KR20230158768A - Method of operating global e-commerce platform that provide information on products preferred by users to sellers by analyzing data based on artificial intelligence - Google Patents

Abstract

The operating method of the e-commerce platform of the present invention includes the steps of a user terminal uploading user personal information to the main server; A seller terminal uploading a product to the main server; Uploading preferred product information by the user terminal to the main server; The main server providing a product list to the user terminal; The user terminal selects a product and transmits order information to the main server to proceed with the contract process; A step of the main server receiving product arrival and shipment information from the seller terminal and receiving product delivery completion information from the user terminal, wherein the main server uses first artificial intelligence to provide user personal information and preferred product information. It is characterized by generating a product list by processing.

Description

A method of operating a global e-commerce platform that matches users with sellers by analyzing data based on artificial intelligence to provide sellers with product information preferred by users TO SELLERS BY ANALYZING DATA BASED ON ARTIFICIAL INTELLIGENCE}

The present invention relates to a method of operating a global e-commerce platform that analyzes data based on artificial intelligence and matches users with sellers who provide sellers with product information preferred by users.

As platform business has become more active recently, the number of e-commerce platforms that match sellers selling products with consumers (users) who want to purchase products is increasing. The domestic e-commerce market is growing at an average annual rate of 26% every year, and the total market size is worth 224 trillion won. In addition, along with the establishment of the e-commerce market, the logistics market is growing rapidly, and the global logistics market is growing at an average annual rate of 10% until 2021.

Meanwhile, sellers who use a conventional e-commerce platform to upload and sell products to multiple shopping malls in multiple countries 1) feel burdened by system usage fees and complicated overseas sales procedures, and 2) the existing logistics system is a warehouse rental business. Focusing on the inconvenience of linking shopping mall/courier/inventory management/tax, and 3) the problem of logistics usage fees being more expensive than the shopping mall sales margin, that is, registering at the shopping mall and managing orders, warehousing, shipping, and transportation, etc. There are many problems with the consumption of human and material resources.

Therefore, there is a need for a total solution all-in-one global e-commerce platform that can easily and conveniently manage the commerce/order/warehouse/transportation/tax management systems of products sold in multiple shopping malls in multiple countries. .

Furthermore, in existing e-commerce platforms, sellers are having difficulty selling products due to a lack of data on products preferred by consumers. Meanwhile, artificial intelligence (AI) is a field of computer engineering and information technology that realizes human learning ability, reasoning ability, perception ability, and natural language understanding ability through computer programs. In particular, supervised learning, which is used in the most fields of artificial intelligence, is a method of predicting future values using training data containing the correct answer (Label). In the data collection stage, the purity of training data and test data is maintained. (For example, accuracy and truthfulness) determine the performance of artificial intelligence algorithms.

Conventional e-commerce platforms are programs based on simple algorithms and do not accurately reflect consumer preferences, so consumers are unable to receive accurate recommendations for products that match them, and at the same time, sellers spend a lot of time and effort predicting products that consumers prefer. There is a problem and a solution to it is required.

The problem that the present invention seeks to solve is to provide a method of operating a global e-commerce platform that analyzes data based on artificial intelligence and matches users with sellers who provide product information preferred by users.

The problems to be solved by the present invention are not limited to the problems mentioned above, and other problems not mentioned can be clearly understood by those skilled in the art from the description below.

The operating method of the e-commerce platform of the present invention to solve the above-mentioned problems includes the steps of a user terminal uploading user personal information to the main server; A seller terminal uploading a product to the main server; Uploading preferred product information by the user terminal to the main server; The main server providing a product list to the user terminal; The user terminal selects a product and transmits order information to the main server to proceed with the contract process; A step of the main server receiving product arrival and shipment information from the seller terminal and receiving product delivery completion information from the user terminal, wherein the main server uses first artificial intelligence to provide user personal information and preferred product information. It may be characterized by generating a product list by processing.

The main server may provide a first artificial intelligence to the seller terminal so that the seller terminal shares a list of products provided to users of a specific category who prefer a specific product.

The user personal information includes information about the user's gender, age, and occupation, and the main server uses virtual user personal information and virtual preferred product information as label values, and a data set with the product list set by the administrator as feature values. It may be characterized by generating a product list from user personal information and preferred product information using the first artificial intelligence that has learned.

transmitting satisfaction index information for the product list from the user terminal to the main server; The main server generates a second artificial intelligence by processing user personal information, preferred product information, product list, and satisfaction index information, and further includes the step of updating the first artificial intelligence using the second artificial intelligence. You can do this.

Satisfaction index information is a natural number that absolutely evaluates the product list provided from the main server, and the main server uses user personal information, preferred product information, and product list as label values and satisfaction index information as feature values to learn a second artificial intelligence. It can be characterized as being ordered.

The e-commerce platform of the present invention has the advantage of providing a total solution that allows sellers to easily and conveniently manage the commerce/order/warehouse/transportation/tax management systems of products sold in multiple shopping malls in multiple countries. .

Additionally, the e-commerce platform of the present invention has the advantage of recommending specific countries and specific shopping malls that match the seller's products by analyzing keyword trend indices for products in multiple countries and multiple shopping malls.

In addition, the e-commerce platform of the present invention has the advantage of providing customized product lists to users based on artificial intelligence and at the same time sharing the corresponding artificial intelligence engine with sellers to predict consumers' preferences for their products.

Furthermore, in the method of operating the e-commerce platform of the present invention, in the early stages of platform operation, a product list is created using an artificial intelligence algorithm that has learned the data set created by the administrator's work, and when the platform enters the stabilization stage, the product list is generated. The advantage of providing a user-customized recommended product list that is continuously upgraded by incorporating the data that users evaluated the recommended product list into the dataset and updating the existing artificial intelligence classification algorithm using the artificial intelligence algorithm learned based on this. There is.

The effects of the present invention are not limited to the effects mentioned above, and other effects not mentioned will be clearly understood by those skilled in the art from the description below.

1 is a flowchart showing the process of operating the e-commerce platform of the present invention.
Figure 2 is a block diagram showing the system used in the operating method of the e-commerce platform of the present invention.
Figure 3 is a conceptual diagram showing the integrated management of product commerce/order/warehouse/transport/tax management system in the operating method of the e-commerce platform of the present invention.
Figure 4 is a conceptual diagram explaining artificial intelligence used in the operating method of the e-commerce platform of the present invention.

The advantages and features of the present invention and methods for achieving them will become clear by referring to the embodiments described in detail below along with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below and may be implemented in various different forms. The present embodiments are merely provided to ensure that the disclosure of the present invention is complete and to provide a general understanding of the technical field to which the present invention pertains. It is provided to fully inform the skilled person of the scope of the present invention, and the present invention is only defined by the scope of the claims.

The terminology used herein is for describing embodiments and is not intended to limit the invention. As used herein, singular forms also include plural forms, unless specifically stated otherwise in the context. As used in the specification, “comprises” and/or “comprising” does not exclude the presence or addition of one or more other elements in addition to the mentioned elements. Like reference numerals refer to like elements throughout the specification, and “and/or” includes each and every combination of one or more of the referenced elements. Although “first”, “second”, etc. are used to describe various components, these components are of course not limited by these terms. These terms are merely used to distinguish one component from another. Therefore, it goes without saying that the first component mentioned below may also be a second component within the technical spirit of the present invention.

Unless otherwise defined, all terms (including technical and scientific terms) used in this specification may be used with meanings commonly understood by those skilled in the art to which the present invention pertains. Additionally, terms defined in commonly used dictionaries are not interpreted ideally or excessively unless clearly specifically defined.

Hereinafter, the operating method 1000 of the e-commerce platform of the present invention will be described with reference to the drawings. Figure 1 is a flow chart showing the process of the operating method of the e-commerce platform of the present invention, Figure 2 is a block diagram showing the system used in the operating method of the e-commerce platform of the present invention, and Figure 3 is the e-commerce platform of the present invention. It is a conceptual diagram showing that the product commerce/order/warehouse/transportation/tax management system is integrated and managed in the operating method, and Figure 4 is a conceptual diagram explaining artificial intelligence used in the operating method of the e-commerce platform of the present invention.

The method 1000 of operating an e-commerce platform of the present invention can be performed within a system including a user terminal 10, a seller terminal 20, a network 30, and a main server 40.

The user terminal 10 and the seller terminal 20 may be terminals that provide a web page, app page (app list), program, or application related to the operating method 1000 of the e-commerce platform of the present invention.

In this case, the user terminal 10 and the seller terminal 20 may be implemented as a computer that can access and connect to the main server 40 at a remote location through the network 30.

In detail, the user terminal 10 and the seller terminal 20 are wireless communication devices, including navigation, PCS (Personal Communication System), GSM (Global System for Mobile communications), PDC (Personal Digital Cellular), and PHS (Personal Handyphone System). ), PDA (Personal Digital Assistant), IMT (International Mobile Telecommunication)-2000, CDMA (Code Division Multiple Access)-2000, W-CDMA (W-Code Division Multiple Access), Wibro (Wireless Broadband Internet) terminal, smartphone It can include all types of handheld wireless communication devices such as (smartphone), smartpad, tablet PC, etc., as well as wired communication devices such as general desktop PCs. It is not limited to this.

The network 30 refers to a connection structure that allows information exchange between nodes such as the user terminal 10, the seller terminal 20, and the main server 40. Examples of such networks include RF, 3GPP ( 3rd Generation Partnership Project) network, LTE (Long Term Evolution) network, 5GPP (5rd Generation Partnership Project) network, WIMAX (World Interoperability for Microwave Access) network, Internet, LAN (Local Area Network), Wireless LAN (Wireless) Includes, but is not limited to, Local Area Network, WAN (Wide Area Network), PAN (Personal Area Network), Bluetooth network, NFC network, satellite broadcasting network, analog broadcasting network, DMB (Digital Multimedia Broadcasting) network, etc. does not

The main server 40 may be a server that provides web pages, app pages, programs, or applications related to the operating method 1000 of the e-commerce platform of the present invention.

The method 1000 of operating an e-commerce platform of the present invention includes the steps 100 of the user terminal 10 uploading user personal information to the main server 40; A step (200) of the seller terminal (20) uploading the product to the main server (40); Step 300 of the user terminal 10 uploading preferred product information to the main server 40; A step (400) in which the main server 40 provides a product list to the user terminal 10 using first artificial intelligence; A step (500) of the user terminal 10 transmitting satisfaction index information for the product list to the main server 40; The main server 40 generates a second artificial intelligence by processing user personal information, preferred product information, product list, and satisfaction index information, and updates the first artificial intelligence using the second artificial intelligence (600); The user terminal 10 selects a product and transmits order information to the main server 40 to proceed with the contract process (700); It may include a step 800 in which the main server 40 receives product arrival and shipment information from the seller terminal 20 and product delivery completion information from the user terminal 10.

The step 100 in which the user terminal 10 uploads the user's personal information to the main server 40 may be a step in which the user downloads an e-commerce platform program and registers as a member, and the user uploads personal information (name, contact information, Gender, age, occupation, ID image, etc.) can be entered and transmitted to the main server 40. In the method 1000 of operating an e-commerce platform of the present invention, identity authentication can be performed by performing mobile real-name authentication using the user's personal information.

The step 200 of the seller terminal 20 uploading a product to the main server 40 may be a step in which the seller inputs information about the product he or she wishes to sell. Specifically, the seller may enter information about the product he or she wishes to sell. You can enter product type, quantity, specifications, options, etc., but are not limited to this.

The main server 40 can recommend multiple countries and multiple shopping malls for uploading products to the seller terminal 20, and the seller terminal 20 can recommend multiple countries and multiple shopping malls recommended by the main server 40. By selecting a product from a shopping mall and uploading the product, the product uploaded by the seller terminal 20 can be sold in conjunction with multiple shopping malls in multiple countries.

In this case, the main server 40 recommends multiple countries and multiple shopping malls for uploading products to the seller terminal 20 based on the results of analyzing keyword trend indices for products in multiple countries and multiple shopping malls. can do. In addition, the main server 40 compares the keyword trend index for the product in the main search engines of a plurality of countries with the keyword trend index for the product in the self-search engine of the plurality of shopping malls and sends the product to the seller terminal 20. Multiple countries and multiple shopping malls can be recommended for uploading. In detail, the main server 40 processes the keyword trend index (number of searches for a specific product) in the main search engine for products uploaded by sellers in each of a plurality of countries, so that the keyword trend index during the first period is a specific value. If the product is above a certain value, the product can be defined as a "popular product", the keyword trend index during the first period is less than a certain value, it belongs to the first period, and the increase rate of the keyword trend index during the second period, which is shorter than the first period, is a certain value. When the value is above this value, the product can be defined as a "mania product (a product popular only with a small number of people)", and the keyword trend index during the first period is less than a certain value and belongs to the first period, and the second period is shorter than the first period. When the growth rate of the keyword trend index for a period is below a certain value, the product can be defined as an “unpopular product.” In this case, the “main search engine” may mean a search engine operated by a search portal site rather than a search engine operated by a shopping mall.

Next, the main server 40 1) processes the keyword trend index in the self-search engine of the shopping mall in the country where the product is a popular product, and if the keyword trend index during the first period is more than a certain value, it sells the product to the shopping mall at a designated selling price. It can be recommended to upload to (reflecting the fact that it is a popular product and is being sold a lot in the relevant shopping mall), the keyword trend index during the first period is below a certain value, it belongs to the first period, and during the second period, which is shorter than the first period. If the growth rate of the keyword trend index is above a certain value, it can be recommended to upload at a designated selling price (reflecting the fact that it is a popular product and that it may be sold a lot in the future at the shopping mall), and the keyword trend index during the first period is a certain value. If the increase rate of the keyword trend index during the second period, which is shorter than the first period and falls within the first period, is below a certain value, it may be recommended to upload at a price lower than the designated selling price (although it is a popular product, it may be sold a lot in the relevant shopping mall) Since there is no possibility, it is a strategy to attract users from other shopping malls by lowering the price). In addition, 2) it processes the keyword trend index in the own search engine of the shopping mall in the country where the product is a product for enthusiasts, and if the keyword trend index during the first period is above a certain value, it is recommended to upload it to the shopping mall at a price higher than the designated selling price. (It is a product for enthusiasts, but it is sold in large quantities in the relevant shopping mall, so it is judged to be difficult to obtain in other shopping malls, so it is a strategy to increase the price), and the keyword trend index during the first period is below a certain value, belongs to the first period, and is higher than the first period. If the increase rate of the keyword trend index during the short second period is more than a certain value, it can be recommended to upload at a designated selling price (although it is a product for enthusiasts, it reflects the situation that it may be sold a lot in the shopping mall in the future), and the keyword during the first period If the trend index is below a certain value, belongs to the first period, and the increase rate of the keyword trend index during the second period, which is shorter than the first period, is below a certain value, the shopping mall may not be recommended (it is a product for enthusiasts and will be sold a lot in the shopping mall) A strategy of giving up on uploading to the shopping mall because there is no possibility). Furthermore, 3) the keyword trend index in the own search engine of the shopping mall in the country where the product is an unpopular product is processed, and if the keyword trend index during the first period is above a certain value, it can be recommended to be uploaded to the shopping mall at a designated selling price ( If the keyword trend index during the first period is below a certain value (reflecting the fact that it is an unpopular product but is being sold a lot in the shopping mall), the shopping mall may not be recommended. In this case, the “self-search engine” may be a search engine operated within the shopping mall itself and used by users to search for products.

Furthermore, when the seller terminal 20 uploads a pre-processing template for a product, the main server 40 converts the pre-processing template uploaded by the seller terminal 20 into a standard template for the country and shopping mall selected by the seller terminal 20 and uploads it. can do.

That is, in the method 1000 of operating an e-commerce platform of the present invention, when a seller uploads a product to the platform, the platform can recommend a country and a shopping mall where the product is popular, the seller creates a pre-processing template provided by the platform, and If you select a country and shopping mall, the platform uploads products according to the standard upload form of the country and shopping mall, which can increase seller's convenience.

The step 300 of the user terminal 10 uploading preferred product information to the main server 40 may be a step in which the user inputs information about the product he or she wants to purchase into the main server 40. For example, preferred product information may include, but is not limited to, the type, quantity, specifications, and options of the user's preferred product.

In step 400, where the main server 40 provides a product list to the user terminal 10, the main server 40 uses first artificial intelligence to process the user's personal information and preferred product information to recommend among the seller's products. This may be a step in which products are selected and a list of products recommended to the user is created.

Meanwhile, in the early stages of platform operation, the data available from the platform is limited, so there may be a problem of not securing enough datasets to train the first artificial intelligence. Accordingly, in the operating method 1000 of the e-commerce platform of the present invention, a product list can be generated by generating an artificial intelligence prediction algorithm with virtual data. A detailed explanation of generating the above-described first artificial intelligence algorithm will be described later.

The step 500 of the user terminal 10 transmitting satisfaction index information about the product list to the main server 40 may be a step of evaluating the user's satisfaction with the product list recommended by the main server 40. In this case, the satisfaction index information may be a natural number value that absolutely evaluates the list of properties provided from the main server 40, but is not limited to this.

The main server 40 generates a second artificial intelligence by processing user personal information, preferred product information, product list, and satisfaction index information, and updates the first artificial intelligence using the second artificial intelligence (600). This may be a step in which the main server 40 updates the first artificial intelligence with the second artificial intelligence learned by the actual user personal information, actual preferred product information, and the user's actual satisfaction index information for the actual product list.

In other words, at the stage when the operation of the platform is stabilized, a new artificial intelligence prediction algorithm is created that updates the above-mentioned first artificial intelligence algorithm in real time by setting the personal information, preferred property information, and satisfaction index information obtained by the platform itself as a dataset. This allows you to continuously create updated listings. A detailed explanation of generating the above-described second artificial intelligence algorithm will be described later.

Step 700, in which the user terminal 10 selects a product and transmits order information to the main server 40 to proceed with the contract process, involves the user selecting a specific product from the product list provided by the main server 40 and purchasing it. This may be the stage of proceeding with an ordering contract.

In the step 800, where the main server 40 receives product arrival and shipment information from the seller terminal 20 and product delivery completion information from the user terminal 10, the platform manager receives and receives the product selected by the user from the seller. This may be the step of completing the sale by receiving information that the product has been shipped and receiving information from the user that the good product has been delivered and approved.

Meanwhile, in the operating method 1000 of the e-commerce platform of the present invention, the main server 40 can regularly provide a sheet summarizing product upload, order information, and stocking and shipping information to the seller terminal 20. In detail, the e-commerce platform provides a user interface (UI/UX) that allows sellers to easily and conveniently manage the commerce/order/warehouse/transportation/tax management systems of products sold in multiple shopping malls in multiple countries. can be provided.

Hereinafter, artificial intelligence used in the operating method 1000 of the e-commerce platform of the present invention will be described in detail. Artificial Intelligence (AI) is a field of computer engineering and information technology that realizes human learning ability, reasoning ability, perception ability, and natural language understanding ability through computer programs. In particular, supervised learning, which is used in the most fields of artificial intelligence, is a method of predicting future values using training data containing the correct answer (Label).

For reference, machine learning can be defined as a methodology that gives computers the ability to learn on their own without being explicitly programmed. This is a method that allows a program to learn data patterns on its own based on data. Machine learning is divided into supervised learning and unsupervised learning, depending on whether the correct answer is specified in the data required for learning. Classification divides the data into a finite number of categories depending on the purpose of use, and continuous learning. It is divided into Regression, which maps to values, Clustering, which groups similar data, and Dimension Reduction, which maps multi-dimensional data into representative lower dimensions.

Deep learning is one of the machine learning techniques that has dramatically improved the performance of machine learning, which had been stagnant for a while. Deep learning is a methodology based on the Artificial Neural Network (ANN) algorithm that mimics the overlap of synapses in the human brain structure. , The deep learning structure is a deep neural network (DNN) with multiple hidden layers between the input layer and the output layer, and a filter required for factor extraction in front of the hidden layer. It can include a convolutional neural network (CNN) that learns filters together, and a recurrent neural network (RNN) that can process time series data by stacking artificial neural networks at each time. Here, the high performance of the deep learning model is explained in two ways. First, the Inkyung Neural Network is a universal approximator that can approximate all types of functions by overlapping the weighted sum of the functions in each layer, if sufficiently general data is given. Data can be simulated with high accuracy. Second, in order to properly classify data, it is important to properly extract factors representing the data, and optimal factors can be extracted through filter learning using a convolutional neural network. In addition, deep learning is a developed form of a model in the field of artificial intelligence called a neural network, and the internal layer (hidden layer) of the hierarchical artificial neural network is composed of several stages. Recent deep learning models have increased internal layers, so the number of weights (meaning connection strength) connecting nodes can reach up to billions.

In the method 1000 of operating an e-commerce platform of the present invention, there is insufficient data to learn artificial intelligence at the beginning of the platform operation, so the main server 40 manages virtual user personal information and virtual preferred product information as label values. Using the first artificial intelligence that learned the dataset set as the feature value of the virtual product list classified by , a product list is generated by entering user personal information and preferred product information entered by the actual user terminal 10. can do.

In this case, the virtual user's personal information may include, but is not limited to, information about the virtual user's gender, age, and occupation, and the virtual preferred product information includes the type and quantity of the virtual user's preferred product. It may include information about specifications and options, but is not limited to this. The virtual product list may include, but is not limited to, information about the types, quantities, specifications, and options of multiple products recommended to the virtual user.

Accordingly, the main server 40 trains artificial intelligence with virtual user personal information (label value), virtual preferred product information (label value), and virtual product list (feature value), so that actual users can use user personal information. By entering preferred product information, you can create the first artificial intelligence prediction algorithm that outputs a list of products from sellers that match the information.

Furthermore, in the operation method 1000 of the e-commerce platform of the present invention, when the operation of the platform is stabilized, artificial intelligence is trained with data generated within the platform itself, and second artificial intelligence prediction is performed to provide feedback to the above-described first artificial intelligence algorithm. By creating an algorithm, the first artificial intelligence algorithm can be updated in real time.

In detail, the main server 40 prefers a specific product using a second artificial intelligence that learns user personal information accumulated by multiple users, preferred product information, and product list as label values, and the satisfaction index as feature value. When a specific product list is recommended to a user, the satisfaction index felt by the user can be predicted. Next, in order to train the first artificial intelligence, the main server 40 inputs the virtual user personal information, virtual preferred product information, and virtual product list set by the existing manager as label values into the second artificial intelligence. User satisfaction index information can be predicted for this. Next, the main server 40 selects a second artificial intelligence from among a plurality of datasets about virtual user personal information, virtual preferred product information, and a virtual product list set by the administrator to train the first artificial intelligence. Data sets in which the value of the satisfaction index information derived by inputting is lower than the average value of the preset satisfaction index (average value of the satisfaction index evaluated by multiple actual users) are excluded from the dataset for training the first artificial intelligence, thereby improving the first artificial intelligence. It can be updated in real time. In this case, the first artificial intelligence continuously receives and learns virtual user personal information, virtual preferred product information, and virtual product list newly set by the administrator, so there is no absence of learning data and it can evolve to suit the user. You can.

Furthermore, in the method 1000 of operating the e-commerce platform of the present invention, the main server 40 provides the first artificial intelligence to the seller terminal 20 so that the seller terminal 20 provides it to users of a specific category who prefer a specific product. By sharing a list of available products, you can predict users' preferences for the products they want to sell.

The operating method 1000 of the e-commerce platform of the present invention described above may be implemented as a program (or application) to be executed in combination with a server, which is hardware, and stored in a medium.

The above-mentioned program is C, C++, JAVA, machine language, etc. that can be read by the processor (CPU) of the computer through the device interface of the computer in order for the computer to read the program and execute the methods implemented in the program. It may include code coded in a computer language. These codes may include functional codes related to functions that define the necessary functions for executing the methods, and control codes related to execution procedures necessary for the processor of the computer to execute the functions according to predetermined procedures. It can be included. In addition, this code may further include a memory reference-related code that determines from which location (address address) in the computer's internal or external memory additional information or media required for the computer's processor to execute the above functions should be referenced. You can. In addition, if the computer's processor needs to communicate with any other remote computer or server in order to execute the above functions, the code uses the computer's communication module to determine how to communicate with any other remote computer or server. It may further include communication-related codes regarding whether communication should be performed and what information or media should be transmitted and received during communication.

The storage medium refers to a medium that stores data semi-permanently and can be read by a device, rather than a medium that stores data for a short period of time, such as a register, cache, or memory. Specifically, examples of the storage medium include ROM, RAM, CD-ROM, magnetic tape, floppy disk, optical data storage device, etc., but are not limited thereto. That is, the program may be stored in various recording media on various servers that the computer can access or in various recording media on the user's computer. Additionally, the medium may be distributed to computer systems connected to a network, and computer-readable code may be stored in a distributed manner.

The steps of the method or algorithm described in connection with the embodiment of the present invention may be implemented directly in hardware, implemented as a software module executed by hardware, or a combination thereof. The software module may be RAM (Random Access Memory), ROM (Read Only Memory), EPROM (Erasable Programmable ROM), EEPROM (Electrically Erasable Programmable ROM), Flash Memory, hard disk, removable disk, CD-ROM, or It may reside in any form of computer-readable recording medium well known in the art to which the present invention pertains.

Above, embodiments of the present invention have been described with reference to the attached drawings, but those skilled in the art will understand that the present invention can be implemented in other specific forms without changing its technical idea or essential features. You will be able to understand it. Therefore, the embodiments described above should be understood in all respects as illustrative and not restrictive.

Claims (5)

Uploading user personal information to the main server by the user terminal;
A seller terminal uploading a product to the main server;
Uploading preferred product information by the user terminal to the main server;
The main server providing a product list to the user terminal;
The user terminal selects a product and transmits order information to the main server to proceed with the contract process; and
A step of the main server receiving product arrival and shipment information from the seller terminal and receiving product delivery completion information from the user terminal,
A method of operating an e-commerce platform, wherein the main server generates a product list by processing user personal information and preferred product information using first artificial intelligence.
According to paragraph 1,
The main server provides first artificial intelligence to the seller terminal so that the seller terminal shares a list of products provided to users of a specific category who prefer specific products.
According to paragraph 1,
User personal information includes information about the user's gender, age, and occupation,
The main server uses the first artificial intelligence that has learned a dataset with virtual user personal information and virtual preferred product information as label values and the product list set by the administrator as feature values, and collects user personal information and preferred product information. A method of operating an e-commerce platform characterized by generating a product list from.
According to paragraph 3,
transmitting satisfaction index information for the product list from the user terminal to the main server; and
The main server generates a second artificial intelligence by processing user personal information, preferred product information, product list, and satisfaction index information, and further includes the step of updating the first artificial intelligence using the second artificial intelligence. How to operate an e-commerce platform.
According to paragraph 4,
Satisfaction index information is a natural number that absolutely evaluates the product list provided from the main server,
A method of operating an e-commerce platform, wherein the main server trains a second artificial intelligence using user personal information, preferred product information, and product list as label values and satisfaction index information as feature values.