, used to feed back the queried inventory data index to the warehouse terminal that sends the training request signal; a sending module, used to respond to the warehouse terminal's selection operation signal for the inventory data index, and send an assistance training signal and a central model to other store terminals that upload these inventory data indexes according to the inventory data index selected by the selection operation signal; a receiving module, used to receive training result data obtained from other store terminals through training the central model with their own inventory data; a distribution module, used to update the central model according to the training result data and distribute the updated central model to the warehouse terminal that sends the training request signal.

[0009] As the third aspect of the present application, some embodiments of the present application provide an electronic device, comprising: one or more processors; a storage device on which one or more programs are stored, and when the one or more programs are executed by one or more processors, the one or more processors implement the method described in any implementation manner of the above-mentioned first aspect.

[0010] As a fourth aspect of the present application, some embodiments of the present application provide a computer-readable medium on which a computer program is stored, wherein when the program is executed by a processor, the method described in any implementation of the above-mentioned first aspect is implemented.

[0011] The beneficial effect of the present application is that through the collaboration of multiple warehouse terminals in machine learning models, model training data and model-related parameters, one of the warehouse terminals is provided with a more complete machine learning model for inventory data management. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] The drawings constituting a part of this application are used to provide a further understanding of this application, so that other features, purposes and advantages of this application become more obvious. The illustrative embodiment drawings and their descriptions of this application are used to explain this application and do not constitute an improper limitation on this application.

[0013] In addition, throughout the drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and that the components and elements are not necessarily drawn to scale.

[0014] In the attached picture:

[0015] Figure 1 is a flow chart of an inventory data management method according to an embodiment of the present application;

[0016] Figure 2It is a flowchart of some steps in the inventory data management method according to an embodiment of the present application;

[0017] Figure 3 is a flowchart of another part of the steps in the inventory data management method according to an embodiment of the present application;

[0018] Figure 4 is a schematic diagram of the architecture of an inventory data management system according to an embodiment of the present application;

[0019] Figure 5 This is a schematic diagram of an operation interface of a warehouse terminal in an inventory data management method according to an embodiment of the present application;

[0020] Figure 6 is another schematic diagram of an operation interface of a warehouse terminal in an inventory data management method according to an embodiment of the present application;

[0021] Figure 7 is another schematic diagram of an operation interface of a warehouse terminal in an inventory data management method according to an embodiment of the present application;

[0022] Figure 8 is a structural diagram of an inventory data management device according to an embodiment of the present application;

[0023] Fig. 9 It is a structural schematic diagram of an electronic device according to an embodiment of the present application.

[0024] Meaning of the reference numerals in the figures:

[0025] Inventory data management system 100, warehouse terminals 101, 102, 103, system server 104. DETAILED DESCRIPTION

[0026] Embodiments of the present application will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present application are shown in the accompanying drawings, it should be understood that the present application can be implemented in various forms, and should not be construed as being limited to the embodiments set forth herein. On the contrary, these embodiments are provided to provide a more thorough and complete understanding of the present application. It should be understood that the drawings and embodiments of the present application are only for exemplary purposes and are not intended to limit the scope of protection of the present application.

[0027] It should also be noted that, for ease of description, only the parts related to the invention are shown in the drawings. In the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other.

[0028] It should be noted that the concepts such as "first" and "second" mentioned in this application are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0029] It should be noted that the modifications of "one" and "plurality" mentioned in the present application are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0030] The names of the messages or information exchanged between multiple devices in the embodiments of the present application are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0031] The present application will be described in detail below with reference to the accompanying drawings and in combination with embodiments.

[0032] Reference Figure 1 As shown, the inventory data management method as an embodiment of the present application includes the following steps:

[0033] S1: In response to a training request signal sent by a warehouse terminal, query the inventory data index uploaded by other store terminals related to the training request signal.

[0034] S2: Feedback the retrieved inventory data index to the warehouse terminal that sent the training request signal.

[0035] S3: In response to the warehouse terminal's selection operation signal for the inventory data index, sending an assistance training signal and a central model to other store terminals that upload the inventory data indexes according to the inventory data indexes selected by the selection operation signal.

[0036] S4: Receive training result data obtained from other store terminals by training the central model using their own inventory data.

[0037] S5: Update the central model according to the training result data and distribute the updated central model to the warehouse terminal that sent the training request signal.

[0038] like Figure 4 As shown, Figure 4 An inventory data management system is shown, which includes: a plurality of warehouse terminals belonging to different users and a system server. Steps S1 to S5 can be executed by the system server.

[0039] The warehouse terminal can be a desktop computer. As a preferred solution, the warehouse terminal is a smart phone. The warehouse terminal has certain data processing capabilities and can send and receive corresponding signals, data, and information through mobile networks. The system server is a system platform built by one or more computers or a system platform composed of cloud servers. The warehouse terminal can exchange data with the system service, but the warehouse terminals do not exchange data directly.

[0040] Reference Figure 5 As shown, Figure 5 The operation interface of the warehouse terminal (a smartphone in this case) is shown. Users can select the required inventory data management function through the operation interface. Among them, "Local analysis of inventory data" is based on the training and input of local data and machine learning models to predict possible external data changes. "Local analysis of inventory data" is to achieve indirect training of machine learning models through collaboration with other warehouse terminals to obtain a more complete machine learning model.

[0041] Reference Figure 6 As shown, Figure 6 Another operation interface of the warehouse terminal is shown. This interface is used for users to select or fill in specific requirements of "inventory data collaborative analysis". Figure 6 As shown, the items that the user needs to operate include: analysis items, forecast time range, and product SKU.

[0042] Among them, the analysis project and the prediction time range are presented in the form of a selection box. When the user clicks the selection box, the selection box for the analysis project and the prediction time range will produce drop-down options, and the user can select one of them.

[0043] Specifically, the analysis items include: inventory forecast, replenishment forecast, shipment forecast, and unit price forecast. The forecast time range includes: next 1 day, next 5 days, next 15 days, next 30 days, and next 3 months. It should be noted here that if the forecast time range is too long, the forecast accuracy and confidence will be greatly reduced and lose reference value. Because the maximum time range is 3 months.

[0044] Product SKU can be filled in the form of a fill-in box. Users can manually fill in the product SKU. When filling in the box, the system will automatically associate the historical filling records and record the product SKU to help users fill in the complete value. As a preferred solution, users can use the "magnifying glass" icon to search the interface to obtain the corresponding product SKU through product name, picture, etc. As a preferred solution, users can obtain the corresponding product SKU through the product name and the text information of the corresponding product specifications. Furthermore, the corresponding product SKU can be obtained by taking a picture of the product and scanning the barcode of the product.

[0045] After completing the analysis project, prediction time range, and product SKU, a machine learning model has actually been specified, that is, the user has specified a preset machine learning model through operation.

[0046] In addition, when users need to predict multiple product SKUs or need summary analysis, they can locally summarize the analysis results of multiple machine learning models and then use a merging algorithm to make predictions.

[0047] In addition, if Figure 6 As shown, the method of the present application provides two solutions for selecting assisting warehouse terminals, wherein the corresponding warehouse terminal is selected according to the user's operation, that is, after the user clicks the "manual matching" button, the warehouse terminal can pop up a list interface (not shown in the figure) for the user to select the corresponding warehouse terminal or the inventory data index of the warehouse terminal.

[0048] In most cases, for users with non-professional needs, they can click "Auto Match" and the system will match all suitable warehouse terminals or inventory data indexes of warehouse terminals in the background (system server).

[0049] like Figure 7 As shown, Figure 7 The interface is shown when the system server sends the queried inventory data index to the warehouse terminal for user selection. Figure 7 As shown, the interface displays the parameters of the inventory data index query result summary items, such as warehouse name, number of data items, and update time. Users can select these inventory data indexes by selecting them.

[0050] Specifically, the inventory data index of the present application refers to index data that can express the difference between each data piece stored in the warehouse terminal and other data pieces in addition to the data content itself, that is, each data piece has a header index, and the data itself can be found through the header index. In the database field, the inventory data index is different from data address indexes such as key values. The object of its service is the construction of the data model. Of course, the inventory data index can be associated with the data structure and key value of the data storage itself.

[0051] As a preferred solution, the inventory data index includes the following parts: warehouse ID, product SKU, data time, and data ID.

[0052] Among them, the warehouse ID is used to distinguish different warehouse terminals, that is, the data owner. The product SKU is used to distinguish different products and is automatically associated when querying. The data time is the time when the data is generated or stored, which can be accurate to milliseconds. The data ID is a random code matched to each data, which is used to distinguish the differences between the above identical data, although generally speaking, data time is difficult to repeat.

[0053] The warehouse ID, product SKU, and data time can all be sent from the warehouse terminal to the system server in plain text, and then sent from the system server to another warehouse terminal. Although the data content cannot be known by obtaining the data ID, in order to further improve data security, the data ID is hashed and then sent to the system server. The system server performs a second hash encryption process when sending it to another warehouse terminal.

[0054] As shown in 7, the system server Figure 6 Configuration, query the required data through the inventory data index, and then summarize it under the corresponding warehouse name, and record the number of data items and the latest update time in these data sets. The update time can be accurate to the day.

[0055] It should be noted that the system server predicts the correspondence between the warehouse ID and other warehouse data, and the warehouse address data and other information can be obtained through the warehouse ID.

[0056] As a preferred solution, Figure 7 For example, the user can click on one of the warehouse names to obtain the warehouse details page interface (not shown in the figure), so as to obtain data such as the warehouse address.

[0057] Continue to refer to Figure 2 As shown, step S1 specifically includes the following steps:

[0058] S11: Analyze the training content data in the training request signal.

[0059] S12: Select one of the multiple central models according to the training content data.

[0060] S13: Query data features of input data and output data required for central model training according to the type of the central model.

[0061] S14: Generate a query range of the inventory data index according to one or more of the data features.

[0062] S15: Select product SKU based on training content data.

[0063] S16: Generate a query range of the inventory data index according to the product SKU.

[0064] As a specific solution, the training request signal is generated and triggered by the operation of the warehouse terminal, such as Figure 6 In the interface shown, click the "Automatic Matching" button to send a training request signal to the system server. The training request signal contains training content data, including analysis items, prediction time range, product SKU, etc.

[0065] The combination of different training content data can specify different central models. The central model refers to a machine learning model pre-stored or updated in the system server, which can be set in multiples according to the training content. As a preferred solution, each product SKU can have a corresponding central model.

[0066] After determining the central model, the system server needs to query the data features of the input data and output data of the central model. Here, data features refer to the type and format of the input data and output data. Therefore, as a preferred solution, the inventory data index also includes: data type and data format. These two parts are also processed by hash encryption.

[0067] As a further preferred solution, when S1 determines the warehouse terminal that sends the training request signal, it can be sent to the warehouse terminal corresponding to the warehouse within a certain set range.

[0068] As a more specific solution, the geographical scope is not determined based on the location of the warehouse that initiates the assistance, but rather based on the product SKU selected by the training request signal to determine the stores that have purchased the product SKU. Then, based on these stores and product SKUs, all warehouses that have provided the product SKU to these stores within a certain time range are queried, and all the queried warehouses are used as the set range for sending the training request signal.

[0069] Continue to refer Figure 3 As shown, step S3 specifically includes:

[0070] S31: Analyze the selected inventory data index in the selection operation signal.

[0071] S32: Selecting a store terminal that sends a training assistance signal according to the inventory data index.

[0072] S33: Sending the corresponding inventory data index selected by the selected operation signal to the store terminal selected to send the training assistance signal.

[0073] S34: Selecting the one with the latest update time from among the multiple historical versions of the central model selected according to the training content data and sending it to the selected store terminal.

[0074] Simply put, the system server not only needs to inform other warehouse terminals (of course, the initiating warehouse terminal can also initiate model training and upload parameters, etc.) to start assisting, but also needs to provide the required data index and the model itself.

[0075] As a specific solution, the training result data includes model parameters, model structure and parameter gradients of the central model.

[0076] Through the above scheme, the data of each collaborating warehouse terminal does not leave the local area, and only the training results are output to the system server. The system server integrates these parameters to update the original central model, and then sends the updated model to the initiating warehouse terminal. The warehouse terminal can use the central model for data prediction, etc.

[0077] like Figure 8 As shown, as an embodiment of the present application, the inventory data management device includes: a query module, which is used to respond to a training request signal sent by a warehouse terminal and query the inventory data index uploaded by other store terminals related to the training request signal; a feedback module, which is used to feed back the queried inventory data index to the warehouse terminal that sends the training request signal; a sending module, which is used to respond to the warehouse terminal's selection operation signal for the inventory data index, and send an assistance training signal and a central model to other store terminals that upload these inventory data indexes according to the inventory data index selected by the selection operation signal; a receiving module, which is used to receive training result data obtained from other store terminals through their own inventory data to train the central model; a distribution module, which is used to update the central model according to the training result data and distribute the updated central model to the warehouse terminal that sends the training request signal.

[0078] like Fig. 9 As shown, the electronic device 800 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 801, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 802 or a program loaded from a storage device 808 into a random access memory (RAM) 803. In the RAM 803, various programs and data required for the operation of the electronic device 800 are also stored. The processing device 801, the ROM 802, and the RAM 803 are connected to each other via a bus 804. An input / output (I / O) interface 805 is also connected to the bus 804.

[0079] Typically, the following devices may be connected to the I / O interface 805: input devices 806 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; output devices 807 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 808 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 809. The communication device 809 may allow the electronic device 800 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 8 The electronic device 800 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead. Figure 8 Each block shown in the figure may represent one device, or may represent multiple devices as required.

[0080] In particular, according to some embodiments of the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, some embodiments of the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In some such embodiments, the computer program can be downloaded and installed from the network through the communication device 809, or installed from the storage device 808, or installed from the ROM 802. When the computer program is executed by the processing device 801, the above-mentioned functions defined in the method of some embodiments of the present application are executed.

[0081] It should be noted that the computer-readable medium described above in some embodiments of the present application may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0082] In some embodiments of the present application, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, device, or device. In some embodiments of the present application, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in combination with an instruction execution system, device, or device. The program code contained on the computer-readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0083] In some embodiments, the client and the server may communicate using any currently known or future developed network protocol such as HTTP (HyperTextTransferProtocol), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an adhoc peer-to-peer network), as well as any currently known or future developed network.

[0084] The computer-readable medium may be included in the electronic device, or may exist independently without being assembled into the electronic device. The computer-readable medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device: responds to a training request signal sent by a warehouse terminal, queries the inventory data index uploaded by other store terminals related to the training request signal; feeds back the queried inventory data index to the warehouse terminal that sent the training request signal; responds to the warehouse terminal's selection operation signal for the inventory data index, sends an assistance training signal and a central model to other store terminals that upload these inventory data indexes according to the inventory data index selected by the selection operation signal; receives training result data obtained from other store terminals through their own inventory data training of the central model; updates the central model according to the training result data and distributes the updated central model to the warehouse terminal that sent the training request signal.

[0085] Computer program code for performing the operations of some embodiments of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0086] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present application. In this regard, each box in the flowchart or block diagram may represent a module, a program segment, or a portion of a code, which contains one or more executable instructions for implementing a specified logical function.

[0087] 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.

[0088] For example, two boxes shown in succession may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of boxes in the block diagram and / or flow chart, can be implemented by a dedicated hardware-based system that performs the specified function or operation, or can be implemented by a combination of dedicated hardware and computer instructions.

[0089] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0090] The above description is only some preferred embodiments of the present application and an explanation of the technical principles used. Those skilled in the art should understand that the scope of the invention involved in the embodiments of the present application is not limited to the technical solutions formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above invention concept. For example, the above features are replaced with (but not limited to) technical features with similar functions disclosed in the embodiments of the present application to form a technical solution.

Claims

1. A method for managing inventory data, comprising: In response to a training request signal sent by a warehouse terminal, query the inventory data index uploaded by other warehouse terminals related to the training request signal, the inventory data index including: warehouse ID, product SKU, data time, data ID; Feeding back the retrieved inventory data index to the warehouse terminal that issued the training request signal; In response to a selection operation signal of the warehouse terminal for the inventory data index, sending an assisting training signal and a central model to other warehouse terminals that upload the inventory data indexes according to the inventory data index selected by the selection operation signal; Receiving training result data obtained by training the central model with the inventory data of other warehouse terminals; updating the central model according to the training result data and distributing the updated central model to the warehouse terminal that sent the training request signal; The step of responding to a training request signal sent by a warehouse terminal and querying the inventory data index uploaded by other warehouse terminals related to the training request signal includes: Parsing the training content data in the training request signal; selecting one of the plurality of central models according to the training content data; Querying data features of input data and output data required for training the central model according to the type of the central model; Generate a query range of the inventory data index according to one or more of the data characteristics; The data characteristics refer to the type and format of input data and output data; the inventory data index also includes: data type and data format; The step of responding to the warehouse terminal's selection operation signal for the inventory data index and sending an assisting training signal and a central model to other warehouse terminals that upload the inventory data indexes according to the inventory data indexes selected by the selection operation signal comprises: parsing the selected inventory data index in the selection operation signal; Selecting the warehouse terminal that sends the assistance training signal according to the inventory data index; Wherein, in response to the selection operation signal of the warehouse terminal for the inventory data index, sending the assistance training signal and the central model to other warehouse terminals that upload the inventory data indexes according to the inventory data index selected by the selection operation signal, comprises: The method includes: sending the corresponding inventory data index selected by the selection operation signal to the warehouse terminal that is selected to send the auxiliary training signal; in response to the selection operation signal of the warehouse terminal for the inventory data index, sending the auxiliary training signal and the central model to other warehouse terminals that upload the inventory data indexes according to the inventory data index selected by the selection operation signal, including: Among multiple historical versions of the central model selected according to the training content data, the one with the latest update time is selected and sent to the selected warehouse terminal; wherein the training result data includes model parameters, model structure and parameter gradients of the central model.

2. An inventory data management device, comprising: A query module, configured to query, in response to a training request signal sent by a warehouse terminal, an inventory data index uploaded by other warehouse terminals related to the training request signal, wherein the inventory data index includes: warehouse ID, commodity SKU, data time, and data ID; A feedback module, used for feeding back the queried inventory data index to the warehouse terminal that sends the training request signal; a sending module, configured to respond to a selection operation signal of the warehouse terminal for the inventory data index, and send an assisting training signal and a central model to other warehouse terminals that upload the inventory data indexes according to the inventory data indexes selected by the selection operation signal; A receiving module, used for receiving training result data obtained by training the central model with its own inventory data from other warehouse terminals; A distribution module, configured to update the central model according to the training result data and distribute the updated central model to the warehouse terminal that sends the training request signal; in response to the training request signal sent by a warehouse terminal, query the inventory data index uploaded by other warehouse terminals related to the training request signal, including: Parsing the training content data in the training request signal; selecting one of the plurality of central models according to the training content data; Querying data features of input data and output data required for training the central model according to the type of the central model; Generate a query range of the inventory data index according to one or more of the data characteristics; The data characteristics refer to the type and format of input data and output data; the inventory data index also includes: data type and data format; The step of responding to the warehouse terminal's selection operation signal for the inventory data index and sending an assisting training signal and a central model to other warehouse terminals that upload the inventory data indexes according to the inventory data indexes selected by the selection operation signal comprises: parsing the selected inventory data index in the selection operation signal; Selecting the warehouse terminal that sends the assistance training signal according to the inventory data index; Wherein, in response to the selection operation signal of the warehouse terminal for the inventory data index, sending the assistance training signal and the central model to other warehouse terminals that upload the inventory data indexes according to the inventory data index selected by the selection operation signal, comprises: The method includes: sending the corresponding inventory data index selected by the selection operation signal to the warehouse terminal that is selected to send the auxiliary training signal; in response to the selection operation signal of the warehouse terminal for the inventory data index, sending the auxiliary training signal and the central model to other warehouse terminals that upload the inventory data indexes according to the inventory data index selected by the selection operation signal, including: Among multiple historical versions of the central model selected according to the training content data, the one with the latest update time is selected and sent to the selected warehouse terminal; wherein the training result data includes model parameters, model structure and parameter gradients of the central model.

3. An electronic device, comprising: one or more processors; a storage device having one or more programs stored thereon; When the one or more programs are executed by the one or more processors, the processors implement the method as claimed in claim 1.

4. A computer readable medium having a computer program stored thereon, wherein: When the computer program is executed by a processor, the method according to claim 1 is implemented.