Method and system for monitoring risk using transaction history in virtual exchange
The risk monitoring system addresses the lack of effective risk management in virtual exchanges by using transaction history and machine learning to identify risky accounts, freezing funds in cold wallets, and implementing user management strategies, thereby enhancing security and mitigating fraudulent transactions.
Patent Information
- Application Number
- KR1020200118530
- Authority / Receiving Office
- KR · KR
- Patent Type
- Patents
- Current Assignee / Owner
- Filing Date
- 2020-09-15
- Publication Date
- 2026-11-11
- Estimated Expiration
- 2040-09-15
AI Technical Summary
Existing virtual exchange systems lack effective risk monitoring methods to identify and mitigate potential risks to user accounts and electronic wallets, particularly through transaction analysis and identity verification.
A risk monitoring system and method that utilizes transaction history and machine learning to generate a black wallet list, perform identity verification, and transfer funds to a cold wallet for freezing based on risk assessment, incorporating internal and external transaction monitoring and reputation analysis.
Effectively identifies and mitigates risks by classifying users and transactions, freezing funds in cold wallets, and implementing user management strategies to enhance security and protect against fraudulent activities.
Smart Images

Figure 112020097915153-PAT00003_ABST
Abstract
Description
Technology Field
[0001] The following description concerns a risk monitoring method and system utilizing transaction history in a virtual exchange. Background Technology
[0002] With the advancement of technology and digitalization, the concept of new currencies, such as virtual currency, has emerged. Unlike physical currency (coins and banknotes) used for actual transactions, virtual currency literally refers to currency that exists only in a virtual environment and has no physical form. While credit cards and various mobile payment methods involve cash transactions where funds are deducted from a deposited account and transferred, virtual currency allows one to buy and sell goods using only the currency itself, without the need for cash.
[0003] Trading of such cryptocurrencies is conducted on virtual exchanges. Virtual exchanges operate on a system where users deposit a corresponding amount from their virtual accounts to purchase desired cryptocurrencies, and they enable the storage and trading of cryptocurrencies in electronic wallets.
[0004] [Prior Literature Number]
[0005] Korean Patent Publication No. 10-2019-0059813 The problem to be solved
[0006] A risk monitoring method and system are provided that determine the risk to a user and / or the user's electronic wallet based on internal and external transactions of a virtual exchange, and can freeze at least a portion of the funds associated with the user by transferring them to a cold wallet based on the determined risk. means of solving the problem
[0007] A risk monitoring method for a computer device comprising at least one processor, wherein the at least one processor generates a black wallet list; the at least one processor determines whether at least one of the plurality of electronic wallets is a black wallet through the black wallet list in response to a transaction request between the plurality of electronic wallets; and the at least one processor transfers the funds to a cold wallet to freeze the funds corresponding to the transaction request, at least based on the determination that the at least one electronic wallet is a black wallet.
[0008] According to one aspect, the step of transferring the funds to a cold wallet may be characterized by including: a step of verifying the identity of at least one user among the users of the plurality of electronic wallets based on a determination that at least one electronic wallet is a black wallet; and a step of transferring the funds to the cold wallet if the identity verification is not performed.
[0009] According to another aspect, the risk monitoring method may further include the step of transferring the funds to the electronic wallet of any one of the users of the plurality of electronic wallets by the at least one processor when the identity verification is performed.
[0010] According to another aspect, the step of generating the black wallet list may be characterized by including: a step of determining the reputation of any electronic wallets using information obtained through web crawling or an externally provided solution; and a step of adding at least some of the any electronic wallets to the black wallet list according to the reputation.
[0011] According to another aspect, the risk monitoring method may further include the step of registering at least one user among the users of the plurality of electronic wallets as a blocked user by the at least one processor based on the determination that the at least one electronic wallet is a black wallet.
[0012] According to another aspect, the plurality of electronic wallets may be characterized by including at least one internal user electronic wallet and at least one external user electronic wallet.
[0013] According to another aspect, the risk monitoring method may further include the step of collecting transaction history through at least one of the applications of financial institutions and users by the at least one processor; the step of classifying users associated with the collected transaction history into a plurality of groups according to transaction activity by the at least one processor; and the step of determining whether any user belongs to a risk group based on the groups to which any user belongs among the plurality of groups classified according to transaction activity by the at least one processor.
[0014] According to another aspect, the step of determining whether the arbitrary user belongs to a risk group may be characterized by determining whether the arbitrary user belongs to a risk group based on the sum of scores set for each of the groups to which the arbitrary user belongs among the plurality of groups classified by transaction activity.
[0015] According to another aspect, the above transaction acts may be characterized by including at least two acts among Buy, Sell, Send, Receive, Deposit, Withdrawal, External Send, and External Receive.
[0016] According to another aspect, the step of classifying into multiple groups may be characterized by inputting the collected transaction history into a machine learning module trained to classify users into multiple groups for each of the transaction activities using existing transaction history, thereby classifying users associated with the collected transaction history into multiple groups for each of the transaction activities.
[0017] According to another aspect, the machine learning module may be further trained to output scores for each classified group of users.
[0018] According to another aspect, the step of classifying into a plurality of groups may be characterized by including: a step of calculating an average value for each item of the transaction for each of the transaction activities; and a step of clustering the users according to the distance between the item-specific value of each transaction activity generated by the users and the average value of the corresponding item to classify the users into a plurality of groups for each transaction activity.
[0019] According to another aspect, the step of classifying into multiple groups may be characterized by classifying the users into multiple groups for each of the transaction activities based on the item-specific value of each transaction activity generated by the users and the standard deviation of the item-specific value.
[0020] According to another aspect, the risk monitoring method may further include the step of determining the grade of a user of the application by using at least one of user information transmitted from the application, transaction history, information about a user classified as a risk group, and information about an electronic wallet determined as a black wallet by the at least one processor.
[0021] According to another aspect, the risk monitoring method may determine whether to perform special user management, including at least one of restricting service usage and initiating user monitoring for the determined user, based on the determined user's grade.
[0022] A computer program stored on a computer-readable recording medium is provided to be combined with a computer device to execute the above method on the computer device.
[0023] A computer-readable recording medium is provided on which a program for executing the above method is recorded on a computer device.
[0024] A computer device is provided that includes at least one processor implemented to execute computer-readable commands, and by the at least one processor generates a black wallet list, determines whether at least one of the plurality of electronic wallets is a black wallet through the black wallet list in response to a transaction request between the plurality of electronic wallets, and transfers the funds to a cold wallet to freeze the funds corresponding to the transaction request, at least based on the determination that the at least one electronic wallet is a black wallet. Effects of the invention
[0025] The risk to the user and / or the user's electronic wallet is determined based on internal and external transactions of the virtual exchange, and based on the determined risk, at least a portion of the amount associated with the user can be transferred to a cold wallet and frozen. Brief explanation of the drawing
[0026] FIG. 1 is a drawing illustrating an example of a network environment according to an embodiment of the present invention. FIG. 2 is a block diagram illustrating an example of a computer device according to an embodiment of the present invention. FIG. 3 is a drawing illustrating an example of the internal configuration of a risk monitoring system according to an embodiment of the present invention. FIG. 4 is a diagram illustrating internal transaction monitoring according to an embodiment of the present invention. FIG. 5 is a diagram illustrating external transaction monitoring according to an embodiment of the present invention. FIG. 6 is a flowchart illustrating an example of a risk monitoring method according to an embodiment of the present invention. FIG. 7 is a flowchart illustrating an example of a method for detecting abnormal financial transactions according to an embodiment of the present invention. FIG. 8 is a diagram illustrating an example of classifying users using standard deviation in an embodiment of the present invention. FIGS. 9 and FIGS. 10 are drawings illustrating groups to which any users belong according to transaction activity in an embodiment of the present invention. Specific details for implementing the invention
[0027] Hereinafter, embodiments will be described in detail with reference to the attached drawings.
[0028] A risk monitoring system according to embodiments of the present invention may be implemented by at least one computer device. In this case, a computer program according to an embodiment of the present invention may be installed and run on the computer device, and the computer device may perform a risk monitoring method according to embodiments of the present invention under the control of the run computer program. The above-described computer program may be stored on a computer-readable recording medium to be combined with the computer device to execute the risk monitoring method on the computer.
[0029] FIG. 1 is a diagram illustrating an example of a network environment according to an embodiment of the present invention. The network environment of FIG. 1 illustrates an example including a plurality of electronic devices (110, 120, 130, 140), a plurality of servers (150, 160), and a network (170). FIG. 1 is an example for explaining the invention, and the number of electronic devices or servers is not limited to that shown in FIG. 1. Furthermore, the network environment of FIG. 1 is merely an example of one of the environments applicable to the present embodiments, and the environments applicable to the present embodiments are not limited to the network environment of FIG. 1.
[0030] Multiple electronic devices (110, 120, 130, 140) may be fixed terminals or mobile terminals implemented as computer devices. Examples of multiple electronic devices (110, 120, 130, 140) include smartphones, mobile phones, navigation systems, computers, laptops, digital broadcasting terminals, PDAs (Personal Digital Assistants), PMPs (Portable Multimedia Players), tablet PCs, etc. For example, FIG. 1 shows the shape of a smartphone as an example of an electronic device (110), but in embodiments of the present invention, the electronic device (110) may substantially refer to one of various physical computer devices capable of communicating with other electronic devices (120, 130, 140) and / or servers (150, 160) via a network (170) using a wireless or wired communication method.
[0031] The communication method is not limited and may include not only communication methods utilizing communication networks (e.g., mobile communication networks, wired internet, wireless internet, broadcasting networks) that the network (170) may include, but also short-range wireless communication between devices. For example, the network (170) may include any one or more networks such as a PAN (personal area network), LAN (local area network), CAN (campus area network), MAN (metropolitan area network), WAN (wide area network), BBN (broadband network), and the Internet. Additionally, the network (170) may include any one or more network topologies such as a bus network, a star network, a ring network, a mesh network, a star-bus network, a tree or hierarchical network, but is not limited thereto.
[0032] Each of the servers (150, 160) may be implemented as a computer device or multiple computer devices that communicate with multiple electronic devices (110, 120, 130, 140) through a network (170) to provide commands, code, files, content, services, etc. For example, the server (150) may be a system that provides services (e.g., virtual exchange service, risk monitoring service, instant messaging service, game service, group call service (or voice conference service), messaging service, mail service, social network service, map service, translation service, financial service, payment service, search service, content provision service, etc.) to multiple electronic devices (110, 120, 130, 140) connected through the network (170).
[0033] FIG. 2 is a block diagram illustrating an example of a computer device according to an embodiment of the present invention. Each of the plurality of electronic devices (110, 120, 130, 140) or servers (150, 160) described above can be implemented by the computer device (200) illustrated in FIG. 2.
[0034] As illustrated in FIG. 2, such a computer device (200) may include memory (210), a processor (220), a communication interface (230), and an input / output interface (240). The memory (210) is a computer-readable recording medium and may include a non-perishable mass storage device such as RAM (random access memory), ROM (read only memory), and a disk drive. Here, a non-perishable mass storage device such as a ROM and a disk drive may be included in the computer device (200) as a separate permanent storage device distinct from the memory (210). Additionally, an operating system and at least one program code may be stored in the memory (210). These software components may be loaded into the memory (210) from a computer-readable recording medium separate from the memory (210). This separate computer-readable recording medium may include a computer-readable recording medium such as a floppy drive, a disk, a tape, a DVD / CD-ROM drive, or a memory card. In another embodiment, software components may be loaded into memory (210) via a communication interface (230) rather than a computer-readable recording medium. For example, software components may be loaded into memory (210) of a computer device (200) based on a computer program installed by files received through a network (170).
[0035] The processor (220) may be configured to process instructions of a computer program by performing basic arithmetic, logic, and input / output operations. Instructions may be provided to the processor (220) via memory (210) or a communication interface (230). For example, the processor (220) may be configured to execute instructions received according to program code stored in a recording device such as memory (210).
[0036] The communication interface (230) may provide a function for the computer device (200) to communicate with other devices (e.g., storage devices described above) through the network (170). For example, requests, commands, data, files, etc. generated by the processor (220) of the computer device (200) according to program code stored in a recording device such as memory (210) may be transmitted to other devices through the network (170) under the control of the communication interface (230). Conversely, signals, commands, data, files, etc. from other devices may be received by the computer device (200) through the communication interface (230) of the computer device (200) via the network (170). Signals, commands, data, etc. received through the communication interface (230) may be transmitted to the processor (220) or memory (210), and files, etc. may be stored in a storage medium (the permanent storage device described above) that the computer device (200) may further include.
[0037] The input / output interface (240) may be a means for interfacing with an input / output device (250). For example, the input device may include a device such as a microphone, keyboard, or mouse, and the output device may include a device such as a display or speaker. As another example, the input / output interface (240) may be a means for interfacing with a device in which the functions for input and output are integrated into one, such as a touchscreen. At least one of the input / output devices (250) may be configured as a single device with the computer device (200). For example, it may be implemented in a form in which a touchscreen, microphone, speaker, etc., are included in the computer device (200), such as in a smartphone.
[0038] Additionally, in other embodiments, the computer device (200) may include fewer or more components than the components of FIG. 2. However, it is not necessary to clearly illustrate most of the prior art components. For example, the computer device (200) may be implemented to include at least some of the input / output devices (250) described above, or may include other components such as a transceiver, a database, etc.
[0039] FIG. 3 is a diagram illustrating an example of the internal configuration of a risk monitoring system according to an embodiment of the present invention. The risk monitoring system (300) according to the present embodiment may be implemented by at least one physical device, wherein the physical device may correspond to, for example, the computer device (200) described through FIG. 2. As illustrated in FIG. 3, such a risk monitoring system (300) may include an internal transaction monitoring module (310), a risk management database (320), an external transaction monitoring module (330), a user wallet (340), and a cold wallet (350). Here, the internal transaction monitoring module (310) and the external transaction monitoring module (330) may substantially be functional representations of operations performed by the processor (220) of the computer device (200) implementing the risk monitoring system (300). For example, "internal transaction monitoring module (310)" may be used as a functional representation of the operation(s) for the processor (220) to monitor internal transactions.
[0040] The internal transaction module (310) can detect abnormal financial transactions by monitoring internal transactions for the virtual exchange and classify users based on this. For example, the internal transaction module (310) can receive transaction history and user information from an application (360) that users install and run on their terminals to use the virtual exchange, and can detect abnormal financial transactions and classify users based on this. Here, the internal transaction module (310) can classify users into three grades: normal users, suspicious users, and fraud users. According to the embodiment, users may be classified into two grades, such as normal users and risk users, or into four or more grades. These user grades can be used to determine whether to implement special user management, such as restricting service usage or initiating user monitoring.
[0041] The external transaction module (330) can monitor external transactions, including transactions between the user wallet (340) and the external wallet (380). Here, the user wallet (340), the external wallet (380), and the cold wallet (350), which will be described later, can be understood through the electronic wallet technology for virtual currency that is already well known. The external transaction module (330) can determine the reputation of the wallets (user wallet (340) and / or external wallet (380)) using information obtained through web crawling (e.g., dark web crawling). According to an embodiment, the external transaction module (330) may also utilize a solution provided to collect and provide information for the reputation of the wallets.
[0042] Transactions between a user wallet (340) and an external wallet (380) can be carried out through the blockchain network (370) shown in FIG. 3, and an external transaction module (330) can monitor such transactions between the user wallet (340) and the external wallet (380). At this time, the external transaction module (330) can transfer funds related to the transaction between the user wallet (340) and the external wallet (380) to the user wallet (340) to complete the transaction based on the reputation of the determined wallet, or transfer the funds to a cold wallet (350) to freeze the funds related to the transaction between the user wallet (340) and the external wallet (380).
[0043] A cold wallet (350) may be an electronic wallet used in an environment where there is no internet connection, and funds frozen in the cold wallet (350) may be permanently stored on the cold wallet (350). For example, the cold wallet (350) may be implemented in the form of a burn wallet that burns incoming coins. However, the cold wallet (350) may be implemented so that stored funds can be withdrawn again according to service operation rules. Information regarding related transactions (user information, wallet information, etc.) may be stored together with the funds stored in the cold wallet (350). This information may be used to provide information about the transaction to investigative authorities when a request for investigation regarding the funds is received.
[0044] In the embodiment of FIG. 3 above, an example is described in which funds are frozen based on the wallet's reputation for external transactions; however, funds may also be frozen based on the wallet's reputation for all internal and external transactions without distinction between internal and external transactions. Furthermore, the decision to freeze funds may be based not only on the wallet's reputation but also on the user's rating described above.
[0045] FIG. 4 is a diagram illustrating internal transaction monitoring according to an embodiment of the present invention. The internal transaction monitoring module (310) according to the present embodiment may include an abnormal financial transaction detection module (410) that determines whether any user is included in a risk group.
[0046] Information regarding suspected users (users included in the risk group) determined by the abnormal financial transaction detection module (410) can be stored in the risk management database (320). The abnormal financial transaction detection module (410) will be described in more detail later.
[0047] The internal transaction monitoring module (310) can analyze the transactions of users in step (421). For example, the internal transaction monitoring module (310) can receive transaction history through the transaction history DB (361) included in the application (360) and user information through the user information DB (362). Additionally, the internal transaction monitoring module (310) can receive further information about a suspicious user determined by the abnormal financial transaction detection module (410) from the risk management database (320). For example, the internal transaction monitoring module (310) can search the risk management database (320) through the user information received from the application (360) to determine whether the user is a suspicious user.
[0048] The internal transaction monitoring module (310) can determine whether the user is a normal user in step (422). For example, the internal transaction monitoring module (310) can determine whether the user is a normal user by utilizing whether the user is a suspicious user, transaction history, and / or user information. In other words, it can determine whether the user is a suspicious user or a fraud user, etc.
[0049] The internal transaction monitoring module (310) may decide to initiate monitoring of the user's transactions in step (423) if the user is determined to be a general user, and may decide to restrict the user's use of the service in step (424) if the user is determined to be a suspicious user or a fraudulent user rather than a general user. The results of the decisions in steps (423) and (424) may be stored in the risk management database (320).
[0050] In this way, the internal transaction monitoring module (310) can detect abnormal financial transactions by monitoring internal transactions for the virtual exchange, and based on this, can classify users by grade and impose sanctions according to these grades.
[0051] FIG. 5 is a diagram illustrating external transaction monitoring according to an embodiment of the present invention. The external transaction monitoring module (330) according to the present embodiment may include a user hot wallet (510), a user warm wallet (520), a black wallet check module (530), a black wallet list (540), and a blocked user list (550), as shown in FIG. 5.
[0052] Monitoring of external transactions between a user wallet (340) and an external wallet (380) can be handled. For example, a transfer from a user wallet (340) to an external wallet (380) can be made by transferring funds from the user wallet (340) to the external wallet (380) via a user hot wallet (510), which is a virtual currency storage module connected online, and a blockchain network (370). Conversely, a transfer from an external wallet (380) to a user wallet (340) can be made by transferring funds from the external wallet (380) to the user wallet (340) via a blockchain network (370) and a user warm wallet (520), which is a virtual currency storage module.
[0053] At this time, the connection between the user wallet (340) and the user hot wallet (510), and the connection between the user wallet (340) and the user warm wallet (520), can be established through the black wallet check module (530). Virtual currency wallets (or cryptocurrency wallets) are commonly referred to as hot wallets or cold wallets. This distinction is intended to highlight fundamental differences regarding how private keys are stored, how easily cryptocurrency can be moved in and out of the wallet, and how these wallets are exposed to external users, such as malicious hackers. A hot wallet is a wallet that is always connected to the internet, and the advantages of a hot wallet are speed and flexibility. However, because a hot wallet is connected to a public network, security flaws in the network can mean serious vulnerability to the user wallet. Meanwhile, a warm wallet is very similar to a hot wallet but differs in two main ways. First, warm wallets tend to be based on downloadable software or applications rather than web-based services. Second, while hot wallets rely on passwords created by users and require users to verify personal information, cold wallets use a 12-digit password or PIN number for security and identity verification. Cold wallets are cryptocurrency wallets that are not connected to a network and can be effectively blocked from potential hackers.
[0054] The black wallet check module (530) can determine whether the user wallet (340) and / or external wallet (380) is a black wallet using the black wallet list (540). If the user wallet (340) and / or external wallet (380) is determined to be a black wallet, the black wallet check module (530) can add the user to the blocked user list (550). In this case, funds transferred from the user wallet (340) to the user hot wallet (510) following a transfer from the user wallet (340) to the external wallet (380) may be blocked by the black wallet check module (530), and funds transferred from the user warm wallet (520) to the user wallet (340) following a transfer from the external wallet (380) to the user wallet (340) may also be blocked by the black wallet check module (530).
[0055] The black wallet list (540) can be created by adding wallets (user wallets (340) and / or external wallets (380)) to the black wallet list (540) according to the reputation determined for the wallets using information obtained through web crawling (e.g., dark web crawling) as previously described. As previously described, the reputation may also be obtained by utilizing a separate solution provided to collect and provide information for the reputation of the wallets.
[0056] If the transfer of funds is blocked, the external transaction monitoring module (330) may undergo a user identity verification process (560). At this time, if identity verification is performed, the funds that were blocked from transfer may be transferred to the user wallet (340), and if identity verification is not performed, the funds that were blocked from transfer may be transferred to a cold wallet (350) and the transaction may be frozen. Identity verification may be performed using secondary KYC (Known Your Customer). This secondary KYC is a technology used as a means to prevent evasion of responsibility by claiming that someone else made the transaction in the event of a problem, as it proves that the person who conducted the transaction at the time of the transaction is the actual person by verifying the identity once more at the time of the transaction.
[0057] The blocked user list (550) is transferred to the risk management database (320) and can be used for internal transaction monitoring as described in FIG. 4.
[0058] FIG. 6 is a flowchart illustrating an example of a risk monitoring method according to an embodiment of the present invention. The risk monitoring method according to the present embodiment can be performed by a computer device (200) that implements the risk monitoring system (300) described through FIG. 3. At this time, the processor (220) of the computer device (200) may be implemented to execute a control instruction according to the code of an operating system or the code of at least one computer program included in the memory (210). Here, the processor (220) may control the computer device (200) so that the computer device (200) performs steps (610 to 680) included in the method of FIG. 6 according to the control instruction provided by the code stored in the computer device (200).
[0059] In step (610), the computer device (200) can generate a black wallet list. For example, the computer device (200) can determine the reputation of any electronic wallets using information obtained through web crawling or an externally provided solution, and can add at least some of the any electronic wallets to the black wallet list based on the reputation.
[0060] In step (620), the computer device (200) may receive a request for a transaction between multiple electronic wallets. The request may be a request generated by at least one of the multiple electronic wallets.
[0061] In step (630), the computer device (200) can determine whether a wallet is black. For example, the computer device (200) can determine whether at least one of the multiple wallets is a black wallet through a black wallet list in response to a transaction request between multiple wallets. As a more specific example, the computer device (200) can determine that a specific wallet is a black wallet if that specific wallet among the multiple wallets is included in the black wallet list. The computer device (200) may determine whether each of the multiple wallets is a black wallet, or it may determine whether any one of the multiple wallets is a black wallet. The multiple wallets may be the wallets of internal users of the virtual exchange, or they may include at least one internal user's wallet and at least one external user's wallet of the virtual exchange. Previously, through FIGS. 3 and 5, a transaction between an internal user's wallet (user wallet (340)) and an external user's wallet (external wallet (380)) was described.
[0062] In step (640), the computer device (200) can process the requested transaction if none of the multiple electronic wallets is a black wallet. Afterward, the risk monitoring method according to the embodiment of FIG. 6 can be terminated as the processing of the transaction is successfully completed.
[0063] In step (650), the computer device (200) may register at least one user among the users of multiple electronic wallets as a blocked user based on the determination that at least one electronic wallet is a black wallet. Information regarding the blocking of users may subsequently be used to determine the user grades based on internal transactions. An example has been previously described in which the grades of these users are classified into three grades: normal users, suspicious users, and fraudulent users.
[0064] In step (660), the computer device (200) may perform identity verification. For example, the computer device (200) may perform identity verification for at least one user among the users of multiple electronic wallets based on the determination that at least one electronic wallet is a black wallet. For example, the computer device (200) may perform identity verification using secondary KYC. At this time, if identity verification is performed, step (670) may be performed, and if identity verification is not performed, step (680) may be performed.
[0065] In step (670), the computer device (200) can transfer funds to the electronic wallet of any one of the users of multiple electronic wallets. For example, FIG. 5 describes an example of transferring funds to the user wallet (340) for a transaction between the user wallet (340) and the external wallet (380). According to the embodiment, funds may be transferred to the electronic wallet of a user whose identity has been verified.
[0066] In step (680), the computer device (200) can transfer funds to a cold wallet. The funds transferred to the cold wallet may be frozen, and as previously described, information regarding the users or electronic wallets associated with the transaction may be stored for the frozen funds.
[0067] Accordingly, according to embodiments of the present invention, a risk to a user and / or a user's electronic wallet is determined based on internal and external transactions of a virtual exchange, and at least a portion of the amount associated with the user can be transferred to a cold wallet and frozen according to the determined risk.
[0068] FIG. 7 is a flowchart illustrating an example of a method for detecting abnormal financial transactions according to an embodiment of the present invention. The steps (710 to 730) according to the embodiment of FIG. 7 can be performed in parallel with the steps (610 to 680) of FIG. 6 and can also be performed by a computer device (200) implementing a risk monitoring system (300). More specifically, the steps (710 to 730) of FIG. 7 can correspond to the operations of the abnormal financial transaction detection module (410) described through FIG. 4.
[0069] In step (710), the computer device (200) may collect transaction history through at least one of the applications of financial institutions and users. Transaction history may be received by the computer device (200) from the system of at least one financial institution or from the application of at least one user through the network (170) and the communication interface (230), but it may also be considered that previously collected transaction history is input into the computer device (200) through the input / output interface (240). In this embodiment, the financial institution may include a virtual exchange, and the application may correspond to the application (360) described through FIGS. 3 and 4.
[0070] In step (720), the computer device (200) can classify users associated with the collected transaction history into multiple groups according to transaction activities. At this time, transaction activities may include at least two of the following: Buy, Sell, Send, Receive, Deposit, Withdrawal, External Send, and External Receive. Here, "External" may mean outside the country in general financial transactions, but in the environment of this embodiment utilizing virtual currency, it may mean outside the system (transaction environment through a virtual exchange) where virtual currency associated with the computer device (200) is traded.
[0071] For example, it is assumed that transaction activities include "transfer" and "receive transfer." In this case, the computer device (200) can classify users who have performed the "transfer" activity in the transaction history collected in relation to the transaction activity "transfer" into multiple groups (e.g., three groups of Group A, Group B, and Group C), and users who have performed the "receive transfer" activity in the transaction history collected in relation to the transaction activity "receive transfer" into multiple groups (e.g., four groups of Group D, Group E, Group F, and Group G). At this time, the number of groups generated for each transaction activity may be the same for each transaction activity, or may differ from one another as in the example above. In this case, a user who has performed the transaction activity "transfer" will be included in one of Group A, Group B, and Group C, and a user who has performed the transaction activity "receive transfer" will be included in one of Group D, Group E, Group F, and Group G. Additionally, a user who has generated both the transaction acts of "transferring" and "receiving transfer" may be included in one of Group A, Group B, and Group C, and one of Group D, Group E, Group F, and Group G, respectively.
[0072] As an example of classifying users, a machine learning module trained to classify users associated with transaction history into multiple groups for each transaction activity using existing transaction history may be utilized. In this case, the computer device (200) may input the transaction history collected in step (710) into the trained machine learning module to classify users associated with the collected transaction history into multiple groups for each transaction activity. According to the embodiment, the machine learning module may be further trained to output a score for each group of users classified. This score may be used as an example to determine whether any user is included in a risk group in a subsequent step (730).
[0073] In another embodiment for classifying users, the computer device (200) may calculate an average value for each transaction activity for each transaction activity and cluster the users according to the distance between the value for each transaction activity generated by the users and the average value of the corresponding item, thereby classifying the users into multiple groups for each transaction activity. Here, the transaction activity items may include items such as "number of transactions" or "transaction amount," for example. For example, it may be assumed that the item for the transaction activity "remittance" is set to "number of transactions." At this time, it may be assumed that the users who generated the transaction activity "remittance" are {a, b, c, d, e, f, g, h, i, j}, and that the "number of transactions" of the users are {1, 3, 2, 120, 2, 3, 5, 2, 1, 1}. In this case, the average value of the item "number of transactions" for the transaction activity "remittance" can be 14 (= (1+3+2+120+2+3+5+2+1+1) / 10). At this time, the computer device (200) can set the criteria for the group based on the average value. For example, the computer device (200) can set users whose "number of transactions" falls within the range of 10 to 18 as Group 1, users whose "number of transactions" falls within 9 or less as Group 2, and users whose "number of transactions" falls within 19 or more as Group 3. In this case, users {a, b, c, e, f, g, h, i, j} can be classified into Group 2, and user {d} can be classified into Group 3. This example is a simplified example to aid in understanding the invention, and there may be multiple items for a single transaction activity, in which case the groups of users can be classified by aggregating the distances calculated for each item. For example, the distance values calculated for each item can all be converted to values between 0 and 1, and then summed or weighted summed to be used for classifying users. In addition, the number of groups or the criteria for dividing groups can also be set in various ways.For example, the computer device (200) can use the standard deviation of the item-specific values of each transaction activity generated by users as a criterion for classifying groups. In other words, the computer device (200) can classify users into multiple groups for each transaction activity based on the item-specific values of each transaction activity generated by users and the standard deviation of the item-specific values.
[0074] FIG. 8 is a diagram illustrating an example of classifying users using standard deviation in an embodiment of the present invention. The graph (800) of FIG. 8 is a random variable X ε represents the probability density function when following a normal distribution with mean μ and standard deviation σ. It is assumed that this probability density function represents the population of specific item values for any transaction. In this case, the group of a specific user can be determined based on which interval the value of that specific item falls into. For example, if the value of a specific item for user a is less than [μ - 3σ], user a can be classified into Group 1. The further a specific user's value of a specific item is from the mean μ, the higher the probability that the user will be classified into the risk group.
[0075] Meanwhile, the computer device (200) can calculate a score for each of the multiple groups by utilizing a distance formula that takes into account the distance and directionality calculated for each item. In this case, for example, a formula based on Mahalanobis' distance may be used as the distance formula. As previously explained, the score may be used as an example to determine whether any user is included in a risk group in a subsequent step (330).
[0076] Referring again to FIG. 7, in step (730), the computer device (200) can determine whether any user belongs to a risk group based on the groups to which any user belongs among a plurality of groups classified by transaction activity. For example, the computer device (200) can determine whether any user belongs to a risk group based on the sum of scores set for each of the groups to which any user belongs among a plurality of groups classified by transaction activity.
[0077] FIGS. 9 and FIGS. 10 are drawings illustrating groups to which any users belong according to transaction activity in an embodiment of the present invention.
[0078] Table (900) of FIG. 9 indicates which group user a is classified into based on transaction activities. In other words, Table (900) indicates that user a is classified into Group A for transaction activities "purchase," "remittance," "withdrawal," and "external remittance," into Group B for transaction activities "sale" and "deposit," and into Group E for transaction activities "receiving remittance" and "receiving external remittance." At this time, it can be assumed that for each group, the higher the score, the higher the probability that users belonging to that group are included in the risk group. In this case, the sum of the scores of each group to which user a is classified can be calculated as 60 (10+8+10+2+8+10+10+2).
[0079] Table (1000) in FIG. 10 indicates which group user b is classified into based on transaction activities. In other words, Table (1000) shows an example where user b is classified into Group E for all transaction activities "purchase," "sale," "remittance," "receive remittance," "deposit," "withdrawal," "external remittance," and "receive external remittance." In this case, the sum of the scores for each group to which user b is classified can be calculated as 16 (2+2+2+2+2+2+2+2).
[0080] In this case, whether a specific user is included in the risk group can be determined by the sum of these scores. In this embodiment, it will be easy to understand that the higher the sum of the scores, the higher the probability that the user is included in the risk group. For example, the computer device (200) can classify users whose sum of scores is greater than or equal to a preset threshold (50 in this embodiment) as a risk group. In this case, user a, whose sum of scores is calculated to be 60, can be classified as a risk group.
[0081] The sum of these scores can be calculated for each user of the collected transaction history, and based on the calculated scores, users classified as a risk group can be determined.
[0082] As previously explained through FIG. 4, information regarding users classified as risk groups (suspected users) can be stored in a risk management database (320) and can be used to classify the grades of users later.
[0083] Additionally, the computer device (200) can determine the grade of a user of an application by using at least one of user information transmitted from the application, transaction history, information about a user classified as a risk group, and information about an electronic wallet determined as a black wallet. As previously explained through FIG. 4, the internal transaction monitoring module (310) can classify the grade of a user by utilizing transaction history from the transaction history DB (361) of the application (360) and information from the risk management database (320). At this time, the risk management database (320) may include information about a suspicious user (information about a user classified as a risk group) obtained by the abnormal financial transaction detection module (410) as previously explained, and information about an electronic wallet determined as a black wallet (information about a blocked user) as explained through FIG. 5.
[0084] As such, according to embodiments of the present invention, users can be managed by grade by monitoring internal and external transactions, and funds of transactions can be frozen if necessary.
[0085] The system or device described above may be implemented as a hardware component, or a combination of a hardware component and a software component. For example, the device and component described in the embodiments may be implemented using one or more general-purpose or special-purpose computers, such as, for example, a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable gate array (FPGA), a programmable logic unit (PLU), a microprocessor, or any other device capable of executing and responding to instructions. The processing unit may execute an operating system (OS) and one or more software applications executed on said operating system. Additionally, the processing unit may access, store, manipulate, process, and generate data in response to the execution of the software. For ease of understanding, the processing unit may be described as being used as a single unit, but those skilled in the art will understand that the processing unit may include multiple processing elements and / or multiple types of processing elements. For example, the processing unit may include multiple processors or one processor and one controller. In addition, other processing configurations, such as parallel processors, are also possible.
[0086] Software may include computer programs, code, instructions, or a combination of one or more of these, and may configure a processing unit to operate as desired or instruct the processing unit independently or collectively. Software and / or data may be embodied in any type of machine, component, physical device, virtual equipment, computer storage medium, or device so as to be interpreted by the processing unit or to provide instructions or data to the processing unit. Software may be distributed over networked computer systems and may be stored or executed in a distributed manner. Software and data may be stored on one or more computer-readable recording media.
[0087] The method according to the embodiment may be implemented in the form of program instructions that can be executed through various computer means and recorded on a computer-readable medium. The computer-readable medium may include program instructions, data files, data structures, etc., either individually or in combination. The medium may continuously store a program executable by a computer, or temporarily store it for execution or download. Furthermore, the medium may be various recording or storage means in the form of a single or multiple hardware components, and is not limited to a medium directly connected to a computer system, but may also exist distributed over a network. Examples of media may include magnetic media such as hard disks, floppy disks, and magnetic tapes; optical recording media such as CD-ROMs and DVDs; magneto-optical media such as floptical disks; and media configured to store program instructions, including ROM, RAM, and flash memory. Additionally, other examples of media may include recording or storage media managed by app stores that distribute applications or sites and servers that supply or distribute various other software. Examples of program instructions include machine code, such as that generated by a compiler, as well as high-level language code that can be executed by a computer using an interpreter, etc.
[0088] Although the embodiments have been described above with reference to limited examples and drawings, those skilled in the art can make various modifications and variations from the description above. For example, suitable results can be achieved even if the described techniques are performed in a different order than described, and / or the components of the described system, structure, device, circuit, etc. are combined or assembled in a form different from described, or replaced or substituted by other components or equivalents.
[0089] Therefore, other implementations, other embodiments, and equivalents to the claims also fall within the scope of the claims set forth below.
Claims
Claim 1 A risk monitoring method for a virtual exchange of a computer device comprising at least one processor, comprising: a step of generating a black wallet list by the at least one processor; a step of determining whether at least one electronic wallet among the plurality of electronic wallets is a black wallet through the black wallet list in response to a transaction request between the plurality of electronic wallets by the at least one processor; and a step of transferring funds to a cold wallet to freeze funds corresponding to the transaction request by the at least one processor, at least based on the determination that the at least one electronic wallet is a black wallet, wherein the plurality of electronic wallets include at least one electronic wallet of an internal user of the virtual exchange and at least one electronic wallet of an external user of the virtual exchange, and the risk monitoring method comprises steps for determining whether any user among the users of the plurality of electronic wallets is in a risk group, wherein the at least one processor collects the transaction history of the users in the virtual exchange; and the at least one processor classifies the respective transaction behavior of each user indicated by the collected transaction history into one of a plurality of groups.Risk monitoring comprising a step of determining whether an arbitrary user is in a risk group based on the result of classifying each transaction activity of each user into one of the plurality of groups by the at least one processor, wherein the classifying step calculates an average value for each item of the plurality of transaction activities of the users, and classifies each user's transaction activity into one of the plurality of groups by clustering each user based on a comparison between the value of each transaction activity of each user and the average value of the transaction activity for the corresponding item or between the value of each transaction activity of each user and the standard deviation of the value for the item, and classifies each transaction activity of two or more transaction activities among the plurality of transaction activities of each user into one of the plurality of groups, wherein a first transaction activity among the two or more transaction activities is classified into the first group among the plurality of groups, and a second transaction activity among the two or more transaction activities is classified into the second group among the plurality of groups, and wherein the step of determining whether an arbitrary user is in a risk group is characterized by determining whether the arbitrary user is in a risk group by determining whether the arbitrary user is in a risk group based at least on the sum of a first score assigned to the first group and a second score assigned to the second group. method.; Claim 2 A risk monitoring method according to claim 1, wherein the step of transferring the funds to a cold wallet comprises: a step of performing identity verification for at least one user among the users of the plurality of electronic wallets based on a determination that at least one electronic wallet is a black wallet; and a step of transferring the funds to the cold wallet if the identity verification is not performed. Claim 3 A risk monitoring method according to paragraph 2, further comprising the step of transferring the funds to the electronic wallet of any one of the users of the plurality of electronic wallets by the at least one processor when the identity verification is performed. Claim 4 A risk monitoring method according to claim 1, wherein the step of generating the black wallet list comprises: determining the reputation of any electronic wallets using information obtained through web crawling or an externally provided solution; and adding at least some of the any electronic wallets to the black wallet list according to the reputation. Claim 5 A risk monitoring method according to claim 1, further comprising the step of registering at least one user among the users of the plurality of electronic wallets as a blocked user based on a determination by the at least one processor that the at least one electronic wallet is a black wallet. Claim 6 delete Claim 7 delete Claim 8 delete Claim 9 A risk monitoring method according to claim 1, characterized in that the transaction acts include at least two acts among Buy, Sell, Send, Receive, Deposit, Withdrawal, External Send, and External Receive. Claim 10 delete Claim 11 delete Claim 12 delete Claim 13 delete Claim 14 A risk monitoring method according to claim 1, further comprising the step of determining the user grade of an application by using at least one of the transaction history, information about a user classified as a risk group, and information about an electronic wallet determined as a black wallet by the at least one processor. Claim 15 A risk monitoring method according to claim 14, further comprising the step of determining whether to perform special user management, including at least one of restricting service usage and initiating user monitoring for the determined user based on the determined user grade by the at least one processor. Claim 16 A computer program stored on a computer-readable recording medium to be combined with a computer device to execute the method of any one of claims 1 through 5, 9, 14 and 15 on the computer device. Claim 17 A computer device for performing risk monitoring for a virtual exchange comprises at least one processor implemented to execute computer-readable commands, wherein the at least one processor generates a black wallet list, determines whether at least one of the plurality of electronic wallets is a black wallet through the black wallet list in response to a transaction request between the plurality of electronic wallets, and transfers the funds to a cold wallet to freeze the funds corresponding to the transaction request based at least on the determination that the at least one electronic wallet is a black wallet, wherein the plurality of electronic wallets include at least one electronic wallet of an internal user of the virtual exchange and at least one electronic wallet of an external user of the virtual exchange, and wherein the at least one processor performs steps for determining whether any user among the users of the plurality of electronic wallets is in a risk group, wherein the at least one processor collects the transaction history of the users in the virtual exchange; and wherein the at least one processor classifies the respective transaction behavior of each user indicated by the collected transaction history into one of a plurality of groups.A computer characterized by the following steps: determining whether an arbitrary user is in a risk group based on the result of classifying each transaction activity of each user into one of the plurality of groups by the at least one processor; wherein the classifying step calculates an average value for each item of the plurality of transaction activities of the users, and clusters each user based on a comparison between the value of each transaction activity of each user and the average value of the transaction activity for the corresponding item, or between the value of each transaction activity of each user and the standard deviation of the value for the item, thereby classifying each user's transaction activity into one of the plurality of groups; and classifying each transaction activity of two or more transaction activities among the plurality of transaction activities of each user into one of the plurality of groups, wherein a first transaction activity among the two or more transaction activities is classified into the first group among the plurality of groups, and a second transaction activity among the two or more transaction activities is classified into the second group among the plurality of groups; and wherein the step of determining whether an arbitrary user is in a risk group is determined by determining whether each user is in a risk group based at least on the sum of a first score assigned to the first group and a second score assigned to the second group. Device.; Claim 18 A computer device according to claim 17, characterized in that, by the at least one processor, identity verification is performed for at least one user among the users of the plurality of electronic wallets based on a determination that the at least one electronic wallet is a black wallet, and if the identity verification is not performed, the funds are transferred to the cold wallet. Claim 19 A computer device according to claim 18, characterized in that when identity verification is performed by at least one processor, the funds are transferred to the electronic wallet of any one of the users of the plurality of electronic wallets. Claim 20 A computer device according to claim 17, characterized in that, by the at least one processor, at least one user among the users of the plurality of electronic wallets is registered as a blocked user in accordance with the determination that the at least one electronic wallet is a black wallet.
Citation Information
Patent Citations
Multiple server systems with different functions to block hacking of the cryptographic exchange and electric wallet management system using closed coin
KR101922567B1
Method, Apparatus and Computer-readable medium for Detecting Abnormal Web Service Use Based on Probability Distribution
KR1020190068856A
Monitoring system comprising function of transaction tracking for block-chain system, and method of monitoring for the same
KR1020200004528A
Method for providing blockchian based loan service using credit scoring to group inclduing individual
KR102024377B1
Method, apparatus and computer program for clustering cryptocurrency accounts using artificial intelligence
KR102112798B1
