Method, device, and system for adjusting standard inventory replenishment quantity linked to kiosk using expiration dates, peak season periods, and growth / decrease rates of social media posts

Abstract

According to one embodiment, at a second point in time, which is after the first product is sold at a first vending machine connected to a first kiosk, the method comprises: a step of confirming the inventory quantity of the first product stored in the first vending machine as a first quantity based on the inventory information of the first vending machine; a step of setting a point in time prior to a preset reference period from the second point in time as a third point in time, setting a point in time prior to the reference period from the third point in time as a fourth point in time, setting a point in time after the reference period from the second point in time as a fifth point in time, setting the period from the fourth point in time to the third point in time as a first period, setting the period from the third point in time to the second point in time as a second period, and setting the period from the second point in time to the fifth point in time as a third period; and a step of analyzing the sales volume fluctuation trend of the first product by comparing the sales volume of the first product sold at the first vending machine during the first period and the second period based on the sales history of the first vending machine. A step of predicting the quantity of the first product expected to be sold at the first vending machine during the third period as a fourth quantity based on the results of analyzing the sales volume fluctuation trend of the first product; a step of setting a first weight based on the rate of increase or decrease in the number of users who purchased the first product through recommendations of the first product, and calculating a second standard quantity using the fourth quantity and the first weight; a step of setting a second weight based on the consumption period of the first product, setting a third weight based on peak periods that have a favorable influence on the sales of the first product within the third period, and setting a fourth weight based on the rate of increase or decrease in the number of posts of the first product uploaded to SNS; a step of calculating an adjusted second standard quantity by multiplying the second standard quantity, the second weight, the third weight, and the fourth weight;A method for adjusting a standard quantity of stock linked to a kiosk using an expiration date, a peak season period, and a rate of increase or decrease in the number of SNS posts is provided, comprising: a step of calculating a fifth quantity by subtracting the first quantity from the adjusted second standard quantity when it is confirmed that the first quantity is less than the adjusted second standard quantity; and a step of transmitting a notification message to a first administrator terminal indicating that the first product of the fifth quantity needs to be stocked in the first vending machine when the fifth quantity is calculated.

Description

Technology Field

[0001] The following embodiments relate to a technology for adjusting the standard inventory replenishment quantity of a kiosk-linked vending machine based on the expiration date, peak season period, and the rate of increase or decrease in the number of social media posts. Background Technology

[0003] As the use of kiosks expands, there is a trend of vending machines selling products being connected to and used with kiosks.

[0004] The variety of products sold in these vending machines is increasing, and users are having difficulty selecting the product they wish to purchase from among those sold.

[0005] Accordingly, it is becoming very important to provide optimized product recommendation services to users who wish to purchase products stored in the vending machine through the kiosk.

[0006] Therefore, as there is an increasing demand for technology that recommends suitable products tailored to users, thereby reducing product selection time and improving purchase conversion rates, the development of related technology is required. Prior art literature

[0008] Korean Published Patent No. 10-2024-0117674, Korean Published Patent No. 10-2024-0068847, Korean Published Patent No. 10-2023-0050811, Korean Published Patent No. 10-2022-0116764 The problem to be solved

[0009] According to one embodiment, the purpose is to provide a method, device, and system for adjusting the standard quantity of stock replenishment linked to a kiosk using the expiration date, peak season period, and the rate of increase or decrease in the number of SNS posts.

[0010] The objectives of the present invention are not limited to those mentioned above, and other unmentioned objectives will be clearly understood from the description below. means of solving the problem

[0012] According to one embodiment, a method for adjusting the standard quantity of inventory linked to a kiosk using an expiration date, a peak season period, and a rate of increase or decrease in the number of SNS posts, performed by a device, comprises: a step of obtaining the first identification information from the first kiosk when it is confirmed that the first identification information, which is identification information for identifying a first user at a first time point, is recognized by the first kiosk; a step of identifying a user using the first kiosk as the first user based on the first identification information; a step of selecting a product expected to be purchased by the first user as a recommended product based on the purchase history of the first user and the inventory information of a first vending machine connected to the first kiosk; a step of controlling the display of recommendation information for the first product on the screen of the first kiosk when the first product is selected as the recommended product; and a step of performing payment for the price of the first product through a pre-registered payment method of the first user when it is recognized that the first user has taken the first product from among the products stored in the first vending machine.

[0013] The step of selecting a product expected to be purchased by the first user as a recommended product comprises: a step of classifying a product confirmed to have been purchased by the first user as a first candidate product; a step of verifying the number of purchases by the first user for each product classified as a first candidate product; a step of assigning a higher first score within a preset first score range to each product classified as a first candidate product as the number of purchases by the first user increases; a step of verifying the time of the first user's recent purchase for each product classified as a first candidate product; a step of analyzing the first user's purchase pattern for each product classified as a first candidate product; a step of predicting an expected purchase time for each product classified as a first candidate product based on the time of the first user's recent purchase and the first user's purchase pattern; a step of calculating the difference between the first time point and the expected purchase time as a difference in days for each product classified as a first candidate product; and a step of assigning a higher second score within a preset second score range as the difference in days is shorter for each product classified as a first candidate product. A step of calculating a total score by summing the first score and the second score for each of the products classified as the first candidate products; a step of classifying products among the first candidate products that are confirmed to have a total score higher than a preset reference score as second candidate products; a step of checking the inventory amount stored in the first vending machine at the first time point for each of the products classified as second candidate products; a step of classifying products among the second candidate products that are confirmed to have an inventory amount stored in the first vending machine at the first time point greater than a preset first reference amount as third candidate products;and may include the step of selecting the product classified as the third candidate product as the recommended product.;

[0014] A kiosk-linked personalized product recommendation and order processing method based on the analysis results of the above user data comprises: a step of confirming that the total score of the first product has been calculated as the first total score after the step of calculating the total score; a step of classifying users confirmed to have used the first kiosk among all users into a first user group; a step of classifying users confirmed to have the same gender and age group as the first user among the users classified into the first user group into a second user group; a step of classifying users confirmed to have recommended the first product among the users classified into the second user group into a third user group; a step of classifying users confirmed to have purchased the first product through a recommendation among the users classified into the third user group into a fourth user group; and a step of classifying users confirmed to have recommended the first product but not purchased the first product among the users classified into the third user group into a fifth user group. A step of identifying the number of users classified into the third user group as the first number, identifying the number of users classified into the fourth user group as the second number, and identifying the number of users classified into the fifth user group as the third number; a step of calculating a first ratio by dividing the second number by the first number, and calculating a second ratio by dividing the third number by the first number; a step of, if the first ratio is confirmed to be higher than a preset first standard ratio, setting a first weighted score to a higher score within a preset third score range as the first ratio increases; and a step of adjusting the first total score by adding the first total score and the first weighted score.If it is confirmed that the second ratio is higher than a preset second reference ratio, the higher the second ratio, the higher the second weighted score is set to a higher score within a preset fourth score range; and the method may further include the step of adjusting the first total score to the value obtained by subtracting the second weighted score from the first total score.;

[0015] A kiosk-linked personalized product recommendation and order processing method based on the analysis results of the above user data comprises: a step of, after performing payment for the price of the above first product, confirming the inventory quantity of the above first product stored in the above first vending machine at a second time point as a first quantity based on the inventory information of the above first vending machine; a step of setting a time point prior to a preset reference period from the above second time point as a third time point, setting a time point prior to the above reference period from the above third time point as a fourth time point, and setting a time point after the above reference period from the above second time point as a fifth time point; a step of setting the period from the above fourth time point to the above third time point as a first period, setting the period from the above third time point to the above second time point as a second period, and setting the period from the above second time point to the above fifth time point as a third period; and a step of confirming the sales quantity of the above first product sold at the above first vending machine during the first period as a second quantity based on the sales history of the above first vending machine, and confirming the sales quantity of the above first product sold at the above first vending machine during the above second period as a third quantity. A step of analyzing the sales volume fluctuation trend of the first product by comparing the second quantity and the third quantity; a step of predicting the quantity of the first product expected to be sold at the first vending machine during the third period as a fourth quantity based on the results of analyzing the sales volume fluctuation trend of the first product; a step of classifying users confirmed to have purchased the first product during the first period among the users classified into the fourth user group into a sixth user group; a step of classifying users confirmed to have purchased the first product during the second period among the users classified into the fourth user group into a seventh user group; a step of confirming the number of users classified into the sixth user group as a fourth number and confirming the number of users classified into the seventh user group as a fifth number;The method may further include the step of calculating a first increase / decrease rate by subtracting the fourth number from the fifth number and dividing by the fourth number; the step of setting a first weight to a higher value within a preset first numerical range as the first increase / decrease rate increases; the step of calculating a second reference quantity by multiplying the fourth quantity by the first weight; the step of calculating a fifth quantity by subtracting the first quantity from the second reference quantity if it is confirmed that the first quantity is less than the second reference quantity; and the step of transmitting a notification message to a first manager terminal indicating that the first product of the fifth quantity needs to be stocked in the first vending machine.

[0016] A kiosk-linked personalized product recommendation and order processing method based on the analysis results of the above user data comprises: a step of confirming that the consumption period of the above first product is set from the manufacturing date to after the fourth period, after the step of calculating the above second standard amount; a step of confirming the number of days in the above fourth period as the first number of days; a step of setting a second weight to a higher value within a preset second numerical range as the longer the first number of days; a step of setting a peak period that has a favorable effect on the sales of the above first product within the above third period as the third-1 period; a step of confirming the number of days in the above third period as the second number of days and confirming the number of days in the above third-1 period as the third number of days; a step of calculating a third ratio as the value obtained by dividing the above third number of days by the above second number of days; a step of setting a third weight to a higher value within a preset third numerical range as the higher the third ratio; and a step of collecting and obtaining a first post classified as a post of the above first product among posts uploaded to SNS via crawling, according to the upload period. The method may further include the steps of: classifying the first post uploaded during the first period into a first post group and classifying the first post uploaded during the second period into a second post group; setting the number of posts classified into the first post group as the first post number and setting the number of posts classified into the second post group as the second post number; calculating a second increase / decrease rate by subtracting the first post number from the second post number and dividing by the first post number; setting a fourth weight to a higher value within a preset fourth numerical range as the second increase / decrease rate increases; and adjusting the second reference amount by the value obtained by multiplying the second reference amount, the second weight, the third weight, and the fourth weight.

[0017] According to another embodiment, a kiosk-linked personalized product recommendation and order processing device based on the analysis results of user data is provided, comprising: an information acquisition unit that acquires the first identification information from the first kiosk when it is confirmed that the first identification information, which is identification information for identifying a first user at a first time, is recognized by the first kiosk; a user identification unit that identifies a user using the first kiosk as the first user based on the first identification information; a recommended product selection unit that selects a product expected to be purchased by the first user as a recommended product based on the purchase history of the first user and the inventory information of a first vending machine connected to the first kiosk; an information display unit that controls the display of recommendation information for the first product on the screen of the first kiosk when the first product is selected as the recommended product; and a payment execution unit that performs payment for the price of the first product through a pre-registered payment means of the first user when it is recognized that the first user has taken the first product from among the products stored in the first vending machine.

[0018] The above recommended product selection unit classifies a product confirmed to have been purchased by the first user as a first candidate product, checks the number of purchases by the first user for each product classified as a first candidate product, assigns a higher first score within a preset first score range as the number of purchases by the first user increases for each product classified as a first candidate product, checks the time of the first user's recent purchase for each product classified as a first candidate product, analyzes the purchase pattern of the first user for each product classified as a first candidate product, predicts an expected purchase time based on the time of the first user's recent purchase and the purchase pattern for each product classified as a first candidate product, calculates the difference between the first time point and the expected purchase time point as a difference in days for each product classified as a first candidate product, assigns a higher second score within a preset second score range as the difference in days is shorter for each product classified as a first candidate product, and for each product classified as a first candidate product, the first score and the The second score is summed to calculate the total score, and among the products classified as the first candidate products, the products confirmed to have a total score higher than a preset standard score are classified as second candidate products, and for each of the products classified as second candidate products, the inventory quantity stored in the first vending machine at the first time is checked, and among the products classified as second candidate products, the products confirmed to have an inventory quantity stored in the first vending machine at the first time is greater than a preset first standard quantity are classified as third candidate products, and the products classified as third candidate products can be selected as recommended products.

[0019] The above recommended product selection unit confirms that the total score of the above first product has been calculated as the first total score, classifies users confirmed to have used the above first kiosk among all users into a first user group, classifies users confirmed to have the same gender and age group as the above first user among the users classified in the first user group into a second user group, classifies users confirmed to have recommended the above first product among the users classified in the second user group into a third user group, classifies users confirmed to have purchased the above first product through a recommendation among the users classified in the third user group into a fourth user group, classifies users confirmed to have recommended the above first product but not purchased the above first product among the users classified in the third user group into a fifth user group, confirms the number of users classified in the above third user group as the first number, confirms the number of users classified in the above fourth user group as the second number, confirms the number of users classified in the above fifth user group as the third number, and the above second number is the A first ratio is calculated by dividing the first number of people, and a second ratio is calculated by dividing the third number of people by the first number of people. If it is confirmed that the first ratio is higher than a preset first standard ratio, the first weighted score is set to a higher score within a preset third score range as the first ratio is higher, and the first total score is adjusted by adding the first total score and the first weighted score. If it is confirmed that the second ratio is higher than a preset second standard ratio, the second weighted score is set to a higher score within a preset fourth score range as the second ratio is higher, and the first total score can be adjusted by subtracting the second weighted score from the first total score.

[0020] Based on the analysis results of the user data above, the kiosk-linked personalized product recommendation and order processing device further includes an inventory management unit, wherein the inventory management unit, based on the inventory information of the first vending machine, identifies the inventory quantity of the first product stored in the first vending machine at a second time point as a first quantity, sets a time point prior to a preset reference period from the second time point as a third time point, sets a time point prior to the reference period from the third time point as a fourth time point, sets a time point after the reference period from the second time point as a fifth time point, sets the period from the fourth time point to the third time point as a first period, sets the period from the third time point to the second time point as a second period, sets the period from the second time point to the fifth time point as a third period, and based on the sales history of the first vending machine, identifies the sales quantity of the first product sold at the first vending machine during the first period as a second quantity, identifies the sales quantity of the first product sold at the first vending machine during the second period as a third quantity, compares the second quantity and the third quantity, and [determines] the first product Analyze the sales volume fluctuation trend, and based on the results of analyzing the sales volume fluctuation trend of the first product, predict the quantity of the first product expected to be sold at the first vending machine during the third period as the fourth quantity; among the users classified into the fourth user group, users confirmed to have purchased the first product during the first period are classified into the sixth user group; among the users classified into the fourth user group, users confirmed to have purchased the first product during the second period are classified into the seventh user group; confirm the number of users classified into the sixth user group as the fourth number; confirm the number of users classified into the seventh user group as the fifth number; and after subtracting the fourth number from the fifth number,A first increase / decrease rate is calculated by dividing by the value of the fourth number above, and the higher the first increase / decrease rate, the higher the first weight is set within a preset first numerical range, a second reference quantity is calculated by multiplying the fourth quantity by the first weight, and if it is confirmed that the first quantity is less than the second reference quantity, a fifth quantity is calculated by subtracting the first quantity from the second reference quantity, and a notification message indicating that the first product of the fifth quantity needs to be stocked in the first vending machine can be transmitted to the first manager terminal.

[0021] The above inventory management department confirms that the consumption period of the above first product is set from the manufacturing date to after the fourth period, confirms the number of days in the above fourth period as the first day, sets a second weight to a higher value within a preset second numerical range as the longer the first day, sets the peak period that has a favorable effect on the sales of the above first product within the above third period as the third-1 period, confirms the number of days in the above third period as the second day, confirms the number of days in the above third-1 period as the third day, calculates a third ratio as the value obtained by dividing the above third day by the above second day, and sets a third weight to a higher value within a preset third numerical range as the higher the third ratio, collects and obtains first posts classified as posts of the above first product among posts uploaded to SNS through crawling according to the upload period, classifies the above first posts uploaded during the above first period into a first post group, classifies the above first posts uploaded during the above second period into a second post group, and the posts classified into the above first post group A number is set as the first number of posts, the number of posts classified into the second post group is set as the second number of posts, a second increase / decrease rate is calculated by subtracting the first number of posts from the second number of posts and dividing by the first number of posts, and the higher the second increase / decrease rate, the higher the fourth weight is set within a preset fourth numerical range, and the second reference amount can be adjusted by multiplying the second reference amount, the second weight, the third weight, and the fourth weight.

[0022] According to another embodiment, in a kiosk-linked personalized product recommendation and order processing system based on the analysis results of user data, a plurality of kiosks; a plurality of vending machines; a plurality of administrator terminals; A kiosk-linked personalized product recommendation and order processing system based on the analysis results of user data is provided, comprising a device and a device, wherein when it is confirmed that first identification information, which is identification information for identifying a first user at a first time, is recognized by a first kiosk that is one of the plurality of kiosks, the device acquires the first identification information from the first kiosk, identifies a user using the first kiosk as the first user based on the first identification information, selects a product expected to be purchased by the first user as a recommended product based on the purchase history of the first user and inventory information of a first vending machine connected to the first kiosk, controls the display of recommendation information for the first product on the screen of the first kiosk when the first product is selected as the recommended product, and performs payment for the price of the first product through a pre-registered payment method of the first user when it is recognized that the first user has taken the first product from among the products stored in the first vending machine.

[0023] The device classifies a product confirmed to have been purchased by the first user as a first candidate product, checks the number of purchases by the first user for each product classified as a first candidate product, assigns a higher first score within a preset first score range to each product classified as a first candidate product as the number of purchases by the first user increases, checks the time of the first user's recent purchase for each product classified as a first candidate product, analyzes the purchase pattern of the first user for each product classified as a first candidate product, predicts an expected purchase time based on the time of the first user's recent purchase and the purchase pattern for each product classified as a first candidate product, calculates the difference between the first time point and the expected purchase time point as a difference in days for each product classified as a first candidate product, assigns a higher second score within a preset second score range as the difference in days is shorter for each product classified as a first candidate product, and for each product classified as a first candidate product, the first score and the second score A total score is calculated by summing the results, and among the products classified as the first candidate products, products confirmed to have a total score higher than a preset standard score are classified as second candidate products, and for each of the products classified as second candidate products, the inventory quantity stored in the first vending machine at the first time is checked, and among the products classified as second candidate products, products confirmed to have an inventory quantity stored in the first vending machine at the first time is greater than a preset first standard quantity are classified as third candidate products, and the products classified as third candidate products can be selected as recommended products.

[0024] The above device confirms that the total score of the first product is calculated as the first total score, classifies users confirmed to have used the first kiosk among all users into a first user group, classifies users confirmed to have the same gender and age group as the first user among the users classified into the first user group into a second user group, classifies users confirmed to have recommended the first product among the users classified into the second user group into a third user group, classifies users confirmed to have purchased the first product through a recommendation among the users classified into the third user group into a fourth user group, classifies users confirmed to have recommended the first product but not purchased the first product among the users classified into the third user group into a fifth user group, confirms the number of users classified into the third user group as the first number, confirms the number of users classified into the fourth user group as the second number, confirms the number of users classified into the fifth user group as the third number, and the second number is the first A first ratio is calculated by dividing the third number by the first number, and a second ratio is calculated by dividing the third number by the first number. If it is confirmed that the first ratio is higher than a preset first standard ratio, the first weighted score is set to a higher score within a preset third score range as the first ratio is higher, and the first total score is adjusted by adding the first total score and the first weighted score. If it is confirmed that the second ratio is higher than a preset second standard ratio, the second weighted score is set to a higher score within a preset fourth score range as the second ratio is higher, and the first total score can be adjusted by subtracting the second weighted score from the first total score.

[0025] The above device, based on the inventory information of the first vending machine, identifies the inventory quantity of the first product stored in the first vending machine at a second time point as a first quantity, sets a time point prior to a preset reference period from the second time point as a third time point, sets a time point prior to the reference period from the third time point as a fourth time point, sets a time point after the reference period from the second time point as a fifth time point, sets the period from the fourth time point to the third time point as a first period, sets the period from the third time point to the second time point as a second period, sets the period from the second time point to the fifth time point as a third period, and based on the sales history of the first vending machine, identifies the sales volume of the first product sold at the first vending machine during the first period as a second quantity, identifies the sales volume of the first product sold at the first vending machine during the second period as a third quantity, compares the second quantity and the third quantity to analyze the sales volume fluctuation trend of the first product, and based on the results of analyzing the sales volume fluctuation trend of the first product, the Predict the quantity of the first product expected to be sold at the first vending machine during the third period as the fourth quantity, classify users among the fourth user group who are confirmed to have purchased the first product during the first period into the sixth user group, classify users among the fourth user group who are confirmed to have purchased the first product during the second period into the seventh user group, identify the number of users classified in the sixth user group as the fourth number, identify the number of users classified in the seventh user group as the fifth number, and calculate the first increase / decrease rate by subtracting the fourth number from the fifth number and dividing by the fourth number.The higher the first increase / decrease rate, the higher the first weight is set within the preset first numerical range, the second reference quantity is calculated by multiplying the fourth quantity by the first weight, and if it is confirmed that the first quantity is less than the second reference quantity, the fifth quantity is calculated by subtracting the first quantity from the second reference quantity, and a notification message indicating that the first product of the fifth quantity needs to be stocked in the first vending machine can be sent to the first manager terminal.

[0026] The above device confirms that the consumption period of the first product is set from the manufacturing date to a fourth period later, identifies the number of days in the fourth period as the first day, sets a second weight to a higher value within a preset second numerical range as the longer the first day, sets the peak period that has a favorable effect on the sales of the first product within the third period as the third-1 period, identifies the number of days in the third period as the second day, identifies the number of days in the third-1 period as the third day, calculates a third ratio by the value obtained by dividing the third day by the second day, sets a third weight to a higher value within a preset third numerical range as the higher the third ratio, collects and obtains first posts classified as posts of the first product among posts uploaded to SNS via crawling according to the upload period, classifies the first posts uploaded during the first period into a first post group, classifies the first posts uploaded during the second period into a second post group, and the number of posts classified into the first post group A first number of posts is set, the number of posts classified into the second post group is set as the second number of posts, a second increase / decrease rate is calculated by subtracting the first number of posts from the second number of posts and dividing by the first number of posts, and the higher the second increase / decrease rate, the higher the fourth weight is set within a preset fourth numerical range, and the second reference amount can be adjusted by multiplying the second reference amount, the second weight, the third weight, and the fourth weight. Effects of the invention

[0028] According to one embodiment, by supporting a standard quantity adjustment that reflects the expiration date, peak season, and the rate of increase or decrease in the number of social media posts, based on sales volume fluctuation trends and the rate of increase or decrease in the number of recommended purchasing users, it is possible to replenish inventory while considering product shelf life, seasonal demand, and changes in online interest, thereby having the effect of reducing the risk of inventory shortage and disposal.

[0029] Meanwhile, the effects according to the embodiments are not limited to those mentioned above, and other unmentioned effects will be clearly understood by those skilled in the art from the description below. Brief explanation of the drawing

[0031] FIG. 1 is a schematic diagram showing the configuration of a system according to one embodiment. FIG. 2 is a flowchart for explaining the process of kiosk-linked personalized product recommendation and order processing based on the analysis results of user data according to one embodiment. FIGS. 3 and 4 are flowcharts for explaining the process of selecting a recommended product according to one embodiment. FIGS. 5 and 6 are flowcharts for explaining the process of adjusting the total score of a product through the purchase history of other users according to one embodiment. FIGS. 7 and 8 are flowcharts for explaining the process of managing product inventory through sales volume fluctuation trends according to one embodiment. FIG. 9 is a flowchart for explaining the process of adjusting the second standard amount by considering the consumption period, peak season, and number of posts according to one embodiment. FIG. 10 is a flowchart for explaining a kiosk-linked personalized product recommendation and order processing process based on the analysis results of user data according to another embodiment. FIG. 11 is a flowchart for explaining the process of controlling the product recommendation information to be divided and displayed by distinguishing the information display area through the total score of the product according to one embodiment. FIG. 12 is a flowchart for explaining the kiosk-linked personalized product recommendation and order processing process based on the analysis results of user data according to another embodiment. FIG. 13 is a flowchart for explaining the process of controlling product recommendation information to be displayed sequentially by setting the information display order and information display time through the total score of the product according to one embodiment. FIG. 14 is a flowchart illustrating a process for controlling the display of recommendation information for a selected product based on the user's mood state according to one embodiment. FIG. 15 is a flowchart illustrating the process of setting the minimum stock quantity according to the number of active people in one embodiment. FIGS. 16 to 17 are flowcharts for explaining the process of displaying product advertisements according to inventory quantity and manufacturing date according to one embodiment. FIG. 18 is a schematic diagram showing the configuration of a device according to one embodiment. Specific details for implementing the invention

[0032] Hereinafter, embodiments are described in detail with reference to the attached drawings. However, various modifications may be made to the embodiments, and thus the scope of the patent application is not limited or restricted by these embodiments. It should be understood that all modifications, equivalents, and substitutions to the embodiments are included within the scope of the rights.

[0033] Specific structural or functional descriptions of the embodiments are disclosed for illustrative purposes only and may be modified and implemented in various forms. Accordingly, the embodiments are not limited to the specific disclosed forms, and the scope of this specification includes modifications, equivalents, or substitutions that fall within the technical concept.

[0034] Terms such as "first" or "second" may be used to describe various components, but these terms should be interpreted solely for the purpose of distinguishing one component from another. For example, the first component may be named the second component, and similarly, the second component may be named the first component.

[0035] When it is stated that a component is "connected" to another component, it should be understood that it may be directly connected to or coupled with that other component, or that there may be other components in between.

[0036] The terms used in the embodiments are for illustrative purposes only and should not be interpreted as intended to be limiting. Singular expressions include plural expressions unless the context clearly indicates otherwise. In this specification, terms such as "comprising" or "having" are intended to indicate the existence of the features, numbers, steps, actions, components, parts, or combinations thereof described in the specification, and should be understood as not precluding the existence or addition of one or more other features, numbers, steps, actions, components, parts, or combinations thereof.

[0037] Unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as generally understood by those skilled in the art to which the embodiments pertain. Terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant technology, and should not be interpreted in an ideal or overly formal sense unless explicitly defined in this application.

[0038] In addition, when describing with reference to the attached drawings, identical components are assigned the same reference numeral regardless of drawing symbols, and redundant descriptions thereof are omitted. In describing the embodiments, if it is determined that a detailed description of related prior art could unnecessarily obscure the essence of the embodiments, such detailed description is omitted.

[0039] The embodiments can be implemented in various forms of products such as personal computers, laptop computers, tablet computers, smartphones, televisions, smart home appliances, intelligent automobiles, kiosks, and wearable devices.

[0040] FIG. 1 is a schematic diagram showing the configuration of a system according to one embodiment.

[0041] Referring to FIG. 1, a system according to one embodiment may include a plurality of kiosks (100), a plurality of vending machines (200), a plurality of administrator terminals (300), and a device (400) that can communicate with each other through a communication network.

[0042] First, the communication network can be configured regardless of the mode of communication, such as wired or wireless, and can be implemented in various forms to enable communication between servers and between servers and terminals.

[0043] Each of the multiple kiosks (100) may be implemented to include a body that stands on the ground, a touchscreen, a speaker, an RFID reader, a barcode / QR scanner, a credit card reader, etc., and may also be configured to include additional basic components necessary for operating the kiosk.

[0044] A plurality of kiosks (100) may be installed separately by zone, and may include, for example, a first kiosk (110) installed in a first zone among the plurality of zones, a second kiosk (120) installed in a second zone among the plurality of zones, etc.

[0045] Multiple kiosks (100) may be configured to perform all or part of the computational functions, storage / reference functions, input / output functions, and control functions that a conventional computer has.

[0046] A plurality of kiosks (100) may be configured to communicate with the device (400) via wired or wireless means and may operate by means of a control signal received from the device (400).

[0047] Multiple vending machines (200) may be configured to display products for sale and include additional separate spaces for storing each product being sold.

[0048] Each of the multiple vending machines (200) can be divided into multiple compartments to separate the space. For example, if the first vending machine (210) is divided into a first compartment and a second compartment, the first product can be displayed in the first compartment and the second product can be displayed in the second compartment.

[0049] Each of the multiple vending machines (200) may be equipped with a door that opens and closes multiple compartments. For example, if a first door that opens and closes a first compartment and a second door that opens and closes a second compartment are installed in the first vending machine (210), the first door and the second door may be implemented through a transparent or translucent window so that the products placed inside the first vending machine (210) can be visually inspected from the outside. In this case, the first door and the second door are provided on the front of the first vending machine (210) and perform the function of opening and closing the space of the first compartment and the second compartment in a pivotal or sliding manner. The first door and the second door are normally kept in a locked state, but when a user is identified, the lock is released and they can be opened.

[0050] Each of the multiple vending machines (200) can maintain the locking state of the first door and the second door until a user is identified through each of the multiple kiosks (100) to prevent the user from taking the product without authorization.

[0051] Multiple vending machines (200) may be configured to perform all or part of the computational function, storage / reference function, input / output function, and control function that a conventional computer has.

[0052] Multiple vending machines (200) may be configured to communicate with the device (400) via wired or wireless means and may operate by means of a control signal received from the device (400).

[0053] Multiple kiosks (100) and multiple vending machines (200) can be physically connected to each other and installed in each zone. For example, a first kiosk (110) and a first vending machine (210) can be connected to each other and installed together in a first zone, and a second kiosk (120) and a second vending machine (220) can be connected to each other and installed together in a second zone.

[0054] That is, a plurality of kiosks (100) are devices operated for purchasing products, and a plurality of vending machines (200) are devices for storing products for sale, and products stored in the first vending machine (210) can be purchased through the operation of the first kiosk (110), and products stored in the second vending machine (220) can be purchased through the operation of the second kiosk (120).

[0055] A plurality of manager terminals (300) are terminals used by managers who manage kiosks and vending machines, and in the case where a first manager manages a first kiosk (110) and a first vending machine (210) and a second manager manages a second kiosk (120) and a second vending machine (220), the first manager terminal (310) used by the first manager, the second manager terminal (320) used by the second manager, etc. may be included.

[0056] Each of the plurality of administrator terminals (300) may be configured to perform all or part of the computational functions, storage / reference functions, input / output functions, communication functions, and control functions that a conventional computer has. The plurality of administrator terminals (300) may be configured to communicate wirelessly with the device (400).

[0057] Multiple administrator terminals (300) may be connected to a web page operated by a person or organization providing a service using the device (400), or may have an application developed and distributed by a person or organization providing a service using the device (400) installed.

[0058] That is, multiple administrator terminals (300) can be linked with the device (400) through a web page or application, and can access the device (400) through a web page, application, etc. provided by the device (400).

[0059] For convenience of explanation, the operation of the first kiosk (110), the first vending machine (210), and the first manager terminal (310) will be described below, but the operation of the first kiosk (110) can be performed in place of another kiosk such as the second kiosk (120), the operation of the first vending machine (210) can be performed in place of another vending machine such as the second vending machine (220), and the operation of the first manager terminal (310) can be performed in place of another manager terminal such as the second manager terminal (320).

[0060] The device (400) may be a private server owned by a person or organization providing a service using the device (400), a cloud server, or a peer-to-peer (P2P) set of distributed nodes. The device (400) may be configured to perform all or part of the computational functions, storage / reference functions, input / output functions, and control functions that a conventional computer possesses.

[0061] The device (400) can be configured to communicate with a plurality of kiosks (100) via wired or wireless means, control the operation of each of the plurality of kiosks (100), and control which information to display on the screen of each of the plurality of kiosks (100).

[0062] The device (400) may be configured to communicate with a plurality of vending machines (200) via wired or wireless means, control the operation of each of the plurality of vending machines (200), and support the management of products stored in each of the plurality of vending machines (200).

[0063] The device (400) may be configured to communicate wirelessly or via wired connection with a plurality of administrator terminals (300), control the operation of each of the plurality of administrator terminals (300), and control which information to display on the screen of each of the plurality of administrator terminals (300).

[0064] The device (400) is implemented as a server that recommends personalized products in conjunction with a kiosk based on the analysis results of user data, and can provide a platform service for product recommendation.

[0065] Meanwhile, for convenience of explanation, only the first kiosk (110) and the second kiosk (120) among the plurality of kiosks (100), only the first vending machine (210) and the second vending machine (220) among the plurality of vending machines (200), and only the first administrator terminal (310) and the second administrator terminal (320) among the plurality of administrator terminals (300) are shown in FIG. 1, but the number of kiosks, the number of vending machines, the number of administrator terminals, etc. can vary depending on the embodiment. As long as the processing capacity of the device (400) allows, there are no special limitations on the number of kiosks, the number of vending machines, the number of administrator terminals, etc.

[0066] FIG. 2 is a flowchart for explaining the process of kiosk-linked personalized product recommendation and order processing based on the analysis results of user data according to one embodiment.

[0067] Referring to FIG. 2, first, in step S201, if the device (400) confirms that the first identification information is recognized by the first kiosk (110) at a first time, it can obtain the first identification information from the first kiosk (110). Here, the first identification information is identification information for identifying the first user, and can be used to identify the first user by being recognized by the reader of the first kiosk (110) through an employee ID card, credit card, fingerprint, facial recognition, ID number, etc.

[0068] For example, when a first user’s ID card with an RFID tag attached is placed against a reader provided in the first kiosk (110), the first kiosk (110) can recognize first identification information through the RFID attached to the first user’s ID card, and the device (400) can obtain the recognized first identification information from the first kiosk (110).

[0069] In step S202, the device (400) can identify a user using the first kiosk (110) as the first user based on the first identification information. To this end, the first identification information includes identification information capable of identifying the first user, and the device (400) can identify a user who intends to purchase a product displayed in the first vending machine (210) through the first kiosk (110) as the first user based on the first identification information.

[0070] In step S203, the device (400) can select a product expected to be purchased by the first user as a recommended product based on the first user's purchase history and the inventory information of the first vending machine (210). To this end, the database of the device (400) stores purchase history categorized by user and inventory information categorized by vending machine. When the user using the first kiosk (110) is identified as the first user, the device (400) queries the information stored in the database to obtain the first user's purchase history and the first vending machine (210) inventory information, respectively. Then, based on the obtained purchase history and inventory information of the first user, the device can predict which product the first user will purchase and select the expected product as a recommended product.

[0071] According to one embodiment, the purchase history is information accumulated from purchase information made by a user, and may be composed of a list indicating which product was purchased at which kiosk and in what quantity at what time, and may include information such as product name, purchase date, place of purchase, and quantity purchased.

[0072] According to one embodiment, inventory information is information indicating the inventory status of products displayed or stored in a vending machine, and may include information such as product name, manufacturing date, and inventory quantity. Even if the products are the same, if the manufacturing dates differ, they may be managed separately by manufacturing date.

[0073] When selecting recommended products, the device (400) may select one or more products as recommended products, analyze which products the first user has purchased and how often, and analyze which products are stored in the first vending machine (210) and how much of each product is stored, and then select recommended products for the first user based on the analysis results, and a detailed explanation related thereto will be described later with reference to FIGS. 3 and 4.

[0074] In step S204, the device (400) can control the display of recommendation information for the first product on the screen of the first kiosk (110) when the first product is selected as a recommended product. Here, the recommendation information for the first product may include information such as a notification message recommending the first product to the first user, the name of the first product, a representative image of the first product, and the price of the first product.

[0075] When the device (400) controls the display of recommendation information for the first product on the screen of the first kiosk (110), it can control the display of recommendation information for a selected product by taking into account the user's mood state, and a detailed explanation related thereto will be described later with reference to FIG. 14.

[0076] In step S205, when the device (400) recognizes that the first user has taken the first product from among the products stored in the first vending machine (210), it can perform payment for the price of the first product through the first user's payment method. To this end, the first user's payment method may be registered in advance when the service user signs up, and account information classified by user is stored in the database of the device (400). The device (400) can query the information stored in the database to obtain the first user account information, verify the first user's payment method based on the first user account information, and perform payment for the price of the first product through the first user's payment method.

[0077] In order to recognize that the first user has taken the first product from among the products stored in the first vending machine (210), the device (400) can check the images, weights, sensing information, etc. of the products displayed before the opening of the door provided in the first vending machine (210) to check the type and quantity of the products displayed in the first vending machine (210) before the opening of the door, and can check the images, weights, sensing information, etc. of the products displayed after the closing of the door to check the type and quantity of the products displayed in the first vending machine (210) after the closing of the door.

[0078] Subsequently, the device (400) compares the products displayed before the opening of the door provided in the first vending machine (210) with the products displayed after the closing of the door, and identifies the type and quantity of products that disappeared from the first vending machine (210) while the door is open, and can recognize the type and quantity of products that disappeared from the first vending machine (210) as the type and quantity of products taken by the first user. At this time, in the process of identifying the type and quantity of products that disappeared from the first vending machine (210) while the door is open, video footage capturing the interior of the first vending machine (210) in real time, changes in the weight of products displayed inside the first vending machine (210), and sensing information detected through sensors installed in each zone of the first vending machine (210) can be utilized, and in addition, the type and quantity of products that disappeared from the first vending machine (210) can be identified through various known technologies.

[0079] FIGS. 3 and 4 are flowcharts for explaining the process of selecting a recommended product according to one embodiment.

[0080] Referring to FIGS. 3 and 4, first, in step S301, the device (400) can classify a product confirmed to have been purchased by the first user as a first candidate product.

[0081] That is, the device (400) can determine which product the first user has purchased based on the first user's purchase history, and classify the product confirmed to have been purchased by the first user as the first candidate product.

[0082] In step S302, the device (400) can check the number of purchases made by the first user for each product classified as the first candidate product.

[0083] For example, if the first product is classified as the first candidate product, the device (400) can determine how many times the first user has purchased the first product based on the first user's purchase history, and if it is confirmed that the first user has purchased the first product 3 times, the number of times the first user has purchased the first product can be determined as 3 times.

[0084] In step S303, the device (400) may assign a higher first score within a first score range to each product classified as a first candidate product as the number of purchases by the first user increases. Here, the first score range may be set differently depending on the embodiment, for example, to a range of 0 to 100 points.

[0085] For example, if the first product is classified as the first candidate product, the device (400) may assign a first score of 10 points to the first product if it is confirmed that the first user's purchase count for the first product is 1 time, and may assign a first score of 20 points to the first product if it is confirmed that the first user's purchase count for the first product is 2 times.

[0086] In step S304, the device (400) can determine the time of the first user's recent purchase for each product classified as a first candidate product.

[0087] For example, if the first product is classified as the first candidate product, the device (400) can determine, based on the first user's purchase history, when the first user purchased the first product, and if it is confirmed that the first user purchased the first product on January 1, January 11, and January 21, respectively, the first user's most recent purchase date for the first product can be determined as January 21.

[0088] In step S305, the device (400) can analyze the purchasing pattern of the first user for each product classified as the first candidate product.

[0089] For example, if the first product is classified as the first candidate product, the device (400) can determine at what time the first user purchased the first product based on the first user's purchase history, and if it is confirmed that the first user purchased the first product on January 1, January 11, and January 21, respectively, the first user's purchase pattern for the first product can be analyzed as purchases at 10-day intervals.

[0090] In step S306, the device (400) can predict the expected time of purchase for each product classified as a first candidate product, based on the first user's recent purchase time and the first user's purchase pattern.

[0091] For example, if the first product is classified as the first candidate product, the device (400) can predict the expected time of purchase for the first product as January 31, which is 10 days after January 21, if the first user's recent purchase time for the first product is confirmed to be January 21 and the first user's purchase pattern for the first product is analyzed as purchases at 10-day intervals.

[0092] In step S307, the device (400) can calculate the difference between the first time point and the expected time point of purchase as the difference in days for each product classified as the first candidate product.

[0093] For example, if the first product is classified as the first candidate product, the device (400) can determine the difference between January 25 and January 31 and calculate the difference in days for the first product as 6 days, if the first time point is confirmed as January 25 and the expected time point for purchasing the first product is predicted as January 31.

[0094] In step S308, the device (400) may assign a second score within a second score range higher for each product classified as a first candidate product, as the difference in days is shorter. Here, the second score range may be set differently depending on the embodiment, for example, to a range of 0 to 100 points.

[0095] For example, if the first product is classified as the first candidate product, the device (400) may assign a second score of 10 points to the first product if the difference in days for the first product is confirmed to be 10 days, and may assign a second score of 20 points to the first product if the difference in days for the first product is confirmed to be 9 days.

[0096] In step S309, the device (400) can calculate a total score by summing the first score and the second score for each product classified as the first candidate product.

[0097] After step S309, in step S401, the device (400) may classify a product among the products classified as first candidate products that is confirmed to have a total score higher than a reference score as a second candidate product. Here, the reference score may be set differently depending on the embodiment, for example, it may be set to 100 points.

[0098] In step S402, the device (400) can check the amount of stock stored in the first vending machine (210) at the first time for each product classified as a second candidate product.

[0099] For example, if the second product is classified as the second candidate product, the device (400) can check the inventory quantity of the first product stored in the first vending machine (210) at the first time based on the inventory information of the first vending machine (210), and if it is confirmed that 5 of the first products are stored, the inventory quantity of the first product stored in the first vending machine (210) can be confirmed as 5.

[0100] In step S403, the device (400) may classify a product among the products classified as second candidate products as a third candidate product if it is confirmed that the inventory amount stored in the first vending machine at the first time is greater than the first reference amount. Here, the first reference amount may be set differently depending on the embodiment, for example, it may be set to 10.

[0101] In step S404, the device (400) can select a product classified as a third candidate product as a recommended product.

[0102] The device (400) can select one product as a recommended product when there is only one product classified as a third candidate product, and can select multiple products as recommended products when there are multiple products classified as third candidate products.

[0103] If there are no products classified as third candidate products, the device (400) can adjust the reference score to a lower score and start the process of classifying second candidate products again using the adjusted reference score.

[0104] FIGS. 5 and 6 are flowcharts for explaining the process of adjusting the total score of a product through the purchase history of other users according to one embodiment.

[0105] According to one embodiment, each step illustrated in FIGS. 5 to 6 can be performed between step S309 and step S401.

[0106] Referring to FIGS. 5 and 6, first, in step S501, the device (400) can confirm that the total score of the first product is calculated as the first total score.

[0107] That is, the device (400) can confirm that for each product classified as a first candidate product, the total score is calculated by summing the first score and the second score, and the total score is calculated as the first total score.

[0108] In step S502, the device (400) can classify users among all users who have been identified as having used the first kiosk (110) into a first user group.

[0109] That is, the device (400) can classify users among all users who have used the first kiosk (110) based on the purchase history of each user, and then classify users who have used the first kiosk (110) into a first user group.

[0110] In step S503, the device (400) can classify users among those classified into the first user group who are identified as having the same gender and age group as the first user into the second user group.

[0111] That is, the device (400) can determine the gender and age group of the first user based on the account information of the first user, and then determine the gender and age group for each user based on the account information of each user classified into the first user group, and then classify users among the users classified into the first user group who are confirmed to have the same gender and age group as the first user into the second user group.

[0112] In step S504, the device (400) may classify users identified as having recommended the first product among the users classified into the second user group into the third user group. To this end, the database of the device (400) stores recommendation history categorized by user, and the recommendation history is information accumulated by matching recommended products recommended to the user with purchased products purchased by the user. It may be composed of a list indicating which product was recommended and which product was purchased at what point in time, and may include information such as the recommended product name, purchased product name, purchase date, place of purchase, and quantity purchased.

[0113] That is, the device (400) can classify the recommended products for each user based on the recommendation history of each user classified into the second user group, and then classify the users among the users classified into the second user group who are confirmed to have the first product as the recommended product into the third user group.

[0114] In step S505, the device (400) can classify users among the users classified into the third user group who have been confirmed to have purchased the first product through a recommendation of the first product into the fourth user group.

[0115] That is, the device (400) can classify users classified into the third user group into the fourth user group after confirming the recommended products and purchased products for each user based on the recommendation history of each user classified into the third user group, and confirming that the first product is both a recommended product and a purchased product among the users classified into the third user group.

[0116] In step S506, the device (400) can classify users classified into the third user group who have been recommended the first product but have not purchased the first product into the fifth user group.

[0117] That is, the device (400) can classify users classified into the third user group into the fifth user group after confirming the recommended products and purchased products for each user based on the recommendation history of each user classified into the third user group, and among the users classified into the third user group, those users confirmed to have a first product as a recommended product and another product as a purchased product.

[0118] In step S507, the device (400) can identify the number of users classified into the third user group as the first number, identify the number of users classified into the fourth user group as the second number, and identify the number of users classified into the fifth user group as the third number.

[0119] In step S601 after step S507, the device (400) can calculate a first ratio by dividing the second number of people by the first number of people, and calculate a second ratio by dividing the third number of people by the first number of people.

[0120] In step S602, the device (400) can check whether the first ratio is higher than the first reference ratio. Here, the first reference ratio may be set differently depending on the embodiment, for example, to 50%.

[0121] If it is confirmed in step S602 that the first ratio is higher than the first reference ratio, in step S603, the device (400) may set the first weighted score to a higher score within the third score range as the first ratio increases. Here, the third score range may be set differently depending on the embodiment, for example, to a range of 0 to 10 points.

[0122] For example, the device (400) can set the first weighted score to 1 point when the first ratio is confirmed to be 60%, and the first weighted score to 2 points when the first ratio is confirmed to be 70%.

[0123] In step S604, the device (400) can adjust the first total score by adding the first total score and the first weighted score.

[0124] For example, if the device (400) confirms that the first total score is 100 points and the first weighted score is 1 point, it can adjust the first total score from 100 points to 101 points through (100 + 1).

[0125] If it is confirmed in step S602 that the first ratio is not higher than the first reference ratio, in step S605, the device (400) can check whether the second ratio is higher than the second reference ratio. Here, the second reference ratio may be set differently depending on the embodiment, for example, it may be set to 50%.

[0126] If it is confirmed in step S605 that the second ratio is higher than the second reference ratio, in step S606, the device (400) may set the second weighted score to a higher score within the fourth score range as the second ratio increases. Here, the fourth score range may be set differently depending on the embodiment, for example, to a range of 0 to 10 points.

[0127] For example, the device (400) can set the second weighted score to 1 point if the second ratio is confirmed to be 60%, and the second weighted score to 2 points if the second ratio is confirmed to be 70%.

[0128] In step S607, the device (400) can adjust the first total score by subtracting the second weighted score from the first total score.

[0129] For example, if the device (400) confirms that the first total score is 100 points and the second weighted score is 1 point, it can adjust the first total score from 100 points to 99 points through (100 - 1).

[0130] If it is confirmed in step S605 that the second ratio is not higher than the second reference ratio, the device (400) may determine that no adjustment is needed for the first total score.

[0131] FIGS. 7 and 8 are flowcharts for explaining the process of managing product inventory through sales volume fluctuation trends according to one embodiment.

[0132] According to one embodiment, each step illustrated in FIGS. 7 to 8 can be performed after step S205.

[0133] Referring to FIGS. 7 and 8, first, in step S701, the device (400) can determine the inventory quantity of the first product stored in the first vending machine at a second time point as the first quantity based on the inventory information of the first vending machine (210). Here, the second time point may mean a time point after the first product has been sold at the first vending machine (210).

[0134] In step S702, the device (400) may set a point in time prior to the reference period from the second point in time as the third point in time, set a point in time prior to the reference period from the third point in time as the fourth point in time, and set a point in time after the reference period from the second point in time as the fifth point in time. Here, the reference period may be set differently depending on the embodiment, for example, it may be set to one week.

[0135] In step S703, the device (400) can set the first period from the fourth point in time to the third point in time, the second period from the third point in time to the second point in time, and the third period from the second point in time to the fifth point in time.

[0136] That is, the device (400) can set each period in the order of the first period, the second period, and the third period, and at this time, the length of each period can be set to be the same as the reference period.

[0137] In step S704, the device (400) can determine the sales volume of the first product sold at the first vending machine (210) during the first period as the second quantity based on the sales history of the first vending machine (210), and determine the sales volume of the first product sold at the first vending machine (210) during the second period as the third quantity. To do this, the database of the device (400) stores sales history categorized by vending machine, and the device (400) can query the information stored in the database to obtain the sales history of the first vending machine (210), and then determine the second quantity and the third quantity, respectively, based on the sales history of the first vending machine (210).

[0138] According to one embodiment, the sales history is information accumulated from sales data of products sold at a vending machine, and may consist of a list indicating how much of which product was sold by which user at what point in time, and may include information such as product name, date of sale, buyer, and sales volume.

[0139] In step S705, the device (400) can analyze the sales volume fluctuation trend for the first product by comparing the second quantity and the third quantity.

[0140] In step S706, the device (400) can predict the quantity of the first product expected to be sold at the first sales machine (210) during the third period as the fourth quantity based on the results of analyzing the sales volume fluctuation trend of the first product.

[0141] For example, if the device (400) confirms that the second quantity is 100 and the third quantity is 102, it can compare the second quantity and the third quantity, analyze the sales volume fluctuation trend of the first product as maintaining the sales volume, and determine that the sales volume of the first product is maintained from the first period to the second period, and predict the fourth quantity as 101, which is the midpoint between the second quantity and the third quantity.

[0142] Additionally, when the device (400) confirms that the second quantity is 100 and the third quantity is 105, it can compare the second quantity and the third quantity to analyze the sales volume fluctuation trend of the first product as an increase in sales volume and determine that the sales volume of the first product is increasing from the first period to the second period, thereby predicting 110, which is a value greater than the third quantity, as the fourth quantity.

[0143] Additionally, when the device (400) confirms that the second quantity is 100 and the third quantity is 95, it can compare the second quantity and the third quantity, analyze the sales volume fluctuation trend of the first product as a decrease in sales volume, and determine that the sales volume of the first product is decreasing from the first period to the second period, and predict the fourth quantity as 90, which is a value smaller than the third quantity.

[0144] After step S706, in step S801, the device (400) can classify users classified into the fourth user group who have been identified as having purchased the first product during the first period into the sixth user group.

[0145] That is, the device (400) can determine at what time each user purchased the first product based on the purchase history of each user classified into the fourth user group, and then classify users among the users classified into the fourth user group who are confirmed to have purchased the first product during the first period into the sixth user group.

[0146] In step S802, the device (400) can classify users classified into the 4th user group who have been identified as having purchased the 1st product during the 2nd period into the 7th user group.

[0147] That is, the device (400) can determine at what time each user purchased the first product based on the purchase history of each user classified into the fourth user group, and then classify users among the users classified into the fourth user group who are confirmed to have purchased the first product during the second period into the seventh user group.

[0148] In step S803, the device (400) can determine the number of users classified into the 6th user group as the 4th number and the number of users classified into the 7th user group as the 5th number.

[0149] In step S804, the device (400) can calculate a first increase / decrease rate by subtracting the fourth number of people from the fifth number of people and dividing by the fourth number of people. Here, the first increase / decrease rate may mean the increase / decrease rate of the number of users who purchased the first product through the recommendation of the first product from the first period to the second period.

[0150] In step S805, the device (400) may set the first weight to a higher value within the first numerical range as the first increase / decrease rate is higher. Here, the first numerical range may be set differently depending on the embodiment, for example, to a range of 0 to 2.

[0151] For example, if the device (400) confirms that the first increase / decrease rate is -10%, it can set the first weight to 0.9; if it confirms that the first increase / decrease rate is 0%, it can set the first weight to 1; and if it confirms that the first increase / decrease rate is 10%, it can set the first weight to 1.1.

[0152] In step S806, the device (400) can calculate a second reference amount by multiplying the fourth quantity by the first weight.

[0153] In step S807, the device (400) can check whether the first quantity is less than the second reference quantity.

[0154] If it is confirmed in step S807 that the first quantity is less than the second reference quantity, in step S808, the device (400) can calculate the fifth quantity as the value obtained by subtracting the first quantity from the second reference quantity.

[0155] In step S809, the device (400) can send a notification message to the first manager terminal (310) indicating that the first vending machine (210) needs to receive a fifth quantity of the first product.

[0156] FIG. 9 is a flowchart for explaining the process of adjusting the second standard amount by considering the consumption period, peak season, and number of posts according to one embodiment.

[0157] According to one embodiment, each step illustrated in FIG. 9 can be performed between step S806 and step S807.

[0158] Referring to FIG. 9, first, in step S901, the device (400) can confirm that the consumption period of the first product is set from the date of manufacture to the fourth period after. At this time, the device (400) can confirm that the consumption period of the first product is set from the date of manufacture to the fourth period after based on the first product information. Here, the first product information can be obtained from the database of the device (400) or from an external server.

[0159] In step S902, the device (400) can determine the number of days of the fourth period as the number of days of the first period.

[0160] For example, the device (400) can confirm, based on the first product information, that the consumption period of the first product is set to six months after the date of manufacture, and if the fourth period is confirmed to be six months, the first number of days can be confirmed to be 180 days.

[0161] In step S903, the device (400) may set the second weight to a higher value within the second numerical range as the first day length increases. Here, the second numerical range may be set differently depending on the embodiment, for example, to a range of 1 to 2.

[0162] For example, if the device (400) confirms that the first number of days is 30 days, it can set the second weight to 1.1, and if it confirms that the first number of days is 60 days, it can set the second weight to 1.2.

[0163] Meanwhile, in step S904, the device (400) may set a peak period that has a favorable effect on the sales of the first product within the third period as the third-1 period. Here, the peak period may refer to a period that includes schedules that have a positive effect on the sales activities of the first product, such as public holidays, national holidays, school vacations, and vacation seasons. To this end, a peak period is pre-set for each product, and the device (400) may set the peak period for the first product within the third period as the third-1 period.

[0164] In step S905, the device (400) can determine the number of days of the third period as the number of days of the second period and determine the number of days of the third-1 period as the number of days of the third period.

[0165] For example, if the third period is from February 1 to February 10 and the 3-1 period is from February 3 to February 5, the device (400) can determine the second number of days as 10 days and the third number of days as 3 days.

[0166] In step S906, the device (400) can calculate the third ratio as the value obtained by dividing the third number of days by the second number of days.

[0167] In step S907, the device (400) may set the third weight to a higher value within the third numerical range as the third ratio increases. Here, the third numerical range may be set differently depending on the embodiment, for example, to a range of 1 to 2.

[0168] For example, if the device (400) confirms that the third ratio is 10%, it can set the third weight to 1.1, and if it confirms that the third ratio is 20%, it can set the third weight to 1.2.

[0169] Meanwhile, in step S908, the device (400) can collect and obtain the first posts classified as posts of the first product among the posts uploaded to SNS through crawling, according to the upload period. Here, crawling is a technology that collects information publicly available online and includes it as an index of search targets. The device (400) collects posts uploaded to SNS through crawling and can classify and obtain the posts of the first product among the collected posts as the first posts.

[0170] When the device (400) distinguishes a post of the first product among posts uploaded to SNS, it can distinguish a post of the first product through the analysis of text, images, etc.

[0171] For example, the device (400) can identify the post uploaded to the first user's SNS as a post of the first product if, as a result of checking the hashtag registered in the post uploaded to the first user's SNS, it is confirmed that the product name of the first product is included in the hashtag.

[0172] Additionally, the device (400) can identify the post uploaded to the first user's SNS as a post of the first product if, as a result of checking the image included in the post uploaded to the first user's SNS, it recognizes that the first product is present in the image.

[0173] In step S909, the device (400) can classify the first posts uploaded during the first period into the first post group and the first posts uploaded during the second period into the second post group.

[0174] That is, the device (400) can determine the upload time of each post classified as a first post, classify posts among the first posts that are confirmed to have an upload time within a first period as a first post group, and classify posts among the first posts that are confirmed to have an upload time within a second period as a second post group.

[0175] In step S910, the device (400) can set the number of posts classified into a first post group as the first post number and the number of posts classified into a second post group as the second post number.

[0176] In step S911, the device (400) can calculate a second increase / decrease rate by subtracting the first number of posts from the second number of posts and dividing by the first number of posts. Here, the second increase / decrease rate may refer to the increase / decrease rate of the number of posts of the first product uploaded to SNS from the first period to the second period.

[0177] In step S912, the device (400) may set the fourth weight to a higher value within the fourth numerical range as the second increase / decrease rate increases. Here, the fourth numerical range may be set differently depending on the embodiment, for example, to a range of 0 to 2.

[0178] For example, if the device (400) confirms that the second increase / decrease rate is -10%, it can set the fourth weight to 0.9; if it confirms that the second increase / decrease rate is 0%, it can set the fourth weight to 1; and if it confirms that the second increase / decrease rate is 10%, it can set the fourth weight to 1.1.

[0179] When the second weight, the third weight, and the fourth weight are each set through steps S903, S907, and S912, in step S913, the device (400) can adjust the second reference amount by the value obtained by multiplying the second reference amount by the second weight, the third weight, and the fourth weight.

[0180] For example, if the second reference quantity is 100, the second weight is 1.1, the third weight is 1.2, and the fourth weight is 1, the device (400) can adjust the second reference quantity from 100 to 132 through (100 X 1.1 X 1.2 X 1).

[0181] FIG. 10 is a flowchart for explaining a kiosk-linked personalized product recommendation and order processing process based on the analysis results of user data according to another embodiment.

[0182] In explaining the content of Fig. 10, parts that overlap with the content explained with reference to Fig. 2 will be omitted.

[0183] Referring to FIG. 10, first, in step S1001, if the device (400) confirms that the first identification information is recognized by the first kiosk (110) at the first time, it can obtain the first identification information from the first kiosk (110).

[0184] In step S1002, the device (400) can identify a user using the first kiosk (110) as the first user based on the first identification information.

[0185] In step S1003, the device (400) can select a product expected to be purchased by the first user as a recommended product based on the first user's purchase history and the inventory information of the first vending machine (210).

[0186] In step S1004, the device (400) can control the first product and the second product to be divided and displayed on the screen of the first kiosk (110) when the first product and the second product are selected as recommended products. Here, the recommendation information for the first product may include information such as a notification message recommending the first product to the first user, the name of the first product, a representative image of the first product, and the price of the first product, and the recommendation information for the second product may include information such as a notification message recommending the second product to the first user, the name of the second product, a representative image of the second product, and the price of the second product.

[0187] When the device (400) controls the display of recommendation information for the first product and recommendation information for the second product on the screen of the first kiosk (110) by dividing the information display area through the total score of the product, the device can control the display of recommendation information for the product by dividing the information display area, and a detailed explanation related thereto will be described later with reference to FIG. 11.

[0188] In step S1005, when the device (400) recognizes that the first user has taken the first product from among the products stored in the first vending machine (210), it can perform payment for the price of the first product through the first user's payment means.

[0189] FIG. 11 is a flowchart for explaining the process of controlling the product recommendation information to be divided and displayed by distinguishing the information display area through the total score of the product according to one embodiment.

[0190] Referring to FIG. 11, first, in step S1101, the device (400) can confirm that the total score of the first product is calculated as the first total score and that the total score of the second product is calculated as the second total score.

[0191] That is, for each product classified as a first candidate product, the device (400) can calculate a total score by summing the first score and the second score, and confirm that the total score of the first product is calculated as the first total score and that the total score of the second product is calculated as the second total score.

[0192] In step S1102, the device (400) can calculate the total sum as the sum of the first total score and the second total score.

[0193] In step S1103, the device (400) can calculate the fourth ratio as the value obtained by dividing the first total score by the total sum.

[0194] In step S1104, the device (400) can calculate the fifth ratio as the value obtained by dividing the second total score by the total sum.

[0195] In step S1105, the device (400) can distinguish the first area by setting the size of the first area at a fourth ratio within the screen of the first kiosk (110).

[0196] In step S1106, the device (400) can distinguish the second area by setting the size of the second area at a fifth ratio within the screen of the first kiosk (110).

[0197] In step S1107, the device (400) can control that recommendation information for the first product is displayed in the first area and recommendation information for the second product is displayed in the second area.

[0198] That is, the device (400) can distinguish between a first area and a second area within the screen of the first kiosk (110), and then control the display so that recommendation information for the first product is displayed in the first area and recommendation information for the second product is displayed in the second area, thereby processing so that recommendation information for the first product and recommendation information for the second product are divided and displayed on the screen of the first kiosk (110).

[0199] FIG. 12 is a flowchart for explaining the kiosk-linked personalized product recommendation and order processing process based on the analysis results of user data according to another embodiment.

[0200] In explaining the content of Fig. 12, parts that overlap with the content explained with reference to Fig. 2 will be omitted.

[0201] Referring to FIG. 12, first, in step S1201, if the device (400) confirms that the first identification information is recognized by the first kiosk (110) at the first time, it can obtain the first identification information from the first kiosk (110).

[0202] In step S1202, the device (400) can identify a user using the first kiosk (110) as the first user based on the first identification information.

[0203] In step S1203, the device (400) can select a product expected to be purchased by the first user as a recommended product based on the first user's purchase history and the inventory information of the first vending machine (210).

[0204] In step S1204, when the first product, the second product, and the third product are selected as recommended products, the device (400) can control the display of recommendation information for the first product, recommendation information for the second product, and recommendation information for the third product sequentially on the screen of the first kiosk (110). Here, the recommendation information for the first product may include information such as a notification message recommending the first product to the first user, the name of the first product, a representative image of the first product, and the price of the first product; the recommendation information for the second product may include information such as a notification message recommending the second product to the first user, the name of the second product, a representative image of the second product, and the price of the second product; and the recommendation information for the third product may include information such as a notification message recommending the third product to the first user, the name of the third product, a representative image of the third product, and the price of the third product.

[0205] When the device (400) controls the display of recommendation information for the first product, recommendation information for the second product, and recommendation information for the third product sequentially on the screen of the first kiosk (110), it can control the display of recommendation information for the products sequentially by setting the information display order and information display time through the total score of the products, and a detailed explanation related thereto will be described later with reference to FIG. 13.

[0206] In step S1205, when the device (400) recognizes that the first user has taken the first product from among the products stored in the first vending machine (210), it can perform payment for the price of the first product through the first user's payment means.

[0207] FIG. 13 is a flowchart for explaining the process of controlling product recommendation information to be displayed sequentially by setting the information display order and information display time through the total score of the product according to one embodiment.

[0208] Referring to FIG. 13, first, in step S1301, the device (400) can confirm that the total score of the first product is calculated as the first total score, confirm that the total score of the second product is calculated as the second total score, and confirm that the total score of the third product is calculated as the third total score.

[0209] That is, for each product classified as a first candidate product, the device (400) can calculate a total score by summing the first score and the second score, and confirm that the total score of the first product is calculated as the first total score, confirm that the total score of the second product is calculated as the second total score, and confirm that the total score of the third product is calculated as the third total score.

[0210] In step S1302, if the device (400) compares the first total score, the second total score, and the third total score and confirms that the first total score is the highest and the third total score is the lowest, it can set the display order of recommendation information in the order of recommendation information for the first product, recommendation information for the second product, and recommendation information for the third product.

[0211] That is, the device (400) can set the display order of recommendation information to an earlier order as the total score of the product increases.

[0212] In step S1303, the device (400) may set the first time within the time range to a longer value as the first total score increases. Here, the time range may be set differently depending on the embodiment, for example, to a range of 0 seconds to 60 seconds.

[0213] For example, the device (400) can set the first time to 10 seconds when the first total score is confirmed to be 100 points, and can set the first time to 20 seconds when the first total score is confirmed to be 110 points.

[0214] In step S1304, the device (400) can set the second time within the time range to a longer value as the second total score increases.

[0215] In step S1305, the device (400) can set the third time to a longer value within the time range as the third total score is higher.

[0216] In step S1306, the device (400) can control that recommendation information for the first product is displayed on the screen of the first kiosk (110) for a first time, then recommendation information for the second product is displayed on the screen of the first kiosk (110) for a second time, and then recommendation information for the third product is displayed on the screen of the first kiosk (110) for a third time.

[0217] That is, the device (400) sets the display order of recommendation information in the order of recommendation information for a first product, recommendation information for a second product, and recommendation information for a third product, and sets the first time, second time, and third time respectively, and then controls the recommendation information for a first product to be displayed on the screen of the first kiosk (110) for the first time, then the recommendation information for a second product to be displayed on the screen of the first kiosk (110) for the second time, and then the recommendation information for a third product to be displayed on the screen of the first kiosk (110) for the third time, so that the recommendation information for a first product, recommendation information for a second product, and recommendation information for a third product are sequentially displayed on the screen of the first kiosk (110).

[0218] FIG. 14 is a flowchart illustrating a process for controlling the display of recommendation information for a selected product based on the user's mood state according to one embodiment.

[0219] Referring to FIG. 14, in step S1401, the device (400) can obtain a first image generated by taking a picture of the first user's face using the camera of the first kiosk (110).

[0220] Specifically, a notification message indicating that a face photo needs to be taken for product recommendation may be displayed on the screen of the first kiosk (110), and if consent to the face photo is selected, the first kiosk (110) may take a picture of the first user's face using a camera and save the image generated by taking the first user's face as the first image, and the device (400) may receive the first image from the first kiosk (110) and obtain the first image.

[0221] In step S1402, the device (400) can recognize the facial expression of the first user based on the first image.

[0222] Specifically, the device (400) can recognize the first user's face in the first image, recognize each part such as the eyes, nose, mouth, and chin in the recognized first user's face, analyze the shape of each recognized part, and recognize the first user's facial expression through the analysis result. At this time, the first user's facial expression can be recognized as joy, sadness, pleasure, anger, anxiety, etc.

[0223] In step S1403, the device (400) can analyze the first state corresponding to the first expression as the first user's mood state based on the first user's expression, if the first user's expression is recognized as the first expression.

[0224] For example, if the first user's facial expression is recognized as a happy expression, the device (400) can analyze the first user's mood state as a happy state, and if the first user's facial expression is recognized as a sad expression, the device can analyze the first user's mood state as a sad state.

[0225] In step S1404, the device (400) can select a popular product among the products stored in the first vending machine (210) that is confirmed to have been purchased the most by a user whose mood state is the first state. To this end, the database of the device (400) stores purchase history classified by mood state, and the device (400) can query the information stored in the database to obtain the purchase history of the first state, and then, based on the purchase history of the first state, determine which product was purchased the most by a user whose mood state is the first state, and select the product confirmed to have been purchased the most as a popular product.

[0226] In step S1405, the device (400) can determine whether the first product and the popular product are the same product.

[0227] If it is confirmed in step S1405 that the first product and the popular product are the same product, in step S1406, the device (400) can control the display of recommendation information for the first product on the screen of the first kiosk (110).

[0228] If it is confirmed in step S1405 that the first product and the popular product are not the same product, in step S1407, the device (400) can control the recommendation information for the first product and the recommendation information for the popular product to be displayed together on the screen of the first kiosk (110). At this time, the device (400) can control the recommendation information for the first product to be displayed on a part of the screen of the first kiosk (110) and control the recommendation information for the popular product to be displayed on another part of the screen of the first kiosk (110).

[0229] FIG. 15 is a flowchart illustrating the process of setting the minimum stock quantity according to the number of active people in one embodiment.

[0230] According to one embodiment, each step illustrated in FIG. 15 may be performed prior to step S201.

[0231] Referring to FIG. 15, first, in step S1501, the device (400) can confirm that the location of the first kiosk (110) is included within the first zone among a plurality of zones. Here, the plurality of zones may be set differently depending on the embodiment and may be set through various criteria such as administrative districts, buildings, etc.

[0232] In step S1502, the device (400) can confirm that the IP address assigned to the first zone is the first address. To this end, IP addresses assigned to each zone are pre-configured, and zone information separated by zone is stored in the database of the device (400). The device (400) can query the information stored in the database to obtain the zone information of the first zone, and then, based on the zone information of the first zone, confirm that the IP address assigned to the first zone is the first address. Here, the first address may be a single IP address or may be an IP address within a certain range. For example, the first address may be 111.111.111.11, or may be in the range from 111.111.111.11 to 111.111.111.13.

[0233] According to one embodiment, the first address is a public IP address, which is an IP address provided by an Internet Service Provider (ISP) to identify the network of an Internet user, and is a unique address that is publicly disclosed. When multiple terminals are connected to the Internet through the first address, a private IP address may be assigned to each of the multiple terminals, and the private IP address assigned to each of the multiple terminals is a local IP address of a network assigned internally, such as a home, organization, or company. That is, the greater the number of terminals connected through the first address at a specific time on a specific date, the greater the number of active people in the first area at that time.

[0234] In step S1503, the device (400) can check the number of terminals connected via the first address during the first reference period by time period. Here, the first reference period may be set differently depending on the embodiment, for example, it may be set to one month.

[0235] In step S1504, the device (400) can calculate an average value for the number of terminals connected via the first address during the first reference period for each time period as an activity index.

[0236] For example, if the first reference period is set from March 1 to March 3 and the first time period is set from 9 to 10, the device (400) can calculate the average value of (10, 20, 18), which is 16, as the activity index of the first time period when it is confirmed that the number of terminals connected through the first address in the first time period on March 1 is 10, the number of terminals connected through the first address in the first time period on March 2 is 20, and the number of terminals connected through the first address in the first time period on March 3 is 18.

[0237] In step S1505, the device (400) can calculate a total index by summing the active indices calculated for each time period.

[0238] In step S1506, the device (400) can set the minimum stock quantity within the quantity range to a higher value as the total index increases. Here, the quantity range may be set differently depending on the embodiment, for example, to a range of 0 to 100.

[0239] For example, the device (400) can set the minimum stock quantity to 100 when the total index is confirmed to be 100, and can set the minimum stock quantity to 200 when the total index is confirmed to be 200.

[0240] In step S1507, the device (400) can determine the inventory amount of the first product stored in the first vending machine (210) at the current time as the first storage amount based on the inventory information of the first vending machine (210).

[0241] In step S1508, the device (400) can check whether the first storage quantity is less than the minimum stock quantity.

[0242] If it is confirmed in step S1508 that the first storage quantity is less than the minimum secured inventory quantity, in step S1509, the device (400) can calculate the first demand quantity as the value obtained by subtracting the first storage quantity from the minimum secured inventory quantity.

[0243] In step S1510, the device (400) can send a notification message to the first manager terminal (310) indicating that the first product of the first demand quantity needs to be stocked at the first vending machine (210).

[0244] FIGS. 16 to 17 are flowcharts for explaining the process of displaying product advertisements according to inventory quantity and manufacturing date according to one embodiment.

[0245] According to one embodiment, each step illustrated in FIGS. 16 to 17 may be performed prior to step S201.

[0246] Referring to FIGS. 16 and 17, first, in step S1601, the device (400) can determine, based on the inventory information of the first vending machine (210), that among the products stored in the first vending machine (210) at the current time, the inventory amount of the first product is the largest.

[0247] In step S1602, the device (400) can group the first products stored in the first vending machine (210) by manufacturing date and classify them into multiple product groups.

[0248] That is, the device (400) can identify the first products stored in the first vending machine (210) at the current time based on the inventory information of the first vending machine (210), classify them by manufacturing date, and classify the first products stored in the first vending machine (210) into multiple product groups based on the manufacturing date.

[0249] In step S1603, the device (400) can set the group with the earliest manufacturing date among a plurality of product groups as the first product group.

[0250] In step S1604, the device (400) can check the inventory amount of the first product classified into the first product group as the first inventory amount.

[0251] In step S1605, the device (400) can verify the manufacturing date of the first product classified into the first product group as the first date.

[0252] In step S1606, the device (400) can confirm that the consumption period of the first product is set from the date of manufacture to after the fourth period.

[0253] In step S1607, the device (400) can identify a date after the fourth period from the first date as the second date.

[0254] In step S1608, the device (400) can check whether the second date is earlier than the current time.

[0255] If it is confirmed in step S1608 that the second date is earlier than the current time, in step S1609, the device (400) can send a notification message to the first manager terminal (310) indicating that the first product classified as the first product group needs to be retrieved.

[0256] If it is confirmed in step S1608 that the second date is not earlier than the current time, in step S1701, the device (400) can set the fifth period from the current time to the second date.

[0257] In step S1702, the device (400) can verify the number of days of the fifth period as the number of days of the fourth period.

[0258] In step S1703, the device (400) may set the fifth weight to a lower value within the fifth numerical range as the fourth day is shorter. Here, the fifth numerical range may be set differently depending on the embodiment, for example, to a range of 0 to 1.

[0259] For example, if the device (400) confirms that the fourth day is 10 days, it can set the fifth weight to 0.9, and if it confirms that the fourth day is 9 days, it can set the fifth weight to 0.8.

[0260] In step S1704, the device (400) can calculate a second inventory amount by multiplying the first inventory amount by a fifth weight.

[0261] In step S1705, the device (400) can check whether the second inventory quantity is less than the third reference quantity. Here, the third reference quantity may be set differently depending on the embodiment, for example, to 10.

[0262] If it is confirmed in step S1705 that the second inventory quantity is less than the third reference quantity, in step S1706, the device (400) can control the display of an advertisement for the first product on the screen of the first kiosk (110). At this time, the device (400) can control the display of an advertisement for the first product on the screen of the first kiosk (110) after obtaining the advertisement for the first product based on the first product information.

[0263] FIG. 18 is a schematic diagram showing the configuration of a device according to one embodiment.

[0264] Referring to FIG. 18, the device (400) may include an information acquisition unit (410), a user identification unit (420), a recommended product selection unit (430), an information display unit (440), a payment execution unit (450), an inventory management unit (460), a processor (470), a memory (480), and a database (490).

[0265] When the information acquisition unit (410) confirms that the first identification information has been recognized by the first kiosk (110) at the first time, it can acquire the first identification information from the first kiosk (110).

[0266] The user identification unit (420) can identify a user using the first kiosk (110) as the first user based on the first identification information.

[0267] The recommended product selection unit (430) can select a product expected to be purchased by the first user as a recommended product based on the first user's purchase history and the inventory information of the first vending machine (210).

[0268] The information display unit (440) can control the display of recommendation information for the first product on the screen of the first kiosk (110) when the first product is selected as a recommended product.

[0269] When the payment execution unit (450) recognizes that the first user has taken the first product from among the products stored in the first vending machine (210), it can perform payment for the price of the first product through the first user's payment means.

[0270] The recommended product selection unit (430) can select a recommended product by performing each step illustrated in FIGS. 3 to 4.

[0271] The recommended product selection unit (430) can adjust the total score of the product through the purchase history of other users by performing each step shown in FIGS. 5 to 6.

[0272] The inventory management department (460) can manage product inventory through sales volume fluctuation trends by performing each step shown in FIGS. 7 to 8.

[0273] The inventory management department (460) can adjust the second standard amount by performing each step shown in FIG. 9, taking into account the expiration date, the season, and the number of posts.

[0274] The information display unit (440) can control the product recommendation information to be divided and displayed by performing each step shown in FIG. 11 and dividing the information display area through the total score of the product.

[0275] The information display unit (440) can control the display of product recommendation information sequentially by performing each step shown in FIG. 13 and setting the information display order and information display time through the total score of the product.

[0276] The information display unit (440) can control the display of recommended product information selected by taking into account the user's mood state by performing each step illustrated in FIG. 14.

[0277] The inventory management department (460) can set the minimum inventory amount according to the number of active people by performing each step shown in FIG. 15.

[0278] The inventory management unit (460) performs each step shown in FIG. 16, and the information display unit (440) performs each step shown in FIG. 17 to display product advertisements based on inventory quantity and manufacturing date.

[0279] The processor (470) may perform at least one of the methods described above with reference to FIGS. 2 through 17. A person or organization using the device (400) may provide services related to some or all of the methods described above with reference to FIGS. 2 through 17.

[0280] The memory (480) may store information related to the methods described above or store a program in which the methods described below are implemented. The memory (480) may be volatile memory or non-volatile memory.

[0281] The processor (470) can execute a program and control the device (400). The code of the program executed by the processor (470) can be stored in memory (480). The device (400) is connected to an external device (e.g., a personal computer or a network) through an input / output device (not shown in the drawing) and can exchange data through wired or wireless communication.

[0282] The database (490) stores information necessary to perform at least one method described above with reference to FIGS. 2 through 17, and the device (400) may be configured to include the database (490) or connected to the database (490).

[0283] The embodiments described above may be implemented as hardware components, software components, and / or combinations of hardware and software components. For example, the devices, methods, and components described in the embodiments may be implemented using one or more general-purpose or special-purpose computers, such as, for example, a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable gate array (FPGA), a programmable logic unit (PLU), a microprocessor, or any other device capable of executing and responding to instructions. The processing unit may execute an operating system (OS) and one or more software applications executed on said operating system. Additionally, the processing unit may access, store, manipulate, process, and generate data in response to the execution of the software. For ease of understanding, the processing unit may be described as being used as a single unit, but those skilled in the art will understand that the processing unit may include multiple processing elements and / or multiple types of processing elements. For example, the processing unit may include multiple processors or one processor and one controller. Additionally, other processing configurations, such as parallel processors, are also possible.

[0284] The method according to the embodiment may be implemented in the form of program instructions that can be executed through various computer means and recorded on a computer-readable medium. The computer-readable medium may include program instructions, data files, data structures, etc., either alone or in combination. The program instructions recorded on the medium may be those specifically designed and configured for the embodiment, or they may be those known and available to those skilled in the art of computer software. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks, and magnetic tapes; optical recording media such as CD-ROMs and DVDs; magneto-optical media such as floptical disks; and hardware devices specifically configured to store and execute program instructions, such as ROM, RAM, and flash memory. Examples of program instructions include machine code, such as that generated by a compiler, as well as high-level language code that can be executed by a computer using an interpreter, etc. The hardware devices described above may be configured to operate as one or more software modules to perform the operation of the embodiment, and vice versa.

[0285] Software may include computer programs, code, instructions, or a combination of one or more of these, and may configure a processing unit to operate as desired or command the processing unit independently or collectively. Software and / or data may be permanently or temporarily embodied in any type of machine, component, physical device, virtual equipment, computer storage medium or device, or transmitted signal wave so as to be interpreted by the processing unit or to provide instructions or data to the processing unit. Software may be distributed over networked computer systems and may be stored or executed in a distributed manner. Software and data may be stored on one or more computer-readable recording media.

[0286] Although the embodiments have been described above with reference to the limited drawings, those skilled in the art can apply various technical modifications and variations based on the above. For example, suitable results may be achieved even if the described techniques are performed in a different order than described, and / or if the components of the described system, structure, device, circuit, etc. are combined or assembled in a form different from described, or replaced or substituted by other components or equivalents.

[0287] Therefore, other implementations, other embodiments, and equivalents to the claims also fall within the scope of the claims set forth below.

Claims

Claim 1 A method for adjusting the standard quantity of stock replenishment linked to a kiosk using the consumption period, peak season period, and the rate of increase or decrease in the number of SNS posts, performed by a device, comprising: a step of confirming the stock quantity of the first product stored in the first vending machine as a first quantity based on the stock information of the first vending machine at a second time point, which is a time point after the first product is sold at the first vending machine connected to the first kiosk; a step of setting a time point prior to a preset standard period from the second time point as a third time point, setting a time point prior to the standard period from the third time point as a fourth time point, setting a time point after the standard period from the second time point as a fifth time point, setting the period from the fourth time point to the third time point as a first period, setting the period from the third time point to the second time point as a second period, and setting the period from the second time point to the fifth time point as a third period; and a step of analyzing the trend of fluctuation in the sales volume of the first product by comparing the sales volume of the first product sold at the first vending machine during the first period and the second period based on the sales history of the first vending machine. A step of predicting the quantity of the first product expected to be sold at the first vending machine during the third period as a fourth quantity based on the results of analyzing the sales volume fluctuation trend of the first product; a step of setting a first weight based on the rate of increase or decrease in the number of users who purchased the first product through recommendations of the first product, and calculating a second standard quantity using the fourth quantity and the first weight; a step of setting a second weight based on the consumption period of the first product, setting a third weight based on peak periods that have a favorable influence on the sales of the first product within the third period, and setting a fourth weight based on the rate of increase or decrease in the number of posts of the first product uploaded to SNS; a step of calculating an adjusted second standard quantity by multiplying the second standard quantity, the second weight, the third weight, and the fourth weight;A method for adjusting a standard quantity of inventory linked to a kiosk using a consumption period, a peak season period, and a rate of increase or decrease in the number of SNS posts, comprising: a step of calculating a fifth quantity by subtracting the first quantity from the adjusted second standard quantity when it is confirmed that the first quantity is less than the adjusted second standard quantity; and a step of transmitting a notification message to a first administrator terminal indicating that the first product of the fifth quantity needs to be stocked in the first vending machine when the fifth quantity is calculated. Claim 2 A method for adjusting the standard quantity of inventory linked to a kiosk using an expiration date, a peak period, and an increase / decrease rate of the number of SNS posts, wherein the step of setting the second weighting factor includes confirming that the expiration date of the first product is set to a period after the manufacturing date, confirming the number of days in the fourth period as the first number of days, and setting the second weighting factor to a higher value within a preset second numerical range as the first number of days is longer; and the step of setting the third weighting factor includes setting the peak period that has a favorable effect on the sales of the first product within the third period as the third-1 period, confirming the number of days in the third period as the second number of days and confirming the number of days in the third-1 period as the third number of days, calculating the third ratio as the value obtained by dividing the third number of days by the second number of days, and setting the third weighting factor to a higher value within a preset third numerical range as the third ratio is higher. Claim 3 In paragraph 2, the step of setting the fourth weight comprises: a step of collecting and obtaining a first post classified as a post of the first product among posts uploaded to SNS via crawling, according to the upload period; a step of classifying the first post uploaded during the first period into a first post group and classifying the first post uploaded during the second period into a second post group; a step of setting the number of posts classified into the first post group as the first post number and setting the number of posts classified into the second post group as the second post number; a step of calculating a second increase / decrease rate by subtracting the first post number from the second post number and dividing by the first post number; and a step of setting the fourth weight to a higher value within a preset fourth numerical range as the second increase / decrease rate is higher, and the step of calculating the adjusted second standard amount comprises a step of calculating the adjusted second standard amount by multiplying the second standard amount, the second weight, the third weight, and the fourth weight. Method for adjusting standard inventory replenishment quantity linked to a kiosk using the rate of increase or decrease in the number of posts.

Images