KR102435287B1 - Method, device and system for providing customized beauty service platform based on artificial intelligence - Google Patents

Abstract

According to an embodiment of the present invention, a method for providing a user-customized beauty service platform based on artificial intelligence, performed by an apparatus, comprises the steps of: extracting beauty consultation information of a first user based on consultation information input into a chat space between a first user account and a first counselor account; extracting lifestyle information of the first user based on lifestyle information input through a first user terminal through which the first user account is logged in; extracting beauty interest information of the first user based on beauty content specifications inquired through the first user terminal; analyzing the skin condition of the first user based on the beauty consultation information of the first user, the lifestyle information of the first user, and the beauty interest information of the first user; inputting an analysis result of the skin condition of the first user to a first artificial neural network and obtaining an output from the first artificial neural network; selecting a first product as a beauty product suitable for the first user based on the output of the first artificial neural network; and transmitting a recommendation notification message for the first product to the first user terminal. The present invention not only recommends a beauty product suitable for personal skin conditions, but also informs the usage method for the beauty product.

Description

Method, device and system for providing artificial intelligence-based user-customized beauty service platform

The following embodiments relate to a technology for providing a user-customized beauty service platform based on artificial intelligence.

Recently, as interest in beauty has increased and beauty products with various functions have appeared, consumption of beauty products has been steadily increasing, and beauty products are positioned as essential consumer goods.

People's skin condition is affected by gender, age, season, etc. In addition, skin condition changes in various ways according to individual lifestyles. In addition, various types of beauty products are being released because skin concerns appear differently depending on the skin condition of each individual.

In general, consumers who purchase beauty products consult with store staff about their skin condition and skin concerns to select and purchase beauty products. However, consumers have the inconvenience of having to visit a store for consultation every time they purchase beauty products.

Therefore, it is required to implement a technology for a customized beauty service that not only recommends a beauty product suitable for an individual's skin condition, but also informs how to use the beauty product by considering the skin condition and lifestyle of the consumer at the same time.

Republic of Korea Patent Publication No. 10-2020-0063300 (published on June 5, 2020) Republic of Korea Patent Publication No. 10-2021-0107354 (published on September 1, 2021) Republic of Korea Patent Publication No. 10-2003-0065181 (published on Aug. 6, 2003) Republic of Korea Patent Registration No. 10-2175251 (Notice on Nov. 9, 2020)

According to one embodiment, based on the consultation information input on the chat space between the first user account and the first counselor account, the first user's beauty consultation information is extracted, and the first user terminal is logged into the first user account. Based on the lifestyle information input via Based on the user's beauty consultation information, the first user's lifestyle information, and the first user's beauty interest information, the skin condition of the first user is analyzed, and the result of the analysis on the skin condition of the first user is returned to the first artificial neural network. input to, obtain an output from the first artificial neural network, select a first product as a beauty product suitable for the first user, based on the output of the first artificial neural network, and send a recommendation notification message for the first product to the first An object of the present invention is to provide a method, apparatus and system for providing an artificial intelligence-based user-customized beauty service platform that is transmitted to a user terminal.

The object of the present invention is not limited to the object mentioned above, and other objects not mentioned will be clearly understood from the description below.

According to one embodiment, in the method of providing an artificial intelligence-based user-customized beauty service platform performed by a device, based on the consultation information input in the chat space between the first user account and the first counselor account, the first user extracting beauty consultation information; extracting lifestyle information of the first user based on the lifestyle information input through the first user terminal to which the first user account is logged; extracting beauty interest information of the first user on the basis of the beauty contents searched through the first user terminal; analyzing the skin condition of the first user based on the first user's beauty consultation information, the first user's lifestyle information, and the first user's beauty interest information; inputting an analysis result of the skin condition of the first user into a first artificial neural network, and obtaining an output from the first artificial neural network; selecting a first product as a beauty product suitable for the first user based on the output of the first artificial neural network; and transmitting a recommendation notification message for the first product to the first user terminal.

The artificial intelligence-based user-customized beauty service platform providing method includes, after transmitting a recommendation notification message for the first product, based on the purchase history of the first user, the first user purchases the first product when it is confirmed that the first product is purchased; When the period of use of the first product is set as the first period and it is confirmed that the second period preset from the time of purchase of the first product has elapsed, the remaining capacity of the first product is transferred to the first user terminal by the first user terminal. Transmitting a shooting request message for; obtaining a first image generated by photographing the first product at a second time point, which is a time point at which the first product is photographed, when the first product is photographed through the camera of the first user terminal; analyzing the remaining capacity of the first product remaining at the second time point as a first remaining capacity based on the first image; A period from the purchase time of the first product to the second time point is set as a third period, the first period and the third period are compared, and the remaining capacity of the first product to remain at the second time point is setting as a first reference dose; calculating a first difference value by subtracting the first reference capacity from the first remaining capacity; checking whether the first difference value is out of a preset reference range; when it is determined that the first difference value is out of the reference range, determining whether the first remaining capacity is greater than the first reference capacity; transmitting a notification message for an increase in usage of the first product to the first user terminal when it is confirmed that the first remaining capacity is greater than the first reference capacity; when it is confirmed that the first remaining capacity is less than the first reference capacity, transmitting a notification message for a decrease in usage of the first product to the first user terminal; when it is confirmed that the first difference value does not deviate from the reference range, checking a second reference capacity set as a minimum remaining capacity of the first product; determining whether the first remaining capacity is less than the second reference capacity; and when it is confirmed that the first remaining capacity is less than the second reference capacity, transmitting a notification message for additional purchase of the first product to the first user terminal.

In the artificial intelligence-based user-customized beauty service platform providing method, whenever an image of a product photographed through the first user terminal is uploaded, a first score, which is set to be given when uploading a product image, is obtained by the first user. providing additional ratings; each time the beauty content is inquired through the first user terminal, additionally giving a second score, which is set to be given when the beauty content is inquired, to the rating of the first user; each time a beauty consultation is performed through the first user terminal, additionally giving a third score set to be given during the beauty consultation to the rating of the first user; each time a beauty product is purchased through the first user terminal, additionally giving a fourth score, which is set to be given when purchasing a beauty product, to the rating of the first user; and selecting the membership level of the first user based on the rating of the first user.

The apparatus according to an embodiment may be controlled by a computer program stored in the medium to execute the method of any one of the above-described methods in combination with hardware.

According to one embodiment, based on the consultation information input on the chat space between the first user account and the first counselor account, the first user's beauty consultation information is extracted, and the first user terminal is logged into the first user account. Based on the lifestyle information input via Based on the user's beauty consultation information, the first user's lifestyle information, and the first user's beauty interest information, the skin condition of the first user is analyzed, and the result of the analysis on the skin condition of the first user is returned to the first artificial neural network. input to, obtain an output from the first artificial neural network, select a first product as a beauty product suitable for the first user, based on the output of the first artificial neural network, and send a recommendation notification message for the first product to the first By transmitting to the user terminal, it is possible to provide a customized beauty service that not only recommends beauty products suitable for an individual's skin condition, but also tells how to use the beauty products, considering the skin condition and lifestyle of consumers at the same time. have.

On the other hand, the effects according to the embodiments are not limited to those mentioned above, and other effects not mentioned will be clearly understood by those of ordinary skill in the art from the following description.

1 is a diagram for explaining the configuration of a system according to an embodiment.
2 is a flowchart illustrating a process of providing an artificial intelligence-based user-customized beauty service platform according to an embodiment.
3 is a flowchart illustrating a process of analyzing a residual capacity through a photographed image of a beauty product according to an exemplary embodiment.
4 is a flowchart illustrating a process of transmitting a notification message according to the remaining capacity of a beauty product according to an exemplary embodiment.
5 is a flowchart illustrating a process of selecting a membership level by giving an additional score to a rating of a first user according to an exemplary embodiment.
6 is a flowchart illustrating a process of granting a reward according to a membership level of a first user according to an exemplary embodiment.
7 is a flowchart for explaining a process of setting a user's allowable range by calculating a content reading time according to an exemplary embodiment.
8 is a flowchart illustrating a process of providing content recommendation information by predicting a content reading time according to an exemplary embodiment.
9 is a diagram for explaining learning of a first artificial neural network according to an embodiment.
10 is an exemplary diagram of a configuration of an apparatus according to an embodiment.

Hereinafter, embodiments will be described in detail with reference to the accompanying drawings. However, since various changes may be made to the embodiments, the scope of the patent application is not limited or limited by these embodiments. It should be understood that all modifications, equivalents and substitutes for the embodiments are included in the scope of the rights.

Specific structural or functional descriptions of the embodiments are disclosed for purposes of illustration only, and may be changed and implemented in various forms. Accordingly, the embodiments are not limited to a specific disclosure form, and the scope of the present specification includes changes, equivalents, or substitutes included in the technical spirit.

Although terms such as first or second may be used to describe various elements, these terms should be interpreted only for the purpose of distinguishing one element from another. For example, a first component may be termed a second component, and similarly, a second component may also be termed a first component.

When a component is referred to as being “connected” to another component, it may be directly connected or connected to the other component, but it should be understood that another component may exist in between.

The terms used in the examples are used for the purpose of description only, and should not be construed as limiting. The singular expression includes the plural expression unless the context clearly dictates otherwise. In the present specification, terms such as “comprise” or “have” are intended to designate that a feature, number, step, operation, component, part, or combination thereof described in the specification exists, but one or more other features It is to be understood that it does not preclude the possibility of the presence or addition of numbers, steps, operations, components, parts, or combinations thereof.

Unless defined otherwise, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by one of ordinary skill in the art to which the embodiment belongs. Terms such as those defined in a commonly used dictionary should be interpreted as having a meaning consistent with the meaning in the context of the related art, and should not be interpreted in an ideal or excessively formal meaning unless explicitly defined in the present application. does not

In addition, in the description with reference to the accompanying drawings, the same components are assigned the same reference numerals regardless of the reference numerals, and the overlapping description thereof will be omitted. In the description of the embodiment, if it is determined that a detailed description of a related known technology may unnecessarily obscure the gist of the embodiment, the detailed description thereof will be omitted.

The embodiments may be implemented in various types of products, such as personal computers, laptop computers, tablet computers, smart phones, televisions, smart home appliances, intelligent cars, kiosks, wearable devices, and the like.

1 is a diagram for explaining the configuration of a system according to an embodiment.

Referring to FIG. 1 , a system according to an embodiment may include a plurality of user terminals 100 and devices 200 capable of communicating with each other through a communication network.

First, the communication network may be configured regardless of its communication mode, such as wired and wireless, and may be implemented in various forms so that communication between a server and a server and communication between a server and a terminal are performed.

Each of the plurality of user terminals 100 may be a desktop computer, a notebook computer, a tablet, a smart phone, or the like. For example, as shown in FIG. 1 , the first user terminal 110 , the second user terminal 120 , etc. may be smartphones, and may be employed differently according to embodiments.

Each of the plurality of user terminals 100 may be configured to perform all or part of an arithmetic function, a storage/referencing function, an input/output function, and a control function of a typical computer. The plurality of user terminals 100 may be configured to communicate with the device 200 by wire or wireless.

Each of the plurality of user terminals 100 is connected to a website operated by a person or organization that provides a service using the device 200 , or is developed and distributed by a person or organization that provides a service using the device 200 . One application can be installed. Each of the plurality of user terminals 100 may be linked with the device 200 through a website or an application.

Each of the plurality of user terminals 100 may access the device 200 through a website or an application provided by the device 200 .

Hereinafter, for convenience of description, the operation of the first user terminal 110 will be mainly described, but other user terminals such as the second user terminal 120 may perform the operation of the first user terminal 110 instead. to be.

The device 200 may be a self-server owned by a person or organization that provides services using the device 200, a cloud server, or a peer-to-peer (p2p) set of distributed nodes. may be The device 200 may be configured to perform all or part of an arithmetic function, a storage/referencing function, an input/output function, and a control function of a typical computer. The device 200 may include at least one artificial neural network that performs an inference function.

The device 200 may be configured to communicate with the plurality of user terminals 100 by wire or wireless, and controls the operation of each of the plurality of user terminals 100 , and displays which information on the screen of each of the plurality of user terminals 100 . You can control what is displayed.

Meanwhile, for convenience of explanation, only the first user terminal 110 and the second user terminal 120 are illustrated in FIG. 1 among the plurality of user terminals 100 , but the number of terminals may vary according to embodiments. . As long as the processing capacity of the apparatus 200 allows, the number of terminals is not particularly limited.

The device 200 may provide a platform so that a user-customized beauty service based on artificial intelligence can be provided, and the user's skin condition is analyzed through the platform, and a beauty product suitable for the user through the analysis result of the skin condition , and recommending the selected beauty product to the user may be performed. Here, the beauty product refers to a product that can be applied to the skin, and for example, may include all skin-related products such as basic products, color cosmetics, body products, cleaning products, and hair products.

2 is a flowchart illustrating a process of providing an artificial intelligence-based user-customized beauty service platform according to an embodiment.

Referring to FIG. 2 , first, in step S201 , the device 200 may extract the beauty consultation information of the first user based on the consultation information input in the chat space between the first user account and the first counselor account. .

Specifically, a chat space through a messenger may be provided between the user account and the counselor account, and counseling information divided for each chat space may be stored in the database of the device 200 . Here, the consultation information may refer to conversation contents input into the chat space through the user account and the counselor account.

After confirming the chat space between the first user account and the first counselor account, the device 200 may obtain consultation information input on the checked chat space from the database, and based on the obtained consultation information, the first user of beauty consultation information can be extracted. Here, the beauty consultation information of the first user may include skin concerns input through the first user account and questions and answers input through the first counselor account in the chat space between the first user account and the first counselor account. can For example, beauty consultation information includes questions and answers regarding skin color, moisture content, oil content, elasticity, wrinkles, skin stains, blemishes, pore size, sebum, dead skin cells, and skin type among the conversations entered in the chat space. It may be information extracted from the contents.

That is, the device 200 analyzes the conversation content input on the chat space between the first user account and the first counselor account based on the consultation information input in the chat space between the first user account and the first counselor account, , the first user's skin concerns, the first user's skin condition, etc. can be checked, and the first user's skin concerns and the first user's skin condition can be checked. may be extracted as the first user's beauty consultation information.

In step S202 , the device 200 may extract the lifestyle information of the first user based on the lifestyle information input through the first user terminal 110 .

When an attempt is made to access the device 200 through the first user terminal 110 , a first user account may be created for logging in. When the first user's account is created, the device 200 may generate a user information input page and transmit it to the first user terminal, and when lifestyle information of the first user is input through the user information input page, the first user terminal Lifestyle information of the first user may be obtained from 110 . Here, the lifestyle information of the first user is information indicating the lifestyle of the first user, and may include, for example, information on lifestyle, sleep pattern, eating habits, activity, health status, stress status, etc. can

According to an embodiment, when the first user account is created, lifestyle information is included in user information required for account creation, and the first user information registered at the time of account creation includes the lifestyle information of the first user. Thus, the lifestyle information of the first user may be stored in the database of the device 200 . In this case, the device 200 may extract the lifestyle information of the first user from the first user information stored in the database.

According to another embodiment, when the first user terminal 110 is logged in through the first user account, the device 200 provides a page for inputting lifestyle information to the first user terminal 110 . can do. When the lifestyle information of the first user is input through the page provided to input the lifestyle information, the device 200 receives the lifestyle information from the first user terminal 110, and sets the received lifestyle information to the first It can be extracted as the user's lifestyle information.

In step S203 , the device 200 may extract the beauty interest information of the first user based on the beauty contents searched through the first user terminal 110 . To this end, the database of the device 200 stores a history of inquiring beauty content for each user terminal. Here, the beauty content may include images, videos, posts, etc. that provide information related to beauty.

The device 200 may obtain the beauty content details inquired through the first user terminal 110 from the database, and extract the beauty interest information of the first user. Here, the beauty interest information may include information on beauty products owned by the first user, and may include information on beauty categories, beauty products, etc., which are confirmed to be frequently inquired through the first user terminal 110 . can

Specifically, the device 200 may check the beauty product owned by the first user based on the first user's purchase history of the beauty product, and when it is confirmed that the first user has the first product, the 1 product may be extracted as beauty interest information of the first user.

In addition, when it is confirmed that the beauty content of the first category among the plurality of beauty categories has been inquired more than other categories based on the details of the beauty content retrieved through the first user terminal 110 , the device 200 ) may determine that the first user is interested in the first category, and extract the first category as beauty interest information of the first user. Here, a plurality of beauty categories in which beauty contents are registered may be divided into skin concerns, types of beauty products, and the like.

In step S204, when the first user's beauty consultation information, the first user's lifestyle information, and the first user's beauty interest information are extracted, the device 200 extracts the first user's beauty consultation information, the first user's life The skin condition of the first user may be analyzed based on the style information and the beauty interest information of the first user.

That is, the device 200 may analyze the skin concerns of the first user, the skin condition of the first user, etc., based on the beauty consultation information of the first user, and based on the lifestyle information of the first user, the second 1 It is possible to analyze the user's lifestyle, sleep pattern, eating habits, activity, health status, stress status, etc. can be analyzed, and by collecting each analysis result, the skin condition of the first user can be analyzed. In this case, the device 200 may also analyze the cause of the skin trouble of the first user.

For example, the device 200 may check the lifestyle information affecting the skin of the first user based on the lifestyle information of the first user, and generate a skin problem according to the lifestyle of the first user. The degree of influence that can cause skin problems can be analyzed, and the cause of the skin troubles of the first user can be analyzed according to the degree of influence that causes skin problems.

In operation S205 , the device 200 may input the analysis result of the first user's skin condition into the first artificial neural network, and obtain an output from the first artificial neural network.

According to an embodiment, the first artificial neural network may be an algorithm for outputting a beauty product suitable for the user after receiving an analysis result of the user's skin condition. For example, when it is analyzed that the skin condition of the first user is dry, the first artificial neural network receives the analysis result of the dry skin condition as an input, selects a beauty product suitable for dry skin, and selects the selected beauty product. can print

In step S206 , the device 200 may select the first product as a beauty product suitable for the first user based on the output of the first artificial neural network.

The first artificial neural network may be trained to select and extract a beauty product suitable for the user through the analysis result of the user's skin condition. The first artificial neural network may be learned through a method described later with reference to FIG. 9 .

For example, as a result of checking the output of the first artificial neural network, when the output value is 1, the device 200 selects a beauty product suitable for the first user as the first product, and when the output value is 2, to the first user A suitable beauty product may be selected as the second product. To this end, when the analysis result of the first user's skin condition is input, the first artificial neural network identifies the cause of the first user's skin trouble and selects a beauty product that can improve the first user's skin trouble. In addition, it is possible to output an output value indicating the selected beauty product.

In step S207 , when the first product is selected as a beauty product suitable for the first user, the device 200 may transmit a recommendation notification message for the first product to the first user terminal 110 . Here, the recommendation notification message for the first product is a notification message for informing that the first product is recommended as a beauty product suitable for the first user, and may include link information leading to a purchase page of the first product, It may be displayed on the screen of the first user terminal 110 . The purchase page of the first product may include information on the type, ingredient, efficacy, usage, shelf life, price, and the like of the first product.

3 is a flowchart illustrating a process of analyzing a residual capacity through a photographed image of a beauty product according to an exemplary embodiment.

Referring to FIG. 3 , first, in step S301 , the device 200 may check the purchase history of the first user. To this end, purchase history information divided for each user is stored in the database of the device 200 , and the device 200 may obtain the purchase history information of the first user by inquiring the information stored in the database. Here, the purchase history information may include information such as the identification number of the purchased beauty product, the time of purchase, the amount of purchase, and the like, and may be sorted in the order of purchase time, so that the most recent purchase history may be confirmed first.

That is, the device 200 may obtain the purchase history of the first user from the database, and check a list of beauty products purchased by the first user through the purchase history of the first user.

In step S302 , the device 200 may determine whether the first user has purchased the first product based on the purchase history of the first user.

If it is confirmed in step S302 that the first user has purchased the first product, in step S303 , the device 200 determines the first time point at which the first user purchases the first product based on the purchase history of the first user. You can check the purchase time of the product.

If it is determined in step S302 that the first user has not purchased the first product, the process returns to step S301 and the device 200 may check the purchase history of the first user again after a certain period of time has elapsed.

In step S304 , the device 200 may check the current time point.

In step S305 , the device 200 may determine whether a second period has elapsed from the time of purchase of the first product to the current time. That is, the device 200 compares the purchase time of the first product confirmed in step S303 with the current time confirmed in step S304, and calculates how much time has elapsed since the current time point is the purchase time of the first product, It may be checked whether a second period has elapsed from the point of purchase of the first product. Here, the second period may be set differently according to the length of the first period, and the first period may be set to maximize the efficacy of the first product as a period of use of the first product.

According to an embodiment, the first period may be set by the product developer, and the efficacy of the first product may be most expressed only when all of the first product is used during the first period. For example, when the first period is set to 3 months, when the first product is used up and exhausted for 3 months, the efficacy of the first product may be most expressed.

The second period may be set according to the length of the first period, and the longer the first period, the longer the second period may be set. For example, when the first period is set to 3 months, the second period may be set to 1 month, and when the first period is set to 6 months, the second period may be set to 2 months.

If it is confirmed in step S305 that the second period has elapsed from the time of purchase of the first product, the device 200 sends a message requesting photographing for the remaining capacity of the first product to the first user terminal 110 in step S306 can be transmitted. That is, when it is confirmed that the second period has elapsed from the time of purchase of the first product, the device 200 determines that it is necessary to check the remaining capacity of the first product, and requests a photographing to check the remaining capacity of the first product. The message may be transmitted to the first user terminal 110 .

If it is determined in step S305 that the second period has not elapsed from the time of purchase of the first product, the current time point returns to step S304, and the device 200 may check the current time point again after a predetermined period has elapsed.

In step S307 , the device 200 performs shooting of the first product through the camera of the first user terminal 110 as a confirmation of the shooting request message for the remaining capacity of the first product. The generated first image may be obtained from the first user terminal 110 . Here, the first image may refer to an image generated by photographing the first product at a second time point, which is a time point at which the first product is photographed.

Specifically, by confirming the photographing request message sent to the first user terminal 110, the first user terminal 110 may generate a first image by photographing the first product at a second time point, The device 200 may acquire a first image from the first user terminal 110 .

In operation S308 , the device 200 may analyze the residual capacity of the first product remaining at the second time point as the first residual capacity based on the first image.

Specifically, the device 200 identifies the area occupied by the first product in the first image and classifies it as the first area, and identifies the area where the first product remains in the first area and classifies it as the second area. Also, the first remaining capacity may be calculated by comparing the sizes of the first and second regions. In this case, the first residual capacity may be calculated through the following equation.

For example, in the first image, when the size of the first region is identified as 10,000 pixels, the size of the second region is identified as 7,000 pixels, and the total capacity of the first product is 100 ml, the device 200 is configured to The remaining capacity can be calculated as 70 ml.

4 is a flowchart illustrating a process of transmitting a notification message according to the remaining capacity of a beauty product according to an exemplary embodiment.

Referring to FIG. 4 , first, in step S401 , the device 200 may analyze the first remaining capacity based on the first image.

In step S402 , the device 200 may set the period from the purchase time of the first product to the second time point as the third period. Here, the third period may refer to a period from the time the first user purchases the first product to the second time point when the first user photographed the first product.

In operation S403 , the device 200 may compare the first period and the third period, and set the remaining capacity of the first product to remain at the second time point as the first reference capacity. In this case, the first reference capacity may be calculated through the following equation.

For example, if the first period is set to 5 months, the third period is set to 1 month, and the total volume of the first product is 100 ml, the device 200 calculates the first reference volume as 80 ml can do.

In operation S404 , the device 200 may calculate a first difference value by subtracting the first reference capacity from the first remaining capacity.

In step S405 , the device 200 may determine whether the first difference value is out of a reference range. Here, the reference range may be set differently according to embodiments.

That is, when the first difference value is within the reference range, the device 200 determines that the first user is using the first product appropriately for a predetermined period and capacity, and when the first difference value is out of the reference range , it may be determined that the first user is using the capacity of the first product inappropriately for a predetermined period and capacity.

If it is determined in step S405 that the first difference value is out of the reference range, in step S406 , the device 200 may determine whether the first remaining capacity is greater than the first reference capacity.

If it is determined in step S406 that the first remaining capacity is greater than the first reference capacity, in step S407 , the device 200 may transmit a notification message for an increase in usage of the first product to the first user terminal 110 . Here, the notification message for the increase in usage of the first product is a notification message informing that the first user needs to increase the usage in order to consume the first product more quickly, and is displayed on the screen of the first user terminal 110. A notification message may be displayed.

That is, the device 200 determines that the first residual capacity is greater than the first reference capacity while the difference between the first remaining capacity and the first reference capacity is out of the reference range, and the amount of the first product is greater than the predetermined amount. It is determined that it is insufficient, and a notification message for an increase in usage of the first product may be transmitted to the first user terminal 110 .

If it is determined in step S406 that the first remaining capacity is less than the first reference capacity, in step S408 , the device 200 may transmit a notification message for a decrease in the usage of the first product to the first user terminal 110 . Here, the notification message about the decrease in usage of the first product is a notification message informing that the first user needs to reduce the usage in order to consume the first product more slowly, and is displayed on the screen of the first user terminal 110 to reduce usage. A notification message may be displayed.

That is, when the device 200 determines that the first residual capacity is less than the first reference capacity while the difference between the first residual capacity and the first reference capacity is out of the reference range, the amount of the first product to be used is greater than the predetermined amount. It is determined that it is overflowing, and a notification message for a decrease in usage of the first product may be transmitted to the first user terminal 110 .

Meanwhile, if it is determined in step S405 that the first difference value does not deviate from the reference range, in step S409 , the device 200 may determine whether the first remaining capacity is less than the second reference capacity. Here, the second reference dose refers to the minimum remaining capacity of the first product, and may be set differently according to the total capacity of the first product.

If it is determined in step S409 that the first remaining capacity is less than the second reference capacity, in step S410 , the device 200 may transmit a notification message for additional purchase of the first product to the first user terminal 110 . Here, the notification message for the additional purchase of the first product is a notification message informing that the remaining capacity of the first product is low and an additional purchase is required, and the first product is added to the screen of the first user terminal 110 . A notification message about the purchase may be displayed.

If it is determined in step S409 that the first remaining capacity is greater than the second reference capacity, the process returns to step S304, and after a predetermined period of time has elapsed, the device 200 may check the current time again.

5 is a flowchart illustrating a process of selecting a membership level by giving an additional score to a rating of a first user according to an exemplary embodiment.

Referring to FIG. 5 , first, in step S501 , the device 200 may confirm that an image of a product photographed through the first user terminal 110 has been uploaded.

Specifically, the device 200 may calculate the number of product image uploads by checking the number of times the first user has uploaded a product image whenever the first user takes and uploads an image of the product through the first user terminal 110 . have.

In step S502 , the device 200 may additionally give a first score, which is set to be given when uploading a product image, to the rating of the first user.

For example, if the initial rating of the first user is 100 points, the number of product image uploads is 6, and the first score is set to 5 points, an additional 30 points are given to the initial rating of the first user, The rating of the first user may be changed to 130 points.

In step S503 , the device 200 may confirm that the beauty content is inquired through the first user terminal 110 .

Specifically, each time the first user inquires the beauty content through the first user terminal 110 , the device 200 may check the number of times the beauty content has been inquired to calculate the number of beauty content inquiry.

In step S504 , the device 200 may additionally give a second score, which is set to be given when viewing beauty content, to the rating of the first user.

For example, if the initial rating of the first user is 100 points, the number of views of beauty content is 12, and the second score is set to 2 points, 24 points are additionally given to the initial rating of the first user, The rating of the first user may be changed to 124 points.

In step S505 , the device 200 may confirm that the beauty consultation has been performed through the first user terminal 110 .

Specifically, whenever the first user conducts beauty consultation through the first user terminal 110 , the device 200 may check the number of beauty consultations and calculate the number of beauty consultations.

In step S506 , the device 200 may additionally give a third score, which is set to be given during beauty consultation, to the rating of the first user.

For example, if the initial rating of the first user is 100 points, the number of beauty consultations is 3 times, and the third score is set to 4 points, 12 points are additionally given to the initial rating of the first user, The rating of the first user may be changed to 112 points.

In step S507 , the device 200 may confirm that the beauty product has been purchased through the first user terminal 110 .

Specifically, whenever the first user purchases a beauty product through the first user terminal 110 , the device 200 may check the number of purchases of the beauty product and calculate the number of purchases of the beauty product.

In step S508 , the device 200 may additionally give a fourth score, which is set to be given when purchasing a beauty product, to the rating of the first user.

For example, if the initial rating of the first user is 100 points, the number of purchases of beauty products is 4, and the fourth score is set to 10 points, an additional 40 points are given to the initial rating of the first user, The rating of the first user may be changed to 140 points.

In step S509 , the device 200 may set the membership level of the first user based on the rating of the first user.

Specifically, the device 200 may calculate the rating of the first user by reflecting the first score, the second score, the third score, and the fourth score in the initial score of the first user.

For example, if the initial rating of the first user is 100 points, the first score is 30 points, the second score is 24 points, the third score is 12 points, and the fourth score is 40 points, the initial rating of the first user is By adding the first score, the second score, the third score, and the fourth score, the score of the first user may be calculated as 206 points.

After calculating the rating of the first user, the device 200 may set the membership level of the first user through the rating of the first user.

For example, if the criteria for classifying member grades are set as 1st grade if the user's rating is 300 or more, 2nd if the user's rating is 200 or more and less than 300, and 3 if the user's rating is less than 200 , when the first user rating is calculated as 206 points, the device 200 may set the membership level of the first user to the second level.

6 is a flowchart illustrating a process of granting a reward according to a membership level of a first user according to an exemplary embodiment.

Referring to FIG. 6 , first, in step S601 , the device 200 may check the rating of the first user. That is, the device 200 may calculate the rating of the first user by reflecting the first score, the second score, the third score, and the fourth score, and may check the calculated score of the first user.

In step S602 , the device 200 may determine whether the rating of the first user is higher than the first reference score. Here, the first reference score may be set differently according to embodiments.

If it is determined in step S602 that the rating of the first user is higher than the first reference score, in step S603 , the device 200 may select the first rating as the membership grade of the first user.

In step S604 , when the membership level of the first user is selected as the first level, the device 200 may grant the first user account access rights to access the first category and the second category. Here, the first category means a category in which user-shared content is registered in the posting space where the beauty content is registered, and the second category is the category in which the self-produced content is registered in the posting space in which the beauty content is registered. can mean The user shared content is content uploaded to the posting space by users registered in the user account, and the self-created content is content uploaded to the posting space by a company operating the device 200 .

In step S605 , the device 200 may issue a discount coupon used for purchasing a beauty product and provide it through the first user account. In this case, when it is confirmed that the first user has purchased the first product, the device 200 may issue a discount coupon for the first product and provide it through the first user account. Here, the discount coupon may be a discount rate coupon that can be purchased by applying a discount rate to the price of a beauty product, or a price coupon that can receive a specific price discount. The type of coupon may be variously changed according to embodiments.

Meanwhile, if it is determined in step S602 that the rating of the first user is lower than the first reference score, in operation S606 , the device 200 may determine whether the rating of the first user is higher than the second reference score. Here, the second reference score may be set to a value lower than the first reference score.

If it is determined in step S606 that the rating of the first user is higher than the second reference score, in operation S607 , the device 200 may select the second rating as the membership rating of the first user.

In step S608 , when the membership level of the first user is selected as the second level, the device 200 may grant the first user account access rights to access the first category and the second category.

If it is determined in step S606 that the rating of the first user is lower than the second reference score, in operation S609 , the device 200 may select the third rating as the membership rating of the first user.

In step S610 , when the membership level of the first user is selected as the third level, the device 200 may grant the first user account an access right to access the first category.

7 is a flowchart illustrating a process of calculating a content reading time and setting a user's allowable range according to an exemplary embodiment.

Referring to FIG. 7 , first, in step S701 , the device 200 may receive a request for access to a website providing beauty content from the first user terminal 110 .

In step S702 , the device 200 processes to access the website according to the request for access to the website, provides the website's home page to the first user terminal 110 , and the home page is displayed on the first user terminal An operation of the first user terminal 110 may be controlled to be displayed on the screen of 110 .

In step S703 , the device 200 may obtain the first user information by checking the first user account. At this time, the device 200 checks the first user account logged in to the first user terminal 110 , inquires the user information stored in the database through the first user account, and obtains the first user information from the database. can Here, the first user information is user information about the first user, and may include profile information, lifestyle information, content usage history, and the like of the first user.

In step S704 , the device 200 may receive a query request for the first content from the first user terminal 110 .

Specifically, when the representative image of the first content, which is any one of the beauty content, is clicked on the home page displayed on the screen of the first user terminal 110 , the device 200 provides information from the first user terminal 110 to the first content. You can receive inquiry requests for For example, if the first content is content promoting a first product, the representative image of the first content is an image of the first product, and the inquiry request for the first content is related to inquiring detailed information of the first product. It may be a request for

In step S705 , the device 200 may obtain first content information by checking the first content. In this case, the device 200 may obtain the first content information from the database by checking the first content through the inquiry request for the first content, inquiring the content information stored in the database. Here, the first content information is content information about the first content, and may include attribute information of the first content, user usage history, and the like.

In step S706 , the device 200 may obtain the user inquiry details of the first content through the first content information. Here, the first content information may include the inquiry details of the user who perused the first content, and the user inquiry details of the first content may include the details of which user perusively read the first content for how long.

For example, when the first content is displayed on the screen of the first user terminal 110, from the time the web page for the first content is displayed to the time when the web page for the first content moves to another page, the second Measured as the perusal time of one content, the first user and the perusal time of the first content may be added to the user inquiry history of the first content.

In step S707 , the device 200 may check the reading time for each user based on the user inquiry details of the first content.

For example, when the first user, the second user, and the third user are registered as the inquired users in the user inquiry history of the first content, the device 200 determines the reading time of the first user and the reading of the second user You can check the time and the third user's perusal time, respectively.

In step S708 , the device 200 may calculate the average reading time of the first content through the average value of the reading times checked for each user.

For example, if the time that the first user peruses the first content is 10 seconds, the time that the second user peruses the first content is 30 seconds, and the time that the third user peruses the first content is 50 seconds, The device 200 may calculate the average reading time of the first content as 30 seconds.

In operation S709 , the device 200 may set a reference value according to the length of the average reading time of the first content.

For example, when the average reading time of the first content is 1 minute, the device 200 may set the reference value to 15 seconds, and when the average reading time of the first content is 2 minutes, the device 200 may set the reference value to 25 seconds. The criterion for setting the reference value may be set differently depending on the embodiment.

In operation S710 , the device 200 may calculate the minimum time within the user permissible range as a value obtained by subtracting the reference value from the average reading time of the first content.

For example, when the average reading time of the first content is 1 minute and the reference value is 15 seconds, the device 200 may calculate the minimum time of the user permissible range as 45 seconds.

In step S711 , the device 200 may calculate the maximum time of the user permissible range as a value obtained by adding a reference value to the average reading time of the first content.

For example, when the average reading time of the first content is 1 minute and the reference value is 15 seconds, the device 200 may calculate the maximum time of the user permissible range as 75 seconds.

In operation S712 , the device 200 may set the user tolerance range based on the minimum time of the user tolerance range and the maximum time of the user tolerance range.

For example, when the average reading time of the first content is 1 minute, the device 200 may set the user permissible range to a range of 45 seconds to 75 seconds.

8 is a flowchart illustrating a process of providing content recommendation information by predicting a content reading time according to an exemplary embodiment.

Referring to FIG. 8 , first, in step S801 , the device 200 may obtain the first user information by checking the first user account.

In step S802 , the device 200 may obtain first content information by checking the first content.

In step S803, based on the first user information and the first content information, the reading time of the first user for the first content may be predicted. Here, the first user's perusing time may mean a time required for the first user to peruse the first content.

In step S804 , the device 200 may determine whether the first user's perusal time is within the user permissible range. Here, as described above, the user allowable range may be set differently according to the average reading time.

If it is confirmed in step S804 that the perusal time of the first user is within the user tolerance range, in step S805 , the device 200 provides the first content to the first user terminal 110 , and the first user terminal 110 ) may control the operation of the first user terminal 110 so that a web page for the first content is displayed on the screen.

Here, the web page for the first content is a web page connected by clicking on the representative image of the first content, and may include detailed information about the first content. For example, when the representative image of the first content is an image of the first product, the web page for the first content is a page on which detailed information of the first product is displayed.

That is, when the inquiry request for the first content is received from the first user terminal 110 , the device 200 predicts the reading time of the first user for the first content, and as a result, the reading time of the first user is If it is confirmed that the content is within the user permissible range, it is determined that the first content is suitable for the first user, and the first content may be provided to the first user terminal 110 .

If it is determined in step S804 that the first user's perusal time is not within the user permissible range and is outside the user permissible range, in step S806, the device 200 determines that the perusal time of the first user is shorter than the minimum time of the user permissible range. You can check whether

If it is confirmed in step S806 that the reading time of the first user is shorter than the minimum time of the user permissible range, in step S807, the device 200 provides the recommended information for the second content to the first user terminal 110, The operation of the first user terminal 110 may be controlled so that the recommendation information for the second content is displayed on the screen of the first user terminal 110 . Here, the second content is content that has the same subject as the first content and has a greater number of characters than the first content, and the recommendation information for the second content may include a representative image of the second content.

For example, the first content is content that promotes the first product and is composed of 100 characters and 20 images, and the second content is content that promotes the first product and is composed of 120 characters and 10 images. In the case of , when it is confirmed that the first user's perusal time is shorter than the minimum time of the user permissible range, the device 200 inquires the content information stored in the database to check the second content composed of a greater number of characters than the first content. In addition, it is possible to provide recommendation information on the second content to the first user terminal 110 .

That is, when the inquiry request for the first content is received from the first user terminal 110 , the device 200 predicts the reading time of the first user for the first content, and as a result, the reading time of the first user is If it is determined that the first content is out of the user tolerance range, it is determined that the first content is not suitable for the first user, and if it is confirmed that the first user's perusing time is shorter than the minimum time of the user permissible range, the first user's perusing time In order to increase the number of characters, it is determined that the second content composed of a larger number of characters than the first content is suitable for the first user, and thus recommendation information on the second content may be provided to the first user terminal 110 . In this case, the device 200 may provide the recommendation information for the first content and the second content together to the first user terminal 110 .

If it is determined in step S806 that the perusal time of the first user is longer than the minimum time of the user permissible range, it is determined that the perusive time of the first user is out of the user permissible range, so that the perusing time of the first user is the maximum of the user permissible range. It may be confirmed that the time is longer than the time, and if it is confirmed that the reading time of the first user is longer than the maximum time of the user permissible range, in step S808 , the device 200 transmits the recommendation information for the third content to the first user terminal ( 110), and may control the operation of the first user terminal 110 so that recommendation information on the third content is displayed on the screen of the first user terminal 110 . Here, the third content is content that has the same subject as the first content and has fewer characters than the first content, and the recommendation information for the third content may include a representative image of the third content.

For example, the first content is content promoting the first product and is composed of 100 characters and 20 images, and the third content is content promoting the first product and is composed of 80 characters and 30 images. If it is determined that the first user's perusal time is longer than the maximum time of the user permissible range, the device 200 inquires the content information stored in the database to check the third content composed of fewer characters than the first content. Also, it is possible to provide recommendation information on the third content to the first user terminal 110 .

That is, when the inquiry request for the first content is received from the first user terminal 110 , the device 200 predicts the reading time of the first user for the first content, and as a result, the reading time of the first user is If it is determined that the first content is out of the user tolerance range, it is determined that the first content is not suitable for the first user, and if it is confirmed that the first user's perusing time is longer than the maximum time of the user permissible range, the first user's perusing time In order to reduce the number of characters, it is determined that the third content composed of fewer characters than the first content is suitable for the first user, so that recommendation information on the third content can be provided to the first user terminal 110 . In this case, the device 200 may provide the recommendation information for the first content and the third content together to the first user terminal 110 .

9 is a diagram for explaining learning of a first artificial neural network according to an embodiment.

According to an embodiment, the first artificial neural network may be an algorithm for outputting a beauty product suitable for the user after receiving an analysis result of the user's skin condition. The device 200 for learning the first artificial neural network may be the same device as the device 200 for recommending a beauty product suitable for a user using the learned first artificial neural network, or may be a separate device. Hereinafter, a process in which the first artificial neural network is trained will be described.

First, in step S901 , the device 200 may generate an input based on the user's skin analysis result.

Specifically, the apparatus 200 may perform a process of pre-processing the user's skin analysis result. The pre-processed user's skin analysis result may be directly used as an input of the first artificial neural network, or the input may be generated through a normal process of removing unnecessary information.

In step S902 , the device 200 may apply an input to the first artificial neural network. The first artificial neural network may be an artificial neural network trained according to reinforcement learning. The first artificial neural network may be a Q-Network, a Depp Q-Network (DQN), or a relational network (RL) structure suitable for outputting abstract reasoning through reinforcement learning. The first artificial neural network trained according to reinforcement learning may be updated and optimized by reflecting the evaluation in various rewards.

The first artificial neural network trained according to reinforcement learning may be updated and optimized by reflecting the evaluation in various rewards. For example, as for the first compensation, if the skin problem identified through the user's skin analysis result is the first problem factor, the compensation value is increased when the first product released to improve the first problem factor is selected as the recommended beauty product. The second compensation may be higher, and if the skin problem identified through the user's skin analysis result is the second problem factor, the compensation value will be increased if the second product released to improve the second problem factor is selected as the recommended beauty product. can rise

In step S903 , the device 200 may obtain an output from the first artificial neural network. The output of the first artificial neural network may include information on recommended beauty products selected to improve skin problem factors according to the user's skin analysis result.

The first artificial neural network analyzes the user's skin condition, identifies the skin problem factors in the skin analysis results, selects recommended beauty products to improve the skin problem factors, and outputs information about the selected beauty products. can

In step S904 , the device 200 may evaluate the output of the first artificial neural network and provide a reward. In this case, the evaluation of the output may be divided into a first compensation, a second compensation, and the like.

Specifically, when it is confirmed through the user's skin analysis result that the first problem element is included in the user's skin problem, the device 200 awards more of the first reward as the first product is selected as the recommended beauty product, and , when it is confirmed that the second problem element is included in the user's skin problem through the user's skin analysis result, the more the second product is selected as the recommended beauty product, the more the second reward can be awarded.

In step S905 , the device 200 may update the first artificial neural network based on the evaluation.

Specifically, in the environment in which the first artificial neural network selects and extracts a beauty product suitable for the user through the user's skin analysis result, the device 200 has an expected value of the sum of the rewards. To be maximized, the first artificial neural network may be updated through a process of optimizing a policy for determining actions to be taken in specific states.

Meanwhile, the process of optimizing the policy may be performed through the process of estimating the maximum value of the expected value of the sum of rewards or the maximum value of the Q-function, or estimating the minimum value of the loss function of the Q-function. Estimation of the minimum value of the loss function may be performed through stochastic gradient descent (SGD) or the like. The process of optimizing the policy is not limited thereto, and various optimization algorithms used in reinforcement learning may be used.

The apparatus 200 may gradually update the first artificial neural network by repeating the learning process of the first artificial neural network as described above. Through this, the device 200 may learn the first artificial neural network for outputting a beauty product matching the skin condition through the analysis result of the user's skin condition.

That is, when selecting a beauty product suitable for the user through the analysis result of the user's skin condition, the device 200 reflects reinforcement learning through the first reward, the second reward, etc., and adjusts the analysis criteria, 1 Artificial neural networks can be trained.

10 is an exemplary diagram of a configuration of an apparatus 200 according to an embodiment.

The device 200 according to an embodiment includes a processor 210 and a memory 220 . The apparatus 200 according to an embodiment may be the above-described server or terminal. The processor 210 may include at least one of the devices described above with reference to FIGS. 1 to 9 , or perform at least one method described above with reference to FIGS. 1 to 9 . A person or organization using the apparatus 200 may provide a service related to some or all of the methods described above with reference to FIGS. 1 to 9 .

The memory 220 may store information related to the above-described method or may store a program in which the above-described method is implemented. The memory 220 may be a volatile memory or a non-volatile memory.

The processor 210 may execute a program and control the device 200 . The code of the program executed by the processor 210 may be stored in the memory 220 . The device 200 may be connected to an external device (eg, a personal computer or a network) through an input/output device (not shown) and exchange data.

The device 200 may be used to train an artificial neural network or to use a learned artificial neural network. The memory 220 may include a learning or learned artificial neural network. The processor 210 may learn or execute an artificial neural network algorithm stored in the memory 220 . The apparatus 200 for learning an artificial neural network and the apparatus 200 for using the learned artificial neural network may be the same or may be separate.

The embodiments described above may be implemented by a hardware component, a software component, and/or a combination of a hardware component and a software component. For example, the apparatus, methods and components described in the embodiments may include, for example, a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable gate (FPGA). array), a programmable logic unit (PLU), a microprocessor, or any other device capable of executing and responding to instructions, may be implemented using one or more general purpose or special purpose computers. The processing device may execute an operating system (OS) and one or more software applications running on the operating system. The processing device may also access, store, manipulate, process, and generate data in response to execution of the software. For convenience of understanding, although one processing device is sometimes described as being used, one of ordinary skill in the art will recognize that the processing device includes a plurality of processing elements and/or a plurality of types of processing elements. It can be seen that may include For example, the processing device may include a plurality of processors or one processor and one controller. Other processing configurations are also possible, such as parallel processors.

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 in a computer-readable medium. The computer-readable medium may include program instructions, data files, data structures, etc. alone or in combination. The program instructions recorded on the medium may be specially designed and configured for the embodiment, or may be known and available to those skilled in the art of computer software. Examples of the computer-readable recording medium include magnetic media such as hard disks, floppy disks and magnetic tapes, optical media such as CD-ROMs and DVDs, and magnetic such as floppy disks. - includes magneto-optical media, and hardware devices specially configured to store and execute program instructions, such as ROM, RAM, flash memory, and the like. Examples of program instructions include not only machine language codes such as those generated by a compiler, but also high-level language codes that can be executed by a computer using an interpreter or the like. The hardware devices described above may be configured to operate as one or more software modules to perform the operations of the embodiments, and vice versa.

The software may comprise a computer program, code, instructions, or a combination of one or more thereof, which configures a processing device to operate as desired or is independently or collectively processed You can command the device. The software and/or data may be any kind of machine, component, physical device, virtual equipment, computer storage medium or device, to be interpreted by or to provide instructions or data to the processing device. , or may be permanently or temporarily embody in a transmitted signal wave. The software may be distributed over networked computer systems and stored or executed in a distributed manner. Software and data may be stored in one or more computer-readable recording media.

As described above, although the embodiments have been described with reference to the limited drawings, those skilled in the art may apply various technical modifications and variations based on the above. For example, the described techniques are performed in a different order than the described method, and/or the described components of the system, structure, apparatus, circuit, etc. are combined or combined in a different form than the described method, or other components Or substituted or substituted by equivalents may achieve an appropriate result.

Therefore, other implementations, other embodiments, and equivalents to the claims are also within the scope of the following claims.

Claims (3)

In the method of providing an artificial intelligence-based user-customized beauty service platform performed by a device,
extracting beauty consultation information of the first user based on the consultation information input on the chat space between the first user account and the first counselor account;
extracting lifestyle information of the first user based on the lifestyle information input through the first user terminal to which the first user account is logged;
extracting beauty interest information of the first user on the basis of the beauty contents searched through the first user terminal;
analyzing the skin condition of the first user based on the first user's beauty consultation information, the first user's lifestyle information, and the first user's beauty interest information;
inputting an analysis result on the skin condition of the first user into a first artificial neural network, and obtaining an output from the first artificial neural network;
selecting a first product as a beauty product suitable for the first user based on the output of the first artificial neural network;
transmitting a recommendation notification message for the first product to the first user terminal;
checking a purchase time of the first product when it is confirmed that the first user has purchased the first product based on the purchase history of the first user;
When the period of use of the first product is set as the first period and the second period is set within the first period according to the length of the first period, the second period from the time of purchase of the first product transmitting a photographing request message for the remaining capacity of the first product to the first user terminal when it is confirmed that this has passed;
acquiring a first image generated by photographing the first product at a second time point, which is a time point at which the first product is photographed, when the first product is photographed through the camera of the first user terminal;
analyzing the remaining capacity of the first product remaining at the second time point as a first remaining capacity based on the first image;
A period from the purchase time of the first product to the second time point is set as a third period, the first period and the third period are compared, and the remaining capacity of the first product to remain at the second time point is setting as a first reference dose;
calculating a first difference value by subtracting the first reference capacity from the first remaining capacity;
checking whether the first difference value is out of a preset reference range;
when it is determined that the first difference value is out of the reference range, determining whether the first remaining capacity is greater than the first reference capacity;
transmitting a notification message for an increase in usage of the first product to the first user terminal when it is confirmed that the first remaining capacity is greater than the first reference capacity;
when it is confirmed that the first remaining capacity is less than the first reference capacity, transmitting a notification message for a decrease in usage of the first product to the first user terminal;
when it is confirmed that the first difference value does not deviate from the reference range, checking a second reference capacity set as a minimum residual capacity of the first product;
determining whether the first remaining capacity is less than the second reference capacity;
transmitting a notification message for additional purchase of the first product to the first user terminal when it is confirmed that the first remaining capacity is less than the second reference capacity;
each time an image of a product photographed through the first user terminal is uploaded, additionally giving a first score, which is set to be given when uploading a product image, to the rating of the first user;
each time the beauty content is inquired through the first user terminal, additionally giving a second score, which is set to be given when the beauty content is inquired, to the rating of the first user;
each time beauty consultation is performed through the first user terminal, additionally giving a third score set to be given during beauty consultation to the rating of the first user;
each time a beauty product is purchased through the first user terminal, additionally giving a fourth score, which is set to be given when purchasing a beauty product, to the rating of the first user; and
Based on the rating of the first user, comprising the step of selecting the membership level of the first user,
A method of providing a user-customized beauty service platform based on artificial intelligence. delete delete

Images