system

Abstract

We provide the system. [Solution] A means for collecting information on companies before they go public, A means of analyzing collected information and evaluating a company's growth potential, A means of simulating the stock price trends of a company before its IPO based on the analysis results, A means of constructing an investment trust based on simulated stock price trends, A system that includes means for selling constructed investment trusts.

Description

Technical Field

[0004] , , , ,

[0005] , , , ,

[0001] The technology of the present disclosure relates to a system.

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] It is very difficult for ordinary investors to access the stocks of pre-listing companies or specific investment opportunities. As a result, there is a problem that investment in companies with high growth potential is limited and the diversification of investment portfolios is restricted. The purpose of the present invention is to eliminate such restrictions on investment opportunities and enable ordinary investors to invest in pre-listing companies, thereby expanding the options for investment.

Means for Solving the Problems

[0005] The system of this invention collects information on companies before they go public, analyzes this information to evaluate their growth potential, and then simulates the stock price trends of the pre-listing companies based on the analysis results. Based on these simulated stock price trends, it constructs an investment trust. This investment trust is then sold to general investors. By performing analysis and simulation using natural language processing technology and machine learning algorithms, the system provides investment opportunities in companies with high growth potential. Furthermore, by incorporating a mechanism to regularly collect new data and update the performance of the investment trust, it is possible to always provide an investment trust based on the latest information. In addition, the system aims to enhance convenience by providing users with a means to purchase investment trusts online.

[0006] A "pre-listing company" refers to a company that is in the stage before its shares are publicly offered on the market.

[0007] "Means of collecting information" refers to methods of obtaining publicly available information about pre-listing companies through web crawling technology and database access.

[0008] "Means of analyzing information" refers to the techniques and methods used to process collected data and extract useful insights and patterns.

[0009] "Methods for evaluating growth potential" refer to methods of using indicators and algorithms to estimate a company's future growth potential.

[0010] "Methods for simulating stock price trends" refer to technologies and algorithms for modeling and predicting future fluctuations in stock prices.

[0011] "Methods for constructing an investment trust" refers to the method of creating an investment fund by combining various assets and stocks based on specific investment objectives and risk tolerance.

[0012] "Means of selling investment trusts" refers to the channels, methods, or systems that enable general investors to purchase investment trusts.

[0013] "Natural language processing technology" refers to techniques that enable computers to understand human language, and includes text analysis and sentiment analysis.

[0014] A "machine learning algorithm" refers to a mathematical method used to learn patterns from data and perform predictions and classifications.

[0015] The "data collection process" refers to a series of steps and methods for systematically gathering information.

[0016] "Rebalancing the portfolio based on analysis results" refers to actions taken to review and optimize the composition of investment funds based on the latest analytical data.

[0017] "Online purchasing methods" refer to the technologies and systems that enable users to purchase goods via the internet.

[0018] "Growth indicators" are metrics that show a company's growth, and include, for example, sales growth rate, increase in the number of employees, and technological progress. [Brief explanation of the drawing]

[0019] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [[ID=I6]] [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

MODE FOR CARRYING OUT THE INVENTION

[0020] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0021] First, the language used in the following description will be explained.

[0022] In the following embodiments, the signed processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Furthermore, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), and APU (Accelerated Processing Unit).

[0023] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0024] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0025] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0026] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0027] [First Embodiment]

[0028] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0029] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0030] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0031] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0032] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0033] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0034] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0035] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0036] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0037] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0038] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0039] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0040] The system of the present invention collects information on companies before they go public, analyzes that information, and evaluates the growth potential of the companies. Next, it includes a process of simulating stock price trends based on the evaluation results, and then constructing and selling investment trusts based on those simulations. Specific embodiments for implementing the present invention are described in detail below.

[0041] Explain the program's processing in natural language.

[0042] Data collection

[0043] The server collects information about pre-IPO companies from the internet. To do this, it uses web crawling technology and APIs (Application Programming Interfaces) to retrieve data such as news articles, company press releases, and industry reports.

[0044] For example, a server might collect information from a specific news portal stating that "Company X has raised funds."

[0045] Data Analysis

[0046] The server analyzes the collected information using natural language processing (NLP) techniques. Specifically, it tokenizes text data and extracts keywords and phrases.

[0047] Next, sentiment analysis is performed to determine whether the news is positive or negative. Additionally, company growth indicators (such as new customer numbers, funding raised, and technological progress) are calculated and scored.

[0048] For example, the server analyzes information such as "Company X's number of employees increased by 30%" and evaluates this as a positive indicator of growth potential.

[0049] Modeling and Simulation

[0050] The server simulates the stock price trends of pre-IPO companies based on the analysis results. To do this, it uses machine learning algorithms to create a stock price prediction model and trains it using historical data.

[0051] The simulation generates prediction results for multiple scenarios (optimistic, neutral, and pessimistic).

[0052] For example, the server might output a result stating, "Company X is projected to see a 20% increase in its stock price over the next six months."

[0053] Constructing an investment trust

[0054] Based on the simulation results, the server constructs an investment trust by combining multiple pre-IPO companies and investment products that can be traded on the market.

[0055] Determine the components of the investment trust (for example, the shares of company X and company Y) and their weights (for example, the proportion of shares of each company).

[0056] For example, the server "creates a portfolio including companies X, Y, and Z, and constructs it as investment trust ABC."

[0057] Sales of investment trusts

[0058] The terminal (the system of a financial institution or securities company engaged in the sale of investment trusts) provides product descriptions to general investors and sells them based on investment trust information provided from the server.

[0059] Users can purchase investment trust ABC through an online platform. For example, a user can search for investment trust ABC from their home computer and submit a purchase request.

[0060] Specific example

[0061] Example 1: Information gathering and analysis of startup company X

[0062] 1. The server collects the latest news about company X (e.g., funding amounts, employee growth, technological progress).

[0063] 2. The server uses natural language processing technology to analyze the news and evaluate the growth potential of company X (e.g., expansion plans through fundraising).

[0064] Example 2: Construction and sales of investment trust ABC

[0065] 1. The server constructs investment trust ABC by combining companies X, Y, and Z based on the simulation results.

[0066] 2. The terminal begins selling investment trust ABC to general investors, and users submit purchase applications online.

[0067] In this way, the present invention can provide general investors with investment opportunities in companies before they go public, thereby increasing investment diversity.

[0068] The following describes the processing flow.

[0069] Step 1:

[0070] The server collects information about pre-IPO companies from the internet. To do this, the server uses web crawling technology to retrieve data such as news articles, company press releases, and industry reports.

[0071] Specifically, the system accesses specific news portals and official company websites and automatically downloads relevant information. The retrieved data is then stored in a database, categorized into fields such as news title, body text, publication date, and company name.

[0072] Step 2:

[0073] The server analyzes the collected information using natural language processing (NLP) techniques. First, it tokenizes the text data and extracts important keywords and phrases.

[0074] Next, the server performs sentiment analysis to determine whether the news content is positive or negative. Furthermore, it calculates the company's growth indicators (such as the number of new customers, the amount of funding raised, and the progress of technology) and scores the results based on those.

[0075] Specifically, the server analyzes information such as "Company X's employee count has increased by 30%" and evaluates this as a positive indicator of growth potential.

[0076] Step 3:

[0077] The server simulates the stock price trends of pre-IPO companies based on the analysis results. To do this, it uses machine learning algorithms to create a stock price prediction model and trains it using historical data.

[0078] The simulation generates prediction results for multiple scenarios (optimistic, neutral, pessimistic). Specifically, the server outputs a result such as "Company X's stock price is projected to increase by 20% over the next six months."

[0079] Step 4:

[0080] The server constructs investment trusts based on the simulation results. First, it determines the combination of pre-listing companies and investment products available on the market.

[0081] Next, the server determines the components of the portfolio (for example, the shares of company X and company Y) and their weights (for example, the proportion of shares of each company). Specifically, the server "creates a portfolio containing companies X, Y, and Z, and constructs it as investment trust ABC."

[0082] Step 5:

[0083] The terminal receives investment trust information from the server and provides it to individual investors. The terminal generates an investment trust prospectus and presents it to the user.

[0084] Next, the user purchases investment trust ABC through an online platform. Specifically, the user searches for investment trust ABC from their home computer and submits a purchase request.

[0085] Step 6:

[0086] The server periodically collects new data to update the contents of the investment trust. The server collects the latest company information and analyzes it using natural language processing technology.

[0087] Afterward, the AI ​​model is retrained to reflect new data and market trends, and the simulation results are updated. Specifically, the server analyzes new information such as "Company X has announced a new technology" and revises the portfolio composition.

[0088] In this way, the present invention can provide general investors with investment opportunities in companies before they go public, thereby increasing investment diversity.

[0089] (Example 1)

[0090] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0091] Predicting a company's growth potential and stock price trends before its IPO, and providing investors with effective investment trusts, requires extremely high levels of expertise, making it difficult for the average investor. Furthermore, traditional methods involve time-consuming information gathering and analysis, making it difficult to make quick investment decisions.

[0092] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0093] In this invention, the server includes means for collecting information about companies from the internet, means for analyzing the collected information using natural language processing technology to evaluate the company's growth potential, and means for simulating the company's stock price trends based on the analysis results using a machine learning algorithm. This makes it possible to efficiently and quickly predict the growth potential and stock price trends of pre-listing companies and provide investment trusts that are easy for general investors to use.

[0094] The "Internet" is a global network and a system for exchanging and sharing information.

[0095] A "company" is an organization whose purpose is to provide products and services and generate revenue.

[0096] "Means of gathering information" refers to the technologies and tools used to obtain necessary data from sources such as news sites, press releases, and industry reports on the internet.

[0097] "Natural language processing technology" refers to technologies that enable computers to understand, analyze, and generate human language, and includes techniques such as tokenization of text data and sentiment analysis.

[0098] "Means of analysis" refers to the processes and tools used to structure collected information and extract useful insights.

[0099] "Growth potential" refers to a company's potential or ability to grow in the future, and is evaluated using indicators such as the amount of funding raised and the increase in the number of customers.

[0100] A "machine learning algorithm" is a mathematical model or method used to learn patterns from large amounts of data and make future predictions or classifications.

[0101] "Methods for simulating stock price trends" refer to systems that predict future stock prices based on past data, and these systems utilize machine learning models.

[0102] An "investment trust" is a financial product that combines multiple investment targets to diversify investments, aiming to provide investors with returns while reducing risk.

[0103] "Methods for constructing a trust" refers to the process and tools for selecting multiple investment targets and combining them into a single portfolio.

[0104] "Means of sale" refers to the platform or system used to provide the constructed investment trust to general investors.

[0105] The system of this invention mainly consists of a server, terminals, and users, and realizes a process of building and selling investment trusts by collecting information on companies before they go public, and by analyzing, evaluating, and simulating that information. Each processing step is described in detail below.

[0106] Information gathering

[0107] The server collects information about companies from the internet. To do this, it uses web crawling tools such as Python's BeautifulSoup and Scrapy to retrieve information from a wide range of data sources, including news sites, official company press releases, and industry reports.

[0108] Specific example:

[0109] The server accesses a specific news portal to collect information such as "Company X has raised new funds." It also retrieves the latest press release from Company X's official website and saves it to a local database.

[0110] Data Analysis

[0111] The server analyzes the collected information using natural language processing (NLP) techniques. Specifically, it tokenizes text data using libraries such as Python's NLTK and spaCy, and extracts keywords and important phrases. After that, it performs sentiment analysis to evaluate the company's growth potential.

[0112] Specific example:

[0113] The server reads the collected news articles and extracts keywords such as "fundraising," "employee growth," and "technological progress." Then, it performs sentiment analysis based on the extracted keywords and determines that "the news about company X is positive."

[0114] Modeling and Simulation

[0115] The server simulates the stock price trends of companies based on the analysis results. To do this, it uses machine learning algorithms such as TENSORFLOW® and scikit-learn, training them with historical data. It makes predictions under different scenarios (optimistic, neutral, and pessimistic).

[0116] Specific example:

[0117] The server takes growth metrics for company X and trains a stock price prediction model. It then runs a simulation and generates a result based on an optimistic scenario: "Company X's stock price will increase by 20% over the next six months."

[0118] Constructing an investment trust

[0119] Based on the simulation results, the server constructs an investment trust by combining multiple companies and market trading products. Using portfolio theory, it determines the optimal combination and sets the contents of the investment trust (stocks of companies X, Y, and Z and their proportions).

[0120] Specific example:

[0121] The server generates a portfolio including companies X, Y, and Z based on their growth forecasts, and constructs investment trust ABC.

[0122] Sales of investment trusts

[0123] The terminal (investment trust sales system) provides product descriptions to general investors based on information provided by the server and then begins sales. Users (investors) can search for and purchase investment trusts through the online platform.

[0124] Specific example:

[0125] The terminal publishes detailed information about investment trust ABC on an online platform, allowing users to search for investment trust ABC from their home computers or smartphones and proceed with the purchase.

[0126] Example of a prompt

[0127] "Please describe in detail the algorithm used to collect information on companies before they go public and to evaluate their growth potential. Also, please detail the process from constructing an investment trust based on simulated stock price trends to selling it."

[0128] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0129] Step 1:

[0130] Information gathering

[0131] The server collects data about companies from multiple sources on the internet. Input data includes news sites, official company press releases, and industry reports. Web crawling tools such as BeautifulSoup and Scrapy are used to retrieve the data. This allows information such as new funding rounds for company X and the contents of press releases to be stored on the server.

[0132] Specific actions:

[0133] The server periodically accesses specific news portals and collects article data such as "Company X has raised funds."

[0134] The server downloads the latest press release document from company X's official website and saves it to its local database.

[0135] Step 2:

[0136] Data Analysis

[0137] The server analyzes the collected data using natural language processing (NLP) techniques. The input data is the text data collected in step 1. The data is tokenized using Python's NLTK and spaCy libraries, keywords and phrases are extracted, and sentiment analysis is performed. This yields numerical data for evaluating the growth potential of companies.

[0138] Specific actions:

[0139] The server reads the news article text and extracts important keywords and phrases such as "fundraising," "employee growth," and "technological progress."

[0140] The server performs sentiment analysis based on the extracted keywords and determines that "the news about company X is positive."

[0141] Step 3:

[0142] Modeling and Simulation

[0143] The server simulates the future stock price trends of companies based on the analysis results. The input data is the analysis results from step 2. A machine learning model is built using TensorFlow or scikit-learn and trained on historical data. This predicts the stock price trends of companies. The simulation provides prediction results for optimistic, neutral, and pessimistic scenarios.

[0144] Specific actions:

[0145] The server inputs the analysis results and historical stock price data into a machine learning model and trains a stock price prediction model based on the growth indicators of company X.

[0146] The server runs simulations based on each scenario and generates a result stating that "Company X's stock price is projected to increase by 20% over the next six months under an optimistic scenario."

[0147] Step 4:

[0148] Constructing an investment trust

[0149] The server constructs an investment trust by combining multiple companies and market trading products based on the simulation results. The input data is the simulation results from step 3. Using portfolio theory, the optimal combination is determined, and the contents of the investment trust (stocks of companies X, Y, and Z and their proportions) are decided.

[0150] Specific actions:

[0151] The server generates a portfolio based on growth forecasts for companies X, Y, and Z, and constructs investment trusts ABC.

[0152] The server calculates the proportion of shares in each company and determines the components of the investment trust, taking into account the balance between risk and return.

[0153] Step 5:

[0154] Sales of investment trusts

[0155] The terminal (investment trust sales system) provides product descriptions to general investors based on information provided by the server. The input data is the detailed information of the investment trust from step 4. The terminal publishes the investment trust on an online platform, making it searchable and available for purchase by users (investors).

[0156] Specific actions:

[0157] The terminal will publish detailed information about investment trust ABC on the online platform.

[0158] Users can search for investment trust ABC from their home computers or smartphones and proceed with the purchase.

[0159] In this way, the entire process, from information gathering to the sale of investment trusts, is automated and carried out efficiently.

[0160] (Application Example 1)

[0161] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0162] Traditional investment trust construction and sales systems have a problem in that they do not adequately collect, analyze, and evaluate information on companies before they go public, and therefore cannot appropriately provide investment opportunities. Furthermore, there is a lack of mechanisms that allow end users to easily select and purchase investment trust products, making it difficult to increase investment diversity. For this reason, there is a need for a system that efficiently provides investors with investment opportunities in promising pre-IPO companies and allows users to easily make investment decisions.

[0163] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0164] In this invention, the server includes means for collecting information about a company before it goes public; means for analyzing the collected information using natural language processing technology to evaluate the company's growth potential; means for simulating the stock price trends of the pre-listing company using a machine learning algorithm based on the analysis results; means for constructing an investment trust based on the simulated stock price trends; means for selling the constructed investment trust; and means for presenting the collected and analyzed data to end users through a smartphone application, and for users to purchase the investment trust via electronic payment. This makes it possible to collect and analyze detailed information about a pre-listing company, and to construct and sell an investment trust based on the evaluation results. Furthermore, it is possible to provide information to end users through a smartphone application and provide an environment in which they can easily purchase investment trusts.

[0165] A "pre-listing company" refers to a company that has not yet been listed on a stock exchange.

[0166] "Means of collecting information" refers to methods and systems for obtaining data about companies before they go public from the internet or databases.

[0167] "Natural language processing technology" refers to computer technology used to understand and analyze human language.

[0168] "Growth potential" refers to an evaluation criterion that quantifies a company's potential for future growth.

[0169] A "machine learning algorithm" refers to a programming technique that learns patterns from data and uses them to make predictions and decisions.

[0170] "Means of simulation" refers to methods or mechanisms for virtually calculating a company's future stock price trends based on analysis results.

[0171] An "investment trust" refers to an investment product that is composed of a combination of stocks and other financial instruments from multiple companies.

[0172] "Means of construction" refers to the methods and mechanisms for generating investment trusts based on collected and analyzed information.

[0173] "Means of sale" refers to the methods and mechanisms for proposing and selling a constructed investment trust product to investors.

[0174] A "smartphone application" refers to a software program that runs on a smartphone.

[0175] "End users" refer to the users who ultimately use the system or product.

[0176] "Electronic payment" refers to electronic payment methods conducted via the internet.

[0177] System Configuration

[0178] The system implementing this invention is comprised of a server, a terminal, and a user. The server is responsible for information gathering, analysis, simulation, and construction of investment trusts. The terminal presents the constructed investment trusts to the user and handles sales and electronic payment processing. The user can refer to this information and purchase investment trusts.

[0179] Program processing

[0180] Server Processing

[0181] The server first collects information about companies before they go public from the internet. For this purpose, it uses web crawling technology and APIs (Application Programming Interfaces).

[0182] For example, a server retrieves information from a specific news portal stating that "Company X has raised funds."

[0183] Next, the collected information is analyzed using natural language processing (NLP) techniques. Specifically, text data is tokenized using libraries such as TextBlob, and keywords and phrases are extracted. Then, sentiment analysis is performed to determine whether the news is positive or negative. In addition, company growth indicators (such as the number of new customers, the amount of funding raised, and the progress of technology) are calculated and scored.

[0184] For example, the server analyzes information such as "Company X's number of employees increased by 30%" and evaluates this as a positive indicator of growth potential.

[0185] Next, based on the analysis results, we simulate the stock price trends of pre-IPO companies using a machine learning algorithm. To do this, we create a stock price prediction model using a machine learning model such as RandomForestRegressor and train it with historical data. Through the simulation, we generate prediction results for multiple scenarios (optimistic, neutral, and pessimistic).

[0186] For example, the server might output a result stating, "Company X is projected to see a 20% increase in its stock price over the next six months."

[0187] Subsequently, based on the simulation results, an investment trust is constructed by combining multiple pre-listing companies and investment products available on the market. The components of the investment trust (e.g., shares of company X and company Y) and their weights (e.g., the proportion of shares of each company) are then determined.

[0188] For example, the server "creates a portfolio including companies X, Y, and Z, and constructs it as investment trust ABC."

[0189] Terminal processing

[0190] The terminal provides product descriptions to general investors based on investment trust information provided by the server and sells the products. It also presents collected and analyzed data to users through a smartphone application and supports users in purchasing investment trusts using electronic payment functions.

[0191] User actions

[0192] Users can search for and apply to purchase investment trusts ABC through the online platform. This provides investment opportunities in promising companies before they go public and increases investment diversification.

[0193] Specific example

[0194] For example, if startup company X raises new funds and increases its number of employees, the server collects and analyzes this news and determines that it has high growth potential. It then creates an investment trust with other companies with growth potential and displays it to the user as a recommended investment trust. Users can view this information through a smartphone application and easily purchase the investment using the electronic payment function.

[0195] Example prompts for generative AI models

[0196] "Please explain how to gather the latest news on a specific startup company and assess its growth potential. Also, please explain in detail how to simulate stock price trends based on that assessment and construct an investment fund."

[0197] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0198] Step 1:

[0199] The server collects information about companies before they go public. Specifically, it retrieves data from news portals and official company websites on the internet using APIs and web crawling technologies. The input is the company name or search query, and the output is the collected text data. For example, it might retrieve a news article stating, "Company X has raised funds."

[0200] Step 2:

[0201] The server analyzes the collected information using natural language processing (NLP) techniques. Specifically, it tokenizes text data using the TextBlob library and extracts keywords and phrases. It performs sentiment analysis to determine whether the news is positive or negative and calculates company growth indicators (such as the number of new customers, the amount of funding raised, and the progress of technology). The input is the collected text data, and the output is the growth potential score and sentiment score as a result of the analysis.

[0202] Step 3:

[0203] The server uses machine learning algorithms to simulate the stock price trends of pre-IPO companies based on the analysis results. Specifically, it uses RandomForestRegressor to create a stock price prediction model and trains it with historical data. The simulation is performed under multiple scenarios (optimistic, neutral, pessimistic), and the prediction results for each scenario are output. The input is analysis data such as growth potential scores and sentiment scores, and the output is stock price prediction data. For example, one might get a result such as, "Company X is predicted to see a 20% increase in its stock price over the next six months."

[0204] Step 4:

[0205] The server constructs an investment trust based on the simulation results. Specifically, it constructs an investment trust by combining multiple pre-listed companies and investment products available on the market, and determines the weighting of each company's shares. The input is the simulation results, and the output is detailed information about the investment trust. For example, "Create a portfolio including companies X, Y, and Z, and construct it as investment trust ABC."

[0206] Step 5:

[0207] The terminal provides product descriptions and sales information to general investors based on investment trust information provided by the server. Specifically, it presents users with collected and analyzed data and details of investment trusts through a smartphone application. The input is detailed information about the investment trust, and the output is product descriptions and purchase screens provided to the user.

[0208] Step 6:

[0209] Users purchase investment trusts through a smartphone application. Specifically, they view detailed information about the displayed investment trusts and complete the purchase process using an electronic payment system. Inputs include the user's purchase instructions and payment information, while output is confirmation information that the purchase has been completed.

[0210] Example of a prompt:

[0211] "Please explain how to gather the latest news on a specific startup company and assess its growth potential. Also, please explain in detail how to simulate stock price trends based on that assessment and construct an investment fund."

[0212] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0213] The system of the present invention collects information on companies before they go public, analyzes that information, and evaluates the growth potential of those companies. Furthermore, it includes a process of simulating stock price trends based on the evaluation results, and then constructing and selling investment trusts based on those simulations. In addition, by combining it with an emotion engine that recognizes user emotions, it is possible to grasp user emotion data and use it to propose and adjust investment trusts. The following describes in detail the embodiments for which the present invention is specifically implemented.

[0214] Explain the program's processing in natural language.

[0215] Data collection

[0216] The server collects information about pre-IPO companies from the internet. To do this, it uses web crawling technology and APIs to retrieve data such as news articles, company press releases, and industry reports.

[0217] Specifically, the system accesses specific news portals and official company websites and automatically downloads relevant information. The retrieved data is stored in a database, categorized into fields such as news title, body text, publication date, and company name.

[0218] Data Analysis

[0219] The server analyzes the collected information using natural language processing (NLP) techniques. First, it tokenizes the text data and extracts important keywords and phrases.

[0220] Next, sentiment analysis is performed to determine whether the news content is positive or negative. Additionally, growth indicators for the company (such as the number of new customers, funding raised, and technological progress) are calculated, and a score is assigned based on these results.

[0221] Specifically, the server analyzes information such as "Company X's number of employees has increased by 30%" and evaluates this as a positive indicator of growth potential.

[0222] Modeling and Simulation

[0223] The server simulates the stock price trends of pre-IPO companies based on the analysis results. To do this, it uses machine learning algorithms to create a stock price prediction model and trains it using historical data.

[0224] The simulation generates prediction results for multiple scenarios (optimistic, neutral, and pessimistic).

[0225] Specifically, the server outputs the result, "Company X's stock price is projected to increase by 20% over the next six months."

[0226] Constructing an investment trust

[0227] Based on the simulation results, the server constructs an investment trust by combining multiple pre-IPO companies and investment products that can be traded on the market.

[0228] Determine the components of the investment trust (for example, the shares of company X and company Y) and their weights (for example, the proportion of shares of each company).

[0229] Specifically, the server creates a portfolio containing companies X, Y, and Z, and then constructs it as investment trust ABC.

[0230] Recognition and analysis of user emotions

[0231] The device uses an emotion engine to collect user emotion data. It analyzes the user's facial expressions and voice using a camera and microphone to identify their emotional state in real time.

[0232] The server analyzes this sentiment data to determine the user's investment risk preference. For example, it assesses whether the user feels anxious about risk.

[0233] Specifically, the device captures the user's facial expressions, and the server determines that "the user is feeling anxious."

[0234] Proposal and adjustment of investment trusts

[0235] The server optimizes investment fund recommendations based on the results of the emotion engine's analysis. For example, if the user indicates an optimistic sentiment, it will suggest high-risk investment funds.

[0236] Furthermore, it is possible to adjust the risk appetite of existing mutual funds based on user sentiment data. For example, if a user is feeling anxious, the portfolio can be restructured to further reduce risk.

[0237] In terms of specific operations, the server analyzes the user's emotional data and suggests investment trusts that match their risk tolerance.

[0238] Sales of investment trusts

[0239] The terminal provides product descriptions to general investors based on investment trust information provided by the server, and then sells the products.

[0240] Users can purchase investment trusts through online platforms. For example, a user can search for investment trusts from their home computer and submit a purchase request.

[0241] Performance Update

[0242] The server periodically collects new data to update the contents of the investment trust. The server collects the latest company information and analyzes it using natural language processing technology.

[0243] Furthermore, the AI ​​model is retrained to reflect new data and market trends, and the simulation results are updated.

[0244] Specifically, the server analyzes new information, such as "Company X has announced a new technology," and then revises its portfolio composition.

[0245] In this way, the present invention provides general investors with investment opportunities in companies before they go public, and further enhances investment diversity and adaptability by utilizing user sentiment data to propose and adjust investment trusts.

[0246] The following describes the processing flow.

[0247] Step 1:

[0248] The server collects information about pre-IPO companies from the internet. To do this, the server uses web crawling technology and APIs to retrieve data such as news articles, company press releases, and industry reports.

[0249] In terms of operation, the server accesses specific news portals or official company websites and automatically downloads relevant information. The retrieved data is then stored in a database, categorized into fields such as news title, body text, publication date, and company name.

[0250] Step 2:

[0251] The server analyzes the collected information using natural language processing (NLP) techniques. First, it tokenizes the text data and extracts important keywords and phrases.

[0252] Next, the server performs sentiment analysis to determine whether the news content is positive or negative. It also calculates the company's growth indicators (such as the number of new customers, the amount of funding raised, and the progress of technology) and scores the company based on the results.

[0253] Specifically, the server analyzes information such as "Company X's employee count has increased by 30%" and evaluates this as a positive indicator of growth potential.

[0254] Step 3:

[0255] The server simulates the stock price trends of pre-IPO companies based on the analysis results. To do this, it uses machine learning algorithms to create a stock price prediction model and trains it using historical data.

[0256] The simulation generates prediction results for multiple scenarios (optimistic, neutral, pessimistic). Specifically, the server outputs a result such as "Company X's stock price is projected to increase by 20% over the next six months."

[0257] Step 4:

[0258] The server constructs an investment fund based on the simulation results. First, it determines the combination of pre-listing companies and investment products that can be traded on the market.

[0259] Next, the server determines the components of the portfolio (for example, the shares of company X and company Y) and their weights (for example, the proportion of shares of each company). Specifically, the server "creates a portfolio containing companies X, Y, and Z, and constructs it as investment trust ABC."

[0260] Step 5:

[0261] The device uses an emotion engine to collect user emotion data. It analyzes the user's facial expressions and voice using the camera and microphone to identify their emotional state in real time.

[0262] In terms of specific operations, the device captures and analyzes the user's facial expressions. For example, the device might determine that "the user is showing positive emotions."

[0263] Step 6:

[0264] The server analyzes emotional data collected by the emotion engine to determine the user's investment risk preference. For example, it assesses whether the user feels anxious about risk.

[0265] In terms of specific operation, the server determines that "the user's risk tolerance is low based on sentiment data."

[0266] Step 7:

[0267] The server optimizes investment fund recommendations based on the results of the emotion engine's analysis. For example, if the user indicates an optimistic sentiment, it will suggest high-risk investment funds.

[0268] In terms of specific operations, the server makes suggestions based on sentiment data, such as "suggesting high-risk investment trusts to the user."

[0269] Step 8:

[0270] The server adjusts the risk appetite of existing mutual funds based on the user's emotional data. For example, if the user is feeling anxious, it will restructure the portfolio to further reduce risk.

[0271] In terms of specific operations, the server performs processes such as "adjusting the portfolio's risk ratio based on the user's emotional state."

[0272] Step 9:

[0273] The terminal provides product descriptions to general investors based on investment trust information provided by the server, and then sells the products.

[0274] In terms of specific actions, the terminal generates a prospectus for the investment trust and presents it to the user.

[0275] Step 10:

[0276] Users purchase investment trusts through an online platform. Specifically, users search for investment trusts from their home computers and submit purchase requests.

[0277] Step 11:

[0278] The server periodically collects new data to update the contents of the investment trust. The server collects the latest company information and analyzes it using natural language processing technology.

[0279] In terms of specific operations, the server analyzes new information, such as "Company X has announced a new technology," and then revises its portfolio composition.

[0280] In this way, the present invention can provide investment opportunities for pre-IPO companies to ordinary investors, and further enhance the diversity and adaptability of investments by utilizing users' emotional data to propose and adjust investment trusts.

[0281] (Example 2)

[0282] Next, Example 2 will be described. In the following description, the data processing device 12 is referred to as a "server", and the smart device 14 is referred to as a "terminal".

[0283] In order to make appropriate investment decisions for pre-IPO companies, advanced data collection and analysis are required. However, it has been difficult for conventional systems to perform this efficiently and accurately. In addition, the proposal and adjustment of investment products corresponding to the risk preferences of individual investors are insufficient, and it is necessary to improve investors' satisfaction. Therefore, a system for analyzing pre-IPO company information and simulating stock price trends is required.

[0284] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0285] In this invention, the server includes means for collecting information on pre-IPO companies, means for analyzing the collected information using natural language processing technology to evaluate the growth potential of the companies, means for simulating the stock price trends of pre-IPO companies based on the analysis results using machine learning algorithms, means for constructing investment products based on the simulated stock price trends, means for collecting and analyzing users' emotional data in real time, means for adjusting the proposed content of investment products based on users' emotional data, and means for selling the constructed investment products. Thereby, it becomes possible to collect and analyze information on pre-IPO companies, simulate stock price trends, and propose and adjust investment products based on users' emotional data.

[0286] "Pre-IPO company" refers to a company at the stage before listing on the stock market.

[0287] The "means for collecting information" refers to technologies and devices for automatically obtaining necessary information from the Internet and other data sources.

[0288] The "natural language processing technology" refers to technologies for a computer to analyze and understand the languages that people use in daily life.

[0289] The "means for evaluating the growth potential of an enterprise" refers to methods and technologies for analyzing and evaluating the future growth ability of an enterprise based on the collected information.

[0290] The "machine learning algorithm" refers to a type of artificial intelligence that automatically learns based on data and performs predictions and decision-making.

[0291] The "means for simulating stock price trends" refers to methods and technologies for predicting the future movements of an enterprise's stock price based on the collected and analyzed data.

[0292] The "means for constructing investment products" refers to methods and technologies for designing and creating investment products such as investment trusts and portfolios based on the simulation results.

[0293] The "user's emotional data" refers to information regarding the emotional state collected from the user's expressions, voices, actions, etc.

[0294] The "means for collecting and analyzing in real time" refers to technologies and devices for collecting the user's emotional state in real time and quickly analyzing it.

[0295] The "means for adjusting the proposed content of investment products" refers to methods and technologies for changing the content and composition of investment products based on the user's emotional data.

[0296] The "means for selling" refers to methods and technologies for providing the constructed investment products to the market so that users can purchase them.

[0297] This invention relates to a system that collects data on companies before they go public, analyzes that data to evaluate the companies' growth potential, and simulates stock price trends. Based on the simulation results, it constructs investment products, collects and analyzes user sentiment data to optimize investment proposals, and then provides and sells the constructed investment products to the market.

[0298] overview

[0299] 1. Data Collection

[0300] The server collects information about pre-IPO companies from the internet. This information collection uses web crawling technology and APIs (e.g., newspaper article APIs, official company APIs). Specifically, the server accesses news portals and official company websites, automatically downloading news articles such as "Company A announces new product" and saving them to a database.

[0301] 2. Data Analysis

[0302] The server analyzes the collected data using natural language processing technologies (e.g., NLTK, spaCy). It tokenizes the text data and extracts important keywords and phrases. It also performs sentiment analysis to determine whether the news is positive or negative. Based on this analysis, it calculates company growth indicators (e.g., number of new customers, progress of proprietary technology) and scores the company's growth potential.

[0303] 3. Modeling and Simulation

[0304] The server simulates the stock price trends of pre-IPO companies based on the analysis results. It creates a stock price prediction model using machine learning algorithms (e.g., random forest, neural network) and trains it with historical data. The simulation generates prediction results under multiple scenarios: optimistic, neutral, and pessimistic. For example, it might output a result such as, "Company A's predicted stock price increase rate is 15% over the next six months."

[0305] 4. Construction of Investment Products

[0306] Based on the simulation results, the server constructs an investment trust by combining multiple pre-listing companies and other investment products. It determines the components (e.g., stocks of Company A, Company B, Company C) and weights (e.g., the ratio of the stocks of each company) of the investment products. Specifically, "Create a portfolio including Company A, Company B, and Company C and construct it as Investment Trust XYZ."

[0307] 5. Recognition and Analysis of User Emotions

[0308] The terminal uses an emotion engine (e.g., camera, microphone) to collect the user's emotion data. It analyzes expressions and voices to identify the user's emotional state in real time and sends this data to the server to analyze the user's investment risk preference. For example, it is determined that "the user is feeling anxious."

[0309] 6. Proposal and Adjustment of Investment Products

[0310] Based on the data obtained from the emotion engine, the server proposes an investment trust according to the user's risk preference. If the user is optimistic, it proposes high-risk investment products; conversely, if the user is feeling anxious, it proposes low-risk investment products. Specifically, "It is determined that the user can tolerate risks and high-return investment products are proposed."

[0311] 7. Sale of Investment Products

[0312] Based on the information of the investment trust provided by the server, the terminal is responsible for explaining and selling the products to general investors. The user can purchase the investment trust through an online platform. For example, the user searches for "Investment Trust XYZ" from their home computer and submits a purchase application.

[0313] 8. Update of Performance

[0314] The server periodically collects new information and updates the contents of the investment trust. It reanalyzes the latest company information and retrains the AI ​​model (e.g., generative AI model) based on the new data. For example, it analyzes new information such as "Company A has raised new funds" and revises the portfolio composition.

[0315] Specific example

[0316] As a concrete example, the server collects news articles and analyzes information such as "Company A has launched a new product on the market." Based on the results of this analysis, it evaluates the company's growth potential and simulates stock price trends. It also collects user sentiment data in real time and proposes the optimal investment product according to the user's risk preference.

[0317] Example of a prompt

[0318] "Company A has launched a new product into the market. How does this affect Company A's growth potential?"

[0319] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0320] Step 1:

[0321] Data collection

[0322] The server collects information about pre-IPO companies from the internet. It uses web crawling technology and APIs to retrieve data from news articles, company press releases, industry reports, etc. Specifically, the server accesses news portals and official company websites and automatically downloads news articles such as "Company A has announced a new product."

[0323] Input: URL of a specific news portal or company website

[0324] Output: Raw data such as news articles, press releases, and industry reports.

[0325] Step 2:

[0326] Data Analysis

[0327] The server analyzes the collected data using natural language processing technologies (e.g., NLTK, spaCy). First, it tokenizes the text data and extracts important keywords and phrases. Next, it performs sentiment analysis to determine whether the news content is positive or negative. Based on this, it calculates company growth indicators (e.g., number of new customers, progress of its own technology) and scores the company's growth potential. Specifically, the server extracts and analyzes information such as "Company A's number of new customers increased by 50%."

[0328] Input: Collected raw data

[0329] Output: Tokenized text, sentiment analysis results, company growth metrics

[0330] Step 3:

[0331] Modeling and Simulation

[0332] The server simulates the stock price trends of pre-IPO companies based on the analysis results. It creates a stock price prediction model using machine learning algorithms (e.g., random forest, neural network) and trains it with historical data. The simulation generates prediction results for multiple scenarios: optimistic, neutral, and pessimistic. Specifically, the server outputs a result such as "Company A's predicted stock price increase rate is 15% over the next 6 months."

[0333] Input: Company growth indicators, historical stock price data

[0334] Output: Simulated stock price trends, multiple scenario prediction results

[0335] Step 4:

[0336] Building an investment product

[0337] Based on the simulation results, the server constructs an investment trust by combining multiple pre-IPO companies and other investment products. It determines the components of the investment product (e.g., shares of company A, company B, and company C) and their weights (e.g., the proportion of shares of each company). Specifically, the server "creates a portfolio including company A, company B, and company C, and constructs this as investment trust XYZ."

[0338] Input: Simulated stock price trends

[0339] Output: Details of the constructed mutual fund (components, ratios, etc.)

[0340] Step 5:

[0341] Recognition and analysis of user emotions

[0342] The device uses an emotion engine (e.g., camera, microphone) to collect user emotion data. It analyzes facial expressions and voice in real time to identify the emotional state and sends that data to the server. The server uses that data to analyze the user's investment risk preferences. Specifically, the device captures the user's facial expressions, and the server determines that "the user is feeling anxious."

[0343] Input: User facial expression data, voice data

[0344] Output: Identified emotional states, investment risk preference analysis results

[0345] Step 6:

[0346] Proposal and adjustment of investment products

[0347] Based on the analysis results of the emotion engine, the server suggests investment products that match the user's risk preference. If the user is optimistic, it suggests high-risk investment products; if the user is anxious, it suggests low-risk investment products. Specifically, the server determines that "the user is in a state where they can tolerate risk and suggests high-return investment products."

[0348] Input: Emotional engine analysis results, user's investment risk preference

[0349] Output: Adjusted investment product proposals

[0350] Step 7:

[0351] Sales of investment products

[0352] The terminal is responsible for providing product descriptions and sales information about investment trusts to general investors based on information provided by the server. Users can purchase investment trusts through the online platform. Specifically, a user searches for "Investment Trust XYZ" from their home computer and submits a purchase request.

[0353] Input: Investment trust information provided by the server

[0354] Output: Purchase request by user

[0355] Step 8:

[0356] Performance Update

[0357] The server regularly collects new information and updates the contents of the investment trust. It reanalyzes the latest company information and retrains the AI ​​model based on the new data. Specifically, the server analyzes new information such as "Company A has raised new funds" and revises the portfolio composition.

[0358] Input: New company information

[0359] Output: Updated investment trust details and retrained AI model

[0360] (Application Example 2)

[0361] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0362] Traditional investment management systems primarily relied on information from listed companies for their evaluations and recommendations, with few utilizing pre-IPO company information. Furthermore, they often failed to consider user sentiment, resulting in poorly optimized risk assessments and investment recommendations for individual users. This led to low investor satisfaction and a lack of investment diversity and adaptability.

[0363] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for collecting information about a company before it goes public, means for analyzing the collected information and evaluating the company's growth potential, means for simulating the stock price trends of the company before it goes public based on the analysis results, means for selling the constructed investment trust, means for collecting user sentiment data, means for analyzing the collected sentiment data and reflecting it in investment trust proposals, and means for users to purchase investment trusts using electronic payment. This makes it possible to utilize information about companies before they go public and to make investment proposals that take into account user sentiment.

[0364] A "pre-listing company" is a company that has not yet publicly traded its shares on the market but aims to go public in the future.

[0365] "Means of collecting information" refers to the technologies and methods used to obtain data from news articles, press releases, industry reports, etc., via the internet.

[0366] "Means of analyzing information and evaluating a company's growth potential" refers to technologies and methods for determining a company's growth potential using techniques such as natural language processing and sentiment analysis.

[0367] "Methods for simulating stock price trends" refer to technologies and methods that use machine learning algorithms to predict future stock price fluctuations from past data.

[0368] "Methods for constructing investment trusts" refer to the techniques and methods for forming a fund by combining multiple investment products based on simulation results.

[0369] "Means of selling constructed investment trusts" refers to the technologies and methods that provide information about investment trusts and enable general investors to purchase them.

[0370] "Means of collecting user emotional data" refers to technologies and methods that use cameras and microphones to capture users' facial expressions and voices in order to understand their emotional state.

[0371] "Means for analyzing emotional data" refers to technologies and methods for analyzing acquired emotional data and evaluating the user's emotional state.

[0372] "Means of reflecting in investment trust proposals" refers to technologies and methods for optimizing and proposing investment trust content and risk levels based on user sentiment data.

[0373] "Methods of purchase using electronic payment" refer to technologies and methods that allow users to purchase proposed investment trusts using electronic means.

[0374] Basic structure of the system program

[0375] The system for implementing this invention provides a program that collects and analyzes information about companies before they go public and handles the entire process from building investment trusts to selling them. The main components of the program are as follows:

[0376] 1. Data Acquisition Module:

[0377] The server collects information about pre-IPO companies, such as news articles, company press releases, and industry reports, via the internet. It uses web crawling technology and APIs to retrieve information from specific websites and store it in a database.

[0378] 2. Data Analysis Module:

[0379] The server analyzes the collected information using natural language processing (NLP) techniques to assess growth potential. Specifically, it tokenizes text data, extracts important keywords and phrases, and performs sentiment analysis. It then calculates and scores company growth indicators (e.g., number of new customers and amount of funding raised).

[0380] 3. Simulation Module:

[0381] Based on the analysis results, the server uses machine learning algorithms to create a stock price prediction model and simulate stock price trends. This prediction includes multiple scenarios (optimistic, neutral, and pessimistic) and forecasts future stock price increases and decreases.

[0382] 4. Investment Trust Construction Module:

[0383] Based on the simulation results, the server constructs an investment trust by combining multiple pre-IPO companies and tradable investment products. In this process, it determines the proportion of each company's shares and the overall portfolio composition.

[0384] 5. User sentiment collection module:

[0385] The device collects user emotion data using input devices such as cameras and microphones. It uses an emotion engine to analyze facial expressions and voice in real time to identify the user's emotional state.

[0386] 6. Emotional Data Analysis Module:

[0387] The server analyzes emotional data collected from users to evaluate their risk preferences and emotional state. For example, if a user is feeling anxious, the server uses that information to adjust investment recommendations to those with lower risk.

[0388] 7. Investment Proposal Module:

[0389] Based on the analysis results of the emotion engine, the server suggests investment trusts optimized for the user. If the user indicates optimistic emotions, it suggests high-risk investment trusts; if the user indicates anxiety, it suggests a portfolio with reduced risk.

[0390] 8. Electronic payment module:

[0391] The terminal assists users in purchasing investment trusts suggested by the server using electronic payment. Existing payment platforms (e.g., Stripe or PayPal) are used for processing electronic payments.

[0392] Specific example

[0393] For example, the system collects information on startup companies from news websites and analyzes positive information, such as when a company announces new technology. As a result, the company's growth potential is highly rated, and its stock price movement is simulated based on this information. When optimistic sentiment data from users is collected, high-risk investment trusts are suggested, and the user then makes an electronic payment through the app to purchase the suggested investment trusts.

[0394] Example of a prompt

[0395] "Explain how to optimize investment trusts by utilizing real-time user sentiment data in investment trust proposals and based on the results of an analysis of the growth potential of pre-IPO companies. The sentiment data will be collected using facial recognition technology, and the investment trust proposals will also include electronic payment functionality."

[0396] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0397] Step 1:

[0398] The server collects information about pre-IPO companies from the internet. Specifically, it uses web crawling technology and APIs to retrieve data such as news articles, company press releases, and industry reports. The input is the URL of a specific news portal or the company's official website, and the output is downloaded text data.

[0399] Step 2:

[0400] The server analyzes the collected information using natural language processing (NLP) techniques to evaluate the company's growth potential. Specifically, it tokenizes text data and extracts important keywords and phrases. The input is the text data collected in the previous step, and the output is the tokenized data and the results of sentiment analysis.

[0401] Step 3:

[0402] The server simulates the stock price trends of pre-IPO companies based on the analysis results. It uses a machine learning algorithm to create a stock price prediction model and learns from historical data. The input is the analysis results obtained in step 2, and the output is predicted stock price trend data under multiple scenarios.

[0403] Step 4:

[0404] Based on the simulation results, the server constructs an investment trust by combining multiple pre-IPO companies and tradable investment products on the market. The input is the stock price trend prediction data obtained in step 3, and the output is the portfolio of the constructed investment trust.

[0405] Step 5:

[0406] The device collects user emotion data using a camera and microphone. Specifically, it uses an emotion engine to analyze the user's facial expressions and voice in real time. The input is the user's facial expressions and voice data, and the output is the analyzed emotion state data.

[0407] Step 6:

[0408] The server analyzes the collected emotional data to evaluate the user's risk preference and emotional state. The input is the emotional state data obtained in step 5, and the output is emotional evaluation data corresponding to the user's risk preference.

[0409] Step 7:

[0410] The server proposes investment trusts optimized for the user based on the analysis results of the emotion engine. Specifically, if the user expresses optimistic emotions, it proposes high-risk investment trusts; if the user expresses anxiety, it proposes a portfolio with reduced risk. The input is the emotion evaluation data obtained in step 6 and the investment trust portfolio constructed in step 4, and the output is the proposed investment trust plan.

[0411] Step 8:

[0412] The terminal provides product descriptions to individual investors based on investment trust information provided by the server and assists with purchases via electronic payment. Specifically, it displays the proposed investment trust and guides the purchase process through the payment platform. The input is the investment trust plan proposed in step 7, and the output is a confirmation of the completed purchase.

[0413] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0414] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0415] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0416] [Second Embodiment]

[0417] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0418] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0419] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0420] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0421] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0422] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0423] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0424] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0425] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0426] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0427] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0428] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0429] The system of the present invention collects information on companies before they go public, analyzes that information, and evaluates the growth potential of the companies. Next, it includes a process of simulating stock price trends based on the evaluation results, and then constructing and selling investment trusts based on those simulations. Specific embodiments for implementing the present invention are described in detail below.

[0430] Explain the program's processing in natural language.

[0431] Data collection

[0432] The server collects information about pre-IPO companies from the internet. To do this, it uses web crawling technology and APIs (Application Programming Interfaces) to retrieve data such as news articles, company press releases, and industry reports.

[0433] For example, a server might collect information from a specific news portal stating that "Company X has raised funds."

[0434] Data Analysis

[0435] The server analyzes the collected information using natural language processing (NLP) techniques. Specifically, it tokenizes text data and extracts keywords and phrases.

[0436] Next, sentiment analysis is performed to determine whether the news is positive or negative. Additionally, company growth indicators (such as new customer numbers, funding raised, and technological progress) are calculated and scored.

[0437] For example, the server analyzes information such as "Company X's number of employees increased by 30%" and evaluates this as a positive indicator of growth potential.

[0438] Modeling and Simulation

[0439] The server simulates the stock price trends of pre-IPO companies based on the analysis results. To do this, it uses machine learning algorithms to create a stock price prediction model and trains it using historical data.

[0440] The simulation generates prediction results for multiple scenarios (optimistic, neutral, and pessimistic).

[0441] For example, the server might output a result stating, "Company X is projected to see a 20% increase in its stock price over the next six months."

[0442] Constructing an investment trust

[0443] Based on the simulation results, the server constructs an investment trust by combining multiple pre-IPO companies and investment products that can be traded on the market.

[0444] Determine the components of the investment trust (for example, the shares of company X and company Y) and their weights (for example, the proportion of shares of each company).

[0445] For example, the server "creates a portfolio including companies X, Y, and Z, and constructs it as investment trust ABC."

[0446] Sales of investment trusts

[0447] The terminal (the system of a financial institution or securities company engaged in the sale of investment trusts) provides product descriptions to general investors and sells them based on investment trust information provided from the server.

[0448] Users can purchase investment trust ABC through an online platform. For example, a user can search for investment trust ABC from their home computer and submit a purchase request.

[0449] Specific example

[0450] Example 1: Information gathering and analysis of startup company X

[0451] 1. The server collects the latest news about company X (e.g., funding amounts, employee growth, technological progress).

[0452] 2. The server uses natural language processing technology to analyze the news and evaluate the growth potential of company X (e.g., expansion plans through fundraising).

[0453] Example 2: Construction and sales of investment trust ABC

[0454] 1. The server constructs investment trust ABC by combining companies X, Y, and Z based on the simulation results.

[0455] 2. The terminal begins selling investment trust ABC to general investors, and users submit purchase applications online.

[0456] In this way, the present invention can provide general investors with investment opportunities in companies before they go public, thereby increasing investment diversity.

[0457] The following describes the processing flow.

[0458] Step 1:

[0459] The server collects information about pre-IPO companies from the internet. To do this, the server uses web crawling technology to retrieve data such as news articles, company press releases, and industry reports.

[0460] Specifically, the system accesses specific news portals and official company websites and automatically downloads relevant information. The retrieved data is then stored in a database, categorized into fields such as news title, body text, publication date, and company name.

[0461] Step 2:

[0462] The server analyzes the collected information using natural language processing (NLP) techniques. First, it tokenizes the text data and extracts important keywords and phrases.

[0463] Next, the server performs sentiment analysis to determine whether the news content is positive or negative. Furthermore, it calculates the company's growth indicators (such as the number of new customers, the amount of funding raised, and the progress of technology) and scores the results based on those.

[0464] Specifically, the server analyzes information such as "Company X's employee count has increased by 30%" and evaluates this as a positive indicator of growth potential.

[0465] Step 3:

[0466] The server simulates the stock price trends of pre-IPO companies based on the analysis results. To do this, it uses machine learning algorithms to create a stock price prediction model and trains it using historical data.

[0467] The simulation generates prediction results for multiple scenarios (optimistic, neutral, pessimistic). Specifically, the server outputs a result such as "Company X's stock price is projected to increase by 20% over the next six months."

[0468] Step 4:

[0469] The server constructs investment trusts based on the simulation results. First, it determines the combination of pre-listing companies and investment products available on the market.

[0470] Next, the server determines the components of the portfolio (for example, the shares of company X and company Y) and their weights (for example, the proportion of shares of each company). Specifically, the server "creates a portfolio containing companies X, Y, and Z, and constructs it as investment trust ABC."

[0471] Step 5:

[0472] The terminal receives investment trust information from the server and provides it to individual investors. The terminal generates an investment trust prospectus and presents it to the user.

[0473] Next, the user purchases investment trust ABC through an online platform. Specifically, the user searches for investment trust ABC from their home computer and submits a purchase request.

[0474] Step 6:

[0475] The server periodically collects new data to update the contents of the investment trust. The server collects the latest company information and analyzes it using natural language processing technology.

[0476] Afterward, the AI ​​model is retrained to reflect new data and market trends, and the simulation results are updated. Specifically, the server analyzes new information such as "Company X has announced a new technology" and revises the portfolio composition.

[0477] In this way, the present invention can provide general investors with investment opportunities in companies before they go public, thereby increasing investment diversity.

[0478] (Example 1)

[0479] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0480] Predicting a company's growth potential and stock price trends before its IPO, and providing investors with effective investment trusts, requires extremely high levels of expertise, making it difficult for the average investor. Furthermore, traditional methods involve time-consuming information gathering and analysis, making it difficult to make quick investment decisions.

[0481] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0482] In this invention, the server includes means for collecting information about companies from the internet, means for analyzing the collected information using natural language processing technology to evaluate the company's growth potential, and means for simulating the company's stock price trends based on the analysis results using a machine learning algorithm. This makes it possible to efficiently and quickly predict the growth potential and stock price trends of pre-listing companies and provide investment trusts that are easy for general investors to use.

[0483] The "Internet" is a global network and a system for exchanging and sharing information.

[0484] A "company" is an organization whose purpose is to provide products and services and generate revenue.

[0485] "Means of gathering information" refers to the technologies and tools used to obtain necessary data from sources such as news sites, press releases, and industry reports on the internet.

[0486] "Natural language processing technology" refers to technologies that enable computers to understand, analyze, and generate human language, and includes techniques such as tokenization of text data and sentiment analysis.

[0487] "Means of analysis" refers to the processes and tools used to structure collected information and extract useful insights.

[0488] "Growth potential" refers to a company's potential or ability to grow in the future, and is evaluated using indicators such as the amount of funding raised and the increase in the number of customers.

[0489] A "machine learning algorithm" is a mathematical model or method used to learn patterns from large amounts of data and make future predictions or classifications.

[0490] "Methods for simulating stock price trends" refer to systems that predict future stock prices based on past data, and these systems utilize machine learning models.

[0491] An "investment trust" is a financial product that combines multiple investment targets to diversify investments, aiming to provide investors with returns while reducing risk.

[0492] "Methods for constructing a trust" refers to the process and tools for selecting multiple investment targets and combining them into a single portfolio.

[0493] "Means of sale" refers to the platform or system used to provide the constructed investment trust to general investors.

[0494] The system of this invention mainly consists of a server, terminals, and users, and realizes a process of building and selling investment trusts by collecting information on companies before they go public, and by analyzing, evaluating, and simulating that information. Each processing step is described in detail below.

[0495] Information gathering

[0496] The server collects information about companies from the internet. To do this, it uses web crawling tools such as Python's BeautifulSoup and Scrapy to retrieve information from a wide range of data sources, including news sites, official company press releases, and industry reports.

[0497] Specific example:

[0498] The server accesses a specific news portal to collect information such as "Company X has raised new funds." It also retrieves the latest press release from Company X's official website and saves it to a local database.

[0499] Data Analysis

[0500] The server analyzes the collected information using natural language processing (NLP) techniques. Specifically, it tokenizes text data using libraries such as Python's NLTK and spaCy, and extracts keywords and important phrases. After that, it performs sentiment analysis to evaluate the company's growth potential.

[0501] Specific example:

[0502] The server reads the collected news articles and extracts keywords such as "fundraising," "employee growth," and "technological progress." Then, it performs sentiment analysis based on the extracted keywords and determines that "the news about company X is positive."

[0503] Modeling and Simulation

[0504] The server simulates the stock price trends of companies based on the analysis results. To do this, it uses machine learning algorithms such as TensorFlow and scikit-learn, training them with historical data. It makes predictions under different scenarios (optimistic, neutral, and pessimistic).

[0505] Specific example:

[0506] The server takes growth metrics for company X and trains a stock price prediction model. It then runs a simulation and generates a result based on an optimistic scenario: "Company X's stock price will increase by 20% over the next six months."

[0507] Constructing an investment trust

[0508] Based on the simulation results, the server constructs an investment trust by combining multiple companies and market trading products. Using portfolio theory, it determines the optimal combination and sets the contents of the investment trust (stocks of companies X, Y, and Z and their proportions).

[0509] Specific example:

[0510] The server generates a portfolio including companies X, Y, and Z based on their growth forecasts, and constructs investment trust ABC.

[0511] Sales of investment trusts

[0512] The terminal (investment trust sales system) provides product descriptions to general investors based on information provided by the server and then begins sales. Users (investors) can search for and purchase investment trusts through the online platform.

[0513] Specific example:

[0514] The terminal publishes detailed information about investment trust ABC on an online platform, allowing users to search for investment trust ABC from their home computers or smartphones and proceed with the purchase.

[0515] Example of a prompt

[0516] "Please describe in detail the algorithm used to collect information on companies before they go public and to evaluate their growth potential. Also, please detail the process from constructing an investment trust based on simulated stock price trends to selling it."

[0517] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0518] Step 1:

[0519] Information gathering

[0520] The server collects data about companies from multiple sources on the internet. Input data includes news sites, official company press releases, and industry reports. Web crawling tools such as BeautifulSoup and Scrapy are used to retrieve the data. This allows information such as new funding rounds for company X and the contents of press releases to be stored on the server.

[0521] Specific actions:

[0522] The server periodically accesses specific news portals and collects article data such as "Company X has raised funds."

[0523] The server downloads the latest press release document from company X's official website and saves it to its local database.

[0524] Step 2:

[0525] Data Analysis

[0526] The server analyzes the collected data using natural language processing (NLP) techniques. The input data is the text data collected in step 1. The data is tokenized using Python's NLTK and spaCy libraries, keywords and phrases are extracted, and sentiment analysis is performed. This yields numerical data for evaluating the growth potential of companies.

[0527] Specific actions:

[0528] The server reads the news article text and extracts important keywords and phrases such as "fundraising," "employee growth," and "technological progress."

[0529] The server performs sentiment analysis based on the extracted keywords and determines that "the news about company X is positive."

[0530] Step 3:

[0531] Modeling and Simulation

[0532] The server simulates the future stock price trends of companies based on the analysis results. The input data is the analysis results from step 2. A machine learning model is built using TensorFlow or scikit-learn and trained on historical data. This predicts the stock price trends of companies. The simulation provides prediction results for optimistic, neutral, and pessimistic scenarios.

[0533] Specific actions:

[0534] The server inputs the analysis results and historical stock price data into a machine learning model and trains a stock price prediction model based on the growth indicators of company X.

[0535] The server runs simulations based on each scenario and generates a result stating that "Company X's stock price is projected to increase by 20% over the next six months under an optimistic scenario."

[0536] Step 4:

[0537] Constructing an investment trust

[0538] The server constructs an investment trust by combining multiple companies and market trading products based on the simulation results. The input data is the simulation results from step 3. Using portfolio theory, the optimal combination is determined, and the contents of the investment trust (stocks of companies X, Y, and Z and their proportions) are decided.

[0539] Specific actions:

[0540] The server generates a portfolio based on growth forecasts for companies X, Y, and Z, and constructs investment trusts ABC.

[0541] The server calculates the proportion of shares in each company and determines the components of the investment trust, taking into account the balance between risk and return.

[0542] Step 5:

[0543] Sales of investment trusts

[0544] The terminal (investment trust sales system) provides product descriptions to general investors based on information provided by the server. The input data is the detailed information of the investment trust from step 4. The terminal publishes the investment trust on an online platform, making it searchable and available for purchase by users (investors).

[0545] Specific actions:

[0546] The terminal will publish detailed information about investment trust ABC on the online platform.

[0547] Users can search for investment trust ABC from their home computers or smartphones and proceed with the purchase.

[0548] In this way, the entire process, from information gathering to the sale of investment trusts, is automated and carried out efficiently.

[0549] (Application Example 1)

[0550] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0551] Traditional investment trust construction and sales systems have a problem in that they do not adequately collect, analyze, and evaluate information on companies before they go public, and therefore cannot appropriately provide investment opportunities. Furthermore, there is a lack of mechanisms that allow end users to easily select and purchase investment trust products, making it difficult to increase investment diversity. For this reason, there is a need for a system that efficiently provides investors with investment opportunities in promising pre-IPO companies and allows users to easily make investment decisions.

[0552] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0553] In this invention, the server includes means for collecting information about a company before it goes public; means for analyzing the collected information using natural language processing technology to evaluate the company's growth potential; means for simulating the stock price trends of the pre-listing company using a machine learning algorithm based on the analysis results; means for constructing an investment trust based on the simulated stock price trends; means for selling the constructed investment trust; and means for presenting the collected and analyzed data to end users through a smartphone application, and for users to purchase the investment trust via electronic payment. This makes it possible to collect and analyze detailed information about a pre-listing company, and to construct and sell an investment trust based on the evaluation results. Furthermore, it is possible to provide information to end users through a smartphone application and provide an environment in which they can easily purchase investment trusts.

[0554] A "pre-listing company" refers to a company that has not yet been listed on a stock exchange.

[0555] "Means of collecting information" refers to methods and systems for obtaining data about companies before they go public from the internet or databases.

[0556] "Natural language processing technology" refers to computer technology used to understand and analyze human language.

[0557] "Growth potential" refers to an evaluation criterion that quantifies a company's potential for future growth.

[0558] A "machine learning algorithm" refers to a programming technique that learns patterns from data and uses them to make predictions and decisions.

[0559] "Means of simulation" refers to methods or mechanisms for virtually calculating a company's future stock price trends based on analysis results.

[0560] An "investment trust" refers to an investment product that is composed of a combination of stocks and other financial instruments from multiple companies.

[0561] "Means of construction" refers to the methods and mechanisms for generating investment trusts based on collected and analyzed information.

[0562] "Means of sale" refers to the methods and mechanisms for proposing and selling a constructed investment trust product to investors.

[0563] A "smartphone application" refers to a software program that runs on a smartphone.

[0564] "End users" refer to the users who ultimately use the system or product.

[0565] "Electronic payment" refers to electronic payment methods conducted via the internet.

[0566] System Configuration

[0567] The system implementing this invention is comprised of a server, a terminal, and a user. The server is responsible for information gathering, analysis, simulation, and construction of investment trusts. The terminal presents the constructed investment trusts to the user and handles sales and electronic payment processing. The user can refer to this information and purchase investment trusts.

[0568] Program processing

[0569] Server Processing

[0570] The server first collects information about companies before they go public from the internet. For this purpose, it uses web crawling technology and APIs (Application Programming Interfaces).

[0571] For example, a server retrieves information from a specific news portal stating that "Company X has raised funds."

[0572] Next, the collected information is analyzed using natural language processing (NLP) techniques. Specifically, text data is tokenized using libraries such as TextBlob, and keywords and phrases are extracted. Then, sentiment analysis is performed to determine whether the news is positive or negative. In addition, company growth indicators (such as the number of new customers, the amount of funding raised, and the progress of technology) are calculated and scored.

[0573] For example, the server analyzes information such as "Company X's number of employees increased by 30%" and evaluates this as a positive indicator of growth potential.

[0574] Next, based on the analysis results, we simulate the stock price trends of pre-IPO companies using a machine learning algorithm. To do this, we create a stock price prediction model using a machine learning model such as RandomForestRegressor and train it with historical data. Through the simulation, we generate prediction results for multiple scenarios (optimistic, neutral, and pessimistic).

[0575] For example, the server might output a result stating, "Company X is projected to see a 20% increase in its stock price over the next six months."

[0576] Subsequently, based on the simulation results, an investment trust is constructed by combining multiple pre-listing companies and investment products available on the market. The components of the investment trust (e.g., shares of company X and company Y) and their weights (e.g., the proportion of shares of each company) are then determined.

[0577] For example, the server "creates a portfolio including companies X, Y, and Z, and constructs it as investment trust ABC."

[0578] Terminal processing

[0579] The terminal provides product descriptions to general investors based on investment trust information provided by the server and sells the products. It also presents collected and analyzed data to users through a smartphone application and supports users in purchasing investment trusts using electronic payment functions.

[0580] User actions

[0581] Users can search for and apply to purchase investment trusts ABC through the online platform. This provides investment opportunities in promising companies before they go public and increases investment diversification.

[0582] Specific example

[0583] For example, if startup company X raises new funds and increases its number of employees, the server collects and analyzes this news and determines that it has high growth potential. It then creates an investment trust with other companies with growth potential and displays it to the user as a recommended investment trust. Users can view this information through a smartphone application and easily purchase the investment using the electronic payment function.

[0584] Example prompts for generative AI models

[0585] "Please explain how to gather the latest news on a specific startup company and assess its growth potential. Also, please explain in detail how to simulate stock price trends based on that assessment and construct an investment fund."

[0586] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0587] Step 1:

[0588] The server collects information about companies before they go public. Specifically, it retrieves data from news portals and official company websites on the internet using APIs and web crawling technologies. The input is the company name or search query, and the output is the collected text data. For example, it might retrieve a news article stating, "Company X has raised funds."

[0589] Step 2:

[0590] The server analyzes the collected information using natural language processing (NLP) techniques. Specifically, it tokenizes text data using the TextBlob library and extracts keywords and phrases. It performs sentiment analysis to determine whether the news is positive or negative and calculates company growth indicators (such as the number of new customers, the amount of funding raised, and the progress of technology). The input is the collected text data, and the output is the growth potential score and sentiment score as a result of the analysis.

[0591] Step 3:

[0592] The server uses machine learning algorithms to simulate the stock price trends of pre-IPO companies based on the analysis results. Specifically, it uses RandomForestRegressor to create a stock price prediction model and trains it with historical data. The simulation is performed under multiple scenarios (optimistic, neutral, pessimistic), and the prediction results for each scenario are output. The input is analysis data such as growth potential scores and sentiment scores, and the output is stock price prediction data. For example, one might get a result such as, "Company X is predicted to see a 20% increase in its stock price over the next six months."

[0593] Step 4:

[0594] The server constructs an investment trust based on the simulation results. Specifically, it constructs an investment trust by combining multiple pre-listed companies and investment products available on the market, and determines the weighting of each company's shares. The input is the simulation results, and the output is detailed information about the investment trust. For example, "Create a portfolio including companies X, Y, and Z, and construct it as investment trust ABC."

[0595] Step 5:

[0596] The terminal provides product descriptions and sales information to general investors based on investment trust information provided by the server. Specifically, it presents users with collected and analyzed data and details of investment trusts through a smartphone application. The input is detailed information about the investment trust, and the output is product descriptions and purchase screens provided to the user.

[0597] Step 6:

[0598] Users purchase investment trusts through a smartphone application. Specifically, they view detailed information about the displayed investment trusts and complete the purchase process using an electronic payment system. Inputs include the user's purchase instructions and payment information, while output is confirmation information that the purchase has been completed.

[0599] Example of a prompt:

[0600] "Please explain how to gather the latest news on a specific startup company and assess its growth potential. Also, please explain in detail how to simulate stock price trends based on that assessment and construct an investment fund."

[0601] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0602] The system of the present invention collects information on companies before they go public, analyzes that information, and evaluates the growth potential of those companies. Furthermore, it includes a process of simulating stock price trends based on the evaluation results, and then constructing and selling investment trusts based on those simulations. In addition, by combining it with an emotion engine that recognizes user emotions, it is possible to grasp user emotion data and use it to propose and adjust investment trusts. The following describes in detail the embodiments for which the present invention is specifically implemented.

[0603] Explain the program's processing in natural language.

[0604] Data collection

[0605] The server collects information about pre-IPO companies from the internet. To do this, it uses web crawling technology and APIs to retrieve data such as news articles, company press releases, and industry reports.

[0606] Specifically, the system accesses specific news portals and official company websites and automatically downloads relevant information. The retrieved data is stored in a database, categorized into fields such as news title, body text, publication date, and company name.

[0607] Data Analysis

[0608] The server analyzes the collected information using natural language processing (NLP) techniques. First, it tokenizes the text data and extracts important keywords and phrases.

[0609] Next, sentiment analysis is performed to determine whether the news content is positive or negative. Additionally, growth indicators for the company (such as the number of new customers, funding raised, and technological progress) are calculated, and a score is assigned based on these results.

[0610] Specifically, the server analyzes information such as "Company X's number of employees has increased by 30%" and evaluates this as a positive indicator of growth potential.

[0611] Modeling and Simulation

[0612] The server simulates the stock price trends of pre-IPO companies based on the analysis results. To do this, it uses machine learning algorithms to create a stock price prediction model and trains it using historical data.

[0613] The simulation generates prediction results for multiple scenarios (optimistic, neutral, and pessimistic).

[0614] Specifically, the server outputs the result, "Company X's stock price is projected to increase by 20% over the next six months."

[0615] Constructing an investment trust

[0616] Based on the simulation results, the server constructs an investment trust by combining multiple pre-IPO companies and investment products that can be traded on the market.

[0617] Determine the components of the investment trust (for example, the shares of company X and company Y) and their weights (for example, the proportion of shares of each company).

[0618] Specifically, the server creates a portfolio containing companies X, Y, and Z, and then constructs it as investment trust ABC.

[0619] Recognition and analysis of user emotions

[0620] The device uses an emotion engine to collect user emotion data. It analyzes the user's facial expressions and voice using a camera and microphone to identify their emotional state in real time.

[0621] The server analyzes this sentiment data to determine the user's investment risk preference. For example, it assesses whether the user feels anxious about risk.

[0622] Specifically, the device captures the user's facial expressions, and the server determines that "the user is feeling anxious."

[0623] Proposal and adjustment of investment trusts

[0624] The server optimizes investment fund recommendations based on the results of the emotion engine's analysis. For example, if the user indicates an optimistic sentiment, it will suggest high-risk investment funds.

[0625] Furthermore, it is possible to adjust the risk appetite of existing mutual funds based on user sentiment data. For example, if a user is feeling anxious, the portfolio can be restructured to further reduce risk.

[0626] In terms of specific operations, the server analyzes the user's emotional data and suggests investment trusts that match their risk tolerance.

[0627] Sales of investment trusts

[0628] The terminal provides product descriptions to general investors based on investment trust information provided by the server, and then sells the products.

[0629] Users can purchase investment trusts through online platforms. For example, a user can search for investment trusts from their home computer and submit a purchase request.

[0630] Performance Update

[0631] The server periodically collects new data to update the contents of the investment trust. The server collects the latest company information and analyzes it using natural language processing technology.

[0632] Furthermore, the AI ​​model is retrained to reflect new data and market trends, and the simulation results are updated.

[0633] Specifically, the server analyzes new information, such as "Company X has announced a new technology," and then revises its portfolio composition.

[0634] In this way, the present invention provides general investors with investment opportunities in companies before they go public, and further enhances investment diversity and adaptability by utilizing user sentiment data to propose and adjust investment trusts.

[0635] The following describes the processing flow.

[0636] Step 1:

[0637] The server collects information about pre-IPO companies from the internet. To do this, the server uses web crawling technology and APIs to retrieve data such as news articles, company press releases, and industry reports.

[0638] In terms of operation, the server accesses specific news portals or official company websites and automatically downloads relevant information. The retrieved data is then stored in a database, categorized into fields such as news title, body text, publication date, and company name.

[0639] Step 2:

[0640] The server analyzes the collected information using natural language processing (NLP) techniques. First, it tokenizes the text data and extracts important keywords and phrases.

[0641] Next, the server performs sentiment analysis to determine whether the news content is positive or negative. It also calculates the company's growth indicators (such as the number of new customers, the amount of funding raised, and the progress of technology) and scores the company based on the results.

[0642] Specifically, the server analyzes information such as "Company X's employee count has increased by 30%" and evaluates this as a positive indicator of growth potential.

[0643] Step 3:

[0644] The server simulates the stock price trends of pre-IPO companies based on the analysis results. To do this, it uses machine learning algorithms to create a stock price prediction model and trains it using historical data.

[0645] The simulation generates prediction results for multiple scenarios (optimistic, neutral, pessimistic). Specifically, the server outputs a result such as "Company X's stock price is projected to increase by 20% over the next six months."

[0646] Step 4:

[0647] The server constructs an investment fund based on the simulation results. First, it determines the combination of pre-listing companies and investment products that can be traded on the market.

[0648] Next, the server determines the components of the portfolio (for example, the shares of company X and company Y) and their weights (for example, the proportion of shares of each company). Specifically, the server "creates a portfolio containing companies X, Y, and Z, and constructs it as investment trust ABC."

[0649] Step 5:

[0650] The device uses an emotion engine to collect user emotion data. It analyzes the user's facial expressions and voice using the camera and microphone to identify their emotional state in real time.

[0651] In terms of specific operations, the device captures and analyzes the user's facial expressions. For example, the device might determine that "the user is showing positive emotions."

[0652] Step 6:

[0653] The server analyzes emotional data collected by the emotion engine to determine the user's investment risk preference. For example, it assesses whether the user feels anxious about risk.

[0654] In terms of specific operation, the server determines that "the user's risk tolerance is low based on sentiment data."

[0655] Step 7:

[0656] The server optimizes investment fund recommendations based on the results of the emotion engine's analysis. For example, if the user indicates an optimistic sentiment, it will suggest high-risk investment funds.

[0657] In terms of specific operations, the server makes suggestions based on sentiment data, such as "suggesting high-risk investment trusts to the user."

[0658] Step 8:

[0659] The server adjusts the risk appetite of existing mutual funds based on the user's emotional data. For example, if the user is feeling anxious, it will restructure the portfolio to further reduce risk.

[0660] In terms of specific operations, the server performs processes such as "adjusting the portfolio's risk ratio based on the user's emotional state."

[0661] Step 9:

[0662] The terminal provides product descriptions to general investors based on investment trust information provided by the server, and then sells the products.

[0663] In terms of specific actions, the terminal generates a prospectus for the investment trust and presents it to the user.

[0664] Step 10:

[0665] Users purchase investment trusts through an online platform. Specifically, users search for investment trusts from their home computers and submit purchase requests.

[0666] Step 11:

[0667] The server periodically collects new data to update the contents of the investment trust. The server collects the latest company information and analyzes it using natural language processing technology.

[0668] In terms of specific operations, the server analyzes new information, such as "Company X has announced a new technology," and then revises its portfolio composition.

[0669] In this way, the present invention provides general investors with investment opportunities in companies before they go public, and further enhances investment diversity and adaptability by utilizing user sentiment data to propose and adjust investment trusts.

[0670] (Example 2)

[0671] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0672] Making appropriate investment decisions regarding companies before they go public requires sophisticated data collection and analysis, but conventional systems have struggled to do this efficiently and accurately. Furthermore, the proposal and adjustment of investment products to suit individual investors' risk preferences are insufficient, and there is a need to improve investor satisfaction. Therefore, a system is needed to analyze company information and simulate stock price trends before an IPO.

[0673] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0674] In this invention, the server includes means for collecting information about a company before it goes public, means for analyzing the collected information using natural language processing technology and evaluating the company's growth potential, means for simulating the stock price trends of the pre-listing company using a machine learning algorithm based on the analysis results, means for constructing investment products based on the simulated stock price trends, means for collecting and analyzing user sentiment data in real time, means for adjusting the content of investment product proposals based on user sentiment data, and means for selling the constructed investment products. This makes it possible to collect and analyze information about companies before they go public, simulate stock price trends, and propose and adjust investment products based on user sentiment data.

[0675] A "pre-listing company" refers to a company that is in the stage before it is listed on the stock market.

[0676] "Means of collecting information" refers to technologies and devices that automatically acquire necessary information from the internet or other data sources.

[0677] "Natural language processing technology" refers to the technology used by computers to analyze and understand the language that humans use on a daily basis.

[0678] "Means for evaluating a company's growth potential" refers to methods and techniques for analyzing and evaluating a company's future growth capabilities based on collected information.

[0679] A "machine learning algorithm" refers to a type of artificial intelligence that automatically learns from data and makes predictions and decisions.

[0680] "Methods for simulating stock price trends" refer to methods and technologies for predicting future stock price movements of a company based on collected and analyzed data.

[0681] "Means of constructing investment products" refers to methods and techniques for designing and creating investment products such as investment trusts and portfolios based on simulation results.

[0682] "User emotional data" refers to information about a user's emotional state collected from their facial expressions, voice, behavior, etc.

[0683] "Means of collecting and analyzing data in real time" refers to technologies and equipment for collecting and quickly analyzing users' emotional states in real time.

[0684] "Means of adjusting the content of investment product proposals" refers to methods and technologies for changing the content and structure of investment products based on user sentiment data.

[0685] "Means of sale" refers to the methods and technologies used to offer the developed investment product to the market and enable users to purchase it.

[0686] This invention relates to a system that collects data on companies before they go public, analyzes that data to evaluate the companies' growth potential, and simulates stock price trends. Based on the simulation results, it constructs investment products, collects and analyzes user sentiment data to optimize investment proposals, and then provides and sells the constructed investment products to the market.

[0687] overview

[0688] 1. Data Collection

[0689] The server collects information about pre-IPO companies from the internet. This information collection uses web crawling technology and APIs (e.g., newspaper article APIs, official company APIs). Specifically, the server accesses news portals and official company websites, automatically downloading news articles such as "Company A announces new product" and saving them to a database.

[0690] 2. Data Analysis

[0691] The server analyzes the collected data using natural language processing technologies (e.g., NLTK, spaCy). It tokenizes the text data and extracts important keywords and phrases. It also performs sentiment analysis to determine whether the news is positive or negative. Based on this analysis, it calculates company growth indicators (e.g., number of new customers, progress of proprietary technology) and scores the company's growth potential.

[0692] 3. Modeling and Simulation

[0693] The server simulates the stock price trends of pre-IPO companies based on the analysis results. It creates a stock price prediction model using machine learning algorithms (e.g., random forest, neural network) and trains it with historical data. The simulation generates prediction results under multiple scenarios: optimistic, neutral, and pessimistic. For example, it might output a result such as, "Company A's predicted stock price increase rate is 15% over the next six months."

[0694] 4. Building an investment product

[0695] The server constructs an investment trust by combining multiple pre-IPO companies and other investment products based on the simulation results. It determines the components of the investment product (e.g., shares of company A, company B, and company C) and their weights (e.g., the proportion of shares of each company). Specifically, it "creates a portfolio including company A, company B, and company C, and constructs this as investment trust XYZ."

[0696] 5. Recognition and Analysis of User Sentiments

[0697] The device uses an emotion engine (e.g., camera, microphone) to collect user emotion data. It analyzes facial expressions and voice to identify the user's emotional state in real time. This data is sent to a server to analyze the user's investment risk preferences. For example, it might determine that "the user is feeling anxious."

[0698] 6. Proposing and adjusting investment products

[0699] Based on data obtained from the emotion engine, the server suggests investment trusts tailored to the user's risk tolerance. If the user is optimistic, it suggests high-risk investment products; conversely, if the user is anxious, it suggests low-risk investment products. Specifically, "it determines that the user is in a state where they can tolerate risk and suggests high-return investment products."

[0700] 7. Sale of investment products

[0701] The terminal is responsible for providing product descriptions and sales information about investment trusts to general investors based on information provided by the server. Users can purchase investment trusts through the online platform. For example, a user can search for "Investment Trust XYZ" from their home computer and submit a purchase request.

[0702] 8. Performance Updates

[0703] The server periodically collects new information and updates the contents of the investment trust. It reanalyzes the latest company information and retrains the AI ​​model (e.g., generative AI model) based on the new data. For example, it analyzes new information such as "Company A has raised new funds" and revises the portfolio composition.

[0704] Specific example

[0705] As a concrete example, the server collects news articles and analyzes information such as "Company A has launched a new product on the market." Based on the results of this analysis, it evaluates the company's growth potential and simulates stock price trends. It also collects user sentiment data in real time and proposes the optimal investment product according to the user's risk preference.

[0706] Example of a prompt

[0707] "Company A has launched a new product into the market. How does this affect Company A's growth potential?"

[0708] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0709] Step 1:

[0710] Data collection

[0711] The server collects information about pre-IPO companies from the internet. It uses web crawling technology and APIs to retrieve data from news articles, company press releases, industry reports, etc. Specifically, the server accesses news portals and official company websites and automatically downloads news articles such as "Company A has announced a new product."

[0712] Input: URL of a specific news portal or company website

[0713] Output: Raw data such as news articles, press releases, and industry reports.

[0714] Step 2:

[0715] Data Analysis

[0716] The server analyzes the collected data using natural language processing technologies (e.g., NLTK, spaCy). First, it tokenizes the text data and extracts important keywords and phrases. Next, it performs sentiment analysis to determine whether the news content is positive or negative. Based on this, it calculates company growth indicators (e.g., number of new customers, progress of its own technology) and scores the company's growth potential. Specifically, the server extracts and analyzes information such as "Company A's number of new customers increased by 50%."

[0717] Input: Collected raw data

[0718] Output: Tokenized text, sentiment analysis results, company growth metrics

[0719] Step 3:

[0720] Modeling and Simulation

[0721] The server simulates the stock price trends of pre-IPO companies based on the analysis results. It creates a stock price prediction model using machine learning algorithms (e.g., random forest, neural network) and trains it with historical data. The simulation generates prediction results for multiple scenarios: optimistic, neutral, and pessimistic. Specifically, the server outputs a result such as "Company A's predicted stock price increase rate is 15% over the next 6 months."

[0722] Input: Company growth indicators, historical stock price data

[0723] Output: Simulated stock price trends, multiple scenario prediction results

[0724] Step 4:

[0725] Building an investment product

[0726] Based on the simulation results, the server constructs an investment trust by combining multiple pre-IPO companies and other investment products. It determines the components of the investment product (e.g., shares of company A, company B, and company C) and their weights (e.g., the proportion of shares of each company). Specifically, the server "creates a portfolio including company A, company B, and company C, and constructs this as investment trust XYZ."

[0727] Input: Simulated stock price trends

[0728] Output: Details of the constructed mutual fund (components, ratios, etc.)

[0729] Step 5:

[0730] Recognition and analysis of user emotions

[0731] The device uses an emotion engine (e.g., camera, microphone) to collect user emotion data. It analyzes facial expressions and voice in real time to identify the emotional state and sends that data to the server. The server uses that data to analyze the user's investment risk preferences. Specifically, the device captures the user's facial expressions, and the server determines that "the user is feeling anxious."

[0732] Input: User facial expression data, voice data

[0733] Output: Identified emotional states, investment risk preference analysis results

[0734] Step 6:

[0735] Proposal and adjustment of investment products

[0736] Based on the analysis results of the emotion engine, the server suggests investment products that match the user's risk preference. If the user is optimistic, it suggests high-risk investment products; if the user is anxious, it suggests low-risk investment products. Specifically, the server determines that "the user is in a state where they can tolerate risk and suggests high-return investment products."

[0737] Input: Emotional engine analysis results, user's investment risk preference

[0738] Output: Adjusted investment product proposals

[0739] Step 7:

[0740] Sales of investment products

[0741] The terminal is responsible for providing product descriptions and sales information about investment trusts to general investors based on information provided by the server. Users can purchase investment trusts through the online platform. Specifically, a user searches for "Investment Trust XYZ" from their home computer and submits a purchase request.

[0742] Input: Investment trust information provided by the server

[0743] Output: Purchase request by user

[0744] Step 8:

[0745] Performance Update

[0746] The server regularly collects new information and updates the contents of the investment trust. It reanalyzes the latest company information and retrains the AI ​​model based on the new data. Specifically, the server analyzes new information such as "Company A has raised new funds" and revises the portfolio composition.

[0747] Input: New company information

[0748] Output: Updated investment trust details and retrained AI model

[0749] (Application Example 2)

[0750] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0751] Traditional investment management systems primarily relied on information from listed companies for their evaluations and recommendations, with few utilizing pre-IPO company information. Furthermore, they often failed to consider user sentiment, resulting in poorly optimized risk assessments and investment recommendations for individual users. This led to low investor satisfaction and a lack of investment diversity and adaptability.

[0752] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for collecting information about a company before it goes public, means for analyzing the collected information and evaluating the company's growth potential, means for simulating the stock price trends of the company before it goes public based on the analysis results, means for selling the constructed investment trust, means for collecting user sentiment data, means for analyzing the collected sentiment data and reflecting it in investment trust proposals, and means for users to purchase investment trusts using electronic payment. This makes it possible to utilize information about companies before they go public and to make investment proposals that take into account user sentiment.

[0753] A "pre-listing company" is a company that has not yet publicly traded its shares on the market but aims to go public in the future.

[0754] "Means of collecting information" refers to the technologies and methods used to obtain data from news articles, press releases, industry reports, etc., via the internet.

[0755] "Means of analyzing information and evaluating a company's growth potential" refers to technologies and methods for determining a company's growth potential using techniques such as natural language processing and sentiment analysis.

[0756] "Methods for simulating stock price trends" refer to technologies and methods that use machine learning algorithms to predict future stock price fluctuations from past data.

[0757] "Methods for constructing investment trusts" refer to the techniques and methods for forming a fund by combining multiple investment products based on simulation results.

[0758] "Means of selling constructed investment trusts" refers to the technologies and methods that provide information about investment trusts and enable general investors to purchase them.

[0759] "Means of collecting user emotional data" refers to technologies and methods that use cameras and microphones to capture users' facial expressions and voices in order to understand their emotional state.

[0760] "Means for analyzing emotional data" refers to technologies and methods for analyzing acquired emotional data and evaluating the user's emotional state.

[0761] "Means of reflecting in investment trust proposals" refers to technologies and methods for optimizing and proposing investment trust content and risk levels based on user sentiment data.

[0762] "Methods of purchase using electronic payment" refer to technologies and methods that allow users to purchase proposed investment trusts using electronic means.

[0763] Basic structure of the system program

[0764] The system for implementing this invention provides a program that collects and analyzes information about companies before they go public and handles the entire process from building investment trusts to selling them. The main components of the program are as follows:

[0765] 1. Data Acquisition Module:

[0766] The server collects information about pre-IPO companies, such as news articles, company press releases, and industry reports, via the internet. It uses web crawling technology and APIs to retrieve information from specific websites and store it in a database.

[0767] 2. Data Analysis Module:

[0768] The server analyzes the collected information using natural language processing (NLP) techniques to assess growth potential. Specifically, it tokenizes text data, extracts important keywords and phrases, and performs sentiment analysis. It then calculates and scores company growth indicators (e.g., number of new customers and amount of funding raised).

[0769] 3. Simulation Module:

[0770] Based on the analysis results, the server uses machine learning algorithms to create a stock price prediction model and simulate stock price trends. This prediction includes multiple scenarios (optimistic, neutral, and pessimistic) and forecasts future stock price increases and decreases.

[0771] 4. Investment Trust Construction Module:

[0772] Based on the simulation results, the server constructs an investment trust by combining multiple pre-IPO companies and tradable investment products. In this process, it determines the proportion of each company's shares and the overall portfolio composition.

[0773] 5. User sentiment collection module:

[0774] The device collects user emotion data using input devices such as cameras and microphones. It uses an emotion engine to analyze facial expressions and voice in real time to identify the user's emotional state.

[0775] 6. Emotional Data Analysis Module:

[0776] The server analyzes emotional data collected from users to evaluate their risk preferences and emotional state. For example, if a user is feeling anxious, the server uses that information to adjust investment recommendations to those with lower risk.

[0777] 7. Investment Proposal Module:

[0778] Based on the analysis results of the emotion engine, the server suggests investment trusts optimized for the user. If the user indicates optimistic emotions, it suggests high-risk investment trusts; if the user indicates anxiety, it suggests a portfolio with reduced risk.

[0779] 8. Electronic payment module:

[0780] The terminal assists users in purchasing investment trusts suggested by the server using electronic payment. Existing payment platforms (e.g., Stripe or PayPal) are used for processing electronic payments.

[0781] Specific example

[0782] For example, the system collects information on startup companies from news websites and analyzes positive information, such as when a company announces new technology. As a result, the company's growth potential is highly rated, and its stock price movement is simulated based on this information. When optimistic sentiment data from users is collected, high-risk investment trusts are suggested, and the user then makes an electronic payment through the app to purchase the suggested investment trusts.

[0783] Example of a prompt

[0784] "Explain how to optimize investment trusts by utilizing real-time user sentiment data in investment trust proposals and based on the results of an analysis of the growth potential of pre-IPO companies. The sentiment data will be collected using facial recognition technology, and the investment trust proposals will also include electronic payment functionality."

[0785] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0786] Step 1:

[0787] The server collects information about pre-IPO companies from the internet. Specifically, it uses web crawling technology and APIs to retrieve data such as news articles, company press releases, and industry reports. The input is the URL of a specific news portal or the company's official website, and the output is downloaded text data.

[0788] Step 2:

[0789] The server analyzes the collected information using natural language processing (NLP) techniques to evaluate the company's growth potential. Specifically, it tokenizes text data and extracts important keywords and phrases. The input is the text data collected in the previous step, and the output is the tokenized data and the results of sentiment analysis.

[0790] Step 3:

[0791] The server simulates the stock price trends of pre-IPO companies based on the analysis results. It uses a machine learning algorithm to create a stock price prediction model and learns from historical data. The input is the analysis results obtained in step 2, and the output is predicted stock price trend data under multiple scenarios.

[0792] Step 4:

[0793] Based on the simulation results, the server constructs an investment trust by combining multiple pre-IPO companies and tradable investment products on the market. The input is the stock price trend prediction data obtained in step 3, and the output is the portfolio of the constructed investment trust.

[0794] Step 5:

[0795] The device collects user emotion data using a camera and microphone. Specifically, it uses an emotion engine to analyze the user's facial expressions and voice in real time. The input is the user's facial expressions and voice data, and the output is the analyzed emotion state data.

[0796] Step 6:

[0797] The server analyzes the collected emotional data to evaluate the user's risk preference and emotional state. The input is the emotional state data obtained in step 5, and the output is emotional evaluation data corresponding to the user's risk preference.

[0798] Step 7:

[0799] The server proposes investment trusts optimized for the user based on the analysis results of the emotion engine. Specifically, if the user expresses optimistic emotions, it proposes high-risk investment trusts; if the user expresses anxiety, it proposes a portfolio with reduced risk. The input is the emotion evaluation data obtained in step 6 and the investment trust portfolio constructed in step 4, and the output is the proposed investment trust plan.

[0800] Step 8:

[0801] The terminal provides product descriptions to individual investors based on investment trust information provided by the server and assists with purchases via electronic payment. Specifically, it displays the proposed investment trust and guides the purchase process through the payment platform. The input is the investment trust plan proposed in step 7, and the output is a confirmation of the completed purchase.

[0802] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0803] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0804] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0805] [Third Embodiment]

[0806] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0807] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0808] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0809] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0810] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0811] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0812] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0813] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0814] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0815] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0816] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0817] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0818] The system of the present invention collects information on companies before they go public, analyzes that information, and evaluates the growth potential of the companies. Next, it includes a process of simulating stock price trends based on the evaluation results, and then constructing and selling investment trusts based on those simulations. Specific embodiments for implementing the present invention are described in detail below.

[0819] Explain the program's processing in natural language.

[0820] Data collection

[0821] The server collects information about pre-IPO companies from the internet. To do this, it uses web crawling technology and APIs (Application Programming Interfaces) to retrieve data such as news articles, company press releases, and industry reports.

[0822] For example, a server might collect information from a specific news portal stating that "Company X has raised funds."

[0823] Data Analysis

[0824] The server analyzes the collected information using natural language processing (NLP) techniques. Specifically, it tokenizes text data and extracts keywords and phrases.

[0825] Next, sentiment analysis is performed to determine whether the news is positive or negative. Additionally, company growth indicators (such as new customer numbers, funding raised, and technological progress) are calculated and scored.

[0826] For example, the server analyzes information such as "Company X's number of employees increased by 30%" and evaluates this as a positive indicator of growth potential.

[0827] Modeling and Simulation

[0828] The server simulates the stock price trends of pre-IPO companies based on the analysis results. To do this, it uses machine learning algorithms to create a stock price prediction model and trains it using historical data.

[0829] The simulation generates prediction results for multiple scenarios (optimistic, neutral, and pessimistic).

[0830] For example, the server might output a result stating, "Company X is projected to see a 20% increase in its stock price over the next six months."

[0831] Constructing an investment trust

[0832] Based on the simulation results, the server constructs an investment trust by combining multiple pre-IPO companies and investment products that can be traded on the market.

[0833] Determine the components of the investment trust (for example, the shares of company X and company Y) and their weights (for example, the proportion of shares of each company).

[0834] For example, the server "creates a portfolio including companies X, Y, and Z, and constructs it as investment trust ABC."

[0835] Sales of investment trusts

[0836] The terminal (the system of a financial institution or securities company engaged in the sale of investment trusts) provides product descriptions to general investors and sells them based on investment trust information provided from the server.

[0837] Users can purchase investment trust ABC through an online platform. For example, a user can search for investment trust ABC from their home computer and submit a purchase request.

[0838] Specific example

[0839] Example 1: Information gathering and analysis of startup company X

[0840] 1. The server collects the latest news about company X (e.g., funding amounts, employee growth, technological progress).

[0841] 2. The server uses natural language processing technology to analyze the news and evaluate the growth potential of company X (e.g., expansion plans through fundraising).

[0842] Example 2: Construction and sales of investment trust ABC

[0843] 1. The server constructs investment trust ABC by combining companies X, Y, and Z based on the simulation results.

[0844] 2. The terminal begins selling investment trust ABC to general investors, and users submit purchase applications online.

[0845] In this way, the present invention can provide general investors with investment opportunities in companies before they go public, thereby increasing investment diversity.

[0846] The following describes the processing flow.

[0847] Step 1:

[0848] The server collects information about pre-IPO companies from the internet. To do this, the server uses web crawling technology to retrieve data such as news articles, company press releases, and industry reports.

[0849] Specifically, the system accesses specific news portals and official company websites and automatically downloads relevant information. The retrieved data is then stored in a database, categorized into fields such as news title, body text, publication date, and company name.

[0850] Step 2:

[0851] The server analyzes the collected information using natural language processing (NLP) techniques. First, it tokenizes the text data and extracts important keywords and phrases.

[0852] Next, the server performs sentiment analysis to determine whether the news content is positive or negative. Furthermore, it calculates the company's growth indicators (such as the number of new customers, the amount of funding raised, and the progress of technology) and scores the results based on those.

[0853] Specifically, the server analyzes information such as "Company X's employee count has increased by 30%" and evaluates this as a positive indicator of growth potential.

[0854] Step 3:

[0855] The server simulates the stock price trends of pre-IPO companies based on the analysis results. To do this, it uses machine learning algorithms to create a stock price prediction model and trains it using historical data.

[0856] The simulation generates prediction results for multiple scenarios (optimistic, neutral, pessimistic). Specifically, the server outputs a result such as "Company X's stock price is projected to increase by 20% over the next six months."

[0857] Step 4:

[0858] The server constructs investment trusts based on the simulation results. First, it determines the combination of pre-listing companies and investment products available on the market.

[0859] Next, the server determines the components of the portfolio (for example, the shares of company X and company Y) and their weights (for example, the proportion of shares of each company). Specifically, the server "creates a portfolio containing companies X, Y, and Z, and constructs it as investment trust ABC."

[0860] Step 5:

[0861] The terminal receives investment trust information from the server and provides it to individual investors. The terminal generates an investment trust prospectus and presents it to the user.

[0862] Next, the user purchases investment trust ABC through an online platform. Specifically, the user searches for investment trust ABC from their home computer and submits a purchase request.

[0863] Step 6:

[0864] The server periodically collects new data to update the contents of the investment trust. The server collects the latest company information and analyzes it using natural language processing technology.

[0865] Afterward, the AI ​​model is retrained to reflect new data and market trends, and the simulation results are updated. Specifically, the server analyzes new information such as "Company X has announced a new technology" and revises the portfolio composition.

[0866] In this way, the present invention can provide general investors with investment opportunities in companies before they go public, thereby increasing investment diversity.

[0867] (Example 1)

[0868] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0869] Predicting a company's growth potential and stock price trends before its IPO, and providing investors with effective investment trusts, requires extremely high levels of expertise, making it difficult for the average investor. Furthermore, traditional methods involve time-consuming information gathering and analysis, making it difficult to make quick investment decisions.

[0870] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0871] In this invention, the server includes means for collecting information about companies from the internet, means for analyzing the collected information using natural language processing technology to evaluate the company's growth potential, and means for simulating the company's stock price trends based on the analysis results using a machine learning algorithm. This makes it possible to efficiently and quickly predict the growth potential and stock price trends of pre-listing companies and provide investment trusts that are easy for general investors to use.

[0872] The "Internet" is a global network and a system for exchanging and sharing information.

[0873] A "company" is an organization whose purpose is to provide products and services and generate revenue.

[0874] "Means of gathering information" refers to the technologies and tools used to obtain necessary data from sources such as news sites, press releases, and industry reports on the internet.

[0875] "Natural language processing technology" refers to technologies that enable computers to understand, analyze, and generate human language, and includes techniques such as tokenization of text data and sentiment analysis.

[0876] "Means of analysis" refers to the processes and tools used to structure collected information and extract useful insights.

[0877] "Growth potential" refers to a company's potential or ability to grow in the future, and is evaluated using indicators such as the amount of funding raised and the increase in the number of customers.

[0878] A "machine learning algorithm" is a mathematical model or method used to learn patterns from large amounts of data and make future predictions or classifications.

[0879] "Methods for simulating stock price trends" refer to systems that predict future stock prices based on past data, and these systems utilize machine learning models.

[0880] An "investment trust" is a financial product that combines multiple investment targets to diversify investments, aiming to provide investors with returns while reducing risk.

[0881] "Methods for constructing a trust" refers to the process and tools for selecting multiple investment targets and combining them into a single portfolio.

[0882] "Means of sale" refers to the platform or system used to provide the constructed investment trust to general investors.

[0883] The system of this invention mainly consists of a server, terminals, and users, and realizes a process of building and selling investment trusts by collecting information on companies before they go public, and by analyzing, evaluating, and simulating that information. Each processing step is described in detail below.

[0884] Information gathering

[0885] The server collects information about companies from the internet. To do this, it uses web crawling tools such as Python's BeautifulSoup and Scrapy to retrieve information from a wide range of data sources, including news sites, official company press releases, and industry reports.

[0886] Specific example:

[0887] The server accesses a specific news portal to collect information such as "Company X has raised new funds." It also retrieves the latest press release from Company X's official website and saves it to a local database.

[0888] Data Analysis

[0889] The server analyzes the collected information using natural language processing (NLP) techniques. Specifically, it tokenizes text data using libraries such as Python's NLTK and spaCy, and extracts keywords and important phrases. After that, it performs sentiment analysis to evaluate the company's growth potential.

[0890] Specific example:

[0891] The server reads the collected news articles and extracts keywords such as "fundraising," "employee growth," and "technological progress." Then, it performs sentiment analysis based on the extracted keywords and determines that "the news about company X is positive."

[0892] Modeling and Simulation

[0893] The server simulates the stock price trends of companies based on the analysis results. To do this, it uses machine learning algorithms such as TensorFlow and scikit-learn, training them with historical data. It makes predictions under different scenarios (optimistic, neutral, and pessimistic).

[0894] Specific example:

[0895] The server takes growth metrics for company X and trains a stock price prediction model. It then runs a simulation and generates a result based on an optimistic scenario: "Company X's stock price will increase by 20% over the next six months."

[0896] Constructing an investment trust

[0897] Based on the simulation results, the server constructs an investment trust by combining multiple companies and market trading products. Using portfolio theory, it determines the optimal combination and sets the contents of the investment trust (stocks of companies X, Y, and Z and their proportions).

[0898] Specific example:

[0899] The server generates a portfolio including companies X, Y, and Z based on their growth forecasts, and constructs investment trust ABC.

[0900] Sales of investment trusts

[0901] The terminal (investment trust sales system) provides product descriptions to general investors based on information provided by the server and then begins sales. Users (investors) can search for and purchase investment trusts through the online platform.

[0902] Specific example:

[0903] The terminal publishes detailed information about investment trust ABC on an online platform, allowing users to search for investment trust ABC from their home computers or smartphones and proceed with the purchase.

[0904] Example of a prompt

[0905] "Please describe in detail the algorithm used to collect information on companies before they go public and to evaluate their growth potential. Also, please detail the process from constructing an investment trust based on simulated stock price trends to selling it."

[0906] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0907] Step 1:

[0908] Information gathering

[0909] The server collects data about companies from multiple sources on the internet. Input data includes news sites, official company press releases, and industry reports. Web crawling tools such as BeautifulSoup and Scrapy are used to retrieve the data. This allows information such as new funding rounds for company X and the contents of press releases to be stored on the server.

[0910] Specific actions:

[0911] The server periodically accesses specific news portals and collects article data such as "Company X has raised funds."

[0912] The server downloads the latest press release document from company X's official website and saves it to its local database.

[0913] Step 2:

[0914] Data Analysis

[0915] The server analyzes the collected data using natural language processing (NLP) techniques. The input data is the text data collected in step 1. The data is tokenized using Python's NLTK and spaCy libraries, keywords and phrases are extracted, and sentiment analysis is performed. This yields numerical data for evaluating the growth potential of companies.

[0916] Specific actions:

[0917] The server reads the news article text and extracts important keywords and phrases such as "fundraising," "employee growth," and "technological progress."

[0918] The server performs sentiment analysis based on the extracted keywords and determines that "the news about company X is positive."

[0919] Step 3:

[0920] Modeling and Simulation

[0921] The server simulates the future stock price trends of companies based on the analysis results. The input data is the analysis results from step 2. A machine learning model is built using TensorFlow or scikit-learn and trained on historical data. This predicts the stock price trends of companies. The simulation provides prediction results for optimistic, neutral, and pessimistic scenarios.

[0922] Specific actions:

[0923] The server inputs the analysis results and historical stock price data into a machine learning model and trains a stock price prediction model based on the growth indicators of company X.

[0924] The server runs simulations based on each scenario and generates a result stating that "Company X's stock price is projected to increase by 20% over the next six months under an optimistic scenario."

[0925] Step 4:

[0926] Constructing an investment trust

[0927] The server constructs an investment trust by combining multiple companies and market trading products based on the simulation results. The input data is the simulation results from step 3. Using portfolio theory, the optimal combination is determined, and the contents of the investment trust (stocks of companies X, Y, and Z and their proportions) are decided.

[0928] Specific actions:

[0929] The server generates a portfolio based on growth forecasts for companies X, Y, and Z, and constructs investment trusts ABC.

[0930] The server calculates the proportion of shares in each company and determines the components of the investment trust, taking into account the balance between risk and return.

[0931] Step 5:

[0932] Sales of investment trusts

[0933] The terminal (investment trust sales system) provides product descriptions to general investors based on information provided by the server. The input data is the detailed information of the investment trust from step 4. The terminal publishes the investment trust on an online platform, making it searchable and available for purchase by users (investors).

[0934] Specific actions:

[0935] The terminal will publish detailed information about investment trust ABC on the online platform.

[0936] Users can search for investment trust ABC from their home computers or smartphones and proceed with the purchase.

[0937] In this way, the entire process, from information gathering to the sale of investment trusts, is automated and carried out efficiently.

[0938] (Application Example 1)

[0939] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0940] Traditional investment trust construction and sales systems have a problem in that they do not adequately collect, analyze, and evaluate information on companies before they go public, and therefore cannot appropriately provide investment opportunities. Furthermore, there is a lack of mechanisms that allow end users to easily select and purchase investment trust products, making it difficult to increase investment diversity. For this reason, there is a need for a system that efficiently provides investors with investment opportunities in promising pre-IPO companies and allows users to easily make investment decisions.

[0941] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0942] In this invention, the server includes means for collecting information about a company before it goes public; means for analyzing the collected information using natural language processing technology to evaluate the company's growth potential; means for simulating the stock price trends of the pre-listing company using a machine learning algorithm based on the analysis results; means for constructing an investment trust based on the simulated stock price trends; means for selling the constructed investment trust; and means for presenting the collected and analyzed data to end users through a smartphone application, and for users to purchase the investment trust via electronic payment. This makes it possible to collect and analyze detailed information about a pre-listing company, and to construct and sell an investment trust based on the evaluation results. Furthermore, it is possible to provide information to end users through a smartphone application and provide an environment in which they can easily purchase investment trusts.

[0943] A "pre-listing company" refers to a company that has not yet been listed on a stock exchange.

[0944] "Means of collecting information" refers to methods and systems for obtaining data about companies before they go public from the internet or databases.

[0945] "Natural language processing technology" refers to computer technology used to understand and analyze human language.

[0946] "Growth potential" refers to an evaluation criterion that quantifies a company's potential for future growth.

[0947] A "machine learning algorithm" refers to a programming technique that learns patterns from data and uses them to make predictions and decisions.

[0948] "Means of simulation" refers to methods or mechanisms for virtually calculating a company's future stock price trends based on analysis results.

[0949] An "investment trust" refers to an investment product that is composed of a combination of stocks and other financial instruments from multiple companies.

[0950] "Means of construction" refers to the methods and mechanisms for generating investment trusts based on collected and analyzed information.

[0951] "Means of sale" refers to the methods and mechanisms for proposing and selling a constructed investment trust product to investors.

[0952] A "smartphone application" refers to a software program that runs on a smartphone.

[0953] "End users" refer to the users who ultimately use the system or product.

[0954] "Electronic payment" refers to electronic payment methods conducted via the internet.

[0955] System Configuration

[0956] The system implementing this invention is comprised of a server, a terminal, and a user. The server is responsible for information gathering, analysis, simulation, and construction of investment trusts. The terminal presents the constructed investment trusts to the user and handles sales and electronic payment processing. The user can refer to this information and purchase investment trusts.

[0957] Program processing

[0958] Server Processing

[0959] The server first collects information about companies before they go public from the internet. For this purpose, it uses web crawling technology and APIs (Application Programming Interfaces).

[0960] For example, a server retrieves information from a specific news portal stating that "Company X has raised funds."

[0961] Next, the collected information is analyzed using natural language processing (NLP) techniques. Specifically, text data is tokenized using libraries such as TextBlob, and keywords and phrases are extracted. Then, sentiment analysis is performed to determine whether the news is positive or negative. In addition, company growth indicators (such as the number of new customers, the amount of funding raised, and the progress of technology) are calculated and scored.

[0962] For example, the server analyzes information such as "Company X's number of employees increased by 30%" and evaluates this as a positive indicator of growth potential.

[0963] Next, based on the analysis results, we simulate the stock price trends of pre-IPO companies using a machine learning algorithm. To do this, we create a stock price prediction model using a machine learning model such as RandomForestRegressor and train it with historical data. Through the simulation, we generate prediction results for multiple scenarios (optimistic, neutral, and pessimistic).

[0964] For example, the server might output a result stating, "Company X is projected to see a 20% increase in its stock price over the next six months."

[0965] Subsequently, based on the simulation results, an investment trust is constructed by combining multiple pre-listing companies and investment products available on the market. The components of the investment trust (e.g., shares of company X and company Y) and their weights (e.g., the proportion of shares of each company) are then determined.

[0966] For example, the server "creates a portfolio including companies X, Y, and Z, and constructs it as investment trust ABC."

[0967] Terminal processing

[0968] The terminal provides product descriptions to general investors based on investment trust information provided by the server and sells the products. It also presents collected and analyzed data to users through a smartphone application and supports users in purchasing investment trusts using electronic payment functions.

[0969] User actions

[0970] Users can search for and apply to purchase investment trusts ABC through the online platform. This provides investment opportunities in promising companies before they go public and increases investment diversification.

[0971] Specific example

[0972] For example, if startup company X raises new funds and increases its number of employees, the server collects and analyzes this news and determines that it has high growth potential. It then creates an investment trust with other companies with growth potential and displays it to the user as a recommended investment trust. Users can view this information through a smartphone application and easily purchase the investment using the electronic payment function.

[0973] Example prompts for generative AI models

[0974] "Please explain how to gather the latest news on a specific startup company and assess its growth potential. Also, please explain in detail how to simulate stock price trends based on that assessment and construct an investment fund."

[0975] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0976] Step 1:

[0977] The server collects information about companies before they go public. Specifically, it retrieves data from news portals and official company websites on the internet using APIs and web crawling technologies. The input is the company name or search query, and the output is the collected text data. For example, it might retrieve a news article stating, "Company X has raised funds."

[0978] Step 2:

[0979] The server analyzes the collected information using natural language processing (NLP) techniques. Specifically, it tokenizes text data using the TextBlob library and extracts keywords and phrases. It performs sentiment analysis to determine whether the news is positive or negative and calculates company growth indicators (such as the number of new customers, the amount of funding raised, and the progress of technology). The input is the collected text data, and the output is the growth potential score and sentiment score as a result of the analysis.

[0980] Step 3:

[0981] The server uses machine learning algorithms to simulate the stock price trends of pre-IPO companies based on the analysis results. Specifically, it uses RandomForestRegressor to create a stock price prediction model and trains it with historical data. The simulation is performed under multiple scenarios (optimistic, neutral, pessimistic), and the prediction results for each scenario are output. The input is analysis data such as growth potential scores and sentiment scores, and the output is stock price prediction data. For example, one might get a result such as, "Company X is predicted to see a 20% increase in its stock price over the next six months."

[0982] Step 4:

[0983] The server constructs an investment trust based on the simulation results. Specifically, it constructs an investment trust by combining multiple pre-listed companies and investment products available on the market, and determines the weighting of each company's shares. The input is the simulation results, and the output is detailed information about the investment trust. For example, "Create a portfolio including companies X, Y, and Z, and construct it as investment trust ABC."

[0984] Step 5:

[0985] The terminal provides product descriptions and sales information to general investors based on investment trust information provided by the server. Specifically, it presents users with collected and analyzed data and details of investment trusts through a smartphone application. The input is detailed information about the investment trust, and the output is product descriptions and purchase screens provided to the user.

[0986] Step 6:

[0987] Users purchase investment trusts through a smartphone application. Specifically, they view detailed information about the displayed investment trusts and complete the purchase process using an electronic payment system. Inputs include the user's purchase instructions and payment information, while output is confirmation information that the purchase has been completed.

[0988] Example of a prompt:

[0989] "Please explain how to gather the latest news on a specific startup company and assess its growth potential. Also, please explain in detail how to simulate stock price trends based on that assessment and construct an investment fund."

[0990] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0991] The system of the present invention collects information on companies before they go public, analyzes that information, and evaluates the growth potential of those companies. Furthermore, it includes a process of simulating stock price trends based on the evaluation results, and then constructing and selling investment trusts based on those simulations. In addition, by combining it with an emotion engine that recognizes user emotions, it is possible to grasp user emotion data and use it to propose and adjust investment trusts. The following describes in detail the embodiments for which the present invention is specifically implemented.

[0992] Explain the program's processing in natural language.

[0993] Data collection

[0994] The server collects information about pre-IPO companies from the internet. To do this, it uses web crawling technology and APIs to retrieve data such as news articles, company press releases, and industry reports.

[0995] Specifically, the system accesses specific news portals and official company websites and automatically downloads relevant information. The retrieved data is stored in a database, categorized into fields such as news title, body text, publication date, and company name.

[0996] Data Analysis

[0997] The server analyzes the collected information using natural language processing (NLP) techniques. First, it tokenizes the text data and extracts important keywords and phrases.

[0998] Next, sentiment analysis is performed to determine whether the news content is positive or negative. Additionally, growth indicators for the company (such as the number of new customers, funding raised, and technological progress) are calculated, and a score is assigned based on these results.

[0999] Specifically, the server analyzes information such as "Company X's number of employees has increased by 30%" and evaluates this as a positive indicator of growth potential.

[1000] Modeling and Simulation

[1001] The server simulates the stock price trends of pre-IPO companies based on the analysis results. To do this, it uses machine learning algorithms to create a stock price prediction model and trains it using historical data.

[1002] The simulation generates prediction results for multiple scenarios (optimistic, neutral, and pessimistic).

[1003] Specifically, the server outputs the result, "Company X's stock price is projected to increase by 20% over the next six months."

[1004] Constructing an investment trust

[1005] Based on the simulation results, the server constructs an investment trust by combining multiple pre-IPO companies and investment products that can be traded on the market.

[1006] Determine the components of the investment trust (for example, the shares of company X and company Y) and their weights (for example, the proportion of shares of each company).

[1007] Specifically, the server creates a portfolio containing companies X, Y, and Z, and then constructs it as investment trust ABC.

[1008] Recognition and analysis of user emotions

[1009] The device uses an emotion engine to collect user emotion data. It analyzes the user's facial expressions and voice using a camera and microphone to identify their emotional state in real time.

[1010] The server analyzes this sentiment data to determine the user's investment risk preference. For example, it assesses whether the user feels anxious about risk.

[1011] Specifically, the device captures the user's facial expressions, and the server determines that "the user is feeling anxious."

[1012] Proposal and adjustment of investment trusts

[1013] The server optimizes investment fund recommendations based on the results of the emotion engine's analysis. For example, if the user indicates an optimistic sentiment, it will suggest high-risk investment funds.

[1014] Furthermore, it is possible to adjust the risk appetite of existing mutual funds based on user sentiment data. For example, if a user is feeling anxious, the portfolio can be restructured to further reduce risk.

[1015] In terms of specific operations, the server analyzes the user's emotional data and suggests investment trusts that match their risk tolerance.

[1016] Sales of investment trusts

[1017] The terminal provides product descriptions to general investors based on investment trust information provided by the server, and then sells the products.

[1018] Users can purchase investment trusts through online platforms. For example, a user can search for investment trusts from their home computer and submit a purchase request.

[1019] Performance Update

[1020] The server periodically collects new data to update the contents of the investment trust. The server collects the latest company information and analyzes it using natural language processing technology.

[1021] Furthermore, the AI ​​model is retrained to reflect new data and market trends, and the simulation results are updated.

[1022] Specifically, the server analyzes new information, such as "Company X has announced a new technology," and then revises its portfolio composition.

[1023] In this way, the present invention provides general investors with investment opportunities in companies before they go public, and further enhances investment diversity and adaptability by utilizing user sentiment data to propose and adjust investment trusts.

[1024] The following describes the processing flow.

[1025] Step 1:

[1026] The server collects information about pre-IPO companies from the internet. To do this, the server uses web crawling technology and APIs to retrieve data such as news articles, company press releases, and industry reports.

[1027] In terms of operation, the server accesses specific news portals or official company websites and automatically downloads relevant information. The retrieved data is then stored in a database, categorized into fields such as news title, body text, publication date, and company name.

[1028] Step 2:

[1029] The server analyzes the collected information using natural language processing (NLP) techniques. First, it tokenizes the text data and extracts important keywords and phrases.

[1030] Next, the server performs sentiment analysis to determine whether the news content is positive or negative. It also calculates the company's growth indicators (such as the number of new customers, the amount of funding raised, and the progress of technology) and scores the company based on the results.

[1031] Specifically, the server analyzes information such as "Company X's employee count has increased by 30%" and evaluates this as a positive indicator of growth potential.

[1032] Step 3:

[1033] The server simulates the stock price trends of pre-IPO companies based on the analysis results. To do this, it uses machine learning algorithms to create a stock price prediction model and trains it using historical data.

[1034] The simulation generates prediction results for multiple scenarios (optimistic, neutral, pessimistic). Specifically, the server outputs a result such as "Company X's stock price is projected to increase by 20% over the next six months."

[1035] Step 4:

[1036] The server constructs an investment fund based on the simulation results. First, it determines the combination of pre-listing companies and investment products that can be traded on the market.

[1037] Next, the server determines the components of the portfolio (for example, the shares of company X and company Y) and their weights (for example, the proportion of shares of each company). Specifically, the server "creates a portfolio containing companies X, Y, and Z, and constructs it as investment trust ABC."

[1038] Step 5:

[1039] The device uses an emotion engine to collect user emotion data. It analyzes the user's facial expressions and voice using the camera and microphone to identify their emotional state in real time.

[1040] In terms of specific operations, the device captures and analyzes the user's facial expressions. For example, the device might determine that "the user is showing positive emotions."

[1041] Step 6:

[1042] The server analyzes emotional data collected by the emotion engine to determine the user's investment risk preference. For example, it assesses whether the user feels anxious about risk.

[1043] In terms of specific operation, the server determines that "the user's risk tolerance is low based on sentiment data."

[1044] Step 7:

[1045] The server optimizes investment fund recommendations based on the results of the emotion engine's analysis. For example, if the user indicates an optimistic sentiment, it will suggest high-risk investment funds.

[1046] In terms of specific operations, the server makes suggestions based on sentiment data, such as "suggesting high-risk investment trusts to the user."

[1047] Step 8:

[1048] The server adjusts the risk appetite of existing mutual funds based on the user's emotional data. For example, if the user is feeling anxious, it will restructure the portfolio to further reduce risk.

[1049] In terms of specific operations, the server performs processes such as "adjusting the portfolio's risk ratio based on the user's emotional state."

[1050] Step 9:

[1051] The terminal provides product descriptions to general investors based on investment trust information provided by the server, and then sells the products.

[1052] In terms of specific actions, the terminal generates a prospectus for the investment trust and presents it to the user.

[1053] Step 10:

[1054] Users purchase investment trusts through an online platform. Specifically, users search for investment trusts from their home computers and submit purchase requests.

[1055] Step 11:

[1056] The server periodically collects new data to update the contents of the investment trust. The server collects the latest company information and analyzes it using natural language processing technology.

[1057] In terms of specific operations, the server analyzes new information, such as "Company X has announced a new technology," and then revises its portfolio composition.

[1058] In this way, the present invention provides general investors with investment opportunities in companies before they go public, and further enhances investment diversity and adaptability by utilizing user sentiment data to propose and adjust investment trusts.

[1059] (Example 2)

[1060] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1061] Making appropriate investment decisions regarding companies before they go public requires sophisticated data collection and analysis, but conventional systems have struggled to do this efficiently and accurately. Furthermore, the proposal and adjustment of investment products to suit individual investors' risk preferences are insufficient, and there is a need to improve investor satisfaction. Therefore, a system is needed to analyze company information and simulate stock price trends before an IPO.

[1062] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1063] In this invention, the server includes means for collecting information about a company before it goes public, means for analyzing the collected information using natural language processing technology and evaluating the company's growth potential, means for simulating the stock price trends of the pre-listing company using a machine learning algorithm based on the analysis results, means for constructing investment products based on the simulated stock price trends, means for collecting and analyzing user sentiment data in real time, means for adjusting the content of investment product proposals based on user sentiment data, and means for selling the constructed investment products. This makes it possible to collect and analyze information about companies before they go public, simulate stock price trends, and propose and adjust investment products based on user sentiment data.

[1064] A "pre-listing company" refers to a company that is in the stage before it is listed on the stock market.

[1065] "Means of collecting information" refers to technologies and devices that automatically acquire necessary information from the internet or other data sources.

[1066] "Natural language processing technology" refers to the technology used by computers to analyze and understand the language that humans use on a daily basis.

[1067] "Means for evaluating a company's growth potential" refers to methods and techniques for analyzing and evaluating a company's future growth capabilities based on collected information.

[1068] A "machine learning algorithm" refers to a type of artificial intelligence that automatically learns from data and makes predictions and decisions.

[1069] "Methods for simulating stock price trends" refer to methods and technologies for predicting future stock price movements of a company based on collected and analyzed data.

[1070] "Means of constructing investment products" refers to methods and techniques for designing and creating investment products such as investment trusts and portfolios based on simulation results.

[1071] "User emotional data" refers to information about a user's emotional state collected from their facial expressions, voice, behavior, etc.

[1072] "Means of collecting and analyzing data in real time" refers to technologies and equipment for collecting and quickly analyzing users' emotional states in real time.

[1073] "Means of adjusting the content of investment product proposals" refers to methods and technologies for changing the content and structure of investment products based on user sentiment data.

[1074] "Means of sale" refers to the methods and technologies used to offer the developed investment product to the market and enable users to purchase it.

[1075] This invention relates to a system that collects data on companies before they go public, analyzes that data to evaluate the companies' growth potential, and simulates stock price trends. Based on the simulation results, it constructs investment products, collects and analyzes user sentiment data to optimize investment proposals, and then provides and sells the constructed investment products to the market.

[1076] overview

[1077] 1. Data Collection

[1078] The server collects information about pre-IPO companies from the internet. This information collection uses web crawling technology and APIs (e.g., newspaper article APIs, official company APIs). Specifically, the server accesses news portals and official company websites, automatically downloading news articles such as "Company A announces new product" and saving them to a database.

[1079] 2. Data Analysis

[1080] The server analyzes the collected data using natural language processing technologies (e.g., NLTK, spaCy). It tokenizes the text data and extracts important keywords and phrases. It also performs sentiment analysis to determine whether the news is positive or negative. Based on this analysis, it calculates company growth indicators (e.g., number of new customers, progress of proprietary technology) and scores the company's growth potential.

[1081] 3. Modeling and Simulation

[1082] The server simulates the stock price trends of pre-IPO companies based on the analysis results. It creates a stock price prediction model using machine learning algorithms (e.g., random forest, neural network) and trains it with historical data. The simulation generates prediction results under multiple scenarios: optimistic, neutral, and pessimistic. For example, it might output a result such as, "Company A's predicted stock price increase rate is 15% over the next six months."

[1083] 4. Building an investment product

[1084] The server constructs an investment trust by combining multiple pre-IPO companies and other investment products based on the simulation results. It determines the components of the investment product (e.g., shares of company A, company B, and company C) and their weights (e.g., the proportion of shares of each company). Specifically, it "creates a portfolio including company A, company B, and company C, and constructs this as investment trust XYZ."

[1085] 5. Recognition and Analysis of User Sentiments

[1086] The device uses an emotion engine (e.g., camera, microphone) to collect user emotion data. It analyzes facial expressions and voice to identify the user's emotional state in real time. This data is sent to a server to analyze the user's investment risk preferences. For example, it might determine that "the user is feeling anxious."

[1087] 6. Proposing and adjusting investment products

[1088] Based on data obtained from the emotion engine, the server suggests investment trusts tailored to the user's risk tolerance. If the user is optimistic, it suggests high-risk investment products; conversely, if the user is anxious, it suggests low-risk investment products. Specifically, "it determines that the user is in a state where they can tolerate risk and suggests high-return investment products."

[1089] 7. Sale of investment products

[1090] The terminal is responsible for providing product descriptions and sales information about investment trusts to general investors based on information provided by the server. Users can purchase investment trusts through the online platform. For example, a user can search for "Investment Trust XYZ" from their home computer and submit a purchase request.

[1091] 8. Performance Updates

[1092] The server periodically collects new information and updates the contents of the investment trust. It reanalyzes the latest company information and retrains the AI ​​model (e.g., generative AI model) based on the new data. For example, it analyzes new information such as "Company A has raised new funds" and revises the portfolio composition.

[1093] Specific example

[1094] As a concrete example, the server collects news articles and analyzes information such as "Company A has launched a new product on the market." Based on the results of this analysis, it evaluates the company's growth potential and simulates stock price trends. It also collects user sentiment data in real time and proposes the optimal investment product according to the user's risk preference.

[1095] Example of a prompt

[1096] "Company A has launched a new product into the market. How does this affect Company A's growth potential?"

[1097] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1098] Step 1:

[1099] Data collection

[1100] The server collects information about pre-IPO companies from the internet. It uses web crawling technology and APIs to retrieve data from news articles, company press releases, industry reports, etc. Specifically, the server accesses news portals and official company websites and automatically downloads news articles such as "Company A has announced a new product."

[1101] Input: URL of a specific news portal or company website

[1102] Output: Raw data such as news articles, press releases, and industry reports.

[1103] Step 2:

[1104] Data Analysis

[1105] The server analyzes the collected data using natural language processing technologies (e.g., NLTK, spaCy). First, it tokenizes the text data and extracts important keywords and phrases. Next, it performs sentiment analysis to determine whether the news content is positive or negative. Based on this, it calculates company growth indicators (e.g., number of new customers, progress of its own technology) and scores the company's growth potential. Specifically, the server extracts and analyzes information such as "Company A's number of new customers increased by 50%."

[1106] Input: Collected raw data

[1107] Output: Tokenized text, sentiment analysis results, company growth metrics

[1108] Step 3:

[1109] Modeling and Simulation

[1110] The server simulates the stock price trends of pre-IPO companies based on the analysis results. It creates a stock price prediction model using machine learning algorithms (e.g., random forest, neural network) and trains it with historical data. The simulation generates prediction results for multiple scenarios: optimistic, neutral, and pessimistic. Specifically, the server outputs a result such as "Company A's predicted stock price increase rate is 15% over the next 6 months."

[1111] Input: Company growth indicators, historical stock price data

[1112] Output: Simulated stock price trends, multiple scenario prediction results

[1113] Step 4:

[1114] Building an investment product

[1115] Based on the simulation results, the server constructs an investment trust by combining multiple pre-IPO companies and other investment products. It determines the components of the investment product (e.g., shares of company A, company B, and company C) and their weights (e.g., the proportion of shares of each company). Specifically, the server "creates a portfolio including company A, company B, and company C, and constructs this as investment trust XYZ."

[1116] Input: Simulated stock price trends

[1117] Output: Details of the constructed mutual fund (components, ratios, etc.)

[1118] Step 5:

[1119] Recognition and analysis of user emotions

[1120] The device uses an emotion engine (e.g., camera, microphone) to collect user emotion data. It analyzes facial expressions and voice in real time to identify the emotional state and sends that data to the server. The server uses that data to analyze the user's investment risk preferences. Specifically, the device captures the user's facial expressions, and the server determines that "the user is feeling anxious."

[1121] Input: User facial expression data, voice data

[1122] Output: Identified emotional states, investment risk preference analysis results

[1123] Step 6:

[1124] Proposal and adjustment of investment products

[1125] Based on the analysis results of the emotion engine, the server suggests investment products that match the user's risk preference. If the user is optimistic, it suggests high-risk investment products; if the user is anxious, it suggests low-risk investment products. Specifically, the server determines that "the user is in a state where they can tolerate risk and suggests high-return investment products."

[1126] Input: Emotional engine analysis results, user's investment risk preference

[1127] Output: Adjusted investment product proposals

[1128] Step 7:

[1129] Sales of investment products

[1130] The terminal is responsible for providing product descriptions and sales information about investment trusts to general investors based on information provided by the server. Users can purchase investment trusts through the online platform. Specifically, a user searches for "Investment Trust XYZ" from their home computer and submits a purchase request.

[1131] Input: Investment trust information provided by the server

[1132] Output: Purchase request by user

[1133] Step 8:

[1134] Performance Update

[1135] The server regularly collects new information and updates the contents of the investment trust. It reanalyzes the latest company information and retrains the AI ​​model based on the new data. Specifically, the server analyzes new information such as "Company A has raised new funds" and revises the portfolio composition.

[1136] Input: New company information

[1137] Output: Updated investment trust details and retrained AI model

[1138] (Application Example 2)

[1139] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1140] Traditional investment management systems primarily relied on information from listed companies for their evaluations and recommendations, with few utilizing pre-IPO company information. Furthermore, they often failed to consider user sentiment, resulting in poorly optimized risk assessments and investment recommendations for individual users. This led to low investor satisfaction and a lack of investment diversity and adaptability.

[1141] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for collecting information about a company before it goes public, means for analyzing the collected information and evaluating the company's growth potential, means for simulating the stock price trends of the company before it goes public based on the analysis results, means for selling the constructed investment trust, means for collecting user sentiment data, means for analyzing the collected sentiment data and reflecting it in investment trust proposals, and means for users to purchase investment trusts using electronic payment. This makes it possible to utilize information about companies before they go public and to make investment proposals that take into account user sentiment.

[1142] A "pre-listing company" is a company that has not yet publicly traded its shares on the market but aims to go public in the future.

[1143] "Means of collecting information" refers to the technologies and methods used to obtain data from news articles, press releases, industry reports, etc., via the internet.

[1144] "Means of analyzing information and evaluating a company's growth potential" refers to technologies and methods for determining a company's growth potential using techniques such as natural language processing and sentiment analysis.

[1145] "Methods for simulating stock price trends" refer to technologies and methods that use machine learning algorithms to predict future stock price fluctuations from past data.

[1146] "Methods for constructing investment trusts" refer to the techniques and methods for forming a fund by combining multiple investment products based on simulation results.

[1147] "Means of selling constructed investment trusts" refers to the technologies and methods that provide information about investment trusts and enable general investors to purchase them.

[1148] "Means of collecting user emotional data" refers to technologies and methods that use cameras and microphones to capture users' facial expressions and voices in order to understand their emotional state.

[1149] "Means for analyzing emotional data" refers to technologies and methods for analyzing acquired emotional data and evaluating the user's emotional state.

[1150] "Means of reflecting in investment trust proposals" refers to technologies and methods for optimizing and proposing investment trust content and risk levels based on user sentiment data.

[1151] "Methods of purchase using electronic payment" refer to technologies and methods that allow users to purchase proposed investment trusts using electronic means.

[1152] Basic structure of the system program

[1153] The system for implementing this invention provides a program that collects and analyzes information about companies before they go public and handles the entire process from building investment trusts to selling them. The main components of the program are as follows:

[1154] 1. Data Acquisition Module:

[1155] The server collects information about pre-IPO companies, such as news articles, company press releases, and industry reports, via the internet. It uses web crawling technology and APIs to retrieve information from specific websites and store it in a database.

[1156] 2. Data Analysis Module:

[1157] The server analyzes the collected information using natural language processing (NLP) techniques to assess growth potential. Specifically, it tokenizes text data, extracts important keywords and phrases, and performs sentiment analysis. It then calculates and scores company growth indicators (e.g., number of new customers and amount of funding raised).

[1158] 3. Simulation Module:

[1159] Based on the analysis results, the server uses machine learning algorithms to create a stock price prediction model and simulate stock price trends. This prediction includes multiple scenarios (optimistic, neutral, and pessimistic) and forecasts future stock price increases and decreases.

[1160] 4. Investment Trust Construction Module:

[1161] Based on the simulation results, the server constructs an investment trust by combining multiple pre-IPO companies and tradable investment products. In this process, it determines the proportion of each company's shares and the overall portfolio composition.

[1162] 5. User sentiment collection module:

[1163] The device collects user emotion data using input devices such as cameras and microphones. It uses an emotion engine to analyze facial expressions and voice in real time to identify the user's emotional state.

[1164] 6. Emotional Data Analysis Module:

[1165] The server analyzes emotional data collected from users to evaluate their risk preferences and emotional state. For example, if a user is feeling anxious, the server uses that information to adjust investment recommendations to those with lower risk.

[1166] 7. Investment Proposal Module:

[1167] Based on the analysis results of the emotion engine, the server suggests investment trusts optimized for the user. If the user indicates optimistic emotions, it suggests high-risk investment trusts; if the user indicates anxiety, it suggests a portfolio with reduced risk.

[1168] 8. Electronic payment module:

[1169] The terminal assists users in purchasing investment trusts suggested by the server using electronic payment. Existing payment platforms (e.g., Stripe or PayPal) are used for processing electronic payments.

[1170] Specific example

[1171] For example, the system collects information on startup companies from news websites and analyzes positive information, such as when a company announces new technology. As a result, the company's growth potential is highly rated, and its stock price movement is simulated based on this information. When optimistic sentiment data from users is collected, high-risk investment trusts are suggested, and the user then makes an electronic payment through the app to purchase the suggested investment trusts.

[1172] Example of a prompt

[1173] "Explain how to optimize investment trusts by utilizing real-time user sentiment data in investment trust proposals and based on the results of an analysis of the growth potential of pre-IPO companies. The sentiment data will be collected using facial recognition technology, and the investment trust proposals will also include electronic payment functionality."

[1174] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1175] Step 1:

[1176] The server collects information about pre-IPO companies from the internet. Specifically, it uses web crawling technology and APIs to retrieve data such as news articles, company press releases, and industry reports. The input is the URL of a specific news portal or the company's official website, and the output is downloaded text data.

[1177] Step 2:

[1178] The server analyzes the collected information using natural language processing (NLP) techniques to evaluate the company's growth potential. Specifically, it tokenizes text data and extracts important keywords and phrases. The input is the text data collected in the previous step, and the output is the tokenized data and the results of sentiment analysis.

[1179] Step 3:

[1180] The server simulates the stock price trends of pre-IPO companies based on the analysis results. It uses a machine learning algorithm to create a stock price prediction model and learns from historical data. The input is the analysis results obtained in step 2, and the output is predicted stock price trend data under multiple scenarios.

[1181] Step 4:

[1182] Based on the simulation results, the server constructs an investment trust by combining multiple pre-IPO companies and tradable investment products on the market. The input is the stock price trend prediction data obtained in step 3, and the output is the portfolio of the constructed investment trust.

[1183] Step 5:

[1184] The device collects user emotion data using a camera and microphone. Specifically, it uses an emotion engine to analyze the user's facial expressions and voice in real time. The input is the user's facial expressions and voice data, and the output is the analyzed emotion state data.

[1185] Step 6:

[1186] The server analyzes the collected emotional data to evaluate the user's risk preference and emotional state. The input is the emotional state data obtained in step 5, and the output is emotional evaluation data corresponding to the user's risk preference.

[1187] Step 7:

[1188] The server proposes investment trusts optimized for the user based on the analysis results of the emotion engine. Specifically, if the user expresses optimistic emotions, it proposes high-risk investment trusts; if the user expresses anxiety, it proposes a portfolio with reduced risk. The input is the emotion evaluation data obtained in step 6 and the investment trust portfolio constructed in step 4, and the output is the proposed investment trust plan.

[1189] Step 8:

[1190] The terminal provides product descriptions to individual investors based on investment trust information provided by the server and assists with purchases via electronic payment. Specifically, it displays the proposed investment trust and guides the purchase process through the payment platform. The input is the investment trust plan proposed in step 7, and the output is a confirmation of the completed purchase.

[1191] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1192] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1193] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[1194] [Fourth Embodiment]

[1195] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1196] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1197] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1198] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[1199] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[1200] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[1201] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[1202] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[1203] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[1204] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1205] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1206] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[1207] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1208] The system of the present invention collects information on companies before they go public, analyzes that information, and evaluates the growth potential of the companies. Next, it includes a process of simulating stock price trends based on the evaluation results, and then constructing and selling investment trusts based on those simulations. Specific embodiments for implementing the present invention are described in detail below.

[1209] Explain the program's processing in natural language.

[1210] Data collection

[1211] The server collects information about pre-IPO companies from the internet. To do this, it uses web crawling technology and APIs (Application Programming Interfaces) to retrieve data such as news articles, company press releases, and industry reports.

[1212] For example, a server might collect information from a specific news portal stating that "Company X has raised funds."

[1213] Data Analysis

[1214] The server analyzes the collected information using natural language processing (NLP) techniques. Specifically, it tokenizes text data and extracts keywords and phrases.

[1215] Next, sentiment analysis is performed to determine whether the news is positive or negative. Additionally, company growth indicators (such as new customer numbers, funding raised, and technological progress) are calculated and scored.

[1216] For example, the server analyzes information such as "Company X's number of employees increased by 30%" and evaluates this as a positive indicator of growth potential.

[1217] Modeling and Simulation

[1218] The server simulates the stock price trends of pre-IPO companies based on the analysis results. To do this, it uses machine learning algorithms to create a stock price prediction model and trains it using historical data.

[1219] The simulation generates prediction results for multiple scenarios (optimistic, neutral, and pessimistic).

[1220] For example, the server might output a result stating, "Company X is projected to see a 20% increase in its stock price over the next six months."

[1221] Constructing an investment trust

[1222] Based on the simulation results, the server constructs an investment trust by combining multiple pre-IPO companies and investment products that can be traded on the market.

[1223] Determine the components of the investment trust (for example, the shares of company X and company Y) and their weights (for example, the proportion of shares of each company).

[1224] For example, the server "creates a portfolio including companies X, Y, and Z, and constructs it as investment trust ABC."

[1225] Sales of investment trusts

[1226] The terminal (the system of a financial institution or securities company engaged in the sale of investment trusts) provides product descriptions to general investors and sells them based on investment trust information provided from the server.

[1227] Users can purchase investment trust ABC through an online platform. For example, a user can search for investment trust ABC from their home computer and submit a purchase request.

[1228] Specific example

[1229] Example 1: Information gathering and analysis of startup company X

[1230] 1. The server collects the latest news about company X (e.g., funding amounts, employee growth, technological progress).

[1231] 2. The server uses natural language processing technology to analyze the news and evaluate the growth potential of company X (e.g., expansion plans through fundraising).

[1232] Example 2: Construction and sales of investment trust ABC

[1233] 1. The server constructs investment trust ABC by combining companies X, Y, and Z based on the simulation results.

[1234] 2. The terminal begins selling investment trust ABC to general investors, and users submit purchase applications online.

[1235] In this way, the present invention can provide general investors with investment opportunities in companies before they go public, thereby increasing investment diversity.

[1236] The following describes the processing flow.

[1237] Step 1:

[1238] The server collects information about pre-IPO companies from the internet. To do this, the server uses web crawling technology to retrieve data such as news articles, company press releases, and industry reports.

[1239] Specifically, the system accesses specific news portals and official company websites and automatically downloads relevant information. The retrieved data is then stored in a database, categorized into fields such as news title, body text, publication date, and company name.

[1240] Step 2:

[1241] The server analyzes the collected information using natural language processing (NLP) techniques. First, it tokenizes the text data and extracts important keywords and phrases.

[1242] Next, the server performs sentiment analysis to determine whether the news content is positive or negative. Furthermore, it calculates the company's growth indicators (such as the number of new customers, the amount of funding raised, and the progress of technology) and scores the results based on those.

[1243] Specifically, the server analyzes information such as "Company X's employee count has increased by 30%" and evaluates this as a positive indicator of growth potential.

[1244] Step 3:

[1245] The server simulates the stock price trends of pre-IPO companies based on the analysis results. To do this, it uses machine learning algorithms to create a stock price prediction model and trains it using historical data.

[1246] The simulation generates prediction results for multiple scenarios (optimistic, neutral, pessimistic). Specifically, the server outputs a result such as "Company X's stock price is projected to increase by 20% over the next six months."

[1247] Step 4:

[1248] The server constructs investment trusts based on the simulation results. First, it determines the combination of pre-listing companies and investment products available on the market.

[1249] Next, the server determines the components of the portfolio (for example, the shares of company X and company Y) and their weights (for example, the proportion of shares of each company). Specifically, the server "creates a portfolio containing companies X, Y, and Z, and constructs it as investment trust ABC."

[1250] Step 5:

[1251] The terminal receives investment trust information from the server and provides it to individual investors. The terminal generates an investment trust prospectus and presents it to the user.

[1252] Next, the user purchases investment trust ABC through an online platform. Specifically, the user searches for investment trust ABC from their home computer and submits a purchase request.

[1253] Step 6:

[1254] The server periodically collects new data to update the contents of the investment trust. The server collects the latest company information and analyzes it using natural language processing technology.

[1255] Afterward, the AI ​​model is retrained to reflect new data and market trends, and the simulation results are updated. Specifically, the server analyzes new information such as "Company X has announced a new technology" and revises the portfolio composition.

[1256] In this way, the present invention can provide general investors with investment opportunities in companies before they go public, thereby increasing investment diversity.

[1257] (Example 1)

[1258] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1259] Predicting a company's growth potential and stock price trends before its IPO, and providing investors with effective investment trusts, requires extremely high levels of expertise, making it difficult for the average investor. Furthermore, traditional methods involve time-consuming information gathering and analysis, making it difficult to make quick investment decisions.

[1260] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1261] In this invention, the server includes means for collecting information about companies from the internet, means for analyzing the collected information using natural language processing technology to evaluate the company's growth potential, and means for simulating the company's stock price trends based on the analysis results using a machine learning algorithm. This makes it possible to efficiently and quickly predict the growth potential and stock price trends of pre-listing companies and provide investment trusts that are easy for general investors to use.

[1262] The "Internet" is a global network and a system for exchanging and sharing information.

[1263] A "company" is an organization whose purpose is to provide products and services and generate revenue.

[1264] "Means of gathering information" refers to the technologies and tools used to obtain necessary data from sources such as news sites, press releases, and industry reports on the internet.

[1265] "Natural language processing technology" refers to technologies that enable computers to understand, analyze, and generate human language, and includes techniques such as tokenization of text data and sentiment analysis.

[1266] "Means of analysis" refers to the processes and tools used to structure collected information and extract useful insights.

[1267] "Growth potential" refers to a company's potential or ability to grow in the future, and is evaluated using indicators such as the amount of funding raised and the increase in the number of customers.

[1268] A "machine learning algorithm" is a mathematical model or method used to learn patterns from large amounts of data and make future predictions or classifications.

[1269] "Methods for simulating stock price trends" refer to systems that predict future stock prices based on past data, and these systems utilize machine learning models.

[1270] An "investment trust" is a financial product that combines multiple investment targets to diversify investments, aiming to provide investors with returns while reducing risk.

[1271] "Methods for constructing a trust" refers to the process and tools for selecting multiple investment targets and combining them into a single portfolio.

[1272] "Means of sale" refers to the platform or system used to provide the constructed investment trust to general investors.

[1273] The system of this invention mainly consists of a server, terminals, and users, and realizes a process of building and selling investment trusts by collecting information on companies before they go public, and by analyzing, evaluating, and simulating that information. Each processing step is described in detail below.

[1274] Information gathering

[1275] The server collects information about companies from the internet. To do this, it uses web crawling tools such as Python's BeautifulSoup and Scrapy to retrieve information from a wide range of data sources, including news sites, official company press releases, and industry reports.

[1276] Specific example:

[1277] The server accesses a specific news portal to collect information such as "Company X has raised new funds." It also retrieves the latest press release from Company X's official website and saves it to a local database.

[1278] Data Analysis

[1279] The server analyzes the collected information using natural language processing (NLP) techniques. Specifically, it tokenizes text data using libraries such as Python's NLTK and spaCy, and extracts keywords and important phrases. After that, it performs sentiment analysis to evaluate the company's growth potential.

[1280] Specific example:

[1281] The server reads the collected news articles and extracts keywords such as "fundraising," "employee growth," and "technological progress." Then, it performs sentiment analysis based on the extracted keywords and determines that "the news about company X is positive."

[1282] Modeling and Simulation

[1283] The server simulates the stock price trends of companies based on the analysis results. To do this, it uses machine learning algorithms such as TensorFlow and scikit-learn, training them with historical data. It makes predictions under different scenarios (optimistic, neutral, and pessimistic).

[1284] Specific example:

[1285] The server takes growth metrics for company X and trains a stock price prediction model. It then runs a simulation and generates a result based on an optimistic scenario: "Company X's stock price will increase by 20% over the next six months."

[1286] Constructing an investment trust

[1287] Based on the simulation results, the server constructs an investment trust by combining multiple companies and market trading products. Using portfolio theory, it determines the optimal combination and sets the contents of the investment trust (stocks of companies X, Y, and Z and their proportions).

[1288] Specific example:

[1289] The server generates a portfolio including companies X, Y, and Z based on their growth forecasts, and constructs investment trust ABC.

[1290] Sales of investment trusts

[1291] The terminal (investment trust sales system) provides product descriptions to general investors based on information provided by the server and then begins sales. Users (investors) can search for and purchase investment trusts through the online platform.

[1292] Specific example:

[1293] The terminal publishes detailed information about investment trust ABC on an online platform, allowing users to search for investment trust ABC from their home computers or smartphones and proceed with the purchase.

[1294] Example of a prompt

[1295] "Please describe in detail the algorithm used to collect information on companies before they go public and to evaluate their growth potential. Also, please detail the process from constructing an investment trust based on simulated stock price trends to selling it."

[1296] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1297] Step 1:

[1298] Information gathering

[1299] The server collects data about companies from multiple sources on the internet. Input data includes news sites, official company press releases, and industry reports. Web crawling tools such as BeautifulSoup and Scrapy are used to retrieve the data. This allows information such as new funding rounds for company X and the contents of press releases to be stored on the server.

[1300] Specific actions:

[1301] The server periodically accesses specific news portals and collects article data such as "Company X has raised funds."

[1302] The server downloads the latest press release document from company X's official website and saves it to its local database.

[1303] Step 2:

[1304] Data Analysis

[1305] The server analyzes the collected data using natural language processing (NLP) techniques. The input data is the text data collected in step 1. The data is tokenized using Python's NLTK and spaCy libraries, keywords and phrases are extracted, and sentiment analysis is performed. This yields numerical data for evaluating the growth potential of companies.

[1306] Specific actions:

[1307] The server reads the news article text and extracts important keywords and phrases such as "fundraising," "employee growth," and "technological progress."

[1308] The server performs sentiment analysis based on the extracted keywords and determines that "the news about company X is positive."

[1309] Step 3:

[1310] Modeling and Simulation

[1311] The server simulates the future stock price trends of companies based on the analysis results. The input data is the analysis results from step 2. A machine learning model is built using TensorFlow or scikit-learn and trained on historical data. This predicts the stock price trends of companies. The simulation provides prediction results for optimistic, neutral, and pessimistic scenarios.

[1312] Specific actions:

[1313] The server inputs the analysis results and historical stock price data into a machine learning model and trains a stock price prediction model based on the growth indicators of company X.

[1314] The server runs simulations based on each scenario and generates a result stating that "Company X's stock price is projected to increase by 20% over the next six months under an optimistic scenario."

[1315] Step 4:

[1316] Constructing an investment trust

[1317] The server constructs an investment trust by combining multiple companies and market trading products based on the simulation results. The input data is the simulation results from step 3. Using portfolio theory, the optimal combination is determined, and the contents of the investment trust (stocks of companies X, Y, and Z and their proportions) are decided.

[1318] Specific actions:

[1319] The server generates a portfolio based on growth forecasts for companies X, Y, and Z, and constructs investment trusts ABC.

[1320] The server calculates the proportion of shares in each company and determines the components of the investment trust, taking into account the balance between risk and return.

[1321] Step 5:

[1322] Sales of investment trusts

[1323] The terminal (investment trust sales system) provides product descriptions to general investors based on information provided by the server. The input data is the detailed information of the investment trust from step 4. The terminal publishes the investment trust on an online platform, making it searchable and available for purchase by users (investors).

[1324] Specific actions:

[1325] The terminal will publish detailed information about investment trust ABC on the online platform.

[1326] Users can search for investment trust ABC from their home computers or smartphones and proceed with the purchase.

[1327] In this way, the entire process, from information gathering to the sale of investment trusts, is automated and carried out efficiently.

[1328] (Application Example 1)

[1329] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1330] Traditional investment trust construction and sales systems have a problem in that they do not adequately collect, analyze, and evaluate information on companies before they go public, and therefore cannot appropriately provide investment opportunities. Furthermore, there is a lack of mechanisms that allow end users to easily select and purchase investment trust products, making it difficult to increase investment diversity. For this reason, there is a need for a system that efficiently provides investors with investment opportunities in promising pre-IPO companies and allows users to easily make investment decisions.

[1331] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1332] In this invention, the server includes means for collecting information about a company before it goes public; means for analyzing the collected information using natural language processing technology to evaluate the company's growth potential; means for simulating the stock price trends of the pre-listing company using a machine learning algorithm based on the analysis results; means for constructing an investment trust based on the simulated stock price trends; means for selling the constructed investment trust; and means for presenting the collected and analyzed data to end users through a smartphone application, and for users to purchase the investment trust via electronic payment. This makes it possible to collect and analyze detailed information about a pre-listing company, and to construct and sell an investment trust based on the evaluation results. Furthermore, it is possible to provide information to end users through a smartphone application and provide an environment in which they can easily purchase investment trusts.

[1333] A "pre-listing company" refers to a company that has not yet been listed on a stock exchange.

[1334] "Means of collecting information" refers to methods and systems for obtaining data about companies before they go public from the internet or databases.

[1335] "Natural language processing technology" refers to computer technology used to understand and analyze human language.

[1336] "Growth potential" refers to an evaluation criterion that quantifies a company's potential for future growth.

[1337] A "machine learning algorithm" refers to a programming technique that learns patterns from data and uses them to make predictions and decisions.

[1338] "Means of simulation" refers to methods or mechanisms for virtually calculating a company's future stock price trends based on analysis results.

[1339] An "investment trust" refers to an investment product that is composed of a combination of stocks and other financial instruments from multiple companies.

[1340] "Means of construction" refers to the methods and mechanisms for generating investment trusts based on collected and analyzed information.

[1341] "Means of sale" refers to the methods and mechanisms for proposing and selling a constructed investment trust product to investors.

[1342] A "smartphone application" refers to a software program that runs on a smartphone.

[1343] "End users" refer to the users who ultimately use the system or product.

[1344] "Electronic payment" refers to electronic payment methods conducted via the internet.

[1345] System Configuration

[1346] The system implementing this invention is comprised of a server, a terminal, and a user. The server is responsible for information gathering, analysis, simulation, and construction of investment trusts. The terminal presents the constructed investment trusts to the user and handles sales and electronic payment processing. The user can refer to this information and purchase investment trusts.

[1347] Program processing

[1348] Server Processing

[1349] The server first collects information about companies before they go public from the internet. For this purpose, it uses web crawling technology and APIs (Application Programming Interfaces).

[1350] For example, a server retrieves information from a specific news portal stating that "Company X has raised funds."

[1351] Next, the collected information is analyzed using natural language processing (NLP) techniques. Specifically, text data is tokenized using libraries such as TextBlob, and keywords and phrases are extracted. Then, sentiment analysis is performed to determine whether the news is positive or negative. In addition, company growth indicators (such as the number of new customers, the amount of funding raised, and the progress of technology) are calculated and scored.

[1352] For example, the server analyzes information such as "Company X's number of employees increased by 30%" and evaluates this as a positive indicator of growth potential.

[1353] Next, based on the analysis results, we simulate the stock price trends of pre-IPO companies using a machine learning algorithm. To do this, we create a stock price prediction model using a machine learning model such as RandomForestRegressor and train it with historical data. Through the simulation, we generate prediction results for multiple scenarios (optimistic, neutral, and pessimistic).

[1354] For example, the server might output a result stating, "Company X is projected to see a 20% increase in its stock price over the next six months."

[1355] Subsequently, based on the simulation results, an investment trust is constructed by combining multiple pre-listing companies and investment products available on the market. The components of the investment trust (e.g., shares of company X and company Y) and their weights (e.g., the proportion of shares of each company) are then determined.

[1356] For example, the server "creates a portfolio including companies X, Y, and Z, and constructs it as investment trust ABC."

[1357] Terminal processing

[1358] The terminal provides product descriptions to general investors based on investment trust information provided by the server and sells the products. It also presents collected and analyzed data to users through a smartphone application and supports users in purchasing investment trusts using electronic payment functions.

[1359] User actions

[1360] Users can search for and apply to purchase investment trusts ABC through the online platform. This provides investment opportunities in promising companies before they go public and increases investment diversification.

[1361] Specific example

[1362] For example, if startup company X raises new funds and increases its number of employees, the server collects and analyzes this news and determines that it has high growth potential. It then creates an investment trust with other companies with growth potential and displays it to the user as a recommended investment trust. Users can view this information through a smartphone application and easily purchase the investment using the electronic payment function.

[1363] Example prompts for generative AI models

[1364] "Please explain how to gather the latest news on a specific startup company and assess its growth potential. Also, please explain in detail how to simulate stock price trends based on that assessment and construct an investment fund."

[1365] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1366] Step 1:

[1367] The server collects information about companies before they go public. Specifically, it retrieves data from news portals and official company websites on the internet using APIs and web crawling technologies. The input is the company name or search query, and the output is the collected text data. For example, it might retrieve a news article stating, "Company X has raised funds."

[1368] Step 2:

[1369] The server analyzes the collected information using natural language processing (NLP) techniques. Specifically, it tokenizes text data using the TextBlob library and extracts keywords and phrases. It performs sentiment analysis to determine whether the news is positive or negative and calculates company growth indicators (such as the number of new customers, the amount of funding raised, and the progress of technology). The input is the collected text data, and the output is the growth potential score and sentiment score as a result of the analysis.

[1370] Step 3:

[1371] The server uses machine learning algorithms to simulate the stock price trends of pre-IPO companies based on the analysis results. Specifically, it uses RandomForestRegressor to create a stock price prediction model and trains it with historical data. The simulation is performed under multiple scenarios (optimistic, neutral, pessimistic), and the prediction results for each scenario are output. The input is analysis data such as growth potential scores and sentiment scores, and the output is stock price prediction data. For example, one might get a result such as, "Company X is predicted to see a 20% increase in its stock price over the next six months."

[1372] Step 4:

[1373] The server constructs an investment trust based on the simulation results. Specifically, it constructs an investment trust by combining multiple pre-listed companies and investment products available on the market, and determines the weighting of each company's shares. The input is the simulation results, and the output is detailed information about the investment trust. For example, "Create a portfolio including companies X, Y, and Z, and construct it as investment trust ABC."

[1374] Step 5:

[1375] The terminal provides product descriptions and sales information to general investors based on investment trust information provided by the server. Specifically, it presents users with collected and analyzed data and details of investment trusts through a smartphone application. The input is detailed information about the investment trust, and the output is product descriptions and purchase screens provided to the user.

[1376] Step 6:

[1377] Users purchase investment trusts through a smartphone application. Specifically, they view detailed information about the displayed investment trusts and complete the purchase process using an electronic payment system. Inputs include the user's purchase instructions and payment information, while output is confirmation information that the purchase has been completed.

[1378] Example of a prompt:

[1379] "Please explain how to gather the latest news on a specific startup company and assess its growth potential. Also, please explain in detail how to simulate stock price trends based on that assessment and construct an investment fund."

[1380] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1381] The system of the present invention collects information on companies before they go public, analyzes that information, and evaluates the growth potential of those companies. Furthermore, it includes a process of simulating stock price trends based on the evaluation results, and then constructing and selling investment trusts based on those simulations. In addition, by combining it with an emotion engine that recognizes user emotions, it is possible to grasp user emotion data and use it to propose and adjust investment trusts. The following describes in detail the embodiments for which the present invention is specifically implemented.

[1382] Explain the program's processing in natural language.

[1383] Data collection

[1384] The server collects information about pre-IPO companies from the internet. To do this, it uses web crawling technology and APIs to retrieve data such as news articles, company press releases, and industry reports.

[1385] Specifically, the system accesses specific news portals and official company websites and automatically downloads relevant information. The retrieved data is stored in a database, categorized into fields such as news title, body text, publication date, and company name.

[1386] Data Analysis

[1387] The server analyzes the collected information using natural language processing (NLP) techniques. First, it tokenizes the text data and extracts important keywords and phrases.

[1388] Next, sentiment analysis is performed to determine whether the news content is positive or negative. Additionally, growth indicators for the company (such as the number of new customers, funding raised, and technological progress) are calculated, and a score is assigned based on these results.

[1389] Specifically, the server analyzes information such as "Company X's number of employees has increased by 30%" and evaluates this as a positive indicator of growth potential.

[1390] Modeling and Simulation

[1391] The server simulates the stock price trends of pre-IPO companies based on the analysis results. To do this, it uses machine learning algorithms to create a stock price prediction model and trains it using historical data.

[1392] The simulation generates prediction results for multiple scenarios (optimistic, neutral, and pessimistic).

[1393] Specifically, the server outputs the result, "Company X's stock price is projected to increase by 20% over the next six months."

[1394] Constructing an investment trust

[1395] Based on the simulation results, the server constructs an investment trust by combining multiple pre-IPO companies and investment products that can be traded on the market.

[1396] Determine the components of the investment trust (for example, the shares of company X and company Y) and their weights (for example, the proportion of shares of each company).

[1397] Specifically, the server creates a portfolio containing companies X, Y, and Z, and then constructs it as investment trust ABC.

[1398] Recognition and analysis of user emotions

[1399] The device uses an emotion engine to collect user emotion data. It analyzes the user's facial expressions and voice using a camera and microphone to identify their emotional state in real time.

[1400] The server analyzes this sentiment data to determine the user's investment risk preference. For example, it assesses whether the user feels anxious about risk.

[1401] Specifically, the device captures the user's facial expressions, and the server determines that "the user is feeling anxious."

[1402] Proposal and adjustment of investment trusts

[1403] The server optimizes investment fund recommendations based on the results of the emotion engine's analysis. For example, if the user indicates an optimistic sentiment, it will suggest high-risk investment funds.

[1404] Furthermore, it is possible to adjust the risk appetite of existing mutual funds based on user sentiment data. For example, if a user is feeling anxious, the portfolio can be restructured to further reduce risk.

[1405] In terms of specific operations, the server analyzes the user's emotional data and suggests investment trusts that match their risk tolerance.

[1406] Sales of investment trusts

[1407] The terminal provides product descriptions to general investors based on investment trust information provided by the server, and then sells the products.

[1408] Users can purchase investment trusts through online platforms. For example, a user can search for investment trusts from their home computer and submit a purchase request.

[1409] Performance Update

[1410] The server periodically collects new data to update the contents of the investment trust. The server collects the latest company information and analyzes it using natural language processing technology.

[1411] Furthermore, the AI ​​model is retrained to reflect new data and market trends, and the simulation results are updated.

[1412] Specifically, the server analyzes new information, such as "Company X has announced a new technology," and then revises its portfolio composition.

[1413] In this way, the present invention provides general investors with investment opportunities in companies before they go public, and further enhances investment diversity and adaptability by utilizing user sentiment data to propose and adjust investment trusts.

[1414] The following describes the processing flow.

[1415] Step 1:

[1416] The server collects information about pre-IPO companies from the internet. To do this, the server uses web crawling technology and APIs to retrieve data such as news articles, company press releases, and industry reports.

[1417] In terms of operation, the server accesses specific news portals or official company websites and automatically downloads relevant information. The retrieved data is then stored in a database, categorized into fields such as news title, body text, publication date, and company name.

[1418] Step 2:

[1419] The server analyzes the collected information using natural language processing (NLP) techniques. First, it tokenizes the text data and extracts important keywords and phrases.

[1420] Next, the server performs sentiment analysis to determine whether the news content is positive or negative. It also calculates the company's growth indicators (such as the number of new customers, the amount of funding raised, and the progress of technology) and scores the company based on the results.

[1421] Specifically, the server analyzes information such as "Company X's employee count has increased by 30%" and evaluates this as a positive indicator of growth potential.

[1422] Step 3:

[1423] The server simulates the stock price trends of pre-IPO companies based on the analysis results. To do this, it uses machine learning algorithms to create a stock price prediction model and trains it using historical data.

[1424] The simulation generates prediction results for multiple scenarios (optimistic, neutral, pessimistic). Specifically, the server outputs a result such as "Company X's stock price is projected to increase by 20% over the next six months."

[1425] Step 4:

[1426] The server constructs an investment fund based on the simulation results. First, it determines the combination of pre-listing companies and investment products that can be traded on the market.

[1427] Next, the server determines the components of the portfolio (for example, the shares of company X and company Y) and their weights (for example, the proportion of shares of each company). Specifically, the server "creates a portfolio containing companies X, Y, and Z, and constructs it as investment trust ABC."

[1428] Step 5:

[1429] The device uses an emotion engine to collect user emotion data. It analyzes the user's facial expressions and voice using the camera and microphone to identify their emotional state in real time.

[1430] In terms of specific operations, the device captures and analyzes the user's facial expressions. For example, the device might determine that "the user is showing positive emotions."

[1431] Step 6:

[1432] The server analyzes emotional data collected by the emotion engine to determine the user's investment risk preference. For example, it assesses whether the user feels anxious about risk.

[1433] In terms of specific operation, the server determines that "the user's risk tolerance is low based on sentiment data."

[1434] Step 7:

[1435] The server optimizes investment fund recommendations based on the results of the emotion engine's analysis. For example, if the user indicates an optimistic sentiment, it will suggest high-risk investment funds.

[1436] In terms of specific operations, the server makes suggestions based on sentiment data, such as "suggesting high-risk investment trusts to the user."

[1437] Step 8:

[1438] The server adjusts the risk appetite of existing mutual funds based on the user's emotional data. For example, if the user is feeling anxious, it will restructure the portfolio to further reduce risk.

[1439] In terms of specific operations, the server performs processes such as "adjusting the portfolio's risk ratio based on the user's emotional state."

[1440] Step 9:

[1441] The terminal provides product descriptions to general investors based on investment trust information provided by the server, and then sells the products.

[1442] In terms of specific actions, the terminal generates a prospectus for the investment trust and presents it to the user.

[1443] Step 10:

[1444] Users purchase investment trusts through an online platform. Specifically, users search for investment trusts from their home computers and submit purchase requests.

[1445] Step 11:

[1446] The server periodically collects new data to update the contents of the investment trust. The server collects the latest company information and analyzes it using natural language processing technology.

[1447] In terms of specific operations, the server analyzes new information, such as "Company X has announced a new technology," and then revises its portfolio composition.

[1448] In this way, the present invention provides general investors with investment opportunities in companies before they go public, and further enhances investment diversity and adaptability by utilizing user sentiment data to propose and adjust investment trusts.

[1449] (Example 2)

[1450] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1451] Making appropriate investment decisions regarding companies before they go public requires sophisticated data collection and analysis, but conventional systems have struggled to do this efficiently and accurately. Furthermore, the proposal and adjustment of investment products to suit individual investors' risk preferences are insufficient, and there is a need to improve investor satisfaction. Therefore, a system is needed to analyze company information and simulate stock price trends before an IPO.

[1452] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1453] In this invention, the server includes means for collecting information about a company before it goes public, means for analyzing the collected information using natural language processing technology and evaluating the company's growth potential, means for simulating the stock price trends of the pre-listing company using a machine learning algorithm based on the analysis results, means for constructing investment products based on the simulated stock price trends, means for collecting and analyzing user sentiment data in real time, means for adjusting the content of investment product proposals based on user sentiment data, and means for selling the constructed investment products. This makes it possible to collect and analyze information about companies before they go public, simulate stock price trends, and propose and adjust investment products based on user sentiment data.

[1454] A "pre-listing company" refers to a company that is in the stage before it is listed on the stock market.

[1455] "Means of collecting information" refers to technologies and devices that automatically acquire necessary information from the internet or other data sources.

[1456] "Natural language processing technology" refers to the technology used by computers to analyze and understand the language that humans use on a daily basis.

[1457] "Means for evaluating a company's growth potential" refers to methods and techniques for analyzing and evaluating a company's future growth capabilities based on collected information.

[1458] A "machine learning algorithm" refers to a type of artificial intelligence that automatically learns from data and makes predictions and decisions.

[1459] "Methods for simulating stock price trends" refer to methods and technologies for predicting future stock price movements of a company based on collected and analyzed data.

[1460] "Means of constructing investment products" refers to methods and techniques for designing and creating investment products such as investment trusts and portfolios based on simulation results.

[1461] "User emotional data" refers to information about a user's emotional state collected from their facial expressions, voice, behavior, etc.

[1462] "Means of collecting and analyzing data in real time" refers to technologies and equipment for collecting and quickly analyzing users' emotional states in real time.

[1463] "Means of adjusting the content of investment product proposals" refers to methods and technologies for changing the content and structure of investment products based on user sentiment data.

[1464] "Means of sale" refers to the methods and technologies used to offer the developed investment product to the market and enable users to purchase it.

[1465] This invention relates to a system that collects data on companies before they go public, analyzes that data to evaluate the companies' growth potential, and simulates stock price trends. Based on the simulation results, it constructs investment products, collects and analyzes user sentiment data to optimize investment proposals, and then provides and sells the constructed investment products to the market.

[1466] overview

[1467] 1. Data Collection

[1468] The server collects information about pre-IPO companies from the internet. This information collection uses web crawling technology and APIs (e.g., newspaper article APIs, official company APIs). Specifically, the server accesses news portals and official company websites, automatically downloading news articles such as "Company A announces new product" and saving them to a database.

[1469] 2. Data Analysis

[1470] The server analyzes the collected data using natural language processing technologies (e.g., NLTK, spaCy). It tokenizes the text data and extracts important keywords and phrases. It also performs sentiment analysis to determine whether the news is positive or negative. Based on this analysis, it calculates company growth indicators (e.g., number of new customers, progress of proprietary technology) and scores the company's growth potential.

[1471] 3. Modeling and Simulation

[1472] The server simulates the stock price trends of pre-IPO companies based on the analysis results. It creates a stock price prediction model using machine learning algorithms (e.g., random forest, neural network) and trains it with historical data. The simulation generates prediction results under multiple scenarios: optimistic, neutral, and pessimistic. For example, it might output a result such as, "Company A's predicted stock price increase rate is 15% over the next six months."

[1473] 4. Building an investment product

[1474] The server constructs an investment trust by combining multiple pre-IPO companies and other investment products based on the simulation results. It determines the components of the investment product (e.g., shares of company A, company B, and company C) and their weights (e.g., the proportion of shares of each company). Specifically, it "creates a portfolio including company A, company B, and company C, and constructs this as investment trust XYZ."

[1475] 5. Recognition and Analysis of User Sentiments

[1476] The device uses an emotion engine (e.g., camera, microphone) to collect user emotion data. It analyzes facial expressions and voice to identify the user's emotional state in real time. This data is sent to a server to analyze the user's investment risk preferences. For example, it might determine that "the user is feeling anxious."

[1477] 6. Proposing and adjusting investment products

[1478] Based on data obtained from the emotion engine, the server suggests investment trusts tailored to the user's risk tolerance. If the user is optimistic, it suggests high-risk investment products; conversely, if the user is anxious, it suggests low-risk investment products. Specifically, "it determines that the user is in a state where they can tolerate risk and suggests high-return investment products."

[1479] 7. Sale of investment products

[1480] The terminal is responsible for providing product descriptions and sales information about investment trusts to general investors based on information provided by the server. Users can purchase investment trusts through the online platform. For example, a user can search for "Investment Trust XYZ" from their home computer and submit a purchase request.

[1481] 8. Performance Updates

[1482] The server periodically collects new information and updates the contents of the investment trust. It reanalyzes the latest company information and retrains the AI ​​model (e.g., generative AI model) based on the new data. For example, it analyzes new information such as "Company A has raised new funds" and revises the portfolio composition.

[1483] Specific example

[1484] As a concrete example, the server collects news articles and analyzes information such as "Company A has launched a new product on the market." Based on the results of this analysis, it evaluates the company's growth potential and simulates stock price trends. It also collects user sentiment data in real time and proposes the optimal investment product according to the user's risk preference.

[1485] Example of a prompt

[1486] "Company A has launched a new product into the market. How does this affect Company A's growth potential?"

[1487] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1488] Step 1:

[1489] Data collection

[1490] The server collects information about pre-IPO companies from the internet. It uses web crawling technology and APIs to retrieve data from news articles, company press releases, industry reports, etc. Specifically, the server accesses news portals and official company websites and automatically downloads news articles such as "Company A has announced a new product."

[1491] Input: URL of a specific news portal or company website

[1492] Output: Raw data such as news articles, press releases, and industry reports.

[1493] Step 2:

[1494] Data Analysis

[1495] The server analyzes the collected data using natural language processing technologies (e.g., NLTK, spaCy). First, it tokenizes the text data and extracts important keywords and phrases. Next, it performs sentiment analysis to determine whether the news content is positive or negative. Based on this, it calculates company growth indicators (e.g., number of new customers, progress of its own technology) and scores the company's growth potential. Specifically, the server extracts and analyzes information such as "Company A's number of new customers increased by 50%."

[1496] Input: Collected raw data

[1497] Output: Tokenized text, sentiment analysis results, company growth metrics

[1498] Step 3:

[1499] Modeling and Simulation

[1500] The server simulates the stock price trends of pre-IPO companies based on the analysis results. It creates a stock price prediction model using machine learning algorithms (e.g., random forest, neural network) and trains it with historical data. The simulation generates prediction results for multiple scenarios: optimistic, neutral, and pessimistic. Specifically, the server outputs a result such as "Company A's predicted stock price increase rate is 15% over the next 6 months."

[1501] Input: Company growth indicators, historical stock price data

[1502] Output: Simulated stock price trends, multiple scenario prediction results

[1503] Step 4:

[1504] Building an investment product

[1505] Based on the simulation results, the server constructs an investment trust by combining multiple pre-IPO companies and other investment products. It determines the components of the investment product (e.g., shares of company A, company B, and company C) and their weights (e.g., the proportion of shares of each company). Specifically, the server "creates a portfolio including company A, company B, and company C, and constructs this as investment trust XYZ."

[1506] Input: Simulated stock price trends

[1507] Output: Details of the constructed mutual fund (components, ratios, etc.)

[1508] Step 5:

[1509] Recognition and analysis of user emotions

[1510] The device uses an emotion engine (e.g., camera, microphone) to collect user emotion data. It analyzes facial expressions and voice in real time to identify the emotional state and sends that data to the server. The server uses that data to analyze the user's investment risk preferences. Specifically, the device captures the user's facial expressions, and the server determines that "the user is feeling anxious."

[1511] Input: User facial expression data, voice data

[1512] Output: Identified emotional states, investment risk preference analysis results

[1513] Step 6:

[1514] Proposal and adjustment of investment products

[1515] Based on the analysis results of the emotion engine, the server suggests investment products that match the user's risk preference. If the user is optimistic, it suggests high-risk investment products; if the user is anxious, it suggests low-risk investment products. Specifically, the server determines that "the user is in a state where they can tolerate risk and suggests high-return investment products."

[1516] Input: Emotional engine analysis results, user's investment risk preference

[1517] Output: Adjusted investment product proposals

[1518] Step 7:

[1519] Sales of investment products

[1520] The terminal is responsible for providing product descriptions and sales information about investment trusts to general investors based on information provided by the server. Users can purchase investment trusts through the online platform. Specifically, a user searches for "Investment Trust XYZ" from their home computer and submits a purchase request.

[1521] Input: Investment trust information provided by the server

[1522] Output: Purchase request by user

[1523] Step 8:

[1524] Performance Update

[1525] The server regularly collects new information and updates the contents of the investment trust. It reanalyzes the latest company information and retrains the AI ​​model based on the new data. Specifically, the server analyzes new information such as "Company A has raised new funds" and revises the portfolio composition.

[1526] Input: New company information

[1527] Output: Updated investment trust details and retrained AI model

[1528] (Application Example 2)

[1529] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1530] Traditional investment management systems primarily relied on information from listed companies for their evaluations and recommendations, with few utilizing pre-IPO company information. Furthermore, they often failed to consider user sentiment, resulting in poorly optimized risk assessments and investment recommendations for individual users. This led to low investor satisfaction and a lack of investment diversity and adaptability.

[1531] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for collecting information about a company before it goes public, means for analyzing the collected information and evaluating the company's growth potential, means for simulating the stock price trends of the company before it goes public based on the analysis results, means for selling the constructed investment trust, means for collecting user sentiment data, means for analyzing the collected sentiment data and reflecting it in investment trust proposals, and means for users to purchase investment trusts using electronic payment. This makes it possible to utilize information about companies before they go public and to make investment proposals that take into account user sentiment.

[1532] A "pre-listing company" is a company that has not yet publicly traded its shares on the market but aims to go public in the future.

[1533] "Means of collecting information" refers to the technologies and methods used to obtain data from news articles, press releases, industry reports, etc., via the internet.

[1534] "Means of analyzing information and evaluating a company's growth potential" refers to technologies and methods for determining a company's growth potential using techniques such as natural language processing and sentiment analysis.

[1535] "Methods for simulating stock price trends" refer to technologies and methods that use machine learning algorithms to predict future stock price fluctuations from past data.

[1536] "Methods for constructing investment trusts" refer to the techniques and methods for forming a fund by combining multiple investment products based on simulation results.

[1537] "Means of selling constructed investment trusts" refers to the technologies and methods that provide information about investment trusts and enable general investors to purchase them.

[1538] "Means of collecting user emotional data" refers to technologies and methods that use cameras and microphones to capture users' facial expressions and voices in order to understand their emotional state.

[1539] "Means for analyzing emotional data" refers to technologies and methods for analyzing acquired emotional data and evaluating the user's emotional state.

[1540] "Means of reflecting in investment trust proposals" refers to technologies and methods for optimizing and proposing investment trust content and risk levels based on user sentiment data.

[1541] "Methods of purchase using electronic payment" refer to technologies and methods that allow users to purchase proposed investment trusts using electronic means.

[1542] Basic structure of the system program

[1543] The system for implementing this invention provides a program that collects and analyzes information about companies before they go public and handles the entire process from building investment trusts to selling them. The main components of the program are as follows:

[1544] 1. Data Acquisition Module:

[1545] The server collects information about pre-IPO companies, such as news articles, company press releases, and industry reports, via the internet. It uses web crawling technology and APIs to retrieve information from specific websites and store it in a database.

[1546] 2. Data Analysis Module:

[1547] The server analyzes the collected information using natural language processing (NLP) techniques to assess growth potential. Specifically, it tokenizes text data, extracts important keywords and phrases, and performs sentiment analysis. It then calculates and scores company growth indicators (e.g., number of new customers and amount of funding raised).

[1548] 3. Simulation Module:

[1549] Based on the analysis results, the server uses machine learning algorithms to create a stock price prediction model and simulate stock price trends. This prediction includes multiple scenarios (optimistic, neutral, and pessimistic) and forecasts future stock price increases and decreases.

[1550] 4. Investment Trust Construction Module:

[1551] Based on the simulation results, the server constructs an investment trust by combining multiple pre-IPO companies and tradable investment products. In this process, it determines the proportion of each company's shares and the overall portfolio composition.

[1552] 5. User sentiment collection module:

[1553] The device collects user emotion data using input devices such as cameras and microphones. It uses an emotion engine to analyze facial expressions and voice in real time to identify the user's emotional state.

[1554] 6. Emotional Data Analysis Module:

[1555] The server analyzes emotional data collected from users to evaluate their risk preferences and emotional state. For example, if a user is feeling anxious, the server uses that information to adjust investment recommendations to those with lower risk.

[1556] 7. Investment Proposal Module:

[1557] Based on the analysis results of the emotion engine, the server suggests investment trusts optimized for the user. If the user indicates optimistic emotions, it suggests high-risk investment trusts; if the user indicates anxiety, it suggests a portfolio with reduced risk.

[1558] 8. Electronic payment module:

[1559] The terminal assists users in purchasing investment trusts suggested by the server using electronic payment. Existing payment platforms (e.g., Stripe or PayPal) are used for processing electronic payments.

[1560] Specific example

[1561] For example, the system collects information on startup companies from news websites and analyzes positive information, such as when a company announces new technology. As a result, the company's growth potential is highly rated, and its stock price movement is simulated based on this information. When optimistic sentiment data from users is collected, high-risk investment trusts are suggested, and the user then makes an electronic payment through the app to purchase the suggested investment trusts.

[1562] Example of a prompt

[1563] "Explain how to optimize investment trusts by utilizing real-time user sentiment data in investment trust proposals and based on the results of an analysis of the growth potential of pre-IPO companies. The sentiment data will be collected using facial recognition technology, and the investment trust proposals will also include electronic payment functionality."

[1564] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1565] Step 1:

[1566] The server collects information about pre-IPO companies from the internet. Specifically, it uses web crawling technology and APIs to retrieve data such as news articles, company press releases, and industry reports. The input is the URL of a specific news portal or the company's official website, and the output is downloaded text data.

[1567] Step 2:

[1568] The server analyzes the collected information using natural language processing (NLP) techniques to evaluate the company's growth potential. Specifically, it tokenizes text data and extracts important keywords and phrases. The input is the text data collected in the previous step, and the output is the tokenized data and the results of sentiment analysis.

[1569] Step 3:

[1570] The server simulates the stock price trends of pre-IPO companies based on the analysis results. It uses a machine learning algorithm to create a stock price prediction model and learns from historical data. The input is the analysis results obtained in step 2, and the output is predicted stock price trend data under multiple scenarios.

[1571] Step 4:

[1572] Based on the simulation results, the server constructs an investment trust by combining multiple pre-IPO companies and tradable investment products on the market. The input is the stock price trend prediction data obtained in step 3, and the output is the portfolio of the constructed investment trust.

[1573] Step 5:

[1574] The device collects user emotion data using a camera and microphone. Specifically, it uses an emotion engine to analyze the user's facial expressions and voice in real time. The input is the user's facial expressions and voice data, and the output is the analyzed emotion state data.

[1575] Step 6:

[1576] The server analyzes the collected emotional data to evaluate the user's risk preference and emotional state. The input is the emotional state data obtained in step 5, and the output is emotional evaluation data corresponding to the user's risk preference.

[1577] Step 7:

[1578] The server proposes investment trusts optimized for the user based on the analysis results of the emotion engine. Specifically, if the user expresses optimistic emotions, it proposes high-risk investment trusts; if the user expresses anxiety, it proposes a portfolio with reduced risk. The input is the emotion evaluation data obtained in step 6 and the investment trust portfolio constructed in step 4, and the output is the proposed investment trust plan.

[1579] Step 8:

[1580] The terminal provides product descriptions to individual investors based on investment trust information provided by the server and assists with purchases via electronic payment. Specifically, it displays the proposed investment trust and guides the purchase process through the payment platform. The input is the investment trust plan proposed in step 7, and the output is a confirmation of the completed purchase.

[1581] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1582] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1583] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[1584] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1585] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[1586] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[1587] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[1588] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[1589] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[1590] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[1591] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[1592] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto,...

Claims

1. Means of collecting information about companies before they go public, A means of analyzing collected information and evaluating a company's growth potential, A means of simulating the stock price trends of a company before its IPO based on the analysis results, A means of constructing an investment trust based on simulated stock price trends, A system that includes means for selling constructed investment trusts.

2. The system according to claim 1, comprising means for analyzing information collected using natural language processing technology.

3. The system according to claim 1, comprising means for simulating the stock price trends of a pre-listing company using a machine learning algorithm.

4. The system according to claim 1, further comprising means for collecting and analyzing new data in order to periodically update the performance of an investment trust.

5. The system according to claim 1, which includes means for a user to purchase an investment trust online.

Images