KR102777191B1 - Method, apparatus, and recording medium of predicting trading volume for product - Google Patents

Abstract

A method, device, and recording medium for predicting a transaction volume for a product that may be the target of an e-commerce service are provided. The method according to one embodiment of the present disclosure may include a step of identifying a target product to be the target of transaction volume prediction among a plurality of products posted on an e-commerce service, wherein the target product includes one or more products; a step of extracting transaction information for the target product, wherein the transaction information includes a stock-out time of the target product and a transaction volume of the target product; and a step of calculating a transaction volume correction value of the target product by correcting the transaction volume of the target product using a reference table defined based on a transaction volume decrease rate according to a stock-out time.

Description

METHOD, APPARATUS, AND RECORDING MEDIUM OF PREDICTING TRADING VOLUME FOR PRODUCT

The present disclosure relates to a technology for predicting transaction volume for a product that can be the target of an e-commerce service.

Due to the development of communication technology, e-commerce services that trade goods online are becoming popular. The range of goods that can be the subject of e-commerce services is expanding to include not only goods but also services. As such, as various types of goods are traded through e-commerce services, the operators of e-commerce services need to establish strategies to effectively sell various types of goods to users.

As an example of the aforementioned strategy, the operator of an e-commerce service needs to predict the demand of users (e.g., customers), that is, the transaction volume of a product, in order to maintain the inventory of the product at an appropriate level. This prediction of the transaction volume of the product can be performed based on the past transaction volume of the product. However, in cases where the past transaction volume of the product cannot fully reflect the demand of the users, such as when the product is out of stock, there is a problem in that the transaction volume cannot be accurately predicted simply based on the past transaction volume.

Japanese Patent Publication No. 2001-282906 International Publication WO2020/031430 Japanese Patent Publication No. 2005-049940

The technical challenge to be solved through this disclosure is to provide a technology capable of predicting future transaction volume for products posted on an e-commerce service.

Another technical challenge to be solved through the present disclosure is to provide a technology capable of preprocessing data used to predict transaction volume for products posted on an e-commerce service.

Another technical challenge to be solved through the present disclosure is to provide a technology that can more accurately predict future transaction volume for a product by compensating transaction volume in a situation where the product is out of stock.

The technical problems of the present disclosure are not limited to the technical problems mentioned above, and other technical problems not mentioned will be clearly understood by a person skilled in the art of the present disclosure from the description of the specification.

According to one embodiment of the present disclosure, a method performed by an electronic device may include: a step of identifying a target product to be a target of transaction volume prediction among a plurality of products posted on an e-commerce service, wherein the target product includes one or more products; a step of extracting transaction information on the target product, wherein the transaction information includes a stock-out time of the target product and a transaction volume of the target product; and a step of calculating a transaction volume correction value of the target product by correcting the transaction volume of the target product using a reference table defined based on a transaction volume decrease rate according to a stock-out time.

In one embodiment, the method may further include a step of performing a future transaction volume prediction for the target product based on the transaction volume correction value of the target product.

In one embodiment, the step of identifying the target product may include the step of identifying a product having an out-of-stock time among the plurality of products as the target product.

In one embodiment, the step of extracting the transaction information for the target product may include the step of extracting the transaction information for the target product by date.

In one embodiment, the step of extracting the transaction information by date may include the step of extracting the transaction information for the target product by date so as to correspond to a minimum period required for predicting transaction volume.

In one embodiment, the method may further include the step of generating the reference table.

In one embodiment, the step of generating the reference table may include the step of generating the reference table by comparing, for a product group including the target product, an average transaction volume when there is no out-of-stock time and an average transaction volume when there is an out-of-stock time.

In one embodiment, the product group may be a set determined based on a grade classified according to the transaction volume of the product or the transaction rate of the product.

In one embodiment, the step of calculating the transaction volume correction value of the target product may include the step of identifying a grade corresponding to the target product, wherein the grade is classified according to the transaction volume of the target product or the transaction rate of the target product, the step of obtaining the reference table corresponding to the grade, and the step of performing correction based on the reference table.

In one embodiment, the step of performing a correction based on the reference table may include the step of identifying a correction value corresponding to the out-of-stock time of the target product among a plurality of correction values included in the reference table, and the step of performing a correction based on the transaction volume of the target product and the reciprocal of the correction value.

In one embodiment, the step of performing a correction based on the reference table may include the step of identifying a correction value corresponding to the out-of-stock time of the target product among a plurality of correction values included in the reference table, and the step of performing a correction based on the average transaction volume of a period without an out-of-stock time for the target product, the transaction volume of the target product, and the correction value.

In one embodiment, the method further includes a step of identifying a third-party product corresponding to the target product and a step of extracting a transaction volume of the third-party product, and the step of calculating a transaction volume correction value of the target product may include a step of calculating the transaction volume correction value of the target product by correcting the transaction volume of the target product based on the transaction volume of the third-party product.

In one embodiment, the step of calculating the transaction volume correction value of the target product based on the transaction volume of the third-party product may include the step of calculating the transaction volume correction value of the target product based on the transaction volume of the third-party product, based on a determination that a condition determined based on the continuity of the out-of-stock time of the target product is satisfied.

According to another embodiment of the present disclosure, a recording medium is a non-transitory computer-readable recording medium having recorded thereon a computer program to be executed by a processor, wherein the computer program may be configured to cause the processor to execute any one of the methods described above.

According to another embodiment of the present disclosure, an electronic device includes a communication interface configured to communicate with a network, a processor configured to execute a computer program including one or more instructions, and a memory configured to load the computer program, wherein when the computer program is executed by the processor, the processor may be configured to execute any one of the methods described above.

According to the present disclosure, it is possible to predict future transaction volume for products posted on an e-commerce service.

According to the present disclosure, data used for predicting transaction volume for products posted on an e-commerce service can be preprocessed.

According to the present disclosure, by correcting the transaction volume in a situation where the product is out of stock, the future transaction volume for the product can be predicted more accurately.

The effects according to the technical idea of the present disclosure are not limited to the effects mentioned above, and other effects not mentioned can be clearly understood by a person skilled in the art of the present disclosure from the description of the specification.

FIG. 1 illustrates an environment in which devices according to one embodiment of the present disclosure can be applied.
FIG. 2 illustrates a computing device capable of implementing devices according to one embodiment of the present disclosure.
FIG. 3 illustrates a flowchart illustrating a method according to one embodiment of the present disclosure.
Figure 4 illustrates a flowchart showing detailed operations of the calculation operation of the transaction volume correction value described with reference to Figure 3.
FIG. 5 is a drawing for more specifically explaining the operation of performing correction based on the reference table described with reference to FIG. 4.
Figure 6 illustrates a drawing for more specifically explaining the transaction volume correction value described with reference to Figures 3 to 5.
FIGS. 7 and 8 illustrate a flowchart illustrating a method according to one embodiment of the present disclosure.

The various embodiments described in this disclosure are exemplified for the purpose of clearly explaining the technical idea of this disclosure, and are not intended to limit it to a specific embodiment. The technical idea of this disclosure includes various modifications, equivalents, alternatives, and embodiments selectively combined from all or part of each embodiment described in this disclosure. In addition, the scope of the technical idea of this disclosure is not limited to the various embodiments presented below or the specific description thereof.

Terms used in this disclosure, including technical or scientific terms, unless otherwise defined, may have the meaning commonly understood by one of ordinary skill in the art to which this disclosure belongs.

The expressions such as “includes,” “may include,” “comprises,” “may have,” “have,” and “may have” used in this disclosure indicate the presence of a target feature (e.g., a function, operation, or component), but do not exclude the presence of other additional features. That is, such expressions should be understood as open-ended terms that imply the possibility of including other embodiments.

As used herein, singular expressions may include plural meanings unless the context clearly indicates otherwise, and the same applies to singular expressions set forth in the claims.

The expressions "first", "second", or "first", "second", etc., used in the present disclosure, unless the context indicates otherwise, are used to distinguish one object from another when referring to a plurality of similar objects, and do not limit the order or importance between the objects. For example, each user terminal included in a plurality of user terminals according to the present disclosure can be distinguished from each other by being expressed as "the first user terminal" and "the second user terminal."

As used herein, the expressions “A, B, and C,” “A, B or C,” “at least one of A, B, and C,” or “at least one of A, B or C” can mean each of the listed items or all possible combinations of the listed items. For example, “at least one of A or B” can refer to (1) at least one A, (2) at least one B, (3) at least one A and at least one B.

The expression "based on" as used in this disclosure is used to describe one or more factors affecting a decision, act of judgment, or action described in a phrase or sentence containing the expression, and the expression does not exclude additional factors affecting the decision, act of judgment, or action.

As used herein, the expression that a component (e.g., a first component) is “connected” or “connected” to another component (e.g., a second component) may mean that the component is directly connected or connected to the other component, but also connected or connected via a new other component (e.g., a third component).

The expression "configured to" used in the present disclosure can have the meanings of "set to", "having the ability to", "modified to", "made to", "capable of", etc., depending on the context. This expression is not limited to the meaning of "specifically designed in hardware", and for example, a processor configured to perform a specific operation can mean a general purpose processor that can perform the specific operation by executing software, or a special purpose computer that is structured through programming to perform the specific operation.

Hereinafter, various embodiments described in the present disclosure will be described with reference to the attached drawings. In the attached drawings and the description of the drawings, identical or substantially equivalent components may be given the same reference numerals. In addition, in the description of various embodiments below, duplicate descriptions of identical or corresponding components may be omitted, but this does not mean that the components are not included in the embodiments.

FIG. 1 illustrates an environment to which devices (110, 120) according to one embodiment of the present disclosure can be applied. The environment illustrated in FIG. 1 may include a management device (110) and a user terminal (120).

Meanwhile, although FIG. 1 illustrates an example in which one user terminal (120) communicates with the management device (110) through a network, this is only for the convenience of understanding, and the number of user terminals (120) that can communicate with the management device (110) through a network may vary. That is, each of one or more user terminals (120) may access the e-commerce service provided by the management device (110). In addition, FIG. 1 illustrates only a preferred embodiment for achieving the purpose of the present disclosure, and some components may be added as needed.

Below, each component shown in Fig. 1 is described in more detail.

The management device (110) may be a server device that provides an e-commerce service. That is, the management device (110) may be a server device that is operated under the management of an operator of the e-commerce service.

The management device (110) can manage transactions regarding products (goods or services) posted on an e-commerce service.

For example, the management device (110) can classify and manage categories for multiple products. The categories of these products can be determined by various criteria. If different products are included in the same category, the different products can have the attributes of the category in common. Each of the multiple products classified in this way can be posted on an e-commerce service, that is, a page related to e-commerce. For another example, the management device (110) can transmit information to the user terminal (120) so that the page related to the products can be displayed on the user terminal (120). For another example, the management device (110) can transmit different responses corresponding to the different requests, respectively, to the user terminal (120) based on different requests related to the products obtained from the user terminal (120).

In addition, the management device (110) can analyze the user's log regarding the e-commerce service and manage the results of the analysis. For example, the management device (110) can calculate the transaction volume of a product based on the user's log. Since the transaction volume of the product can reflect the user's demand, the management device (110) can predict the future transaction volume of the product based on the transaction volume of the product. When predicting the transaction volume, the management device (110) can correct the past transaction volume of the product.

In addition to the examples described above, the management device (110) can perform operations related to known technologies that can be performed by a server device providing an e-commerce service. Therefore, applying the technical ideas of the present disclosure by referring to operations related to the known technologies is not excluded from the scope of the present disclosure.

The aforementioned management device (110) may be implemented by one or more computing devices. For example, all functions of the management device (110) may be implemented by a single computing device. For another example, the first function of the management device (110) may be implemented by a first computing device, and the second function may be implemented by a second computing device. For example, the computing device may be, but is not limited to, a desktop computer, a laptop computer, an application server, a proxy server, or a cloud server, and any type of device equipped with computing functions may be a computing device.

The user terminal (120) may be a terminal of a user who uses an e-commerce service. The user terminal (120) may display a page regarding the e-commerce service on the display of the user terminal (120) by the management device (110). This page may have a user interface applied to it that is provided as a function related to the e-commerce service. The application of this user interface may be managed by the management device (110) described above. In addition, the user terminal (120) may obtain a user input from a user for the page and transmit the user input to the management device (110). Here, the user terminal (120) may obtain a response corresponding to the user input from the management device (110), thereby allowing the user terminal (120) to perform operations defined to correspond to the user input. As described above, in order for the user to use the e-commerce service through the user terminal (120), a web browser or an application may be installed on the user terminal (120).

The user terminal (120) described above may be, for example, any one of devices such as a desktop computer, a laptop computer, a tablet computer, a wearable device, or a smart phone, but is not limited thereto, and any type of device equipped with computing functions may be the user terminal (120).

The management device (110) and the user terminal (120) illustrated in Fig. 1 can communicate through a network. This network can be implemented as any type of wired or wireless network, such as, for example, a local area network (LAN), a wide area network (WAN), a mobile radio communication network (MRCN), or WiBro (Wireless Broadband).

FIG. 2 illustrates a computing device (200) that can implement devices (110, 120) according to one embodiment of the present disclosure. That is, the management device (110) or the user terminal (120) illustrated in FIG. 1 can be implemented by the computing device (200) illustrated in FIG. 2. For reference, the computing device (200) in the present disclosure can be interchangeably referred to as an electronic device.

The computing device (200) may include one or more processors (210), one or more memories (220), or communication interfaces (230). In one embodiment, some components may be removed from the computing device (200), or other components (e.g., a display or an input device, etc.) may be added to the computing device (200). Additionally or alternatively, some components may be implemented in an integrated manner, or implemented as a single or multiple entities. In the present disclosure, one or more processors (210) may be referred to as a processor (210). The term processor (210) may mean a set of one or more processors, unless the context clearly indicates otherwise. In the present disclosure, one or more memories (220) may be referred to as a memory (220). The term memory (220) may mean a set of one or more memories, unless the context clearly indicates otherwise.

Below, each component illustrated in Fig. 2 is described in more detail.

The processor (210) can perform calculations or information processing related to control or communication of each component of the computing device (200). Specifically, the processor (210) can control at least one component of the computing device (200) connected to the processor (210) by driving software (or a computer program) received from another component. As an example, the processor (210) can load a command (e.g., an instruction, a code, or a code segment) or information into the memory (220), process the command or information stored in the memory (220), and store result information according to the processing in the memory (220). In addition, the processor (210) can be operatively connected to the components of the computing device (200) to perform various operations such as calculations, processing, generation, or processing related to the present disclosure.

The memory (220) can store various information. The information stored in the memory (220) is information acquired, processed, or used by at least one component of the computing device (200), and may include software. The software may include one or more commands that cause the processor (210) to perform operations according to various embodiments of the present disclosure when loaded into the memory (220). That is, the processor (210) may perform operations according to various embodiments of the present disclosure by executing the one or more commands described above. The memory (220) may include, for example, volatile or nonvolatile memory. In one embodiment, the program is software stored in the memory (220), and may include an operating system for controlling resources of the computing device (200), an application, or middleware that provides various functions to an application so that the application can utilize resources of the computing device (200).

The communication interface (230) can establish a wired or wireless communication channel with another device and transmit and receive various information with the other device. In one embodiment, the communication interface (230) can include at least one port for being connected to another device with a wired cable in order to communicate with the other device through a wire. In this case, the communication interface (230) can perform communication with another device connected through a wire through at least one port. In one embodiment, the communication interface (230) can be configured to be connected to a cellular network (e.g., 3G, LTE, 5G, Wibro, or Wimax) by including a cellular communication module. In one embodiment, the communication interface (230) can include a short-range communication module to transmit and receive information with another device using short-range communication (e.g., Wi-Fi, Bluetooth, Bluetooth Low Energy (BLE), UWB). In one embodiment, the communication interface (230) can include a non-contact communication module for non-contact communication. The contactless communication may include at least one non-contact type of proximity communication technology, such as, for example, Near Field Communication (NFC) communication, Radio Frequency Identification (RFID) communication, or Magnetic Secure Transmission (MST) communication. In addition to the various examples described above, the computing device (200) may be implemented in various known ways for communicating with other devices, and the scope of the present disclosure is not limited by the examples described above.

In one embodiment, the computing device (200) may include a display. The display may display various screens (e.g., one or more pages) based on the control of the processor (210). In order to display screens to which various interfaces are applied on the display, for example, a web browser or a dedicated application may be installed on the computing device (200). In addition, the display may be a configuration that can interact with a user and may receive user input from the user. Such a display may be implemented in the form of a touch sensor panel (TSP) that can recognize contact or proximity of various external objects (e.g., a user's finger or stylus).

In one embodiment, the computing device (200) may include an input device (e.g., a mouse or keyboard). The input device may receive information to be used in components of the computing device (200) from an external source (e.g., a user) of the computing device (200).

The processor (210), memory (220), and communication interface (230) illustrated in FIG. 2 are connected to each other through a bus, GPIO (General Purpose Input/Output), SPI (Serial Peripheral Interface), or MIPI (Mobile Industry Processor Interface), and can send or receive information or signals.

Hereinafter, methods according to various embodiments of the present disclosure will be described in detail. Although operations are illustrated in the drawings below in a particular order, it should be noted that the operations do not necessarily have to be performed in the particular order illustrated or in a sequential order, or that all illustrated operations must be performed to obtain a desired result.

In addition, the operations of the method to be described with reference to the drawings below may be performed by a computing device. In other words, the operations of the method may be implemented by one or more instructions executed by a processor of the computing device. All operations included in this method may be executed by a single physical computing device, but for example, the first operation of the method may be performed by a first computing device, and the second operation of the method may be performed by a second computing device. In other words, the operations included in the method may be performed by being divided among a plurality of computing devices.

In the following, the explanation will be continued assuming that the operation of the above-described method is performed by the management device (110) illustrated in Fig. 1. In addition, for the convenience of explanation, the subject of the operation included in the method may be omitted, but unless otherwise indicated in the context, it may be interpreted that the operation is performed by the management device (110).

FIG. 3 is a flowchart illustrating a method according to one embodiment of the present disclosure. The method illustrated in FIG. 3 may include a series of operations for correcting the transaction volume for a period (e.g., out of stock) during which the transaction volume cannot fully reflect the demand for a product posted on an e-commerce service, that is, the customer demand for the product, and predicting the future transaction volume for the product based on the correction. Hereinafter, the operations illustrated in FIG. 3 will be described in detail.

Among multiple products posted on an e-commerce service, one or more target products that will be the subject of transaction volume prediction can be identified (S310).

The target product may be a product that is the subject of the transaction volume prediction. For example, if "Product A" and "Product B" are posted on an e-commerce service, among these products, "Product A," "Product B," or "Product A" and "Product B" may be identified as the target products.

In addition, the target product can be determined from among multiple products based on an identification criterion. This identification criterion can be a criterion for identifying one of the multiple products.

With respect to the identification criterion, in one embodiment, the operation (S310) of identifying the target product may include an operation of identifying a product with an out-of-stock time among a plurality of products as the target product. That is, the identification criterion in this embodiment may be the presence or absence of an out-of-stock time.

Here, the out-of-stock time can mean the length of time during the day (24 hours) that the product is out of stock. For example, if the target product was out of stock for 8 hours during the day, the out-of-stock time is 8 hours. If the out-of-stock time is calculated by day, the maximum out-of-stock time can be 24 hours. The out-of-stock time can be changed by week, month, or year, not by day.

The presence or absence of such out-of-stock time may mean whether or not there is an out-of-stock time for the product within the target period. In this case, the target period may be a period that includes information about the product (e.g., past transaction volume information) used to predict the transaction volume of the product. For example, a period that starts from one month before the time of transaction volume prediction and ends at the time of transaction volume prediction may be the target period, and information about the product included in this target period may be used to predict the transaction volume. The length of this target period may be a fixed value (e.g., one month) or a variable value (e.g., a value that can be changed depending on the product's properties, etc.). The presence or absence of the out-of-stock time mentioned above may be managed to have a "True" or "False" value as a field for each of a plurality of products. According to this embodiment, a product with an out-of-stock time is identified as a target product, so that a product requiring correction of the transaction volume can be identified.

In addition, with respect to the identification criterion, in another embodiment, the operation (S310) for identifying the target product may include an operation for identifying a product that is not a third party product among a plurality of products as the target product. That is, the identification criterion in this embodiment may be whether or not it is a third party product.

Third-party products may be products for which the operator of the e-commerce service does not have ownership of the product. In addition, third-party products may be products for which a third party related to the product directly delivers the product to the user, thereby not bearing the burden of delivery for the product. In other words, third-party products may be posted on the e-commerce service in such a way that the operator grants a third party the right to post the product on the e-commerce service and receives a corresponding incentive. According to this embodiment, for products for which the operator does not have the burden of inventory management, such as third-party products, it may be unnecessary to predict the transaction volume for the product, and therefore, third-party products may be excluded when identifying the target product.

Transaction information for the target product can be extracted (S320).

Transaction information is information about the transaction of the target product, and may include, for example, the out-of-stock time of the target product or the transaction volume of the target product as items. Here, the transaction information may be obtained by analyzing the logs of users using the e-commerce service, etc. In addition, the transaction information may be extracted only if it is included in the target period. When extracting such transaction information, the extracted value may be processed according to a scale defined to correspond to the item included in the transaction information. For example, if the scale corresponding to the out-of-stock time is defined as "hour", if the out-of-stock time is "1 hour 29 minutes", the value may be processed as "1 hour" or "2 hours". For another example, if the scale corresponding to the out-of-stock time is defined as "hour minute", if the out-of-stock time is "1 hour 30 minutes 21 seconds", the value may be processed as "1 hour 30 minutes" or "1 hour 31 minutes".

With respect to the extraction method, in one embodiment, the operation (S320) of extracting transaction information for the target product may include an operation of extracting transaction information for the target product by date. For example, for the target product, the out-of-stock time of "May 1, 2023" may be extracted as "1 hour" and the transaction volume may be extracted as "101 units". For another example, the out-of-stock time of "May 2, 2023" may be extracted as "24 hours" and the transaction volume may be extracted as "0 units". For another example, the out-of-stock time of "May 3, 2023" may be extracted as "0 hours" and the transaction volume may be extracted as "150 units". According to the present embodiment, since the basic unit required for transaction volume prediction may be the transaction volume by date, the transaction information for the target product may be extracted by date so as to correspond to the transaction volume prediction. The transaction information extracted in this way may be corrected according to the operation described below, and thus may be used for transaction volume prediction. Therefore, if the basic unit required for predicting transaction volume is changed to a weekly, monthly or yearly unit, transaction information for the target product can be extracted in weekly, monthly or yearly units to correspond to the change.

With respect to the extraction method, in another embodiment, the operation (S320) of extracting transaction information for the target product may include an operation of extracting transaction information for the target product by date so as to correspond to the minimum period required for predicting the transaction volume. This embodiment may be understood as relating to the extraction period of transaction information for the target product, in other words, to the target period. Specifically, the target period may be determined so as to correspond to the minimum period required for predicting the transaction volume, preferably, the target period may include the minimum period. According to this embodiment, since the target period that can cover the period required for predicting the transaction volume is determined, transaction information for the target product of the target period may be extracted by date.

Based on a reference table including a correction value, the transaction volume of the extracted target product is corrected, thereby calculating a transaction volume correction value of the target product (S330).

The reference table may be a table defined for the transaction volume decrease rate according to the out-of-stock time of a product. The correction value may be closer to 1 as the out-of-stock time is shorter and closer to 0 as the out-of-stock time is longer. For example, if the out-of-stock time is "1 hour", the correction value included in the reference table may be "0.9". For another example, if the out-of-stock time is "22 hours", the correction value included in the reference table may be "0.2". Such a reference table may be generated based on the out-of-stock time of a specific product that may be acquired while operating an e-commerce service and the transaction volume corresponding to the out-of-stock time. In order to avoid redundant explanation, the method of generating the reference table will be described later with reference to FIG. 8.

In the case of a product that is out of stock, even if there are users who want to purchase it, actual product sales cannot take place, so the transaction volume of the target product with an out of stock time is likely not to reflect the full demand of the users. Therefore, if this transaction volume is used as it is in the transaction volume prediction execution operation (S340) described later, an inaccurate transaction volume prediction may be performed. According to this operation, the transaction volume of the target product is corrected based on the reference table, more specifically, the correction value of the reference table, so that a transaction volume correction value can be calculated to reflect the full demand of the users. By using this transaction volume correction value in the transaction volume prediction execution operation (S340) described later, an accurate transaction volume prediction can be performed.

Regarding the method of calculating the transaction volume correction value, for example, if the target product's out-of-stock time is "22 hours", the transaction volume is "205", and the correction value is "0.2", the transaction volume correction value can be calculated as "1000". Such an example is only an example for roughly explaining the calculation operation (S330) of the transaction volume correction value, and a more specific method of the calculation operation (S330) of the transaction volume correction value will be explained later with reference to FIGS. 4 to 6.

Based on the transaction volume correction value of the target product, a transaction volume prediction for the target product can be performed (S340).

Volume forecasting is the prediction of future volume of transactions for a target product, which may indicate future demand from users for the target product. This volume forecasting may be performed for a specific date, or may be performed for a period that includes multiple dates.

This method of predicting transaction volume can be basically performed based on the past transaction volume of the target product. In the simplest way, the average transaction volume for each day of the target period for the target product can be calculated as the value of the transaction volume prediction for the target product. In addition, since the transaction volume of the target product can have a first pattern for each specific cycle (e.g., daily, weekly, monthly, etc.), this first pattern can be used for predicting the transaction volume. In addition, since the transaction volume of the target product can have a second pattern based on a specific date (e.g., public holiday, etc.), this second pattern can be used for predicting the transaction volume. In addition, transaction volume prediction can be performed in any number of ways by referring to known techniques related to transaction volume prediction. In other words, any known technique for predicting future transaction volume based on past transaction volume can be included in the scope of the present disclosure.

Hereinafter, with reference to FIGS. 4 to 6, the calculation operation (S330) of the transaction volume correction value described with reference to FIG. 3 will be described in more detail. FIG. 4 is a flowchart showing the detailed operation of the calculation operation (S330) of the transaction volume correction value described with reference to FIG. 3. The operation S400 of FIG. 4 may be the calculation operation (S330) of the transaction volume correction value of FIG. 3. Hereinafter, the operations illustrated in FIG. 4 will be described in detail.

The grade corresponding to the target product can be identified (S410).

The grade may be classified according to the transaction volume of the target product or the transaction rate of the target product. Here, the transaction rate may be the rate at which the user purchased the target product among multiple products posted on the e-commerce service. With respect to the grade, for example, if "Grade A" means that the transaction volume in the target period is "5,000 or more" and "Grade B" means that the transaction volume in the target period is "less than 5,000", the grade of "Product A" with a transaction volume of "10,000" may be classified as "Grade A". In addition, under the conditions described above, the grade of "Product B" with a transaction volume of "4,000" may be classified as "Grade B". Although only examples of target products being classified into two grades have been mentioned, target products may be classified into any number of different grades. In addition, although only examples of having a fixed value (e.g., 5,000) as the classification criterion value have been mentioned, the classification criterion value may be implemented so that it can be changed according to, for example, the total transaction volume in the target period.

According to this operation, the grade corresponding to the target product can be identified.

A reference table corresponding to the grade can be obtained (S420).

The reference table may be a unique table for each grade. For example, "grade A" and "A reference table" may correspond, and "grade B" and "B reference table" may correspond. In addition, a specific reference table may be related to at least two grades. For example, "grade C" and "grade B" may correspond to "reference table C." In this operation, a reference table may be determined in advance to correspond to a grade. Specifically, the correspondence relationship (e.g., one-to-one correspondence, many-to-one correspondence) between the grade and the reference table in the above-described example may be determined in advance. Accordingly, by determining the reference table according to the correspondence relationship, a reference table corresponding to the grade may be obtained.

Correction based on a reference table can be performed (S430).

A correction based on a reference table, more specifically, a correction value of the reference table, is described with reference to FIG. 5.

FIG. 5 is a drawing for more specifically explaining the operation (S430) of performing correction based on the reference table (510) described with reference to FIG. 4.

The reference table (510) may be a table that indicates a correction value for each out-of-stock time. This reference table (510) may be created to have a corresponding value (e.g., correction value) according to a scale (e.g., time). For example, if the out-of-stock time is "5", the correction value may be "0.8". The correction value in the above example may be understood as a transaction volume decrease rate of the target product when the out-of-stock time is "5 hours", as described above.

Each correction value included in the reference table (510) can be substituted as "Ref[X]" into mathematical expressions 1 (520) and 2 (530). In addition, "Sale|X" in mathematical expressions 1 (520) and 2 (530) can be the transaction volume (sale) of the target product when the out-of-stock time is "X time". Furthermore, "AVG" in mathematical expression 1 (520) can be the average transaction volume during a period without an out-of-stock time. In this case, the period without an out-of-stock time can be N days (N is a natural number) among the latest days without an out-of-stock time.

As described above, by substituting the values that can be acquired or calculated into the mathematical expression 1 (520) or the mathematical expression 2 (530), the trading volume correction value "Sale|0" can be calculated. This "Sale|0" can be understood as a predicted trading volume value when the sold-out time is "0 hours". That is, the mathematical expression 1 (520) or the mathematical expression 2 (530) predicts how much trading volume would have occurred ("Sale|0") if there was no sold-out time on the date (i.e., if the sold-out time was "0 hours"), based on the trading volume ("Sale|X") on a specific date when the sold-out time was "X hours".

With respect to mathematical expression 1 (520), in one embodiment, the operation (S430) of performing a correction based on the reference table (510) may include an operation of identifying a correction value corresponding to the out-of-stock time of the target product among a plurality of correction values included in the reference table (510), and an operation of performing a correction based on the average transaction volume (e.g., “AVG”) of a period without an out-of-stock time for the target product, the transaction volume of the target product (e.g., “Sale|X”), and the correction value (e.g., “Ref[X]”).

With respect to mathematical expression 2 (530), in one embodiment, the operation (S430) of performing a correction based on the reference table (510) may include an operation of identifying a correction value corresponding to the out-of-stock time of the target product among a plurality of correction values included in the reference table (510) and an operation of performing a correction based on the transaction volume of the target product (e.g., “Sale|X”) and the reciprocal of the correction value (e.g., “1/Ref[X]”).

Hereinafter, the results of daily correction will be described with reference to Fig. 6. Fig. 6 illustrates a drawing for more specifically explaining the transaction volume correction value described with reference to Figs. 3 to 5.

The result table (600) of the correction for the transaction volume of the target product includes the product ID, date, transaction volume, out-of-stock time, and transaction volume correction value of the target product. In order to specifically compare the effect of the present disclosure, the result table (600) additionally includes a comparative example in which the immediately preceding transaction volume value is given as it is if the out-of-stock time is M (M is a natural number) hours or longer. Specifically, the result table includes a comparative example in which the transaction volume of "181" on March 25, 2022 is given as it is for the period from March 26, 2022 to May 13, 2022, which includes the subsequent out-of-stock time.

As a result of comparing the transaction volume correction value according to the comparative example and the present disclosure, the transaction volume correction value is calculated to be closer to the past transaction volume with a sold-out time of "0 hours" (e.g., the transaction volume from March 18, 2022 to March 24, 2022) than the comparative example. According to the present disclosure, a transaction volume correction value that can fully reflect the user's demand can be calculated, and by using this transaction volume correction value for transaction volume prediction, a more accurate transaction volume prediction can be performed.

Hereinafter, various methods of the present disclosure will be described with reference to FIGS. 7 and 8.

Figure 7 includes a series of operations for calculating a transaction volume correction value of a target product using the transaction volume of a third-party product.

A third-party product corresponding to the target product can be identified (S710).

Multiple products posted on an e-commerce service can be classified and determined as categories based on various criteria. According to this operation, by using this category, a third-party product corresponding to a target product can be identified. For example, if the category of a target product (e.g., "Product A") and the category of a third-party product ("Product a") are the same as "Home Appliances/Monitors", "Product a" can be identified as a third-party product corresponding to "Product A". Unlike the examples described above, these categories can have various ranges. As specific examples, the category can have various ranges such as "Home Appliances/Monitors/28 inches", "Home Appliances/Monitors/28 inches/A Manufacturer", or "Home Appliances/Monitors/28 inches/A Manufacturer/Product Code 1234".

According to this operation, if there are multiple third-party products identified to correspond to the target product, one of the multiple third-party products may be selected and identified. For example, the third-party product with the largest transaction volume may be selected and identified. In this case, the transaction volume of the third-party product with the largest transaction volume may be referenced to calculate the transaction volume correction value of the target product. In addition, if there are multiple third-party products identified to correspond to the target product, all of the multiple third-party products may be identified. In this case, the transaction volume of all third-party products related to the target product may be referenced to calculate the transaction volume correction value of the target product.

The transaction volume of third-party products can be extracted (S720).

This operation can be understood with reference to the description of the operation for extracting transaction information (S320) described with reference to Fig. 3. That is, this operation can have the same extraction method as the operation for extracting transaction information (S320) of Fig. 3, except that the transaction volume of a third-party product is extracted.

Based on the transaction volume of a third-party product, the transaction volume of the target product is corrected, thereby calculating the transaction volume correction value of the target product (S730).

With respect to the method of correction, the transaction volume correction value of the target product may be calculated based on the increase in the transaction volume of the third-party product during the out-of-stock period of the target product. Specifically, an additional factor "Ref[Y]" may be multiplied to "AVG*(1-Ref[X])" of the mathematical expression 1 (520) of FIG. 5 or "Sale|X*(1/Ref[X])" of the mathematical expression 2 (530). Here, "Ref[Y]" may be, for example, a ratio of the transaction volume of the third-party product during the out-of-stock period of the target product and the transaction volume of the third-party product during a period other than the out-of-stock period of the target product. If multiple third-party products are identified, "Ref[Y]" may be, for example, a ratio of the sum total of the transaction volume of the third-party products during the out-of-stock period of the target product and the sum total of the transaction volume of the third-party products during a period other than the out-of-stock period of the target product. Since the increase in the transaction volume of a third-party product may be a result of the third-party product being selected as a substitute for the target product, according to this embodiment, the transaction volume correction value of the target product can be calculated based on the increase in the transaction volume of the third-party product.

With regard to the method of correction, the transaction volume of the third-party product can be the transaction volume correction value of the target product as it is. Specifically, if the transaction volume of the third-party product is "100", the transaction volume correction value of the target product can be "100". If multiple third-party products are identified, the sum of the transaction volumes of the multiple third-party products can be the transaction volume correction value of the target product as it is. In addition, the transaction volume (or the sum of the transaction volume) of the third-party product that will be the transaction volume correction value in this way can be adjusted by multiplying a factor.

Since the third-party product shares properties with the target product, the third-party product may be more likely to be perceived as a substitute for the target product by users. Therefore, according to the method described with reference to Fig. 7, the user demand for the target product can be estimated by adjusting the transaction volume of the target product that is out of stock based on the transaction volume of the third-party product.

However, since a third-party product cannot completely replace the target product, the transaction volume of the third-party product may be considered only under certain conditions to correct the transaction volume of the target product. Specifically, the operation (S730) of calculating the transaction volume correction value of the target product based on the transaction volume of the third-party product may include an operation of calculating the transaction volume correction value of the target product based on the transaction volume of the third-party product based on a determination that a condition determined based on the continuity of the out-of-stock time of the target product is satisfied.

The condition for considering the transaction volume of third-party products may be a condition determined based on the continuity of the out-of-stock time of the target product. For example, a condition that is satisfied when the out-of-stock time is L hours (L is a natural number) or more consecutively occurs K times (K is a natural number) may be included in the above-mentioned conditions.

If the out-of-stock time is long, the transaction volume of the target product before the out-of-stock time may not fully reflect the user's demand. Therefore, if the out-of-stock time is long, in other words, only when the condition determined based on the continuity of the out-of-stock time is satisfied, the transaction volume of the target product can be adjusted based on the transaction volume of the third-party product related to the target product. Accordingly, the transaction volume of the target product can be adjusted to reflect the user's latest demand.

Hereinafter, a method for generating a reference table will be described with reference to FIG. 8. FIG. 8 is a flowchart illustrating a method according to one embodiment of the present disclosure.

A reference table can be created (S810).

Specifically, the operation (S810) of generating a reference table may include an operation of generating a reference table by comparing the average transaction volume when there is no out-of-stock time and the average transaction volume when there is an out-of-stock time for a product group including the target product.

A product group may be a set determined based on a grade classified according to the transaction volume or transaction rate of the product. Here, different products belonging to the same product group may have the same grade. In short, products with similar transaction volumes or transaction rates may be determined as a single product group. This may be for the purpose of generating a reference table for each product group, since the correction value included in the reference table may vary depending on the transaction volume or transaction rate of the product (in other words, depending on the grade). The reference table generated in this way may be used specifically for the grade, as described with reference to FIG. 4.

With respect to the calculation method of the correction value included as an item of the reference table, the correction value may be calculated by comparing the average transaction volume of products included in the product group when the out-of-stock time is a specific time with the average transaction volume of products included in the product group when there is no out-of-stock time. For example, if the average transaction volume of products included in the product group when the out-of-stock time is "1 hour" is "995" and the average transaction volume of products included in the product group when the out-of-stock time is "0 hours" is "1000", the correction value when the out-of-stock time is "1 hour" may be calculated as "0.995". In the above-described example, the average transaction volume of products included in the product group was described, but it may also be included in the scope of the present disclosure to change it to a value that can replace the average transaction volume of products included in the product group, such as the average transaction volume of some products included in the product group, the median transaction volume of the product group, etc.

By calculating the correction values included in the reference table according to the above-described method, a reference table for a product group can be created.

The reference table generation operation (S810) described with reference to Fig. 8 can be repeated with a cycle, thereby updating the reference table. This cycle can be a fixed value (e.g., 1 month). In addition, this cycle can be a fluid value, such as, for example, the point in time when the difference between the predicted transaction volume and the actual transaction volume becomes greater than a reference value.

According to the method of generating the reference table described with reference to Fig. 8 so far, a criterion (e.g., a correction value) for correcting the transaction volume of the target product can be determined. According to this criterion, even if the target product has a time of being out of stock, the transaction volume of the target product can be corrected to fully reflect the demand for the target product.

In the flowchart of the present disclosure, the operations of the method or algorithm are described in a sequential order, but may be performed in an order that can be arbitrarily combined, in addition to being performed sequentially. The description of the flowchart of the present disclosure does not exclude changes or modifications to the method or algorithm, and does not imply that any operation is essential or desirable. In one embodiment, at least some of the operations may be performed in parallel, iteratively, or heuristically. In another embodiment, at least some of the operations may be omitted, or other operations may be added.

Various embodiments of the present disclosure may be implemented as software in a machine-readable storage medium (MRSM) that can be read by a computing device. The software may be software for implementing various embodiments of the present disclosure. The software may be inferred from various embodiments of the present disclosure by programmers in the technical field to which the present disclosure belongs. For example, the software may be a computer program including instructions that can be read by a computing device. The computing device is a device that can operate according to instructions called from a storage medium, and may be interchangeably referred to as, for example, an electronic device. In one embodiment, a processor of the computing device may execute the called instructions, causing components of the computing device to perform functions corresponding to the instructions. The storage medium may mean any type of recording medium that can be read by a device and on which information is stored. The storage medium may include, for example, a ROM, a RAM, a CD-ROM, a magnetic tape, a floppy disk, or an optical information storage device. In one embodiment, the storage medium may be implemented in a distributed form in a computer system connected to a network, etc. In this case, the software may be distributed and stored in the computer system, etc., and may be executed. In another embodiment, the storage medium may be a non-transitory storage medium. A non-transitory storage medium means a medium that exists regardless of whether information is stored semi-permanently or temporarily, and does not include signals that are propagated transitorily.

Although the technical idea according to the present disclosure has been described by various embodiments above, the technical idea according to the present disclosure includes various substitutions, modifications, and changes that can be made within the scope understandable by a person having ordinary skill in the art to which the present disclosure belongs. In addition, it should be understood that such substitutions, modifications, and changes can be included within the scope of the appended claims.

Claims (15)

In a method performed by an electronic device,
A step of identifying a target product to be the subject of transaction volume prediction among multiple products posted on an e-commerce service, wherein the target product includes one or more products;
A step of extracting transaction information for the above target product, wherein the transaction information includes the out-of-stock time of the above target product and the transaction volume of the above target product; and
A step of calculating a transaction volume correction value of the target product using a reference table defined based on a transaction volume decrease rate according to the out-of-stock time is included.
The above method,
A step of identifying a third-party product corresponding to the above target product; and
Further comprising a step of extracting the transaction volume of the above third party product,
The step of calculating the transaction volume correction value of the above target product is:
A method comprising the step of calculating the transaction volume correction value of the target product by correcting the transaction volume of the target product based on the transaction volume of the third-party product, when the condition that the out-of-stock time of the target product exceeds a certain period of time is satisfied and continues for a reference value or longer is satisfied.
In the first paragraph,
A method further comprising a step of performing a future transaction volume prediction for the target product based on the transaction volume correction value of the target product.
In the first paragraph,
The step of identifying the above target product is:
A method comprising a step of identifying a product having an out-of-stock time among the above multiple products as the target product.
In the first paragraph,
The step of extracting the transaction information for the above target product is:
A method comprising the step of extracting transaction information for the above target product by date.
In paragraph 4,
The steps for extracting the above transaction information by date are:
A method comprising the step of extracting the transaction information for the target product on a daily basis so as to correspond to the minimum period required for predicting the transaction volume.
In the first paragraph,
A method further comprising the step of generating the above reference table.
In Article 6,
The steps for creating the above reference table are:
A method comprising the step of generating the reference table by comparing the average transaction volume when there is no out-of-stock time and the average transaction volume when there is an out-of-stock time for a group of products including the above target products.
In Article 7,
The above product group is,
A method in which a set is determined based on a grade classified according to the trading volume or trading rate of the product.
In the first paragraph,
The step of calculating the transaction volume correction value of the above target product is:
A step of identifying a grade corresponding to the above target product, wherein the grade is classified according to the transaction volume of the above target product or the transaction rate of the above target product;
A step of obtaining the reference table corresponding to the above grade; and
A method comprising the step of performing a correction based on the above reference table.
In Article 9,
The step of performing correction based on the above reference table is:
A step of identifying a correction value corresponding to the out-of-stock time of the target product among the plurality of correction values included in the above reference table; and
A method comprising a step of performing a correction based on the transaction volume of the target product and the reciprocal of the correction value.
In Article 9,
The step of performing correction based on the above reference table is:
A step of identifying a correction value corresponding to the out-of-stock time of the target product among the plurality of correction values included in the above reference table; and
A method comprising a step of performing a correction based on the average transaction volume of the period during which there is no out-of-stock time for the target product, the transaction volume of the target product, and the correction value.
delete delete In a non-transitory computer-readable recording medium having recorded thereon a computer program to be executed by a processor,
A non-transitory computer-readable recording medium configured to cause the processor to execute a method according to any one of claims 1 to 11.
A communication interface configured to enable communication with a network;
A processor configured to execute a computer program comprising one or more instructions; and
comprising a memory configured to load the above computer program;
An electronic device, wherein when the computer program is executed by the processor, the processor is configured to execute a method according to any one of claims 1 to 11.

Images