Method and system for providing safe, non face to face second hand transaction platform based on ai based abnormal transaction detection and delivery driver matching

The system addresses fraud in second-hand trading by using AI for transaction detection and driver matching, ensuring safe and cost-effective non-face-to-face transactions.

KR103047264B1Active Publication Date: 2026-11-10변성진
View PDF 3 Cites 0 Cited by

Patent Information

Application Number
KR1020250163834
Authority / Receiving Office
KR · KR
Patent Type
Patents
Current Assignee / Owner
Filing Date
2025-11-04
Publication Date
2026-11-10
Estimated Expiration
2045-11-04

AI Technical Summary

Technical Problem

Current second-hand trading platforms face issues with fraud and require mutual trust between traders, leading to low usage and high transaction costs, with scams involving fake item photos and personal information disclosure, necessitating a safer non-face-to-face transaction solution.

Method used

A system utilizing AI for abnormal transaction detection and delivery driver matching, including product registration, purchase requests, delivery driver assignment, and real-time risk scoring to ensure safe non-face-to-face transactions.

Benefits of technology

Ensures safety in second-hand trading by detecting abnormal transactions and providing convenient non-face-to-face transactions, reducing fraud and transaction costs.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 112025122762854-PAT00003_ABST
    Figure 112025122762854-PAT00003_ABST
Patent Text Reader

Abstract

According to an embodiment of the present invention, a safe non-face-to-face second-hand trading platform provision system based on AI abnormal transaction detection and delivery driver matching is provided, comprising: a product information registration unit that receives information about a product subject to transaction from a seller terminal and transmits it to a plurality of buyer terminals; a purchase request receiving unit that receives a purchase request for the product subject to transaction from a buyer terminal, transmits a payment request for the product price to the buyer terminal, and receives and stores the amount paid by the buyer; a delivery driver matching unit that transmits a delivery request for the product subject to transaction to a plurality of delivery driver terminals and enables delivery by a specific delivery driver; and an abnormal transaction detection unit that detects whether there is an abnormal transaction during the transaction process for the product subject to transaction.
Need to check novelty before this filing date? Find Prior Art

Description

Technology Field

[0001] The present invention relates to a method and system for providing a safe non-face-to-face second-hand trading platform based on AI abnormal transaction detection and delivery driver matching. More specifically, it relates to a method and system that enables non-face-to-face trading while ensuring safety in second-hand trading, and enables accurate detection in the event of an abnormal transaction. Background Technology

[0002] As the online second-hand market grows, transactions based on C2C, as well as B2C which served as the foundation of e-commerce, are growing rapidly. With the advancement of information technology, the second-hand market is gradually becoming globalized and expanding in scale, and is expected to have a significant socioeconomic impact; however, due to an imperfect system, complex problems, including fraud cases, continue to occur in the current second-hand market.

[0003] To address this, second-hand trading platforms are implementing measures such as secure transaction systems. While this can resolve internet fraud issues to some extent, actual usage remains low due to high commission rates.

[0004] Consequently, second-hand trading platforms essentially remain at the level of providing an online space where consumers and sellers verify each other's information. Although transactions rely on mutual trust between trading partners, mutual trust is difficult to establish easily. As a result, in many cases, traders engage in limited transactions or use trading methods that incur high transaction costs.

[0005] In addition, when a seller registers an item for sale, they are required to attach multiple photos to prove that the item is legitimate or disclose a certain amount of their personal information, making second-hand goods transactions increasingly difficult. Despite these efforts, the number of victims of second-hand goods transaction fraud continues to rise.

[0006] In particular, the most common type of scam involves posting photos taken by others of used items that the seller does not possess and claiming to sell those items.

[0007] Therefore, technology is needed to enable safe non-face-to-face transactions without causing harm to the buyer, instead of offline face-to-face transactions. Prior art literature

[65535] Published Patent Application No. 10-2025-0144673 (Oct. 13, 2025) Registered Patent Application No. 10-2442796 (Sept. 15, 2022) Published Patent Application No. 10-2019-0075452 (July 1, 2019) The problem to be solved

[0008] The purpose of the present invention is to solve the problems of the aforementioned prior art.

[0009] The objective of the present invention is to ensure safety in the trading of used goods while enabling convenient non-face-to-face transactions.

[0010] The objectives of the present invention are not limited to those mentioned above, and other unmentioned objectives will be clearly understood from the description below. means of solving the problem

[0011] According to one embodiment of the present invention for achieving the above-mentioned purpose, a system for providing a safe non-face-to-face second-hand trading platform based on AI abnormal transaction detection and delivery driver matching is provided, comprising: a product information registration unit that receives information about a product subject to transaction from a seller terminal and transmits it to a plurality of buyer terminals; a purchase request receiving unit that receives a purchase request for the product subject to transaction from a buyer terminal, transmits a payment request for the product price to the buyer terminal, and receives and stores the amount paid by the buyer; a delivery driver matching unit that transmits a delivery request for the product subject to transaction to a plurality of delivery driver terminals and ensures that delivery is carried out by a specific delivery driver; and an abnormal transaction detection unit that detects whether there is an abnormal transaction during the transaction process for the product subject to transaction.

[0012] The above delivery driver matching unit can receive recognition information for a first identification code when picking up the transaction target item from the delivery driver terminal, and receive recognition information for a second identification code when the delivery of the transaction target item is completed.

[0013] The above abnormal transaction detection unit calculates a risk score based on rating information received from buyers regarding the seller's past number of product sales and the time elapsed from the time of payment completion by the buyer to the time of receiving recognition information for the first identification code, and can determine that it is an abnormal transaction if the risk score is greater than or equal to a threshold value. Effects of the invention

[0014] According to an embodiment of the present invention, safety in the trading of used goods is guaranteed, and at the same time, convenient non-face-to-face trading becomes possible. Brief explanation of the drawing

[0015] FIG. 1 is a diagram schematically illustrating the configuration of a safe non-face-to-face used goods trading platform provision system based on AI abnormal transaction detection and delivery driver matching according to one embodiment of the present invention. FIG. 2 is a diagram showing the detailed operation and internal configuration of a platform server according to one embodiment of the present invention. Specific details for implementing the invention

[0016] The following detailed description of the invention refers to the accompanying drawings, which illustrate specific embodiments in which the invention may be practiced. These embodiments are described in sufficient detail to enable those skilled in the art to practice the invention. It should be understood that various embodiments of the invention are different but need not be mutually exclusive. For example, specific shapes, structures, and characteristics described herein with respect to one embodiment may be implemented in other embodiments without departing from the spirit and scope of the invention. It should also be understood that the location or arrangement of individual components within each disclosed embodiment may be changed without departing from the spirit and scope of the invention. Accordingly, the following detailed description is not intended to be limiting, and the scope of the invention is limited only by the appended claims, including all equivalents to those claimed therein, provided appropriately described. Similar reference numerals in the drawings refer to the same or similar functions across various aspects.

[0017] Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the attached drawings in order to enable a person skilled in the art to easily practice the present invention.

[0018] FIG. 1 is a diagram schematically illustrating the configuration of a safe non-face-to-face used goods trading platform provision system based on AI abnormal transaction detection and delivery driver matching according to one embodiment of the present invention.

[0019] Referring to FIG. 1, a system according to an embodiment of the present invention may be configured to include a seller terminal (100), a buyer terminal (200), a delivery driver terminal (300), and a platform server (400).

[0020] The seller terminal (100), buyer terminal (200), delivery driver terminal (300), and platform server (400) can communicate with each other through a communication network, for example, a mobile communication network, a local area network (LAN), a metropolitan area network (MAN), a wide area network (WAN), the World Wide Web (WWW), and a wireless communication network (WiFi).

[0021] The seller terminal (100), buyer terminal (200), and delivery driver terminal (300) are equipped with computing functions and may be implemented in any form as long as they are devices capable of communicating with the outside. For example, they may be implemented as smartphones, tablet PCs, desktops, laptops, PDAs, etc., but are not limited thereto.

[0022] The seller terminal (100) and the buyer terminal (200) may substitute for each other's functions, or a single terminal may perform all the functions of the seller terminal (100) and the buyer terminal (200). In other words, the service provider may become the service recipient.

[0023] The delivery driver terminal (300) performs the function of querying used item delivery orders received from the platform server (400) and receiving detailed information about the delivery order selected by the delivery driver.

[0024] The platform server (400) receives product information, personal information, and account number information, etc., from the seller terminal (100), transmits information about the product to the buyer terminal (200), and when the buyer terminal (200) requests to purchase the product, deposits the corresponding payment amount, and when delivery by the delivery driver is completed, transfers the product amount to the seller's account.

[0025] FIG. 2 is a diagram showing the detailed operation and internal configuration of a platform server according to one embodiment of the present invention.

[0026] Referring to FIG. 2, a platform server (400) according to one embodiment may be configured to include an item information registration unit (410), a purchase request receiving unit (420), an article matching unit (430), an abnormal transaction detection unit (440), and a settlement unit (450).

[0027] The item information registration unit (410), purchase request receiving unit (420), article matching unit (430), abnormal transaction detection unit (440), and settlement unit (450) may be program modules or hardware capable of communicating with external devices. Such program modules or hardware may be included in the platform server (400) or other devices capable of communicating therewith in the form of an operating system, application program modules, and other program modules, and may be physically stored on various known storage devices. Meanwhile, such program modules or hardware include, but are not limited to, routines, subroutines, programs, objects, components, data structures, etc., that perform specific tasks or execute specific abstract data types as described below according to the present invention.

[0028] The item information register (410) receives information regarding items desired for trade (item name, item details, item image, desired price, etc.), location information (source address, etc.), and payment deposit account information from the seller terminal (100). In addition, personal information such as name and phone number may also be received. The received information is registered on a used goods trading platform and transmitted to multiple buyer terminals (200). That is, multiple buyers can access the platform and view information on items desired for trade registered by multiple sellers.

[0029] The purchase request receiving unit (420) receives a purchase request from the buyer terminal (200) for a specific used item registered by the seller. When a purchase request is made, delivery location information (such as the destination address), payment method information, etc., may be transmitted together. The purchase request receiving unit (420) transmits a request for payment of the transaction amount for the item to the buyer terminal (200), and the buyer performs the payment in accordance with the payment request. The amount paid is deposited into an account held by the operator of the platform server (400) and is temporarily stored. At this time, it is not deposited into the seller's account.

[0030] The driver matching unit (430) considers the origin address and destination address of the item to be traded and transmits a delivery request for the delivery of the item to a delivery driver terminal (300) located within a pre-set radius from the origin address, destination address, or any point on the route. At this time, the delivery request may be transmitted preferentially to the delivery driver terminal (300) with a good review score accumulated through deliveries so far.

[0031] Delivery drivers can select specific delivery requests, and through this, a delivery driver can be matched for the corresponding transaction items.

[0032] When a delivery driver goes to the originating address to pick up an item, the driver can recognize an identification code (e.g., QR code, etc.) displayed on the item or seller terminal (100) through the delivery driver terminal (300), and the recognition information is transmitted to the platform server (400). The platform server (400) can transmit information that the item has been picked up to the buyer terminal (200). Additionally, after delivery is completed, the delivery driver can recognize an identification code displayed on the buyer terminal (200) located at the destination address through their own terminal (300), and the recognition information is transmitted to the platform server (400). The platform server (400) confirms that the item has been delivered and can transmit delivery completion information to the seller terminal (100).

[0033] The above identification code can be generated by the article matching unit (430) when the delivery driver identification is completed and transmitted to the seller terminal (100) and the buyer terminal (200).

[0034] Meanwhile, the driver matching unit (430) can transmit real-time location information of the driver terminal (300) to the seller terminal (100) and the buyer terminal (200) after matching the driver, and if the driver deviates from the normal route, it can notify the seller terminal (100) or the buyer terminal (200), save the log, or block the driver so that delivery requests for subsequent deliveries are not transmitted to the driver terminal (300).

[0035] The abnormal transaction detection unit (440) performs the function of detecting whether the transaction of the goods is an abnormal transaction.

[0036] According to one embodiment, the abnormal transaction detection unit (440) can perform an analysis of the transaction pattern or history of the seller of the goods to automatically detect a transaction with a high probability of fraud and calculate a risk score per user and per transaction. If a transaction is determined to be dangerous, additional authentication may be requested or the transaction may be prohibited.

[0037] According to one embodiment, the abnormal transaction detection unit (440) calculates the following risk score (S).

[0038]

[0039] In the above mathematical formula, A is the number of past item sales by the seller on the platform, and B is the number of times the buyer rating given to the seller during past item transactions is less than a preset value. If the seller is making their first transaction, B / A is set to a default value (e.g., 1).

[0040] T1 is a value proportional to the time elapsed from the time when the buyer decides to purchase the item and performs payment or when the delivery driver matching is completed until the time when identification code recognition information from the origin address is received by the delivery driver terminal (300).

[0041] N is a value proportional to the similarity between the seller's name or phone number and the matched delivery driver's name or phone number. The similarity of names increases in proportion to the number of identical letters (surname, given name, etc.) or spellings (consonants, vowels, etc.) that make up the name. The similarity of phone numbers increases as the number of matching digits in the last four digits increases.

[0042] ΔP is a value proportional to the difference from the average asking price registered by other sellers for the same item in question. If other sellers are not selling the same item, the ΔP value may be proportional to the difference from the new product price for the same item in question. Additionally, if this information cannot be obtained, N is set to a default value.

[0043] F is a value proportional to the number of transactions by the seller during a pre-set period.

[0044] In other words, the above risk score (S) increases if there are many instances where buyers have given the seller a rating below a certain value during past transactions, if the delivery driver's movements are abnormal such as picking up late, if there is a relationship between the seller and the delivery driver, or if the selling price is abnormal.

[0045] The abnormal transaction detection unit (440) can detect the transaction as an abnormal transaction and notify the buyer terminal (100) if the risk score (S) is above a threshold value. After receiving the notification that the transaction is abnormal, the buyer may refuse to accept the goods. Additionally, if the goods cannot be delivered, there is no need to refuse acceptance. Furthermore, the payment amount held can be returned to the buyer's account.

[0046] The settlement unit (450) processes the remaining amount, excluding shipping costs and platform usage fees from the amount paid by the buyer during a normal transaction, into the seller's deposit account. All or part of the shipping costs may be processed into the delivery driver's account.

[0047] The foregoing description of the present invention is for illustrative purposes only, and those skilled in the art will understand that other specific forms can be easily modified without altering the technical spirit or essential features of the present invention. Therefore, the embodiments described above should be understood as illustrative in all respects and not restrictive. For example, each component described as a single unit may be implemented in a distributed manner, and components described as distributed may likewise be implemented in a combined form.

[0048] The scope of the present invention is defined by the claims set forth below, and all modifications or variations derived from the meaning and scope of the claims and equivalent concepts thereof should be interpreted as being included within the scope of the present invention. Explanation of the symbols

[0049] 100: Seller's terminal 200: Buyer's terminal 300: Delivery driver terminal 400: Platform Server 410: Item Information Register 420: Purchase Request Receiver 430: Article Matching Department 440: Anomaly Detection Unit 450: Settlement Department

Claims

Claim 1 A system for providing a safe non-face-to-face second-hand trading platform based on AI abnormal transaction detection and delivery driver matching, comprising: an item information registration unit that receives information about an item subject to transaction from a seller terminal and transmits it to multiple buyer terminals; a purchase request receiving unit that receives a purchase request for the item subject to transaction from a buyer terminal, transmits a payment request for the item price to the buyer terminal, and receives and stores the amount paid by the buyer; a delivery driver matching unit that transmits a delivery request for the item subject to transaction to multiple delivery driver terminals and ensures delivery by a specific delivery driver; and an abnormal transaction detection unit that detects whether there is an abnormal transaction during the transaction process for the item subject to transaction, wherein the abnormal transaction detection unit calculates the following risk score (S), and detects a transaction as an abnormal transaction if the calculated risk score (S) is greater than or equal to a threshold value. In the above mathematical formula, A is the number of past item sales by the seller within the platform, B is the number of times the buyer rating assigned to the seller during past item transactions is less than a preset value, and if the seller is making a first transaction, B / A is set to a default value, T1 is a value proportional to the time elapsed from the point when the buyer decides to purchase the item and performs payment or the point when the delivery driver matching is completed until the point when identification code recognition information from the origin address is received by the delivery driver terminal, N is a value proportional to the similarity between the seller's name or phone number and the name or phone number of the matched delivery driver, ΔP is a value proportional to the difference from the average desired transaction price registered by other sellers for the same item as the item being traded, and F is a value proportional to the number of transactions by the seller during a preset period, a non-face-to-face used goods trading platform providing system. Claim 2 A non-face-to-face second-hand trading platform providing system according to claim 1, wherein the delivery driver matching unit receives recognition information for a first identification code when picking up the item to be traded from the delivery driver terminal, and receives recognition information for a second identification code when the delivery of the item to be traded is completed. Claim 3 delete

Citation Information

Patent Citations

  • How to trade used goods using matching and trading zones

    KR1020190075452A

  • Method and system for providing pre-paying service for online saller

    KR1020250144673A

  • Online used market based verify transaction service using offline check

    KR102442796B1