KR20210106602A - Method, apparatus and computer program for forecasting cryptocurrency cost variability using artificial intelligence - Google Patents

Abstract

Provided are a method, device, and computer program for predicting a cryptocurrency price fluctuation using artificial intelligence. The method for predicting the cryptocurrency price fluctuation using the artificial intelligence according to various embodiments of the present invention may comprise: a step of determining a use for each of the plurality of cryptocurrency accounts by using the cryptocurrency transaction information generated between the plurality of cryptocurrency accounts; a step of collecting information related to the cryptocurrency for each of the plurality of cryptocurrency accounts whose use has been determined; and a step of predicting price fluctuation of the cryptocurrency by analyzing the collected information related to the cryptocurrency.

Description

Method, Apparatus and Computer Program for Predicting Cryptocurrency Price Volatility Using Artificial Intelligence

Various embodiments of the present invention relate to a method, apparatus, and computer program for predicting cryptocurrency price volatility using artificial intelligence.

As cryptocurrency (e.g., Bitcoin), which was used among a small number of users, gradually gained attention from the media and the general public, the number of users began to increase exponentially, which caused a sharp increase in the price and transaction volume of cryptocurrency. The bubble phenomenon occurred and had a profound impact on society.

Various industries using the cryptocurrency system are developing, but the evaluation of the impact it will have on society and the prospects for future development are greatly mixed, and the responses of each country are also showing a big difference. Countries that negatively evaluate the impact of cryptocurrencies are trying to alleviate the social shock caused by the introduction of new technologies by making the entire use of cryptocurrencies illegal or restricting the use of cryptocurrencies by financial institutions.

Analyzing the price and volume of cryptocurrency, the trading volume decreased due to a sharp price drop in early 2018, but the trading volume recovered rapidly in 2019, indicating that the global cryptocurrency market has matured one step after the bubble.

In addition, considering that cryptocurrency has been confirmed as an alternative investment asset in the financial market, and Brazil, Argentina, and Venezuela are actively using cryptocurrency as an alternative to fiat currency, the cryptocurrency trading market is expected to continue to grow in the future. do.

As various types of cryptocurrencies appear and trading begins through exchanges, many users are directly participating in or interested in trading cryptocurrencies. As cryptocurrencies are traded in this way, prospects for various cryptocurrencies are emerging.

However, the prospects for cryptocurrencies are simply news, press releases, or predictions, and there is a problem that users only refer to it and it is difficult to give more value than that.

Korean Patent Registration No. 10-1862000 (May 23, 2018)

The problem to be solved by the present invention is a method of predicting cryptocurrency price volatility using artificial intelligence that can predict the price volatility of cryptocurrency by using the use of each of a plurality of cryptocurrency accounts and information related to cryptocurrency collected in the cryptocurrency account , devices and computer programs.

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

Cryptocurrency price volatility prediction method using artificial intelligence according to an embodiment of the present invention for solving the above-mentioned problems, in a method performed by a computing device, cryptocurrency transaction information generated between a plurality of cryptocurrency accounts Determining the use for each of the plurality of cryptocurrency accounts using It may include predicting the price volatility of the cryptocurrency.

In various embodiments, the collecting of the information related to the cryptocurrency may include, according to the cryptocurrency holding amount and the cryptocurrency holding amount of the cryptocurrency account in which the predetermined use among the plurality of cryptocurrency accounts is determined as a miners account. Collecting information related to a mining pattern, wherein predicting the price volatility of the cryptocurrency, predicting the price volatility of the cryptocurrency by analyzing based on the amount of cryptocurrency held in the miner's account and the mining pattern may include the step of

In various embodiments, the collecting of the information related to the cryptocurrency includes collecting information on the total amount of cryptocurrency flowing from a cryptocurrency derivatives exchange, and predicting the price volatility of the cryptocurrency determining the futures trading volume of the cryptocurrency based on the total amount of cryptocurrency flowing from the cryptocurrency derivatives exchange, and predicting the price volatility of the cryptocurrency using the futures trading volume of the cryptocurrency can

In various embodiments, predicting the price volatility of the cryptocurrency using the futures trading volume of the cryptocurrency may include analyzing the futures trading volume of the cryptocurrency to increase the difference between the withdrawal amount and the deposit amount of the cryptocurrency. It may include predicting the magnitude of the price volatility of the cryptocurrency in proportion.

In various embodiments, the step of predicting the magnitude of the price volatility of the cryptocurrency in proportion to the increase in the difference between the withdrawal amount and the deposit amount of the cryptocurrency is predicting that the magnitude of the price volatility of the cryptocurrency is equal to or greater than a reference value If the short buying quantity of the cryptocurrency at one point is greater than the short selling quantity, predicting that the price of the cryptocurrency will decrease and the short selling of the cryptocurrency at the time when the size of the price volatility of the cryptocurrency is predicted to be greater than or equal to the reference value It may include predicting that the price of the cryptocurrency will increase when the amount is greater than the short purchase amount.

In various embodiments, the predicting of the price volatility of the cryptocurrency includes analyzing the collected information related to the cryptocurrency and a cryptocurrency transaction target according to the cryptocurrency holding amount of each of a plurality of cryptocurrency accounts and the cryptocurrency transaction information It may include predicting the price volatility of the cryptocurrency based on

In various embodiments, determining the use for each of the plurality of cryptocurrency accounts includes visualizing cryptocurrency transaction information generated between the plurality of cryptocurrency accounts, and analyzing the visualized cryptocurrency transaction information to determine the use of the plurality of cryptocurrency accounts. determining a use for each of the cryptocurrency accounts of

In various embodiments, the determining of the use for each of the plurality of cryptocurrency accounts may include, in the case where the number of the plurality of cryptocurrency accounts included in the visualized cryptocurrency transaction information is less than or equal to a first reference value, determining the use for each of the plurality of cryptocurrency accounts by analyzing the transaction pattern for each cryptocurrency account, and when the number of transactions according to the cryptocurrency transaction information is less than or equal to the second reference value, based on the owner of the cryptocurrency account Grouping at least one cryptocurrency account among the plurality of cryptocurrency accounts, and using the cryptocurrency transaction information generated in the grouped at least one cryptocurrency account, a pattern for the grouped at least one cryptocurrency account and determining a use for each of the plurality of cryptocurrency accounts by analyzing the .

Cryptocurrency price volatility prediction apparatus using artificial intelligence according to another embodiment of the present invention for solving the above-described problems, a memory for storing one or more instructions, and a processor for executing the one or more instructions stored in the memory. , the processor may perform the cryptocurrency price volatility prediction method using artificial intelligence according to an embodiment of the present invention by executing the one or more instructions.

A computer program according to another embodiment of the present invention for solving the above-described problems is combined with a computer that is hardware, so that the cryptocurrency price volatility prediction method using artificial intelligence according to an embodiment of the present invention can be performed. It may be stored in a computer-readable recording medium.

Other specific details of the invention are included in the detailed description and drawings.

According to various embodiments of the present invention, there is an advantage that the price volatility of cryptocurrency can be accurately predicted by using the use of each of a plurality of cryptocurrency accounts and information related to cryptocurrency collected in the cryptocurrency account.

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

1 is a diagram illustrating a cryptocurrency price volatility prediction system using artificial intelligence according to an embodiment of the present invention.
2 is a hardware configuration diagram of an apparatus for predicting cryptocurrency price volatility using artificial intelligence according to another embodiment of the present invention.
3 is a flowchart of a method for predicting cryptocurrency price volatility using artificial intelligence according to another embodiment of the present invention.
4 is a flowchart of a cryptocurrency account classification method performed by the cryptocurrency price volatility prediction apparatus in various embodiments.
5 is a diagram illustrating visualized cryptocurrency transaction information in various embodiments.
6 is a diagram illustrating a configuration for determining the use of a cryptocurrency account using a graph-based semi-map learning model in various embodiments.
7 is a diagram illustrating a configuration for determining the use of a cryptocurrency account using an account address-based supervised learning model, in various embodiments.
8 is a diagram illustrating a configuration for determining the use of a cryptocurrency account using an owner-based semi-guided learning model, in various embodiments.
9 is a diagram illustrating a configuration for determining the use of a cryptocurrency account by using image-type cryptocurrency account information and keywords obtained from a website, in various embodiments.
10 is a table showing deposits and withdrawals of cryptocurrencies by time in various embodiments.
11 is a graph showing the amount of change in the price of cryptocurrency according to the amount of deposit and withdrawal of cryptocurrency, in various embodiments.

Advantages and features of the present invention and methods of achieving them will become apparent with reference to the embodiments described below in detail in conjunction with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below, but may be implemented in various different forms, and only these embodiments allow the disclosure of the present invention to be complete, and those of ordinary skill in the art to which the present invention pertains. It is provided to fully understand the scope of the present invention to those skilled in the art, and the present invention is only defined by the scope of the claims.

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

Unless otherwise defined, all terms (including technical and scientific terms) used herein will have the meaning commonly understood by those of ordinary skill in the art to which this invention belongs. In addition, terms defined in a commonly used dictionary are not to be interpreted ideally or excessively unless specifically defined explicitly.

As used herein, the term “unit” or “module” refers to a hardware component such as software, FPGA, or ASIC, and “unit” or “module” performs certain roles. However, “part” or “module” is not meant to be limited to software or hardware. A “unit” or “module” may be configured to reside on an addressable storage medium or to reproduce one or more processors. Thus, by way of example, “part” or “module” refers to components such as software components, object-oriented software components, class components and task components, processes, functions, properties, Includes procedures, subroutines, segments of program code, drivers, firmware, microcode, circuitry, data, databases, data structures, tables, arrays and variables. Components and functionality provided within “parts” or “modules” may be combined into a smaller number of components and “parts” or “modules” or as additional components and “parts” or “modules”. can be further separated.

Spatially relative terms "below", "beneath", "lower", "above", "upper", etc. It can be used to easily describe the correlation between a component and other components. A spatially relative term should be understood as a term that includes different directions of components during use or operation in addition to the directions shown in the drawings. For example, when a component shown in the drawing is turned over, a component described as “beneath” or “beneath” of another component may be placed “above” of the other component. can Accordingly, the exemplary term “below” may include both directions below and above. Components may also be oriented in other orientations, and thus spatially relative terms may be interpreted according to orientation.

In this specification, a computer means all types of hardware devices including at least one processor, and may be understood as encompassing software configurations operating in the corresponding hardware device according to embodiments. For example, a computer may be understood to include a smartphone, a tablet PC, a desktop, a notebook computer, and a user client and an application running on each device, but is not limited thereto.

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings.

Each step described in this specification is described as being performed by a computer, but the subject of each step is not limited thereto, and at least a portion of each step may be performed in different devices according to embodiments.

1 is a diagram illustrating a cryptocurrency price volatility prediction system using artificial intelligence according to an embodiment of the present invention.

The cryptocurrency price volatility prediction system using artificial intelligence according to an embodiment of the present invention shown in FIG. 1 may include a cryptocurrency price volatility prediction apparatus 100 , a user terminal 200 , and an external server 300 . .

Here, the cryptocurrency price volatility prediction system using artificial intelligence shown in FIG. 1 is according to an embodiment, and its components are not limited to the embodiment shown in FIG. 1, and add, change, or delete as necessary. can be

In one embodiment, the cryptocurrency price volatility prediction device 100 collects cryptocurrency transaction information (eg, a transaction) generated between a plurality of cryptocurrency accounts, and uses the collected cryptocurrency transaction information to obtain a plurality of You can determine the purpose of each cryptocurrency account (eg type of account, role).

In various embodiments, the cryptocurrency price volatility prediction device 100 collects cryptocurrency transaction information generated between a plurality of cryptocurrency accounts from an external server 300 (eg, cryptocurrency transaction brokerage server) through the network 400 . and can visualize the collected cryptocurrency transaction information (eg, FIGS. 4 and 5 ), and analyze the visualized cryptocurrency transaction information to determine the use of each of a plurality of cryptocurrency accounts. However, the present invention is not limited thereto.

In various embodiments, the cryptocurrency price volatility prediction device 100 analyzes the visualized cryptocurrency transaction information to determine the use of each of a plurality of cryptocurrency accounts, but according to the analysis result, individual accounts, exchanges It can be determined as any one of an account, a Miners account, a Mixers account, a Merchant account, a Services account, a Darkweb account, and a hedge funds account. However, the present invention is not limited thereto.

In one embodiment, the cryptocurrency price volatility prediction apparatus 100 uses the predetermined use for each of the plurality of cryptocurrency accounts, and information related to cryptocurrency for each of the plurality of cryptocurrency accounts whose use is determined (eg, cryptocurrency account) balance information and transaction history information) and analyze the collected information related to cryptocurrency to predict the price volatility of cryptocurrency. For example, the cryptocurrency price volatility prediction apparatus 100 may analyze the collected information related to cryptocurrency and predict that the price will rise or fall. In addition, the cryptocurrency price volatility prediction apparatus 100 may predict the price of a cryptocurrency (eg, a price increase or a decrease in price). However, the present invention is not limited thereto.

In one embodiment, the user terminal 200 may be connected to the cryptocurrency price volatility prediction apparatus 100 through the network 400, and various information related to whether cryptocurrency tax evasion is obtained from the cryptocurrency price volatility prediction apparatus 100 ( Example: information on the price volatility of cryptocurrency) can be provided. For example, the user terminal 200 may include at least one of a smartphone, a tablet PC, a laptop computer, and a desktop having a display in at least a partial area of the user terminal 200, and predicting cryptocurrency price volatility through the display Cryptocurrency price volatility prediction information provided by the cryptocurrency price volatility prediction apparatus 100 may be output through a user interface (UI) provided by the device 100 . However, the present invention is not limited thereto.

In one embodiment, the external server 300 may be connected to the cryptocurrency price volatility prediction apparatus 100 through the network 400, and the cryptocurrency price volatility prediction apparatus 100 predicts the cryptocurrency price volatility. Various necessary information (eg, cryptocurrency transaction information, information related to the use of each of a plurality of cryptocurrency accounts) can be provided. For example, the external server 300 may be a cryptocurrency transaction brokerage server that provides a service for brokering cryptocurrency transactions, and is generated by conducting transactions between cryptocurrency accounts through a service brokering cryptocurrency transactions. It is possible to store the cryptocurrency transaction information, and provide the stored cryptocurrency transaction information to the cryptocurrency price volatility prediction apparatus 100 .

In various embodiments, the external server 300 receives various data from the cryptocurrency price volatility prediction device 100 (eg, information on usage determined for each of a plurality of cryptocurrency accounts, price volatility prediction information of cryptocurrency) can be saved For example, the external server 300 may be a storage device separately provided outside the cryptocurrency price volatility prediction device 100 . However, the present invention is not limited thereto.

In various embodiments, the cryptocurrency price volatility prediction apparatus 100 may have a storage device (not shown) for storing various data generated by the cryptocurrency price volatility prediction apparatus 100 itself. For example, the cryptocurrency price volatility prediction apparatus 100 may systematically store and manage tens of billions of account information and transaction information using a storage device. For example, the cryptocurrency price volatility prediction apparatus 100 may store the visualized cryptocurrency transaction information, and may include a graph-only database (Graph DB) optimized for cryptocurrency fund tracking, and using this, In order to predict price volatility in real time, the analysis engine of the DB can be tuned as a high-performance engine dedicated to graph information. Hereinafter, the hardware configuration of the cryptocurrency price volatility prediction apparatus 100 will be described with reference to FIG. 2 .

2 is a hardware configuration diagram of an apparatus for predicting cryptocurrency price volatility using artificial intelligence according to another embodiment of the present invention.

Referring to FIG. 2 , an apparatus 100 for predicting cryptocurrency price volatility according to another embodiment of the present invention (hereinafter, "computing apparatus 100") may include a processor 110 and a memory 120 . In various embodiments, the computing device 100 may further include a network interface (or communication interface) (not shown), storage (not shown), and a bus (not shown).

In an embodiment, the processor 110 may control the overall operation of each component of the computing device 100 . The processor 110 may include a central processing unit (CPU), a micro processor unit (MPU), a micro controller unit (MCU), or any type of processor well known in the art.

In various embodiments, the processor 110 may perform an operation on at least one application or program for executing the method according to the embodiments of the present invention. In various embodiments, the processor 110 includes one or more cores (not shown) and a graphic processing unit (not shown) and/or a connection path (eg, a bus, etc.) for transmitting and receiving signals to and from other components. can do.

In various embodiments, the processor 110 temporarily and/or permanently stores a signal (or data) processed inside the processor 110 , a random access memory (RAM) and a read access memory (ROM). -Only Memory, not shown) may be further included. In addition, the processor 110 may be implemented in the form of a system on chip (SoC) including at least one of a graphic processing unit, a RAM, and a ROM.

In one embodiment, the processor 110 executes one or more instructions stored in the memory 120 , so that the method to be described with reference to FIGS. 3 to 11 (eg, a method of predicting cryptocurrency price volatility using artificial intelligence) can be performed. For example, the processor 110 executes one or more instructions stored in the memory 120, thereby determining the use for each of the plurality of cryptocurrency accounts using cryptocurrency transaction information generated between the plurality of cryptocurrency accounts. Cryptocurrency using artificial intelligence, comprising the steps of collecting information related to cryptocurrency for each of a plurality of cryptocurrency accounts whose use is determined, and predicting price volatility of cryptocurrency by analyzing the collected information related to cryptocurrency A method of predicting price volatility can be performed.

In one embodiment, memory 120 may store various data, commands, and/or information. The memory 120 may store programs (one or more instructions) for processing and controlling the processor 110 . Programs stored in the memory 120 may be divided into a plurality of modules according to functions.

In various embodiments, steps of a method or algorithm described in connection with an embodiment of the present invention may be implemented directly in hardware, as a software module executed by hardware, or by a combination thereof. A software module may contain random access memory (RAM), read only memory (ROM), erasable programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), flash memory, hard disk, removable disk, CD-ROM, or It may reside in any type of computer-readable recording medium well known in the art to which the present invention pertains.

The components of the present invention may be implemented as a program (or application) to be executed in combination with a computer, which is hardware, and stored in a medium. The components of the present invention may be implemented as software programming or software components, and similarly, embodiments may include various algorithms implemented as data structures, processes, routines, or combinations of other programming constructs, including C, C++ , Java, assembler, etc. may be implemented in a programming or scripting language. Functional aspects may be implemented in an algorithm running on one or more processors. Hereinafter, a method of predicting cryptocurrency price volatility using artificial intelligence performed by the computing device 100 will be described with reference to FIG. 3 .

3 is a flowchart of a method for predicting cryptocurrency price volatility using artificial intelligence according to another embodiment of the present invention.

Referring to FIG. 3 , in step S110 , the computing device 100 may determine a use for each of the plurality of cryptocurrency accounts by using cryptocurrency transaction information generated between the plurality of cryptocurrency accounts.

In various embodiments, the computing device 100 may collect cryptocurrency transaction information generated between a plurality of cryptocurrency accounts, visualize the collected cryptocurrency transaction information, and analyze the visualized cryptocurrency transaction information. It is possible to determine the use of each of a plurality of cryptocurrency accounts. Hereinafter, a method of determining the use of a cryptocurrency account performed by the computing device 100 will be described with reference to FIGS. 4 to 9 .

4 is a flowchart of a cryptocurrency account classification method performed by the cryptocurrency price volatility prediction apparatus in various embodiments.

Referring to FIG. 4 , in step S210 , the computing device 100 may collect cryptocurrency transaction information generated between a plurality of cryptocurrency accounts. For example, the computing device 100 generates cryptocurrency transaction information (eg, transaction) generated between a plurality of cryptocurrency accounts from the external server 300 (eg, a server that mediates cryptocurrency transactions between a plurality of cryptocurrency accounts). can be provided. However, the present invention is not limited thereto.

In step S220, the computing device 100 may visualize the cryptocurrency transaction information generated between the plurality of cryptocurrencies collected in step S110.

In various embodiments, the computing device 100 may visualize cryptocurrency transaction information generated between a plurality of cryptocurrencies in a graph form. However, the present invention is not limited thereto, and the computing device 100 may visualize cryptocurrency transaction information in various forms. Hereinafter, a configuration in which the computing device 100 visualizes cryptocurrency transaction information will be described with reference to FIG. 5 .

5 is a diagram illustrating visualized cryptocurrency transaction information in various embodiments.

Referring to FIG. 5 , in one embodiment, the computing device 100 may generate a plurality of nodes 10 corresponding to each of a plurality of cryptocurrency accounts. For example, the computing device 100 may generate one node corresponding to one cryptocurrency account.

In various embodiments, the computing device 100 may generate a node in the form of a square having a predetermined size, but is not limited thereto, and various forms (eg: round, oval, or rectangular).

In various embodiments, the computing device 100 generates a node corresponding to each of the plurality of cryptocurrency accounts, and a node corresponding to each of the plurality of cryptocurrency accounts based on the use of the cryptocurrency account determined through step S240 to be described later. properties can be determined. For example, the computing device 100 selects a node 11 corresponding to a cryptocurrency account (eg, a black market account, a fraudulent account, and a gambling account) used for crime and fraud based on the use of each of the plurality of cryptocurrency accounts. A first color (eg, red) may be set, and a node 12 corresponding to a cryptocurrency account associated with a criminal and fraudulent use account may be set as a second color (eg, yellow). Also, the computing device 100 may set the node 13 corresponding to the normally used cryptocurrency account (eg, an exchange account, a mining account, and a commerce account) to a third color (eg, white). Through this, a user who receives and monitors visualized cryptocurrency transaction information can more easily track and monitor cryptocurrency accounts used for crime and fraud. However, the present invention is not limited thereto.

In an embodiment, the computing device 100 may connect the sender's cryptocurrency account and the receiver's cryptocurrency account among nodes corresponding to a plurality of cryptocurrency accounts with an edge based on the cryptocurrency transaction information. For example, when it is determined that the remittance is made from the first cryptocurrency account to the second cryptocurrency account among the plurality of cryptocurrency accounts based on the cryptocurrency transaction information, the computing device 100 corresponds to the first cryptocurrency account. The node 11 and the node 12 corresponding to the second cryptocurrency account may be connected with a line.

In various embodiments, the computing device 100 connects a line (eg, a line in the form of an arrow) from the node of the sender's cryptocurrency account to the node of the receiver's cryptocurrency account, and the cryptocurrency is positioned adjacent to the connected line. Transaction quantity, number of transactions, and transaction time information according to transaction information can be output together. However, the present invention is not limited thereto.

According to an embodiment, the computing device 100 connects the node of the sender's cryptocurrency account and the node of the receiver's cryptocurrency account according to the transaction quantity, number of transactions, and transaction time information according to the cryptocurrency transaction information. can change the form of For example, the thickness of the line may change depending on the amount of cryptocurrency transaction (or transaction amount), and the shape of the line (eg, broken line, double line, etc.) may change depending on the number of cryptocurrency transactions, and the cryptocurrency transaction time or The length of the line may be changed according to the transaction frequency, but is not limited thereto.

The shape of the line connecting the nodes may be variously set so that at least some of the transaction quantity, number of transactions, and transaction time information according to the cryptocurrency transaction information can be visualized and read according to a preset rule.

The computing device 100 may extract various feature values based on the connection relationship between nodes, the characteristics of each node, and the shape of a line connecting each node using the pre-learned artificial intelligence model, and accordingly, The attributes of the corresponding accounts may be determined.

In an embodiment, the computing device 100 may determine the attribute of a transaction corresponding to each line by using a pre-learned artificial intelligence model. For example, when a node-to-node remittance is made, it may be a remittance for a cryptocurrency transaction for investment purposes, a remittance to pay for a product or service, asset management, tax evasion, or illegal transfer of funds. It may be a remittance for

In order to determine this, the computing device 100 may utilize not only information on the quantity, number, frequency, and time of each transaction, but also cryptocurrency price information at the time of the transaction. Unlike traditional currencies, cryptocurrency has a characteristic that its value can change significantly from moment to moment. Therefore, by utilizing the market price information at the time of the transaction of the cryptocurrency, the value of the amount actually transferred can be determined, and accordingly, the attribute of the transaction can be determined.

For example, if there are multiple remittances between different nodes and the value of the remittance calculated by reflecting the market price of cryptocurrency is constant, it can be determined that the price has been paid for a product or service with a specific value. . On the other hand, if a certain amount of cryptocurrency is being remitted despite fluctuations in the price of cryptocurrency, it can be determined that the remittance has occurred regardless of the actual value and has other purposes. However, the purpose of remittance may be evaluated differently depending on specific situation information, and the criteria for determination are not limited to the above example.

In addition, if a large number of transactions occur in a situation in which the cryptocurrency market price changes rapidly, it may be judged to be a transaction for the purpose of investment. Transactions between accounts, asset management, tax evasion, etc.)

According to an embodiment, as described above, a line connecting each node may be visualized according to a preset rule, and the computing device 100 uses a pre-learned artificial intelligence model to display a transaction attribute of each line. can be judged For example, the computing device 100 may extract various features from the visualized shape of each line, and estimate properties of a transaction corresponding thereto.

In the disclosed embodiment, the artificial intelligence model may be learned based on a deep learning model and training data including information on a visualized image and an answer (eg, account attribute, transaction attribute, etc.) corresponding to each image. However, the present invention is not limited thereto.

Referring back to FIG. 4 , in step S230 , the computing device 100 may analyze the cryptocurrency transaction information visualized in step S220 , and in step S240 , the computing device 100 is visualized through step S230 . Based on the analysis result of the cryptocurrency transaction information, it is possible to determine the use for each of the plurality of cryptocurrency accounts.

In various embodiments, the computing device 100 automatically extracts a feature value from the cryptocurrency transaction information visualized in a graph form in step S220 using a pre-trained artificial intelligence model (eg, a deep learning model). and the use of each of the plurality of cryptocurrency accounts can be determined using the extracted feature value. For example, the feature value may be in the overall form of a graph, and the computing device 100 determines which cryptocurrency account is located on the graph according to the overall shape of the cryptocurrency transaction information visualized in the graph form. It can be determined whether the account is performing a role. However, the present invention is not limited thereto.

In one embodiment, the pre-trained artificial intelligence model is based on the training data in which the properties of the cryptocurrency account corresponding to one or more nodes included in the visualized cryptocurrency transaction information and the visualized cryptocurrency transaction information in the form of a graph are labeled. can be learned As another example, the pre-trained artificial intelligence model clusters the attributes of accounts corresponding to one or more nodes from the cryptocurrency transaction information visualized in the form of a graph, and receives or automatically determines the attribute information of each clustered account. It is also possible to perform classification on the properties of .

In various embodiments, the computing device 100 uses a graph-based semi-map learning model based on the visualized state of the cryptocurrency transaction information (eg, the number of nodes, the number of lines connecting the nodes, etc.) The use of a cryptocurrency account can be determined by using any one of the determination method, the method of determining the use of a cryptocurrency account using an account address-based supervised learning model, and the method of determining the use of a cryptocurrency account using an owner-based semi-supervised learning model. have.

In various embodiments, the computing device 100 uses any one of a graph-based semi-supervised learning model, an account address-based supervised learning model, and an owner-based semi-supervised learning model based on the type of input data to generate a cryptocurrency account use can be determined. Hereinafter, it will be described with reference to FIGS. 6 to 8 .

6 is a diagram illustrating a configuration for determining the use of a cryptocurrency account using a graph-based semi-map learning model in various embodiments.

Referring to FIG. 6 , in various embodiments, the computing device 100 determines the use of a cryptocurrency account by using a graph-based semi-map learning model when the number of interconnected nodes in the visualized cryptocurrency transaction information is not large. can

The graph-based semi-supervised learning model is a model that can process tens of billions of cryptocurrency transaction information stored in graph format into meaningful information. : Deep learning analysis) may be a model that can determine the use of a cryptocurrency account. For example, the graph-based semi-supervised learning model in-depth analysis (e.g., clustering, classification) of the node corresponding to the cryptocurrency account and the characteristics of the line representing the cryptocurrency transaction information. It is possible to derive the necessary information in determining the use. In addition, the graph-based semi-supervised learning model may be a model to which semi-supervised learning is applied so that it can have higher accuracy using a small amount of correct answer data. However, the present invention is not limited thereto.

In various embodiments, the computing device 100 uses a graph-based semi-map learning model when it is determined that the number of a plurality of nodes included in the visualized cryptocurrency transaction information exceeds a preset first reference value (eg : Using the visualized cryptocurrency transaction information as an input value), it is possible to determine the form in which a plurality of nodes are connected by a line (eg, the overall shape of the graph), and a cryptocurrency account based on the form in which a plurality of nodes are connected by a line use can be determined. For example, when the overall shape of the graph has the graph pattern of the exchange, the computing device 100 may determine the use of the corresponding cryptocurrency account as the exchange account. However, the present invention is not limited thereto.

7 is a diagram illustrating a configuration for determining the use of a cryptocurrency account using an account address-based supervised learning model, in various embodiments.

Referring to FIG. 7 , in the visualized cryptocurrency transaction information, when the number of interconnected nodes is not large, the computing device 100 may determine the use of the cryptocurrency account by using the account address-based supervised learning model.

The account address-based supervised learning model may be a model for identifying the use of each cryptocurrency account by analyzing a transaction pattern based on individual cryptocurrency accounts. The account address-based supervised learning model may be a model in which a cryptocurrency transaction pattern is learned using only a cryptocurrency account whose use is determined in advance through the above method and a cryptocurrency account with 100% certainty through manual operation.

In various embodiments, the computing device 100 performs account address-based supervised learning when the number of a plurality of nodes connected by lines is less than or equal to a first reference value and the number of lines for each of the plurality of nodes exceeds a second reference value. Using the model, it is possible to analyze the transaction pattern for each cryptocurrency account according to the transaction history for each of the plurality of cryptocurrency accounts, and determine the use of each of the plurality of cryptocurrency accounts based on the analyzed transaction pattern. For example, the computing device 100 may determine the use of the cryptocurrency account as an ICO account when the transaction pattern for the cryptocurrency account shows a wave shape, and determines the form in which the transaction pattern for the cryptocurrency account occurs frequently. If it is visible, the use of the cryptocurrency account can be determined as an exchange hot wallet account, and when the transaction pattern for the cryptocurrency account shows a step shape, the use of the cryptocurrency account can be determined as a personal account and an exchange cold wallet account, If the deposit and withdrawal amounts show the same form in the transaction pattern for the cryptocurrency account, the use of the cryptocurrency account can be determined as the exchange user wallet account. However, the present invention is not limited thereto.

8 is a diagram illustrating a configuration for determining the use of a cryptocurrency account using an owner-based semi-guided learning model, in various embodiments.

Referring to FIG. 8 , in various embodiments, when the number of transaction details between cryptocurrency accounts for determining a transaction pattern is a small number (eg, one), the computing device 100 uses an owner-based semi-guided learning model to encrypt You can decide the purpose of the monetary account.

The owner-based semi-supervised learning model is a technology that processes the reclassified cryptocurrency transaction information into meaningful information based on the owner of the cryptocurrency account. It may be a model that learned the owner's transaction pattern identified through Entity Heuristic Clustering. The owner-based semi-supervised learning model can be a model that has learned various data through semi-supervised learning with high accuracy with only a small amount of correct data, and can determine the use of a cryptocurrency account by performing semi-supervised deep learning analysis.

In various embodiments, when the number of the plurality of nodes connected by lines is less than or equal to the first reference value and the number of lines for each of the plurality of nodes is less than or equal to the second reference value, the computing device 100 generates an owner-based semi-supervised learning model. Grouping at least one cryptocurrency account among a plurality of cryptocurrency accounts based on the owner of the cryptocurrency account using A pattern for the currency account may be analyzed, and a use for each of the grouped at least one cryptocurrency account may be determined based on the grouped pattern (eg, FIG. 8 ) for the at least one cryptocurrency account. However, the present invention is not limited thereto.

In various embodiments, the computing device 100 may collect image form of cryptocurrency account information and one or more keywords from an external website, and use the collected information to determine the use of the cryptocurrency account. Hereinafter, it will be described with reference to FIG.

9 is a diagram illustrating a configuration for determining the use of a cryptocurrency account by using image-type cryptocurrency account information and keywords obtained from a website, in various embodiments.

Referring to FIG. 9 , the computing device 100 may collect image form of cryptocurrency account information and one or more keywords from an external website, and analyze the image form of cryptocurrency account information to obtain a text form of cryptocurrency account. Information may be extracted, and one or more keywords may be analyzed to determine the use of a cryptocurrency account corresponding to the extracted text-type cryptocurrency account information.

In general, transactions using cryptocurrency value anonymity, so the address of the cryptocurrency account is often stored in the form of an image. In this case, the computing device 100 may search for the cryptocurrency account information in the form of an image, and extract the cryptocurrency account in the form of a text from the found cryptocurrency account information in the form of an image (eg, by using OCR character reading technology). .

In addition, the computing device 100 may extract one or more main keywords from a website on which the cryptocurrency account address is posted, and may determine a use for the cryptocurrency account extracted in text form according to the extracted keywords. For example, when the keywords extracted from the website on which the cryptocurrency account address is posted are Drugs and Weeds, the computing device 100 may determine the use of the cryptocurrency account extracted in text form as a black market account.

In various embodiments, the computing device 100 may collect information related to cryptocurrency from an illegal dark web site, and use it to determine the use of a cryptocurrency account.

In general, a dark web site refers to a web that requires the use of a specific program to access it, and is used for cybercriminals because the visitor or server cannot be identified in a normal way. In particular, various illegal crimes using cryptocurrency as a payment method are prevalent in the dark web. In order to monitor the cryptocurrency account performing such an illegal transaction, the computing device 100 uses pre-stored Darkweb access software (using Tor browser, software that accesses domains ending in *.onion). Access the dark web site, automatically collect information related to cryptocurrency from the dark web site at preset intervals, and determine the use of each of a plurality of cryptocurrency accounts based on the information related to cryptocurrency collected from the dark web site can For example, the computing device 100 may set a cryptocurrency account corresponding to a cryptocurrency account address obtained from a dark web site among a plurality of cryptocurrency accounts as a dark web account. However, the present invention is not limited thereto.

Referring again to FIG. 3 , in step S120 , the computing device 100 may collect information related to cryptocurrency for each of a plurality of cryptocurrency accounts whose use is determined in step S110 . For example, the computing device 100 may obtain the use of each of the plurality of cryptocurrency accounts, the amount of cryptocurrency held in the cryptocurrency account, and information on the cryptocurrency transaction history. However, the present invention is not limited thereto.

In various embodiments, the computing device 100 may collect the cryptocurrency holding amount of the cryptocurrency account in relation to the cryptocurrency account determined as the miner account in step S110 and information related to the mining pattern according to the cryptocurrency holding amount. For example, the computing device 100 may collect the amount of cryptocurrency in the miner's account and information related to whether cryptocurrency mining continues according to the amount of cryptocurrency held.

In an embodiment, the computing device 100 may monitor the amount of cryptocurrency entering or leaving (ie, deposited and withdrawn) from an exchange account by using attribute information of each account. Also, the computing device 100 may monitor the number of users of the exchange (eg, the number of personal accounts transacting with the exchange account).

The computing device 100 may predict the volatility of cryptocurrency based on the monitored amount of deposit and withdrawal of the exchange and the number of users.

Unlike other existing financial products such as stocks, cryptocurrency is characterized in that execution, clearing, and settlement occur simultaneously. Accordingly, it is possible to obtain settlement information of cryptocurrency in real time, and by analyzing it, volatility information of cryptocurrency can be predicted.

In particular, when a large amount of deposit occurs from the exchange account to the miner's account, it can be predicted that the miner will perform any operation or strategy on the exchange. In the disclosed embodiment, the computing device 100 obtains volatility information of cryptocurrency from settlement information obtained in real time using an artificial intelligence model learned (machine learning) using learning data including various money flows and settlement information. predictable.

In various embodiments, the computing device 100 may collect information on the total amount of cryptocurrency flowing from the cryptocurrency derivatives exchange by using transaction information of a plurality of cryptocurrency accounts.

In step S130, the computing device 100 may predict the price volatility of the cryptocurrency by analyzing the information related to the cryptocurrency collected in step S120. For example, the computing device 100 may analyze the information related to the cryptocurrency to predict the price volatility of the cryptocurrency based on the cryptocurrency holding amount of each of a plurality of cryptocurrency accounts and the cryptocurrency transaction target according to the cryptocurrency transaction information. have.

In various embodiments, the computing device 100 may predict the price volatility of the cryptocurrency by analyzing it based on the amount of cryptocurrency held by the miner's account and the mining pattern. For example, the computing device 100 may determine whether the miner continues to mine cryptocurrency by analyzing the amount of cryptocurrency held by the miner and the mining pattern according to the amount of cryptocurrency held in the miner's cryptocurrency account. In addition, the computing device 100 may predict the price volatility of the cryptocurrency according to whether the miner continues to mine the cryptocurrency. For example, the computing device 100 predicts that the price of the cryptocurrency will decrease in response to the miner being determined to continue mining the cryptocurrency, and in response to determining that the miner will stop mining the cryptocurrency, the cryptocurrency It can be predicted that the price of However, the present invention is not limited thereto.

In various embodiments, the computing device 100 determines the futures trading volume of the cryptocurrency based on the total amount of cryptocurrency flowing from the cryptocurrency derivatives exchange, and predicts the price volatility of the cryptocurrency by using the futures trading volume of the cryptocurrency. can For example, the computing device 100 may analyze the futures trading volume of the cryptocurrency to predict the magnitude of price volatility of the cryptocurrency in proportion to an increase in the difference between the withdrawal amount and the deposit amount of the cryptocurrency. Hereinafter, it will be described with reference to FIGS. 10 and 11 .

10 is a table showing the amount of deposit and withdrawal of cryptocurrency by time in various embodiments, and FIG. 11 is a graph showing the amount of change in the price of cryptocurrency according to the amount of deposit and withdrawal of cryptocurrency in various embodiments.

Referring to FIGS. 10 and 11 , it can be seen that a large-scale cryptocurrency withdrawal occurred before a rapid change in the cryptocurrency price occurred. In the case of cryptocurrencies (e.g. Bitcoin), unlike general stocks, there is a policy of withdrawing all at once at 13:00 UTC, so if a large amount of Bitcoin is withdrawn at that time, the Bitcoin flow tends to decrease sharply.

In addition, in the case of futures trading, since all transactions are made in Bitcoin, a large amount of Bitcoin is deposited and withdrawn from the exchange per day. At this time, deposits of bitcoins are possible at any time, but in the case of withdrawals, since a large amount of bitcoins are withdrawn at once, the amount of bitcoins withdrawn overwhelms the amount of bitcoins deposited. can occur. In this case, the bitcoin flow in the exchange temporarily decreases, and the difference between the withdrawal and deposit of cryptocurrency increases, which may cause rapid price fluctuations.

In addition, if the amount of Bitcoin flow in the exchange decreases (for example, if the difference between the withdrawal amount and the deposit amount of cryptocurrency increases), the spread increases and the price difference between the buyer and the seller widens. change is bound to happen. Here, in futures trading, contracts are liquidated when a price change of more than a certain percentage occurs, so as the futures trade is liquidated, a more rapid price change occurs, and this price change triggers a chain reaction that again liquidates large-scale transactions.

In various embodiments, the computing device 100 determines the futures trading volume of the cryptocurrency based on the total amount of cryptocurrency flowing from the cryptocurrency derivatives exchange, and predicts the price volatility of the cryptocurrency by using the futures trading volume of the cryptocurrency However, the larger the difference between the withdrawal amount and the deposit amount of the cryptocurrency, the greater the price volatility of the cryptocurrency. However, the present invention is not limited thereto.

In various embodiments, the computing device 100 may predict the price volatility of the cryptocurrency based on the short purchase amount and the short sale amount of the cryptocurrency.

In general, large-scale withdrawals of Bitcoin have a significant impact on price volatility, but it may be difficult to predict perfect price volatility simply with large-scale withdrawals. Therefore, for a more complete price volatility prediction, the computing device 100 improves the accuracy of price volatility prediction by using the ratio of the short buying quantity (eg Long) and short buying quantity (eg Short) of the cryptocurrency. can do it

In various embodiments, when it is predicted that the magnitude of the price volatility of the cryptocurrency is equal to or greater than the reference value, if the short purchase amount of the cryptocurrency is greater than the short sale amount, it can be predicted that the price of the cryptocurrency will decrease. In addition, the computing device 100 may predict that the price of the cryptocurrency will rise when the short selling amount of the cryptocurrency is greater than the short buying amount at the time when the magnitude of the price volatility of the cryptocurrency is predicted to be equal to or greater than the reference value.

The aforementioned method of predicting cryptocurrency price volatility using artificial intelligence has been described with reference to the flowchart shown in the drawing. For a simple explanation, the method of predicting cryptocurrency price volatility using artificial intelligence has been described by showing a series of blocks, but the present invention is not limited to the order of the blocks, and some blocks are in an order different from that shown and operated in this specification may be performed or may be performed simultaneously. In addition, new blocks not described in this specification and drawings may be added, or some blocks may be deleted or changed.

In various embodiments, the computing device 100 tracks the money flow of cryptocurrency based on the cryptocurrency account attribute corresponding to each block obtained based on the above-described method, and thus the distribution of illegal funds or money laundering information can be obtained.

For example, money laundering technology in the cryptocurrency field is gradually developing, and as a result, transactions are divided into thousands or tens of thousands of transactions at one time, and some are sent to various exchanges in each country, and some transactions are passed through by opening a cannon account at the exchange. Mixing method via exchange through the method, and coin join method in which hundreds of recipients and senders are entered in a transaction are used.

As a result, it is practically impossible to view all transaction volumes using the manual data collection method, and there are difficulties in preventing and tracking crime. In the disclosed embodiment, a mixer account is found based on the above-described method for determining account attributes, and a flow of funds including the mixer account can be determined and tracked as an illegal flow of funds.

In addition, the computing device 100 according to the disclosed embodiment performs machine learning learning to determine its properties (eg, normal flow and illegal money flow) based on flow information of cryptocurrency funds, and the learned artificial intelligence model It is also possible to determine the attribute corresponding to the flow information of cryptocurrency funds using

For example, the flow information of cryptocurrency funds may be expressed as nodes and lines based on the above-described visualization method, but is not limited thereto. In addition, the flow information of the cryptocurrency funds may include attribute information of the cryptocurrency account corresponding to each node, but is not limited thereto. As another example, attribute information on at least some or all of the nodes may not be given.

The computing device 100 may determine the property of the money flow according to the flow information of the money by using the pre-learned artificial intelligence model. More specifically, the attribute of the money flow may include the attribute of an illegal money flow, such as money laundering, tax evasion, payment for illegal goods or services, and the like.

In the cryptocurrency price volatility prediction method according to the disclosed embodiment, the attribute information of each transaction or money flow obtained as described above may be used to predict cryptocurrency price volatility.

As a non-limiting example, if it is determined that the purpose of a specific transaction is investment, if the transaction volume increases by more than a certain level and the price of the cryptocurrency rises or falls more than a preset range, the transaction is stopped and the transaction proceeds again later However, if it is determined that the purpose of a specific transaction being carried out is money laundering or illegal transaction, a fixed amount of transactions may be performed regardless of the fluctuation of cryptocurrency.

Accordingly, the computing device 100 may predict a transaction pattern according to the attribute of a transaction based on a pre-learned artificial intelligence model or a pre-stored database, and may utilize this for predicting volatility of cryptocurrency.

As mentioned above, although embodiments of the present invention have been described with reference to the accompanying drawings, those skilled in the art to which the present invention pertains can realize that the present invention can be embodied in other specific forms without changing its technical spirit or essential features. you will be able to understand Therefore, it should be understood that the embodiments described above are illustrative in all respects and not restrictive.

100: Cryptocurrency price volatility prediction device (computing device)
200: user terminal
300 : external server
400: network

Claims (10)

A method performed by a computing device, comprising:
determining a use for each of the plurality of cryptocurrency accounts by using the cryptocurrency transaction information generated between the plurality of cryptocurrency accounts;
collecting information related to cryptocurrency for each of the plurality of cryptocurrency accounts whose use has been determined; and
Analyzing the collected information related to the cryptocurrency to predict the price volatility of the cryptocurrency,
A method of predicting cryptocurrency price volatility using artificial intelligence. According to claim 1,
The step of collecting information related to the cryptocurrency includes:
Collecting information related to a cryptocurrency holding amount of a cryptocurrency account whose predetermined use among the plurality of cryptocurrency accounts is determined as a miners account and a mining pattern according to the cryptocurrency holding amount,
Predicting the price volatility of the cryptocurrency includes:
and predicting price volatility of the cryptocurrency by analyzing it based on the amount of cryptocurrency held in the miner's account and the mining pattern,
A method of predicting cryptocurrency price volatility using artificial intelligence. According to claim 1,
The step of collecting information related to the cryptocurrency includes:
Collecting information on the total amount of cryptocurrency flowing from the cryptocurrency derivatives exchange,
Predicting the price volatility of the cryptocurrency includes:
determining the futures trading volume of the cryptocurrency based on the total amount of cryptocurrency flowing from the cryptocurrency derivatives exchange, and predicting the price volatility of the cryptocurrency using the futures trading volume of the cryptocurrency,
A method of predicting cryptocurrency price volatility using artificial intelligence. 4. The method of claim 3,
Predicting the price volatility of the cryptocurrency using the futures trading volume of the cryptocurrency includes:
Analyzing the futures trading volume of the cryptocurrency and predicting the magnitude of the price volatility of the cryptocurrency in proportion to the increase in the difference between the withdrawal amount and the deposit amount of the cryptocurrency,
A method of predicting cryptocurrency price volatility using artificial intelligence. 5. The method of claim 4,
Predicting the size of the price volatility of the cryptocurrency in proportion to the increase in the difference between the withdrawal amount and the deposit amount of the cryptocurrency,
predicting that the price of the cryptocurrency will decrease if the short purchase quantity of the cryptocurrency is greater than the short sale quantity at the time when the magnitude of the price volatility of the cryptocurrency is predicted to be equal to or greater than the reference value; and
Comprising the step of predicting that the price of the cryptocurrency will rise when the amount of short selling of the cryptocurrency is greater than the quantity of short selling at the time when the magnitude of the price volatility of the cryptocurrency is predicted to be equal to or greater than the reference value,
A method of predicting cryptocurrency price volatility using artificial intelligence. According to claim 1,
Predicting the price volatility of the cryptocurrency includes:
Analyzing the collected cryptocurrency-related information to predict the price volatility of the cryptocurrency based on the cryptocurrency holding amount of each of a plurality of cryptocurrency accounts and the cryptocurrency transaction target according to the cryptocurrency transaction information,
A method of predicting cryptocurrency price volatility using artificial intelligence. According to claim 1,
Determining the use for each of the plurality of cryptocurrency accounts comprises:
Visualizing the cryptocurrency transaction information generated between the plurality of cryptocurrency accounts, and analyzing the visualized cryptocurrency transaction information to determine a use for each of the plurality of cryptocurrency accounts,
A method of predicting cryptocurrency price volatility using artificial intelligence. 8. The method of claim 7,
Determining the use for each of the plurality of cryptocurrency accounts comprises:
When the number of the plurality of cryptocurrency accounts included in the visualized cryptocurrency transaction information is less than or equal to the first reference value, the use for each of the plurality of cryptocurrency accounts by analyzing the transaction pattern for each of the plurality of cryptocurrency accounts determining a; and
When the number of transactions according to the cryptocurrency transaction information is less than or equal to a second reference value, at least one cryptocurrency account among the plurality of cryptocurrency accounts is grouped based on the owner of the cryptocurrency account, and the grouped at least one cryptocurrency Analyzing a pattern for the grouped at least one cryptocurrency account using the cryptocurrency transaction information generated in the account to determine a use for each of the plurality of cryptocurrency accounts,
A method of predicting cryptocurrency price volatility using artificial intelligence. a memory storing one or more instructions; and
a processor executing the one or more instructions stored in the memory;
The processor by executing the one or more instructions,
An apparatus for performing the method of claim 1 . A computer program stored in a computer-readable recording medium in combination with a computer, which is hardware, to perform the method of claim 1.

Images