System for executing investment strategy and sharing profit using large language model and method for operating the same

Abstract

A method for operating a system that executes an investment strategy and distributes profits using a large-scale language model (LLM) is disclosed, comprising the steps of: receiving an investment strategy written in natural language from a user device; converting the investment strategy into executable structured data by interpreting the investment strategy using a large-scale language model (LLM); transmitting the interpreted investment strategy to the user device to request confirmation from the user; granting the user a virtual account linked to the main account and allocating test funds; if the user agrees to execute the interpreted investment strategy, and if the conditions of the interpreted investment strategy are met, automatically executing a transaction from the main account; recording the results of the transaction execution in the virtual account; determining the profit or loss of the virtual account when a predetermined test period ends; and, if a profit is generated, distributing the profit of the virtual account to the user and the system at a predetermined ratio.

Description

Technology Field

[0001] The present invention relates to a system for executing investment strategies and distributing profits using a Large Language Model (LLM) and a method for operating the same. More specifically, it relates to a technology that utilizes a Large Language Model (LLM) to automatically interpret and execute a user's natural language investment strategy, grants virtual trading accounts to multiple users to test actual market trading with small amounts of capital, and distributes the resulting profits at a predetermined ratio. Background Technology

[0002] Existing algorithmic trading platforms have adopted a method where users must directly implement trading strategies in code using programming languages ​​such as Python. Since this requires significant programming knowledge, it acts as a high barrier to entry for non-experts who lack coding skills, even if they possess financial knowledge.

[0003] Accordingly, there is a demand for integrated platform technology that enables non-experts to easily propose investment ideas using natural language without coding, allows the platform to interpret and automatically execute them in a secure environment, and transparently distributes the generated profits. Prior art literature

[0004] Korean Registered Patent No. 10-2863955 (September 19, 2025) The problem to be solved

[0005] The present invention aims to provide a system for executing investment strategies and distributing profits using a large-scale language model (LLM), and a method for operating the same. means of solving the problem

[0006] As a technical means for achieving the above-mentioned objective, the first aspect of the present invention may provide a method for operating a system that executes an investment strategy and distributes profits using a large-scale language model (LLM), comprising the steps of: receiving an investment strategy written in natural language from a user device; converting the investment strategy into executable structured data by interpreting the investment strategy using a large-scale language model (LLM); transmitting the interpreted investment strategy to the user device and requesting confirmation from the user; granting the user a virtual account linked to the main account and allocating test funds; if the user agrees to execute the interpreted investment strategy, and if the conditions of the interpreted investment strategy are met, automatically executing a transaction from the main account; recording the results of the transaction execution in the virtual account; determining the profit or loss of the virtual account when a predetermined test period ends; and, if a profit is generated, distributing the profit of the virtual account to the user and the system at a predetermined ratio.

[0007] Additionally, test funds may be physically in the main account but treated as belonging to a virtual account for accounting purposes.

[0008] Additionally, the step of automatically executing a transaction in this account may include a step of verifying whether the conditions of an interpreted investment strategy are met while monitoring market data in real time, a step of executing a buy or sell order in this account by linking with an exchange API if it is confirmed that the conditions of the interpreted investment strategy are met, and a step of tagging the user's identifier in the order.

[0009] In addition, the results of the transaction execution are immediately reflected in the virtual account, and the transaction may be executed within the limits of the test funds.

[0010] In addition, if a loss occurs, the loss may be treated as test funds.

[0011] In addition, the test funding may be $10, the predetermined test period may be one week, and the pre-agreed rate may be 50%.

[0012] A second aspect of the present invention may provide a computer-readable storage medium having a program recorded thereon for executing the method of the first aspect on a computer. Effects of the invention

[0013] The present invention has the advantageous effect of significantly lowering the entry barrier to the algorithmic trading market, as it allows even ordinary people without programming knowledge to easily implement their investment ideas into automated trading strategies through natural language.

[0014] In addition, the risk of malfunction can be minimized through a procedure in which users directly verify and approve the interpretation results of the Large Language Model (LLM), and the virtual account method, in which a small amount of actual funds is deposited, has the advantage of providing a safe environment where users can test strategies in a real market setting without the risk of losing their own capital.

[0015] Furthermore, a structure in which users directly receive a share of the profits generated by their strategies provides strong financial incentives to encourage the development of superior and creative strategies, thereby creating a virtuous cycle in which the system accumulates high-quality strategy data.

[0016] Furthermore, by executing all transactions in the system's centralized main account and separating and managing user-specific profits and losses via software, there is an advantage in reducing the costs and complexity associated with operating multiple accounts and streamlining infrastructure management. Brief explanation of the drawing

[0017] FIG. 1 is a diagram illustrating an example of a system that executes an investment strategy and distributes profits according to one embodiment. FIGS. 2 and 3 are flowcharts illustrating a method of operating a system for executing an investment strategy and distributing profits according to one embodiment. FIG. 4 is a diagram illustrating an example of a single user transaction scenario according to one embodiment. FIG. 5 is a diagram illustrating an example of a simultaneous transaction scenario for multiple users according to one embodiment. FIG. 6 is a block diagram illustrating the configuration of a system for executing an investment strategy and distributing profits according to one embodiment. Specific details for implementing the invention

[0018] The invention will be described in detail below by way of exemplary embodiments with reference to the attached drawings. The following embodiments are intended only to embody the invention and do not limit or restrict the scope of the invention. Anything that can be easily inferred by a person skilled in the art to which the invention pertains from the detailed description and embodiments shall be interpreted as falling within the scope of the invention.

[0019] Terms such as 'composed' or 'comprising' as used in this specification should not be interpreted as necessarily including all of the various components or steps, and should be interpreted as some of the components or steps may not be included, or additional components or steps may be included.

[0020] The terms used in this specification are described in their current, general form considering the functions mentioned herein; however, they may refer to various other terms depending on the intent of those skilled in the art, case law, the emergence of new technologies, etc. Therefore, the terms used in this specification should not be interpreted solely by their names, but should be interpreted based on the meaning of the terms and the overall content of this specification. Furthermore, singular expressions include a plural meaning unless the context clearly indicates a singular meaning.

[0021] The terms “above” and similar designations used in this specification (particularly in the claims) may indicate both singular and plural forms. Furthermore, unless there is a description explicitly specifying the order of the steps describing the method according to this specification, the described steps may be performed in a suitable order. The present invention is not limited by the order in which the described steps are described.

[0022] Phrases such as "in one embodiment" appearing in various places in this specification do not necessarily refer to the same embodiment.

[0023] Some embodiments of this specification may be represented by functional block configurations and various processing steps. Some or all of these functional blocks may be implemented by various numbers of hardware and / or software configurations that execute specific functions.

[0024] Furthermore, the connecting lines or connecting members between the components depicted in the drawings are merely illustrative of functional connections and / or physical or circuit connections. In the actual device, connections between components may be represented by various alternative or added functional connections, physical connections, or circuit connections.

[0025] The embodiments relate to a system for executing investment strategies and distributing profits using a Large Language Model (LLM) and a method of operating the same. Detailed descriptions of matters widely known to those skilled in the art to which the following embodiments belong are omitted. The present invention will be described in detail below with reference to the attached drawings.

[0026] Preferred embodiments of the present invention will be described in detail below with reference to the drawings.

[0027] FIG. 1 is a diagram illustrating an example of a system that executes an investment strategy and distributes profits according to one embodiment.

[0028] In one embodiment, the system may be connected to a user device, a market data API, an exchange API, etc. In particular, the system (100) and the user device may exchange messages with each other in natural language through a conversational interface.

[0029] The user device may be, but is not limited to, a smartphone, tablet PC, PC, smart TV, mobile phone, PDA (personal digital assistant), laptop, media player, e-book reader, digital broadcasting terminal, navigation system, kiosk, MP3 player, digital camera, home appliance, and other mobile or non-mobile computing devices. Additionally, the user device may be a wearable device such as a watch, glasses, hair band, and ring equipped with communication and data processing functions. However, it is not limited thereto, and the user device may include any type of device capable of transmitting and receiving information to and from other devices or systems to input investment strategies and receive profit distributions. For example, the user may submit investment strategies through a web browser or a mobile app, etc.

[0030] The system (100) may be a computing device such as a server or a micro server, but is not limited thereto, and may include any type of device capable of receiving investment strategies, executing trades, and transmitting and receiving information with other devices using a large-scale language model (LLM) to distribute profits.

[0031] As illustrated in Figure 1, the process of executing investment strategies and distributing profits in the system is explained step-by-step as follows.

[0032] 1. Strategy Submission: The user enters a natural language strategy statement through the platform interface. (e.g., Buy if Bitcoin RSI is below 30, and sell if it is above 70.)

[0033] 2. Strategy Interpretation: The input sentence is passed to an LLM-based strategy interpretation module, where it is parsed and converted into elements such as asset type, indicator conditions (RSI 30, 70, etc.), and order actions (buy / sell). At this time, the module generates a strategy using an internal rule language or script and may request additional information regarding ambiguous parts if necessary.

[0034] 3. Verification of Interpretation Result: The system displays the interpreted strategy to the user in the form of a natural language description. For example, it provides a confirmation message such as, “Interpreted Strategy: Buy Bitcoin at market price when the Bitcoin Price Index (RSI) falls below 30, and sell your holdings at market price when the RSI exceeds 70. Would you like to execute?” The user reviews whether the strategy was interpreted as intended and approves it. If necessary, the user may request a re-interpretation by modifying the strategy wording or adding additional conditions.

[0035] 4. Preparation of Virtual Account: After user approval, the user's virtual account is activated. The virtual account is prepared with pre-allocated real trading funds for testing (e.g., a deposit of a certain amount of cryptocurrency or fiat currency) and is set as the initial capital to be used for executing this strategy. With this, the user begins trading experiments on a virtual account basis.

[0036] 5. Automatic Strategy Execution: Real-time market data is monitored according to the interpreted strategy. For example, the value of the Bitcoin RSI indicator is continuously tracked. When a set condition is met (e.g., the moment the RSI falls below 30), the system (100) immediately executes a buy order through the main account. The order is received as a market order on the actual exchange and executed, and the result of the execution is recorded as a buy position in the user's virtual account. Subsequently, when the RSI exceeds 70, the system (100) executes a sell order in the opposite direction, and closes the position resulting from the execution and confirms the net profit or loss. The execution of these buy / sell transactions is entirely automated and proceeds without human intervention.

[0037] 6. Transaction and Account Management: During the execution of a strategy, changes in the balance and fluctuations in profit and loss resulting from the strategy are reflected in the user's virtual account in real time. For example, when a buy order is executed, Bitcoin assets and funds used are displayed in the virtual account, and after a sell, the balance that has increased or decreased compared to the initial funds is calculated. The system (100) can process transactions by multiple users simultaneously, and each transaction is managed separately on the main account through a unique user identification key. This allows for accurate differentiation of profit and loss and asset status by account, even if orders from multiple users are executed in one account.

[0038] 7. End of Test Period: The test operation period of the user strategy ends after it has been conducted for a predetermined schedule (e.g., one week or one month). At the end of the period, all open positions in the virtual account may be closed to finalize the profit or loss, or only the profit or loss already realized may be aggregated according to the strategy.

[0039] 8. Rate of Return Calculation: Calculate the rate of return or net profit by calculating the change in the final funds relative to the initial funds of the virtual account. For example, if the initial test funds are worth 1 million won and the final balance is 1.1 million won, a profit of 100,000 won (10% rate of return) has been generated. If a loss occurs, that amount is recorded as a loss of test funds in the system.

[0040] 9. Profit Distribution: When profit is generated, the profit is divided according to a pre-agreed distribution ratio. For example, in the case of a 50:50 fixed-rate distribution, 50,000 won of the example profit of 100,000 won is attributed to the user. The system (100) automatically settles 50,000 won into the user's virtual account and recovers the remaining 50,000 won into the system's profit account. This process is transparently recorded by the system, and the user is notified of the settlement details.

[0041] 10. Result Feedback and Termination: The user checks their final performance and profit distribution history. The system (100) provides feedback on the validity of the strategy by providing evaluation indicators for the user's strategy (e.g., Sharpe ratio, maximum drawdown, etc.) as needed. The user can withdraw the distributed profits or use them to execute the next strategy within the system. Meanwhile, the virtual account used in this test is kept in record, and when the user executes a new strategy, the same virtual account can be reused or initialized.

[0042] FIGS. 2 and 3 are flowcharts illustrating a method of operating a system for executing an investment strategy and distributing profits according to one embodiment.

[0043] In step S210, an investment strategy written in natural language can be received from a user device. In one embodiment, the system and the user device may communicate and exchange data through a predetermined network. In this case, the network includes a Local Area Network (LAN), a Wide Area Network (WAN), a Value Added Network (VAN), a mobile radio communication network, a satellite communication network, and combinations thereof, and is a data communication network in a comprehensive sense that enables each network constituent entity to communicate smoothly with one another, and may include wired internet, wireless internet, and mobile wireless communication networks.

[0044] For example, users can freely describe investment strategies in everyday language, such as, "Buy 50% of my assets when the Bitcoin RSI indicator falls below 30, and sell the entire amount when it rises above 70." Alternatively, users can upload sophisticated trading algorithm files written in Python or similar languages ​​to the system.

[0045] In step S220, the investment strategy can be converted into executable structured data by interpreting the investment strategy using a large-scale language model (LLM). The sentence of the investment strategy input in natural language can be parsed to extract key elements such as the asset (Bitcoin), condition (RSI < 30), action (buy), and parameter (50% of the asset), and converted into executable structured data (e.g., JSON format or internal script). In the case of an investment strategy uploaded as code, the code can be parsed to standardize it for the system's execution environment and extract trading commands.

[0046] In step S230, the interpreted investment strategy may be transmitted to the user device to request user confirmation. This serves as a safeguard to obtain clear confirmation from the user before executing a transaction. The system may present the strategy to the user in a human-readable language, such as: "Interpreted investment strategy: If the Bitcoin RSI indicator falls below 30, execute a market buy order with 50% of the virtual account balance. If the RSI exceeds 70, sell all held Bitcoin at market price. Would you like to execute this strategy?" The user must review whether it aligns with their intentions and give final approval before proceeding to the next step. This process has the advantageous effect of fundamentally preventing trading accidents caused by LLM interpretation errors or user misunderstandings.

[0047] In step S240, test funds may be allocated to the user by granting a virtual account linked to the main account. As a core fund management structure of this specification, the system may operate a single or a few main accounts (Master Accounts) holding actual funds on the exchange. When a user joins the platform, a unique identification key (USER_KEY) is issued, and a logical virtual account (Virtual Sub-account) corresponding to the identification key is created within the system. The platform allocates a small amount of actual test funds (e.g., $10) to each virtual account; although the test funds are physically in the main account, they may be treated as belonging to the virtual account for accounting purposes. All transactions and profits and losses are tracked and recorded at the virtual account level, ensuring that the assets of multiple users are clearly separated without mixing.

[0048] In step S250, if the user agrees to the execution of the interpreted investment strategy, a transaction can be automatically executed in this account when the conditions of the interpreted investment strategy are met. In one embodiment, market data is monitored in real time to check whether the conditions of the interpreted investment strategy are met, and if it is confirmed that the conditions of the interpreted investment strategy are met, a buy or sell order is executed in this account by linking with an exchange API, and the user's identifier can be tagged in the order. This allows identification of which user's strategy the order is based on. For example, the automatically executed transaction may be a buy / sell order for virtual assets such as Bitcoin or Ethereum, but is not limited thereto, and may also include transactions for stocks or bonds.

[0049] In step S260, the execution result of the transaction can be recorded in the virtual account. In one embodiment, the execution result of the transaction is immediately reflected in the virtual account (e.g., asset purchase, cash deduction, etc.), and the transaction can be executed within the limits of the test funds. Since all transactions are made only within the limits of the test funds allocated to the virtual account, risk can be strictly controlled.

[0050] In step S270, when the predetermined test period ends, the profit or loss of the virtual account can be determined. For example, the predetermined test period may be one week. The final performance settlement for each virtual account calculates the net profit or loss by comparing the final assets against the initial allocated funds.

[0051] In step S280, if profit is generated, the profit from the virtual account may be distributed to the user and the system at a pre-agreed ratio. For example, the pre-agreed ratio may be 50%. The user's share of the profit is paid to the user's account, and the user may withdraw it or use it for the next strategy test.

[0052] In another embodiment, if a loss occurs, the loss may be covered by test funds. This allows the user to be held not financially liable for any losses that may occur.

[0053] As illustrated in FIG. 3, the system includes an operation campaign setting function that allows an administrator to run trading tests or competitions with a specific purpose. For example, the administrator can provide a test environment with specific conditions to multiple users in bulk by pre-setting key parameters such as the following.

[0054] · Test Period: (e.g., 2025.07.13 ~ 2025.07.20)

[0055] · Amount Provided (Initial Capital): (e.g., 10 USD per person)

[0056] · Trading Type: Futures Trading

[0057] · Margin Mode and Leverage: Cross Margin, 10x

[0058] · Allowed order type: Market order

[0059] · Timeframe: Based on 1-minute chart data

[0060] · Position Constraint: Only long positions allowed

[0061] · Revenue sharing ratio: 50% of the revenue is distributed to users

[0062] Through these functions, the system goes beyond being a mere strategy testing tool and can flexibly plan and operate various forms of crowdsourcing events, such as hosting regular investment competitions and strategy contests tailored to specific market conditions.

[0063] FIG. 4 is a diagram illustrating an example of a single user transaction scenario according to one embodiment.

[0064] Referring to FIG. 4, User A was granted a virtual account with test funds allocated upon signing up as a member of the platform of the present invention. A has a virtual account with 100 USD allocated as initial test funds and entered a natural language strategy such as “Buy if RSI is less than 30.” The system analyzed this sentence using a Large Language Model (LLM) and structured the target asset as Bitcoin, the condition as price RSI < 30, and the buy weight as the entire holding fund. The user was presented with the interpretation result, “If the Bitcoin RSI indicator falls below 30, execute a market buy order for the entire virtual account fund,” and User A confirmed and approved this.

[0065] Subsequently, the system automatically monitored the RSI indicator in User A's virtual account. When the RSI indicator fell below 30, it immediately purchased Bitcoin worth 100 USD at market price. Although this order was executed from the system's main account, internal records processed it as if 100 USD had been used from A's virtual account and Bitcoin assets had been added.

[0066] After the test period ended, the system performed profit settlement for A's virtual account. Since a profit of approximately 5% was generated, 2.5 USD was allocated to User A and 2.5 USD was processed as the system's share, in accordance with the 50% fixed-rate policy. A's final virtual account balance was displayed as 102.5 USD, and the additional profit equivalent to 2.5 USD was paid out, allowing for withdrawal or a request to transfer it to a real account. User A can experience the entire process of executing automated trading solely through natural language strategies without complex coding or direct trading intervention, verifying the strategy with a small amount of real capital, and earning profits based on performance. Furthermore, while the system secures a portion of the profits generated through A's strategy, it obtains verification data that can be utilized as a promising strategy in the future.

[0067] FIG. 5 is a diagram illustrating an example of a simultaneous transaction scenario for multiple users according to one embodiment.

[0068] Referring to Fig. 5, users B and C can simultaneously execute different strategies using their respective virtual accounts. User B submitted an investment strategy in the stock market stating, "If a specific stock plummets by more than 10% during trading hours, buy to aim for a short-term rebound," while User C submitted an investment strategy in the cryptocurrency market stating, "If Bitcoin's daily volatility increases, day trading via algorithmic trading." The strategies of the two users were interpreted and verified through a Large Language Model (LLM) and executed separately. The platform's main account processes orders from both User B and User C, but each order is tagged with the unique identifiers of User B and User C to accurately separate and record the trading results in their respective virtual accounts. Consequently, if User B's strategy incurs a loss and User C's strategy generates a profit, the profit settlement module performs profit distribution only for User C's virtual account. For example, if User C earns a 10% profit on $1,000 in virtual funds, a profit of $100 is generated; $50 is paid to User C, and the remaining $50 is aggregated as profit for the system. Although User B incurred a loss, it was covered by depleting User B's test funds, so User B bears no financial burden. In this way, the system has the advantage of providing consistent service even in a multi-user environment by independently managing the strategies of multiple users simultaneously, efficiently operating the execution infrastructure through a single account, and settling profits and losses for each account individually.

[0069] FIG. 6 is a block diagram illustrating the configuration of a system for executing an investment strategy and distributing profits according to one embodiment.

[0070] As illustrated in FIG. 6, the system (100) of the present invention may include a control unit (130), a communication unit (150), and a memory (170). However, not all of the illustrated components are essential components. The system (100) may be implemented with more components than illustrated, or with fewer components. The above components will be examined in turn below.

[0071] The control unit (130) typically controls the overall operation of the system (100). The control unit (130) may be equipped with at least one processor. Depending on its function and role, the control unit (130) may include multiple processors or a single processor in an integrated form. A processor may primarily refer to a central processing unit (CPU), an application processor (AP), a graphics processing unit (GPU), etc. Additionally, the CPU, AP, or GPU may include one or more cores within it, and the CPU, AP, or GPU may operate using an operating voltage and a clock signal. However, while the CPU or AP is composed of a few cores optimized for serial processing, the GPU may be composed of thousands of smaller and more efficient cores designed for parallel processing.

[0072] For example, the control unit (130) can control the output unit (not shown), the communication unit (150), etc., by executing programs stored in the memory (170). The control unit (130) can control the communication unit (150) to transmit and receive information with external devices (e.g., a user device (not shown) and an external data source (not shown)).

[0073] The communication unit (150) may include one or more components that enable the system (100) to communicate with an external device. The external device may be a computing device such as the system (100), but is not limited thereto.

[0074] The memory (170) stores data that supports various functions of the control unit (130). The memory (170) can store a number of application programs (or applications) running on the control unit (130), data for the operation of the control unit (130), and instructions. At least some of these application programs may be downloaded from an external device or another server via wireless communication. Additionally, the application programs may be stored in the memory (170), installed on the control unit (130), and driven by a processor to perform the operation (or function) of the control unit (130).

[0075] The memory (170) may include at least one type of storage medium among flash memory type, hard disk type, SSD type (Solid State Disk type), SSD type (Silicon Disk Drive type), multimedia card micro type, card type memory (e.g., SD or XD memory, etc.), RAM (random access memory; RAM), SRAM (static random access memory), ROM (read-only memory; ROM), EEPROM (electrically erasable programmable read-only memory), PROM (programmable read-only memory), magnetic memory, magnetic disk, and optical disk. Additionally, the memory (170) may include web storage that performs storage functions over the internet.

[0076] A system (100) according to another embodiment of the present invention may be implemented to include a strategy submission interface, a strategy interpretation module, a user verification module, a virtual account management module, a transaction execution engine, a data storage module, and a profit settlement and distribution module. The aforementioned software modules may correspond to the hardware modules of FIG. 6, for example, the control unit (130) may include a strategy submission interface, a strategy interpretation module, a user verification module, a virtual account management module, a transaction execution engine, and a profit settlement and distribution module, and the memory (170) may include a data storage module.

[0077] The strategy submission interface is an interface that receives investment strategies from users in natural language. For example, users can describe strategies in everyday language, such as “buy when the Bitcoin RSI falls below 30 and sell when it rises above 70.” This interface is provided in the form of a web or mobile app, enhancing the convenience of strategy input for users.

[0078] The strategy interpretation module is an AI-based strategy interpretation engine, such as a Large Language Model (LLM). It parses natural language strategies entered by the user, extracts key parameters such as asset type, indicator conditions, and order type, and converts them into internally executable rules. For instance, it interprets the aforementioned investment strategy example and converts it into a structured strategy script or JSON format, such as “Asset: Bitcoin, Condition: Buy at market price when RSI < 30 / Sell at market price when RSI > 70.”

[0079] The User Confirmation Module is a component that obtains user confirmation regarding the trading strategy execution plan generated by the Strategy Interpretation Module. The system summarizes the LLM interpretation results into a human-readable format and presents them to the user. The user can review whether the strategy has been interpreted as intended and provide consent for modification or approval to ensure there is no ambiguity. This prevents malfunctions caused by incorrect interpretation and allows for the re-verification of the user's intent.

[0080] The virtual account management module is a component that creates and manages user-specific virtual accounts within the system's actual trading account (main account). Each user is assigned a unique identification key upon platform registration, and a sub-virtual account is opened within the main account in correspondence. A small amount of test funds is allocated to each virtual account, and transactions are configured to occur only within that amount. The virtual account management module tracks the transaction history and balances of multiple users separately by account; while the actual funds physically reside in the main account, they are accounted for in the accounting records as belonging to the user-specific virtual account.

[0081] The trade execution engine is responsible for executing actual trades based on strategy analysis results and user approval. It integrates with exchange APIs or proprietary trading servers to execute orders from real accounts, recording them as trades in the corresponding user's virtual account. The trade execution engine monitors conditions included in the strategy (e.g., RSI monitoring) in real time and automatically triggers buy or sell orders when the conditions are met. Order types can be executed as market orders or limit orders, and all trades are conducted within isolated limits for each virtual account, thereby controlling risk.

[0082] The data storage module is a component that stores the execution status, transaction history, and indicator data of each trading strategy, and monitors them in real time. Users can check their virtual account performance (e.g., current balance, positions, profit / loss, etc.) through dashboards. The data storage module also tracks the performance of strategies over a specific period (e.g., a test period) to provide the data necessary for subsequent profit settlement.

[0083] The profit settlement and distribution module is a component that calculates the net profit or loss of the virtual account and distributes the profits once the predetermined test period ends. The profit settlement and distribution module aggregates realized profits or losses for each account, and if a profit is generated, it calculates the user's share according to a predetermined distribution rate (e.g., 50%). The calculated profits are centrally managed by the system and paid into each user's virtual account or wallet. If a loss occurs, the user bears no separate financial burden, and the loss is processed within the funds allocated for the test.

[0084] The present invention described above can be modeled as computer-readable code on a medium on which a program is recorded. A computer-readable medium includes all types of recording devices in which data that can be read by a computer system is stored. Examples of computer-readable media include HDD (Hard Disk Drive), SSD (Solid State Disk), SSD (Silicon Disk Drive), ROM, RAM, CD-ROM, magnetic tape, floppy disk, optical data storage device, etc., and also include being modeled in the form of a carrier wave (e.g., transmission over the Internet).

[0085] Meanwhile, the configuration of the system (100) illustrated in FIG. 6 is an example, and each component of the system (100) may be integrated, added, or omitted according to the specifications of the system (100) being implemented. That is, as needed, two or more components may be combined into a single component, or a single component may be subdivided into two or more components. Furthermore, the functions performed by each component (or module) are intended to explain the examples, and the specific operations or devices thereof do not limit the scope of the present invention.

[0086] Meanwhile, the embodiments of the present invention described above can be written as a program executable on a computer and can be implemented on a general-purpose digital computer that operates the program using a computer-readable recording medium.

[0087] The above computer-readable recording media includes storage media such as magnetic storage media (e.g., ROM, floppy disk, hard disk, etc.) and optical reading media (e.g., CD-ROM, DVD, etc.).

[0088] Although embodiments of the present invention have been described above with reference to the attached drawings, those skilled in the art will understand that the present invention may be implemented in other specific forms without changing its technical concept or essential features. Therefore, the embodiments described above should be understood as illustrative in all respects and not restrictive. Explanation of the symbols

[0089] 100: System 130: Control unit 150: Communications Department 170: Memory

Claims

Claim 1 A method for executing an investment strategy and distributing profits using a Large Language Model (LLM), performed by a system comprising at least one processor, a communication unit, and memory, wherein the method is performed by the at least one processor executing instructions stored in the memory and receiving an investment strategy written in natural language from a user device; converting the investment strategy into executable structured data by interpreting the investment strategy using the Large Language Model (LLM); transmitting the interpreted investment strategy to the user device and requesting confirmation from the user; assigning a virtual account linked to the main account to the user and allocating test funds; if the user agrees to execute the interpreted investment strategy, and if the conditions of the interpreted investment strategy are satisfied, automatically executing a transaction in the main account; recording the result of the transaction execution in the virtual account; determining the profit or loss of the virtual account when a predetermined test period ends; and if the profit is generated, distributing the profit of the virtual account to the user and the system in a predetermined ratio. Claim 2 A method according to claim 1, wherein the test funds are physically in the main account but are treated as belonging to the virtual account for accounting purposes. Claim 3 A method according to claim 1, wherein the step of automatically executing a transaction in the above-mentioned account comprises: a step of checking whether the conditions of the interpreted investment strategy are satisfied while monitoring market data in real time; a step of executing a buy or sell order in the above-mentioned account by linking with an exchange API when it is confirmed that the conditions of the interpreted investment strategy are satisfied; and a step of tagging the user's identifier in the order. Claim 4 A method according to claim 1, wherein the result of executing the above transaction is immediately reflected in the above virtual account, and the above transaction is executed within the limit of the above test funds. Claim 5 A method according to claim 1, wherein if the above loss occurs, the above loss is treated as test funds. Claim 6 A method according to claim 1, wherein the test funds are 10 dollars, the predetermined test period is 1 week, and the predetermined rate is 50%. Claim 7 A computer-readable storage medium having a program recorded thereon for executing the method of any one of paragraphs 1 through 6 on a computer.

Images