KR20210016747A - Method, Apparatus and System for Recommending Promotion Time - Google Patents

Abstract

Disclosed are a method, an apparatus, and a system for recommending a promotion time. According to the present invention, the method for recommending a promotion time comprises: a step of receiving a daily sales volume of products from a shopping mall for a first period from a release date; a step of calculating a cumulative sales volume for a second period for each reference date after the release date based on the received daily sales volume; a step of calculating a maximum cumulative sales volume which is the maximum value among the cumulative sales volumes for the second period for each reference date; a step of calculating a sales activity value for each reference date corresponding to the product based on the calculated cumulative sales volume and the maximum cumulative sales volume; and a step of detecting a reference date corresponding to the promotion time of the product based on the calculated sales activity value. Accordingly, based on analyzing a sales trend of products sold in the shopping mall, a time point when product promotion is requested can be detected and an appropriate promotion time for the products can be recommended to a user.

Description

Method, Apparatus and System for Recommending Promotion Time {Method, Apparatus and System for Recommending Promotion Time}

The present invention relates to a method, apparatus, and system for automatically recommending a promotion point, and more particularly, to a method, apparatus and system for automatically recommending a promotion point by detecting a point in time when a promotion is required by analyzing the sales trend of a product. About.

In recent years, the popularization of online communications such as the Internet has dramatically changed the commerce environment more than ever. Now, the word “online” or “online shopping” is unfamiliar, and the word “internet” or “online” feels like an unnecessary modifier. And the expansion trend of the online e-commerce market is expected to further expand.

In the operation of a shopping mall that sells products online, proper inventory management is very important. For example, in order to prevent loss of sales opportunities due to lack of stock, shopping mall operators should estimate the sales quantity within a predetermined period based on the production or order-to-stock period of products, and maintain inventory according to the forecast. .

On the other hand, inventory due to sluggish sales or excessive predicted sales volume, for example, becomes a major risk factor for the business, such as making it difficult to rotate funds. Therefore, it is common for the operator to unpredictably determine that the inventory is excessively accumulated, that the sales are not good, or to aggressively exhaust the inventory by performing promotions such as price discounts to reverse the sales trend.

For example, Korean Patent Registration No. 0749093 discloses a product promotion system that performs promotion by determining a group of promotional consumers who are likely to purchase user promotional products.

Korean Patent Registration No. 0749093

The present invention is to solve this problem, and based on analyzing the sales trend of products sold in shopping malls, the present invention detects a time when product promotion is necessary, and a promotion that can recommend an appropriate promotion time for the product to the user An object thereof is to provide an apparatus, method, and system for automatically recommending a viewpoint.

In order to achieve this object, the present invention provides a method of automatically recommending a promotion point in one aspect. The method of automatically recommending a promotion point is a method performed by a server interlocking with a shopping mall, the method comprising: receiving a daily sales amount of a product from the shopping mall during a first period from a release date; Calculating a cumulative sales volume for a second period for each reference date after the release date based on the received daily sales volume ??the second period is a period from a start date to a reference date and is included in the first period-; Calculating a maximum cumulative sales volume, which is a maximum value of the cumulative sales volume for the second period for each reference day; Calculating a sales activity value for each reference day corresponding to the product based on the calculated accumulated sales amount and the maximum accumulated sales amount; And detecting a reference date corresponding to a promotion time point of the product based on the calculated sales activity value.

The calculating of the sales activity value for each reference day may include dividing the accumulated sales amount for each reference day by the maximum accumulated sales amount for each reference day. The first period may be at least 1 month, and the second period may be at least 7 days.

The detecting of a reference date corresponding to the promotion time may include determining a reference date corresponding to a time point at which the sales activity value transitions below a set value as the promotion time point; And determining a reference date corresponding to a time point at which a set period elapses after the sales activity value transitions below a set value as the promotion time point.

The detecting of a reference date corresponding to the promotion point may include: detecting a sales state corresponding to a sales activity value for each reference date; And determining a reference date corresponding to the promotion point based on the sales status.

The sales state includes: a first state indicating that a sales activity value is equal to or greater than a first value, and a product is actively being sold; A second state in which the sales activity value is greater than or equal to a second value less than the first value and less than the first value, and the product indicates a normal level of sales; And a third state indicating that the sales activity value is less than the second value and sales of products are slowing.

The determining of the reference date may include determining a reference date at which the sales state transitions to a third state as a promotion time; And when the sales state transitions to the third state and a third period elapses from the third state, determining a reference date at which the third time elapses as a promotion time point.

The daily sales amount of the product may include the daily sales amount up to the current point in time; And at least one of the predicted daily sales amount predicted from the current point in time. The method of automatically recommending a promotion time may further include transmitting a promotion time recommendation message to the shopping mall informing that promotion of the product should be performed on the detected reference date.

The method for automatically recommending a promotion point displays a user interface including product identification information of the product, a graph representing a change in a cumulative sales volume and a sales activity value of the product over time from the release date, wherein the graph is the It may further include displaying a promotion point based on the sales activity value.

On the other hand, in order to achieve the object of the present invention described above, the present invention provides a device for automatically recommending a promotion point in another aspect. The apparatus for automatically recommending a promotion point may include: a receiving unit configured to receive a daily sales amount of a product during a first period from a release date from a shopping mall; Based on the received daily sales volume, the cumulative sales volume for the second period is calculated for each reference day after the release date, the maximum cumulative sales volume, which is the maximum value of the cumulative sales volume for the second period for each base day, is calculated, and the calculated cumulative An operation unit that calculates a sales activity value for each reference day corresponding to the product based on the sales amount and the maximum accumulated sales amount ??the second period is a period from a start date to a reference date and is included in the first period-; And a detector configured to detect a reference date corresponding to a promotion time point of the product based on the calculated sales activity value.

The calculation unit may divide the cumulative sales amount for each reference day by the maximum cumulative sales amount for each reference day. The first period may be at least 1 month, and the second period may be at least 7 days.

The detection unit may determine a reference date corresponding to a time point at which the sales activity value transitions below a set value as the promotion time point, or a reference date corresponding to a time point at which a set period elapses after the sales activity value transitions below a set value May be determined as the promotion time point.

The detection unit may detect a sales state corresponding to a sales activity value for each reference day, and determine a reference date corresponding to the promotion time based on the sales state.

The sales state includes: a first state indicating that a sales activity value is equal to or greater than a first value, and a product is actively being sold; A second state in which the sales activity value is greater than or equal to a second value less than the first value and less than the first value, and the product indicates a normal level of sales; And a third state indicating that the sales activity value is less than the second value and sales of products are slowing.

The detection unit may determine a reference date at which the sales state transitions to the third state as a promotion timing, or when the sales state transitions to the third state and a third period elapses from the third state, the third time period The reference date when this elapses may be determined as the promotion time. The daily sales amount of the product may include the daily sales amount up to the current point in time; And at least one of the predicted daily sales amount predicted from the current point in time.

The apparatus for automatically recommending a promotion time may further include a transmission unit for transmitting a promotion time recommendation message notifying that promotion of the product should be performed on the detected reference date to the shopping mall.

The promotion point automatic recommendation device displays a user interface including product identification information of the product, a graph representing a change in the accumulated sales amount and sales activity value of the product over time from the release date, wherein the graph is the The display unit may further include a display unit that displays a promotion timing based on the sales activity value.

On the other hand, in order to achieve the object of the present invention described above, the present invention provides an automatic promotion point recommendation system in another aspect. The automatic promotion point recommendation system includes: a shopping mall; And receiving a daily sales amount of a product during a first period from the launch date from the shopping mall, calculating the cumulative sales amount for a second period for each reference date after the release date, based on the received daily sales amount, and calculating a second period for each reference date. The maximum cumulative sales volume, which is the maximum value of the cumulative sales volume during the period, is calculated, based on the calculated cumulative sales volume and the maximum cumulative sales volume, the sales activity value for each reference day corresponding to the product is calculated, and the calculated sales activity value is calculated. Based on the basis, a recommendation server for detecting a reference date corresponding to the promotion time point of the product may include a period from a start date to a reference date and included in the first period.

Meanwhile, in order to achieve the object of the present invention described above, the present invention provides a method of automatically recommending a promotion point in another aspect. The method for automatically recommending a promotion point includes: receiving a daily sales amount of a product from a shopping mall during a first period from a release date to a current date; Calculating a cumulative sales volume for a second period for each reference date after the release date based on the received daily sales volume ??the second period is a period from a start date to a reference date and is included in the first period-; Calculating a maximum cumulative sales volume, which is a maximum value of the cumulative sales volume for the second period for each reference day; Calculating a sales activity value based on the cumulative sales volume of the current day and the maximum cumulative sales volume; Based on the calculated sales activity value, determining whether the current date is a time point to start the promotion.

The method of automatically recommending a promotion point may further include transmitting a message to the shopping mall informing that the promotion starts when the current date is determined as a point in time to start the promotion.

On the other hand, in order to achieve the object of the present invention described above, the present invention provides an automatic promotion point recommendation device in another aspect. The apparatus for automatically recommending a promotion point may include: a receiving unit configured to receive a daily sales amount of a product from a shopping mall during a first period from a release date to a current date; Based on the received daily sales volume, the cumulative sales volume for the second period is calculated for each reference day after the release date, the maximum cumulative sales volume, which is the maximum value of the cumulative sales volume for the second period for each reference day, is calculated, and An operation unit that calculates a sales activity value based on the cumulative sales volume and the maximum cumulative sales volume ??the second period is a period from a start date to a reference date and is included in the first period-; And a determination unit determining whether the current date is a time point to start the promotion based on the calculated sales activity value.

The apparatus for automatically recommending a promotion point may further include a transmitting unit to the shopping mall with a message informing that a promotion is started when the current date is determined as a point in time to start the promotion.

As described above, according to the present invention, based on analyzing the sales trend of products sold in shopping malls, a time point when product promotion is required may be detected, and an appropriate time point for product promotion may be recommended to a user. Accordingly, the shopping mall can perform product promotion by receiving an objectified promotion time according to the sales trend, away from arbitrarily and subjectively performing product promotion, and without specially analyzing for promotion.

1 is a block diagram illustrating a system configuration for realizing preferred embodiments of the present invention.
FIG. 2 is a block diagram illustrating the configuration of a service server shown in FIG. 1.
FIG. 3 is a flowchart illustrating a flow of a procedure for automatically recommending a promotion point performed by the service server shown in FIG. 2.
FIG. 4 is a table for illustratively illustrating a process of calculating the cumulative sales amount for the second period for each reference date after the release date based on the received daily sales amount.
5 is an exemplary diagram illustrating a part of a user interface displayed by a display unit of a service server.
6 is an exemplary diagram illustrating a sales state according to a sales activity value of products.
FIG. 7 is a flowchart illustrating a procedure for displaying a promotion point performed by the service server illustrated in FIG. 2.
FIG. 8 is an exemplary diagram illustrating that a service server displays information indicating a reference date corresponding to a promotion time point of a plurality of products on one screen.
9 and 10 are exemplary diagrams illustrating graphs in which a service server displays a sales state of a product and a promotion timing.
11 is a flowchart illustrating a process of displaying information indicating a plurality of sales states corresponding to a plurality of products on a screen.
FIG. 12 is an exemplary view illustrating displaying information indicating a plurality of sales states for a plurality of products on a screen.

In the present invention, various modifications may be made and various embodiments may be provided, and specific embodiments will be illustrated in the drawings and described in detail. However, this is not intended to limit the present invention to a specific embodiment, it is to be understood to include all changes, equivalents, and substitutes included in the spirit and scope of the present invention.

Terms such as first and second may be used to describe various elements, but the elements should not be limited by the terms. These terms are used only for the purpose of distinguishing one component from another component. For example, without departing from the scope of the present invention, a first element may be referred to as a second element, and similarly, a second element may be referred to as a first element. The term and/or includes a combination of a plurality of related listed items or any of a plurality of related listed items.

When a component is referred to as being'connected' or'connected' to another component, it is understood that it may be directly connected or connected to the other component, but other components may exist in the middle. Should be. On the other hand, when a component is referred to as being'directly connected' or'directly connected' to another component, it should be understood that there is no other component in the middle.

The terms used in the present application are only used to describe specific embodiments, and are not intended to limit the present invention. Singular expressions include plural expressions unless the context clearly indicates otherwise. In the present application, terms such as'comprise' or'have' are intended to designate the presence of features, numbers, steps, actions, components, parts, or combinations thereof described in the specification, but one or more other features It is to be understood that the presence or addition of elements or numbers, steps, actions, components, parts, or combinations thereof, does not preclude in advance.

Hereinafter, preferred embodiments of the present invention will be described in more detail with reference to the accompanying drawings. In describing the present invention, in order to facilitate an overall understanding, the same reference numerals are used for the same elements in the drawings, and duplicate descriptions for the same elements are omitted.

1 is a block diagram illustrating a system configuration for realizing preferred embodiments of the present invention.

As shown in FIG. 1, the system may include a service server 100 interworking with a plurality of shopping malls 10. Here, the shopping mall 10 may mean, for example, an e-commerce server that sells products through online.

The service server 100 may be implemented based on one or a plurality of server-class computer terminals. The computer terminal may be a network terminal including a memory for storing a program, a processor for executing a program stored in the memory, a hard disk for storing information, an input unit for inputting information, an output unit for outputting information, and the like. .

The service server 100 receives a daily sales volume for each product from the shopping malls 10 through a communication network, analyzes the received daily sales volume, and provides services such as automatic recommendation of product promotion time and display of promotion time. It can be provided to the shopping mall 10.

2 is a block diagram for explaining the configuration of the service server 100 shown in FIG. 1, and FIG. 3 is a flow of a procedure for automatically recommending a promotion point performed by the service server 100 shown in FIG. This is a flow chart for explanation.

Referring to FIGS. 1 to 3, the receiving unit 110 of the service server 100 may receive a daily sales amount of a product from the shopping mall 10 from the launch date of the product to the first period (step: S1).

The first period may be, for example, a period from a release date to the present. That is, the daily sales amount of the product may be the daily sales amount from the release date to the present time point. In this case, the service server 100 may continuously receive the daily sales volume of the newly updated day whenever the date is updated from the current point in time. In this case, the first period can be increased by the renewed date. The first period may be at least 1 month or longer for reliability of the analysis.

Alternatively, the first period may mean a period from the release date to a preset time point after the present. That is, the daily sales amount of the product may be information including a daily sales amount up to the current point in time and a daily predicted sales amount predicting the daily sales amount after the current point in time.

In this case, the first period is a period that can be set in advance by the administrator based on the user interface displayed by the service server 100, and may be set in units of months such as 1 month, 2 months, etc., or 30 days, It can also be set on a daily basis, such as 45 days. The first period may be at least 1 month or longer for reliability of the analysis.

For example, assuming that the first period is set to 1 month, the service server 100 may receive a daily sales volume from the shopping mall A 10 to the time point 1 month has elapsed from the release date of the "XXX" product. Assuming that the daily sales volume received here is 15 days from the release date, the daily sales volume from the release date to the present time point (e.g., 15 days elapsed from the release date) and after the current point (e.g., 16 days from the release date) You can include the daily forecast sales volume from) to the point in time 30 days have elapsed.

The daily predicted sales amount may be calculated by a sales amount predicting unit (not shown). The sales amount prediction unit may be provided in the shopping mall 10, may be provided in a separate sales amount prediction server, or may be provided in the service server 100. The process of calculating the daily forecast sales volume will be described later.

Next, the operation unit 120 of the service server 100 may calculate the accumulated sales amount for the second period for each reference date after the product release date based on the received daily sales amount (step: S2). The second period is a period from the start date to the reference date and is included in the first period. For example, the second period may be set such as 7 days, 10 days, and the like. The reference date may mean a date that becomes a standard for calculating sales activity.

In the present embodiment, it is assumed that the first period is set to 31 days and the second period is set to 7 days. FIG. 4 is a table for illustratively illustrating a process of calculating the cumulative sales amount for the second period for each reference date after the release date based on the received daily sales amount.

As shown in Figure 4, for a specific product, during the first period of 31 days, the daily sales volume is 11 on the first day of the release date, 9 on the second day from the release date, 10 on the third day, and 8 on the fourth day. , 4 on the 5th, 5 on the 6th, 12 on the 7th, 11 on the 8th, 10 on the 9th, 7 on the 10th,… , 1 on day 30 and 0 on day 31.

The service server 100 calculates the cumulative sales volume for each reference day based on the daily sales volume for the 31 days. Here, since the second period is 7 days, it is impossible to calculate from the first to the 6th day, which is less than the second period after the release date, so the service server 100 calculates the accumulated sales from the 7th day corresponding to the second period from the release date. I can.

First, if calculated on the basis of the 7th day, the cumulative sales volume for 7 days, which is the second period, is 59. Here, the day corresponding to the 7th day may be referred to as a reference date, which is a standard date for calculating the cumulative sales volume. That is, the second period may mean a period from the start date to the reference date. Here, the start date may be a day obtained by adding 1 to the second period minus the reference date.

The service server 100 may calculate the cumulative sales volume for each reference day until the last day of the first period using the first day in which the cumulative sales amount can be calculated as a reference date. For example, if day 8 is the reference date, the cumulative sales volume for 7 days, which is the second period, is 59, and if day 9 is the reference date, the cumulative sales volume for 7 days is 60. You can calculate the cumulative sales volume.

When the cumulative sales volume for each reference day is calculated, the operation unit 120 of the service server 100 may calculate the maximum cumulative sales volume, which is the maximum value among the calculated cumulative sales volume for each reference day (step: S3). The maximum cumulative sales volume may mean the maximum sales volume up to the base date, which is a calculation standard, of the cumulative sales volume per base day. For example, in the example shown in FIG. 4, the maximum cumulative sales volume up to the 10th day is 60 units at the 9th day, and the maximum cumulative sales volume up to the 31st day is 64 units at the 13th day of the reference day.

Subsequently, the operation unit 120 of the service server 100 may calculate a sales activity value for each reference day corresponding to the product based on the calculated accumulated sales amount per reference day and the maximum accumulated sales amount (step: S4). For example, the service server 100 may calculate a sales activity value for each reference day by dividing the accumulated sales amount for each reference day by the maximum accumulated sales amount.

For example, in the example shown in FIG. 4, when the reference date is the 8th day, the cumulative sales volume for 7 days is 59 and the maximum cumulative sales volume for 7 days is 59, so the sales activity value is 1. If the reference date is the 20th day, the cumulative sales volume for 7 days is 29 and the maximum cumulative sales volume is 64, so the sales activity value is 0.45. If the reference date is the 27th day, the cumulative sales volume for 7 days is 16 and the maximum cumulative sales volume is 64, so the sales activity value is 0.25.

Next, the detection unit 130 of the service server 100 may detect a reference date corresponding to the promotion point of the product based on the calculated sales activity value for each reference day (step: S5).

For example, the service server 100 may determine a reference date corresponding to a time point at which the sales activity value first transitions below the set value as the promotion time point. The setting value may be a value that can be directly set by the user through a user interface, and may be a positive value of 0.5 or less, such as 0.2.

The sales activity value may be increased to exceed the set value at least one day after transitioning below the set value. In this case, the service server 100 recommends withdrawing the promotion based on the policy setting through the user interface. A message or information requesting or indicating, or requesting or indicating that the promotion continues to be maintained, may be transmitted or displayed to the shopping mall 10. Here, when the promotion is withdrawn, a message or information indicating or requesting to perform the promotion again may be transmitted to the shopping mall 10 when the sales activity value again falls below the set value.

Alternatively, the service server 100 may determine a reference date corresponding to a time point at which the set period elapses while maintaining the sales activity value below the set value after transitioning to the set value or less as the promotion time point. That is, when the sales activity value transitions below the set value and then at least the set period elapses from less than the set value, the reference date is determined as the promotion time point.

Alternatively, the service server 100 calculates the average of the sales activity values for each reference day for a set period after the sales activity value transitions to a set value or less, and promotes the last day of the set period when the average value is less than the set sales activity value. You can also decide by the time point.

Meanwhile, the detection unit 130 of the service server 100 may detect a sales state corresponding to a sales activity value for each reference day, and may determine a reference date corresponding to the promotion time based on each sales state.

The sales state of the product may include a first state, a second state, and a third state. The first state is a state in which the sales activity value of the product is equal to or greater than the first value, and may indicate a state in which the product is actively being sold. For example, the first state may be a state in which the sales activity value of the product is 0.7 or more and may be in the "ACTIVE" state. The second state is a state in which the sales activity value of the product is greater than or equal to a second value less than the first value and less than the first value, and may indicate a state in which the product represents a normal sales level. For example, the second state may be a "NORMAL" state in which the product has a sales activity value of 0.2 or more and less than 0.7. The third state is a state in which the sales activity value of the product is less than the second value, and may indicate that the sales of the product is slowing. For example, the third state may be a "SLOW" state as a state in which the sales activity value of the product is less than 0.2.

6 is an exemplary diagram illustrating a sales state according to a sales activity value of products. In the example shown in FIG. 6, if the sales activity value is 0.7 or more, the sales state is "ACTIVE", if the sales activity value is 0,2 or more and less than 0.7, the sales state is "NORMAL", and if the sales activity value is less than 0.2, the sales state is Assume the state is "SLOW".

As shown in FIG. 6, a total of 255 products A have been sold after being released, and since the sales activity value is 0.75, the sales state is "ACTIVE". 132 units of Product B have been sold after launch, and since the sales activity value is 0.52, the sales status is "NORMAL". Product C sold 1026 units after launch, and sold quite a lot, but the current sales activity value is 0.18, so the sales status is "SLOW".

The service server 100 may determine a reference date when the sales state transitions to the third state as the promotion time point. Alternatively, the service server 100 may determine a reference date at which the set period elapses as the promotion time when the sales state transitions to the third state and then elapses for a set period in the third state.

When the reference date corresponding to the promotion time is determined by the detection unit 130, the transmission unit 150 of the service server 100 may transmit a promotion time recommendation message indicating that the reference date is the promotion time to the shopping mall 10 (step :S7). The promotion time recommendation message may include a recommendation message indicating that promotion of the product should be performed on the detected reference date.

On the other hand, when the reference date corresponding to the promotion point is determined by the detection unit 130, the display unit 140 of the service server 100 displays a user interface including information indicating the promotion point in the shopping mall 10. It can be displayed on the screen (step: S6).

The user interface includes product identification information of the product, a graph representing the change in the accumulated sales volume and sales activity value of the product over time from the release date, and the graph allows the user to easily recognize the promotion timing according to the detected reference date. Can be marked to be able to.

5 is an exemplary diagram illustrating a part of a user interface displayed by the display unit 140 of the service server 100 by way of example.

As shown in FIG. 5, product identification information of a product is displayed at the top of the user interface. The X axis of the graph is an axis to indicate the first difference after release, and the Y axis is an axis to indicate the total cumulative sales volume and sales activity value according to the first order.

Products are actively sold from the first day, and the cumulative sales volume increases almost linearly, and as the cumulative sales volume approaches 60 days, the increase in cumulative sales volume is slowing. On the other hand, the sales activity value of the product is calculated from the 7th day after launch, increases to almost 1, then decreases, and falls below 0.2 after 60 days. Accordingly, when the determination setting value at the time of promotion is 0.2, the reference date corresponding to the time of promotion is 60 days, and promotion may be performed thereafter. The graph may be visually displayed so that the user can easily recognize that the promotion should be performed after the promotion point.

Meanwhile, the display unit 140 may indicate a sales state according to the primary order of the product on the graph, and the display unit 140 may display a time point at which the sales state transitions to the third state as a promotion time point.

Meanwhile, the service server 100 may display the promotion timing for a plurality of products sold in the shopping mall 10, and the procedure will be described below.

FIG. 7 is a flowchart illustrating a procedure for displaying a promotion point performed by the service server 100 shown in FIG. 2.

As shown in FIG. 7, the receiving unit 110 of the service server 100 may collect daily sales for a plurality of products from a release date (step: S11). The daily sales amount from the release date may be the daily sales amount from the release date of each product to the present time point. Alternatively, the daily sales volume from the release date may include the daily sales volume from the release date of each product to the current time point and the daily predicted sales volume from the current time point to a preset time point. That is, the daily sales volume from the release date may be real-time data for each product up to the present time, or may be data further including the daily predicted sales volume up to the time set in the real-time data.

The daily predicted sales amount may be calculated by a sales amount predicting unit (not shown). The sales amount prediction unit may be provided in the shopping mall 10, may be provided in a separate sales amount prediction server, or may be provided in the service server 100.

Next, the operation unit 120 of the service server 100 may calculate sales activity values for a plurality of products by reference day based on the collected daily sales volume (step: S12).

Here, the procedure for calculating the sales activity value for each reference day of each product has been previously mentioned in the description of steps S2 to S4 with reference to FIG. 3. For example, the service server 100 calculates the cumulative sales volume for the second period for each reference day after the release date of the first product, calculates the maximum cumulative sales volume, which is the maximum value of the cumulative sales volume for the second period for each reference day, and calculates Based on the accumulated sales amount and the maximum accumulated sales amount, the sales activity value for each reference day corresponding to the first product may be calculated.

Here, calculating the sales activity value for each reference day corresponding to the first product may be, for example, dividing the accumulated sales amount for each reference day corresponding to the first product by the maximum accumulated sales amount for each reference day. The second period, as mentioned above, may mean a period from the start date to the reference date, and may be, for example, 7 days.

The operation unit 120 of the service server 100 may calculate sales activity values for a plurality of products for each reference day by repeating the above-described process for each product.

Subsequently, the detection unit 130 of the service server 100 may detect a reference date corresponding to the promotion timing of the plurality of products based on the calculated sales activity values for each reference day for the plurality of products (step: S13). .

For example, the service server 100 may determine a reference date corresponding to a time point at which the sales activity value of the first product transitions below a set value as the promotion time point of the first product. Alternatively, the service server 100 may determine a reference date corresponding to a time point at which a set period elapses after the sales activity value of the first product transitions below the set value as the promotion time point of the first product. Alternatively, the service server 100 may determine a reference date corresponding to the last day of the set period as the promotion time when the average value for the set period is less than the set value after the sales activity value of the first product transitions below the set value. . The service server 100 may detect a reference date corresponding to a promotion time point of a plurality of products by repeating at least one of the above-described processes.

On the other hand, the service server 100 detects a plurality of sales states corresponding to the sales activity values for each reference day for a plurality of products, and determines a reference date corresponding to the promotion timing for a plurality of products based on the plurality of sales states. May be.

Here, the sales state of the product may include a first state, a second state, and a third state. The first state is a state in which the sales activity value of the product is equal to or greater than the first value, and may indicate a state in which the product is actively being sold. For example, the first state may be a state in which the sales activity value of the product is 0.7 or more and may be in the "ACTIVE" state. The second state is a state in which the sales activity value of the product is greater than or equal to a second value less than the first value and less than the first value, and may indicate a state in which the product represents a normal sales level. For example, the second state may be a "NORMAL" state in which the product has a sales activity value of 0.2 or more and less than 0.7. The third state is a state in which the sales activity value of the product is less than the second value, and may indicate that the sales of the product is slowing. For example, the third state may be a "SLOW" state as a state in which the sales activity value of the product is less than 0.2.

For example, the service server 100 may determine a reference date at which the sales state of the first product transitions to the third state as the promotion time of the first product. Alternatively, the service server 100 may determine the reference date at which the set period elapses as the promotion point of the first product when the sales state of the first product transitions to the third state and a set period has elapsed in the third state. have.

Next, the display unit 140 of the service server 100 may display information indicating a reference date corresponding to the promotion timing of a plurality of products on one screen of the shopping mall 10 (step: S14).

FIG. 8 is an exemplary diagram illustrating that the service server 100 displays information indicating a reference date corresponding to a promotion time point of a plurality of products on one screen.

As shown in FIG. 8, the date may be displayed on the X axis of the graph. The total cumulative sales volume of the product may be displayed on the Y-axis of the graph. The display unit 140 of the service server 100 may visually display the change in the total cumulative sales volume of individual products according to the flow of the date, and the reference date corresponding to the promotion time point for the individual product by the detection unit 130 When this is detected, the detected reference date can be visually and easily recognizably displayed as a promotion time point. Accordingly, promotion timing of a plurality of products may be displayed on one screen.

The display unit 140 of the service server 100 may extract thumbnail images for individual products from the database. The thumbnail image may be a representative image of a sales page of the shopping mall 10. To this end, the display unit 140 may collect representative images of individual products from the shopping mall 10 and store them in a database, and extract a representative image stored at the time of displaying the user interface from the database and use it as a thumbnail image.

The display unit 140 of the service server 100 highlights the thumbnail image and date of the corresponding product extracted on a date corresponding to the promotion point on a visual graphic representing a change in the total cumulative sales volume of individual products for a plurality of products. Can be displayed in a way. Accordingly, on the screen displayed in the shopping mall 10, changes in the total cumulative sales amount of individual products are displayed in a visual graphic for a number of products, and the date at the time of promotion and a thumbnail image are highlighted on the visual graphic. .

On the other hand, when the daily sales volume data for each product is updated every set period, the service server 100 updates the total cumulative sales volume and sales status of the product each time the daily sales volume data for each product is updated, and when the reference date corresponding to the promotion time arrives, You can mark the time of promotion.

9 and 10 are exemplary diagrams illustrating a graph in which the service server 100 displays the sales status and promotion timing of products. As shown in the graph shown in FIG. 8, the total number of products is displayed on one graph. A graphic representing the cumulative sales volume may be visually displayed, but for convenience of understanding, one of the products, Product A, is shown.

As illustrated in FIGS. 9 to 10, a date may be displayed on the X axis of the graph, and a total accumulated sales amount of the product may be displayed on the Y axis of the graph. Referring to FIG. 9, a graph indicating that product A is released on June 1, 2018 and that the total cumulative sales volume is increasing almost linearly may be updated every set period (eg, 1 day).

Assuming that the current product A has a sales activity value of 0.2 or more and less than 0.7, and the sales status is "NORMAL", the graph will visually display a graphic showing the change in the total cumulative sales of product A from the date of release to the present (e.g. And a thumbnail image of the product A and "NORMAL" indicating the current sales state may be displayed at the end of the graphic indicating the total cumulative sales amount of product A (ie, the current time point).

Thereafter, as time passes, the daily sales volume data is continuously updated and when September 10 comes, the reference date corresponding to the promotion time is detected as September 10 by the detection unit 130, thereby detecting that the promotion time has arrived.

Referring to FIG. 10, in the graph, a graphic representing the change in the total cumulative sales volume of product A from the date of release to the present is visually displayed (e.g., indicated by a wire), and the end of the graphic representing the total cumulative sales volume of product A Current time), a thumbnail image of product A and "SLOW" indicating the current sales status may be displayed, and a highlight indicating that the promotion time of September 10, 2018 and the promotion time may be displayed.

Even if the graphic representing the change in the total cumulative sales volume of Product A is further extended as the daily sales data is continuously updated as time passes, the thumbnail image and the date and highlight at the time of promotion are not changed unless the sales status of Product A is changed. Will not move from September 10, the time of promotion.

Meanwhile, unlike the above-described method, the display unit 140 of the service server 100 may display information indicating a plurality of sales states corresponding to a plurality of products on the screen of the shopping mall 10.

11 is a flowchart illustrating a process of displaying information indicating a plurality of sales states corresponding to a plurality of products on a screen.

As shown in FIG. 11, the service server 100 includes a sales status display area including a first area corresponding to a first state, a second area corresponding to a second state, and a third area corresponding to a third state. Can be displayed (step: S21). On the other hand, the service server 100 may extract a plurality of thumbnail images corresponding to a plurality of products from the database (step: S22).

Subsequently, the service server 100 displays thumbnail images corresponding to the plurality of products according to the plurality of sales states corresponding to the plurality of products, from among the first area, the second area, and the third area of the sales status display area. A thumbnail image may be inserted in the area to correspond to the individual sales status (step: S23).

FIG. 12 is an exemplary view illustrating displaying information indicating a plurality of sales states for a plurality of products on a screen.

As shown in FIG. 12, the X axis of the graph displayed on the screen represents the sales activity value, and the Y axis represents the total cumulative sales amount. ㅊ

As for the thumbnail images of each product, the Y-axis and X-axis values are determined according to the total cumulative sales volume and sales activity value of the corresponding product, and the thumbnail image is inserted and displayed at the point where the specified X-axis and Y-axis intersect.

Accordingly, the user can easily recognize the sales status of each product by looking at the graph, and in particular, it can be recognized that the product in which the thumbnail image is arranged in the "SLOW" area should perform promotion.

13 exemplarily shows a graph displayed by inserting thumbnail images of actual products according to the display method of the graph shown in FIG. 12.

As shown in Fig. 13, an area having a sales activity value of less than 0.2, that is, a third area, is indicated as a "LAGGERS" area, and an area having a sales activity value of 0.2 or more and less than 0.7, that is, a second area, is a "FOLLOWERS" area. Is displayed, and the area having a sales activity value of 0.7 or more, that is, the first area may be displayed as a “FRONT RUNNERS” area. Each area is marked with a unique color to distinguish it from other areas.

For each product's thumbnail image, the Y-axis and X-axis values are determined according to the total cumulative sales volume and sales activity value of the product, and the thumbnail image is inserted and displayed at the point where the specified X-axis and Y-axis intersect. have.

Meanwhile, as mentioned above, the daily predicted sales volume may be calculated by the sales volume predicting unit. The sales amount prediction unit may predict the sales amount of a product, may be provided in the shopping mall 10, may be provided in a separate sales amount forecasting server, or may be provided in the service server 100. The prediction of the sales amount of the product may be at least one of a first prediction, a second prediction, and a third prediction.

The first prediction is to obtain daily cumulative sales amount information of the first product up to a first point in time, estimate a parameter of a time series data analysis model using the obtained daily cumulative sales amount information, and analyze the time series data using the estimated parameter. The average and standard deviation of the cumulative sales volume after the first point in time is predicted using the model, and the maximum of the cumulative sales volume at the second point in time after the first point in time under a predetermined first reliability by using the predicted cumulative sales volume average and standard deviation. You can calculate the value.

For example, the time series data analysis model may be an Auto-Regressive Integrated Moving Average (ARIMA) model. Estimating the parameters of the time series data analysis model using the obtained daily cumulative sales volume information is, for example, by changing at least one of a plurality of parameters of the ARIMA model and determining whether the time series data is in a steady state, The values of the parameters may be determined, and parameters related to coefficients for at least some terms included in the equations of the ARIMA model may be estimated based on the determined values of the plurality of parameters.

The plurality of parameters are a first parameter (p) representing the lag of an autoregression (AR) model, a second parameter (d) representing the number of differences, and a moving average (MA) model. It may include a third parameter (q) indicating the lag of.

The second prediction obtains daily sales volume information of the first product up to a first time point, and considers a first prediction model following a discrete probability distribution based on the daily sales volume information until a second time point later than the first time point. The daily sales amount of the first product may be calculated. Here, calculating the daily sales amount of the first product up to the second point in time may include a process of estimating the distribution of parameters of the first prediction model through Bayesian inference.

The parameters of the first prediction model may include a first parameter associated with a maximum daily sales amount of the first product and a second parameter associated with an expected sales period of the first product. The discrete probability distribution may be, for example, a Poission Distribution. The value of the first parameter may be determined as a sales quantity of the first product at an initial sale point.

Calculating the daily sales amount of the first product up to the second point in time may include sampling the value of the first parameter and the value of the second parameter using the estimated distribution of the parameter of the first prediction model. And, by using the sampled first and second parameter values, the daily sales volume of the first period is simulated from the first point in time, and a statistical value associated with the daily sales volume of the first period can be calculated using the simulation result. have.

In the third prediction, the acquired daily sales quantity information up to the first point in time of the first product is obtained, and the obtained daily sales quantity information is obtained for predicting the sales quantity at a second point in time that is later than the first point in time of the first product. Using as training data, an artificial intelligence-based first prediction model is generated, and the sales quantity of the first product at the second time point is calculated using the generated first prediction model based on the daily sales quantity information. It is predictable.

Generating the first prediction model may include learning the first prediction model while changing a value of a hyper parameter of the first prediction model using the daily sales quantity information, and the daily sales quantity information As a result of evaluating the learning performance by using, the value of the hyper parameter having the best learning performance may be determined as the value of the hyper parameter of the first prediction model.

The first prediction model may include a Long Short Term Memory (LSTM) model. The learning data may include sales quantity information obtained by summing sales quantity generated in units of a first period from the start of sales.

The present invention has been described by exemplifying preferred embodiments thereof, but those skilled in the art will variously modify and change the present invention within the scope not departing from the technical matters and scope of the present invention described in the following claims. You will be able to understand that it can be done. Therefore, changes in the embodiments of the present invention will not be able to depart from the technology of the present invention.

10: shopping mall
100: service server
110: receiver
120: operation unit
130: detection unit
140: display
150: transmission unit

Claims (25)

As a method performed by a server interlocking with a shopping mall,
Receiving a daily sales amount of a product from the shopping mall during a first period from a release date;
Calculating a cumulative sales volume for a second period for each reference date after the release date, based on the received daily sales volume-the second period is a period from a start date to a reference date and is included in the first period;
Calculating a maximum cumulative sales volume, which is a maximum value of the cumulative sales volume for the second period for each reference day;
Calculating a sales activity value for each reference day corresponding to the product based on the calculated accumulated sales amount and the maximum accumulated sales amount; And
And detecting a reference date corresponding to a promotion time point of the product based on the calculated sales activity value.
The method of claim 1, wherein calculating a sales activity value for each reference day comprises:
And dividing the cumulative sales volume for each reference day by the maximum cumulative sales volume for each reference date.
The method of claim 1, wherein the first period is at least 1 month, and the second period is at least 7 days.
The method of claim 1, wherein detecting a reference date corresponding to the promotion time point,
Determining a reference date corresponding to a time point at which the sales activity value transitions below a set value as the promotion time point; And
The method of automatically recommending a promotion point, characterized in that any one of the steps of determining a reference date corresponding to a point in time when a set period elapses after the sales activity value transitions below a set value as the promotion point.
The method of claim 1, wherein detecting a reference date corresponding to the promotion time point,
Detecting a sales status corresponding to a sales activity value for each reference day; And
And determining a reference date corresponding to the promotion time based on the sales status.
The method of claim 5, wherein the sales state is,
A first state indicating that the sales activity value is equal to or greater than the first value, and that the product is actively being sold;
A second state in which the sales activity value is greater than or equal to a second value less than the first value and less than the first value, and the product indicates a normal level of sales; And
A method for automatically recommending a promotion point, characterized in that the sales activity value is less than the second value and is in any one of a third state indicating that sales of products are slowing.
The method of claim 6, wherein the determining of the reference date comprises:
Determining a reference date when the sales state transitions to a third state as a promotion time point; And
When the sales state transitions to the third state and a third period elapses from the third state, the promotion timing automatic, characterized in that it is any one of the steps of determining a reference date at which the third time elapses as a promotion timing Recommended way.
The method of claim 1, wherein the daily sales amount of the product is
Daily sales to date; And
A method for automatically recommending a promotion point, comprising at least one of the predicted daily sales amount predicting the daily sales amount after the current point in time.
The method of claim 1, further comprising transmitting a promotion point recommendation message indicating that promotion of the product should be performed on the detected reference date, to the shopping mall.
The method of claim 1, further comprising: displaying a user interface including product identification information of the product, a graph representing a change in a cumulative sales amount and a sales activity value of the product over time from the release date, wherein the graph is the sales activity The method of automatically recommending a promotion point, further comprising the step of displaying a promotion point based on a value.
A receiving unit for receiving a daily sales amount of a product from the shopping mall during a first period from the release date;
Based on the received daily sales volume, the cumulative sales volume for the second period is calculated for each reference day after the release date, the maximum cumulative sales volume, which is the maximum value of the cumulative sales volume for the second period for each base day, is calculated, and the calculated cumulative An operation unit that calculates a sales activity value for each reference day corresponding to the product based on the sales volume and the maximum accumulated sales volume-the second period is a period from a start date to a reference date and is included in the first period; And
And a detection unit configured to detect a reference date corresponding to a time point of promotion of the product based on the calculated sales activity value.
The method of claim 11, wherein the calculation unit,
For each of the reference days, the device for automatically recommending a promotion point, wherein the accumulated sales amount for each reference day is divided by the maximum accumulated sales amount.
The apparatus of claim 11, wherein the first period is at least 1 month and the second period is at least 7 days.
The method of claim 11, wherein the detection unit,
A reference date corresponding to a time point at which the sales activity value transitions below a set value is determined as the promotion time point, or a reference date corresponding to a time point at which a set period elapses after the sales activity value transitions below a set value is set at the promotion time point. Promotion point automatic recommendation device, characterized in that determined by.
The method of claim 11, wherein the detection unit,
A promotion point automatic recommendation device, characterized in that: detecting a sales state corresponding to a sales activity value for each reference day, and determining a reference date corresponding to the promotion point based on the sales state.
The method of claim 15, wherein the sales state,
A first state indicating that the sales activity value is equal to or greater than the first value, and that the product is actively being sold;
A second state in which the sales activity value is greater than or equal to a second value less than the first value and less than the first value, and the product indicates a normal level of sales; And
A promotion point automatic recommendation device, characterized in that the sales activity value is less than the second value and is in any one of a third state indicating that sales of a product are slowing.
The method of claim 16, wherein the detection unit,
The reference date at which the sales state transitions to the third state is determined as the promotion point, or when the third time period elapses when the sales state transitions to the third state and a third period elapses from the third state Promotion point automatic recommendation device, characterized in that determining the reference date of the promotion point.
The method of claim 11, wherein the daily sales amount of the product,
Daily sales to date; And
Automatic promotion point recommendation device comprising at least one of the predicted daily sales amount predicting the daily sales amount after the current point in time.
12. The apparatus of claim 11, further comprising a transmission unit for transmitting a promotion point recommendation message notifying that promotion of the product should be performed on the detected reference date to the shopping mall.
The method of claim 11, wherein a user interface including product identification information of the product, a graph representing a change in a cumulative sales amount and a sales activity value of the product over time from the release date is displayed, wherein the graph is the sales activity Promotion point automatic recommendation device, characterized in that further comprising a display for displaying the promotion point based on the value.
shopping mall; And
Receives the daily sales amount of the product during the first period from the launch date from the shopping mall, calculates the cumulative sales amount for the second period for each reference date after the release date, based on the received daily sales amount, and during the second period for each reference day Calculate the maximum cumulative sales volume, which is the maximum value of the cumulative sales volume of, based on the calculated cumulative sales volume and the maximum cumulative sales volume, calculate the sales activity value for each reference day corresponding to the product, and based on the calculated sales activity value And a recommendation server for detecting a reference date corresponding to the promotion time of the product, wherein the second period is a period from a start date to a reference date and is included in the first period.
Receiving a daily sales amount of a product from a shopping mall during a first period from a release date to a current date;
Calculating a cumulative sales volume for a second period for each reference date after the release date, based on the received daily sales volume-the second period is a period from a start date to a reference date and is included in the first period;
Calculating a maximum cumulative sales volume, which is a maximum value of the cumulative sales volume for the second period for each reference day;
Calculating a sales activity value based on the cumulative sales volume of the current day and the maximum cumulative sales volume;
And determining whether the current date is a time point to start the promotion based on the calculated sales activity value.
23. The method of claim 22, further comprising transmitting, to the shopping mall, a message notifying that the promotion starts when the current date is determined as the promotion start time point.
A receiving unit configured to receive a daily sales amount of a product during a first period from a release date to a current date from the shopping mall;
Based on the received daily sales volume, the cumulative sales volume for the second period is calculated for each reference day after the release date, the maximum cumulative sales volume, which is the maximum value of the cumulative sales volume for the second period for each reference day, is calculated, and An operation unit that calculates a sales activity value based on the cumulative sales volume and the maximum cumulative sales volume-the second period is a period from a start date to a reference date and is included in the first period; And
And a determination unit configured to determine whether the current date is a time point to start the promotion, based on the calculated sales activity value.
25. The apparatus of claim 24, further comprising a transmission unit for transmitting a message to the shopping mall informing that the promotion starts when the current date is determined as a time point to start the promotion.

Images