KR102532679B1 - O2o electronic commerce system based on ai - Google Patents

Abstract

A user terminal accessing an online shopping mall and purchasing products; and a management server connected to the user terminal through a network and collecting data related to product purchase through the user terminal.

Description

E-commerce system using artificial intelligence algorithm {O2O ELECTRONIC COMMERCE SYSTEM BASED ON AI}

The present invention relates to an AI-based O2O e-commerce system, and more particularly, to an e-commerce system for food transactions between wholesalers and retailers.

Efforts are being made to create a so-called ubiquitous environment in which information and communication devices can be naturally and conveniently applied to real life regardless of place or time in accordance with the rapid development of information and communication technology.

In order to create such a ubiquitous environment, wireless recognition technology that can effectively detect and recognize each other remotely between information and communication devices is essential, and a representative wireless recognition technology is radio frequency identification (RFID). ) technology, NFC technology is attracting attention.

This wireless recognition technology is a field of automatic recognition technology such as barcodes, magnetic sensors, IC cards, etc., and uses microwave or long waves to wirelessly recognize data stored in microchips. Recognizable by the leader.

Recently, with the development of RFID or NFC technology, tagged objects are exponentially disseminated, and users can easily obtain tag information using a terminal with a reader function. level at which information is provided.

In general, products sold to consumers have expiration dates and manufacturing dates, and may be sold to consumers through predetermined distribution channels (wholesale and retailers).

When sold to consumers, sales information on a corresponding product is acquired through wireless recognition technology, for example, wireless recognition technology using a barcode, and can be used for inventory management, sales management, and the like.

However, when a product whose expiration date has expired or a problem product manufactured on a specific manufacturing date is sold, it is essential to accurately locate the product in order to retrieve it.

On the other hand, there is a lack of scientific analysis of customers due to customer segmentation at the level of frequency analysis of demographic characteristics and purchase patterns of current shopping mall buyers, and product recommendations tend to be recommended based on the marketing manager's intuition or past behavior, and scientific products are more likely to be recommended. There is a problem that recommendations are not made. In order to solve this problem, it is necessary to shorten the search time of purchasing customers and develop an optimal shopping mall recommendation technology, through which the competitiveness of shopping mall operators can be enhanced.

One aspect of the present invention provides an e-commerce system that can predict product purchases of shopping mall customers by utilizing artificial intelligence algorithms.

The technical problem of the present invention is not limited to the technical problem mentioned above, and other technical problems not mentioned will be clearly understood by those skilled in the art from the following description.

An electronic commerce system according to an embodiment of the present invention includes a user terminal that accesses an online shopping mall and purchases products; And a management server connected to the user terminal through a network and collecting data related to product purchase through the user terminal;

The management server includes a product purchase prediction platform providing device that provides a product purchase prediction service to the user terminal,

The apparatus for providing a product purchase prediction platform includes: a data warehouse construction unit that collects product purchase data of a purchase customer object for product purchase prediction of a purchase customer using a shopping mall and builds a data warehouse; a data warehouse updating unit that verifies the lifestyle of each purchasing customer based on the product purchase data and adds it to the data warehouse; a candidate data population generation unit generating a plurality of candidate data randomly extracted from the data warehouse as candidate data populations and determining predictive independent variables that satisfy statistical criteria; and an optimization model determiner determining a product purchase prediction model having the highest product purchase predictive value as an optimization model for each predictive independent variable by applying a plurality of artificial intelligence algorithms to the prediction independent variable based on the candidate data population.

Meanwhile, the product purchase data may include demographic characteristics, purchasing season characteristics, purchasing time characteristics, purchase price fluctuations, and purchased products.

In addition, the data warehouse updating unit selects one of a fashion pursuit type, a happiness pursuit type, an information preference type, a foreign product preference type, and an advertisement preference type as a predefined lifestyle for each purchasing customer based on the product purchase data. can be characterized as determined.

The apparatus for providing a product purchase prediction platform may further include a product purchase prediction providing unit that predicts product purchase for a specific customer based on the optimization model and provides recommended products.

In addition, a product packaging box having a product accommodating space formed therein, an opening communicating with the product accommodating space is formed in one region, and a product recognition code recognized through a predetermined scanning device is printed; further comprising,

The management server may further include performing inventory management of the product by receiving the product identification code from the scanning device.

According to the present invention described above, product purchase data such as demographic characteristics, lifestyles, and symbolic consumption trends of shopping mall customers are subdivided and artificial intelligence algorithms are applied to analyze customers' product purchase patterns, seasonal characteristics, time characteristics, and purchase price fluctuations. A product purchase prediction platform can be provided.

In addition, it can contribute to shortening the search time of purchasing customers and developing optimal shopping mall recommendation technology, thereby increasing the competitiveness of shopping mall operators.

1 is a network configuration diagram showing the overall configuration of an electronic commerce system according to an embodiment of the present invention.
2 is a block diagram showing the detailed configuration of an integrated product management server according to an embodiment of the present invention.
3 is a flowchart illustrating a process of generating an identification number according to product distribution in an e-commerce system according to an embodiment of the present invention.
4 is a flowchart illustrating a process of managing a plurality of retail product management data in a retail device according to an embodiment of the present invention.
5 is a flowchart illustrating a process of matching identifiers according to sales of products in a retail device according to an embodiment of the present invention.
6 is a flowchart illustrating a process of matching identifiers according to sale of products in a retail device according to another embodiment of the present invention.
8 is a flowchart illustrating in detail an identifier setting process for an identifier composed of two or more numbers in an e-commerce system according to an embodiment of the present invention.
9 is a diagram illustrating the configuration of a system for providing a shopping mall product purchase prediction platform based on artificial intelligence according to the present invention.
FIG. 10 is a block diagram illustrating the physical configuration of the device for providing a product purchase prediction platform in FIG. 9 .
FIG. 11 is a block diagram illustrating a functional configuration of an apparatus for providing a product purchase prediction platform in FIG. 9 .
FIG. 12 is a flowchart illustrating a process of providing an artificial intelligence-based product purchase prediction platform performed by the product purchase prediction platform providing device in FIG. 9 .
13 is an exemplary view illustrating an embodiment of a data warehouse used in the system for providing an AI-based shopping mall product purchase prediction platform according to the present invention.
14 is a conceptual diagram illustrating the overall operation of the apparatus for providing a product purchase prediction platform according to the present invention.
15 is a diagram showing the configuration of a safe login system according to an embodiment of the present invention.
16 is a flowchart illustrating a method of performing login authentication in a safe login system according to an embodiment of the present invention.
17 is a diagram illustrating a web page displaying a safe login menu according to an embodiment of the present invention.
18 is a flowchart illustrating a method of performing login authentication in a safe login system according to another embodiment of the present invention.
19 is a flowchart illustrating a method of performing login authentication in a safe login system according to another embodiment of the present invention.
20 is a flowchart illustrating a method of performing login authentication in a safe login system according to another embodiment of the present invention.
21 is a diagram showing an electronic commerce system according to another embodiment of the present invention.
22 is a view showing a portion of the product packaging box shown in FIG. 21;

Advantages and features of the present invention, and methods of achieving them, will become clear with reference to the detailed description of the following embodiments taken in conjunction with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below, but will be implemented in various different forms, only these embodiments make the disclosure of the present invention complete, and common knowledge in the art to which the present invention belongs. It is provided to fully inform the holder of the scope of the invention, and the present invention is only defined by the scope of the claims. Like reference numbers designate like elements throughout the specification.

Terminology used herein is for describing the embodiments and is not intended to limit the present invention. In this specification, singular forms also include plural forms unless specifically stated otherwise in a phrase. As used herein, “comprises” and/or “comprising” do not preclude the presence or addition of one or more other components, steps, and operations to the stated components, steps, and operations.

1 is a network configuration diagram showing the overall configuration of an electronic commerce system according to an embodiment of the present invention.

As shown in FIG. 1, the e-commerce system is for managing products produced by product manufacturers, and for this purpose, a plurality of manufacturer side devices 100 and wholesale side devices 120 interconnected through wired or wireless networks. , the retail device 140, the payment terminal 160, and the consumer 180.

Prior to the description of the e-commerce system according to an embodiment of the present invention, products produced by manufacturers may be supplied to retailers via a plurality of wholesalers and sold to a plurality of final consumers 180 .

In an embodiment of the present invention, the product may include foodstuffs, processed foods, etc. having a manufacturing date and expiration date. For this reason, not only can products supplied to retailers be discarded or recalled according to the expiration date, but also recall measures are required due to problems with specific products, so it is necessary to closely grasp inventory information and sales information of products for each retailer. .

To this end, the e-commerce system according to an embodiment of the present invention may generate and manage product management data that can be updated according to a product supply route based on a manufacturing date.

That is, after the product is produced by the manufacturer, the e-commerce system generates wholesale product management data for the product produced by the manufacturer's device 100 and transmits it to the wholesale device 120 before supplying the product to the wholesaler. .

The manufacturer side device 100 generates an identification number for the product produced based on the total number of products produced, and based on the number of wholesalers requesting product supply, an identification number based on the number of products to be paid to each wholesaler After generating a wholesale identification number for each wholesaler, product management data for each wholesaler can be generated using the generated wholesale identification number, manufacturing date, expiration date, manufacturer's identification information, and wholesaler's identification information. there is.

For example, if 300,000 products are manufactured and supplied to 4 wholesalers (10,000 pieces of wholesaler A, 90,000 pieces of wholesaler B, 50,000 pieces of wholesaler C, and 150,000 pieces of wholesaler D), the manufacturer's device 100 includes the date of manufacture, After generating the manufacturer's product management data consisting of the expiration date, manufacturer's identification information, and identification numbers from 1 to 300,000, 4 wholesale identification numbers are generated based on the number of products requested by the wholesaler (the number of delivery requests). can do. That is, the manufacturer's device 100 has A wholesale identification number consisting of 1 to 10,000, B wholesale identification number consisting of 10,001 to 100,000, C wholesale identification number consisting of 100,001 to 150,000, and D wholesale identification number consisting of 150,001 to 300,000. An identification number may be generated, and wholesale product management data composed of each generated wholesale identification number, manufacturing date, expiration date, manufacturer's identification information, and wholesaler's identification information may be generated for each wholesaler.

On the other hand, each of the plurality of manufacturers can be overlapped through mutual information exchange through the manufacturer's device 100 to prevent the identification number of the product from being generated.

That is, the manufacturer's device 100 operated by each of a plurality of manufacturers can mutually share the manufacturing date and identification number of the product and use it as reference data when generating the product identification number.

For example, other than the case where the manufacturer's device 100 called A generates an identification number of 1 to 100,000, the manufacturer's device 100 may generate another identification number except for the identification number of 1 to 100,000.

A wholesaler may supply products supplied from a manufacturer to a retailer at the request of a plurality of retailers.

At this time, the wholesale device 120 generates retail product management data for each retailer by dividing the wholesale identification number in the wholesale product management data based on the number of products requested for delivery by the retailer and the number of retailers requesting product supply. can

Specifically, the wholesale-side device 120 may generate N pieces of retail product management data corresponding to the number (N) of retailers through division of an identification number in the wholesale product management data.

In this case, identification information of the retailer may be matched with each of the N pieces of retail product management data.

For example, if wholesaler A, which has been supplied with 10,000 units, supplies 2,000 units to each of 5 retailers, wholesale product management data may generate 5 retail product management data changed by dividing wholesale identification numbers. For example, when a wholesaler receiving 10,000 units supplies 2,000 products to each of 5 retailers, the wholesaler device 120 includes a manufacturing date, expiration date, manufacturer's identification information, wholesaler's identification information, and 1 to 10,00 Five retail identification numbers may be generated based on the number of products (the number of delivery requests) requested by the retailer for the wholesale identification number in the wholesale product management data composed of the identification number.

That is, the wholesale device 120 has an A retail identification number consisting of 1 to 2,000, a B retail identification number consisting of 2,001 to 4,000, a C retail identification number consisting of 4,001 to 6,000, and a D retail identification number consisting of 6,001 to 8,000. An identification number and an E retail identification number consisting of 8,001 to 10,000 are generated, and retail goods consisting of each generated retail identification number, manufacturing date, expiration date, manufacturer's identification information, wholesaler's identification information, and retailer's identification information Management data can be created individually for each retailer.

The wholesale-side device 120 may transmit the generated retail product management data through interworking with the retail-side device 140 when delivering the product to the retailer.

The retail device 140 may manage sales route data of products by matching and storing predetermined identifiers with sales information generated when products are sold to each consumer 180 based on the retail product management data.

To this end, the retail device 140 may include a product management application 150 for generating and matching predetermined identifiers.

In an embodiment of the present invention, the product management application 150 of the retail device 140 uses the retail product management data provided from the wholesale device 120 to identify identifiers for products sold to each consumer, such as numbers. can be obtained.

To this end, the retail device 140 according to an embodiment of the present invention may acquire product sales information through interworking with the payment terminal 160, for example, a POS terminal.

In addition, the product management application 150 receives product sales information including the manufacturing date from the payment terminal 160, searches the database 155 for retail product management data corresponding to the received manufacturing date, and then retrieves the product. A number may be determined based on a retail identification number in one retail product management data and matched with sales information.

In this case, the payment terminal 160 may receive information corresponding to the date of manufacture from the salesperson and provide the information to the product management application 150 .

Meanwhile, when only sales information not including a manufacturing date is received from the payment terminal 160, the product management application 150 calculates the number of sales based on the sales information for a specific product as the expiration date for the specific product expires. Calculate, set the number of the specific product purchased by the consumer 180 (a number given based on the retail identification number) based on the retail identification number, the number of sales, and the number of stocks of the specific product, and set the set number And the date of manufacture may be matched with the sales information and stored in the database 155 .

If a specific product with a manufacturing date of January 1 and a shelf life of up to 3 days is sold at a retail store, the retail product identification number in the retail product management data by manufacturing date (January 1, 2, and 3) is 1 to 100. , if a total of 300 products are stored and sold to the retailer as an example, first, as the expiration date expires, that is, January 4th, the product management application 150 displays a specific item sold by January 3rd. The number of actual sales of a product is acquired through sales information, and if the actual number of sales obtained is 120 and the number of stocks of a specific product for each manufacturing date is 10, 80, or 100, the number of sales of a specific product with a manufacturing date of January 1 is 90, and the number of sales of a specific product having a manufacturing date of January 2, sold until January 3, may be 20.

Accordingly, the product management application 150 arranges the sales information for a specific product on January 1st in chronological order, and then displays the arranged sales information (including consumer identification information) with the manufacturing date of January 1st. Select a number as an identifier using the retail identification number of the retail product management data, arrange the sales information for a specific product on January 2nd in chronological order, and then manufacture on January 1st or January 2nd Select a number that is an identifier from the retail identification number of retail product management data with a date, arrange the sales information for a specific product on January 3 in chronological order, and then display the manufacturing date of January 1 or January 2 The identifier may be matched with the sales information by selecting a number as an identifier from the retail identification number of the retail product management data having the manufacturing date or the manufacturing date of January 3.

A detailed description of the identifier matching method is as follows.

First, when the product sales deadline of January 1 is reached, each sales information for the product on January 1 is sequentially numbered from the retail identification number in the retail product management data having the manufacturing date of January 1. After selection, the manufacturing date and sequentially selected numbers are matched with sales information and stored in the database 155.

That is, when only retail product management data having a manufacturing date of January 1 exists in the database 155, the retail device 140 sells a number that is an identifier selected by using the retail identification number in the retail product management data. information can be matched.

If the product sale deadline on January 2nd is reached and retail product management data with a manufacturing date of January 2nd is received, the products sold on January 2nd will have a manufacturing date of January 1st and January 2nd. Products with a manufacturing date of January 2 can be sold.

Accordingly, after arranging the sales information of products sold on January 2nd in chronological order, the number can be selected and matched with sales information.

That is, on January 2nd, if there is no stock of a product having a manufacturing date of January 1st, the retail device 140 determines that all products having a manufacturing date of January 1st are exhausted, and stores the product with the manufacturing date of January 2nd Each number can be selected and matched from the retail identification number with .

On the other hand, if all products having a manufacturing date of January 1 are not exhausted, the retail device 140 displays the retail information having a manufacturing date of January 1 in sales information corresponding to the number of products sold on January 2. After selecting and matching numbers from the retail identification number and the retail identification number with the manufacturing date on January 2nd, as sales close on January 2nd, Identifier based on the number of products in stock on January 1st and January 2nd decision-making process can be performed.

The identifier determination process calculates the number of sales of products with a manufacturing date of January 1 sold on January 2 based on the number of products in stock on January 1, and the sales information corresponding to the number of sales of the calculated products Only the number selected from the retail identification number in the retail merchandising management data with the manufacturing date of January 1 is left, and the number selected as the retail identification number in the retail merchandising management data with the manufacturing date of January 2 is deleted. Based on the number of products in stock on the 2nd, the number of sales with the manufacturing date of January 2nd sold on January 2nd is calculated, and then the manufacturing date of January 2nd is assigned to the sales information corresponding to the number of sales of the calculated product. It may be a method of leaving only the number selected from the retail product identification number in the retail product management data having.

In the identifier determination process as described above, it has been explained by deleting the number, but the number selected from the retail identification number in the retail product management data having the manufacturing date of January 1 is set as the main identifier, and the January A retail identification number in retail product management data having a manufacturing date of 2 days may be set as a sub identifier.

It can be granted based on the number of products in stock for each manufacturing date at the time of sales closing on January 3rd. If there are products with manufacturing dates of January 1st, 2nd, and 3rd, 1 Calculate the number of sales of products with manufacturing dates of January 1st, January 2nd, and January 3rd, and calculate the sales information of January 3rd corresponding to the number of sales of products with manufacturing dates of January 1st. Select a number using the retail identification number in the retail product management data with manufacturing dates of January 1, January 2, and January 3, and 1 corresponding to the number of sales of products with manufacturing dates of January 2 Select a number using the retail identification number in the retail product management data with January 2nd and January 3rd manufacturing dates in the sales information on the 3rd of the month, and the number of sales of the products with the manufacturing date of January 3rd A number can be selected using the retail identification number in the retail product management data having the manufacturing date of January 3 in the sales information of January 3 corresponding to .

Meanwhile, an identification number in retail product management data whose expiration date has expired may be matched with sales information. For example, if retail product management data with a manufacturing date of January 1 expires on January 3, sales information of January 4 includes retail product management data with a manufacturing date of January 1 The identification number of does not match. To this end, the product management application 150 of the retail device 140 may check the expiration date of the retail product management data and deactivate the retail product management data whose expiration date has expired.

On the other hand, if all products with a manufacturing date of January 1 are exhausted on the same day, the sales information is arranged in chronological order, then the identification number and manufacturing date are sequentially matched to the sales information, and all products with a manufacturing date of January 1 are sold out on the same day. If a product with a manufacturing date of January 2nd is received and sold on January 2nd in excess of the number of identification numbers with a manufacturing date of January 1st, the number of products sold on January 2nd In some of the sales information, an identification number having a manufacturing date of January 1 and a number in the identification number having a manufacturing date of January 2 may be matched.

Products with a manufacturing date of January 1 are not exhausted on the same day, products with a manufacturing date of January 2 and January 3 are received, and on January 3, more than the number of identification numbers with a manufacturing date of January 1 If a product is sold, some of the sales information of the product sold on January 3 matches the numbers in the identification number with the manufacturing date of January 1, January 2, and January 3, and the remaining sales information Numbers in the identification number with January 2nd and January 3rd manufacturing dates can be matched.

According to the embodiment of the present invention as described above, although the manufacturer's device 100 has been described as an example of generating the identification number of a product, it can be generated through a separate integrated product management server 200.

In this case, each manufacturer's device 100 may transmit information on the manufacturing date and product name to the integrated product management server 200 connected through a wired or wireless network, and then receive an identification number of the product in response.

In this case, the integrated product management server 200 is a technical means for achieving the above technical problem, and the e-commerce system according to an embodiment of the present invention provides the total number of products produced and the date of manufacture from manufacturer devices connected through a wired or wireless communication network. , After receiving the expiration date and the number of paid products for each wholesaler, the first function generates an identification number for a product with a manufacturing date based on this, and divides the identification number for each wholesaler based on the number of products delivered to each wholesaler. After generating the wholesale identification number for the wholesale product management data having the generated wholesale identification number, manufacturing date, and expiration date, each wholesaler generates the wholesale device 120 corresponding to each wholesaler's identification information. A second function of matching the wholesale identification number generated for each wholesaler with the identification information of each wholesaler and storing it in the database 210 for product management, and a wholesale device 120 connected through a wired or wireless communication network to the retailer As the number of products paid for each product and identification information of the wholesaler are provided, a wholesale identification number matched with the wholesaler's identification information is searched in the product management database 210, and the searched wholesale identification number is divided into the number of deliveries per retailer. After generating a retail identification number for each retailer, create retail product management data for each retailer, including the generated retail identification number, manufacturing date, expiration date, and retailer's identification information, to respond to each retailer's identification information. A third function for transmitting to the retail-side device 140 may be included.

Accordingly, the retail device 140 stores the retail product management data received from the integrated product management server in the database 155, and stores the retail product in the sales information received from the payment terminal 160 according to product sales. Based on the retail identification number in the management data, the selected identifier and the manufacturing date may be matched and stored in the database 155 .

That is, the integrated product management server 200 may generate identification numbers for the same product and products manufactured on the date of manufacture based on the date of manufacture and product name so as not to overlap, and then provide them to the manufacturer side device 100 .

In addition, as shown in FIG. 2, the integrated product management server 200 according to an embodiment of the present invention receives inventory data by manufacturing date from the retail device 140, and stores the provided inventory data as a database for product management. (210) can be stored and managed.

To this end, the integrated product management server 200 according to an embodiment of the present invention includes an identification number generation unit 202 for generating identification numbers for each different product and each manufacturing date according to the request of the manufacturer side device 100, the retail side It may include a retailer interlocking unit 204 that receives inventory data through interworking with the device 140 and stores and manages the inventory data in the database 210 for product management.

The retailer interlocking unit 204 receives product sales-related data such as product price information, retailer location information, and product sales format as well as inventory data through interworking with the retail device 140, and receives product management database (210). ) can be stored and managed. Here, the product sales format may mean direct transaction, delivery transaction, same-day delivery, and the like.

In addition, the integrated product management server 200 according to an embodiment of the present invention receives a product purchase request through linkage with the product purchase application 192 in the smartphone 190 possessed by the consumer 180, and receives the product purchase request. In response to a product purchase request, a consumer linkage unit capable of generating retailer information corresponding to the product purchase request based on product sales related data stored in the product management database 210 and providing the information to the smartphone 190 ( 206) may be further included.

Here, the product purchase request may include a product name, location information of the consumer, and the like, and the retailer information may include inventory data for the product name, location information of the retailer within a predetermined radius based on the location information of the consumer, and sales method information. etc. may be included.

Specifically, the consumer interlocking unit 206 retrieves inventory data for product names from the database 210 for product management, that is, searches for retailers that have inventory for the product, and then retrieves the retailer's sales type information, price information, and A retailer list that sells products may be generated using location information of the retailer, etc., and the generated retailer list may be provided to the consumer's smartphone 190 .

In addition, the consumer linking unit 206 may connect the consumer and the retailer by providing an interface through which the product requested to be purchased is purchased by selecting one from the retailer list. Specifically, the consumer linkage unit 206 provides a payment interface to the smartphone 190 through which the consumer can purchase and request a product from the retailer, and when the payment is completed by the consumer, the payment is completed to the retail device 140. In addition, you can request delivery.

On the other hand, the integrated product management server 200 according to an embodiment of the present invention further includes a product purchase history providing unit 208 capable of providing consumer purchase history information on a product on a specific manufacturing date according to a manufacturer's or wholesaler's request. can include

The product purchase history providing unit 208 interlocks with the retail device 140 in response to a request for history inquiry from the manufacturer device 100 or the wholesale device 120, and provides sales information about the manufacturing date within the history inquiry request, and accordingly. The matched number may be requested and received, and the received sales information and the number matched thereto may be provided to the manufacturer device 100 or the wholesale device 120 .

In this case, the retail device 140 searches the database 155 based on the date of manufacture and product name when a request for history inquiry through the date of manufacture and product name is received, and provides sales information and numbers matched to the product and date of manufacture. It can be provided to the purchase history providing unit 208 .

According to the embodiment of the present invention as described above, although the history search request has been described as being made through the integrated product management server 200 as an example, direct history inquiry from the manufacturer device 100 or the wholesale device 120 The retail side device 140 receiving the request may provide sales information and numbers for the history search request.

A process of operating the electronic commerce system having the above configuration will be described with reference to FIGS. 3 to 8 .

3 is a flowchart illustrating a process of generating an identification number according to product distribution in an e-commerce system according to an embodiment of the present invention.

As shown in FIG. 3, first, as products are produced by the manufacturer, the integrated product management server 200 generates an identification number based on the number of products produced by the manufacturer at the request of the manufacturer's device 100. (S300).

Then, when the manufacturer supplies the product to the wholesaler at the request of at least one wholesaler, the integrated product management server 200 receives the identification information of each wholesaler and the number of supplies for each wholesaler from the manufacturer's device 100, and then the wholesaler Based on the number of supplies per star, the identification number is divided to generate a wholesale identification number for each wholesaler (S302),

Wholesale product management data including manufacturing date, expiration date, manufacturer's identification information, wholesaler's identification information, and wholesale identification number are generated for each wholesaler and then provided to the manufacturer's device 100 (S304).

Accordingly, the manufacturer may deliver the product requested by the wholesaler to the wholesaler, and the manufacturer-side device 100 may transmit wholesale product management data to the wholesale-side device 120 .

Thereafter, when the wholesaler supplies products to the retailer at the request of at least one retailer, the integrated product management server 200 receives identification information of each retailer and the number of supplies for each retailer from the wholesale device 120, and then provides each retailer with the number of supplies. Based on the number of supplies, the identification number in the wholesale product management data is divided to generate a retail identification number for each retailer (S306), manufacturing date, expiration date, manufacturer's identification information, retailer's identification information, wholesaler's identification Retail product management data including information and retail identification numbers are generated for each wholesaler and then provided to the manufacturer's device 100 .

Accordingly, the wholesaler may deliver products requested by the retailer to the wholesaler, and the wholesale device 120 may transmit retail product management data to the retail device 120 .

Then, the retail device 140 receives sales information of the product from the payment terminal 160 according to product sales, and an identifier to be matched with the received sales information based on the retail identification number in the retail product management data ( For example, a number) is generated (S310), and then the generated identifier and the manufacturing date of the product are matched with the received sales information and stored in the database 155 (S312).

According to the embodiment of the present invention as described above, although the identification number and product management data have been described as being generated by the integrated product management server 200 as an example, only the first identification number is stored in the integrated product management server 200. After being generated by the manufacturer side device 100 and the wholesale side device 120, the wholesale identification number, the retail identification number, the wholesale product management data, and the retail product management data may be generated.

Further, according to an embodiment of the present invention, numbers have been described as an identifier, but consecutive characters, binary numbers, and the like may be used.

4 is a flowchart illustrating a process of managing a plurality of retail product management data in the retail device 140 according to an embodiment of the present invention.

For convenience of explanation, a state in which the retail device 140 receives at least two pieces of retail product management data and stores them in the database 155 will be described as an example.

As shown in FIG. 4 , the retail device 140 receives the number of products in stock by manufacturing date through the product management application 150 (S400).

The product management application 150 of the retail device 140 checks the number of products in stock by date of manufacture to determine whether there is a date of manufacture in which the number of products in stock is “0” (S402).

As a result of the determination in S402, if there is a manufacturing date in which the number of products in stock is “0”, the product management application 150 stores product management data for retail corresponding to the manufacturing date in which the number of products in stock is “0” in the database 155 After searching in ), the searched retail product management data is deactivated (S404). Here, deactivation may mean excluding when generating an identifier to be matched with sales information.

Then, the product management application 150 determines whether retail product management data whose expiration date has expired exists through analysis of the retail product management data in the database 155 (406).

As a result of determination in S406, if there is retail product management data whose expiration date has expired, the product management application 150 deactivates the retail product management data whose expiration date has expired (S408).

5 is a flowchart illustrating a process of matching identifiers according to sales of products in the retail device 140 according to an embodiment of the present invention.

As shown in FIG. 5 , the retail side device 140 receives sales information including a manufacturing date from the payment terminal 160 according to product sales (S500).

Accordingly, the product management application 150 of the retail device 140 searches the database 155 for retail product management data having a manufacturing date based on the manufacturing date (S502).

Then, the product management application 150 generates an identifier to be matched with the sales information using the retail identification number in the retrieved retail product management data (S504). Specifically, the product management application 150 may generate an identifier by selecting a number from a retail identification number.

Thereafter, the product management application 150 matches the generated identifier and manufacturing date to the sales information and stores them in the database 155 (S508).

6 is a flowchart illustrating a process of matching identifiers according to sales of products in the retail device 140 according to another embodiment of the present invention.

As shown in FIG. 6 , the retail device 140 receives sales information from the payment terminal 160 according to product sales (S600).

Accordingly, the product management application 150 of the retail device 140 searches the database 155 for activated retail product management data (S602).

Then, the product management application 150 generates an identifier to be matched with the sales information using the retail identification number in the retrieved retail product management data (S604).

Specifically, when two or more retail product management data are retrieved, the product management application 150 may use two or more retail identification numbers to generate an identifier composed of at least two or more numbers.

Then, the product management application 150 matches the generated identifier and the manufacturing date to the sales information and stores them in the database 155 (S606).

Thereafter, when the sales deadline is reached, the product management application 150 receives input of the number of products in stock by manufacturing date (S608).

Then, the product management application 150 performs an identifier setting process in the identifier consisting of at least two or more numbers based on the number of products in stock (S610).

That is, the product management application 150 extracts the number of sales information including the number in the retail identification number of the retail product management data on the manufacturing date when the product inventory number is “0”, and calculates the product inventory count by manufacturing date per day. After calculating the number of products with a manufacturing date of which the number of products in stock today is “0” based on the product inventory, manage retail products with a manufacturing date of “0” in the sales information corresponding to the calculated number of products The digit selection process can be performed by leaving only the digits in the Retail Identification Number of the data and deleting the remaining digits.

For example, as an identifier, the retail identification number of manufacturing date A and the retail identification number of manufacturing date B are matched to 10 sales information, the number of stocks of products with manufacturing date A is "0", and manufacturing A per day If the number of products on the date of manufacture A sold today is 5 based on the number of products in stock on that date, the product management application 150 uses identifiers corresponding to 5 sales information out of 10 pieces of sales information for retail use on the date of manufacture A. The identifier setting process is performed in such a way that only the number assigned based on the identification number is left, and the retail identification number of the manufacturing date of B is deleted.

7 is a flowchart illustrating a process of matching identifiers according to sales of products in the retail device 140 according to another embodiment of the present invention.

First, as shown in FIG. 7 , the product management application 150 provides retail product management data (hereinafter referred to as 'first retail store') having a retail identification number received from the wholesale side device 120 according to the arrival of the product. First retail product management data consisting of manufacturing date, expiration date, manufacturer's identification information, wholesaler's identification information, retailer's identification information, retail identification number, etc. stored in (S700).

Then, when sales information about the product on the day of arrival is received from the payment terminal 160, the product management application 150 adds retail identification in the first retail product management data to the received sales information as the sales information is received. After determining the number corresponding to the identifier using the number (S702), the determined number and the manufacturing date are matched with the sales information and stored in the database 155.

In this way, by sequentially selecting and determining numbers from the retail identification number in the sales information of products sold on the same day and matching them with the sales information, it is possible to recognize consumers who have purchased products with a manufacturing date and expiration date.

When the sale on the first day ends (S704), the product management application 150 on the second day receives the number of stocks corresponding to the first retail product management data (S706) and stores them in the database 155.

Thereafter, as products having a manufacturing date and expiration date of the second day are received, the product management application 150 of the retail device 140 has a different manufacturing date, expiration date, and manufacturer's identification information from the wholesale device 120. , Second retail product management data having wholesaler's identification information, retailer's identification information, and retail identification number are received and stored in the database 155 (S708).

Then, as the product is sold on the second day, the product management application 150 of the retail device 140 that has received the sales information determines whether the product corresponding to the first retail product management data is in stock (S710). ).

As a result of the determination in S710, if there is stock, the product management application 150 determines each number using the retail identification number of the first and second retail product management data (S712), and then determines each number and Manufacturing dates of the first and second retail merchandise management data are matched with sales information and stored in the database 155 .

Then, the product management application 150 deducts the number of products in stock corresponding to the first retail product management data (S714) and proceeds to S710 to perform subsequent steps.

On the other hand, as a result of the determination in S710, if there is no stock, the product management application 150 determines an identifier using the retail identification number of the second retail product management data (S716), and then determines the identifier and the second retail product management The manufacturing date of the data is matched with the sales information and stored in the database 155.

By performing the above-described steps on a daily basis, sales information may be matched with information for identifying the consumer 180 who has purchased the corresponding product.

8 is a flowchart illustrating in detail an identifier setting process for an identifier composed of two or more numbers in an e-commerce system according to an embodiment of the present invention.

As shown in FIG. 8, it is for processing data matched to sales information on the third day when the expiration date of the goods received on the first day expires, and on the third day, the product management application 150 is for third retail use. Product management data is received from the wholesale side device 120 and stored in the database 155 (S800).

In addition, the product management application 150 receives (S802) the number of stocks corresponding to the first and second retail product management data (ie, the number of products stocked by date of manufacture) and stores them in the database 155.

Then, the product management application 150 calculates the number of products sold for each manufacturing date based on the number of products in stock for each manufacturing date and the number of products sold up to the second day (S804).

Then, the product management application 150 searches the database 155 for sales information in which an identifier composed of at least two or more numbers is matched (S806).

Then, the product management application 150 corrects the identifier matched with the searched sales information (S808).

Specifically, the product management application 150 extracts sales information corresponding to the number of sales of products having a manufacturing date in the first retail product management data from the searched sales information, and matches the extracted sales information to the first retail product. Correction is performed by setting the manufacturing date and number of the product management data as the main identifier and setting other manufacturing dates and numbers as the sub identifier.

9 is a diagram illustrating the configuration of a system for providing a shopping mall product purchase prediction platform based on artificial intelligence according to the present invention.

Referring to FIG. 9 , the artificial intelligence-based shopping mall product purchase prediction platform providing system 100 may include a user terminal 110, a product purchase prediction platform providing device 130, and a database 150.

The user terminal 110 may correspond to a computing device capable of accessing an online shopping mall to purchase a product and receive product recommendation through product purchase prediction, and may be implemented as a smartphone, a laptop computer, or a computer. It is not limited and may be implemented in various devices such as a tablet PC. The user terminal 110 may be connected to the product purchase prediction platform providing device 130 through a network, and a plurality of user terminals 110 may be simultaneously connected to the product purchase prediction platform providing device 130 .

The product purchase prediction platform providing device 130 corresponds to a computer or program capable of collecting and analyzing product purchase-related data from users to predict product purchase and providing optimized recommended products to users through this. It can be implemented as a server that The product purchase prediction platform providing device 130 may be wirelessly connected to the user terminal 110 through Bluetooth, WiFi, or a communication network, and may exchange data with the user terminal 110 through the network.

In one embodiment, the product purchase prediction platform providing device 130 may store data for product purchase prediction of shopping mall purchase customers in association with the database 150 .

Meanwhile, unlike FIG. 9 , the product purchase prediction platform providing device 130 may be implemented by including the database 150 therein. In addition, the product purchase prediction platform providing device 130 may be implemented by including a processor, a memory, a user input/output unit, and a network input/output unit, which will be described in more detail with reference to FIG. 10 .

The database 150 may correspond to a storage device for storing various pieces of information necessary in the process of predicting product purchases of shopping mall customers and providing related information.

The database 150 may store user demographic information collected from a plurality of user terminals 110 and store product purchase information in a shopping mall, but is not limited thereto, and an apparatus for providing a product purchase prediction platform Information collected or processed in various forms may be stored in the process of predicting product purchase and providing product recommendation (130).

FIG. 10 is a block diagram illustrating the physical configuration of the device for providing a product purchase prediction platform in FIG. 9 .

Referring to FIG. 10 , an apparatus 130 for providing a product purchase prediction platform may be implemented by including a processor 210, a memory 230, a user input/output unit 250, and a network input/output unit 270.

The processor 210 may execute a procedure for processing each operation in the process of predicting product purchase by collecting and analyzing product purchase data of shopping mall customers, and may store the memory 230 that is read or written throughout the process. It is possible to manage and schedule synchronization time between volatile memory and non-volatile memory in the memory 230 .

The processor 210 may control the overall operation of the product purchase prediction platform providing device 130, and is electrically connected to the memory 230, the user input/output unit 250, and the network input/output unit 270 so as to flow data between them. can control.

The processor 210 may be implemented as a central processing unit (CPU) of the product purchase prediction platform providing device 130 .

The memory 230 is implemented as a non-volatile memory such as a solid state drive (SSD) or a hard disk drive (HDD) and may include a secondary storage device used to store all data necessary for the product purchase prediction platform providing device 130. It may include a main memory implemented as a volatile memory such as RAM (Random Access Memory).

The user input/output unit 250 may include an environment for receiving user input and an environment for outputting specific information to the user.

For example, the user input/output unit 250 may include an input device including an adapter such as a touch pad, a touch screen, an on-screen keyboard, or a pointing device, and an output device including an adapter such as a monitor or touch screen.

In one embodiment, the user input/output unit 250 may correspond to a computing device connected through remote access, and in such a case, the product purchase prediction platform providing device 130 may be implemented as a server.

The network input/output unit 270 includes an environment for connecting to an external device or system through a network, and includes, for example, a local area network (LAN), a metropolitan area network (MAN), a wide area network (WAN), and a VAN ( An adapter for communication such as Value Added Network) may be included.

FIG. 10 is a block diagram illustrating the functional configuration of the device for providing a product purchase prediction platform in FIG. 9 .

Referring to FIG. 10 , an apparatus for providing a product purchase prediction platform 130 includes a warehouse builder 310, a warehouse updater 320, a candidate data population generator 330, an optimization model determiner 340, and a product It may include a purchase prediction providing unit 350 and a controller 360 .

The warehouse constructing unit 310 collects product purchase data including demographic characteristics, purchasing season characteristics, purchasing time characteristics, purchase price fluctuations, and purchased products of the purchasing customer object for predicting product purchase of purchasing customers using the shopping mall. You can build a data warehouse. Here, the data warehouse may correspond to the database 150 that collects and stores related data generated in the process of using the shopping mall of customers who use the shopping mall.

In this case, the database 150 of FIG. 9 may operate as a data warehouse, and may be implemented in a form in which a plurality of partial databases distribute and store each data.

In FIG. 13, the database 150 sets a purchasing customer as an object, configures and stores data on demographic characteristics, purchasing season characteristics, purchasing time characteristics, purchase price fluctuations, purchased products and lifestyle as independent data sets, respectively. can

The demographic characteristics may include personal information about the purchasing customer, and may include, for example, ID information, age, gender, place of residence, etc. as an identifier for identifying the purchasing customer.

The warehouse constructing unit 310 may collect information related to demographic characteristics from the user terminal 110 of a purchasing customer using the shopping mall, and may collect information related to demographic characteristics based on user information input when subscribing to or paying for the shopping mall. It can be collected, but is not necessarily limited thereto, and demographic characteristics can be collected through various methods.

The purchase season feature is information about the purchase time of the purchaser and may include season information at the time the product is purchased, number of purchases per season, purchase amount per season, and the like. The purchasing time characteristic is information about the purchasing time of the purchasing customer, and may include time information at the time the product is purchased, the number of purchases per hour, the purchase price per hour, and the like.

The purchase price change is information about the product purchase price related to product purchase, and may include a product purchase price, a discount price, a settlement price, and the like.

The purchased product is information about a product to be purchased, and may include product name, brand name, manufacturing date, expiration date, capacity, raw material, and the like. The lifestyle may correspond to a purchasing customer's personal purchase pattern associated with product purchase, and may be predefined based on statistical information of product purchase data.

The warehouse updating unit 320 may verify the lifestyle of each purchasing customer based on the product purchase data and add it to the data warehouse.

If necessary, the database 150 may build a separate partial database capable of storing lifestyles for each purchasing customer separately from a pre-built data warehouse.

The warehouse updating unit 320 may verify the lifestyle of each purchasing customer through various methods based on product purchase data.

For example, the warehouse updating unit 320 may classify the product purchase data into at least one group by applying a clustering algorithm based on the product purchase data, and determine a representative characteristic of the data for each group to determine a plurality of predefined lifestyles. can be associated with any of them.

In addition, the warehouse updater 320 may input an input vector generated based on product purchase data of a specific purchaser to a classification model generated through machine learning, and obtain a classification result for a lifestyle as an output.

In one embodiment, the warehouse updating unit 320 selects among a fashion-seeking type, a happiness-seeking type, an information preference type, a foreign product preference type, and an advertisement preference type as predefined lifestyles for each purchasing customer based on product purchase data. can decide which one.

Here, the lifestyle may correspond to information about a personal life pattern that may affect product purchases of shopping mall customers.

The trend-seeking type may correspond to a purchasing pattern that selects products to purchase according to the trend, the happiness-seeking type may correspond to a purchasing pattern that considers individual satisfaction as the top priority in product purchase, and the information preference type Regardless of satisfaction level, it may correspond to a purchase pattern in which the best product is selected through information collection.

In addition, the foreign product preference type may correspond to a purchase pattern in which foreign products are preferred over domestic products under the same conditions, and the advertisement preference type may correspond to a purchase pattern in which purchases are determined according to product advertisements rather than products.

The candidate data population generating unit 330 may generate a plurality of candidate data randomly extracted from the data warehouse as a candidate data population and determine a predictive independent variable that satisfies a statistical criterion.

The candidate data population may be composed of data randomly selected from product purchase data stored in the data warehouse, and may correspond to learning data used for learning for product purchase prediction.

That is, the candidate data population generating unit 330 may determine, as a prediction independent variable, a significant independent variable that may affect product purchase prediction based on randomly selected data from among product purchase data stored in the data warehouse, and The accuracy of product purchase prediction can be improved by extracting only the data corresponding to the variable and using it for product purchase prediction.

The candidate data population generating unit 330 may set and use statistical criteria in advance to select predictive independent variables, and at this time, the statistical criteria may be used in the product purchasing process of actual customers among various independent variables included in the product purchase data. may correspond to the criteria used to determine independent variables that can have a significant effect on

Accordingly, the candidate data population generation unit 330 compares the statistical values derived for each independent variable of the candidate data population with the statistical criterion, and determines them as predictive independent variables only when specific conditions are satisfied.

In one embodiment, the candidate data population generating unit 330 randomly selects n (n is a natural number) candidate data from the data warehouse to generate a candidate data population, in a first step, an artificial intelligence algorithm for the candidate data population A second step of determining a candidate independent variable that satisfies the statistical criterion by applying , and a third step of finally determining a predictive independent variable based on the number of repetitions of the candidate independent variable determined by repeatedly performing the first and second steps. can be done

More specifically, the candidate data population generation unit 330 may randomly extract product purchase data stored in the data warehouse, and may extract preset n pieces of product purchase data and generate them as candidate data populations.

Next, the candidate data population generating unit 330 may apply an artificial intelligence algorithm to the candidate data population to determine candidate independent variables that satisfy statistical criteria.

Next, the candidate data population generation unit 330 may repeat the first and second steps a predetermined number of times, and finally determine the prediction independent variable based on the number of repetitions of the candidate independent variable determined by the repetition.

That is, in an iterative process, a candidate independent variable that is repeatedly determined a certain number of times or more as a candidate independent variable may be finally determined as a predictive independent variable.

The candidate data population generation unit 330 may randomly generate candidate data populations from the data warehouse, and the process of determining candidate independent variables may be repeatedly performed. It can be composed of independent modules that perform

In one embodiment, in a third step, the candidate data population generation unit 330 generates a predicted independent variable based on the number of repetitions of the candidate independent variable determined by repeatedly performing the first and second steps and the correlation index between the independent variables. final decision can be made.

Here, the correlation index between independent variables may correspond to multicollinearity between independent variables. That is, the candidate data population generation unit 330 may first determine a predicted independent variable based on the number of duplicates of the candidate independent variable, and if the association index among the primarily determined predictive independent variables exceeds a threshold criterion, the predicted independent variable Only one of them can be finally decided.

At this time, the correlation index between independent variables can be measured through Variation Inflation Factor (VIF), Tolerance, or Condition Index (CN).

In one embodiment, in the second step, the candidate data population generation unit 330 may set the significance level as 0.05 as a statistical standard and determine that the statistical standard is satisfied when the significance probability p is less than the significance level.

Here, the significance level may correspond to the maximum value of the probability of making a type 1 error in statistical determination and may be expressed as α. The significance probability p (significance probability) may correspond to the minimum probability of rejecting the null hypothesis (the hypothesis subject to verification) with respect to the current data.

Therefore, if the significance level (α) is set to 0.05 and the calculated significance probability (p) is less than 0.05, the null hypothesis can be rejected and the alternative hypothesis (the hypothesis that is the subject of the argument as a fact contrary to the null hypothesis) can be adopted. there is.

More specifically, the candidate data population generation unit 330 sets the significance level to 0.05 as a statistical criterion and compares the significance level with the significance probability p by applying an artificial intelligence algorithm to each independent variable for the candidate data population to determine a significant variable. can be derived

As a result, a significant variable may be determined according to a statistical criterion and a candidate data population as a main variable influencing product purchase prediction of shopping mall customers.

In one embodiment, in the second step, the candidate data population generation unit 330 may use any one of logistic regression, decision tree, and artificial neural network as an artificial intelligence algorithm. there is.

Logistic regression is a probability model proposed by D.R.Cox and may correspond to a statistical technique used to predict the probability of occurrence of an event using a linear combination of independent variables. The purpose of logistic regression is to express the relationship between the dependent variable and the independent variable as a specific function, the same as the goal of general regression analysis, and use it for future prediction models. Unlike linear regression analysis, the dependent variable targets categorical data and the input data Since the result of the corresponding data is divided into a specific classification when given, it may correspond to a kind of classification technique.

The candidate data population generation unit 330 may configure the dependent variable as a categorical type as binary data of 0 (don't buy) and 1 (buy), and in this case, the dependent variable is the probability of an event occurring, and the predicted value is It can be limited and expressed between 0 and 1.

In addition, the candidate data population generating unit 330 calculates the dependent variable according to the formula in the graph when the data for the independent variables (demographic characteristics, purchase season characteristics, purchase time characteristics, purchase price, purchase product and lifestyle) change by 1. Values with significance probability p less than 0.05 can be derived as significant variables based on the size of the effect and the value of Exp(B), which is the probability of the event occurring.

A decision tree may correspond to a predictive model that connects an observed value and a target value for a certain item, and may correspond to one of predictive modeling methods used in statistics, data mining, and machine learning.

The candidate data population generating unit 330 may classify the purchasing customers by considering the relevance and similarity between the data using the behavior-related data of the purchasing customers.

For example, the analysis algorithm is a chi-squared automatic interaction detection method, and the chi-squared amount or F test can be used regardless of whether the dependent variable is a quantitative or qualitative variable.

The candidate data population generation unit 330 may select a parent node having a large chi-square statistic and a significance probability p < 0.05 as a useful variable for forming a child node.

An artificial neural network may correspond to a statistical learning algorithm inspired by neural networks in biology (particularly the brain among the central nervous system of animals) in machine learning and cognitive science, and artificial neurons formed by combining synapses to form a network. (Node) may correspond to a model having problem solving ability by changing synaptic coupling strength through learning.

The candidate data population generation unit 330 may analyze complex, nonlinear, and multivariate data having relationships using an artificial neural network, predict a probability of occurring in a specific future situation, or estimate a specific behavior of a customer. can do.

The candidate data population generation unit 330 may perform detailed analysis through the following steps.

(i) The candidate data population generation unit 330 may randomly divide and allocate 70% of training data and 30% of verification data for data in the data warehouse.

In addition, (ii) the candidate data population generation unit 330 may generate a network diagram according to the corresponding covariate variable using demographic characteristics, purchase season characteristics, purchasing time characteristics, etc. of shopping mall purchasing customers as data input covariate variables. .

(iii) The candidate data population generator 330 may apply a hyperbolic tangent function as an activation function to the hidden layer and a softmax function as an activation function to the output layer. In this case, the synaptic weight in the diagram may mean the relationship between a given layer and the next layer.

In addition, (iv) the candidate data population generation unit 330 can generate a ROC curve (Receiver Operating Characteristic curve) by R programming, and the ratio of training data and verification data to confirm the result of the importance analysis of independent variables Accuracy can be derived for each.

(v) The candidate data population generation unit 330 may determine a variable drawn as a thick solid line in the hidden layer for each variable of the network diagram as a candidate independent variable in order to derive a candidate independent variable.

The optimization model determiner 340 may apply a plurality of artificial intelligence algorithms to the predictive independent variables based on the candidate data population, and determine a product purchase prediction model having the highest product purchase predictive value as an optimization model for each predictive independent variable.

The optimization model determining unit 340 may learn by applying information on whether a customer purchases a product for each predictive independent variable using product purchase data to an artificial intelligence algorithm, and generate a product purchase prediction model as a learning result. there is.

Here, the product purchase prediction model may correspond to a probabilistic model that outputs a product purchase probability when a specific predictive independent variable is input, and the optimization model determiner 340 performs a product purchase prediction based on the product purchase probability. can do.

The optimization model determiner 340 may calculate a product purchase prediction degree for the corresponding product purchase prediction model by comparing a result predicted through the product purchase prediction model with a product purchase result that can be confirmed through actual product purchase data.

In this case, the product purchase prediction degree may be calculated as a ratio of the number of matches to the number of predictions, and if necessary, normalization may be performed to have a value within a specific range.

As a result, the optimization model determiner 340 may apply a plurality of artificial intelligence algorithms for each predictive independent variable, determine a model having the highest product purchase predictiveness among the generated product purchase prediction models, and apply the prediction to the corresponding predictive independent variable. can be determined as an optimization model for

In one embodiment, the optimization model determiner 340 divides the candidate data population to generate a learning data population and a verification data population, and learning about the learning data population using each of a plurality of artificial intelligence algorithms. A step of constructing a purchase prediction model, a step of verifying a verification data population using the product purchase prediction model, and a step of determining a product purchase prediction model having the highest product purchase predictiveness as an optimization model may be performed.

At this time, the optimization model determiner 340 may determine an optimization model for each prediction independent variable determined by the candidate data population generation unit 330, and for this purpose, extract only the prediction independent variable from the product purchase data of the candidate data population and learn. can be performed.

That is, the optimization model determiner 340 may determine an optimization model by performing learning for each predicted independent variable and each artificial intelligence algorithm.

In one embodiment, the optimization model determiner 340 calculates a split ratio between the training data population and the verification data population for the candidate data population based on the size of the candidate data population, the number of artificial intelligence algorithms, and the number of predictive independent variables. can do.

More specifically, the optimization model determiner 340 adjusts the size of the training data population and the verification data population to become similar as the size of the candidate data population increases, the number of artificial intelligence algorithms increases, or the number of predictive independent variables increases. The split ratio can be determined.

For example, when the basic split ratio between the learning data population and the verification data population is 7:3, the optimization model determiner 340 determines whether the size of the candidate data population is large, the number of artificial intelligence algorithms is large, or the predictive independent variable As the number of is increased, the division ratio may be determined so that the division ratio approaches 5:5.

The product purchase prediction providing unit 350 may predict product purchase for a specific purchasing customer based on the optimization model determined by the optimization model determining unit 240 and provide recommended products.

For example, the product purchase prediction providing unit 350 can predict whether a specific purchase customer will purchase a product by product when using a shopping mall, and select products that the corresponding purchase customer has the highest purchase probability or is predicted to purchase as recommended products. can provide

The controller 360 controls the overall operation of the product purchase prediction platform providing device 130, and includes the warehouse builder 310, the warehouse updater 320, the candidate data population generator 330, and the optimization model determiner. Control flow or data flow between the product purchase prediction provider 340 and the product purchase prediction providing unit 350 may be managed.

FIG. 12 is a flowchart illustrating a process of providing an artificial intelligence-based product purchase prediction platform performed by the product purchase prediction platform providing device in FIG. 9 .

Referring to FIG. 12 , the apparatus 130 for providing a product purchase prediction platform determines demographic characteristics, purchasing season characteristics, and purchasing time of a purchasing customer object for predicting product purchase of purchasing customers using a shopping mall through the warehouse building unit 310. A data warehouse may be constructed by collecting product purchase data including characteristics, purchase price changes, and purchased products (step S410).

The product purchase prediction platform providing device 130 may verify the lifestyle of each purchasing customer based on the product purchase data through the warehouse updating unit 320 and add the product to the data warehouse (step S430).

In addition, the product purchase prediction platform providing device 130 selects a data set satisfying statistical criteria from among a plurality of candidate data sets randomly extracted from the data warehouse through the candidate data population generation unit 330, and obtains a candidate data population can be generated (step S450). The product purchase prediction platform providing device 130 may apply a plurality of artificial intelligence algorithms to the candidate data population through the optimization model determiner 340 to determine a product purchase prediction model having the highest product purchase predictive value as the optimization model. (Step S470).

In addition, the product purchase prediction platform providing device 130 may predict product purchase for a specific purchase customer based on the optimization model through the product purchase prediction providing unit 350 and provide recommended products (step S490).

14 is a conceptual diagram illustrating the overall operation of the apparatus for providing a product purchase prediction platform according to the present invention.

Referring to FIG. 14 , the product purchase prediction platform providing device 130 may build a data warehouse for product purchase prediction, and the data warehouse may include demographic characteristics, purchase season characteristics, purchase time characteristics, Data on purchase price fluctuations and purchased products can be collected and stored separately. To this end, the database 150 may be composed of a plurality of partial databases, and may be distributedly stored and managed through a network.

In addition, the product purchase prediction platform providing device 130 may verify the lifestyle of each purchasing customer through the built data warehouse.

In this case, an independent database for storing lifestyles can be built, and the pre-built data

You can update it by adding it to the warehouse. The product purchase prediction platform providing device 130 may derive significant variables for product purchase prediction through various artificial intelligence algorithms and statistical criteria, and the significant variables may correspond to independent variables that may affect product purchase prediction. there is.

The product purchase prediction platform providing device 130 may increase the accuracy of product purchase prediction by using only significant independent variables, and may repeatedly perform data collection, analysis, and modeling processes to build an optimized model.

The device for providing a product purchase prediction platform 130 selects a model with the best product purchase prediction among AI-based product purchase prediction platforms and secures additional data several times until the Nth time to increase the product purchase prediction rate of shopping mall purchasers.

An e-commerce system according to another embodiment of the present invention may include a secure login system.

15 is a diagram showing the configuration of a safe login system according to an embodiment of the present invention.

Referring to FIG. 15, the safe login system according to an embodiment of the present invention includes a first communication device 10, a second communication device 20, a security relay server 30, a web server 40, and a location confirmation server. (50) and an authentication information storage server (60).

The first communication device 10, the second communication device 20, the security relay server 30, the web server 40, the positioning server 50, and the authentication information storage server 60 each form a network 70. communicate with each other through Here, the network 70 includes a mobile communication network, a wired Internet network, a local area wireless communication network, and the like, and since it corresponds to well-known and used technology in the present invention, a detailed description thereof will be omitted.

16 is a flowchart illustrating a method of performing login authentication in a safe login system according to an embodiment of the present invention.

Referring to FIG. 16, the second communication device 20 accesses the web server 40 to which the web site address entered by the user is assigned, and the web server 40 has a login menu for entering an ID and password. The included web page is transmitted to the second communication device 20 (S201).

Next, the second communication device 20 displays the web page received from the web server 40 on the screen. Also, the agent 21 of the second communication device 20 outputs a disabled safe login menu under the login menu of the web page.

17 is a diagram illustrating a web page displaying a safe login menu according to an embodiment of the present invention.

As shown in FIG. 17, the agent 21 may display a secure login menu 32 according to the present invention on the web page in addition to the login menu 31 provided on the web page itself.

Next, the agent 21 of the second communication device 20 confirms that the second communication device 20 starts browsing the web page, informs the start of the safe login service, and informs the user of the second communication device 20. A service notification message including identification information and second communication device identification information is transmitted to the security relay server 30 (S203).

Then, the security relay server 30 checks the user identification information included in the service notification message, and checks the identification information of the first communication device 10 mapped to the user identification information. Then, the security relay server 30 transmits the service notification message to the first communication device 10 having the identified identification information (S205).

Subsequently, the first communication device 10 checks the location information of the second communication device 20 connected to the web server 40 and also checks its own location information (S207).

Next, the first communication device 10 compares the location information of the second communication device 20 with its own location information, and determines whether it is located in the same place as the second communication device 20 (S209). . At this time, the first communication device 10 checks whether it is located in the same administrative district as the second communication device 20 or whether the distance between the second communication device 20 and itself is within a critical distance (eg, 100 m). By doing so, it is possible to determine whether or not the second communication device 20 is located in the same place.

When it is determined that the first communication device 10 is located in the same place as the second communication device 20 as a result of the determination, it transmits a safe log-in activation message to the second communication device 20 (S211).

Next, the agent 21 of the second communication device 20 monitors whether the safe login menu is clicked, and when the safe login menu is clicked, the identification information of the website to be logged in and access to the web server 40 are provided. A log-in notification message including the accessible access token, user identification information, and identification information of the second communication device 20 is generated and transmitted to the security relay server 30 (S213 and S215).

Then, the security relay server 30 checks the user identification information included in the login notification message, and checks the identification information of the first communication device 10 mapped to the user identification information. Then, the security relay server 30 transmits the login notification message to the first communication device 10 having the identified identification information (S217).

Next, the first communication device 10 extracts user identification information, website identification information, an access token, and identification information of the second communication device 20 from the login notification message received from the secure relay server 30 . Subsequently, the first communication device 10 checks the extracted web site identification information and the mapped security level in the security policy table (S219).

Next, the first communication device 10 checks the location determination result performed in step S209 again, and applies the checked security level or enhanced security level based on the location determination result (S221).

Subsequently, the first communication device 10 acquires login authentication information (ie, ID and password), which is one of authentication related data, based on the applied security level (S223).

Next, the first communication device 10 checks the website identification information and the access token extracted from the log-in notification message, and uses the web server 40 to which the website identification information has been assigned to obtain the login authentication information, reinforcement At least one of the authentication information is transmitted (S225).

Then, the web server 40 identifies the second communication device 20 attempting to log in based on the access token received from the first communication device 10 and checks whether the authentication information is accurate, thereby performing the second communication device 20. Login authentication of the device 20 is performed (S227).

Next, if the login authentication fails, the web server 40 fails the login of the second communication device 20, and if the login authentication succeeds, the authentication success message is transmitted to the second communication device 20. After that (S229), the second communication device 20 provides the requested online service.

Meanwhile, the first communication device 10 may transmit, to the web server 40, only enhanced authentication information excluding login authentication information when a security level of 3 is applied. In this case, the web server 40 performs authentication of the second communication device 20 based on the reinforced authentication information.

In addition, the first communication device 10 may transmit at least one of decrypted login authentication information and enhanced authentication information to the second communication device 20 . In this case, the second communication device 20 transmits the authentication information received from the first communication device 10 to the web server 40 to perform login authentication.

Hereinafter, in the description with reference to FIGS. 18 to 20, steps having the same reference numerals as those in FIG. 16 are applied in the same manner as in FIG.

18 is a flowchart illustrating a method of performing login authentication in a safe login system according to another embodiment of the present invention.

Referring to FIG. 18, after applying the security level, the first communication device 10 acquires the user's login authentication information based on the security level (S423).

On the other hand, if the first communication device 10 has a security level of 3, which is the highest level, it obtains reinforced authentication information by receiving reinforced login authentication information such as biometric information and OTP from the user.

Alternatively, if the security level is level 3, the first communication device 10 outputs an input window for inputting personal authentication information, and through this input window, password and biometric information (eg, fingerprint information, iris information, etc.) , User authentication information such as resident registration number can be input from the user.

Next, the first communication device 10 transmits at least one of the obtained encrypted login authentication information and the reinforced authentication information to the second communication device 20 (S425).

Then, the second communication device 20 decrypts the encrypted login authentication information received from the first communication device 10 using the decryption key stored therein (S427), and sends the decrypted login authentication information to the web server 40. ) to request login authentication (S429).

Next, the web server 40 checks whether the authentication information received from the second communication device 20 is correct, thereby performing login authentication of the second communication device 20 (S431).

Next, if the login authentication fails, the web server 40 fails the login of the second communication device 20, and if the login authentication succeeds, the authentication success message is transmitted to the second communication device 20. After (S433), the second communication device 20 provides the requested online service.

19 is a flowchart illustrating a method of performing login authentication in a safe login system according to another embodiment of the present invention.

In the embodiment described with reference to FIG. 19 , the first communication device 10 stores decryption keys classified for each communication device, and the second communication device 20 stores encrypted login authentication information for each website.

Referring to FIG. 19, upon application of the security level, the first communication device 10 proceeds with a process of extracting a decryption key, which is one of authentication related data, based on the applied security level (S523).

On the other hand, if the first communication device 10 has a security level of 3, which is the highest level, it extracts a decryption key corresponding to the identification information of the second communication device, and also receives enhanced authentication information such as biometric information and OTP from the user. By receiving the input, reinforced authentication information is obtained (S525). Alternatively, if the security level is level 3, the first communication device 10 outputs an input window for inputting user authentication information, receives user authentication information through the input window, and receives user authentication information from the user through the input window. After authenticating whether the information is correct, it is possible to optionally obtain authentication-related data. That is, if the security level is level 3, the first communication device 10 authenticates whether the user authentication information input from the user is correct, and if the authentication is successful, it receives enhanced authentication information from the user, extracts a decryption key, or both. (That is, the enhanced authentication information and the decryption key) may all be acquired.

In the description referring to FIG. 19 , it is described that the first communication device 10 applies a security level of 3 and additionally acquires enhanced authentication information.

Next, the first communication device 10 transmits the extracted decryption key and reinforced authentication information to the second communication device 20 (S527).

Subsequently, the second communication device 20 extracts encrypted login authentication information mapped to the currently accessed website identification information from the encrypted login authentication information for each site being stored therein (S529). Next, the second communication device 20 decrypts the extracted login authentication information using the decryption key received from the first communication device 10 (S531). In addition, the second communication device 20 decrypts the reinforced authentication information received from the first communication device 10 using the decryption key stored therein.

Next, the second communication device 20 transmits the decrypted login authentication information and the reinforced authentication information to the web server 40 to request login authentication (S533).

Then, the web server 40 checks whether both the login authentication information and the reinforced authentication information received from the second communication device 20 are correct, thereby performing login authentication on the second communication device 20 (S535). ). Next, if the login authentication fails, the web server 40 fails the login of the second communication device 20, and if the login authentication succeeds, the authentication success message is transmitted to the second communication device 20. After (S537), the second communication device 20 provides the requested online service.

On the other hand, when the first communication device 10 applies the first level or the second level of security, it transmits only the decryption key excluding the enhanced authentication information to the second communication device 20, and the second communication device ( 20) decrypts the login authentication information extracted in step S529 using the decryption key and transmits it to the web server 40. That is, when the first or second level of security is applied in the first communication device 10, the second communication device 20 transmits only the login authentication information excluding the reinforced authentication information to the web server 40. and the web server 40 performs login authentication of the second communication device 20 based on the login authentication information.

20 is a flowchart illustrating a method of performing login authentication in a safe login system according to another embodiment of the present invention.

In the embodiment described with reference to FIG. 20 , the first communication device 10 classifies and stores authentication information storage addresses for each encrypted web site by communication device identification information.

Referring to FIG. 20 , when a security level is applied, the first communication device 10 proceeds with a process of extracting an authentication information storage address, which is one of authentication related data, based on the applied security level (S623).

On the other hand, if the first communication device 10 has a security level of 3, which is the highest level, it extracts an encrypted authentication information storage address mapped with site identification information from storage address data dedicated to the second communication device, and also provides information from the user. Reinforced authentication information is obtained by receiving reinforced login authentication information such as biometric information and OTP (S625).

In the description referring to FIG. 20 , it is described that the first communication device 10 applies a security level of 3 and additionally obtains enhanced authentication information.

Next, the first communication device 10 transmits the extracted encrypted authentication information storage address and reinforced authentication information to the second communication device 20 (S627).

Subsequently, the second communication device 20 decrypts the encrypted authentication information storage address using the decryption key stored therein. Then, the second communication device 20 transmits the authentication information request message in which the storage address is recorded to the authentication information storage server 60 (S629).

Then, the authentication information storage server 60 checks the authentication information storage address in the authentication information request message, extracts the encrypted authentication information stored in the storage address, and transmits it to the second communication device 20 (S631).

Next, the second communication device 20 decrypts the encrypted authentication information using the decryption key stored therein, and also decrypts the reinforced authentication information received from the first communication device 10 (S633). Next, the second communication device 20 requests login authentication by transmitting the decrypted login authentication information and the reinforced authentication information to the web server 40 (S635).

Then, the web server 40 checks whether both the login authentication information and the reinforced authentication information received from the second communication device 20 are correct, thereby performing login authentication on the second communication device 20 (S637). ). Next, if the login authentication fails, the web server 40 fails the login of the second communication device 20, and if the login authentication succeeds, the authentication success message is transmitted to the second communication device 20. After (S639), the second communication device 20 provides the requested online service.

21 is a diagram showing an electronic commerce system according to another embodiment of the present invention.

Referring to FIG. 21 , an electronic commerce system according to another embodiment of the present invention may include a user terminal 10 and a management server 20 .

The user terminal 10 may correspond to a computing device capable of accessing an online shopping mall, purchasing products, and receiving product recommendations through product purchase prediction.

For example, the user terminal 10 may be implemented as a smart phone, laptop computer, or computer, but is not necessarily limited thereto, and may be implemented as various devices such as a tablet PC.

The management server 20 may be connected to the user terminal 10 through a network, and may exchange data with the user terminal 10 through the network.

The management server 20 corresponds to a computer or program capable of collecting and analyzing data related to product purchase through the user terminal 10 and predicting product purchase, and providing optimized recommended products to users through this. It can be implemented as a server that

The management server 20 may provide a product purchase prediction service to the user terminal 10 , including the product purchase prediction platform providing device 130 shown in FIG. 9 .

Meanwhile, the electronic commerce system according to another embodiment of the present invention may further include a product packaging box 30 .

The product packaging box 30 may be a product packaging basket for packaging products to be sold in this embodiment. For example, a product accommodation space is formed therein, and an opening communicating with the product accommodation space is formed in one area. It may be formed in the form of a plastic box that is formed.

The product packaging box 30 may include a product recognition unit on which a product recognition code is printed. The product recognition unit may be formed of a barcode or QR code, and the product recognition code may be recognized through a predetermined scanning device and transmitted to the management server 20 . The management server 20 may collect current state information such as product inventory and delivery through a product recognition unit of the product packaging box 30 .

22 is a view showing a portion of the product packaging box shown in FIG. 21;

Referring to FIG. 22 , the product packaging box 30 may include a push member 310 .

A pair of push members 310 may be installed on both sides of the inner bottom surface of the product packaging box 30, and are installed to move in the left and right directions, respectively, and operate to grip and fix products accommodated therebetween. do.

The push member 310 includes a horizontal member 311 inserted into the inner bottom surface of the product packaging box 30, a fixing part 313 formed at one end of the horizontal member 311, and the other end of the horizontal member 311. It may include a vertical member 312 extending in the vertical direction from the product packaging box 30 and protruding in the vertical direction from the inner bottom surface of the product packaging box 30 .

At this time, at least a part of the inner bottom surface of the product packaging box 30 may be formed to be opened so that the vertical member 312 protrudes and moves in the left and right directions.

A pair of protrusions 3111 may be formed at both ends of the bottom surface of the horizontal member 311, and a spring 3112 may be installed between the pair of protrusions 3111.

The fixing part 313 operates according to a predetermined control signal to allow the horizontal member 311 and the vertical member 312 to move in the left and right directions.

The fixing part 313 may include a cover 3131 formed to cover the upper side of one end of the horizontal member 311 , a fixing pin 3132 and a driving part 3133 embedded in the cover 3131 .

A plurality of locking grooves 3113 may be formed on the upper surface of one end of the horizontal member 311 . The fixing pin 3132 may be selectively caught in any one of the plurality of locking grooves 3113. At this time, the fixing pin 3132 can be moved in the vertical direction by the drive unit 3133 formed as a solenoid valve. The driving unit 3133 may be manually controlled by a user's button manipulation including a predetermined operation button, or may be automatically controlled when a predetermined sensor detects that a product is accommodated in the product packaging box 30 .

When a product is accommodated in the product packing box 30, the push member 310 moves upward by the operation of the drive unit 3133 so that the locking pin 3132 is disengaged from the locking groove 3113, In that state, the vertical member 312 moves in the left and right directions to grip the product, and the fixing pin 3132 moves downward by the operation of the drive unit 3133 and is caught in the locking groove 3113, thereby The movement state can be fixed.

Accordingly, the push member 310 can safely fix the product accommodated in the product packaging box 30 .

Although the embodiments of the present invention have been described with reference to the accompanying drawings, those skilled in the art can realize that the present invention can be implemented in other specific forms without changing the technical spirit or essential features. you will be able to understand Therefore, the embodiments described above should be understood as illustrative in all respects and not limiting.

100: manufacturer's device
120: wholesale device
140: retail device
150: application for product management
155: database
160: payment terminal
180: consumer
190: smartphone
192: application for product purchase
200: integrated product management server

Claims (2)

A user terminal accessing an online shopping mall and purchasing products; and
A management server connected to the user terminal through a network and collecting data related to product purchase through the user terminal;
The management server,
A product purchase prediction platform providing device for providing a product purchase prediction service to the user terminal;
The product purchase prediction platform providing device,
a data warehouse construction unit that collects product purchase data of a purchaser object to predict product purchases of purchasers using a shopping mall and builds a data warehouse;
a data warehouse updating unit verifying the lifestyle of each purchasing customer based on the product purchase data and adding it to the data warehouse;
a candidate data population generation unit generating a plurality of candidate data randomly extracted from the data warehouse as candidate data populations and determining predictive independent variables that satisfy statistical criteria;
An optimization model determiner determining a product purchase prediction model having the highest product purchase predictive value as an optimization model for each prediction independent variable by applying a plurality of artificial intelligence algorithms to the prediction independent variable based on the candidate data population;
A product packaging box having a product accommodating space formed therein, an opening communicating with the product accommodating space formed in one area, and a product recognition code recognized by a predetermined scanning device printed thereon; further comprising,
The product packaging box,
A pair of push members installed on both sides of the inner bottom surface and installed to be movable in the left and right directions, respectively, to grip and fix the product accommodated therebetween; includes,
The push member,
a horizontal member inserted into the inner bottom surface of the product packaging box;
a fixing part formed at one end of the horizontal member; and
A vertical member extending in a vertical direction from the other end of the horizontal member and protruding in a vertical direction from the bottom surface of the inside of the product packaging box;
The product packaging box,
At least a part of the inner bottom surface is formed so that the vertical member protrudes and moves in the left and right directions,
The horizontal member,
A pair of protrusions are formed at both ends of the bottom surface, and a spring is installed between the pair of protrusions,
The fixing part,
It operates according to a predetermined control signal to enable left and right movement of the horizontal member and the vertical member,
The fixing part,
a cover formed to cover the upper side of one end of the horizontal member;
A fixing pin embedded in the cover; and
A drive unit formed of a solenoid valve and moving the fixing pin in the vertical direction; includes,
The horizontal member,
A plurality of locking grooves are formed on the upper surface of one end,
The fixing pin is
When it is sensed that a product is accommodated in the product packing box by a predetermined sensor, it is moved upward by the control of the driving unit, and the locking with any one of the plurality of locking grooves is released, and the vertical member moves in the left and right directions. When the product is gripped, it moves downward under the control of the driving unit and is caught in one of the plurality of locking grooves to fix the moving state of the vertical member,
The product purchase prediction platform providing device,
A product purchase prediction providing unit that predicts product purchase for a specific customer based on the optimization model and provides a recommended product;
The product purchase data,
E-commerce system, including demographic characteristics, purchase season characteristics, purchase timing characteristics, purchase price fluctuations, and purchased products.
delete

Images