Method of identifying sales volume information of item at future, electronic device and recording medium

Abstract

A method for determining sales volume information of a product at a future point in time, performed by an electronic device according to various embodiments of the present disclosure, may include: a step of obtaining sales volume information according to a time interval of a first product among a plurality of products and category information of said first product; a step of identifying whether said first product is a period product; a step of identifying at least one second product included in the same category as said first product in response to identifying said first product as a period product; a step of obtaining sales volume information according to a time interval of said at least one second product; and a step of determining sales volume information of said first product at a future point in time based on the sales volume information according to a time interval of said first product, category information and the sales volume information according to a time interval of said at least one second product.

Description

Technology Field

[0001] The present disclosure relates to a method for verifying sales volume information at a future point in time, an electronic device, and a recording medium. Background Technology

[0002] In the context of e-commerce services, accurately predicting product sales volume is crucial when operating an online store. If sales are overestimated, excess inventory may be discarded; conversely, if sales are underestimated, insufficient stock may lead to significant delays in product delivery.

[0003] Traditionally, future product sales trends have been predicted simply based on past sales patterns, but this method is inaccurate. Therefore, an accurate sales forecasting method is required.

[0004] The aforementioned background technology is technical information that the inventor possessed for the derivation of the present invention or acquired during the process of deriving the present invention, and it cannot be considered as prior art disclosed to the general public prior to the filing of the present invention. The problem to be solved

[0005] According to various embodiments of the present disclosure, the technical problem is to identify seasonal items among various products and to predict the sales volume of seasonal items at a future point in time.

[0006] According to various embodiments of the present disclosure, the technical problem is to predict the sales volume of a period product at a future point in time by synthesizing sales volume information according to time intervals of the period product, category information of the period product, and sales volume information according to time intervals of products similar to the period product.

[0007] According to various embodiments of the present disclosure, the technical problem to be solved is to predict sales volume information of period products at a future point in time using a trained deep learning model.

[0008] According to various embodiments of the present disclosure, the technical problem is to adjust the target inventory of a product based on predicted product sales volume information. means of solving the problem

[0009] A method for determining sales volume information of a product at a future point in time, performed by an electronic device according to various embodiments of the present disclosure, may include: a step of obtaining sales volume information according to a time interval of a first product among a plurality of products and category information of said first product; a step of identifying whether said first product is a period product; a step of identifying at least one second product included in the same category as said first product in response to identifying said first product as a period product; a step of obtaining sales volume information according to a time interval of said at least one second product; and a step of determining sales volume information of said first product at a future point in time based on the sales volume information according to a time interval of said first product, category information and the sales volume information according to a time interval of said at least one second product.

[0010] A step of identifying whether the first product is a period product according to one embodiment may include: a step of obtaining sales volume information according to a time interval by year of the first product; a step of identifying a period in which the sales volume by year is higher than a threshold value based on the sales volume information according to a time interval by year of the first product; and a step of identifying whether the first product is a period product based on the period in which the sales volume is higher than the threshold value.

[0011] According to one embodiment, the threshold value may be determined based on an average sales volume calculated based on sales volume information according to the yearly time interval and a preset threshold ratio.

[0012] The step of identifying whether the first product is the period product according to one embodiment may include: a step of confirming an overlapping period of periods in which the sales volume over the past three years is higher than a threshold value; a step of calculating the ratio of the overlapping period to the periods in which the sales volume over the past three years is higher than a threshold value; and a step of determining that the first product is the period product if the calculated ratio is greater than or equal to a preset threshold ratio.

[0013] The step of confirming sales volume information of the first product at a future point in time according to one embodiment may include: inputting sales volume information according to a time interval of at least one second product, sales volume information according to a time interval of the first product, category information, and information regarding the future point in time into a learned deep learning model; and obtaining sales volume information of the first product at the future point in time output from the deep learning model.

[0014] The deep learning model according to one embodiment may be a deep learning model constructed by using a deep learning algorithm to model the correlation between the training input data and the training output data, wherein the data set includes sales volume information according to a time interval of the first product, category information, and sales volume information according to a time interval of at least one second product, with sales volume information of the first product at a plurality of specific points in time labeled thereon, is used as training input data, and the data set including sales volume information of the first product at a plurality of specific points in time is used as training output data.

[0015] According to one embodiment, sales volume information according to the time interval of the first product, which is labeled with sales volume information of the first product at a plurality of specific points in time, may include sales volume information prior to the plurality of specific points in time and sales volume information after the plurality of specific points in time.

[0016] The category information of the first product according to one embodiment may be information in the form of a tree structure having at least 5 layers.

[0017] The step of identifying the at least one second product according to one embodiment may include the step of identifying the product having the same category information in the lowest layer among the category information of the first product having a tree structure as the at least one second product.

[0018] According to one embodiment, the method for checking the sales volume information of the product at the future point in time may further include the step of transmitting the sales volume information of the first product at the future point in time to an external device.

[0019] According to one embodiment, a method for verifying sales volume information of a product at a future point in time may further include: a step of adjusting the target inventory number of the first product at a current point in time based on the sales volume information of the first product at the future point in time; and a step of transmitting the adjusted target inventory number of the first product to an external device.

[0020] According to one embodiment, a method for checking sales volume information of a product at a future point in time may include: a step of checking the actual inventory number of the first product in a warehouse storing the first product from the external device when the future point in time arrives; a step of transmitting a request to the external device to replenish the inventory of the first product in the warehouse to the target inventory number of the first product when the actual inventory number of the first product is less than or equal to the target inventory number of the first product; and a step of deciding not to transmit a request for the first product to the external device when the actual inventory number of the first product exceeds the target inventory number of the first product.

[0021] An electronic device according to one embodiment of the present disclosure comprises: a communication circuit; one or more processors; and one or more memories for storing one or more instructions. The one or more processors may be configured to obtain sales volume information according to a time interval of a first product among a plurality of products and category information of the first product by executing the one or more instructions, identify whether the first product is a period product, identify at least one second product included in the same category as the first product in response to identifying the first product as a period product, obtain sales volume information according to a time interval of the at least one second product, and determine sales volume information of the first product at a future point in time based on the sales volume information according to a time interval of the first product, category information, and sales volume information according to a time interval of the at least one second product.

[0022] According to one embodiment of the present disclosure, in a computer-readable non-transient recording medium storing a program for executing on a computer a method for verifying sales volume information of a product at a future point in time performed by an electronic device, the method for verifying sales volume information of a product at a future point in time may include: a step of obtaining sales volume information according to a time interval of a first product among a plurality of products and category information of the first product; a step of identifying whether the first product is a period product; a step of identifying at least one second product included in the same category as the first product in response to identifying the first product as a period product; a step of obtaining sales volume information according to a time interval of the at least one second product; and a step of verifying sales volume information of the first product at a future point in time based on the sales volume information according to a time interval of the first product, category information and the sales volume information according to a time interval of the at least one second product. Effects of the invention

[0023] According to various embodiments of the present disclosure, a period product among various products can be identified, and the sales volume of the period product at a future point in time can be predicted.

[0024] According to various embodiments of the present disclosure, by combining sales volume information according to time intervals of a period product, category information of a period product, and sales volume information according to time intervals of products similar to the period product, future sales volume of a period product can be predicted.

[0025] According to various embodiments of the present disclosure, sales volume information of period products at a future point in time can be predicted using a trained deep learning model.

[0026] According to various embodiments of the present disclosure, the target inventory of a product can be adjusted based on predicted sales volume information of the product. Brief explanation of the drawing

[0027] FIG. 1 is a diagram showing a system for performing a method to check sales volume information of a product according to one embodiment of the present disclosure. FIG. 2 is a block diagram of an electronic device according to one embodiment of the present disclosure. FIG. 3 is a flowchart of the operation of an electronic device according to one embodiment of the present disclosure. FIG. 4 is a flowchart of the operation of an electronic device according to one embodiment of the present disclosure. FIG. 5 is a flowchart of the operation of an electronic device according to one embodiment of the present disclosure. FIG. 6 is a flowchart of the operation of an electronic device according to one embodiment of the present disclosure. Specific details for implementing the invention

[0028] The terms used in the embodiments have been selected to be as widely used as possible, taking into account their functions in the present disclosure; however, these may vary depending on the intent of those skilled in the art, case law, the emergence of new technologies, etc. Additionally, in specific cases, terms have been arbitrarily selected by the applicant, and in such cases, their meanings will be described in detail in the relevant explanatory section. Therefore, terms used in the present disclosure should be defined not merely by their names, but based on their meanings and the overall content of the present disclosure.

[0029] When a part of a specification is described as “comprising” a certain component, this means that, unless specifically stated otherwise, it does not exclude other components but may include additional components. Furthermore, terms such as “...part” or “...module” as used in the specification refer to a unit that processes at least one function or operation, and this may be implemented in hardware or software, or as a combination of hardware and software.

[0030] The expression “at least one of a, b, and c” described throughout the specification may include ‘a alone’, ‘b alone’, ‘c alone’, ‘a and b’, ‘a and c’, ‘b and c’, or ‘a, b, and c all’.

[0031] The "terminal" mentioned below may be implemented as a computer or portable terminal capable of connecting to a server or other terminal via a network. Here, the computer includes, for example, a notebook, desktop, or laptop equipped with a web browser, and the portable terminal may include, for example, a wireless communication device that ensures portability and mobility, and may include all types of handheld-based wireless communication devices such as communication-based terminals like IMT (International Mobile Telecommunication), CDMA (Code Division Multiple Access), W-CDMA (W-Code Division Multiple Access), and LTE (Long Term Evolution), smartphones, tablet PCs, etc.

[0032] Embodiments of the present disclosure are described below with reference to the attached drawings so that those skilled in the art can easily implement them. However, the present disclosure may be embodied in various different forms and is not limited to the embodiments described herein.

[0033] Hereinafter, embodiments of the present invention will be described in detail with reference to the attached drawings.

[0034] In describing the embodiments, technical details that are well known in the technical field to which the present invention belongs and are not directly related to the present invention are omitted. This is intended to convey the essence of the present invention more clearly without obscuring it by omitting unnecessary explanations.

[0035] For the same reason, some components in the attached drawings have been exaggerated, omitted, or schematically depicted. Additionally, the size of each component does not entirely reflect its actual dimensions. Identical or corresponding components in each drawing have been assigned the same reference numbers.

[0036] The advantages and features of the present invention and the methods for achieving them will become clear by referring to the embodiments described below in detail together with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below but can be implemented in various different forms. These embodiments are provided merely to ensure that the disclosure of the present invention is complete and to fully inform those skilled in the art of the scope of the invention, and the present invention is defined only by the scope of the claims. Throughout the specification, the same reference numerals refer to the same components.

[0037] At this time, it will be understood that each block of the process flow diagrams and combinations of the flow diagrams can be executed by computer program instructions. Since these computer program instructions can be loaded into the processor of a general-purpose computer, a special-purpose computer, or other programmable data processing equipment, the instructions executed through the processor of the computer or other programmable data processing equipment create means to perform the functions described in the flow diagram block(s). Since these computer program instructions can also be stored in computer-available or computer-readable memory that can be directed toward the computer or other programmable data processing equipment to implement the function in a specific way, the instructions stored in computer-available or computer-readable memory can also produce a manufactured item containing the means of instruction to perform the function described in the flow diagram block(s). Since computer program instructions can be loaded onto a computer or other programmable data processing equipment, instructions that perform a series of operation steps on the computer or other programmable data processing equipment to create a process executed by the computer can also provide steps for executing the functions described in the flowchart block(s).

[0038] Additionally, each block may represent a module, segment, or part of code containing one or more executable instructions for executing a specified logical function(s). It should also be noted that in some alternative execution examples, the functions mentioned in the blocks may occur out of order. For instance, two blocks described in succession may actually be executed substantially simultaneously, or the blocks may be executed in reverse order according to their corresponding functions.

[0039] FIG. 1 is a drawing showing a system (10) that performs a method of checking sales volume information of a product at a future point in time according to one embodiment of the present disclosure.

[0040] Referring to FIG. 1, a system (10) according to one embodiment may include an electronic device (100) and an external device (200). A system (10) according to one embodiment may be a system (10) for predicting sales volume information of a product at a future point in time. The external device (200) may be connected to the electronic device (100) via a network.

[0041] An electronic device (100) according to one embodiment can store and manage sales volume information according to time intervals of a plurality of products. Sales volume information according to time intervals may be a graph showing the trend of sales volume by day. The electronic device (100) can store sales volume information according to time intervals for each of a plurality of products and for a plurality of years. For example, sales volume information according to time intervals of a product may be a graph showing sales volume by day with the x-axis as the date and the y-axis as the sales volume.

[0042] An electronic device (100) according to one embodiment can store and manage category information for each of a plurality of products. The category information may be information having a tree structure, for example, and may have at least five layers (hierarchies). For example, a specific product may have category information such as '1st layer: food' - '2nd layer: vegetables' - '3rd layer: mushrooms' - '4th layer: other mushrooms' - '5th layer: pine mushrooms'.

[0043] An electronic device (100) according to one embodiment can identify period products among various products. A period product may refer to a product whose sales volume during a similar period (or similar season) is higher than the average sales volume when considering a sales volume graph according to an annual time period. For example, period products may include seasonal products, Christmas products, Children's Day products, or camping season products. For example, if, as a result of checking the annual sales volume information of a specific product, the sales volume from one week before Christmas to Christmas Day is above a predetermined threshold value compared to the annual average sales volume, the electronic device (100) may determine that the specific product is a period product. A specific method for identifying period products among a plurality of products will be described later.

[0044] An electronic device (100) according to one embodiment can predict sales volume information at a future point in time for a period product. The electronic device (100) can predict sales volume information at a future point in time for a period product by using a learned deep learning model (or artificial intelligence model, machine learning model). A specific method for predicting sales volume information using a deep learning model will be described later.

[0045] An external device (200) according to one embodiment may be a device for managing the inventory of goods. For example, the external device (200) may be a device for operating a warehouse management system. The external device (200) may manage the actual inventory count and target inventory count of each product stored in the warehouse. The external device (200) may be connected to an electronic device (100) for communication and may transmit and receive various information.

[0046] FIG. 2 is a block diagram of an electronic device (100) according to one embodiment of the present disclosure.

[0047] An electronic device (100) according to one embodiment may include a processor (110), memory (120), and a communication circuit (130). At least one of the components included in the electronic device (100) may be omitted, or another component may be added to the electronic device (100). Additionally, some components may be implemented as an integrated unit or as a single or multiple unit. At least some components within the electronic device (100) may be implemented as an integrated unit or as a single or multiple unit. At least some components within the electronic device (100) may be connected to each other via a bus, GPIO (general purpose input / output), SPI (serial peripheral interface), or MIPI (mobile industry processor interface), etc., to exchange data and / or signals.

[0048] A processor (110) of an electronic device (100) according to one embodiment is configured to perform operations or data processing regarding the control and / or communication of each component of the electronic device (100) and can be operatively connected to the components of the electronic device (100). The processor (110) can load commands or data received from other components of the electronic device (100) into memory (120), process commands or data stored in memory (120), and store result data. Unless there are special circumstances, in this disclosure, the processor (110) may mean a set of one or more processors (110).

[0049] A memory (120) of an electronic device (100) according to one embodiment may store various data used by at least one component (e.g., processor (110)). The memory (120) may store instructions for the operation of the processor (110) described above. A program may be stored in the memory (120) as software and may include, for example, an operating system, middleware, or an application. Unless otherwise specified, in this disclosure, memory (120) may mean a set of one or more memories (120).

[0050] A communication circuit (130) of an electronic device (100) according to one embodiment may establish a wired or wireless communication channel with an external device (e.g., external device (200)) and transmit and receive various data with the external device. The communication circuit (130) of the electronic device (100) may include at least one port for connecting to the external device via a wired cable in order to communicate with the external device via a wired connection. The communication circuit (130) of the electronic device (100) may include a cellular communication module and be configured to be connected to a cellular network (e.g., 3G, LTE, 5G, Wibro, or Wimax). According to one embodiment, the communication circuit (130) of the electronic device (100) may include a short-range communication module and transmit and receive data with the external device using short-range communication (e.g., Wi-Fi, Bluetooth, Bluetooth Low Energy (BLE), UWB), but is not limited thereto.

[0051] FIG. 3 is an operation flowchart of an electronic device (100) according to one embodiment of the present disclosure.

[0052] Referring to operation flowchart 300, the processor (110) of the electronic device (100) according to one embodiment can, in step 310, obtain sales volume information according to the time interval of the first product among a plurality of products and category information of the first product. Sales volume information according to the time interval of each of the plurality of products and category information of each of the plurality of products may be stored in the memory (120) of the entire device. The processor (110) can obtain a graph showing the annual daily sales volume trend of the first product. For example, the processor (110) can obtain a graph showing the daily sales volume trend of the recent few years. The processor (110) can obtain sales volume information according to the yearly time interval of the first product. For example, the processor (110) can obtain sales volume information according to the time interval corresponding to 2023, sales volume information according to the time interval corresponding to 2022, and sales volume information according to the time interval corresponding to 2021 for the first product.

[0053] Category information may be information having a tree structure, for example, and may have at least five layers (hierarchies). For example, the first product may have category information such as 'Layer 1: Fashion' - 'Layer 2: Men' - 'Layer 3: Clothing' - 'Layer 4: Bottoms' - 'Layer 5: Hiking Pants'.

[0054] A processor (110) according to one embodiment can identify whether the first product is a period product in step 320. The processor (110) can identify whether the first product is a period product based on sales volume information according to the yearly time interval of the first product. A method for identifying whether the first product is a period product will be described in detail in FIG. 4.

[0055] A processor (110) according to one embodiment can identify at least one second product included in the same category as the first product in response to identifying the first product as a period product in step 330. The processor (110) can identify at least one second product included in the same category as the first product based on category information corresponding to the fifth layer among category information having a tree structure. For example, if the category information of the first product is 'Layer 1: Fashion' - 'Layer 2: Men' - 'Layer 3: Clothing' - 'Layer 4: Bottoms' - 'Layer 5: Hiking Pants', the processor (110) can identify at least one second product based on 'Hiking Pants' corresponding to the fifth layer. For example, at least one second product may mean a product where the information corresponding to the fifth layer among the category information is 'Hiking Pants'.

[0056] A processor (110) according to one embodiment can obtain sales volume information according to the time interval of at least one second product in step 340. The processor (110) can obtain sales volume information according to the time interval of each year of at least one second product.

[0057] A processor (110) according to one embodiment can check sales volume information of a first product at a future point in time at step 350. The processor (110) can predict sales volume information of a first product at a future point in time based on sales volume information according to the time interval of the first product, category information of the first product, and sales volume information according to the time interval of at least one second product. The processor (110) can check sales volume information of a first product at a future point in time by inputting sales volume information according to the time interval of the first product, category information of the first product, and sales volume information according to the time interval of at least one second product into a trained deep learning model. A method for using a deep learning model will be described later.

[0058] FIG. 4 is an operation flowchart of an electronic device (100) according to one embodiment of the present disclosure. Specifically, FIG. 4 is an operation flowchart relating to a method for identifying whether a first product is a period product.

[0059] Referring to operation flowchart 400, the processor (110) of the electronic device (100) according to one embodiment can obtain sales volume information according to the yearly time interval of the first product in step 410. The processor (110) can obtain sales volume information according to the time interval of the first product for the past three years. For example, the processor (110) can obtain a graph showing the daily sales volume trend of the first product for each of 2022, 2023, and 2024.

[0060] A processor (110) according to one embodiment can, in step 420, identify a period in which the sales volume is higher than a threshold value for each year. According to one embodiment, the threshold value may be a value that can be determined by default. According to one embodiment, the threshold value may be determined based on an average sales volume calculated based on sales volume information according to the time interval for each year and a preset threshold ratio. For example, if the average daily sales volume of the first product during 2022 is 1,000 units and the preset threshold ratio is 10%, the processor (110) may determine the threshold value to be 1,100 units.

[0061] A processor (110) according to one embodiment can identify, in step 430, overlapping periods of periods with relatively high sales volume over the past three years.

[0062] A processor (110) according to one embodiment can calculate, in step 440, the ratio of the overlapping periods for periods with relatively high sales volumes over the past three years.

[0063] A processor (110) according to one embodiment can compare the calculated ratio with a preset threshold ratio in step 450.

[0064] If the above-determined ratio is greater than or equal to the threshold ratio, branch to step 460 (step 450 -> yes), and the processor (110) according to one embodiment can determine that the first product is a period product.

[0065] If the above-mentioned ratio is less than the threshold ratio, branch to step 470 (step 450 -> no), and the processor (110) according to one embodiment may determine that the first product is not a period product.

[0066] The method for identifying period products disclosed in FIG. 4 is exemplary, and a wider variety of identification methods may be used. For example, based on sales volume information according to the yearly time intervals of the first product, if there is a graph interval showing a similar pattern each year, the first product may be determined to be a period product.

[0067] FIG. 5 is a flowchart of the operation of an electronic device (100) according to one embodiment of the present disclosure. Specifically, FIG. 5 relates to a specific method for verifying sales volume information of a first product at a future point in time using a deep learning model.

[0068] Referring to the operation flowchart 500, the processor (110) of the electronic device (100) according to one embodiment may, in step 510, input sales volume information according to the time interval of at least one second product, sales volume information according to the time interval of the first product, category information of the first product, and information regarding a future point in time to a learned deep learning model. Along with the information described above, the processor (110) may also input information regarding a future point in time to check the sales volume.

[0069] At least one second product may mean a product included in the same category as the first product. The category information of the first product may be information in the form of a tree structure having at least five layers. The processor (110) may identify at least one second product as a product in which the category information of the lowest layer of the category information of the first product having a tree structure is the same.

[0070] The deep learning model may be a deep learning model constructed by using a deep learning algorithm to model the correlation between the training input data and the training output data, wherein the data set includes sales volume information according to time intervals of the first product, category information of the first product, and sales volume information according to time intervals of at least one second product, with sales volume information of the first product at multiple specific points in time labeled thereon, is used as training input data, and the data set including sales volume information of the first product at multiple specific points in time is used as training output data. That is, the deep learning model may be an artificial intelligence model trained to output sales volume information of the first product at a desired future point in time when input is the sales volume information of the first product, category information of the first product, and sales volume information of at least one second product that is a similar product included in the same category as the first product. The sales volume information according to time intervals of the first product, with sales volume information of the first product at multiple specific points in time labeled thereon as described above, may include sales volume information prior to the multiple specific points in time and sales volume information after the multiple specific points in time.

[0071] The sales volume information according to the time interval of the first product may further include not only daily sales volume information for the first product, but also daily price information, daily search count information, and out-of-stock period information (i.e., information regarding the period during which the first product is out of stock). The processor (110) may extract past sales volume information (i.e., past characteristic information) based on a specific point in time and future sales volume information (i.e., future characteristic information) based on said specific point in time from the sales volume information according to the time interval of the first product. Past sales volume information based on a specific point in time may include sales volume information, price information, out-of-stock period information, and search count information for each of the following: one week ago, two weeks ago, three weeks ago, and four weeks ago based on the specific point in time. Future sales volume information based on a specific point in time may include sales volume information, price information, out-of-stock period information, and search count information for each of the following: one week later, two weeks later, three weeks later, four weeks later, and five weeks later based on the specific point in time.

[0072] The sales volume information according to the time interval of at least one second product may be statistical information regarding at least one second product included in the same category as the first product. The sales volume information according to the time interval of at least one second product may further include daily sales volume information for at least one second product, as well as daily price information, information indicating whether it is out of stock on a daily basis, and daily search count information. The processor (110) may extract period-related features from the sales volume information according to the time interval of at least one second product. The period-related feature information may include information indicating periods in which sales volume increases and periods in which sales volume decreases. The period-related feature information may include information regarding periods in which sales volume is higher than a threshold value by year. In addition, the period-related features may extract various features from a graph showing the daily sales volume trend of at least one second product.

[0073] In the case of the first product, which is a period product, it exhibits similar sales volume trends during periods of high sales each year; therefore, by training a deep learning model with sales volume information according to time intervals of the first product, it is possible to predict sales volume information at a desired future point in time. Furthermore, since the model is trained not only on the sales volume information of the first product but also on the category information of the first product and the sales volume information according to time intervals of at least one second product included in the same category as the first product, more accurate sales volume information can be predicted. Since at least one second product is also a similar product included in the same category as the first product, it is highly likely to exhibit similar sales volume trends, thereby enabling more accurate learning.

[0074] A processor (110) according to one embodiment can obtain sales volume information of a first product at a future point in time output from a deep learning model in step 520. That is, the processor (110) can obtain sales volume information at a desired future point in time by using a deep learning model learned for a period product. The processor (110) can transmit the sales volume information of the first product at a future point in time to an external device (200).

[0075] FIG. 6 is a flowchart of the operation of an electronic device (100) according to one embodiment of the present disclosure. Specifically, FIG. 6 is a diagram showing a method of managing the inventory of a first product based on sales volume information of the first product at a future point in time.

[0076] Referring to operation flowchart 600, the processor (110) of the electronic device (100) according to one embodiment can, in step 610, adjust the target inventory number of the first product at the current time based on sales volume information of the first product at a future time. For example, if the existing target inventory number of the first product at the current time is 1,000 and the sales volume information of the first product one week later is predicted to be 1,500, the processor (110) can adjust the target inventory number of the first product at the current time from 1,000 to 1,500.

[0077] A processor (110) according to one embodiment can transmit the target inventory number of the adjusted first product to an external device (200) in step 620.

[0078] A processor (110) according to one embodiment can, at step 630, check the actual number of stock of the first product in a warehouse storing the first product from an external device (200) when a future point in time arrives. In the example described above, when one week has passed, the processor (110) can request and receive information regarding the actual number of stock of the first product from the external device (200).

[0079] A processor (110) according to one embodiment can compare the actual inventory of the first product with the target inventory of the first product at step 640. The processor (110) can determine whether the actual inventory of the first product exceeds the target inventory.

[0080] If the actual inventory of the first product exceeds the target inventory, branch to step 660 (step 650 -> yes), the processor (110) may decide not to send a request for the first product to the external device (200). That is, if the actual inventory exceeds the target inventory, it may be determined that there is sufficient inventory of the first product stored in the warehouse and that there is no need to change the inventory of the first product. For example, if the adjusted target inventory is 1500 and the actual inventory is 1600, the processor (110) may decide not to send a request for the first product to the external device (200).

[0081] If the actual inventory of the first product is less than or equal to the target inventory, branch to step 670 (step 650 -> No), and the processor (110) may send a request to an external device (200) to replenish the inventory of the first product in the warehouse to the target inventory of the first product. That is, if the actual inventory is less than or equal to the target inventory, it may be determined that the inventory of the first product stored in the warehouse is insufficient and that it is necessary to replenish the inventory of the first product. For example, if the adjusted target inventory is 1500 and the actual inventory is 1200, the processor (110) may send a request to replenish the inventory of the first product to 1500.

[0082] The aforementioned embodiments can be implemented as artificial intelligence (AI) through the processor and memory of an electronic device. The processor may consist of one or more processors, and the one or more processors may be general-purpose processors such as CPUs, APs, and DSPs (digital signal processors), graphics-dedicated processors such as GPUs and VPUs (vision processing units), or AI-dedicated processors such as NPUs. The one or more processors may be controlled to process input data according to predefined operation rules or AI models stored in memory. Alternatively, if the one or more processors are AI-dedicated processors, the AI-dedicated processors may be designed with a hardware structure specialized for processing a specific AI model.

[0083] The predefined rules of operation or artificial intelligence models are characterized by being created through learning. Here, being created through learning means that a predefined rules of operation or artificial intelligence models configured to perform a desired characteristic (or objective) are created by a basic artificial intelligence model being trained using a number of learning data by a learning algorithm. Such learning may be performed on the electronic device itself where the artificial intelligence according to the present disclosure is executed, or it may be performed through a separate server and / or system. Examples of learning algorithms include supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning, but are not limited to the examples described above.

[0084] An artificial intelligence model may be composed of multiple neural network layers. Each of the multiple neural network layers has multiple weight values ​​and can perform neural network operations through operations between the results of previous layers and the multiple weights. The multiple weights possessed by the multiple neural network layers can be optimized based on the learning results of the artificial intelligence model. For example, the multiple weights can be updated so that the loss value or cost value obtained from the artificial intelligence model during the learning process is reduced or minimized. The artificial neural network may include, but is not limited to, deep neural networks (DNN), convolutional neural networks (CNN), recurrent neural networks (RNN), restricted Boltzmann machines (RBM), deep belief networks (DBN), bidirectional recurrent deep neural networks (BRDNN), or deep Q-networks.

[0085] Meanwhile, the present specification and drawings disclose preferred embodiments of the present invention. Although specific terms have been used, they are used merely in a general sense to facilitate the explanation of the technical content of the present invention and to aid in understanding the invention, and are not intended to limit the scope of the present invention. It is obvious to those skilled in the art that, in addition to the embodiments disclosed herein, other variations based on the technical concept of the present invention are possible.

[0086] A device or terminal according to the embodiments described above may include a processor, memory for storing and executing program data, permanent storage such as a disk drive, a communication port for communicating with an external device, and user interface devices such as a touch panel, a key, a button, etc. Methods implemented as software modules or algorithms may be stored on a computer-readable recording medium as computer-readable code or program instructions executable on the processor. Here, computer-readable recording media include magnetic storage media (e.g., ROM (read-only memory), RAM (random-access memory), floppy disks, hard disks, etc.) and optical reading media (e.g., CD-ROM, DVD (Digital Versatile Disc)). Computer-readable recording media may be distributed across networked computer systems, allowing computer-readable code to be stored and executed in a distributed manner. The medium may be readable by a computer, stored in memory, and executed by a processor.

[0087] The present embodiment may be represented by functional block configurations and various processing steps. These functional blocks may be implemented by various numbers of hardware and / or software configurations that execute specific functions. For example, the embodiment may employ integrated circuit configurations such as memory, processing, logic, look-up tables, etc., capable of executing various functions by the control of one or more microprocessors or other control devices. Similar to how components may be implemented as software programming or software elements, the present embodiment may be implemented in programming or scripting languages ​​such as C, C++, Java, assembler, Python, etc., including various algorithms implemented as combinations of data structures, processes, routines, or other programming configurations. Functional aspects may be implemented as algorithms executed on one or more processors. Additionally, the present embodiment may employ prior art for electronic configuration, signal processing, and / or data processing. Terms such as "mechanism," "element," "means," and "configuration" may be used broadly and are not limited to mechanical and physical configurations. The above terms may include the meaning of a series of software processes (routines) in conjunction with processors, etc.

[0088] The aforementioned embodiments are merely examples, and other embodiments may be implemented within the scope of the claims set forth below.

Claims

Claim 1 A method for verifying sales volume information of a product at a future point in time performed by an electronic device comprises: a step of obtaining sales volume information according to a time interval of a first product among a plurality of products and category information of said first product; a step of identifying whether said first product is a period product; a step of identifying at least one second product included in the same category as said first product in response to identifying said first product as a period product; a step of obtaining sales volume information according to a time interval of said at least one second product; and a step of verifying sales volume information of said first product at a future point in time based on the sales volume information according to a time interval of said first product, said category information and said sales volume information according to a time interval of said at least one second product, wherein the step of identifying whether said first product is a period product comprises: a step of obtaining sales volume information according to a time interval by year of said first product; and a step of verifying a period in which the sales volume by year is higher than a threshold value based on the sales volume information according to a time interval by year of said first product. A method for verifying sales volume information of a product at a future point in time, comprising the step of identifying whether the first product is a period product based on the period during which the sales volume is higher than a threshold value, wherein the step of identifying whether the first product is a period product comprises: the step of identifying an overlapping period of periods during which the sales volume over the past three years is higher than a threshold value; the step of calculating the ratio of the overlapping period to the periods during which the sales volume over the past three years is higher than a threshold value; and the step of determining that the first product is a period product if the calculated ratio is greater than or equal to a preset threshold ratio. Claim 2 delete Claim 3 A method for verifying sales volume information of a product at a future point in time, wherein the threshold value is determined based on an average sales volume calculated based on sales volume information according to the yearly time interval and a preset threshold ratio. Claim 4 delete Claim 5 A method for verifying sales volume information of a product at a future point in time, wherein the step of verifying sales volume information of the first product at a future point in time comprises: inputting sales volume information according to a time interval of at least one second product, sales volume information according to a time interval of the first product, category information of the first product, and information regarding the future point in time into a learned deep learning model; and obtaining sales volume information of the first product at a future point in time output from the deep learning model. Claim 6 A method for verifying sales volume information of a product at a future point in time, wherein the deep learning model is a deep learning model constructed by using a deep learning algorithm to model the correlation between the training input data and the training output data, wherein the deep learning model is a data set including sales volume information according to time intervals of the first product, category information of the first product, and sales volume information according to time intervals of at least one second product, with sales volume information of the first product at a plurality of specific points in time labeled therewith, as training input data, and a data set including sales volume information of the first product at a plurality of specific points in time as training output data. Claim 7 A method for verifying sales volume information of a product at a future point in time, wherein, in claim 6, sales volume information according to the time interval of the first product, labeled with sales volume information of the first product at the plurality of specific points in time, includes sales volume information prior to the plurality of specific points in time and sales volume information after the plurality of specific points in time. Claim 8 A method for verifying future sales volume information of a product, wherein the category information of the first product is information in the form of a tree structure having at least five layers, in accordance with claim 1. Claim 9 A method for verifying sales volume information of a product at a future point in time, wherein the step of identifying at least one second product includes the step of identifying a product as the at least one second product that has the same category information in the lowest layer of the category information of the first product having a tree structure. Claim 10 A method for verifying sales volume information of a product at a future point in time, further comprising the step of transmitting sales volume information of the first product at the future point in time to an external device, in accordance with claim 1. Claim 11 A method for verifying sales volume information of a product at a future point in time, further comprising: a step of adjusting the target inventory number of the first product at a current point in time based on sales volume information of the first product at a future point in time; and a step of transmitting the adjusted target inventory number of the first product to an external device. Claim 12 A method for verifying sales volume information of a product at a future point in time, comprising: a step of verifying the actual number of stock of the first product in a warehouse storing the first product from the external device when the future point in time arrives; a step of transmitting a request to the external device to replenish the stock of the first product in the warehouse to the target stock number of the first product if the actual number of stock of the first product is less than or equal to the target stock number of the first product; and a step of deciding not to transmit a request for the first product to the external device if the actual number of stock of the first product exceeds the target stock number of the first product. Claim 13 In an electronic device, a communication circuit; one or more processors; The apparatus includes one or more memories for storing one or more instructions, and the one or more processors are configured to execute the one or more instructions to obtain sales volume information according to a time interval of a first product among a plurality of products and category information of the first product, identify whether the first product is a period product, and in response to identifying the first product as a period product, identify at least one second product included in the same category as the first product, obtain sales volume information according to a time interval of the at least one second product, and check sales volume information of the first product at a future point in time based on the sales volume information according to a time interval of the first product, category information, and sales volume information according to a time interval of the at least one second product, and the one or more processors are configured to execute the one or more instructions to obtain sales volume information according to a time interval of the first product by year, and based on the sales volume information according to a time interval of the first product by year, check a period in which the sales volume by year is higher than a threshold value, and based on the period in which the sales volume is higher than the threshold value, the first product An electronic device configured to identify whether the product is of the aforementioned period, wherein the one or more processors, by executing the one or more instructions, identify overlapping periods of periods in which the sales volume over the past three years is higher than a threshold value, calculate the ratio of the overlapping periods to the periods in which the sales volume over the past three years is higher than the threshold value, and determine that the first product is of the aforementioned period if the calculated ratio is greater than or equal to a preset threshold ratio. Claim 14 In a computer-readable non-transient recording medium storing a program for executing on a computer a method for verifying sales volume information of a product at a future point in time performed by an electronic device, the method for verifying sales volume information of a product at a future point in time comprises: a step of obtaining sales volume information according to a time interval of a first product among a plurality of products and category information of the first product; a step of identifying whether the first product is a period product; a step of identifying at least one second product included in the same category as the first product in response to identifying the first product as a period product; and a step of obtaining sales volume information according to a time interval of the at least one second product. A non-temporal recording medium comprising: a step of confirming sales volume information of the first product at a future point in time based on sales volume information according to a time interval of the first product, category information, and sales volume information according to a time interval of at least one second product; and a step of identifying whether the first product is a period product, comprising: a step of obtaining sales volume information according to a time interval of the first product by year; a step of confirming a period in which the sales volume by year is higher than a threshold value based on the sales volume information according to a time interval of the first product by year; and a step of identifying whether the first product is a period product based on the period in which the sales volume is higher than the threshold value, wherein the step of identifying whether the first product is a period product comprises: a step of confirming an overlapping period of periods in which the sales volume over the past three years is higher than the threshold value; a step of calculating the ratio of the overlapping period to the periods in which the sales volume over the past three years is higher than the threshold value; and a step of determining that the first product is a period product if the calculated ratio is greater than or equal to a preset threshold ratio.

Images