KR102573336B1 - Method for recommending an online market based on subscription information and customer information of a customer terminal - Google Patents

Abstract

A method for recommending an online market based on customer information and subscription information of a customer terminal of the present disclosure includes obtaining at least one of online market subscription information and customer information from a customer terminal; determining whether online market subscription information has been obtained from a customer terminal; Calculating a first additional point of the subscription online market based on the number of subscribers, sales, monthly payment amount of the customer, delivery possibility within the deadline, delivery cost, delivery period, number of advertisements, and search volume of the portal site; determining from a subscription online market server whether there is an affiliated online market of the customer's subscription online market; Based on the ratio of subscription online market customers to affiliate online market customers, the number of affiliated online market subscribers, sales, monthly payment amount of customers, possibility of delivery within the deadline, shipping cost, delivery period, number of advertisements, and portal site search volume Calculating a second additional point of the online market; Classifying a customer into any one target customer list among a plurality of customer lists based on customer information of a customer terminal; obtaining additional point calculation factors including a ratio of target customers among total customers, sales, and satisfaction scores from an online market server; calculating a third additional point for each online market based on the additional point calculation factor; and recommending an online market to a customer terminal based on the sum of the first to third additional points.

Description

Method for recommending an online market based on subscription information and customer information of a customer terminal

The present disclosure relates to a method of recommending an online market, and more particularly, to a method of recommending an online market based on subscription information and customer information of a customer terminal.

With the rapid development of Internet-related technologies, a number of online services are provided through the Internet. For example, customers may use their terminals (eg, smart phones) to access sales services provided by the online market. In general, an online market announces its business model through the Internet and uses a server to process data received from a customer terminal.

Servers in online marketplaces can divide their business models into different categories based on the type of service they provide. Also, the server of the online market may provide a category related to a product sales model and products for sale by category to a customer terminal. Accordingly, the customer may select one of a plurality of categories through the customer terminal and view products for sale within the selected category.

With the development of Internet technology, deep learning, and artificial intelligence, attempts are being made to improve user convenience during online shopping. Korean Patent Publication No. 10-2015-0036128 discloses a method and apparatus for recommending clothing products. In this document, a specific clothing product is identified based on a preset correspondence relationship between an attribute characteristic related to the clothing product and a user ID.

The present disclosure intends to provide a method of recommending an online market that can provide utility to a customer based on subscription information and customer information stored in a customer terminal, in a situation where there are many online markets. In addition, the present disclosure intends to recommend a product for sale based on customer information in the recommended online market, and finally propose a price of the recommended product for sale.

Korean Patent Publication No. 10-2015-0036128

An object of the present disclosure is to provide a method of recommending an online market expected to be highly useful to a customer based on subscription information and customer information obtained from a customer terminal.

In addition, an object of the present disclosure is to provide a method for improving sales power of an online market by recommending a sales product that is expected to be highly useful to a customer based on customer information in the recommended online market.

In addition, an object of the present disclosure is to provide a method for securing customer attraction in an online market by automatically determining a price of a product for sale in consideration of a purchase price of a product desired by a customer and a selling price of a product in another online market.

In addition, an object of the present disclosure is to provide a method for securing market competitiveness in an online market by determining a price of a product for sale by additionally considering various variables of the international economy.

According to the technical idea of the present disclosure, a method for recommending an online market based on customer information and subscription information of a customer terminal obtains at least one of online market subscription information and customer information from a customer terminal by an online market recommendation server. doing; determining whether online market subscription information has been obtained from a customer terminal by the online market recommendation server; By the online market recommendation server, based on the number of subscribers of the subscription online market, sales, monthly payment amount of the customer, possibility of delivery within the deadline, shipping cost, delivery period, number of advertisements, and portal site search volume, Calculating additional points; determining, by the online market recommendation server, whether there is an affiliated online market of the customer's subscription online market from the subscription online market server; By the online market recommendation server, the ratio of subscription online market customers among affiliated online market customers, the number of affiliated online market subscribers, sales, customer's monthly payment amount, delivery possibility within the deadline, shipping cost, delivery period, number of advertisements, Calculating a second additional point of an affiliated online market based on a portal site search volume; classifying a customer into any one target customer list among a plurality of customer lists based on customer information of a customer terminal by the online market recommendation server; obtaining, by the online market recommendation server, an additional point calculation factor including a ratio of target customers out of all customers, sales, and satisfaction scores from the online market server; calculating a third additional point for each online market based on the additional point calculating factor by the online market recommendation server; and recommending, by the online market recommendation server, an online market to a customer terminal based on the sum of the first additional points, the second additional points, and the third additional points.

In an exemplary embodiment, when the customer's subscription information is obtained in the step of determining whether the online market subscription information is acquired from the customer terminal, the step of calculating a first additional point is performed, and the online market subscription from the customer terminal When the customer's subscription information is not acquired in the step of determining whether the information has been acquired, the step of classifying the customer into one of a plurality of customer lists based on the customer information is performed.

In an exemplary embodiment, in the step of determining from the subscription online market server whether there is an affiliate online market of the customer's subscription online market, if it is determined that there is an affiliate online market, the step of calculating a second additional point is performed, and the customer In the step of determining from the subscription online market server whether there is an affiliate online market of the subscription online market, if it is determined that there is no affiliate online market, the customer is selected as one of the plurality of customer lists based on the customer information. It is characterized in that the step of classifying is performed.

In an exemplary embodiment, the first added point is calculated by Equation 1 below,

[Equation 1]

In Equation 1, AP1 is the first additional point of the subscription online market subscribed by the customer, Cf1 is the sales weight for the payment amount of the customer in the subscription online market, P_m1 is the monthly payment amount of the customer in the subscription online market, Cf2 is the shipping weight of the subscription online market, T_d1 is the delivery probability of products sold in the subscription online market, T_m1 is the average shipping cost of products sold in the subscription online market, and T_t1 is the average of products sold in the subscription online market Delivery period, Cf3 is the weight of the market competitiveness of the subscription online market, S_b1 is the number of subscribers of the subscription online market, S_m1 is the sales of the subscription online market, Cf4 is the weight of the advertising power of the subscription online market, and Ad_m1 is the weight of the advertising power of the subscription online market. Ad_p1, the number of online advertisements in the subscription online market, is defined as the search volume in the portal site of the subscription online market.

In an exemplary embodiment, the second added point is calculated by Equation 2 below,

[Equation 2]

In Equation 2, AP2 is the second additional point of the affiliated online market, Cf5 is the shipping weight of the affiliated online market, T_d2 is the delivery possibility of products sold in the affiliated online market within the deadline, and T_m2 is the product sold in the affiliated online market. T_t2 is the average delivery cost of products, T_t2 is the average delivery period of products sold in the affiliate online market, Cf6 is the weight for the market competitiveness of the affiliate online market, S_b2 is the number of subscribers of the affiliate online market, S_m2 is sales of the affiliate online market Ad_m2 is the number of online advertisements in the affiliated online market, Ad_p2 is the search volume in the portal site of the affiliated online market, and Cf8 is the number of subscription online market customers within the affiliated online market. It is a weight for the ratio, and Cu_t2 is characterized in that it is defined as the ratio of subscription online market customers to affiliate online market customers.

In an exemplary embodiment, the third additional point is calculated by Equation 3 below,

[Equation 3]

In Equation 3, AP3 is the third additional point of the online market, Cf9 is the weight for the market competitiveness of the online market, S_m3 is the sales of the affiliated online market, and Cf10 is the weight for the influence of the online market on the target customer , Ps_3 is the percentage of target customers out of all customers in the online market, Cf11 is a weight related to the satisfaction index of customers in the online market, and Sf_3 is defined as the satisfaction score of customers using the online market.

In an exemplary embodiment, the step of recommending an online market to a customer terminal based on the sum of the first additional points, the second additional points, and the third additional points includes, by the online market recommendation server, the first additional points, determining whether the sum of the second additional points and the third additional points exceeds a reference value; and recommending, by the online market recommendation server, an online market in which a sum of the first additional points, the second additional points, and the third additional points exceeds a reference value to a customer terminal.

The method according to the technical idea of the present disclosure may recommend an online market expected to be highly useful to a customer based on subscription information and customer information acquired from a customer terminal.

In addition, the method of the present disclosure may improve sales power of the online market by recommending products for sale that are expected to be highly useful to customers based on customer information in the recommended online market.

In addition, the method of the present disclosure can secure customer attraction in the online market by automatically determining the price of the product for sale in consideration of the purchase price of the product desired by the customer and the selling price of the product in other online markets.

In addition, the method of the present disclosure can secure market competitiveness of the online market by determining the price of a product for sale by additionally considering various variables of the international economy.

1 is a flow chart showing the flow of a method for recommending an online market based on customer information and subscription information of a customer terminal according to an exemplary embodiment of the present disclosure.
Fig. 2 is a flow chart showing the flow of a method for recommending an online market, recommending a product for sale in the online market, and controlling a selling price of the recommended product for sale, according to an exemplary embodiment of the present disclosure.
3 is a flow chart showing a flow of recommending a product for sale in a recommended online market using customer information according to an exemplary embodiment of the present disclosure.
4 is a flow chart showing a flow of recommending a product for sale in an online market using customer information according to an exemplary embodiment of the present disclosure.
5 is a flow chart showing a flow of recommending a product for sale in an online market using customer information according to an exemplary embodiment of the present disclosure.
6 is a flow chart showing a flow of determining a selling price of a recommended selling product based on selling information of another online market and a customer's desired purchase price according to an exemplary embodiment of the present disclosure.
7 is a flow chart showing a flow of determining a selling price of a recommended selling product based on selling information of another online market and a customer's desired purchase price according to an exemplary embodiment of the present disclosure.
8 is a block diagram illustrating a pricing system according to an exemplary embodiment of the present disclosure.
Fig. 9 is a flow chart illustrating a method of controlling a sales price of a product for sale based on an exchange rate according to an exemplary embodiment of the present disclosure.
Fig. 10 is a flowchart illustrating a price control method according to an exemplary embodiment of the present disclosure.
Fig. 11 is a table showing a similar product DB according to an exemplary embodiment of the present disclosure.
12 is a flow chart illustrating a pricing method according to an exemplary embodiment of the present disclosure.
Fig. 13 is a flowchart illustrating a pricing method according to an exemplary embodiment of the present disclosure.
14A and 14B are graphs showing exchange rate trends according to exemplary embodiments of the present disclosure.
15 is a flow chart illustrating a pricing method according to an exemplary embodiment of the present disclosure.
16 is a flowchart illustrating a pricing method according to an exemplary embodiment of the present disclosure.
Fig. 17 is a flowchart illustrating a pricing method according to an exemplary embodiment of the present disclosure.
18 is a flowchart illustrating a pricing method according to an exemplary embodiment of the present disclosure.
Fig. 19 is a flowchart illustrating a pricing method according to an exemplary embodiment of the present disclosure.
20 is a diagram showing a customer terminal, an online market recommendation server, and another online market server according to an exemplary embodiment of the present disclosure.

Hereinafter, preferred embodiments of the present disclosure will be described in detail with reference to the accompanying drawings. Advantages and features of the present disclosure, and methods of achieving them, will become clear with reference to the embodiments described below in detail in conjunction with the accompanying drawings. However, the technical idea of the present disclosure is not limited to the following embodiments and can be implemented in various different forms, and only the following embodiments complete the technical idea of the present disclosure, and in the technical field to which the present disclosure belongs. It is provided to completely inform those skilled in the art of the scope of the present disclosure, and the technical spirit of the present disclosure is only defined by the scope of the claims.

In adding reference numerals to components of each drawing, it should be noted that the same components have the same numerals as much as possible even if they are displayed on different drawings. In addition, in describing the present disclosure, if it is determined that a detailed description of a related known configuration or function may obscure the gist of the present disclosure, the detailed description will be omitted.

Unless otherwise defined, all terms (including technical and scientific terms) used in this specification may be used with meanings commonly understood by those of ordinary skill in the art to which this disclosure belongs. In addition, terms defined in commonly used dictionaries are not interpreted ideally or excessively unless explicitly specifically defined. Terminology used herein is for describing the embodiments and is not intended to limit the present disclosure. In this specification, singular forms also include plural forms unless specifically stated otherwise in a phrase.

Also, terms such as first, second, A, B, (a), and (b) may be used in describing the components of the present disclosure. These terms are only used to distinguish the component from other components, and the nature, order, or order of the corresponding component is not limited by the term. When an element is described as being “connected,” “coupled to,” or “connected” to another element, that element is directly connected or connectable to the other element, but there is another element between the elements. It will be understood that elements may be “connected”, “coupled” or “connected”.

As used in this disclosure, "comprises" and/or "comprising" means that a stated component, step, operation, and/or element is one or more other components, steps, operations, and/or elements. Existence or additions are not excluded.

Components included in one embodiment and components including common functions may be described using the same names in other embodiments. Unless stated to the contrary, descriptions described in one embodiment may be applied to other embodiments, and detailed descriptions will be omitted to the extent of overlapping or to the extent that those skilled in the art can clearly understand. can

Hereinafter, the present invention will be described in detail with reference to preferred embodiments and accompanying drawings of the present invention.

1 is a flow chart showing the flow of a method ( S10 ) of recommending an online market based on subscription information and customer information of a customer terminal according to an exemplary embodiment of the present disclosure.

The method (S10) of recommending an online market based on subscription information and customer information of a customer terminal according to the present disclosure may be performed by an online market recommendation server 2000 including a processor 2100 of FIG. 20 to be described later.

The method of recommending an online market based on subscription information and customer information of a customer terminal of the present disclosure (S10) includes obtaining at least one of online market subscription information and customer information from a customer terminal (S110), The step of determining whether the subscription information of the online market has been acquired (S120), the number of subscribers of the subscription online market, sales, monthly payment amount of the customer, possibility of delivery within the deadline, shipping cost, delivery period, number of advertisements, and portal site search volume Calculating the first additional point based on (S130), determining whether there is an affiliate online market of the subscription online market (S140), ratio of subscription online market customers among affiliate online market customers, number of subscribers of affiliate online market, sales , Calculating a second additional point based on the customer's monthly payment amount, delivery possibility within the deadline, delivery cost, delivery period, number of advertisements, and portal site search volume (S150), a plurality of customers based on customer information of the customer terminal Classifying customers into one of the target customer lists (S160), obtaining additional point calculation factors including the percentage of the target customer among all customers of the online market server, sales, and satisfaction scores (S170), additional points It may include calculating a third additional point based on the calculation factor (S180) and recommending an online market to the customer terminal based on the sum of the first to third additional points (S190).

In step S110 , the online market recommendation server 2000 may obtain at least one of online market subscription information and customer information from the customer terminal 1000 .

The subscription information may include information of an online market where a customer regularly pays a subscription fee and receives a delivery benefit for product purchase, a purchase price benefit, and the like. However, it is not limited thereto, and the subscription information may further include information of an online market in which a customer regularly accesses and receives a delivery benefit for a product purchase, a purchase price benefit, and the like, even if the customer does not pay a subscription fee.

Also, the customer information may include at least one of age, gender, and occupation of the customer acquired from the customer terminal. However, it is not limited thereto, and the customer information may include the customer's name, home address, work address, monthly consumption amount of the online market, and the like.

In step S110 , the online market recommendation server 2000 may obtain at least one of the aforementioned subscription information and customer information from the customer terminal 1000 .

In an exemplary embodiment, the online market recommendation server 2000 may obtain subscription information and customer information from the customer terminal 1000 through scraping technology. The scraping technology may be defined as a technology of automatically extracting customer's personal information using customer's authentication information. However, it is not limited thereto, and the online market recommendation server 2000 may call subscription information and customer information from the customer terminal 1000 using an API.

In an exemplary embodiment, in step S110, the online market recommendation server 2000 requests the customer terminal 1000 to authenticate the customer himself, and when the customer authentication is performed, the online market recommendation server 2000 sends the customer A step of collecting data related to subscription information and customer information using text and pictures provided by the terminal 1000 may be included.

For example, the online market recommendation server 2000 includes text and pictures provided by an application executed by the customer terminal 1000 (including online market subscription payment details, online market consumption details, and delivery information of purchased products). text and photos) to collect data related to subscription information and customer information.

In addition, in step S110, the online market recommendation server 2000 stores subscription information and personal information-related data collected from the customer terminal 1000 in the memory 2200, and extracts and uses the data as needed. . Accordingly, in the online market recommendation method ( S10 ), the online market recommendation server 2000 may continuously use subscription information and customer information obtained through one-time scraping.

In step S120, the online market recommendation server 2000 may determine whether online market subscription information has been obtained from the customer terminal.

The accessibility of the online market for each customer will be formed differently based on the customer's propensity, age, gender, etc. Accordingly, while some of the customers (eg, those in their 20s to 40s) may be using the subscription service of the online market due to relatively large accessibility of the online market, other customers (eg, those in their 60s or older) The online market's accessibility is relatively small, so you may not be using the online market's subscription service.

Accordingly, in step S120, the online market recommendation server 2000 of the present disclosure may perform a step of determining whether subscription information of the online market is obtained from the customer terminal 1000 in step S110.

In step S120, when the online market recommendation server 2000 obtains online market subscription information from the customer terminal 1000, a step of calculating a first additional point for the subscription online market may be performed (S130). Step S130 will be described later in more detail.

In addition, in step S120, if the online market recommendation server 2000 does not acquire online market subscription information from the customer terminal 1000, steps S130 to S150 to be described later are omitted, and based on the customer information of the customer terminal Classifying a customer into any one target customer list among a plurality of customer lists (S160) may be performed. Step S160 will be described later in more detail.

In step S130, the online market recommendation server 2000 determines the subscription online market based on the number of subscribers, sales, customer's monthly payment amount, delivery possibility within the deadline, shipping cost, delivery period, number of advertisements, and portal site search volume of the subscription online market. The first additional point of the market may be calculated.

Specifically, the first added point may be calculated by Equation 1 below.

In Equation 1, AP1 is the first additional point of the subscription online market subscribed by the customer, Cf1 is the sales weight for the payment amount of the customer in the subscription online market, P_m1 is the monthly payment amount of the customer in the subscription online market, Cf2 is the shipping weight of the subscription online market, T_d1 is the delivery probability of products sold in the subscription online market, T_m1 is the average shipping cost of products sold in the subscription online market, and T_t1 is the average of products sold in the subscription online market Delivery period, Cf3 is the weight of the market competitiveness of the subscription online market, S_b1 is the number of subscribers of the subscription online market, S_m1 is the sales of the subscription online market, Cf4 is the weight of the advertising power of the subscription online market, and Ad_m1 is the weight of the advertising power of the subscription online market. Ad_p1, the number of online advertisements in the subscription online market, may be defined as the search volume in the portal site of the subscription online market.

In addition, when the online market recommendation server 2000 does not detect at least one value of the variables in Equation 1, the variable not detected in Equation 1 is applied as 1, and Equation 1 can be calculated. there is.

Specifically, the first additional point AP1 of the subscription online market to which the customer subscribes may be calculated in consideration of the payment amount of the corresponding customer in the subscription online market. For example, if the customer has a high regular payment amount in the subscription online market, the first additional point may be calculated relatively large.

When calculating the first additional point AP1 using Equation 1, the monthly payment amount P_m1 of the customer in the subscription online market may be calculated as an exponential value unlike other variables. That is, the first additional point is more weighted on the customer's payment amount in the subscription online market than delivery, market competitiveness, and advertising power of the subscription online market, so that a relatively high score can be given to the online market that customers frequently use and purchase. there is.

Also, the first additional point AP1 may be calculated in consideration of delivery information of the subscription online market. For example, when a product in the subscription online market is more likely to be delivered within the deadline, the average delivery cost is low, and the average delivery period is short, the first additional point AP1 may be calculated relatively large. Conversely, when the possibility of delivering products in the subscription online market within the deadline is low, the average delivery cost is high, and the average delivery period is long, the first additional point AP1 may be calculated relatively small.

Also, the first additional point AP1 may be calculated in consideration of market competitiveness of the subscription online market. For example, when the number of subscribers of the subscription online market is large and the sales of the subscription online market are large, the first additional point AP1 may be calculated relatively large.

Also, the first additional point AP1 may be calculated in consideration of the advertising power of the subscription online market. For example, when the number of online advertisements in the subscription online market and the number of searches in the portal site are large, the first additional point AP1 may be calculated relatively large.

The first additional point (Ap1) of the subscription online market of the present disclosure may be calculated in consideration of customer payment information in the subscription online market, shipping information of the subscription online market, market competitiveness of the subscription online market, and advertising power of the subscription online market. In this case, the online market recommendation server 2000 may recommend to the customer terminal 1000 an online market equipped with customer attractiveness, prompt delivery, and market competitiveness.

In step S130, the online market recommendation server 2000 may calculate a first additional point AP1 for each of a plurality of online markets subscribed to by the customer among a plurality of online markets, and then store the first additional point AP1. there is.

In step S140, the online market recommendation server 2000 may determine whether there is an affiliated online market of the subscription online market.

Multiple online marketplaces are collaborating with other online marketplaces to improve their purchasing power. For example, a service subscribing to a first online market may receive a delivery benefit, a purchase price benefit, and the like from a second online market affiliated with the first online market.

The online market recommendation server 2000 of the present disclosure may calculate second additional points AP2 of online markets affiliated with the online market subscribed to by the customer and add the first additional points AP1. After that, based on the added points, an online market equipped with attractiveness of customers, prompt delivery, and market competitiveness may be recommended to the customer terminal 1000 .

Accordingly, step S140 may include a step in which the online market recommendation server 2000 accesses the subscription online market server and acquires affiliated online market information.

In an exemplary embodiment, the online market recommendation server 2000 may acquire information of an affiliated online market through scraping technology. However, the present invention is not limited thereto, and the online market recommendation server 2000 may obtain information of an affiliated online market using an API.

In step S140, when the online market recommendation server 2000 obtains affiliated online market information of the subscription online market, a step of calculating a second additional point of the affiliated online market may be performed (S150). Step S150 will be described later in more detail.

In addition, in step S140, if the online market recommendation server 2000 fails to obtain affiliated online market information of the subscription online market, the customer is selected as one of a plurality of customer lists based on the customer information of the customer terminal. A step of classifying (S160) may be performed. Step S160 will be described later in more detail.

In step S150, the online market recommendation server 2000 determines the percentage of subscription online market customers among affiliated online market customers, the number of affiliated online market subscribers, sales, the customer's monthly payment amount, delivery possibility within the deadline, delivery cost, and delivery period. , the number of advertisements, and the search volume of the portal site, the second additional point of the affiliated online market can be calculated.

Specifically, the second added point may be calculated by Equation 2 below.

In Equation 2, AP2 is the second additional point of the affiliated online market, Cf5 is the shipping weight of the affiliated online market, T_d2 is the delivery possibility of products sold in the affiliated online market within the deadline, and T_m2 is the product sold in the affiliated online market. T_t2 is the average delivery cost of products, T_t2 is the average delivery period of products sold in the affiliate online market, Cf6 is the weight for the market competitiveness of the affiliate online market, S_b2 is the number of subscribers of the affiliate online market, S_m2 is sales of the affiliate online market Ad_m2 is the number of online advertisements in the affiliated online market, Ad_p2 is the search volume in the portal site of the affiliated online market, and Cf8 is the number of subscription online market customers within the affiliated online market. It is a weight for the ratio, and Cu_t2 may be defined as a ratio of subscription online market customers to affiliate online market customers.

In addition, when the online market recommendation server 2000 does not detect at least one value of the variables in Equation 2, the variable not detected in Equation 2 is applied as 1, and Equation 2 can be calculated. there is.

Specifically, the second additional point AP2 of the affiliated online market may be calculated in consideration of the ratio of customers of the subscription online market among customers of the affiliated online market. For example, when the ratio of customers of the subscription online market among customers of the affiliate online market is high, the second additional points may be calculated relatively large.

When calculating the second additional point AP2 using Equation 2, the customer ratio Cu_t2 of the subscription online market within the affiliate online market may be calculated as an index value unlike other variables. In other words, the second additional point is more weighted on the ratio of customers in the subscription online market within the affiliated online market rather than delivery, market competitiveness, and advertising power of the subscription online market, so that a significant number of customers in the subscription online market receive additional benefits (delivery benefits, Relatively high scores can be given to affiliated online markets enjoying purchase benefits, etc.).

In addition, the second additional point AP2 may be calculated in consideration of delivery information of an affiliated online market. For example, when the possibility of delivery within the deadline of the product of the affiliated online market is high, the average delivery cost is small, and the average delivery period is short, the second additional point AP2 may be calculated relatively large. Conversely, when the possibility of delivery within the deadline of the product of the affiliated online market is low, the average delivery cost is high, and the average delivery period is long, the second additional point AP2 may be calculated relatively small.

In addition, the second additional point AP2 may be calculated in consideration of the market competitiveness of the affiliated online market. For example, when the number of subscribers to the affiliated online market is large and sales of the affiliated online market are large, the second additional point AP2 may be calculated relatively large.

In addition, the second additional point AP2 may be calculated in consideration of advertising power of an affiliated online market. For example, when the number of online advertisements in the affiliated online market and the amount of searches in the portal site are large, the second additional point AP2 may be calculated relatively large.

The second additional point (AP2) of the affiliate online market of the present disclosure is calculated by considering the customer ratio of the subscription online market within the affiliate online market, shipping information of the subscription online market, market competitiveness of the subscription online market, and advertising power of the subscription online market Therefore, the online market recommendation server 2000 may recommend to the customer terminal 1000 an online market equipped with customer attractiveness, prompt delivery, and market competitiveness. For example, an affiliated online market with many benefits that customers of the subscription online market can enjoy may be provided to the customer terminal 1000 . Accordingly, the customer of the subscription online market may also acquire information about an affiliated online market that he or she has not previously known about.

In step S160 , the online market recommendation server 2000 may classify the customer into any one target customer list among a plurality of preset customer lists based on the customer information obtained from the customer terminal 1000 in step S110 .

In an exemplary embodiment, in step S160 , the online market recommendation server 2000 may use a plurality of customer lists previously stored in the memory 2200 . The plurality of customer lists may be customer lists classified by age, gender, and occupation.

In an example embodiment, the first plurality of customer lists are age (eg, teenagers, 20's, 30's, etc.), gender (eg, male, female), and occupation (eg, office worker, professional, doctor, businessman, etc.) may be a list of customers classified by any one.

For example, the first plurality of customer lists may be customer lists set by age, such as those in their teens, 20s, and 30s. Also, the first plurality of customer lists may be male and female customer lists. Also, the first plurality of customer lists may be customer lists set to include office workers, professionals, doctors, and businessmen.

In an example embodiment, the second plurality of customer lists may be sorted by a combination of two of age, gender, and occupation. That is, the second plurality of customer lists may be customer lists classified according to age and gender of customers, gender and occupation of customers, or age and occupation of customers.

For example, the second plurality of customer lists may be a list of customers classified as male teenagers, female teenagers, male in their 20s, female in their 20s, and the like. Also, the second plurality of customer lists may be customer lists classified into female students, male students, female entrepreneurs, male professionals, and the like. Also, the second plurality of customer lists may be customer lists classified into students in their twenties, office workers in their thirties, and businessmen in their fifties.

In an example embodiment, the third plurality of customer lists may be a customer list classified by a combination of all age, gender and occupation.

In step S160 , the online market recommendation server 2000 may classify the customer into one of the first to third customer lists based on the customer information obtained in step S110 .

For example, in step S110, when the online market recommendation server 2000 acquires one customer information among age, gender, and occupation, the online market recommendation server 2000 selects one of the first plurality of customer lists. Customers can be classified as one. In addition, when the online market recommendation server 2000 acquires two types of customer information among age, gender, and occupation, the online market recommendation server 2000 may classify the customer as one of a plurality of second customer lists. there is. In addition, when the online market recommendation server 2000 acquires three pieces of customer information among age, gender, and occupation, the online market recommendation server 2000 may classify the customer as one of a plurality of third customer lists. there is.

In an exemplary embodiment, the online market recommendation server 2000 may automatically classify a customer into one of a plurality of customer lists by utilizing artificial intelligence (AI) based on customer information obtained from the customer terminal 1000. can

In step S170, the online market recommendation server 2000 obtains additional point calculation factors including a ratio of target customers among online market customers, sales, and satisfaction scores (eg, ratings, star ratings, etc.) from a plurality of online market servers. can do.

For example, the online market recommendation server 2000 may obtain an additional point calculation factor from the online market server through a scraping technique. Also, the online market recommendation server 2000 may obtain an additional point calculation element from the online market server using an API. However, the present invention is not limited thereto, and the online market recommendation server 2000 may receive an additional point calculation element from the online market recommendation server 2000 .

In step S180, the online market recommendation server 2000 may calculate a third additional point of the online market based on the additional point calculation factor.

Specifically, the third added point may be calculated by Equation 3 below.

In Equation 3 above, AP3 is the third additional point of the online market. For example, the third additional point AP3 may be calculated for all online markets stored in the memory of the online market recommendation server 2000, including subscription online markets and affiliated online markets.

At this time, Cf9 is the weight of the market competitiveness of the online market, S_m3 is the sales of the affiliated online market, Cf10 is the weight of the online market's influence on the target customer, and Ps_3 is the target customer's total number of online market customers. ratio, Cf11 is a weight related to the satisfaction index of customers in the online market, and Sf_3 may be defined as a satisfaction score (eg, rating, star rating, etc.) of customers using the online market.

It can be inferred that the higher the ratio of the target customer among customers in the online market, the more products for sale targeting the target customer. Accordingly, the online market recommendation server 2000 of the present disclosure may consider the ratio of the target customer among online market customers as an index value and place a weight on the ratio of the target customer rather than other variables.

The third additional point (AP3) of the online market of the present disclosure can be calculated in consideration of the ratio of target customers among online market customers, sales, and satisfaction scores, so that the online market recommendation server 2000 provides an online market suitable for the customer's inclination. may be recommended to the customer terminal 1000 . In addition, the online market recommendation server 2000 may recommend to the customer terminal 1000 an online market equipped with customer attractiveness and market competitiveness.

In step S190 , the online market recommendation server 2000 may recommend an online market to the customer terminal 1000 based on the sum of the first additional points, the second additional points, and the third additional points.

In an exemplary embodiment, in step S190, the online market recommendation server 2000 determines whether the sum of the first additional points, the second additional points, and the third additional points exceeds a reference value; and recommending, to a customer terminal, an online market in which a sum of the first additional points, the second additional points, and the third additional points exceeds a reference value.

Since the method of the present disclosure can recommend an online market based on online market subscription information and customer information obtained from the customer terminal 1000, the method of the present disclosure provides customers with an online market that is expected to be highly useful. can recommend That is, the online market recommendation server 2000 may recommend an online market equipped with customer attractiveness, market competitiveness, and delivery power to the customer terminal 1000, and accordingly, a customer using the online market recommendation server 2000 satisfaction can be improved.

2 is a flow chart showing the flow of a method (S1) of recommending an online market, recommending a sale product in the online market, and controlling a selling price of the recommended sale product according to an exemplary embodiment of the present disclosure.

Referring to FIG. 2 , a method (S1) according to an exemplary embodiment of the present disclosure includes a step (S10) of recommending an online market using at least one of online market subscription information and customer information of a customer terminal, customer information recommending a product for sale in the recommended online market using (S20), determining the price of the recommended product for sale based on the sales information and desired purchase price of other online markets (S30), and selling based on the exchange rate It may include controlling the price of the product (S40).

Since the technical concept of step S10 is duplicated with the description with reference to FIG. 1 , detailed description thereof will be omitted.

Hereinafter, recommending a product for sale in the recommended online market using customer information (S20), determining a price for a product for sale recommended based on sales information and a desired purchase price in another online market (S30), And the step (S40) of controlling the price of the product for sale based on the exchange rate will be described in detail later.

3 is a flow chart showing the flow of recommending a product for sale in the recommended online market using customer information (S20a) according to an exemplary embodiment of the present disclosure. Step S20 of the present disclosure described above may include steps S20a to S20c.

Step S20a of the present disclosure may be performed after performing step S10 described with reference to FIG. 1 . Hereinafter, a plurality of steps included in S20a of the present disclosure will be described in more detail.

In the step (S20a) of recommending a product for sale in an online market using customer information according to an exemplary embodiment of the present disclosure, acquiring customer information including at least one of age, gender, and occupation of the customer from the customer terminal ( S210), classifying the customer into one of a plurality of preset customer lists based on the obtained customer information (S220), a plurality of websites and social network services (SNS) accessed by the customer from the customer terminal Acquiring search keywords from a customer terminal (S230), arranging search records among a plurality of search keywords in order of increasing number of search records (S240), and acquiring target keywords (S240), synonyms and synonyms of the target keyword are extracted to target keyword groups Obtaining (S250), extracting a sales product with a name overlapping with synonyms and similar words in the target keyword group from among a plurality of recommended sales products for each preset target customer list (2160), and removing the extracted sales product. 1 may include a step of determining the recommended selling product (S270).

In step S210 , the online market recommendation server 2000 may obtain customer information such as age, gender, and occupation of the customer from the customer terminal 1000 .

In an exemplary embodiment, the online market recommendation server 2000 may obtain customer information from the customer terminal 1000 through scraping technology. The scraping technology may be defined as a technology of automatically extracting customer's personal information using customer's authentication information. However, it is not limited thereto, and the online market recommendation server 2000 may call customer information from the customer terminal 1000 using an API.

For example, in step S210, the online market recommendation server 2000 requests the customer terminal 1000 to authenticate the customer himself. 1000) may include collecting data related to customer information using text and pictures provided.

In addition, in step S210, the online market recommendation server 2000 stores data related to personal information collected from the customer terminal 1000 in the memory 2200, and can extract and use the data as needed. Accordingly, the online market recommendation server 2000 may continue to use customer information obtained through one-time scraping.

For example, step S210 may use customer information acquired in step S110 of FIG. 1 . When customer information is acquired in step S110 of FIG. 1 , step S20a may omit the aforementioned step S210.

In step S220 , the online market recommendation server 2000 may classify a customer into one of a plurality of preset customer lists based on customer information obtained from the customer terminal 1000 .

In an exemplary embodiment, in step S220 , the online market recommendation server 2000 may use a plurality of customer lists previously stored in the memory 2200 . The plurality of customer lists may be customer lists classified by age, gender, and occupation.

In an example embodiment, the first plurality of customer lists are age (eg, teenagers, 20's, 30's, etc.), gender (eg, male, female), and occupation (eg, office worker, professional, doctor, businessman, etc.) may be a list of customers classified by any one.

For example, the first plurality of customer lists may be customer lists set by age, such as those in their teens, 20s, and 30s. Also, the first plurality of customer lists may be male and female customer lists. Also, the first plurality of customer lists may be customer lists set to include office workers, professionals, doctors, and businessmen.

In an example embodiment, the second plurality of customer lists may be sorted by a combination of two of age, gender, and occupation. That is, the second plurality of customer lists may be customer lists classified according to age and gender of customers, gender and occupation of customers, or age and occupation of customers.

For example, the second plurality of customer lists may be a list of customers classified as male teenagers, female teenagers, male in their 20s, female in their 20s, and the like. Also, the second plurality of customer lists may be customer lists classified into female students, male students, female entrepreneurs, male professionals, and the like. Also, the second plurality of customer lists may be customer lists classified into students in their twenties, office workers in their thirties, and businessmen in their fifties.

In an example embodiment, the third plurality of customer lists may be a customer list classified by a combination of all age, gender and occupation.

In step S220, the online market recommendation server 2000 may classify the customer into one of the first to third customer lists based on the customer information obtained in step S210.

For example, in step S210, when the online market recommendation server 2000 acquires one customer information among age, gender, and occupation, the online market recommendation server 2000 selects one of the first plurality of customer lists. Customers can be classified as one. In addition, when the online market recommendation server 2000 acquires two types of customer information among age, gender, and occupation, the online market recommendation server 2000 may classify the customer as one of a plurality of second customer lists. there is. In addition, when the online market recommendation server 2000 acquires three pieces of customer information among age, gender, and occupation, the online market recommendation server 2000 may classify the customer as one of a plurality of third customer lists. there is.

In an exemplary embodiment, the online market recommendation server 2000 may automatically classify a customer into one of a plurality of customer lists by utilizing artificial intelligence (AI) based on customer information obtained from the customer terminal 1000. can For example, the online market recommendation server 2000 obtains at least one customer information of age, gender, and occupation from the customer terminal 1000 by using artificial intelligence, and based on the acquired customer information, a plurality of preset A customer can be classified as one of the customer lists of

In step S230 , the online market recommendation server 2000 may obtain from the customer terminal 1000 a plurality of search keywords of websites and social network services (SNS) accessed by the customer from the customer terminal 1000 .

In an exemplary embodiment, in step S230, the online market recommendation server 2000 scrapes and collects keywords searched for on websites, portal sites, social network services, etc. accessed by the customer terminal 1000, and stores them in the memory 2200. can be saved However, it is not limited to this, and in step S230, the online market recommendation server 2000 calls the keyword searched for on the website, portal site, social network service, etc. accessed by the customer terminal 1000 using an API (Application Programming Interface). and can be stored in the memory 2000.

For example, when a customer searches for shoes, bags, neck pain, dizziness, anemia, etc. on portal sites and social networks, in step S230, the online market recommendation server 2000 uses scraping technology or API to the customer terminal ( Keywords such as shoes, bag, neck pain, dizziness, and anemia may be called from 1000 and stored in the memory 2000.

In step S240, the online market recommendation server 2000 may obtain a target keyword by arranging a plurality of search keywords based on at least one of search frequency and search time.

In an exemplary embodiment, in step S240, the online market recommendation server 2000 may sort the keywords acquired in step S230 in order of search frequency. For example, the number of searches for 'shoes, bags, sore throat, dizziness, anemia', which is a keyword searched by a customer on a portal site and a social network from a customer terminal 1000, is '5 times, 3 times, 12 times, and 1 time', respectively. In the case of 'time, twice', the online market recommendation server 2000 may sort the keywords in the order of 'sore throat, shoes, bag, anemia, dizziness'.

At this time, the online market recommendation server 2000 may determine a keyword with the greatest number of searches as a target keyword. For example, the online market recommendation server 2000 may determine a keyword of 'throat pain', which is searched the most, as a target keyword.

However, it is not limited thereto, and the online market recommendation server 2000 may determine a keyword whose number of searches exceeds the number of references as a target keyword. For example, when the number of references is 4 times, the online market recommendation server 2000 may determine the keyword 'shoes, sore throat' as the target keyword.

In an exemplary embodiment, the online market recommendation server 2000 sequentially sorts search keywords obtained by utilizing artificial intelligence based on at least one of search frequency and search time, and selects a target keyword based on the sorted order. can be determined automatically.

Also, in step S240, the online market recommendation server 2000 may sort the keywords obtained in step S230 in order of search time. For example, the search time for 'shoes, bag, sore throat, dizziness, anemia', which is a keyword searched by a customer on a portal site and a social network from a customer terminal 1000, is '1 minute, 5 minutes, 2 minutes, and 10 minutes'. , 7 minutes', the online market recommendation server 2000 may sort the keywords in the order of 'dizziness, anemia, bag, sore throat, shoes'.

At this time, the online market recommendation server 2000 may determine a keyword with the longest search time as a target keyword. For example, the online market recommendation server 2000 may determine the keyword 'dizzy', which takes the most search time, as the target keyword.

In step S250, the online market recommendation server 2000 may obtain a target keyword group by extracting synonyms, synonyms, and related words of the target keyword obtained in step S240.

In an exemplary embodiment, the online market recommendation server 2000 may acquire a target keyword group by accessing the Internet vocabulary and extracting synonyms, synonyms, and related words of the target keyword acquired in step S240.

In an exemplary embodiment, the online market recommendation server 2000 may extract synonyms, synonyms, and related words of a target keyword by accessing a synonym dictionary, synonym dictionary, and related word dictionary provided by a portal site by using an API.

Not limited thereto, the online market recommendation server 2000 may directly input a target keyword into the thesaurus, synonym dictionary, or related word dictionary, and extract searched synonyms, similar words, or related words. A set of synonyms, similar words, and related words of the extracted target keyword may be defined as a target keyword group.

For example, if the online market recommendation server 2000 obtains 'throat pain' as a target keyword in step S240, the online market recommendation server 2000 uses an API in step S250 to obtain a synonym dictionary provided by the portal site, Synonyms, synonyms, and related words of 'throat pain, sore throat, runny nose, cough, corona, cold, sore throat medicine, corona medicine, quince tea, vitamins, etc.' can be obtained by accessing a synonym dictionary or a related word dictionary. Also, the online market recommendation server 2000 may set a combination of synonyms, similar words, and related words as a target keyword group.

In an exemplary embodiment, the online market recommendation server 2000 may obtain a target keyword group by automatically extracting synonyms, synonyms, and related words of the target keyword using artificial intelligence.

In step S260, the online market recommendation server 2000 may extract sales products whose names overlap with synonyms, similar words, and related words in the target keyword group from among a plurality of pre-set sales products for each target customer list.

The online market recommendation server 2000 may hold data related to a plurality of products for sale for each target customer list in the memory 2200 in advance. As described above, the online market recommendation server 2000 may classify a plurality of customer lists based on customer information such as age, gender, and occupation, and may provide data of sales products expected to be sold a lot for each customer list. may have in advance.

In an exemplary embodiment, the online market recommendation server 2000 divides the customer list into first to third plurality of customer lists based on age, gender, and occupation of the customer, and the first to third plurality of customer lists. Data of sales products that are expected to be sold in particular may have data in advance.

For example, the online market recommendation server 2000 may classify the customer as a 'male in his 30s' based on age and gender information of the customer. Also, the online market recommendation server 2000 may have lists of sales products that are expected to sell a lot among 'men in their 30s' in advance.

In step S260, the online market recommendation server 2000 may extract sales products whose names overlap with synonyms, similar words, and related words in the target keyword group from among a plurality of pre-set sales products for each customer list.

In an exemplary embodiment, in step S250, the online market recommendation server 2000 selects a target keyword group consisting of 'throat, sore throat, runny nose, cough, corona, cold, sore throat medicine, corona medicine, quince tea, vitamins, etc.' If acquired, in step S260, the online market recommendation server 2000 selects 'throat pain, sore throat, runny nose, cough, corona, cold, sore throat medicine, corona medicine, quince tea, vitamins' among a plurality of pre-set sales products for each customer list. It is possible to extract sales products with overlapping names with 'etc.'.

For example, if the online market recommendation server 2000 has a list of sales products such as 'vitamins, iron content, dumbbells, quince tea, citron tea, sore throat medicine, etc.' The market recommendation server 2000 may extract 'vitamin, quince tea, sore throat', which is a name overlapping with a word in the target keyword group.

In an exemplary embodiment, the online market recommendation server 2000 may automatically extract sales products whose names overlap with synonyms, similar words, and related words in a target keyword group from among a plurality of sales products by using artificial intelligence.

In step S270 , the online market recommendation server 2000 may determine the sale product extracted in step S260 as the first recommendation sale product. For example, the online market recommendation server 2000 determines 'vitamins, quince tea, sore throat medicine' extracted in step S260 as products for sale in the online market, and provides a service for selling the products to the customer terminal 1000. can provide

Method S20a of the present disclosure acquires customer information from the customer terminal 1000, classifies the customer into a customer list based on the acquired customer information, obtains a search keyword from the customer terminal 1000, and acquires the customer terminal Based on the search frequency and search time of (1000), a target keyword among search keywords is acquired, a target keyword group including synonyms, similar words, and related words of the target keyword is acquired, and a plurality of pre-set sales products for each customer list Among them, sales products with names overlapping with words in the target keyword group can be extracted, and the extracted sales products can be determined as recommended sales products. You can sell the kinds of products you need on the online market. Accordingly, market competitiveness of the online market using the method of the present disclosure can be improved.

4 is a flow chart showing the flow of recommending a product for sale in an online market using customer information according to an exemplary embodiment of the present disclosure ( S20b ).

Step S20b may be performed after step S20a described with reference to FIG. 3 . Specifically, steps S310 to S330 may be performed after step S270.

Referring to FIG. 4 , in the step 20b of recommending a product for sale in an online market using customer information of the present disclosure, a plurality of sales items exceeding a first standard sales volume among a plurality of sale items sold in a plurality of other online markets. Acquiring a list of 1 reference sale items (S310), when the sum of the sales volume of the first reference sale items in a plurality of other online markets exceeds the second reference sales amount, the first reference sale product is sold as a second reference sale It may include determining as a product (S320), and determining a product overlapping with the name of the second reference selling item among the first recommended selling products as a second recommended selling product (S330).

In step S310, the online market recommendation server 2000 may acquire a list of a plurality of first reference sale items exceeding the first standard sales amount from other online market servers 3000. The first reference sales volume may be a value arbitrarily determined by a manager of the online market recommendation server 2000 .

However, it is not limited thereto, and the online market recommendation server 2000 calls information related to products sold in other online markets and sales volume of the products by using API, and sells products that exceed the first standard sales amount among the products sold. 1 Can be determined as a reference sale item.

For example, when the first reference sales volume is determined to be 1000 units, in step S310, the online market recommendation server 2000 acquires a list of first reference sales products whose sales volume exceeds 1000 units among products sold in other online markets. can do.

In step S320 , the online market recommendation server 2000 may determine a second reference sale product based on the sum of sales of the first reference sale product in a plurality of other online markets. In an exemplary embodiment, the online market recommendation server 2000 sells the first reference sale product as a second reference when the total of the sales volume of the first reference sale product in a plurality of other online markets exceeds the second reference sales volume. product can be determined. The second reference sales amount may be a value arbitrarily determined by a manager of the online market recommendation server 2000 .

In an exemplary embodiment, in step S320, the online market recommendation server 2000 calculates the sales volume of the first reference sale product in each other online market, and sums the sales volume of the first reference sale product in other online markets. It may include the step of determining whether the combined sales volume exceeds the second reference sales volume, and determining the first reference selling product as the second reference selling product if it exceeds.

For example, if the second reference sales volume is determined to be 100,000 units, in step S320, the online market recommendation server 2000 calculates the sum of sales of the first reference sales products in a plurality of other online markets, and the total of the sales is If the number exceeds 100,000, the first reference selling product may be determined as the second reference selling product.

In step S330, the online market recommendation server 2000 may extract a product that overlaps with the name of the second reference selling product from among the first recommended selling products determined in step S270, and determine the extracted product as the second recommended selling product. .

Since the method of recommending a product for sale in an online market of the present disclosure may further include S20b in addition to the above-described S20a, the method for recommending a product for sale in an online market of the present disclosure includes customer personal information, customer search information, and Sales information from other online markets can also be considered. Accordingly, the online market using the method of the present disclosure can recommend products with excellent sales power to customers, thereby improving customer attraction. can

5 is a flow chart showing the flow of recommending a product for sale in an online market using customer information according to an exemplary embodiment of the present disclosure ( S20c ).

Step S20c may be performed after step S20b described with reference to FIG. 4 . Specifically, steps S410 and S420 may be performed after step S330.

Referring to FIG. 5 , the step of recommending a product for sale in an online market using customer information of the present disclosure (S20c) includes the delivery possibility of the second recommended product for sale within the deadline, delivery distance, search frequency in the customer terminal, and other online products. Calculating a sales suitability score of the second recommended selling product based on the search frequency in the market (S410), and determining a third recommended selling product based on the selling suitability score of the second recommended selling product (S420) can include

In step S410, the online market recommendation server 2000 may have in advance in the memory 2200 data on delivery possibility for each product sold, delivery distance, search frequency in the customer terminal, and search frequency in other online markets.

In an exemplary embodiment, the online market recommendation server 2000 may calculate a sales suitability score of the second recommended sale product by Equation 4 below.

In Equation 4, Ga may be a sales suitability score Ga of the second recommended selling product. In addition, Ca is a delivery weight (Ca) determined differently based on the location of the customer terminal, Pa is a delivery possibility (Pa) of the second recommended selling product within the period, and Da is the current location of the second recommended selling product and is a delivery distance (Da) between customer terminals, Ta is a search weight (Ta) that is set differently based on the type of product, Ea is a search frequency (Ea) of a second recommended selling product in a customer terminal, and Fa is The search frequency (Fa) of the second recommended selling product in another online market may be a search frequency (Fa), and Xa may be an age/gender weight (Xa) differently set based on the age and gender of the customer.

Specifically, the sales suitability score Ga for the second recommended sale product may be calculated in consideration of the aspect of prompt delivery of the second recommended sale product. The sales suitability score Ga may consider the delivery distance between the current location of the second recommended sale product and the customer terminal, and the possibility of delivery within a deadline.

For example, the sales suitability score (Ga) for the second recommended sale product with a high possibility of delivery within the deadline may have a relatively large value, and the sales suitability score (Ga) for the second recommended sale product with a long delivery distance may have a relatively low value.

In addition, the sales suitability score Ga for the second recommended selling product may be calculated in consideration of the search frequency of the second recommended selling product searched in the customer terminal and other online markets. When the search frequency (Ea) of the customer terminal and the search frequency (Fa) of the second recommended selling product are high, the sales suitability score (Ga) may have a relatively large value.

In addition, the sales suitability score Ga for the second recommended selling product may further consider an age/gender weight Xa that is differently set based on the customer's age and gender. The age/gender weight (Xa) may be a value determined in advance based on the correlation between the customer list into which customers are classified in step S220 and the second recommended selling product.

In addition, the sales suitability score Ga for the second recommended selling product is differently based on the location of the customer terminal in order to adjust the sum of the scores for delivery, search frequency, and age/gender of the second recommended selling product. The determined delivery weight (Ca), the search weight (Ta) set differently based on the type of product, and the age/gender weight (Xa) set differently based on the age and gender of the customer may be considered.

The online market recommendation server 2000 of the present disclosure may calculate a sales suitability score (Ga) in consideration of delivery information of the second recommended sales product, search information of the second recommended sales product, and personal information of the customer. Accordingly, the sales suitability score Ga may be determined by reflecting customer attractiveness, prompt delivery, and market competitiveness.

In step S420 , the online market recommendation server 2000 may determine a third recommended sale product based on the sales suitability score Ga of the second recommended sale product.

In an exemplary embodiment, the online market recommendation server 2000 may determine a sale product having the highest sales suitability score Ga among a plurality of second recommended sale products as the third recommended sale product.

However, the present invention is not limited thereto, and the online market recommendation server 2000 may determine a sales product whose sales suitability score Ga exceeds the reference sales suitability score among the plurality of second recommended sales products as the third recommended sales product.

Since the method of recommending a product for sale in an online market of the present disclosure may further include S20c in addition to the above-described S20a and S20b, the method for recommending a product for sale in an online market of the present disclosure includes product delivery information, search information, and Products for sale in the online market may be recommended based on age/gender information. Accordingly, the online market using the method of the present disclosure may recommend a product desired by the customer to the customer terminal, and may additionally consider whether delivery of the product can proceed smoothly. Accordingly, customer attraction, delivery speed, and market competitiveness of the online market using the method of the present disclosure can be improved.

6 is a flow chart showing the flow of determining a selling price of a recommended selling product based on sales information of another online market and a customer's desired purchase price according to an exemplary embodiment of the present disclosure ( S30a ).

S30a may be performed after step S20c. Specifically, S30a may be performed after step S420 of S20c. Step S30 of the present disclosure may include steps S30a and S30b.

Determining the selling price of the recommended selling product based on the sales information of other online markets and the customer's desired purchase price of the present disclosure (S30a) includes the sales volume and selling price of the third recommended selling product in a plurality of other online markets. Obtaining (S510), determining a weighted average selling price of the third recommended selling product based on the sales volume and selling price of a plurality of other online markets (S520), the third recommended selling product from the customer terminal Obtaining a desired purchase price of (S530), determining a price adjustment value of the third recommended selling product based on the raw material content, raw material price fluctuation rate, inventory amount, shipping cost, and foreign currency fluctuation rate of the third recommended selling product (S530) S540), and determining the sum of the customer's desired purchase price and the price adjustment value as the product suggested selling price of the third recommended selling product (S550).

In step S510, the online market recommendation server 2000 may acquire the sales volume and selling price of the third recommended sales product from the other online market server 3000. In an exemplary embodiment, the online market recommendation server 2000 may automatically obtain the sales volume and sales price of the third recommended sales product from the other online market server 3000 by utilizing artificial intelligence.

However, the present invention is not limited thereto, and the online market recommendation server 2000 may call and store information related to the sales volume and sales price of the third recommended sales product in other online markets using an API and store in the memory 2200 .

In step S520, the online market recommendation server 2000 may determine a weighted average selling price of the third recommended selling product based on the sales volume and selling price of the third recommended selling product in a plurality of other online markets. The weighted average selling price may be an average selling price of the third recommended selling product determined by considering sales volume in other online markets.

Specifically, the weighted average selling price of the third recommended selling product may be calculated by Equation 5 below.

In Equation 5, Aa is the weighted average selling price of the third recommended selling product in n other online markets, Mai is the sales weight of the third recommended selling product in other online markets, and Pai is the third selling product in other online markets. 3 is the selling price of the recommended selling product, and Zai may mean the sales volume of the third recommended selling product in another online market.

Based on Equation 5, a weighted average selling price of the third recommended selling product considering sales volume of a plurality of other online markets selling the third recommended selling product may be determined.

In step S530 , the online market recommendation server 2000 may acquire the desired purchase price of the third recommended selling product from the customer terminal 1000 . The desired purchase price of the third recommended sale product may be a value input by the customer terminal 1000 and transmitted to the online market recommendation server 2000, or may be a value determined by the customer.

In step S540, the online market recommendation server 2000 may determine a price adjustment value of the third recommended sale product based on the raw material content, raw material price change rate, stock amount, delivery cost, and foreign currency change rate of the third recommended sale product. In an exemplary embodiment, the online market recommendation server 2000 may automatically obtain price adjustment values for a plurality of third recommended selling products.

Specifically, the price adjustment value of the third recommended selling product may be calculated by Equation 6 below.

In Equation 6, Ba is the price adjustment value of the third recommended selling product, La is the raw material price change weight differently set based on the type of raw material, Qa is the raw material price change rate, and Ha is the third recommended selling product. Is the raw material content contained in , Ia is a shipping weight that is set differently based on the type of the third recommended selling product, Ka is the shipping cost of the third recommended selling product, Ja is the inventory quantity of the third recommended selling product, Oa is a foreign currency price change weight differently set based on the type of foreign currency, and Ra means a foreign currency change rate.

Specifically, the price adjustment value Ba of the third recommended selling product may be calculated in consideration of the content of the raw material contained in the third recommended selling product and the price change of the raw material. For example, when the content of the raw material is high and the price of the raw material is currently increasing, the price adjustment value Ba may increase.

In addition, the price adjustment value Ba of the third recommended selling product may be selected in consideration of the stock quantity and delivery cost of the third recommended selling product. For example, if the inventory of the third recommended selling product is large and the delivery cost is low, the price adjustment value Ba may increase, and if the inventory quantity is small and the delivery cost is high, the price adjustment value Ba may decrease.

In addition, the price adjustment value Ba of the third recommended selling product may be calculated in consideration of the foreign currency price fluctuation. For example, when the third recommended selling product is a product that needs to be imported and the price of a foreign currency is currently rising, the price adjustment value Ba may increase.

The price adjustment value (Ba) of the third recommended selling product is a raw material price fluctuation weight (La), which is set differently based on the type of raw material, in order to adjust the value considering all of the raw material price variable, foreign currency price variable, and delivery variable. 3 A delivery weight (Ia) differently set based on the type of recommended selling product and a foreign currency price change weight (Oa) differently set based on the type of foreign currency may be considered.

The price adjustment value (Ba) of the third recommended selling product of the present disclosure may be calculated considering all of the raw material price variable, the foreign currency price variable, and the delivery variable. Accordingly, the online market recommendation server 2000 of the present disclosure reflects the price adjustment value (Ba) in the customer's desired purchase price to set the selling price of the product that can improve all of the attractiveness of the customer, prompt delivery, and market competitiveness. It can be proposed to the customer terminal 1000 .

In step S550, the online market recommendation server 2000 may determine the sum of the customer's desired purchase price Ya and the price adjustment value Ba as the proposed product sale price of the third recommended sales product.

Specifically, the proposed product selling price of the third recommended selling product may be determined by Equation 7 below.

In Equation 7, CPa is the proposed product selling price (CPa) of the third recommended selling product, Ya is the customer's desired purchase price (Ya) of the third recommended selling product, and Ba is the price adjustment of the third recommended selling product. value (Ba).

Method S30a of the present disclosure obtains a customer's desired purchase price (Ya) for a third recommended selling product, calculates a price adjustment value (Ba) considering raw materials, delivery, and foreign currency, and calculates the customer's desired purchase price (Ya) and A product proposed sales price (CPa) in which the price adjustment value (Ba) is reflected may be determined.

That is, the online market recommendation server 2000 may reflect the price desired by the customer and global economic conditions such as exchange rates and raw material prices in the selling price of the third recommended selling product. Accordingly, the online market recommendation server 2000 can secure customer attraction and market competitiveness.

FIG. 7 is a flow chart showing the flow of determining a selling price of a recommended selling product based on sales information of another online market and a customer's desired purchase price according to an exemplary embodiment of the present disclosure ( S30b ).

S30b may be performed after the aforementioned S30a. Specifically, S30b may be performed after step S550 of S30a.

S30b of the present disclosure includes determining whether the proposed product selling price (Cpa) of the third recommended selling product is smaller than the weighted average selling price (Aa) of the third recommended selling product obtained in step S520 (S610), the proposed product selling price If (CPa) is less than the weighted average selling price (Aa), determining the price of a third recommended selling product as the product suggested selling price (CPa) (S620), the product suggested selling price (CPa) is the weighted average selling price (Aa) ), stopping the sale of the third recommended selling product (S630) may be included.

In an exemplary embodiment, the online market recommendation server 2000 uses artificial intelligence to determine the product proposed selling price (Cpa) of a plurality of third recommended selling products by using artificial intelligence (S520). It can be automatically determined whether it is smaller than Aa).

In general, when the online market recommendation server 2000 presents a price higher than the weighted average selling price (Aa) of other online markets for the third recommended sale product to the customer terminal 1000, the price competitiveness is low, and customer attraction will be low. can

Accordingly, the online market recommendation server 2000 according to the present disclosure adds the price adjustment value Ba calculated by the product recommendation server 2000 to the customer's desired purchase price Ya proposed by the customer, and then the proposed selling price for the product. (CPa) can be determined. In addition, the online market recommendation server 2000 may determine the third recommended selling product's selling price as the suggested product selling price (Cpa) only when the suggested product selling price (CPa) is smaller than the weighted average selling price (Aa). Accordingly, price competitiveness of the third recommended selling product may be improved, and customer attraction may be improved.

Hereinafter, a method (S40) of controlling a sales price of a product for sale based on an exchange rate according to an exemplary embodiment of the present disclosure will be described in detail. The method ( S40 ) of controlling the sales price of a product for sale according to the present disclosure may also be performed by the online market recommendation server 2000 including the processor 2100 . Also, the online market recommendation server 2000 may include the price determination system 100 performing step S40.

8 is a block diagram illustrating a pricing system according to an exemplary embodiment of the present disclosure.

Referring to FIG. 8 , the pricing system 100 may calculate a sales price (SP) that can be sold in the future by predicting a future exchange rate based on target product information (Info_MP). To this end, the pricing system 100 may be configured as a server or a terminal, and when configured as a server, the pricing system 100 may collectively refer to a server or a computing device that operates the same, and may be configured as a terminal. The pricing system 100 includes a laptop, personal computer (PC), navigation, personal communication system (PCS), global system for mobile communications (GSM), personal digital cellular (PDC), personal handyphone system (PHS), PDA (Personal Digital Assistant), IMT (International Mobile Telecommunication)-2000, CDMA (Code Division Multiple Access)-2000, W-CDMA (W-Code Division Multiple Access), Wibro (Wireless Broadband Internet) terminal, Smartpad ), a tablet PC, a cellular phone, and a smart phone.

In this specification, an operation performed by the pricing system 100 or a component included in the pricing system 100 is actually performed by using an application program built in the storage device of the pricing system 100 to determine the pricing system 100. It may be an operation performed by a processor of The storage device may include a non-volatile memory, a volatile memory, a flash-memory, a hard disk drive (HDD), or a solid state drive (SSD). Also, the processor may include at least one of a Central Processing Unit (CPU), a Graphic Processing Unit (GPU), a Neural Processing Unit (NPU), a RAM, a ROM, a system bus, and an application processor.

The contents performed by the price determination system 100 in this specification may be performed by at least one artificial intelligence module using a neural network, and the neural network may be expressed as a mathematical model using nodes and edges. The neural network may be an architecture of a deep neural network (DNN) or n-layers neural networks. DNN or n-layer neural networks may correspond to Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNN), Deep Belief Networks, Restricted Boltzman Machines, and the like. For example, the neural network may be implemented as a convolutional neural network (CNN), but is not limited thereto.

The price determination system 100 may include a sales period prediction unit 110, a prediction constant determination unit 120, an exchange rate prediction unit 130, an inventory cost determination unit 140, and a sales price determination unit 150. . The sales period predictor 110 may calculate a sales period prediction value EST, which is an expected period from purchase to sale of the target product, based on the target product information Info_MP. In an embodiment, the pricing system 100 obtains sales periods ST(i) for similar products using a similar product DB (DB_SP), and uses the obtained sales periods to obtain a sales period prediction value (EST). ) can be calculated. (n is the number of similar products)

The prediction constant determination unit 120 may determine the prediction constant (A) based on the target product information (Info_MP). In this specification, the prediction constant (A) is a constant used to calculate the exchange rate prediction value (Er_t2), and may be determined differently depending on the characteristics of the target product.

The exchange rate prediction unit 130 may obtain a first exchange rate value (Er_t1) of the first time point t1 corresponding to the current time point. In one example, the exchange rate prediction unit 130 may acquire the current exchange rate value as the first exchange rate value Er_t1 by accessing the exchange rate notification system based on the current time point. In an embodiment, the target product information (Info_MP)_ may include information on a purchase place and a seller, and the exchange rate prediction unit 130 uses country information of a purchase place and a seller included in the target product information (Info_MP) A first exchange rate value (Er_t1) may be obtained.

The exchange rate prediction unit 130 may calculate a second point in time t0 corresponding to the past by using the predicted sales period value EST and the first point in time t1. In one example, the exchange rate prediction unit 130 subtracts the sales period prediction value (EST) from the first time point (t1) (or returns to the past by the sales period prediction value (EST) from the first time point (t1)). It can be determined as 2 time points t0 (eg, Equation 9 below).

The exchange rate prediction unit 130 may obtain the second exchange rate value (Er_t0) of the second time point (t0) through the exchange rate request (Req_Er) for the second time point (t0). In one example, the exchange rate prediction unit 130 may obtain the second exchange rate value Er_t0 by accessing an exchange rate notification system.

The exchange rate prediction unit 130 may calculate an exchange rate prediction value (Er_t2) using the first exchange rate value (Er_t1), the second exchange rate value (Er_t0), the sales period prediction value (EST), and the prediction constant (A). In one embodiment, the exchange rate prediction unit 130 may calculate the exchange rate prediction value (Er_t2) using Equation 10 below. According to an embodiment of the present disclosure, the exchange rate prediction value Er_t2 may correspond to the exchange rate at a third time point t2, when a time equal to the sales period prediction value EST has elapsed from the first time point t1.

The inventory cost determination unit 140 may receive the target product information (Info_MP) and the estimated sales period value (EST), and determine the expected inventory cost (IP) to keep the target product as inventory until the target product is sold. there is. In one example, the inventory cost determination unit 140 obtains an inventory constant (IC) corresponding to the target product from the inventory constant DB (DB_IC) using the target product information (Info_MP), and the inventory constant as shown in Equation 11 below. Inventory cost (IP) can be determined by multiplying (IC)) by the selling period forecast (EST).

The selling price determination unit 150 receives the purchase price BP as the target product information Info_MP, multiplies the exchange rate prediction value Er_t2 by the purchase price BP, and adds the inventory cost IP to the selling price. (SP) can be determined (Equation 12).

According to an embodiment of the present disclosure, the pricing system 100 calculates a sales period forecast value (EST) for a target product based on a sales period of a similar product, and calculates an exchange rate point to be obtained using the EST. You can calculate the exchange rate at an exact point in time.

According to an embodiment of the present disclosure, the pricing system 100 determines the prediction constant (A) using the information (Info_MP) of the target product, thereby applying the characteristics of different target products to the exchange rate prediction to determine the characteristics of the product. Exchange rate forecasting can be performed.

According to an embodiment of the present disclosure, the pricing system 100 determines the past second exchange rate value (Er_t0) and the first exchange rate based on the sales period prediction value (EST) as well as the current exchange rate slope (dEr_t1/dt). In order to reflect the average slope ((Er_t1-Er_t0)/(t1-t0)) between the values (Er_t1) together, a weighted sum between the two elements can be performed to predict an accurate exchange rate considering both the instantaneous slope and the average slope. .

According to an embodiment of the present disclosure, the pricing system 100 can accurately predict inventory costs that may be required until sales by calculating inventory values using inventory constants (IC) reflecting product characteristics.

Fig. 9 is a flow chart illustrating a method of controlling a sales price of a product for sale based on an exchange rate according to an exemplary embodiment of the present disclosure.

Referring to FIG. 9 , the price determination system 100 may receive the purchase price BP of the first country at the first point in time t1 for the target product (S110p). The price determination system 100 may obtain a first exchange rate value (Er_t1) between the first country, which is a purchasing country, and the second country, which is a selling country, at a first point in time t1 (S120p).

The pricing system 100 may calculate a sales period prediction value (EST) for the target product using the similar product DB (DB_SP) (S130p). The pricing system 100 may obtain the second exchange rate value Er_t0 at the second point in time t0 based on the predicted sales period value EST (S140p). In one example, the second point in time t0 may be a past point in time different from the first point in time t1 by the predicted sales period value EST.

The pricing system 100 may calculate an exchange rate prediction value (Er_t2) at the third time point (t2) based on the first exchange rate value (Er_t1) and the second exchange rate value (Er_t0) (S150p). In one embodiment, the pricing system 100 may calculate the exchange rate prediction value (Er_t2) by using a predetermined formula reflecting the prediction constant in which product characteristics are reflected (S150p).

Pricing system 100 may determine the inventory cost based on the information of the target product (S160p). In one example, the pricing system 100 may determine the inventory cost by determining an inventory constant based on the size and nature of the target product, and multiplying the inventory constant by an estimated sales period value (EST).

The pricing system 100 may determine the sales price (SP) based on the exchange rate prediction value (Er_t2) and the inventory cost (IP) (S170p).

Fig. 10 is a flow chart showing a price control method according to an exemplary embodiment of the present disclosure, and Fig. 11 is a table showing similar product DBs according to an exemplary embodiment of the present disclosure. In detail, FIG. 10 shows the calculation step (S130p) of the sales period prediction value (EST) of FIG. 9 .

Referring to FIG. 10 , the price determination system 100 may determine at least one first similar product having the same item code of the target product from the similar product DB (DB_SP) (S131p). In one example, the product code may be determined to correspond to the type of product, and if the product code is the same, the product type may be similar or identical. The price determination system 100 may determine at least one second similar product having the same sales destination as the target product among the first similar products (S132p). In another embodiment, the pricing system may determine at least one second similar product from the same producer among the first similar products.

The price determination system 100 may determine at least one third similar product having a price range similar to the purchase price among the second similar products (S133p). In one embodiment, pricing system 100 may determine a third similar product as a second similar product that is within a predetermined offset of the purchase price.

The pricing system 100 may obtain a sales period of at least one third similar product (S134p). The pricing system 100 may determine the average of sales periods as a sales period prediction value (EST) (S135p).

Referring to FIG. 11 , assuming that the target product is PC2 as a product code, the seller is company B, and the price is 30 dollars, the pricing system 100 determines three to three items having the same product code as PC2 among the similar product DB (DB_SP). Product No. 6 may be determined as the first similar product. Among the first similar products, the price determination system 100 may determine products No. 4 to 6 having the same vendor as company B as the second similar products. The pricing determination system 100 may determine products No. 4 and No. 5, the price of which is similar to $30 (for example, within $10 as an offset value) among the second similar products, as the third similar product.

The pricing system 100 may determine 15 days, which is an average of 16 days of the sales period of product No. 4 and 14 days of the sales period of product No. 5, as the predicted sales period value (EST).

According to an embodiment of the present disclosure, similar products similar to the target product are filtered based on various criteria (eg, product code, vendor, price), and the average sales period for the similar products is calculated as a sales period prediction value (EST). ), it is possible to accurately predict the expected sales period from purchase to sale of the target product.

12 is a flow chart illustrating a pricing method according to an exemplary embodiment of the present disclosure. In detail, FIG. 12 shows the obtaining step S140p of the second exchange rate value Er_t0 of FIG. 9 .

Referring to FIG. 12 , the pricing system 100 may determine a time point obtained by subtracting the sales period prediction value EST from the first time point t1 as the second time point t0 (S141p). The price determination system 100 may obtain an exchange rate between the first country (purchasing country) and the second country (seller country) at the second point in time t0 as a second exchange rate value (S142p).

13 is a flowchart illustrating a price determination method according to an exemplary embodiment of the present disclosure, and FIGS. 14A and 14B are graphs illustrating exchange rate trends according to an exemplary embodiment of the present disclosure. In detail, FIG. 13 shows the calculation step (S150p) of the predicted exchange rate value (Er_t2) of FIG. 9, the horizontal axis of FIGS. 14A and 14B represents the flow of time, and the vertical axis represents the exchange rate.

Referring to FIG. 13 , the pricing system 100 may calculate a first exchange rate gradient value S1 at a first time point t1 ( S151p ). In one example, the pricing system 100 may determine a differential value (instantaneous slope) of the exchange rate graph Er at a first time point t1 as a first exchange rate slope value S1 = dEr_t1/dt.

The pricing system 100 may calculate a second exchange rate gradient value S2 between the first time point t1 and the second time point t0 (S152p). In one example, the pricing system 100 calculates the average slope between the first time point t1 and the second time point t0 of the exchange rate graph Er as a second exchange rate slope value S2 = (Er_t1-Er_t0)/( t1-t0)) can be determined.

The pricing system 100 may calculate an exchange rate gradient prediction value (S) through a weighted average of the first exchange rate gradient value (S1) and the second exchange rate gradient value (S2) (S153p). In one embodiment, the pricing system 100 may determine a prediction constant (A) by reflecting product characteristics, and calculate an exchange rate gradient prediction value (S) according to Equation 13 based on the prediction constant (A). .

The pricing system 100 calculates an expected exchange rate increase value by multiplying the exchange rate gradient prediction value S and the sales period prediction value EST (S154), and adds the expected exchange rate increase value to the first exchange rate value Er_t1. By doing so, the exchange rate prediction value (Er_t2) can be determined (S155p).

Referring to FIG. 14A , the pricing system 100 determines a second time point t0 prior to the sales period prediction value EST from the first time point t1, and determines the instantaneous slope of the first time point t1. 1 exchange rate slope value S1 may be calculated, and a second exchange rate slope value S2 may be calculated as an average slope between the second time point t0 and the first time point t1. In the case of FIG. 14A, the prediction constant (A) may be determined to be relatively small as an exchange rate for a product having a higher influence of the average slope (S2) on product characteristics (eg, country, price, sales period). . Accordingly, the predicted value S of the exchange rate slope may be determined to be similar to the second exchange rate slope S2 rather than the first exchange rate slope S1.

In the case of FIG. 14B, the prediction constant (A) may be determined to be relatively large as an exchange rate for a product in which the influence of the instantaneous slope (S1) is higher in terms of product characteristics (eg, country, price, sales period). . Accordingly, the predicted value S of the exchange rate slope may be determined to be similar to the first exchange rate slope S1 rather than the second exchange rate slope S2.

According to an embodiment of the present disclosure, the pricing system 100 considers both the average slope between the second time point t0 and the first time point t1 as well as the instantaneous slope S1 at the first time point t1. By determining the predicted value (S) of the exchange rate gradient, it is possible to reflect not only the exchange rate flow at the time of the first time point (t1) but also the exchange rate flow between the first time point (t1) and the second time point (t0), and as a result, an accurate exchange rate can predict

Also, according to an embodiment of the present disclosure, the pricing system 100 may determine the second time point t0 for calculating the average slope S2 based on the sales period prediction value EST, and accordingly, the sales price may increase. For the exchange rate value at the expected time, it can accurately reflect the exchange rate flow during the same period in the previous period.

In addition, according to an embodiment of the present disclosure, the reflection ratio of the average slope S2 and the instantaneous slope S1 can be adjusted by adjusting the prediction constant A according to the characteristics of the product, and as a result, the instantaneous It is possible to adaptively control the degree of reflection of the exchange rate flow and the average exchange rate flow.

15 is a flow chart illustrating a pricing method according to an exemplary embodiment of the present disclosure. In detail, FIG. 15 shows a method of determining the prediction constant (A) based on the sales period prediction value (EST) in the calculation step (S153p) of the exchange rate gradient prediction value of FIG. 13 .

Referring to FIG. 15 , the price determination system 100 may determine a sales period prediction value (EST) (S153_1p), and may determine a prediction constant (A) based on the sales period prediction value (EST) (S153_2p). The pricing system 100 determines the prediction constant (A) as an integer greater than 0.7 when the sales period prediction value (EST) is less than 7 days, and when the sales period prediction value (EST) is 7 days or more and less than 30 days, the prediction constant ( A) is determined as an integer greater than 0.4 and less than or equal to 0.7, and when the predicted sales period value (EST) is 30 days or more, the prediction constant (A) may be determined as an integer less than 0.4.

As the sales period gets longer, the average slope can have a greater impact than the instantaneous slope. As a result of hundreds of simulations, the most accurate exchange rate was calculated when the prediction constant (A) was 0.7 based on 7 days, and based on 30 days As a result, the most accurate exchange rate was calculated when the prediction constant (A) was 0.4.

According to an embodiment of the present disclosure, an accurate exchange rate considering product characteristics may be calculated by determining different prediction constants for each sales period.

16 is a flowchart illustrating a pricing method according to an exemplary embodiment of the present disclosure. In detail, FIG. 16 shows a method of determining the prediction constant based on the GDP of the purchasing country in the step of calculating the predicted value of the slope of the exchange rate of FIG. 15 (S153p).

Referring to FIG. 16 , the price determination system 100 obtains the GDP of the first country, which is a purchasing country (S153_1ap), and may determine a smaller prediction constant (A) as the GDP of the first country is higher (S153_2ap).

As a country with a large GDP does not have a large change in the exchange rate, the average slope can have a greater effect than the instantaneous slope. As a result of hundreds of simulations, the prediction constant (A) is greater than or equal to 0.2 and less than 0.3 when the United States is a purchasing country. The most accurate exchange rate was calculated when it was an integer (preferably 0.25), and when China was a purchasing country, the most accurate exchange rate was calculated when the prediction constant (A) was an integer greater than or equal to 0.3 and smaller than 0.4 (preferably 0.32), and Vietnam In the case of this purchasing country, the most accurate exchange rate was calculated when the prediction constant (A) was an integer greater than or equal to 0.6 and less than 0.8 (preferably 0.72).

According to an embodiment of the present disclosure, an accurate exchange rate considering the characteristics of a purchasing country may be calculated by determining different prediction constants for each purchasing country in which a product is purchased.

Fig. 17 is a flowchart illustrating a pricing method according to an exemplary embodiment of the present disclosure. In detail, FIG. 17 shows a method of determining a prediction constant based on the purchase price (BP) of a target product in the calculation step (S153p) of an exchange rate gradient prediction value of FIG. 13 .

Referring to FIG. 17 , the pricing system 100 may obtain a purchase price (BP) of a target product (S153_1bp) and determine a prediction constant (A) based on the purchase price (BP) (S153_2bp). The pricing determination system 100 determines the prediction constant (A) as an integer greater than 0.8 when the purchase price (BP) is less than 10 dollars, and when the purchase price (BP) is greater than or equal to 10 dollars and less than 100 dollars, the prediction constant (A) is determined as an integer greater than 0.2 and less than or equal to 0.8, and when the purchase price (BP) is greater than or equal to 100 dollars, the prediction constant (A) may be determined as an integer less than 0.2.

The higher the purchase price (BP), the more difficult it is to sell, so the average slope can have a greater effect than the instantaneous slope. As a result of hundreds of simulations, the most accurate exchange rate is when the prediction constant (A) is 0.8 based on 10 dollars. , and the most accurate exchange rate was calculated when the prediction constant (A) was 0.2 based on 100 dollars.

According to an embodiment of the present disclosure, an accurate exchange rate for each product characteristic may be calculated by determining different prediction constants for each purchase price (BP).

18 is a flowchart illustrating a pricing method according to an exemplary embodiment of the present disclosure. In detail, FIG. 18 shows the inventory cost (IP) determining step S160p of FIG. 9 .

Referring to FIG. 18 , the pricing system 100 may determine an inventory constant (IC) based on product characteristics (S161p). The pricing system 100 may determine the inventory cost (IP) by multiplying the inventory constant by the sales period forecast value (EST) (S162p).

According to an embodiment of the present disclosure, by determining an inventory constant based on product characteristics and reflecting it in a product price, not only exchange rates but also costs consumed as inventory during the sales period can be reflected in the sales price, resulting in accurate sales. A price can be determined.

Fig. 19 is a flowchart illustrating a pricing method according to an exemplary embodiment of the present disclosure. In detail, FIG. 19 shows the inventory constant (IC) determining step (S161p) of FIG. 18 .

Referring to FIG. 19 , the pricing system 100 may receive target product information (Info_MP) (S161_1p) and obtain a product size (wt) from the target product information (Info_MP) (S161_2p). When the product size (wt) is smaller than the first size (w1), the pricing system 100 may determine the first value (k1) as the first sub inventory constant (IC1), and the product size (wt) is When greater than or equal to the first size w1 and smaller than the second size w2, the second value k2 may be determined as the first sub inventory constant IC1, and the product size wt is the second size w2 ), the third value k3 may be determined as the first sub inventory constant IC1. In one embodiment, the first value (k1) < the second value (k2) < the third value (k3) may have a large value in the order.

The pricing system 100 may obtain whether or not a frozen product is a frozen product from the target product information (Info_MP) (S161_4p). The pricing system 100 may determine the fourth value l1 as the second sub inventory constant IC2 when the product is a frozen product, and as the second sub inventory constant IC2 when the product is not a frozen product. A fifth value l2 may be determined. In one embodiment, the fourth value l1 < the fifth value l2 may have large values in the order of.

The pricing system 100 may determine the inventory constant (IC) by adding the first sub inventory constant (IC1) and the second sub inventory constant (IC2) (S161_6p).

According to an embodiment of the present disclosure, by determining an inventory constant in consideration of product characteristics such as product size or frozen products, and calculating inventory costs based thereon, accurate inventory costs required for inventory maintenance can be calculated, and accurate inventory costs are calculated. Selling cost can be calculated.

20 is a diagram showing a customer terminal 1000, an online market recommendation server 2000, and another online market server 3000 according to an exemplary embodiment of the present disclosure.

Referring to FIG. 20 , the customer terminal 1000 recommends an online market based on at least one of online market subscription information and customer information of the customer terminal according to the present disclosure (S10), and recommends an online market using customer information. A method of recommending a product for sale in the market (S20), a method for determining a selling price of a product for sale recommended based on sales information in other online markets and a customer's desired purchase price (S30), and a method for recommending a product for sale based on an exchange rate In the selling price controlling method (S40), it may be a terminal operated by a customer.

In an exemplary embodiment, the customer terminal 1000 includes a cellular phone, a smart phone, a laptop, a personal computer (PC), a navigation system, a personal communication system (PCS), and a global system (GSM). for Mobile communications), PDC(Personal Digital Cellular), PHS(Personal Handyphone System), PDA(Personal Digital Assistant), IMT(International Mobile Telecommunication)-2000, CDMA(Code Division Multiple Access)-2000, W-CDMA(W -Code Division Multiple Access), Wibro (Wireless Broadband Internet) terminal, smart pad (Smartpad), tablet PC (Tablet PC), etc. can include various terminal devices capable of communication.

In addition, the customer terminal 1000 may be connected to the online market recommendation server 2000 through a wireless communication network. Also, the online market recommendation server 2000 may be connected to other online market servers 3000 through a wireless communication network.

In an exemplary embodiment, the wireless communication network is a local area network (LAN), a wide area network (WAN), a wired and wireless data communication network, a telephone network, a wired and wireless television communication network, a 3G, 4G, 5G, and a 3rd generation 3GPP (3GPP) Partnership Project), 5GPP (5th Generation Partnership Project), LTE (Long Term Evolution), WIMAX (World Interoperability for Microwave Access), Wi-Fi, Internet, LAN (Local Area Network), Wireless LAN ( Wireless Local Area Network), WAN(Wide Area Network), PAN(Personal Area Network), RF(Radio Frequency), Bluetooth Network, NFC(Near-Field Communication) Network, Satellite Broadcasting Network, Analog Broadcasting Network, DMB (Digital Multimedia Broadcasting) networks, etc. are included, but are not limited thereto.

The online market recommendation server 2000 may be a server that performs the methods of the present disclosure described with reference to FIGS. 1 to 19 .

In this specification, the content performed by the online market recommendation server 2000 may be performed by at least one artificial intelligence module using a neural network, and the neural network may be expressed as a mathematical model using nodes and edges. The neural network may be an architecture of a deep neural network (DNN) or n-layers neural networks. DNN or n-layer neural networks may correspond to Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNN), Deep Belief Networks, Restricted Boltzman Machines, and the like. For example, the neural network may be implemented as a convolutional neural network (CNN), but is not limited thereto.

The online market recommendation server 2000 of the present disclosure may include a processor 2100, a memory 2200, an input/output device 2300, a storage device 2400, and a power supply 2500.

The processor 2100 may be implemented with firmware, software, routines, and instructions for performing the methods of the present disclosure described with reference to FIGS. 1 to 19 . For example, the processor 2100 may be implemented by software that receives data for feedback, generates signals for operating the methods of the present disclosure, and performs predetermined operations.

Processor 2100 may perform certain calculations or tasks. Depending on embodiments, the processor 2100 may be a microprocessor or a central processing unit (CPU). The processor 2100 communicates with the memory 2200, the storage device 2400, and the input/output device 230 through a bus such as an address bus, a control bus, and a data bus. can do. According to an embodiment, the processor 2100 may also be connected to an expansion bus such as a Peripheral Component Interconnect (PCI) bus.

The memory 2200 may store data necessary for operations of the methods of the present disclosure described with reference to FIGS. 1 to 19 . For example, the memory 2200 may be implemented as DRAM, mobile DRAM, SRAM, PRAM, FRAM, RRAM, and/or MRAM. .

The storage device 2400 may include a solid state drive, a hard disk drive, a CD-ROM, and the like. The memory 2200 and the storage device 2400 may store programs executed in the operations of the methods of the present disclosure.

As above, exemplary embodiments have been disclosed in the drawings and specifications. Embodiments have been described using specific terms in this specification, but they are only used for the purpose of explaining the technical spirit of the present disclosure, and are not used to limit the scope of the present disclosure described in the meaning or claims. Therefore, those of ordinary skill in the art will understand that various modifications and equivalent other embodiments are possible therefrom. Therefore, the true technical scope of protection of the present disclosure should be determined by the technical spirit of the appended claims.

Claims (7)

A method for recommending an online market based on subscription information and customer information of a customer terminal, performed by an online market recommendation server including a processor, comprising:
obtaining at least one of online market subscription information and customer information from a customer terminal by the online market recommendation server;
determining whether online market subscription information has been obtained from a customer terminal by the online market recommendation server;
By the online market recommendation server, based on the number of subscribers of the subscription online market, sales, monthly payment amount of the customer, possibility of delivery within the deadline, shipping cost, delivery period, number of advertisements, and portal site search volume, Calculating additional points;
determining, by the online market recommendation server, whether there is an affiliated online market of the customer's subscription online market from the subscription online market server;
By the online market recommendation server, the ratio of subscription online market customers among affiliated online market customers, the number of affiliated online market subscribers, sales, customer's monthly payment amount, delivery possibility within the deadline, shipping cost, delivery period, number of advertisements, Calculating a second additional point of an affiliated online market based on a portal site search volume;
classifying a customer into any one target customer list among a plurality of customer lists based on customer information of a customer terminal by the online market recommendation server;
obtaining, by the online market recommendation server, an additional point calculation factor including a ratio of target customers out of all customers, sales, and satisfaction scores from the online market server;
calculating a third additional point for each online market based on the additional point calculating factor by the online market recommendation server; and
recommending, by the online market recommendation server, an online market to a customer terminal based on a sum of the first additional points, the second additional points, and the third additional points;
including,
The first added point is calculated by Equation 1 below,
[Equation 1]

In Equation 1, AP1 is the first additional point of the subscription online market subscribed by the customer, Cf1 is the sales weight for the payment amount of the customer in the subscription online market, P_m1 is the monthly payment amount of the customer in the subscription online market, Cf2 is the shipping weight of the subscription online market, T_d1 is the delivery probability of products sold in the subscription online market, T_m1 is the average shipping cost of products sold in the subscription online market, and T_t1 is the average of products sold in the subscription online market Delivery period, Cf3 is the weight of the market competitiveness of the subscription online market, S_b1 is the number of subscribers of the subscription online market, S_m1 is the sales of the subscription online market, Cf4 is the weight of the advertising power of the subscription online market, and Ad_m1 is the weight of the advertising power of the subscription online market. A method for recommending an online market based on subscription information and customer information of a customer terminal, wherein Ad_p1, the number of online advertisements in the subscription online market, is defined as a search volume in a portal site of the subscription online market. According to claim 1,
If the customer's subscription information is acquired in the step of determining whether the online market subscription information has been obtained from the customer terminal, a step of calculating a first additional point is performed;
Classifying the customer into any one target customer list among a plurality of customer lists based on the customer information when the customer's subscription information is not obtained in the step of determining whether subscription information of the online market has been obtained from the customer terminal. A method of recommending an online market based on subscription information and customer information of a customer terminal, characterized in that performing. According to claim 2,
In the step of determining from the subscription online market server whether there is an affiliate online market of the customer's subscription online market, if it is determined that there is an affiliate online market, a step of calculating a second additional point is performed;
In the step of determining, from the subscription online market server, whether there is an affiliated online market of the customer's subscription online market, if it is determined that there is no affiliated online market, one target customer list among a plurality of customer lists is selected based on the customer information. A method of recommending an online market based on customer information and subscription information of a customer terminal, characterized in that the step of classifying customers is performed. delete According to claim 1,
The second added point is calculated by Equation 2 below,
[Equation 2]

In Equation 2, AP2 is the second additional point of the affiliated online market, Cf5 is the shipping weight of the affiliated online market, T_d2 is the delivery possibility of products sold in the affiliated online market within the deadline, and T_m2 is the product sold in the affiliated online market. T_t2 is the average delivery cost of products, T_t2 is the average delivery period of products sold in the affiliate online market, Cf6 is the weight for the market competitiveness of the affiliate online market, S_b2 is the number of subscribers of the affiliate online market, S_m2 is sales of the affiliate online market Ad_m2 is the number of online advertisements in the affiliated online market, Ad_p2 is the search volume in the portal site of the affiliated online market, and Cf8 is the number of subscription online market customers within the affiliated online market. A method for recommending an online market based on subscription information and customer information of a customer terminal, wherein Cu_t2 is a weight for the ratio, and Cu_t2 is defined as a ratio of subscription online market customers to affiliate online market customers. According to claim 5,
The third added point is calculated by Equation 3 below,
[Equation 3]

In Equation 3, AP3 is the third additional point of the online market, Cf9 is the weight for the market competitiveness of the online market, S_m3 is the sales of the affiliated online market, and Cf10 is the weight for the influence of the online market on the target customer Ps_3 is the percentage of target customers out of all customers in the online market, Cf11 is a weight related to the satisfaction index of customers in the online market, and Sf_3 is defined as the satisfaction score of customers using the online market. How to recommend online marketplaces based on subscription information and customer information. According to claim 6,
The step of recommending an online market to a customer terminal based on the sum of the first additional points, the second additional points, and the third additional points,
determining, by the online market recommendation server, whether a sum of the first additional points, the second additional points, and the third additional points exceeds a reference value; and
recommending, by the online market recommendation server, an online market in which a sum of the first additional points, the second additional points, and the third additional points exceeds a reference value to a customer terminal;
A method for recommending an online market based on subscription information and customer information of a customer terminal, comprising: