Ai based social trading service providing system and method performing thereof
The social trading service system addresses volatile prices in virtual asset exchanges by estimating dealer performance and offering a trading bot to advise on optimal trading times, enhancing user transaction insights and reducing financial risks.
Patent Information
- Application Number
- KR1020240037318
- Authority / Receiving Office
- KR · KR
- Patent Type
- Patents
- Current Assignee / Owner
- Filing Date
- 2024-03-18
- Publication Date
- 2026-11-10
- Estimated Expiration
- 2043-07-31
AI Technical Summary
In virtual asset exchanges, consumers face significant financial risks due to volatile prices resulting from wash trading and fictitious transactions, as there are no legal requirements for maintaining stable quote prices, leading to potential losses for general buyers.
A social trading service system that estimates dealer performance using dealer-specific trading information, provides trading information to users, and offers a trading bot to learn and advise on optimal buying and selling times based on historical patterns.
Enables users to receive high-performing dealer information and trading advice, reducing financial risks by predicting profitable trading times and providing a subscription service for transaction insights.
Smart Images

Figure R1020240037318_ABST
Abstract
Description
Technology Field
[0001] The present invention relates to a system for providing a social trading service based on artificial intelligence and a method for implementing the same. More specifically, it relates to a system for providing a social trading service and a method for implementing the same that estimates performance by dealer using dealer-specific trading information, provides trading information of any dealer to a user, or manages the user's assets according to the trading of any dealer. Background Technology
[0003] If reasonable quotes are not presented on asset exchanges to stably respond to volatility, general buyers may suffer losses by purchasing assets at high prices and selling them at low prices. The Liquidity Providing system, first adopted in Europe, concerns the obligation to maintain quotes corresponding to recent trading prices to foster a healthy market environment on asset exchanges.
[0004] In the KOSPI and KOSDAQ markets, the LP system was introduced and is in operation in the late 2000s, so asset exchanges or securities-listed foundations bear the obligation to provide liquidity to maintain stable quotes even for stocks with relatively low trading volume, whereas virtual asset exchanges or virtual asset-listed foundations are not legally required to provide liquidity to maintain stable quotes.
[0005] Meanwhile, since virtual assets with higher trading volumes tend to rank higher on exchanges, foundations that list virtual assets often inflate trading volume through wash trading or fictitious transactions for marketing purposes. When prices skyrocket or plummet due to wash trading or fictitious transactions, it can result in significant losses for general consumers.
[0006] In other words, in coin exchanges that are relatively more volatile than assets and lack institutional safeguards, there is a risk that general consumers may suffer financial losses if quote prices are not maintained stably. Prior art literature
[0007] Published Patent Application No. 10-2021-0058178 (May 24, 2021) Registered Patent Application No. 10-2464199 (November 10, 2022) Published Patent Application No. 10-2023-0000411 (January 2, 2023) Published Patent Application No. 10-2023-0038375 (March 20, 2023) The problem to be solved
[0008] The present invention aims to provide a social trading service provision system and a method for implementing the same, which provides trading information of any dealer with good performance to a user by estimating the performance of each dealer using dealer-specific trading information.
[0009] In addition, the present invention aims to provide a social trading service provision system and a method for implementing the same, which enables a user to receive advice on the timing of buying and selling when trading by creating and providing a trading bot that learns the trading patterns of any dealer by learning the trading information of any dealer.
[0010] In addition, the present invention aims to provide a social trading service provision system and a method for implementing the same, which enables users to refer to trading information of high-performing dealers when trading by providing this information to users as a subscription service.
[0012] The objects of the present invention are not limited to those mentioned above, and other unmentioned objects and advantages of the present invention may be understood from the following description and will be more clearly understood by the embodiments of the present invention. Furthermore, it will be readily apparent that the objects and advantages of the present invention can be realized by the means and combinations thereof set forth in the claims. means of solving the problem
[0014] A social trading service providing server for achieving this purpose comprises: a dealer information collection unit that receives transaction information by asset dealer from multiple asset trading platform servers and stores it in a dealer information database; a dealer classification unit that identifies the period from the time of purchase to the time of sale based on dealer action information among the dealer's transaction information, determines the investment period group of the asset dealer according to the range of said period, determines the rate of return for each investment period group, and classifies the asset dealers grouped by investment period group into sub-groups again according to the rate of return; and a dealer-specific learning model generation unit that extracts the types of assets invested by the asset dealers classified into the sub-classification groups of the corresponding group by investment period group, displays the transaction prices of the asset types invested by the asset dealers on a graph, and generates a learning model that analyzes the changes in said transaction prices between the time of purchase and the time of sale to predict the point at which the asset dealer's profit amount increases as the dealer's selling point. The system may include a chatbot service provider that, upon receiving an asset investment consultation request message from a user terminal, extracts an investment period, rate of return, and asset type from the asset investment consultation request message, determines a dealer corresponding to the investment period, rate of return, and asset type, and, if the user requests consultation on the selling time after purchasing a specific asset, inputs the buying time and asset type into a learning model associated with the dealer to predict the selling time and provides it to the user terminal.
[0015] In one embodiment, a social trading service providing server may include a learning model generating unit that generates a learning model by determining a first possible selling time, which is a first possible selling price higher than the purchase price of the asset invested by the asset dealer, between the purchase time and the sale time of the asset, and determining a second possible selling time, which is a second possible selling price lower than the first possible selling price but higher than the purchase price, calculating a first average price by applying a weight corresponding to the market conditions of the first possible selling time to the first possible selling price and averaging it, calculating a second average price by applying a weight corresponding to the market conditions of the second possible selling time to the second possible selling price and averaging it, and predicting the time when the profit amount increases as the dealer's selling time by comparing the difference between the first average price and the second average price and the profit amount.
[0016] In addition, a social trading service provision method executed on a social trading service provision server for achieving this purpose may include the steps of: receiving transaction information by asset dealer from a plurality of asset trading platform servers and storing it in a dealer information database; determining the period from the time of purchase to the time of sale based on dealer action information among the transaction information by asset dealer, and determining an investment period group of asset dealers according to the range of said period; determining the rate of return by each investment period group and classifying the asset dealers grouped by each investment period group into sub-groups again according to the rate of return; analyzing the transaction information of asset dealers classified into sub-classification groups of the corresponding group by the investment period group to extract transaction patterns and then creating a learning model that predicts the time of purchase and the time of sale; when an asset investment consultation request message is received from a user terminal, extracting the investment period, rate of return, asset type, etc. from the asset investment consultation request message and then determining a dealer corresponding to the investment period, rate of return, and asset type; and when a user requests consultation on the time of sale after purchasing a specific asset, inputting the time of purchase and asset type into a learning model associated with the dealer to predict the time of sale and providing it to the user terminal. Effects of the invention
[0018] According to the present invention as described above, there is an advantage in that transaction information of a dealer with good performance can be provided to the user by estimating the performance of each dealer using transaction information by dealer.
[0019] In addition, according to the present invention, there is an advantage in that a user can receive advice on the timing of buying and selling when trading by creating and providing a trading bot that learns the trading patterns of a dealer by learning the trading information of a dealer with good performance.
[0020] In addition, according to the present invention, there is an advantage in that transaction information of high-performing dealers is provided to the user as a subscription service, allowing the user to refer to it when conducting transactions with the company. Brief explanation of the drawing
[0022] FIG. 1 is a network configuration diagram for explaining a social trading service provision system according to one embodiment of the present invention. FIG. 2 is a block diagram illustrating the internal structure of a social trading service providing server according to the present invention. FIG. 3 is a flowchart illustrating an embodiment of a method for providing a social trading service according to the present invention. FIG. 4 is a flowchart illustrating another embodiment of a method for providing a social trading service according to the present invention. Specific details for implementing the invention
[0023] The aforementioned objectives, features, and advantages are described in detail below with reference to the attached drawings, thereby enabling those skilled in the art to easily implement the technical concept of the present invention. In describing the present invention, detailed descriptions of known technologies related to the present invention are omitted if it is determined that such descriptions would unnecessarily obscure the essence of the invention. Hereinafter, preferred embodiments according to the present invention will be described in detail with reference to the attached drawings. In the drawings, the same reference numerals are used to indicate the same or similar components.
[0024] FIG. 1 is a network configuration diagram for explaining a social trading provision system according to one embodiment of the present invention.
[0025] Referring to FIG. 1, the social trading providing system includes an asset trading platform server (100_1 to 100_N), a social trading service providing server (200), and a user terminal (300).
[0026] Multiple asset trading platform servers (100_1 to 100_N) provide a platform for mediating the trading of assets listed on an exchange and can mediate the trading of assets in response to a purchase or sale request from a user terminal (300).
[0027] Multiple asset trading platform servers (100_1 to 100_N) provide various types of overall services for investors, including not only services related to asset trading, but also payment of bills such as loans, credit card bills, and communication bills, reservation services for hotel rooms, game tickets, itinerary tours, and restaurant reservations, and donation services for transferring donations to charity accounts.
[0028] Multiple asset trading platform servers (100_1 to 100_N) provide an account registration request message to a user terminal (300) to register an investor's account (A), and when they receive investor information in response to the account registration request message from the user terminal (300), they create an account using the investor information.
[0029] After that, multiple asset trading platform servers (100_1 to 100_N) register an account with the investor's real name. To this end, the asset trading platform servers (100_1 to 100_N) verify the investor's identity via email or SMS message.
[0030] The procedure for verifying the investor's identity may follow conventional methods related to user authentication. Furthermore, according to an embodiment of the present invention, a plurality of asset trading platform servers (100_1 to 100_N) may authenticate the user's identification card and / or user identification card through the user terminal (300).
[0031] For example, multiple asset trading platform servers (100_1 to 100_N) can perform user authentication using the user identification code when they receive the user identification code by scanning an ID card and / or a user identification card through a user terminal (300) held by the user.
[0032] The above-mentioned user identification card has a transparent printing layer formed thereon, and a user identification code may be formed in a pattern form on the transparent printing layer. In this case, a user identification code value may be formed in a pattern form on the transparent printing layer using transparent ink.
[0033] Accordingly, the user terminal (300) can scan a user identification card and generate a user identification code using light information reflected from the user identification card, and provide it to a plurality of asset trading platform servers (100_1 to 100_N).
[0034] Multiple asset trading platform servers (100_1 to 100_N) actively connect to a trading financial institution, e.g., a bank, to verify and confirm the identity of the investor. After the identity is verified, the asset trading platform servers (100_1 to 100_N) will take the financial institution account as the verified valid account.
[0035] Preferably, the verified financial institution account is considered to be the sole financial institution account of the asset trading platform system (100). After the verification of the financial institution account, the asset trading platform server (100_1 to 100_N) will establish a connection between the financial institution account and the registered account so that currency can be transferred from the financial institution account to the registered account.
[0036] Therefore, the investor can use money transferred to an account registered to perform general asset trading, personal asset trading, or both general asset trading and personal asset trading by using a trading execution module connected to the asset trading platform server (100_1~100_N).
[0037] When an asset trading platform server (100_1~100_N) receives a purchase message from an investor or an asset dealer authorized by the investor, it proceeds with the purchase of the corresponding asset and then stores the asset's stock, quantity, purchase price, market, and investment type (i.e., individual investment, agent investment, etc.) in the investor database.
[0038] Subsequently, when the asset trading platform server (100_1~100_N) receives a sell message from an investor or an asset dealer authorized by the investor, if the item of the asset requested for sale exists in the investor database, it proceeds with the sale of the corresponding asset and then saves the item, quantity, purchase price, sale price, market, and investment type (i.e., individual investment, agent investment, etc.) of the asset in the investor database.
[0039] The social trading service providing server (200) is a server that mediates to enable consultation with users by receiving and analyzing dealer trading information from each of the multiple asset trading platform servers (100_1 to 100_N) and generating a learning model that predicts buying and selling points.
[0040] The social trading service provider server (200) enables investors to discuss with asset dealers in a convenient way and to perform asset trading through text messages or real-time video calls.
[0041] For example, the social trading service provider server (200) can automatically output all of the investor's asset trading records recorded this month, or instead output specific asset trading of this year at the investor's manual request.
[0042] The social trading service provider server (200) executes a liquidity supply program to receive asset dealer-specific trading information (i.e., asset type, market conditions, dealer action information, etc.) from the asset trading platform servers (100_1 to 100_N).
[0043] First, the social trading service provider server (200) determines the investment period group of an asset dealer based on the period from the time of purchase to the time of sale, based on the dealer action information among the asset dealer's transaction information. At this time, the investment period group may include short-term, medium-term, medium-long-term, long-term, etc.
[0044] In one embodiment, the social trading service providing server (200) can determine the investment period group of an asset dealer based on the dealer action information among the asset dealer's trading information, and whether the period from the time of purchase to the time of sale belongs to which investment period range.
[0045] Additionally, the social trading service provider server (200) determines the rate of return by comparing the market price at the time of purchase and the market price at the time of sale for each investment period group, and classifies the asset dealers grouped by investment period group into subgroups according to the rate of return.
[0046] The reason for this is to classify asset dealers based on their trading patterns and then train them on how to determine the timing of purchases and sales.
[0047] First, the social trading service provider server (200) extracts the types of assets invested by asset dealers classified into sub-groups of the corresponding group for each investment period group.
[0048] After that, the social trading service provider server (200) displays the trading price of the asset type invested in by the asset dealer on a graph and analyzes the change in the curve between the time of purchase and the time of sale.
[0049] In one embodiment, the social trading service providing server (200) stores the first sellable price when the market price rises from the time of purchase and the first sellable time is determined, and then determines the second sellable time when the market price falls and is lower than the first sellable time but higher than the purchase price.
[0050] After that, the social trading service provider server (200) calculates a first average price by applying a weight corresponding to the market condition to the price at the first selling point and averaging it, and calculates a second average price by applying a weight corresponding to the market condition to the price at the second selling point and averaging it.
[0051] In conclusion, the social trading service provider server (200) can generate a learning model by calculating the difference price between the first average price and the second average price, and by comparing the difference price and the profit amount to learn the point where the profit amount increases as the dealer sell prediction point.
[0052] Additionally, the social trading service provider server (200) displays the trading price of the type of asset invested in by the asset dealer on a graph and analyzes the change in the curve of the trading price graph over a specific period from before the time of purchase.
[0053] In one embodiment, the social trading service providing server (200) determines a first possible purchase time by the market price falling on a trading price graph for a specific period prior to the purchase time, and then stores the first possible purchase price, and then determines a second possible purchase time when the market price rises and is higher than a specific price above the first possible purchase price.
[0054] After that, the social trading service provider server (200) calculates a first average price by applying a weight corresponding to the market condition to the price at the first purchase-possible time and averaging it, and calculates a second average price by applying a weight corresponding to the market condition to the price at the second purchase-possible time and averaging it.
[0055] In conclusion, the social trading service provider server (200) can generate a learning model by calculating the difference price between the first average price and the second average price, and by comparing the difference price and the actual purchase amount to learn the point at which the difference price decreases as the dealer purchase prediction point.
[0056] Additionally, when the social trading service provider server (200) receives an asset investment consultation request message from a user terminal (300), it determines a dealer that matches the user based on the asset investment consultation request message. That is, the social trading service provider server (200) extracts the investment period, rate of return, and asset type from the asset investment consultation request message, and then determines a dealer corresponding to the investment period, rate of return, and asset type.
[0057] Then, the social trading service provider server (200) uses a learning model associated with a dealer to predict and provide at least one of the user's buying time and selling time.
[0058] In one embodiment, when a user requests advice on the selling point after purchasing a specific asset, the social trading service providing server (200) inputs the buying point and the type of asset into a learning model associated with a dealer to predict the selling point and then provides it to the user terminal (300).
[0059] In another embodiment, when a user requests consultation on the timing of purchasing a specific asset, the social trading service providing server (200) inputs the type of asset into a learning model associated with a dealer to predict the timing of the purchase and then provides it to the user terminal (300).
[0060] When the social trading service provider server (200) receives an account automatic operation request message from the user terminal (300), it determines a dealer matched with the user based on an asset investment consultation request message. That is, the social trading service provider server (200) extracts the investment period, rate of return, and asset type from the asset investment consultation request message, and then determines a dealer corresponding to the investment period, rate of return, and asset type.
[0061] Then, the social trading service provider server (200) uses a learning model associated with a dealer to predict at least one of the user's buying time and selling time and automatically executes buying and selling.
[0062] In one embodiment, when a user requests consultation on the timing of purchasing a specific asset, the social trading service provider server (200) can input the type of asset into a learning model associated with a dealer to predict the timing of purchase and then automatically execute the purchase at the time of purchase.
[0063] In another embodiment, the social trading service provider server (200) can input the buying time and asset type into a learning model associated with a dealer to predict the selling time, and then automatically proceed with the selling at the selling time.
[0065] FIG. 2 is a block diagram illustrating the internal structure of a social trading service providing server according to the present invention.
[0066] Referring to FIG. 2, the social trading service providing server (200) includes a dealer information collection unit (210), a dealer information database (220), a dealer classification unit (230), a dealer-specific learning model generation unit (240), a chatbot service providing unit (250), an asset management service providing unit (260), and a control unit (270).
[0067] The dealer information collection unit (210) executes a liquidity supply program to receive asset dealer-specific trading information (i.e., asset type, market conditions, dealer action information, etc.) from asset trading platform servers (100_1 to 100_N) and stores it in the dealer information database (220).
[0068] The dealer classification unit (230) determines the investment period group of the asset dealer based on the period from the time of purchase to the time of sale, based on the dealer action information among the transaction information of the asset dealer. At this time, the investment period group may include short-term, medium-term, medium-long-term, long-term, etc.
[0069] In one embodiment, the dealer classification unit (230) can determine the investment period group of an asset dealer based on the dealer action information among the asset dealer's transaction information, and whether the period from the time of purchase to the time of sale belongs to which investment period range.
[0070] Additionally, the dealer classification unit (230) determines the rate of return by comparing the market price at the time of purchase and the market price at the time of sale for each investment period group, and classifies the asset dealers grouped by investment period group into subgroups based on the rate of return.
[0071] The reason for this is to classify asset dealers based on their trading patterns and then train them on how to determine the timing of purchases and sales.
[0072] The dealer-specific learning model generation unit (240) extracts the types of assets invested by asset dealers classified into sub-categories of the corresponding group for each investment period group from the dealer information database (220).
[0073] After that, the dealer-specific learning model generation unit (240) displays the transaction price of the asset type invested by the asset dealer on a graph and analyzes the change in the curve between the time of purchase and the time of sale.
[0074] In one embodiment, the dealer-specific learning model generation unit (240) determines a first sellable time when the market price rises from the time of purchase and a first sellable time is determined, and then stores the first sellable price, and then determines a second sellable time when the market price falls and is lower than the first sellable time but higher than the purchase price.
[0075] After that, the dealer-specific learning model generation unit (240) calculates a first average price by applying a weight corresponding to the market condition to the price at the first selling time and averaging it, and calculates a second average price by applying a weight corresponding to the market condition to the price at the second selling time and averaging it.
[0076] In conclusion, the dealer-specific learning model generation unit (240) can generate a learning model by calculating the difference price between the first average price and the second average price, and by comparing the difference price and the profit amount to learn the point where the profit amount increases as the dealer selling prediction point.
[0077] Additionally, the dealer-specific learning model generation unit (240) displays the transaction price of the asset type invested by the asset dealer on a graph and analyzes the change in the curve of the transaction price graph over a specific period from before the time of purchase.
[0078] In one embodiment, the dealer-specific learning model generation unit (240) determines the first possible purchase time by the market price falling on a transaction price graph for a specific period prior to the purchase time, and then stores the first possible purchase price, and then determines the second possible purchase time by the market price rising and being higher than the first possible purchase price.
[0079] After that, the dealer-specific learning model generation unit (240) calculates a first average price by applying a weight corresponding to the market condition to the price at the first purchase-possible time and averaging it, and calculates a second average price by applying a weight corresponding to the market condition to the price at the second purchase-possible time and averaging it.
[0080] In conclusion, the dealer-specific learning model generation unit (240) can generate a learning model by calculating the difference price between the first average price and the second average price, and by comparing the difference price and the actual purchase amount to learn the point in time when the difference price decreases as the dealer purchase prediction point.
[0081] When the chatbot service provider (250) receives an asset investment consultation request message from a user terminal (300), it determines a dealer that matches the user based on the asset investment consultation request message. That is, the chatbot service provider (250) extracts the investment period, rate of return, and asset type from the asset investment consultation request message and then determines a dealer corresponding to the investment period, rate of return, and asset type.
[0082] Then, the chatbot service provider (250) uses a learning model associated with a dealer to predict and provide at least one of the user's buying time and selling time.
[0083] In one embodiment, when a user requests consultation on the time of sale after purchasing a specific asset, the chatbot service provider (250) inputs the time of purchase and the type of asset into a learning model associated with a dealer to predict the time of sale and then provides it to the user terminal (300).
[0084] In another embodiment, when a user requests consultation on the timing of purchasing a specific asset, the chatbot service provider (250) inputs the type of asset into a learning model associated with a dealer to predict the timing of purchase and then provides it to the user terminal (300).
[0085] When the asset management service provider (260) receives an account automatic management request message from the user terminal (300), it determines a dealer that matches the user based on the asset investment consultation request message. That is, the asset management service provider (260) extracts the investment period, rate of return, and asset type from the asset investment consultation request message, and then determines a dealer corresponding to the investment period, rate of return, and asset type.
[0086] Then, the asset management service provider (260) uses a learning model associated with a dealer to predict at least one of the user's buying time and selling time and automatically executes buying and selling.
[0087] In one embodiment, when a user requests consultation on the timing of purchasing a specific asset, the asset management service provider (260) can input the type of asset into a learning model associated with a dealer to predict the timing of purchase and then automatically execute the purchase at the time of purchase.
[0088] In another embodiment, the asset management service provider (260) can input the buying time and asset type into a learning model associated with a dealer to predict the selling time, and then automatically proceed with the sale at the selling time.
[0090] FIG. 3 is a flowchart illustrating an embodiment of a method for providing a social trading service according to the present invention.
[0091] Referring to FIG. 3, the social trading service providing server (200) receives trading information for each asset dealer from a plurality of asset trading platform servers and stores it in a dealer information database (step S310).
[0092] The social trading service provider server (200) determines the investment period group of asset dealers based on the period from the time of purchase to the time of sale, based on the dealer action information among the transaction information of asset dealers (step S320).
[0093] The social trading service provider server (200) determines the rate of return by comparing the market price at the time of purchase and the market price at the time of sale for each investment period group, and classifies the asset dealers grouped by investment period group into subgroups according to the rate of return (step S330).
[0094] The social trading service provider server (200) analyzes the trading information of asset dealers classified into sub-groups of the corresponding group for each investment period group, extracts trading patterns, and then creates a learning model that predicts the buying and selling points (step S340).
[0095] First, the social trading service provider server (200) extracts the types of assets invested by asset dealers classified into sub-groups of the corresponding group for each investment period group.
[0096] After that, the social trading service provider server (200) displays the trading price of the asset type invested in by the asset dealer on a graph and analyzes the change in the curve between the time of purchase and the time of sale.
[0097] In one embodiment, the social trading service providing server (200) stores the first sellable price when the market price rises from the time of purchase and the first sellable time is determined, and then determines the second sellable time when the market price falls and is lower than the first sellable time but higher than the purchase price.
[0098] After that, the social trading service provider server (200) calculates a first average price by applying a weight corresponding to the market condition to the price at the first selling point and averaging it, and calculates a second average price by applying a weight corresponding to the market condition to the price at the second selling point and averaging it.
[0099] In conclusion, the social trading service provider server (200) can generate a learning model by calculating the difference price between the first average price and the second average price, and by comparing the difference price and the profit amount to learn the point where the profit amount increases as the dealer sell prediction point.
[0100] Additionally, the social trading service provider server (200) displays the trading price of the type of asset invested in by the asset dealer on a graph and analyzes the change in the curve of the trading price graph over a specific period from before the time of purchase.
[0101] In one embodiment, the social trading service providing server (200) determines a first possible purchase time by the market price falling on a trading price graph for a specific period prior to the purchase time, and then stores the first possible purchase price, and then determines a second possible purchase time when the market price rises and is higher than a specific price above the first possible purchase price.
[0102] After that, the social trading service provider server (200) calculates a first average price by applying a weight corresponding to the market condition to the price at the first purchase-possible time and averaging it, and calculates a second average price by applying a weight corresponding to the market condition to the price at the second purchase-possible time and averaging it.
[0103] In conclusion, the social trading service provider server (200) can generate a learning model by calculating the difference price between the first average price and the second average price, and by comparing the difference price and the actual purchase amount to learn the point at which the difference price decreases as the dealer purchase prediction point.
[0105] FIG. 4 is a flowchart illustrating another embodiment of a method for providing a social trading service according to the present invention.
[0106] Referring to FIG. 4, when the social trading service providing server (200) receives an account automatic operation request message from a user terminal (300) (step S410), it determines a dealer matched with the user based on an asset investment consultation request message (step S420).
[0107] That is, the social trading service provider server (200) extracts the investment period, rate of return, and asset type from the asset investment consultation request message, and then determines a dealer corresponding to the investment period, rate of return, and asset type.
[0108] Then, the social trading service provider server (200) predicts at least one of the user's buy time and sell time using a learning model associated with a dealer and provides the buy time and sell time to the user terminal (300) (step S430).
[0110] Although the present invention has been described by limited embodiments and drawings, it is not limited to the above embodiments, and various modifications and variations are possible from this description by those skilled in the art. Accordingly, the concept of the present invention should be understood only by the claims set forth below, and all equivalent or analogous variations thereof shall be considered to be within the scope of the concept of the present invention. Explanation of the symbols
[0112] 100_1~100_N: Asset trading platform server, 200: Social trading service provider server, 210: Dealer Information Collection Department, 220: Dealer Information Database, 230: Dealer Classification Department, 240: Dealer-specific learning model generation unit, 250: Chatbot Service Provider, 260: Control unit 300: User terminal
Claims
Claim 1 A dealer information collection unit that receives asset dealer-specific trading information, including asset type, market conditions, and dealer action information, from multiple asset trading platform servers and stores it in a database; a dealer classification unit that identifies the period from the time of purchase to the time of sale based on dealer action information among the dealer's trading information, determines the asset dealer's investment period group as one of short-term, medium-term, medium-long-term, or long-term according to the range of said period, determines the rate of return by comparing the market price at the time of purchase and the market price at the time of sale for each investment period group, and classifies the asset dealers grouped by investment period group into sub-groups once again according to the rate of return; and a dealer-specific learning model generation unit that extracts the asset type invested by the asset dealer classified into the sub-classification group of the corresponding group for each investment period group, expresses the transaction price of the asset type invested by the asset dealer on a graph, and generates a learning model that predicts the point at which the asset dealer's profit amount increases as the dealer's selling point by analyzing the change in the curve between the time of purchase and the time of sale. A social trading service providing server characterized by including a chatbot service providing unit that, upon receiving an asset investment consultation request message from a user terminal, extracts an investment period, a rate of return, and an asset type from the asset investment consultation request message, determines a dealer corresponding to the investment period, rate of return, and asset type, and predicts at least one of the user's purchase time and sale time using a learning model associated with the determined dealer and provides it to the user terminal, wherein if the user requests consultation on the sale time after purchasing a specific asset, inputs the purchase time and asset type into the learning model associated with the dealer to predict the sale time and provides it to the user terminal. Claim 2 A social trading service providing server, wherein the dealer-specific learning model generating unit determines a first possible selling time at a first possible selling price higher than the purchase price of the asset between the purchase time and the sale time of the asset invested by the asset dealer, determines a second possible selling time at a second possible selling price lower than the first possible selling price but higher than the purchase price, calculates a first average price by applying a weight corresponding to the market conditions at the first possible selling time to the first possible selling price and averaging it, calculates a second average price by applying a weight corresponding to the market conditions at the second possible selling time to the second possible selling price and averaging it, and generates a learning model that predicts the point in time when the profit amount increases as the dealer's selling time by comparing the difference between the first average price and the second average price with the profit amount. Claim 3 A method for providing a social trading service executed on a server providing a social trading service comprises: receiving asset dealer-specific trading information, including asset type, market conditions, and dealer action information, from a plurality of asset trading platform servers and storing it in a dealer information database; determining the period from the time of purchase to the time of sale based on the dealer action information among the asset dealer-specific trading information, and determining the investment period group of the asset dealer as one of short-term, medium-term, medium-long-term, or long-term according to the range of the said period; determining the rate of return by comparing the market price at the time of purchase and the market price at the time of sale for each investment period group, and classifying the asset dealers grouped by each investment period group into subgroups based on the rate of return; extracting the asset type invested by the asset dealer classified into the sub-classification group of the corresponding group for each investment period group, representing the transaction price of the asset type invested by the asset dealer on a graph, and generating a learning model that predicts the point at which the asset dealer's profit amount increases as the dealer's selling point by analyzing the change in the curve between the time of purchase and the time of sale. A method for providing a social trading service characterized by comprising: a step of receiving an asset investment consultation request message from a user terminal, extracting an investment period, a rate of return, and an asset type from the asset investment consultation request message, and determining a dealer corresponding to the investment period, rate of return, and asset type; and a step of predicting at least one of a user's buying time and selling time using a learning model associated with the determined dealer and providing it to the user terminal, wherein if the user requests consultation on the selling time after purchasing a specific asset, the buying time and asset type are input into the learning model associated with the dealer to predict the selling time and provide it to the user terminal.
Citation Information
Patent Citations
Public announcement service platform and application of professional grading system for investor expertise who recommend stocks
KR1020210058178A
Server, method and computer program for providing investment guide
KR1020230000411A
Value-sharing matching system and how it matches between experts and demanders
KR1020230038375A
Method for providing stock investment leading service and system thereof
KR102464199B1
Social trading service providing system and method performing thereof
KR102650137B1
