KR102467194B1 - System and method for product inspection using artificial intelligence and computer program for the same - Google Patents

Abstract

The present invention relates to a product inspection system and method using artificial intelligence and a computer program therefor. A product inspection system according to the present invention includes a database for storing sales data for at least one of a seller and a product registered from a seller terminal; a machine learning-based reliability calculation unit that uses the stored sales data as prior learning data and calculates reliability of at least one of the product and the seller based on the learning data; a communication unit which receives information on the product and the seller from the seller terminal and transmits information on the calculated reliability to a buyer terminal; and a product inspection server composed of a controller that controls the reliability calculation unit to receive a request from the purchaser terminal and transmit the calculated reliability to the purchaser terminal in the form of a numerical value or grade. In this way, by measuring the reliability of the seller or the product using artificial intelligence technology, it is possible to provide the buyer with information on whether the seller or the product is trustworthy, and periodically update the seller and used product data. Through this, it is possible to provide accurate prediction information by measuring the reliability of a seller or a used item.

Description

Product inspection system and method using artificial intelligence and computer program for it { SYSTEM AND METHOD FOR PRODUCT INSPECTION USING ARTIFICIAL INTELLIGENCE AND COMPUTER PROGRAM FOR THE SAME }

The present invention relates to a product inspection system and method using artificial intelligence and a computer program therefor. More specifically, it relates to a product inspection system and method using artificial intelligence that provides predictive information when fraud is suspected in the process of selling products online, and a computer program therefor.

Recently, with the rapid development of information and communication technology, most goods can be traded online. Among them, not only new products but also used products are actively sold online.

These online trading methods for used goods are gradually diversifying, such that sellers can directly register and sell their goods not only through cafes and bulletin boards on portal sites, but also through open markets and smartphone applications linked with them. have.

However, when such used goods are traded online, it is difficult for the buyer to trust the seller and transact with the seller because it is difficult to confirm whether the seller is the person who legally owns the goods or whether the goods are genuine or not.

Korean Patent Registration No. 10-439332

Therefore, the present invention measures the reliability of a seller or an item using artificial intelligence technology, thereby providing a buyer with information on whether the seller or the corresponding item is trustworthy, and an item inspection system using artificial intelligence and the item inspection It aims to provide a method.

In addition, the present invention periodically updates data on the seller and used items and measures the reliability of the seller or used items through this, thereby providing accurate prediction information and product inspection system using artificial intelligence and the product inspection It aims to provide a method.

The above object is to include a database for storing sales data for at least one of a seller and an item registered from a seller terminal; a machine learning-based reliability calculation unit that uses the stored sales data as prior learning data and calculates reliability of at least one of the product and the seller based on the learning data; a communication unit which receives information on the product and the seller from the seller terminal and transmits information on the calculated reliability to a buyer terminal; An article inspection server comprising a control unit that controls the reliability calculation unit to receive a request from the purchaser terminal and transmit the calculated reliability to the purchaser terminal in the form of a numerical value or grade. It is achieved by the product inspection system.

The control unit may store reliability-based information, which is a basis for calculating the reliability, in the database, and transmit the reliability-based information to the purchaser's terminal according to a request of the purchaser.

The reliability basis information includes the selling price of the product, whether or not the product is duplicated registration, a picture of the product, the title of the uploaded content, detailed description information of the uploaded content, and information about the uploaded content. Product reliability information including at least one of the publisher's comment information; Including at least one of the seller's name, the seller's ID, the seller's nickname, the seller's contact information, the seller's account number, the seller's platform level, and the seller's product transaction information It may include seller reliability information.

The control unit updates the reliability and the reliability basis information according to a preset time interval, and determines the number of registered products of the same category as the registered product during the preset time among the stored sales data during the past time interval. When the number of registrations is greater than the number of registrations, a weight is assigned to the seller reliability information, and when the number of registrations of a seller's product during the preset time is greater than the number of registrations during the same time interval in the past, a weight is assigned to the reliability information of the product. have.

Storing, by the product inspection system, sales data for at least one of the product and the seller; The product inspection system uses artificial intelligence, comprising the step of using the stored sales data as prior learning data and calculating reliability for at least one of the product and the seller based on the learning data. The above object is also achieved by a product inspection method.

The product inspection system may further include receiving a request from a purchaser terminal and transmitting information on the calculated reliability in the form of a numerical value or grade to the purchaser terminal.

In the transmitting of the reliability information, reliability basis information that is a basis for calculating the reliability may be stored and additionally transmitted to the purchaser terminal.

The reliability basis information includes the selling price of the product, whether or not the product is duplicated registration, a picture of the product, the title of the uploaded content, detailed description information of the uploaded content, and information about the uploaded content. Product reliability information including at least one of the publisher's comment information; Including at least one of the seller's name, the seller's ID, the seller's nickname, the seller's contact information, the seller's account number, the seller's platform level, and the seller's product transaction information It may include seller reliability information.

In the step of storing the sales data, the sales data is updated and stored according to a predetermined time interval, and in the step of calculating the reliability, among the stored sales data for the predetermined time period, the same category as the registered product is stored. When the number of product registrations is greater than the number of registrations during the past time interval, a weight is given to the seller reliability information, and the number of product registrations of any one seller during the predetermined time period is greater than the number of registrations during the same past time interval. In this case, a weight may be assigned to the product reliability information.

According to the product inspection system and method using artificial intelligence according to the present invention and the computer program therefor, information on whether the seller or the product is trustworthy to the buyer by measuring the reliability of the seller or the product and providing it to the buyer. can provide.

In addition, according to the product inspection system and method using artificial intelligence and the computer program for this according to the present invention, by periodically updating data on sellers and used items and measuring the reliability of sellers or used items through this, accurate forecast information can be provided.

1 is a block diagram showing the configuration of a product inspection system according to the present invention.
2 is a diagram for explaining the reliability calculation process of the product inspection system according to the present invention.
3 is a diagram showing a user interface of the product inspection system according to the present invention.
Figure 4 is a flow chart showing a product inspection method of the product inspection system according to the present invention.

Hereinafter, with reference to the accompanying drawings, a product inspection system and method using artificial intelligence according to the present invention and a computer program therefor will be described in detail.

1 is a block diagram showing the configuration of a product inspection system using artificial intelligence according to an embodiment of the present invention. As shown in FIG. 1 , the product inspection system according to an embodiment of the present invention includes a seller terminal 1 , a buyer terminal 2 , and an item inspection server 3 .

The seller terminal 1 is a device for use by a seller who wants to upload information or posts related to the goods he/she sells to a used goods trading platform or shopping mall website, and the buyer terminal 2 is a used goods trading platform or shopping mall web site. It is a device for use by a buyer who wants to purchase used goods registered by a seller through a site, etc.

In FIG. 1 , the seller terminal 1 and the buyer terminal 2 are shown as one device, but this is for convenience of description, and the actual number of users or the number of user devices using the product inspection system according to the embodiments It will be readily understood that it is not intended to limit

The seller terminal 1 and the buyer terminal 2 according to the present invention are a mobile communication terminal such as a smartphone, a personal computer, a personal digital assistant (PDA), a tablet, and an Internet Protocol Television (IPTV) ) may be implemented in the form of any computing device such as a set-top box for the like.

The product inspection server 3 is a server associated with an institution that provides a shopping mall website or a used product trading platform where a user, that is, a seller, can sell used products by uploading data. For example, the product inspection server 3 interworks with a web server providing a shopping mall website or an application service server, etc., to at least one of registered used products and sellers registered used products. Reliability can be calculated and provided to the buyer.

In this specification, the communication method between the shopping mall website and the used goods trading platform, the product inspection server 3, the seller terminal 1 and the buyer terminal 2 requires networking between objects through wired and/or wireless networks. It may include all possible communication methods, and is not limited to wired communication, wireless communication, 3G, 4G, 5G or other methods.

For example, wired and/or wireless networks between the product inspection server 3, the seller terminal 1, and the buyer terminal 2 may be LAN (Local Area Network), MAN (Metropolitan Area Network), GSM (Global System for Mobile Network), EDGE (Enhanced Data GSM Environment), HSDPA (High Speed Downlink Packet Access), W-CDMA (Wideband Code Division Multiple Access), CDMA (Code Division Multiple Access), TDMA (Time Division Multiple Access), Bluetooth ( Bluetooth), Zigbee, Wi-Fi, Voice over Internet Protocol (VoIP), LTE Advanced, IEEE802.16m, WirelessMAN-Advanced, HSPA+, 3GPP Long Term Evolution (LTE), Mobile WiMAX (IEEE) 802.16e), UMB (formerly EV-DO Rev. C), Flash-OFDM, iBurst and MBWA (IEEE 802.20) systems, HIPERMAN, Beam-Division Multiple Access (BDMA), World Interoperability for Microwave Access (Wi-MAX) and It may refer to a communication network by one or more communication methods selected from the group consisting of ultrasonic communication, but is not limited thereto.

The product inspection server 3 according to an embodiment of the present invention includes a communication unit 31, a database 32, a reliability calculation unit 33, and a control unit 34.

The product inspection system and the product inspection server 3 according to embodiments of the present invention and each unit 31 to 34 included therein may have an aspect of being entirely hardware, or partially hardware and partially software. can For example, the product inspection server 3 and each unit 31 to 34 included therein may collectively refer to hardware and related software for processing data of a specific format and content or/or exchanging data in an electronic communication method. In this specification, terms such as "unit", "module", "device", "terminal", "server" or "system" are intended to refer to a combination of hardware and software driven by the hardware. For example, the hardware may be a data processing device including a CPU or other processor. In addition, software driven by hardware may refer to a running process, an object, an executable file, a thread of execution, a program, and the like.

In addition, each element constituting the product inspection server 3 is not necessarily intended to refer to a separate device that is physically separated from each other. That is, the communication unit 31, the database 32, the reliability calculation unit 33, and the control unit 34 of FIG. 1 change the hardware constituting the product inspection system or the product inspection server 3 to the operation performed by the corresponding hardware. It is only functionally divided according to, and each part does not necessarily have to be provided independently of each other. Of course, depending on embodiments, one or more of the communication unit 31, the database 32, the reliability calculation unit 33, and the control unit 34 may be implemented as separate devices that are physically separated from each other.

The communication unit 31 receives information about the seller, an image of a product that the seller wants to sell, and product information from the seller terminal 1, and information about the buyer and information about the product the buyer wants to purchase from the buyer terminal 2. receive

The database 32 stores sales data for at least one of a product and a seller. Here, the sales data includes information such as the seller's name, ID, nickname, e-mail, phone number, account number, transaction period, etc., type of product, sales price, photo of the product, title of the post registered by the seller, and product It includes information such as detailed information.

The reliability calculation unit 33 uses the sales data stored in the database 32 as prior learning data, calculates the reliability of at least one of the product and the seller based on the learning data, and the control unit 34 Receives a request from the purchaser's terminal and controls the reliability calculation unit 33 to transmit the calculated reliability to the purchaser's terminal in the form of a numerical value or grade.

2 is a diagram for explaining a reliability calculation process of a product inspection system according to an embodiment of the present invention. As shown in FIG. 2, in the product inspection system according to the present invention, the reliability calculation unit 33 of the product inspection server 3 preprocesses pre-stored sales data as big data and machine learning to detect fraud and suspicion learned in advance. Using the model, the reliability of products and sellers registered on a shopping mall website or a used product trading platform is calculated.

The reliability calculation unit 33 according to the present invention collects, pre-processes, and learns sales data of used goods to generate a fraud suspected model, and similarly collects and pre-processes used goods prediction data to suspect fraud. In this case, a reliability calculation algorithm may be configured by learning the reliability basis information corresponding to the case by machine learning.

In addition, the reliability calculation unit 33 according to the present invention collects, pre-processes, and learns the seller's sales data to create a fraud-suspected model, and uses the collected and pre-processed seller's prediction data to suspect fraud. In this case, a reliability calculation algorithm may be configured by learning the reliability basis information corresponding to the case by machine learning.

Here, the reliability basis information includes product reliability information and seller reliability information.

Reliability information of an item includes the selling price of the item, whether or not the item is duplicated, a picture of the item, the title of the uploaded content, detailed description information of the uploaded content, and the publisher's comment information on the uploaded content. At least one may be included.

More specifically, the reliability information on the photo of the product is whether the photo was taken in the same space and location, the number of uploaded photos, whether the uploaded photo matches the category of the registered product, and previously registered as a fraudulent product. It may include information such as whether or not it matches the photograph.

The title and detailed description information of the uploaded content may include information such as the size of the input text and whether or not prohibited words are included in the input text.

In addition, the publisher's comment information on the uploaded content may include information such as a seller's response time to the comment, whether or not a banned word is included in the comment, and the like.

And the seller's reliability information is at least one of the seller's name, the seller's ID, the seller's nickname, the seller's contact information, the seller's account number, the seller's website or platform rating, and the seller's product transaction information. It may include seller reliability information including.

More specifically, whether the seller's name, ID, nickname, e-mail address, contact number, and account number are stored in the existing blacklist database, the seller's transaction period, and during the set period (eg: 1 day) of the goods registered by the seller Information on whether duplicate registrations have been made, and the sincerity of sellers through buyer surveys may be included.

It is possible to calculate the reliability of the product and the seller using the reliability calculation algorithm generated according to the reliability basis information configured as described above, and provide information about the calculated reliability to a linked shopping mall website or used transaction product platform.

Meanwhile, the controller 34 according to the present invention may store reliability basis information, which is a basis for calculating reliability, in a database, and provide the reliability basis information to a purchaser's terminal according to a purchaser's request.

3 is a diagram illustrating a user interface of a product inspection system according to an embodiment of the present invention. As shown in FIG. 3, the product inspection system according to the present invention is based on the reliability calculated by the reliability calculation unit 33 and the reliability calculation so that it can be displayed on the seller terminal 1 or the buyer terminal 2. Reliability basis information may be transmitted to the seller terminal 1 or the purchaser terminal 2 . The reliability calculated by the reliability calculation unit 33 may be displayed as a numerical value or may be displayed in the form of a predetermined grade such as safe, normal, or dangerous.

Here, the control unit 34 of the product inspection server 3 according to an embodiment of the present invention updates the reliability and reliability basis information according to a predetermined time interval and sets a predetermined time among sales data stored in the database 32. If the number of registrations of products of the same category as those registered during the past period is greater than the number of registrations during the same time interval in the past, seller reliability information may be weighted.

That is, in this case, the control unit 34 according to the present invention may determine that the possibility of fraud by the seller who registered the product is high, and calculate the reliability by assigning a weight to the reliability information of the seller rather than the reliability information of the product.

In addition, the control unit 34 may assign a weight to the product reliability information when the number of product registrations of any one seller during a predetermined time period among the sales data stored in the database 32 is greater than the number of registrations during the same time interval in the past. have.

In this case, since the reliability of the product itself may be questionable, the reliability of the product may be calculated by assigning a weight to the reliability information of the product rather than the reliability information of the seller.

Hereinafter, with reference to FIG. 4, an article inspection method of an article inspection system using artificial intelligence according to an embodiment of the present invention will be described.

First, the product inspection server 3 of the product inspection system stores sales data for at least one of the product and the seller (S10).

Then, the sales data stored in step S10 is used as prior learning data, and based on this learning data, reliability for at least one of the product and the seller is calculated based on machine learning (S20).

Here, the product inspection method of the product inspection system using artificial intelligence according to an embodiment of the present invention receives a request from the purchaser terminal 2 and converts information on the calculated reliability to the purchaser terminal 2 in the form of a numerical value or grade. ), and at this time, it is also possible to additionally transmit reliability basis information that is a basis for reliability calculation.

In addition, the product inspection method of the product inspection system using artificial intelligence according to an embodiment of the present invention updates and stores sales data according to a preset time interval in step S10, and stores the registered data for a preset time in step S20. When the number of registrations of an article of the same classification as the article is greater than the number of registrations during the past time interval, reliability may be calculated by assigning a weight to seller reliability information. Or, conversely, when the number of product registrations of any one seller during a predetermined time is greater than the number of registrations during the same time interval in the past, a weight may be assigned to the product reliability information.

Operations according to the product inspection method of the product inspection system using artificial intelligence according to the embodiments described above may be at least partially implemented as a computer program and recorded on a computer-readable recording medium. The computer-readable recording medium on which the program for implementing the operation of the product inspection method according to the embodiments is recorded includes all kinds of recording devices in which computer-readable data is stored. Examples of computer-readable recording media include ROM, RAM, CD-ROM, magnetic tape, floppy disk, and optical data storage devices. In addition, computer-readable recording media may be distributed in computer systems connected through a network, and computer-readable codes may be stored and executed in a distributed manner. In addition, functional programs, codes, and code segments for implementing this embodiment can be easily understood by those skilled in the art to which this embodiment belongs.

The present invention reviewed above has been described with reference to the embodiments shown in the drawings, but this is only exemplary, and those skilled in the art will understand that various modifications and variations of the embodiments are possible therefrom. However, such modifications should be considered within the technical protection scope of the present invention. Therefore, the true technical protection scope of the present invention should be determined by the technical spirit of the appended claims.

1: seller terminal 2: buyer terminal
3: product inspection server 31: communication department
32: database 33: reliability calculation unit
34: control unit

Claims (10)

a database for storing sales data for at least one of a seller and a product registered from a seller terminal;
a machine learning-based reliability calculation unit that uses the stored sales data as prior learning data and calculates reliability of at least one of the product and the seller based on the learning data;
a communication unit which receives information on the product and the seller from the seller terminal and transmits information on the calculated reliability to a buyer terminal;
An article inspection server composed of a control unit controlling the reliability calculation unit to receive a request from the purchaser terminal and transmit the calculated reliability to the purchaser terminal in the form of a numerical value or grade;
The reliability basis information, which is the basis of the reliability calculation,
At least one of the selling price of the product, whether or not the product is duplicated, a picture of the product, the title of the uploaded content, detailed description information of the uploaded content, and the publisher's comment information on the uploaded content. product reliability information including any one;
Including at least one of the seller's name, the seller's ID, the seller's nickname, the seller's contact information, the seller's account number, the seller's platform level, and the seller's product transaction information Include seller reliability information that
The control unit stores the reliability basis information in the database, transmits the reliability basis information to the purchaser terminal according to the purchaser's request, and the purchaser terminal displays the transmitted reliability level and the reliability basis information;
The control unit,
Updating the reliability and the reliability basis information according to a predetermined time interval;
When the number of registrations of products of the same category as the registered goods during the preset time period among the stored sales data is greater than the number of registrations during a past time interval, a weight is assigned to the seller reliability information;
The product inspection system using artificial intelligence, characterized in that for assigning a weight to the product reliability information when the number of product registrations of any one seller during the preset time is greater than the number of registrations during the same time interval in the past.
delete delete delete Storing, by the product inspection system, sales data for at least one of the product and the seller;
using the stored sales data as prior learning data by the product inspection system, and calculating reliability of at least one of the product and the seller based on the learning data;
receiving, by the product inspection system, a request from a purchaser terminal and transmitting information on the calculated reliability in the form of a numerical value or grade to the purchaser terminal together with reliability basis information that is a basis for calculating the reliability; and
The purchaser terminal includes displaying the transmitted reliability level and the reliability basis information;
The reliability basis information,
At least one of the selling price of the product, whether or not the product is duplicated, a picture of the product, the title of the uploaded content, detailed description information of the uploaded content, and the publisher's comment information on the uploaded content. product reliability information including any one;
Including at least one of the seller's name, the seller's ID, the seller's nickname, the seller's contact information, the seller's account number, the seller's platform level, and the seller's product transaction information Include seller reliability information that
In the step of storing the sales data,
Updating and storing the sales data at predetermined time intervals;
The step of calculating the reliability is,
When the number of registrations of products of the same category as the registered goods during the preset time period among the stored sales data is greater than the number of registrations during a past time interval, a weight is assigned to the seller reliability information;
If the number of registered products of any one seller during the predetermined time period is greater than the number of registrations during the same time interval in the past, a weight is assigned to the product reliability information. .
delete delete delete delete A computer program stored in a computer-readable recording medium combined with hardware to execute the product inspection method of the product inspection system using artificial intelligence according to claim 5.

Images