system

Abstract

Provide a system. [Solution] data collection means; data analysis means; Business plan evaluation tools; Investment recommendation measures, an interface providing means; A system including:

Description

[Technical Field]

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

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the chatbot character, 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] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] In recent years, as the number of startup companies has increased, there has been a demand for support in helping these companies develop appropriate business plans. It is also difficult for investors to select the most suitable investment targets from the large number of startup companies. This has led to problems of reduced efficiency and accuracy in the development of business plans and the selection of investment targets. Therefore, there is a need for a system that supports startup companies in developing business plans and enables investors to efficiently select the most suitable investment targets. [Means for solving the problem]

[0005] The present invention solves the above problems by the following means. Specifically, the present invention includes a data collection means, a data analysis means, a business plan evaluation means, an investment target recommendation means, and an interface provision means. The data collection means collects business plans, financial data, and market analysis information from companies, and collects investment policies, past investment history, and risk tolerance from investors. The data analysis means analyzes the company data by applying a profit forecasting model and a risk evaluation model, and the business plan evaluation means evaluates the company's business plan based on the analysis results. The investment target recommendation means recommends optimal investment target companies based on the investor's policies, and the interface provision means provides an interface that allows users to view the evaluation results and recommendation details. This effectively supports the formulation of business plans for startup companies and enables investors to efficiently select optimal investment targets.

[0006] "Data collection tools" refers to the functionality of the equipment or software used to collect the necessary information from companies and investors.

[0007] "Data analysis means" refers to the functionality of the equipment or software used to analyze collected data and apply revenue forecasting and risk assessment models.

[0008] The "business plan evaluation means" refers to a device or software function for evaluating a company's business plan based on the analysis results obtained by the data analysis means.

[0009] "Investment target recommendation means" refers to the function of a device or software for selecting and recommending the most suitable investment target companies in consideration of the investor's policies.

[0010] The term "interface providing means" refers to a device or software function that provides an interface that allows a user to view the evaluation results and recommendations.

[0011] "Company" refers to an entity that has developed a business plan, such as a startup, and requires investment.

[0012] "Investor" refers to an individual or institution that provides capital to invest in a company.

[0013] "Revenue forecasting model" refers to mathematical and statistical methods used to forecast a company's future revenues.

[0014] "Risk Assessment Model" refers to a mathematical and statistical method for assessing the risks associated with a company or investor.

[0015] A "business plan" refers to a document in which a company describes its business vision, strategy, and financial plans. [Brief explanation of the drawings]

[0016] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0017] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0018] First, the terms used in the following description will be explained.

[0019] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0020] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0021] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0022] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0023] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0024] [First embodiment]

[0025] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0026] 1, a 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.

[0027] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0028] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0029] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the 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.

[0030] 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 of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0031] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0032] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] 2, in the data processing device 12, a specific process 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" according to the technology of the present 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 process 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.

[0034] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0035] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0036] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0037] This invention is a system that helps start-up companies develop effective business plans and allows investors to efficiently select the most suitable companies to invest in. This system consists of three elements: a server, a terminal, and a user.

[0038] System Configuration

[0039] 1. Data Collection

[0040] Server: Receives data from companies and investors. From startups, collects information such as business plans, financial data, market analysis reports, and team composition. From investors, collects information such as investment policy, past investment history, risk tolerance, desired investment return, and investment period.

[0041] 2. Data Analysis

[0042] Server: Analyzes collected data using machine learning algorithms and statistical methods. Applying revenue forecasting models and risk assessment models to startup company data to evaluate future revenue and risk. Applying portfolio optimization models to investor data to help select optimal investment targets.

[0043] 3. Business plan evaluation

[0044] Server: Evaluates the company's business plan based on the analysis results. The results of revenue forecasts, risk assessments, and SWOT analysis are compiled using business plan evaluation tools. This results in a report in natural language summarizing the company's strengths and weaknesses, which is then provided to the user (startup company representative).

[0045] 4. Investment recommendation

[0046] Server: Based on the investor's investment policy, the server selects the most suitable investment targets from the collected startup companies. It generates a detailed report including the reasons for the recommendation and risk factors and provides it to the user (investor).

[0047] 5. Providing an Interface

[0048] Terminal: Provides an interface that allows users to view evaluation results and recommendations. Users can request re-evaluation based on changes to conditions or new scenarios from the server via their terminal, and receive a new report.

[0049] Specific examples

[0050] Support for developing business plans for startups

[0051] 1. User (startup staff): Logs into the system using a terminal and enters information such as business plans, financial data, market analysis reports, and team composition.

[0052] 2. Server: Collects input data and performs data analysis, such as using linear regression models to forecast profits and Monte Carlo simulations to assess risk.

[0053] 3. Server: Based on the analysis results, the business plan evaluation instrument generates a natural language report including strengths and weaknesses.

[0054] 4. Terminal: This report is provided to the user (startup staff) so that it can be viewed on the screen.

[0055] Investor selection of investment companies

[0056] 1. User (Investor): Logs into the system using a terminal and provides information such as investment policy, past investment history, and risk tolerance.

[0057] 2. Server: Analyzes collected data on startups based on investment policies, and uses portfolio optimization models to forecast returns and assess risks.

[0058] 3. Server: Selects the best startups to invest in and generates a natural language report containing the reasons for the recommendation and risk factors.

[0059] 4. Terminal: This report is provided to the user (investor) so that it can be viewed on the screen.

[0060] This will enable startups to effectively develop business plans and investors to efficiently select the most suitable investment targets.

[0061] The processing flow will be explained below.

[0062] Step 1:

[0063] Users log in to the system using a terminal. If they log in as a startup company, they enter their company's business plan, financial data, market analysis report, team composition, etc. into the system. If they log in as an investor, they enter their investment policy, past investment history, risk tolerance, etc.

[0064] Step 2:

[0065] The server receives the information entered by the user and stores it in a database. The startup company data is classified as business plan-related data, including financial data and market analysis information. The investor data is classified as investment policy-related data, including investment history and risk tolerance.

[0066] Step 3:

[0067] The server cleans the collected data, filling in missing values ​​and standardizing the data format to make it analyzable. For example, it checks the consistency of numerical data and converts or fills in data as necessary.

[0068] Step 4:

[0069] The server applies revenue forecasting and risk assessment models to the startup company data. Specifically, it uses a linear regression model to forecast revenue based on past data and market analysis information, and performs risk assessment using Monte Carlo simulation.

[0070] Step 5:

[0071] The server applies a portfolio optimization model to the investor data, analyzing the investor's past investment patterns and taking into account current market conditions to generate a list of optimal investments.

[0072] Step 6:

[0073] The server converts the startup's business plan assessment into natural language and creates a detailed report including the company's strengths and weaknesses based on revenue forecasts, risk assessments, SWOT analysis, and other information.

[0074] Step 7:

[0075] The server then converts the list of recommended investments and the reasons for them into a natural language report for the investor, detailing each company's earnings forecast, risk assessment, and points that match the investor's investment policy.

[0076] Step 8:

[0077] The terminal provides an interface that allows users to view the evaluation results and recommendations. Users can also view detailed reports and input new conditions or scenarios to request a re-evaluation.

[0078] Step 9:

[0079] The system provides an interface through which users input new data and scenarios for revaluation, for example, new market conditions or investment strategies.

[0080] Step 10:

[0081] The server then re-analyzes the newly entered data and scenarios, applies revenue forecasting and risk assessment models, and generates updated reports.

[0082] Step 11:

[0083] The terminal provides the reevaluated results to the user, who then uses them to formulate a final business plan and decide on investment destinations.

[0084] Example 1

[0085] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0086] When startups develop effective business plans, there is no system that can efficiently collect and analyze large amounts of data and reduce the effort required for investors to select optimal investment targets.In addition, there is a lack of functionality to generate reports in natural language based on the collected data, which delays user understanding and decision-making.

[0087] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0088] In this invention, the server includes a data collection means, a data analysis means, a business plan evaluation means, an investment target recommendation means, an interface provision means, and a means for converting the data analysis results into a natural language report using a generative AI model, thereby enabling startup companies to formulate business plans and investors to efficiently select optimal investment targets.

[0089] "Data collection means" refers to means for collecting information such as business plans, financial data, market analysis information, investment policies, past investment history, and risk tolerance from organizations and investors.

[0090] "Data analysis means" refers to means for conducting analysis such as revenue forecasting and risk assessment based on collected data using machine learning algorithms and statistical methods.

[0091] The "business plan evaluation means" is a means for evaluating the business plans of startup companies based on the analysis results obtained by the data analysis means and compiling the results into a report.

[0092] The "investment recommendation means" is a means for selecting the most suitable investment based on the investor's investment policy and risk tolerance, and generating a report including the reasons for the recommendation and risk factors.

[0093] The "interface providing means" is a means for providing an interface that allows the user to view the evaluation results and the recommended contents.

[0094] "Means for converting data analysis results into natural language reports using generative AI models" refers to means for generating reports in a format that is easy for users to understand, based on collected and analyzed data, using natural language generation algorithms.

[0095] This invention is a system that helps start-up companies develop effective business plans and allows investors to efficiently select the most suitable companies to invest in. This system consists of three elements: a server, a terminal, and a user.

[0096] 1. Data Collection Methods

[0097] The server collects data from companies and investors. At the same time, it collects data such as business plans, financial data, market analysis reports, and team composition from organizations, and information such as investment policy, past investment history, risk tolerance, desired investment return, and investment period from investors. The data is stored in a relational database (e.g., MySQL (registered trademark) or PostgreSQL). During the data collection phase, validation scripts are run to detect and complete input errors and missing values.

[0098] 2. Data analysis methods

[0099] The server analyzes the collected data using machine learning algorithms and statistical methods. Specifically, it preprocesses the data using Python's Pandas and NumPy. It then applies a linear regression model using Scikit-learn to predict future revenue. It also performs risk assessment using Monte Carlo simulation. The data analysis script is automatically executed periodically by a job scheduler (Cron or Airflow).

[0100] 3. Business plan evaluation tools

[0101] The server evaluates the business plan based on the analysis results. Specifically, it uses a Python NLP library (e.g., a generative AI model such as SpaCy or GPT-3 (registered trademark)) to compile revenue forecasts and risk assessment results into a natural language report. It also generates a template-based report that includes SWOT analysis results to clearly identify the company's strengths and weaknesses. The prompt for the generative AI model is, "Based on the revenue forecast results, please explain the strengths and weaknesses of this company."

[0102] 4. Investment Recommendation Methods

[0103] The server selects the best investment targets based on the investor's investment policy. It matches investor data with startup company analysis data and applies a portfolio optimization model. It uses libraries such as PyPortfolioOpt to select the best investment target companies. The prompt for the generative AI model is, "Select the best company for this investor's portfolio and explain why."

[0104] 5. Means of providing interface

[0105] The terminal provides an interface that allows users to view the evaluation results and recommendations. React.js and Vue.js are used as front-end technologies, while web frameworks such as Django and Flask are used for the back-end. Once users log in, they can access a dashboard screen where they can download or view the evaluation results and investment recommendation reports. A form for submitting a reevaluation request is also provided, allowing users to submit new data to the server.

[0106] The above configuration realizes a system that enables startup companies to effectively formulate business plans and investors to efficiently select optimal investment targets.

[0107] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0108] Step 1:

[0109] Data Entry

[0110] Users log in to the system using a terminal. Startup company representatives input data such as business plans, financial data, market analysis reports, and team composition. Investors input information such as investment policy, past investment history, risk tolerance, desired investment return, and investment period. The input data is saved in the system's database.

[0111] Step 2:

[0112] Data collection

[0113] The server receives data entered by users and stores it in a relational database (MySQL or PostgreSQL). During the data collection phase, validation scripts are run to verify the input data. Input errors and missing values ​​are detected and completed to ensure accurate data is collected.

[0114] Step 3:

[0115] Data analysis

[0116] The server analyzes the collected data. It preprocesses the data using Python's Pandas and NumPy. It then uses Scikit-learn to apply a linear regression model to predict future revenue. It also performs risk assessment using Monte Carlo simulation. The analysis script is automatically executed periodically using a job scheduler (Cron or Airflow). It uses the collected company data and investor data as input, and outputs revenue forecasts and risk assessment results.

[0117] Step 4:

[0118] Business plan evaluation

[0119] The server evaluates the company's business plan based on the results of the data analysis. It uses Python NLP libraries (e.g., SpaCy or generative AI models) to compile revenue forecasts and risk assessment results into natural language reports. It also adds SWOT analysis results to highlight strengths and weaknesses. Template-based reports are generated. The analysis results are used as input, and the natural language report is the output.

[0120] Step 5:

[0121] Investment recommendation

[0122] The server selects optimal investments based on the investor's investment policy and risk tolerance. It uses PyPortfolioOpt to run a portfolio optimization model and select appropriate investment companies. The generative AI model receives a prompt, "Select the best companies for this investor's portfolio and explain why," and generates a report. Investor data and company data are used as input, and a report of investment recommendations is obtained as output.

[0123] Step 6:

[0124] Interface provided

[0125] The terminal provides an interface that allows users to view evaluation results and recommendations. React.js and Vue.js are used as front-end technologies, while web frameworks such as Django and Flask are used for the back-end. Once users log in, they can view evaluation results and investment recommendation reports on the dashboard screen. A function to send re-evaluation requests is also provided. User input includes login information, and evaluation results and recommendations are provided as output.

[0126] (Application example 1)

[0127] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0128] Currently, many startups lack effective support when formulating their business plans, and investors face difficulties in efficiently selecting the most suitable investment targets. Furthermore, investors lack the means to obtain the latest investment information and risk assessments in real time, which can delay appropriate decision-making. This not only results in missed growth opportunities for startups, but also makes it difficult for investors to realize the investment returns they expect.

[0129] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0130] In this invention, the server includes a data collection means, a data analysis means, a business plan evaluation means, an investment target recommendation means, an interface provision means, a dashboard display means, a business plan evaluation report generation means, an alert notification means, and an AI assistant recommendation means, thereby enabling startup companies to effectively formulate business plans and investors to efficiently select optimal investment targets while also being able to grasp the latest investment information and risk assessments in real time.

[0131] "Data collection means" refers to means for collecting business plans, financial data, and market analysis information from companies, and investment policies, past investment history, and risk tolerance from investors.

[0132] "Data analysis means" refers to means for analyzing collected data using machine learning algorithms and statistical methods to forecast profits and assess risks.

[0133] The "business plan evaluation tool" is a tool that evaluates a company's business plan based on the analysis results and generates a report that includes strengths and weaknesses.

[0134] An "investment recommendation tool" is a tool that selects optimal investments based on an investor's investment policy and generates a detailed report including the reasons for the recommendation and risk factors.

[0135] The "interface providing means" is a means for providing an interface that allows the user to view the evaluation results and recommendations, and to request re-evaluation based on changes to conditions or a new scenario.

[0136] A "dashboard display" is a visual display that allows a user to manage their investment portfolio and see important information at a glance.

[0137] The "business plan evaluation report generating means" is a means for evaluating a company's business plan based on the collected and analyzed data and generating the results in the form of a report.

[0138] The "alert notification means" is a means for notifying the user when a new investment destination is found or when there is a change in the status of an investment destination.

[0139] "AI assistant recommendation method" is a recommendation method that uses artificial intelligence to propose optimal investment strategies to investors and predict risks and returns.

[0140] This invention is a system for enabling start-up companies to formulate effective business plans and for investors to efficiently select optimal companies to invest in. The system includes a data collection means, a data analysis means, a business plan evaluation means, an investment target recommendation means, an interface provision means, a dashboard display means, a business plan evaluation report generation means, an alert notification means, and an AI assistant recommendation means.

[0141] Hardware and Software Configuration

[0142] The system consists of three elements: a server, a terminal, and a user. The server uses machine learning libraries such as Python and scikit-learn to collect data, analyze it, and generate reports. The terminal is a smartphone, and the user enters information and views the evaluation results through an interface.

[0143] Operation explanation

[0144] Data collection methods

[0145] The server collects business plans, financial data, and market analysis information from companies, and investment policies, past investment history, and risk tolerance from investors, creating a comprehensive database.

[0146] Data Analysis Methods

[0147] The collected data is analyzed using machine learning algorithms and statistical methods, such as linear regression models for revenue forecasting and Monte Carlo simulations for risk assessment.

[0148] Business plan evaluation tools

[0149] Based on the analysis results, the company's business plan is evaluated and a report containing strengths and weaknesses is generated, which is then compiled in an easy-to-read format using natural language generation (NLG) technology.

[0150] Investment recommendation methods

[0151] Based on the investor's investment policy, the system selects the most suitable companies to invest in. A report is generated detailing the reasons for recommending the selected companies and the risk factors involved.

[0152] Interface provision means

[0153] It provides an interface for users to view evaluation results and recommendations, and users can request re-evaluation from the server via their terminal, changing conditions or using new scenarios.

[0154] Dashboard display method

[0155] It provides a dashboard that allows users to manage their investment portfolio and see key information at a glance, enabling them to make decisions instantly.

[0156] Business plan evaluation report generation tool

[0157] Based on the collected and analyzed data, the business plans of companies are evaluated and the results are generated in the form of a report, which is provided to startup companies to help them develop effective business plans.

[0158] Alert notification method

[0159] Users will receive alerts when new investments are discovered or when there is a change in the status of an investment, allowing them to stay informed of important information in real time.

[0160] AI assistant recommended methods

[0161] Using artificial intelligence, the company offers investors optimal investment strategies and predicts risks and returns.

[0162] Specific examples

[0163] Startup Company A enters its business plan and financial data into the system. The server analyzes the entered data, performs revenue forecasts and risk assessments, and compiles the results into a report. Investors can view this report on their devices and confirm that Company A has a high likelihood of generating revenue and low risk.

[0164] Prompt Sentence Examples

[0165] "Enter the business plan and financial data for startup company A below. Please provide a revenue forecast and risk assessment for this company.

[0166] Current earnings: 10,000

[0167] Future market growth rate: 20%

[0168] Expected cost: 25,000.”

[0169] These features enable startups to effectively develop business plans and investors to efficiently select the best investment targets.

[0170] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0171] Step 1:

[0172] A user logs into the system using a terminal. Depending on their role, the user can log in as a representative of the startup company or as an investor.

[0173] Step 2:

[0174] Users (startup staff) input business plans, financial data, and market analysis information through a terminal, which is then sent to a server and stored in a database.

[0175] Step 3:

[0176] The server analyzes the collected data. For example, to predict the revenue of a startup company, a linear regression model is used, taking data such as market growth rate and costs as inputs to predict future revenue. The output is the revenue forecast.

[0177] Step 4:

[0178] The server performs risk assessment using Monte Carlo simulation, using input data such as revenue forecasts and the standard deviation of market growth rates, and running multiple simulations to obtain a risk assessment value.

[0179] Step 5:

[0180] The server evaluates the business plan based on the revenue forecast results and risk assessment value, and generates a business plan evaluation report including its strengths and weaknesses. This report is created in text format using natural language generation technology and provided to the user (startup manager).

[0181] Step 6:

[0182] A user (investor) logs into the system through a terminal and provides their investment policy, past investment history, and risk tolerance. This data is sent to the server and stored in a database.

[0183] Step 7:

[0184] The server analyzes the collected data on startup companies based on the investor's investment policy, selects the most suitable investment target companies using a portfolio optimization model, and generates a report containing the reasons for the recommendation and risk factors using the company's revenue forecast and risk assessment value as input.

[0185] Step 8:

[0186] The server generates a recommendation report and provides it to the user (investor), who then views the report through their terminal and makes a decision on investment destinations.

[0187] Step 9:

[0188] The server sends alert notifications when new investments are discovered or when there is a change in the status of an investment. Alert notifications are sent in real time, providing users with the latest information.

[0189] Step 10:

[0190] The server uses its AI assistant function to propose optimal investment strategies to investors. The AI ​​model receives inputs such as the user's investment policy and past investment history, and outputs predicted risks and returns, as well as optimal investment strategies.

[0191] These processing steps create a system that allows startup companies to effectively develop business plans and investors to efficiently select the most suitable investment targets.

[0192] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0193] This invention combines a system that helps startup companies formulate effective business plans and helps investors efficiently select the most suitable companies to invest in with an emotion engine that recognizes the user's emotions. This system consists of four elements: a server, a terminal, a user, and an emotion engine.

[0194] System Configuration

[0195] 1. Data Collection

[0196] Server: Receives data from companies and investors. From startups, collects information such as business plans, financial data, market analysis reports, and team composition. From investors, collects information such as investment policy, past investment history, risk tolerance, desired investment return, and investment period.

[0197] 2. Data Analysis

[0198] Server: Analyzes collected data using machine learning algorithms and statistical methods. Applying revenue forecasting models and risk assessment models to startup company data to evaluate future revenue and risk. Applying portfolio optimization models to investor data to help select optimal investment targets.

[0199] 3. Business plan evaluation

[0200] Server: Evaluates the company's business plan based on the analysis results. The results of revenue forecasts, risk assessments, and SWOT analysis are compiled using business plan evaluation tools. This results in a report in natural language summarizing the company's strengths and weaknesses, which is then provided to the user (startup company representative).

[0201] 4. Investment recommendation

[0202] Server: Based on the investor's investment policy, the server selects the most suitable investment targets from the collected startup companies. It generates a detailed report including the reasons for the recommendation and risk factors and provides it to the user (investor).

[0203] 5. Providing an Interface

[0204] Terminal: Provides an interface that allows users to view evaluation results and recommendations. Users can request re-evaluation based on changes to conditions or new scenarios from the server via their terminal, and receive a new report.

[0205] 6. Adding an Emotion Engine

[0206] Emotion engine: Analyzes user input data and responses to recognize the user's emotional state. Includes algorithms that analyze emotions from voice and text data. The results of this analysis are reflected in ratings and recommendations, providing a more personalized service.

[0207] Server: Reflects the emotional data obtained from the emotion engine and takes the user's emotional state into account when evaluating business plans and recommending investment targets. For example, if a user is in a positive emotional state, it can present more risky options.

[0208] Device: Adjust the user interface based on feedback from the emotion engine. For example, if the user is feeling stressed, the interface may be simplified.

[0209] Specific examples

[0210] Support for developing business plans for startups

[0211] 1. User (startup staff): Logs into the system using a terminal and inputs information such as a business plan, financial data, market analysis reports, and team composition. The emotion engine analyzes the user's text input and voice instructions to recognize their emotional state.

[0212] 2. Server: Collects input data and performs data analysis. For example, it uses linear regression models to forecast profits and Monte Carlo simulations to assess risk. It also takes into account sentiment data from the sentiment engine and reflects it in the evaluation report.

[0213] 3. Server: Based on the analysis results, the business plan evaluator generates a natural language report containing strengths and weaknesses. Based on sentiment data, for example, it highlights risky options if the user is optimistic.

[0214] 4. Terminal: This report is provided to the user (startup staff) and can be viewed on the screen. An interface is provided that responds to the user's emotional state.

[0215] Investor selection of investment companies

[0216] 1. User (investor): Logs in to the system using a terminal and provides information such as investment policy, past investment history, risk tolerance, etc. The emotion engine analyzes the user's input data and reactions to recognize their emotional state.

[0217] 2. Server: Analyzes the collected data of startups based on the investment policy. Uses a portfolio optimization model to forecast returns and assess risks. Considers sentiment data from the sentiment engine and reflects it in recommendation reports.

[0218] 3. Server: Selects the best startups to invest in and generates a natural language report with recommendations and risk factors. Based on sentiment data, for example, if the user is feeling anxious, it will highlight options with reduced risk.

[0219] 4. Terminal: This report is provided to the user (investor) for viewing on the screen, and the interface is adjusted based on feedback from the sentiment engine.

[0220] This will enable startups to develop more precise business plans and investors to make optimal investment decisions that take into account their own emotional state.

[0221] The processing flow will be explained below.

[0222] Step 1:

[0223] Users log in to the system using a terminal. If they log in as a startup company, they enter their company's business plan, financial data, market analysis report, team composition, etc. into the system. If they log in as an investor, they enter their investment policy, past investment history, risk tolerance, etc.

[0224] Step 2:

[0225] The server receives the information entered by the user and stores it in a database. The startup company data is classified as business plan-related data, including financial data and market analysis information. The investor data is classified as investment policy-related data, including investment history and risk tolerance.

[0226] Step 3:

[0227] The server cleans the collected data, filling in missing values ​​and standardizing the data format to make it analyzable. For example, it checks the consistency of numerical data and converts or fills in data as necessary.

[0228] Step 4:

[0229] The emotion engine analyzes the user's input data and reactions. For example, it uses algorithms to analyze emotions from the language used when the user enters text and from voice data. The emotion engine recognizes the user's current emotional state (positive, negative, neutral) in real time.

[0230] Step 5:

[0231] The server applies revenue forecasting and risk assessment models to the startup company data. Specifically, it uses a linear regression model to predict revenue based on past data and market analysis information, and Monte Carlo simulation to assess risk. It also takes into account emotional data from the emotion engine, and adjusts the risk estimate slightly higher if the user is positive, for example.

[0232] Step 6:

[0233] The server applies a portfolio optimization model to the investor's data, analyzing their past investment patterns and taking into account current market conditions to generate a list of optimal investments. It also incorporates sentiment data from the sentiment engine, making recommendations to reduce risk, for example, if the user is feeling anxious.

[0234] Step 7:

[0235] The server converts the startup's business plan evaluation into natural language. It creates a detailed report including the company's strengths and weaknesses based on revenue forecasts, risk assessments, SWOT analysis, etc. It also makes personalized suggestions based on sentiment data, such as proposing aggressive strategies if the user is optimistic.

[0236] Step 8:

[0237] The server converts a list of recommended investments and the reasons for them into a natural language report for the investor. It details each company's revenue forecast and risk assessment, as well as points that match the investor's investment policy. Based on emotional data, for example, if the user is feeling stressed, it will recommend low-risk investments to give them a sense of security.

[0238] Step 9:

[0239] The device provides an interface where users can view the evaluation results and recommendations. Users can also input new conditions or scenarios to request a re-evaluation. Based on feedback from the emotion engine, the interface is adjusted to optimize the user experience.

[0240] Step 10:

[0241] The server then re-analyzes the newly entered data and scenarios, applies revenue forecasting and risk assessment models, and generates updated reports, incorporating sentiment data from the emotion engine and providing recommendations based on the latest user state.

[0242] Step 11:

[0243] The device then provides the reevaluated results to the user, who can then use them to formulate a final business plan and decide where to invest. Information is displayed in a way that is tailored to the user based on the emotional data.

[0244] Example 2

[0245] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0246] In the past, startups developed business plans and investors selected investment targets in a way that the analysis and evaluation of collected data was not efficient and accurate enough, and in particular, the emotional state of the user was not taken into consideration, which can lead to a decrease in the reliability and satisfaction of the results. Furthermore, in the past, the user experience was often inconsistent because the interface was not adjusted according to the emotional state of the user.

[0247] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a data collection means, a data analysis means, a business plan evaluation means, an investment destination recommendation means, an interface provision means, an emotion analysis means, and an emotion-based interface adjustment means. This allows startup companies to formulate business plans more precisely and enables investors to select optimal investments taking into account their emotional state.

[0248] "Data collection methods" are the means used to collect necessary information from companies and investors.

[0249] "Data analysis means" refers to means for analyzing collected data using machine learning algorithms and statistical methods.

[0250] A "business plan evaluation tool" is a tool for evaluating a company's business plan based on the results of data analysis.

[0251] "Investment recommendation tools" are tools for selecting and recommending optimal investments based on an investor's investment policy and risk tolerance.

[0252] "Interface providing means" refers to a means for providing an interface that allows users to view and operate evaluation results and recommendations.

[0253] The "emotion analysis means" is a means for analyzing the user's input data and reactions and recognizing the user's emotional state.

[0254] The "emotion-based interface adjustment means" is a means for adjusting the user interface based on the emotion data obtained from the emotion analysis means.

[0255] This invention combines a system that helps startup companies formulate effective business plans and helps investors efficiently select the most suitable companies to invest in with an emotion engine that recognizes the user's emotions. This system consists of four elements: a server, a terminal, a user, and an emotion engine.

[0256] First, the overall flow of the system will be described.

[0257] Data collection

[0258] The server collects data from companies and investors. Specifically, from startup companies, it collects information such as business plans, financial data, market analysis reports, and team composition. From investors, it collects information such as investment policy, past investment history, risk tolerance, desired investment return, and investment period. In this way, all necessary data is consolidated on the server.

[0259] Data analysis

[0260] The server analyzes the collected data using machine learning algorithms and statistical methods. It applies revenue prediction models and risk assessment models to the startup company data to evaluate future revenue and risk. For example, it uses Python libraries such as Scikit-learn and TENSORFLOW (registered trademark) to predict revenue using linear regression models and conduct risk assessments using Monte Carlo simulations. It applies portfolio optimization models to investor data to help select optimal investment targets.

[0261] Business plan evaluation

[0262] The server evaluates the company's business plan based on the analysis results. Specifically, the business plan evaluation tool generates a report based on revenue forecast results, risk assessment results, SWOT analysis results, etc. The report is created using natural language processing technology, allowing the user (startup company representative) to understand the company's strengths and weaknesses.

[0263] Investment recommendation

[0264] The server selects the most suitable startups based on the investor's investment policy and risk tolerance. It generates a detailed report including the reasons for the recommendation and risk factors and provides it to the user (investor), allowing the investor to make a more appropriate decision.

[0265] Providing an interface

[0266] The terminal provides an interface that allows users to view the evaluation results and recommendations. Users can also request re-evaluation based on changes to conditions or new scenarios from the server via the terminal, and receive a new report.

[0267] Adding an Emotion Engine

[0268] The emotion engine analyzes the user's input data and reactions to recognize the user's emotional state. This analysis uses an algorithm that analyzes emotions from text data and voice data. For example, it can use the Google® Cloud Natural Language API or IBM Watson® emotion analysis tools.

[0269] The server reflects the emotional data obtained from the emotion engine and takes the user's emotional state into account when evaluating business plans and recommending investments. For example, if the user is in a positive emotional state, it can present more risk-taking options.

[0270] Emotion-based interface adjustment

[0271] The device adjusts the user interface based on feedback from the emotion engine. For example, if the user is feeling stressed, the device may simplify the interface.

[0272] Specific examples

[0273] Support for developing business plans for startups

[0274] 1. A user (startup representative) logs into the system using a terminal and inputs information such as a business plan, financial data, market analysis report, and team composition. The emotion engine analyzes the user's text input and voice instructions to recognize their emotional state.

[0275] 2. The server collects the input data and performs data analysis. For example, it uses a linear regression model to predict profits and a Monte Carlo simulation to assess risk. It also takes into account the sentiment data from the sentiment engine and reflects it in the evaluation report.

[0276] 3. Based on the analysis results, the server generates a natural language report containing the business plan evaluation tools' strengths and weaknesses. Based on the sentiment data, it highlights risk-taking options if the user is optimistic.

[0277] 4. The terminal provides this report to the user (startup staff) and allows them to view it on the screen, providing an interface that responds to the user's emotional state.

[0278] Investor selection of investment companies

[0279] 1. A user (investor) logs into the system using a terminal and provides information such as investment policy, past investment history, and risk tolerance. The emotion engine analyzes the user's input data and reactions to recognize their emotional state.

[0280] 2. Based on the investment policy, the server analyzes the collected data on startup companies using a portfolio optimization model to select the optimal investment targets. The server takes into account the sentiment data from the sentiment engine and reflects this in the recommendation report.

[0281] 3. The server selects the best startups to invest in and generates a natural language report with recommendations and risk factors. Based on sentiment data, it highlights lower-risk options if the user feels unsure.

[0282] 4. The terminal provides this report to the user (investor) for viewing on the screen, adjusting the interface based on feedback from the sentiment engine.

[0283] Prompt Sentence Examples

[0284] "Users input their business plan and financial data into the device, and the emotion engine analyzes their emotional state. The generated business plan report is adjusted based on the emotion analysis results."

[0285] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0286] Step 1: User logs into the system

[0287] A user accesses the system using a terminal and enters login information. The entered user ID and password are sent from the terminal to the server.

[0288] The server authenticates the received login information by checking it against a database. If authentication is successful, it identifies the user's type (startup or investor) and generates the appropriate dashboard, which becomes the gateway for the user to perform further operations.

[0289] Step 2: Data entry

[0290] After logging in, users enter information such as business plans, financial data, market analysis reports, and team composition into the terminal. This information is provided by the startup company's representatives. Investors also enter their investment policy, past investment history, risk tolerance, and other information.

[0291] The terminal temporarily stores the entered data and converts it into an appropriate format for transmission to the server.

[0292] Step 3: Data collection

[0293] The server receives the data sent from the terminal and stores it in a database. The server checks the consistency and completeness of the received data and detects missing information and input errors.

[0294] If the server detects missing data or errors, it notifies the user and prompts them to make corrections or enter additional information.

[0295] Step 4: Data analysis

[0296] The server analyzes the data stored in the database using machine learning algorithms and statistical methods, specifically using Python libraries such as Scikit-learn and TensorFlow.

[0297] The server uses a revenue forecasting model to predict the revenue of startup companies and performs risk assessment using Monte Carlo simulation. After the analysis, the server saves the results.

[0298] Step 5: Evaluate your business plan

[0299] The server evaluates the business plan based on the results of the data analysis. The business plan evaluation means generates a report based on the results of the revenue forecast, risk assessment, SWOT analysis, etc.

[0300] The server uses natural language processing technology to document the evaluation in a user-friendly format and stores the results on the server. This evaluation helps users make important decisions.

[0301] Step 6: Recommend investments

[0302] The server analyzes the collected startup company data using a portfolio optimization model based on the investor's investment policy and risk tolerance.

[0303] The server uses the analysis results to select the most suitable startups to invest in and generates a detailed report including the reasons for the recommendation and risk factors. The report is generated using natural language processing technology.

[0304] Step 7: Providing the resulting interface

[0305] The device displays the evaluation results and recommendations received from the server to the user, who can then review the information through a dashboard or report.

[0306] The user can request the server to reassess the results based on changes to the conditions or new scenarios via the terminal. The terminal sends these requests to the server, which then performs the reanalysis.

[0307] Step 8: Emotion Engine Analysis

[0308] The emotion engine analyzes user input data and reactions in real time to recognize emotional states, using Google Cloud Natural Language API and IBM Watson emotion analysis tools.

[0309] The emotion engine identifies positive and negative emotions from text and voice data and sends the results to the server.

[0310] Step 9: Emotion-Based Interface Adjustment

[0311] The server reflects the emotional data obtained from the emotion engine and takes the user's emotional state into account when evaluating business plans and recommending investment targets. For example, if the user is in a positive emotional state, it presents risk-taking options.

[0312] The device adjusts the user interface based on feedback from the emotion engine. For example, if the user is feeling stressed, the device may simplify the interface.

[0313] In this way, the system takes into account the user's emotional state to support startups in formulating business plans and investors in selecting investment targets, thereby improving user satisfaction and the accuracy of decision-making.

[0314] (Application example 2)

[0315] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0316] Conventional systems for developing business plans for startups and selecting investment targets for investors were unable to provide personalized advice that took into account the user's emotional state. This meant that users' emotional biases could affect their decision-making, making it difficult to select optimal business plans and investment targets. Furthermore, particularly in fields with volatile markets such as the food delivery business, rapid and appropriate responses in real time are required, but conventional systems were unable to adequately address this.

[0317] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0318] In this invention, the server includes a data collection means, a data analysis means, a business plan evaluation means, an investment recommendation means, an emotional state recognition means, an emotional feedback reflection means, and an interface provision means, thereby enabling highly accurate business plan formulation and investment selection while taking into account the emotional state of the user.

[0319] "Data collection means" is a function for collecting necessary information such as business plans, financial data, and investment policies from companies and investors.

[0320] "Data analysis means" is a function that analyzes collected data and performs profit forecasts and risk assessments.

[0321] The "business plan evaluation tool" is a function that evaluates a company's business plan based on the analysis results and compiles a report on its strengths and weaknesses.

[0322] "Investment recommendation tool" is a function that selects the most suitable investment based on the investor's investment policy and generates a report including the reasons for the recommendation and risk factors.

[0323] The "emotional state recognition means" is a function that analyzes the input data and reactions of the user and recognizes the user's emotional state.

[0324] The "emotion feedback reflection means" is a function that reflects the recognized user emotion data in the evaluation of business plans and the selection of investment targets.

[0325] The "interface providing means" is a function that provides an interface that allows the user to view the evaluation results and recommendations, and makes adjustments according to the user's emotional state.

[0326] This invention relates to a system that uses a smartphone application specialized for food delivery businesses to help startup companies formulate effective business plans and investors select optimal investment targets. The system of the present invention consists of three main components: a server, a user terminal, and an emotion engine.

[0327] System Configuration

[0328] 1. Server

[0329] Data collection methods:

[0330] The server collects data from startups, such as market size, marketing costs, and delivery time, as well as data from investors, such as investment policy, past investment history, and risk tolerance.

[0331] Data analysis methods:

[0332] The server analyzes the collected data using Scikit-Learn's LinearRegression and StandardScaler, which allows for profit forecasting and risk assessment.

[0333] Business plan evaluation tools:

[0334] The server evaluates the business plan based on the analysis results and generates a natural language report that includes the startup's strengths and weaknesses.

[0335] Recommended investment vehicles:

[0336] The server selects the most suitable investments based on the investor's investment policy and generates a detailed report including the reasons for the recommendation and risk factors.

[0337] Emotional state recognition means:

[0338] The server performs emotion analysis using TextBlob and recognizes the user's emotional state from input data and voice instructions.

[0339] Emotional feedback methods:

[0340] The server then reflects the recognized emotional data in its evaluations and recommendations, for example, emphasizing risk-taking options when the user has positive emotions and emphasizing risk-avoiding options when the user has negative emotions.

[0341] User terminal

[0342] The user terminal is provided with the following features:

[0343] Interface provided by:

[0344] Based on the analysis results of the emotion engine, a user-friendly interface is provided. The interface is adjusted according to the user's emotional state. For example, if the user is feeling stressed, the information displayed will be concise.

[0345] Specific examples

[0346] Support for developing business plans for startups

[0347] 1. User:

[0348] Startup company representatives log into the system using their smartphones and enter data such as market size, marketing costs, and delivery times. An emotion engine analyzes emotions from the user's text input.

[0349] 2. Server:

[0350] Analyze the input data, use LinearRegression to predict revenue, and perform sentiment analysis using TextBlob. Based on the prediction results and sentiment data, generate a business plan evaluation report. For example, if the market size is large and profits are expected, and positive sentiment is recognized, emphasize advice to take risks.

[0351] 3. User Device:

[0352] Users can view this report on their device and request a reassessment based on new scenarios through an intuitive interface.

[0353] Investor selection of investment companies

[0354] 1. User:

[0355] Investors log in to the system using their smartphones and enter data such as their investment policy, past investment history, risk tolerance, etc. The sentiment engine analyzes emotions from the user's input text.

[0356] 2. Server:

[0357] It analyzes the collected data based on the investment policy and selects the most suitable startups to invest in. It also takes into account sentiment data and generates a detailed report including the risks and reasons for recommendations. For example, if the user is feeling anxious, it will highlight options with reduced risk.

[0358] 3. User Device:

[0359] Users can view this report on their devices and make optimal investment decisions through an interface that responds to their emotional state.

[0360] Example prompts to input to a generative AI model:

[0361] "The market size is large and profits are expected. Should I choose the company with the lowest risk as my investment target among Company A, Company B, or Company C?"

[0362] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0363] Step 1:

[0364] User Data Entry

[0365] Users (startup company representatives or investors) log into the system using their smartphones and enter data such as market size, marketing costs, delivery time, as well as information such as investment policy, past investment history, risk tolerance, etc. Based on this input, the system sends the data to the server.

[0366] Inputs: Business data such as market size, marketing costs, delivery time, investment policy, investment history, risk tolerance

[0367] Output: Input data sent to the server

[0368] Step 2:

[0369] Data collection and preprocessing

[0370] The server receives the data entered by the user and standardizes it as needed. For example, StandardScaler is used to standardize data such as market size, marketing costs, and delivery times.

[0371] Input: Received user data

[0372] Output: Standardized data

[0373] Step 3:

[0374] Revenue forecasting and risk assessment

[0375] The server uses the standardized data to run revenue forecasting and risk assessment models. Specifically, it uses Linear Regression to forecast revenue and obtains the model's prediction results. For risk assessment, it uses other statistical methods and machine learning algorithms.

[0376] Input: Standardized data

[0377] Output: Predicted revenue and risk assessment results

[0378] Step 4:

[0379] Recognition of emotional states

[0380] The server analyzes the user's text input using TextBlob to recognize the user's emotional state, which is classified into three categories: positive, neutral, and negative.

[0381] Input: User text input

[0382] Output: User's emotional state (positive, neutral, negative)

[0383] Step 5:

[0384] Reflecting emotional feedback

[0385] The server generates advice for revenue prediction and risk assessment results based on the recognized emotional state, for example, advising to take risks in the case of a positive emotional state and advising to refrain from risks in the case of a negative emotional state.

[0386] Inputs: Revenue forecast, risk assessment results, user emotional state

[0387] Output: Personalized advice

[0388] Step 6:

[0389] Generate a report of the results

[0390] The server combines revenue forecasts, risk assessments, and emotional state-based advice to generate a natural language report that includes the strengths and weaknesses of the business plan, as well as the reasons and risk factors for investment recommendations.

[0391] Inputs: Revenue forecast, risk assessment results, personalized advice

[0392] Output: Natural language report

[0393] Step 7:

[0394] User interface adjustments

[0395] The device displays the report received from the server to the user. Based on the analysis results of the emotion engine, the device adjusts the interface to present information appropriately according to the user's emotional state. For example, if the user is feeling stressed, the device displays brief information, and if the user is relaxed, the device displays detailed information.

[0396] Input: Report received from the server, analysis results of the emotion engine

[0397] Output: A tailored user interface

[0398] Example prompts to input to a generative AI model:

[0399] "The market size is large and profits are expected. Should I choose the company with the lowest risk as my investment target among Company A, Company B, or Company C?"

[0400] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the 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.

[0401] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0402] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0403] [Second embodiment]

[0404] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0405] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0406] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0407] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0408] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0409] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0410] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0411] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0412] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[0413] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0414] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0415] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[0416] This invention is a system that helps start-up companies develop effective business plans and allows investors to efficiently select the most suitable companies to invest in. This system consists of three elements: a server, a terminal, and a user.

[0417] System Configuration

[0418] 1. Data Collection

[0419] Server: Receives data from companies and investors. From startups, collects information such as business plans, financial data, market analysis reports, and team composition. From investors, collects information such as investment policy, past investment history, risk tolerance, desired investment return, and investment period.

[0420] 2. Data Analysis

[0421] Server: Analyzes collected data using machine learning algorithms and statistical methods. Applying revenue forecasting models and risk assessment models to startup company data to evaluate future revenue and risk. Applying portfolio optimization models to investor data to help select optimal investment targets.

[0422] 3. Business plan evaluation

[0423] Server: Evaluates the company's business plan based on the analysis results. The results of revenue forecasts, risk assessments, and SWOT analysis are compiled using business plan evaluation tools. This results in a report in natural language summarizing the company's strengths and weaknesses, which is then provided to the user (startup company representative).

[0424] 4. Investment recommendation

[0425] Server: Based on the investor's investment policy, the server selects the most suitable investment targets from the collected startup companies. It generates a detailed report including the reasons for the recommendation and risk factors and provides it to the user (investor).

[0426] 5. Providing an Interface

[0427] Terminal: Provides an interface that allows users to view evaluation results and recommendations. Users can request re-evaluation based on changes to conditions or new scenarios from the server via their terminal, and receive a new report.

[0428] Specific examples

[0429] Support for developing business plans for startups

[0430] 1. User (startup staff): Logs into the system using a terminal and enters information such as business plans, financial data, market analysis reports, and team composition.

[0431] 2. Server: Collects input data and performs data analysis, such as using linear regression models to forecast profits and Monte Carlo simulations to assess risk.

[0432] 3. Server: Based on the analysis results, the business plan evaluation instrument generates a natural language report including strengths and weaknesses.

[0433] 4. Terminal: This report is provided to the user (startup staff) so that it can be viewed on the screen.

[0434] Investor selection of investment companies

[0435] 1. User (Investor): Logs into the system using a terminal and provides information such as investment policy, past investment history, and risk tolerance.

[0436] 2. Server: Analyzes collected data on startups based on investment policies, and uses portfolio optimization models to forecast returns and assess risks.

[0437] 3. Server: Selects the best startups to invest in and generates a natural language report containing the reasons for the recommendation and risk factors.

[0438] 4. Terminal: This report is provided to the user (investor) so that it can be viewed on the screen.

[0439] This will enable startups to effectively develop business plans and investors to efficiently select the most suitable investment targets.

[0440] The processing flow will be explained below.

[0441] Step 1:

[0442] Users log in to the system using a terminal. If they log in as a startup company, they enter their company's business plan, financial data, market analysis report, team composition, etc. into the system. If they log in as an investor, they enter their investment policy, past investment history, risk tolerance, etc.

[0443] Step 2:

[0444] The server receives the information entered by the user and stores it in a database. The startup company data is classified as business plan-related data, including financial data and market analysis information. The investor data is classified as investment policy-related data, including investment history and risk tolerance.

[0445] Step 3:

[0446] The server cleans the collected data, filling in missing values ​​and standardizing the data format to make it analyzable. For example, it checks the consistency of numerical data and converts or fills in data as necessary.

[0447] Step 4:

[0448] The server applies revenue forecasting and risk assessment models to the startup company data. Specifically, it uses a linear regression model to forecast revenue based on past data and market analysis information, and performs risk assessment using Monte Carlo simulation.

[0449] Step 5:

[0450] The server applies a portfolio optimization model to the investor data, analyzing the investor's past investment patterns and taking into account current market conditions to generate a list of optimal investments.

[0451] Step 6:

[0452] The server converts the startup's business plan assessment into natural language and creates a detailed report including the company's strengths and weaknesses based on revenue forecasts, risk assessments, SWOT analysis, and other information.

[0453] Step 7:

[0454] The server then converts the list of recommended investments and the reasons for them into a natural language report for the investor, detailing each company's earnings forecast, risk assessment, and points that match the investor's investment policy.

[0455] Step 8:

[0456] The terminal provides an interface that allows users to view the evaluation results and recommendations. Users can also view detailed reports and input new conditions or scenarios to request a re-evaluation.

[0457] Step 9:

[0458] The system provides an interface through which users input new data and scenarios for revaluation, for example, new market conditions or investment strategies.

[0459] Step 10:

[0460] The server then re-analyzes the newly entered data and scenarios, applies revenue forecasting and risk assessment models, and generates updated reports.

[0461] Step 11:

[0462] The terminal provides the reevaluated results to the user, who then uses them to formulate a final business plan and decide on investment destinations.

[0463] Example 1

[0464] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0465] When startups develop effective business plans, there is no system that can efficiently collect and analyze large amounts of data and reduce the effort required for investors to select optimal investment targets.In addition, there is a lack of functionality to generate reports in natural language based on the collected data, which delays user understanding and decision-making.

[0466] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0467] In this invention, the server includes a data collection means, a data analysis means, a business plan evaluation means, an investment target recommendation means, an interface provision means, and a means for converting the data analysis results into a natural language report using a generative AI model, thereby enabling startup companies to formulate business plans and investors to efficiently select optimal investment targets.

[0468] "Data collection means" refers to means for collecting information such as business plans, financial data, market analysis information, investment policies, past investment history, and risk tolerance from organizations and investors.

[0469] "Data analysis means" refers to means for conducting analysis such as revenue forecasting and risk assessment based on collected data using machine learning algorithms and statistical methods.

[0470] The "business plan evaluation means" is a means for evaluating the business plans of startup companies based on the analysis results obtained by the data analysis means and compiling the results into a report.

[0471] The "investment recommendation means" is a means for selecting the most suitable investment based on the investor's investment policy and risk tolerance, and generating a report including the reasons for the recommendation and risk factors.

[0472] The "interface providing means" is a means for providing an interface that allows the user to view the evaluation results and the recommended contents.

[0473] "Means for converting data analysis results into natural language reports using generative AI models" refers to means for generating reports in a format that is easy for users to understand, based on collected and analyzed data, using natural language generation algorithms.

[0474] This invention is a system that helps start-up companies develop effective business plans and allows investors to efficiently select the most suitable companies to invest in. This system consists of three elements: a server, a terminal, and a user.

[0475] 1. Data Collection Methods

[0476] The server collects data from companies and investors. At the same time, it collects data such as business plans, financial data, market analysis reports, and team composition from organizations, and information such as investment policy, past investment history, risk tolerance, desired investment return, and investment period from investors. The data is stored in a relational database (e.g., MySQL or PostgreSQL). During the data collection phase, validation scripts are run to detect and complete input errors and missing values.

[0477] 2. Data analysis methods

[0478] The server analyzes the collected data using machine learning algorithms and statistical methods. Specifically, it preprocesses the data using Python's Pandas and NumPy. It then applies a linear regression model using Scikit-learn to predict future revenue. It also performs risk assessment using Monte Carlo simulation. The data analysis script is automatically executed periodically by a job scheduler (Cron or Airflow).

[0479] 3. Business plan evaluation tools

[0480] The server evaluates the business plan based on the analysis results. Specifically, it uses Python NLP libraries (e.g., generative AI models such as SpaCy and GPT-3) to compile revenue forecasts and risk assessment results into a natural language report. It also generates a template-based report that includes SWOT analysis results to clearly identify the company's strengths and weaknesses. The prompt for the generative AI model is, "Based on the revenue forecast results, please explain the strengths and weaknesses of this company."

[0481] 4. Investment Recommendation Methods

[0482] The server selects the best investment targets based on the investor's investment policy. It matches investor data with startup company analysis data and applies a portfolio optimization model. It uses libraries such as PyPortfolioOpt to select the best investment target companies. The prompt for the generative AI model is, "Select the best company for this investor's portfolio and explain why."

[0483] 5. Means of providing interface

[0484] The terminal provides an interface that allows users to view the evaluation results and recommendations. React.js and Vue.js are used as front-end technologies, while web frameworks such as Django and Flask are used for the back-end. Once users log in, they can access a dashboard screen where they can download or view the evaluation results and investment recommendation reports. A form for submitting a reevaluation request is also provided, allowing users to submit new data to the server.

[0485] The above configuration realizes a system that enables startup companies to effectively formulate business plans and investors to efficiently select optimal investment targets.

[0486] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0487] Step 1:

[0488] Data Entry

[0489] Users log in to the system using a terminal. Startup company representatives input data such as business plans, financial data, market analysis reports, and team composition. Investors input information such as investment policy, past investment history, risk tolerance, desired investment return, and investment period. The input data is saved in the system's database.

[0490] Step 2:

[0491] Data collection

[0492] The server receives data entered by users and stores it in a relational database (MySQL or PostgreSQL). During the data collection phase, validation scripts are run to verify the input data. Input errors and missing values ​​are detected and completed to ensure accurate data is collected.

[0493] Step 3:

[0494] Data analysis

[0495] The server analyzes the collected data. It preprocesses the data using Python's Pandas and NumPy. It then uses Scikit-learn to apply a linear regression model to predict future revenue. It also performs risk assessment using Monte Carlo simulation. The analysis script is automatically executed periodically using a job scheduler (Cron or Airflow). It uses the collected company data and investor data as input, and outputs revenue forecasts and risk assessment results.

[0496] Step 4:

[0497] Business plan evaluation

[0498] The server evaluates the company's business plan based on the results of the data analysis. It uses Python NLP libraries (e.g., SpaCy or generative AI models) to compile revenue forecasts and risk assessment results into natural language reports. It also adds SWOT analysis results to highlight strengths and weaknesses. Template-based reports are generated. The analysis results are used as input, and the natural language report is the output.

[0499] Step 5:

[0500] Investment recommendation

[0501] The server selects optimal investments based on the investor's investment policy and risk tolerance. It uses PyPortfolioOpt to run a portfolio optimization model and select appropriate investment companies. The generative AI model receives a prompt, "Select the best companies for this investor's portfolio and explain why," and generates a report. Investor data and company data are used as input, and a report of investment recommendations is obtained as output.

[0502] Step 6:

[0503] Interface provided

[0504] The terminal provides an interface that allows users to view evaluation results and recommendations. React.js and Vue.js are used as front-end technologies, while web frameworks such as Django and Flask are used for the back-end. Once users log in, they can view evaluation results and investment recommendation reports on the dashboard screen. A function to send re-evaluation requests is also provided. User input includes login information, and evaluation results and recommendations are provided as output.

[0505] (Application example 1)

[0506] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0507] Currently, many startups lack effective support when formulating their business plans, and investors face difficulties in efficiently selecting the most suitable investment targets. Furthermore, investors lack the means to obtain the latest investment information and risk assessments in real time, which can delay appropriate decision-making. This not only results in missed growth opportunities for startups, but also makes it difficult for investors to realize the investment returns they expect.

[0508] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0509] In this invention, the server includes a data collection means, a data analysis means, a business plan evaluation means, an investment target recommendation means, an interface provision means, a dashboard display means, a business plan evaluation report generation means, an alert notification means, and an AI assistant recommendation means, thereby enabling startup companies to effectively formulate business plans and investors to efficiently select optimal investment targets while also being able to grasp the latest investment information and risk assessments in real time.

[0510] "Data collection means" refers to means for collecting business plans, financial data, and market analysis information from companies, and investment policies, past investment history, and risk tolerance from investors.

[0511] "Data analysis means" refers to means for analyzing collected data using machine learning algorithms and statistical methods to forecast profits and assess risks.

[0512] The "business plan evaluation tool" is a tool that evaluates a company's business plan based on the analysis results and generates a report that includes strengths and weaknesses.

[0513] An "investment recommendation tool" is a tool that selects optimal investments based on an investor's investment policy and generates a detailed report including the reasons for the recommendation and risk factors.

[0514] The "interface providing means" is a means for providing an interface that allows the user to view the evaluation results and recommendations, and to request re-evaluation based on changes to conditions or a new scenario.

[0515] A "dashboard display" is a visual display that allows a user to manage their investment portfolio and see important information at a glance.

[0516] The "business plan evaluation report generating means" is a means for evaluating a company's business plan based on the collected and analyzed data and generating the results in the form of a report.

[0517] The "alert notification means" is a means for notifying the user when a new investment destination is found or when there is a change in the status of an investment destination.

[0518] "AI assistant recommendation method" is a recommendation method that uses artificial intelligence to propose optimal investment strategies to investors and predict risks and returns.

[0519] This invention is a system for enabling start-up companies to formulate effective business plans and for investors to efficiently select optimal companies to invest in. The system includes a data collection means, a data analysis means, a business plan evaluation means, an investment target recommendation means, an interface provision means, a dashboard display means, a business plan evaluation report generation means, an alert notification means, and an AI assistant recommendation means.

[0520] Hardware and Software Configuration

[0521] The system consists of three elements: a server, a terminal, and a user. The server uses machine learning libraries such as Python and scikit-learn to collect data, analyze it, and generate reports. The terminal is a smartphone, and the user enters information and views the evaluation results through an interface.

[0522] Operation explanation

[0523] Data collection methods

[0524] The server collects business plans, financial data, and market analysis information from companies, and investment policies, past investment history, and risk tolerance from investors, creating a comprehensive database.

[0525] Data Analysis Methods

[0526] The collected data is analyzed using machine learning algorithms and statistical methods, such as linear regression models for revenue forecasting and Monte Carlo simulations for risk assessment.

[0527] Business plan evaluation tools

[0528] Based on the analysis results, the company's business plan is evaluated and a report containing strengths and weaknesses is generated, which is then compiled in an easy-to-read format using natural language generation (NLG) technology.

[0529] Investment recommendation methods

[0530] Based on the investor's investment policy, the system selects the most suitable companies to invest in. A report is generated detailing the reasons for recommending the selected companies and the risk factors involved.

[0531] Interface provision means

[0532] It provides an interface for users to view evaluation results and recommendations, and users can request re-evaluation from the server via their terminal, changing conditions or using new scenarios.

[0533] Dashboard display method

[0534] It provides a dashboard that allows users to manage their investment portfolio and see key information at a glance, enabling them to make decisions instantly.

[0535] Business plan evaluation report generation tool

[0536] Based on the collected and analyzed data, the business plans of companies are evaluated and the results are generated in the form of a report, which is provided to startup companies to help them develop effective business plans.

[0537] Alert notification method

[0538] Users will receive alerts when new investments are discovered or when there is a change in the status of an investment, allowing them to stay informed of important information in real time.

[0539] AI assistant recommended methods

[0540] Using artificial intelligence, the company offers investors optimal investment strategies and predicts risks and returns.

[0541] Specific examples

[0542] Startup Company A enters its business plan and financial data into the system. The server analyzes the entered data, performs revenue forecasts and risk assessments, and compiles the results into a report. Investors can view this report on their devices and confirm that Company A has a high likelihood of generating revenue and low risk.

[0543] Prompt Sentence Examples

[0544] "Enter the business plan and financial data for startup company A below. Please provide a revenue forecast and risk assessment for this company.

[0545] Current earnings: 10,000

[0546] Future market growth rate: 20%

[0547] Expected cost: 25,000.”

[0548] These features enable startups to effectively develop business plans and investors to efficiently select the best investment targets.

[0549] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0550] Step 1:

[0551] A user logs into the system using a terminal. Depending on their role, the user can log in as a representative of the startup company or as an investor.

[0552] Step 2:

[0553] Users (startup staff) input business plans, financial data, and market analysis information through a terminal, which is then sent to a server and stored in a database.

[0554] Step 3:

[0555] The server analyzes the collected data. For example, to predict the revenue of a startup company, a linear regression model is used, taking data such as market growth rate and costs as inputs to predict future revenue. The output is the revenue forecast.

[0556] Step 4:

[0557] The server performs risk assessment using Monte Carlo simulation, using input data such as revenue forecasts and the standard deviation of market growth rates, and running multiple simulations to obtain a risk assessment value.

[0558] Step 5:

[0559] The server evaluates the business plan based on the revenue forecast results and risk assessment value, and generates a business plan evaluation report including its strengths and weaknesses. This report is created in text format using natural language generation technology and provided to the user (startup manager).

[0560] Step 6:

[0561] A user (investor) logs into the system through a terminal and provides their investment policy, past investment history, and risk tolerance. This data is sent to the server and stored in a database.

[0562] Step 7:

[0563] The server analyzes the collected data on startup companies based on the investor's investment policy, selects the most suitable investment target companies using a portfolio optimization model, and generates a report containing the reasons for the recommendation and risk factors using the company's revenue forecast and risk assessment value as input.

[0564] Step 8:

[0565] The server generates a recommendation report and provides it to the user (investor), who then views the report through their terminal and makes a decision on investment destinations.

[0566] Step 9:

[0567] The server sends alert notifications when new investments are discovered or when there is a change in the status of an investment. Alert notifications are sent in real time, providing users with the latest information.

[0568] Step 10:

[0569] The server uses its AI assistant function to propose optimal investment strategies to investors. The AI ​​model receives inputs such as the user's investment policy and past investment history, and outputs predicted risks and returns, as well as optimal investment strategies.

[0570] These processing steps create a system that allows startup companies to effectively develop business plans and investors to efficiently select the most suitable investment targets.

[0571] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0572] This invention combines a system that helps startup companies formulate effective business plans and helps investors efficiently select the most suitable companies to invest in with an emotion engine that recognizes the user's emotions. This system consists of four elements: a server, a terminal, a user, and an emotion engine.

[0573] System Configuration

[0574] 1. Data Collection

[0575] Server: Receives data from companies and investors. From startups, collects information such as business plans, financial data, market analysis reports, and team composition. From investors, collects information such as investment policy, past investment history, risk tolerance, desired investment return, and investment period.

[0576] 2. Data Analysis

[0577] Server: Analyzes collected data using machine learning algorithms and statistical methods. Applying revenue forecasting models and risk assessment models to startup company data to evaluate future revenue and risk. Applying portfolio optimization models to investor data to help select optimal investment targets.

[0578] 3. Business plan evaluation

[0579] Server: Evaluates the company's business plan based on the analysis results. The results of revenue forecasts, risk assessments, and SWOT analysis are compiled using business plan evaluation tools. This results in a report in natural language summarizing the company's strengths and weaknesses, which is then provided to the user (startup company representative).

[0580] 4. Investment recommendation

[0581] Server: Based on the investor's investment policy, the server selects the most suitable investment targets from the collected startup companies. It generates a detailed report including the reasons for the recommendation and risk factors and provides it to the user (investor).

[0582] 5. Providing an Interface

[0583] Terminal: Provides an interface that allows users to view evaluation results and recommendations. Users can request re-evaluation based on changes to conditions or new scenarios from the server via their terminal, and receive a new report.

[0584] 6. Adding an Emotion Engine

[0585] Emotion engine: Analyzes user input data and responses to recognize the user's emotional state. Includes algorithms that analyze emotions from voice and text data. The results of this analysis are reflected in ratings and recommendations, providing a more personalized service.

[0586] Server: Reflects the emotional data obtained from the emotion engine and takes the user's emotional state into account when evaluating business plans and recommending investment targets. For example, if a user is in a positive emotional state, it can present more risky options.

[0587] Device: Adjust the user interface based on feedback from the emotion engine. For example, if the user is feeling stressed, the interface may be simplified.

[0588] Specific examples

[0589] Support for developing business plans for startups

[0590] 1. User (startup staff): Logs into the system using a terminal and inputs information such as a business plan, financial data, market analysis reports, and team composition. The emotion engine analyzes the user's text input and voice instructions to recognize their emotional state.

[0591] 2. Server: Collects input data and performs data analysis. For example, it uses linear regression models to forecast profits and Monte Carlo simulations to assess risk. It also takes into account sentiment data from the sentiment engine and reflects it in the evaluation report.

[0592] 3. Server: Based on the analysis results, the business plan evaluator generates a natural language report containing strengths and weaknesses. Based on sentiment data, for example, it highlights risky options if the user is optimistic.

[0593] 4. Terminal: This report is provided to the user (startup staff) and can be viewed on the screen. An interface is provided that responds to the user's emotional state.

[0594] Investor selection of investment companies

[0595] 1. User (investor): Logs in to the system using a terminal and provides information such as investment policy, past investment history, risk tolerance, etc. The emotion engine analyzes the user's input data and reactions to recognize their emotional state.

[0596] 2. Server: Analyzes the collected data of startups based on the investment policy. Uses a portfolio optimization model to forecast returns and assess risks. Considers sentiment data from the sentiment engine and reflects it in recommendation reports.

[0597] 3. Server: Selects the best startups to invest in and generates a natural language report with recommendations and risk factors. Based on sentiment data, for example, if the user is feeling anxious, it will highlight options with reduced risk.

[0598] 4. Terminal: This report is provided to the user (investor) for viewing on the screen, and the interface is adjusted based on feedback from the sentiment engine.

[0599] This will enable startups to develop more precise business plans and investors to make optimal investment decisions that take into account their own emotional state.

[0600] The processing flow will be explained below.

[0601] Step 1:

[0602] Users log in to the system using a terminal. If they log in as a startup company, they enter their company's business plan, financial data, market analysis report, team composition, etc. into the system. If they log in as an investor, they enter their investment policy, past investment history, risk tolerance, etc.

[0603] Step 2:

[0604] The server receives the information entered by the user and stores it in a database. The startup company data is classified as business plan-related data, including financial data and market analysis information. The investor data is classified as investment policy-related data, including investment history and risk tolerance.

[0605] Step 3:

[0606] The server cleans the collected data, filling in missing values ​​and standardizing the data format to make it analyzable. For example, it checks the consistency of numerical data and converts or fills in data as necessary.

[0607] Step 4:

[0608] The emotion engine analyzes the user's input data and reactions. For example, it uses algorithms to analyze emotions from the language used when the user enters text and from voice data. The emotion engine recognizes the user's current emotional state (positive, negative, neutral) in real time.

[0609] Step 5:

[0610] The server applies revenue forecasting and risk assessment models to the startup company data. Specifically, it uses a linear regression model to predict revenue based on past data and market analysis information, and Monte Carlo simulation to assess risk. It also takes into account emotional data from the emotion engine, and adjusts the risk estimate slightly higher if the user is positive, for example.

[0611] Step 6:

[0612] The server applies a portfolio optimization model to the investor's data, analyzing their past investment patterns and taking into account current market conditions to generate a list of optimal investments. It also incorporates sentiment data from the sentiment engine, making recommendations to reduce risk, for example, if the user is feeling anxious.

[0613] Step 7:

[0614] The server converts the startup's business plan evaluation into natural language. It creates a detailed report including the company's strengths and weaknesses based on revenue forecasts, risk assessments, SWOT analysis, etc. It also makes personalized suggestions based on sentiment data, such as proposing aggressive strategies if the user is optimistic.

[0615] Step 8:

[0616] The server converts a list of recommended investments and the reasons for them into a natural language report for the investor. It details each company's revenue forecast and risk assessment, as well as points that match the investor's investment policy. Based on emotional data, for example, if the user is feeling stressed, it will recommend low-risk investments to give them a sense of security.

[0617] Step 9:

[0618] The device provides an interface where users can view the evaluation results and recommendations. Users can also input new conditions or scenarios to request a re-evaluation. Based on feedback from the emotion engine, the interface is adjusted to optimize the user experience.

[0619] Step 10:

[0620] The server then re-analyzes the newly entered data and scenarios, applies revenue forecasting and risk assessment models, and generates updated reports, incorporating sentiment data from the emotion engine and providing recommendations based on the latest user state.

[0621] Step 11:

[0622] The device then provides the reevaluated results to the user, who can then use them to formulate a final business plan and decide where to invest. Information is displayed in a way that is tailored to the user based on the emotional data.

[0623] Example 2

[0624] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0625] In the past, startups developed business plans and investors selected investment targets in a way that the analysis and evaluation of collected data was not efficient and accurate enough, and in particular, the emotional state of the user was not taken into consideration, which can lead to a decrease in the reliability and satisfaction of the results. Furthermore, in the past, the user experience was often inconsistent because the interface was not adjusted according to the emotional state of the user.

[0626] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a data collection means, a data analysis means, a business plan evaluation means, an investment destination recommendation means, an interface provision means, an emotion analysis means, and an emotion-based interface adjustment means. This allows startup companies to formulate business plans more precisely and enables investors to select optimal investments taking into account their emotional state.

[0627] "Data collection methods" are the means used to collect necessary information from companies and investors.

[0628] "Data analysis means" refers to means for analyzing collected data using machine learning algorithms and statistical methods.

[0629] A "business plan evaluation tool" is a tool for evaluating a company's business plan based on the results of data analysis.

[0630] "Investment recommendation tools" are tools for selecting and recommending optimal investments based on an investor's investment policy and risk tolerance.

[0631] "Interface providing means" refers to a means for providing an interface that allows users to view and operate evaluation results and recommendations.

[0632] The "emotion analysis means" is a means for analyzing the user's input data and reactions and recognizing the user's emotional state.

[0633] The "emotion-based interface adjustment means" is a means for adjusting the user interface based on the emotion data obtained from the emotion analysis means.

[0634] This invention combines a system that helps startup companies formulate effective business plans and helps investors efficiently select the most suitable companies to invest in with an emotion engine that recognizes the user's emotions. This system consists of four elements: a server, a terminal, a user, and an emotion engine.

[0635] First, the overall flow of the system will be described.

[0636] Data collection

[0637] The server collects data from companies and investors. Specifically, from startup companies, it collects information such as business plans, financial data, market analysis reports, and team composition. From investors, it collects information such as investment policy, past investment history, risk tolerance, desired investment return, and investment period. In this way, all necessary data is consolidated on the server.

[0638] Data analysis

[0639] The server analyzes the collected data using machine learning algorithms and statistical methods. It applies revenue prediction and risk assessment models to the startup company data to evaluate future revenue and risk. For example, it uses Python libraries such as Scikit-learn and TensorFlow to predict revenue using linear regression models and conduct risk assessments using Monte Carlo simulations. It applies portfolio optimization models to investor data to help select optimal investment targets.

[0640] Business plan evaluation

[0641] The server evaluates the company's business plan based on the analysis results. Specifically, the business plan evaluation tool generates a report based on revenue forecast results, risk assessment results, SWOT analysis results, etc. The report is created using natural language processing technology, allowing the user (startup company representative) to understand the company's strengths and weaknesses.

[0642] Investment recommendation

[0643] The server selects the most suitable startups based on the investor's investment policy and risk tolerance. It generates a detailed report including the reasons for the recommendation and risk factors and provides it to the user (investor), allowing the investor to make a more appropriate decision.

[0644] Providing an interface

[0645] The terminal provides an interface that allows users to view the evaluation results and recommendations. Users can also request re-evaluation based on changes to conditions or new scenarios from the server via the terminal, and receive a new report.

[0646] Adding an Emotion Engine

[0647] The emotion engine analyzes the user's input data and reactions to recognize the user's emotional state. This analysis uses algorithms that analyze emotions from text and voice data. For example, it can use Google Cloud Natural Language API or IBM Watson's emotion analysis tool.

[0648] The server reflects the emotional data obtained from the emotion engine and takes the user's emotional state into account when evaluating business plans and recommending investments. For example, if the user is in a positive emotional state, it can present more risk-taking options.

[0649] Emotion-based interface adjustment

[0650] The device adjusts the user interface based on feedback from the emotion engine. For example, if the user is feeling stressed, the device may simplify the interface.

[0651] Specific examples

[0652] Support for developing business plans for startups

[0653] 1. A user (startup representative) logs into the system using a terminal and inputs information such as a business plan, financial data, market analysis report, and team composition. The emotion engine analyzes the user's text input and voice instructions to recognize their emotional state.

[0654] 2. The server collects the input data and performs data analysis. For example, it uses a linear regression model to predict profits and a Monte Carlo simulation to assess risk. It also takes into account the sentiment data from the sentiment engine and reflects it in the evaluation report.

[0655] 3. Based on the analysis results, the server generates a natural language report containing the business plan evaluation tools' strengths and weaknesses. Based on the sentiment data, it highlights risk-taking options if the user is optimistic.

[0656] 4. The terminal provides this report to the user (startup staff) and allows them to view it on the screen, providing an interface that responds to the user's emotional state.

[0657] Investor selection of investment companies

[0658] 1. A user (investor) logs into the system using a terminal and provides information such as investment policy, past investment history, and risk tolerance. The emotion engine analyzes the user's input data and reactions to recognize their emotional state.

[0659] 2. Based on the investment policy, the server analyzes the collected data on startup companies using a portfolio optimization model to select the optimal investment targets. The server takes into account the sentiment data from the sentiment engine and reflects this in the recommendation report.

[0660] 3. The server selects the best startups to invest in and generates a natural language report with recommendations and risk factors. Based on sentiment data, it highlights lower-risk options if the user feels unsure.

[0661] 4. The terminal provides this report to the user (investor) for viewing on the screen, adjusting the interface based on feedback from the sentiment engine.

[0662] Prompt Sentence Examples

[0663] "Users input their business plan and financial data into the device, and the emotion engine analyzes their emotional state. The generated business plan report is adjusted based on the emotion analysis results."

[0664] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0665] Step 1: User logs into the system

[0666] A user accesses the system using a terminal and enters login information. The entered user ID and password are sent from the terminal to the server.

[0667] The server authenticates the received login information by checking it against a database. If authentication is successful, it identifies the user's type (startup or investor) and generates the appropriate dashboard, which becomes the gateway for the user to perform further operations.

[0668] Step 2: Data entry

[0669] After logging in, users enter information such as business plans, financial data, market analysis reports, and team composition into the terminal. This information is provided by the startup company's representatives. Investors also enter their investment policy, past investment history, risk tolerance, and other information.

[0670] The terminal temporarily stores the entered data and converts it into an appropriate format for transmission to the server.

[0671] Step 3: Data collection

[0672] The server receives the data sent from the terminal and stores it in a database. The server checks the consistency and completeness of the received data and detects missing information and input errors.

[0673] If the server detects missing data or errors, it notifies the user and prompts them to make corrections or enter additional information.

[0674] Step 4: Data analysis

[0675] The server analyzes the data stored in the database using machine learning algorithms and statistical methods, specifically using Python libraries such as Scikit-learn and TensorFlow.

[0676] The server uses a revenue forecasting model to predict the revenue of startup companies and performs risk assessment using Monte Carlo simulation. After the analysis, the server saves the results.

[0677] Step 5: Evaluate your business plan

[0678] The server evaluates the business plan based on the results of the data analysis. The business plan evaluation means generates a report based on the results of the revenue forecast, risk assessment, SWOT analysis, etc.

[0679] The server uses natural language processing technology to document the evaluation in a user-friendly format and stores the results on the server. This evaluation helps users make important decisions.

[0680] Step 6: Recommend investments

[0681] The server analyzes the collected startup company data using a portfolio optimization model based on the investor's investment policy and risk tolerance.

[0682] The server uses the analysis results to select the most suitable startups to invest in and generates a detailed report including the reasons for the recommendation and risk factors. The report is generated using natural language processing technology.

[0683] Step 7: Providing the resulting interface

[0684] The device displays the evaluation results and recommendations received from the server to the user, who can then review the information through a dashboard or report.

[0685] The user can request the server to reassess the results based on changes to the conditions or new scenarios via the terminal. The terminal sends these requests to the server, which then performs the reanalysis.

[0686] Step 8: Emotion Engine Analysis

[0687] The emotion engine analyzes user input data and reactions in real time to recognize emotional states, using Google Cloud Natural Language API and IBM Watson emotion analysis tools.

[0688] The emotion engine identifies positive and negative emotions from text and voice data and sends the results to the server.

[0689] Step 9: Emotion-Based Interface Adjustment

[0690] The server reflects the emotional data obtained from the emotion engine and takes the user's emotional state into account when evaluating business plans and recommending investment targets. For example, if the user is in a positive emotional state, it presents risk-taking options.

[0691] The device adjusts the user interface based on feedback from the emotion engine. For example, if the user is feeling stressed, the device may simplify the interface.

[0692] In this way, the system takes into account the user's emotional state to support startups in formulating business plans and investors in selecting investment targets, thereby improving user satisfaction and the accuracy of decision-making.

[0693] (Application example 2)

[0694] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0695] Conventional systems for developing business plans for startups and selecting investment targets for investors were unable to provide personalized advice that took into account the user's emotional state. This meant that users' emotional biases could affect their decision-making, making it difficult to select optimal business plans and investment targets. Furthermore, particularly in fields with volatile markets such as the food delivery business, rapid and appropriate responses in real time are required, but conventional systems were unable to adequately address this.

[0696] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0697] In this invention, the server includes a data collection means, a data analysis means, a business plan evaluation means, an investment recommendation means, an emotional state recognition means, an emotional feedback reflection means, and an interface provision means, thereby enabling highly accurate business plan formulation and investment selection while taking into account the emotional state of the user.

[0698] "Data collection means" is a function for collecting necessary information such as business plans, financial data, and investment policies from companies and investors.

[0699] "Data analysis means" is a function that analyzes collected data and performs profit forecasts and risk assessments.

[0700] The "business plan evaluation tool" is a function that evaluates a company's business plan based on the analysis results and compiles a report on its strengths and weaknesses.

[0701] "Investment recommendation tool" is a function that selects the most suitable investment based on the investor's investment policy and generates a report including the reasons for the recommendation and risk factors.

[0702] The "emotional state recognition means" is a function that analyzes the input data and reactions of the user and recognizes the user's emotional state.

[0703] The "emotion feedback reflection means" is a function that reflects the recognized user emotion data in the evaluation of business plans and the selection of investment targets.

[0704] The "interface providing means" is a function that provides an interface that allows the user to view the evaluation results and recommendations, and makes adjustments according to the user's emotional state.

[0705] This invention relates to a system that uses a smartphone application specialized for food delivery businesses to help startup companies formulate effective business plans and investors select optimal investment targets. The system of the present invention consists of three main components: a server, a user terminal, and an emotion engine.

[0706] System Configuration

[0707] 1. Server

[0708] Data collection methods:

[0709] The server collects data from startups, such as market size, marketing costs, and delivery time, as well as data from investors, such as investment policy, past investment history, and risk tolerance.

[0710] Data analysis methods:

[0711] The server analyzes the collected data using Scikit-Learn's LinearRegression and StandardScaler, which allows for profit forecasting and risk assessment.

[0712] Business plan evaluation tools:

[0713] The server evaluates the business plan based on the analysis results and generates a natural language report that includes the startup's strengths and weaknesses.

[0714] Recommended investment vehicles:

[0715] The server selects the most suitable investments based on the investor's investment policy and generates a detailed report including the reasons for the recommendation and risk factors.

[0716] Emotional state recognition means:

[0717] The server performs emotion analysis using TextBlob and recognizes the user's emotional state from input data and voice instructions.

[0718] Emotional feedback methods:

[0719] The server then reflects the recognized emotional data in its evaluations and recommendations, for example, emphasizing risk-taking options when the user has positive emotions and emphasizing risk-avoiding options when the user has negative emotions.

[0720] User terminal

[0721] The user terminal is provided with the following features:

[0722] Interface provided by:

[0723] Based on the analysis results of the emotion engine, a user-friendly interface is provided. The interface is adjusted according to the user's emotional state. For example, if the user is feeling stressed, the information displayed will be concise.

[0724] Specific examples

[0725] Support for developing business plans for startups

[0726] 1. User:

[0727] Startup company representatives log into the system using their smartphones and enter data such as market size, marketing costs, and delivery times. An emotion engine analyzes emotions from the user's text input.

[0728] 2. Server:

[0729] Analyze the input data, use LinearRegression to predict revenue, and perform sentiment analysis using TextBlob. Based on the prediction results and sentiment data, generate a business plan evaluation report. For example, if the market size is large and profits are expected, and positive sentiment is recognized, emphasize advice to take risks.

[0730] 3. User Device:

[0731] Users can view this report on their device and request a reassessment based on new scenarios through an intuitive interface.

[0732] Investor selection of investment companies

[0733] 1. User:

[0734] Investors log in to the system using their smartphones and enter data such as their investment policy, past investment history, risk tolerance, etc. The sentiment engine analyzes emotions from the user's input text.

[0735] 2. Server:

[0736] It analyzes the collected data based on the investment policy and selects the most suitable startups to invest in. It also takes into account sentiment data and generates a detailed report including the risks and reasons for recommendations. For example, if the user is feeling anxious, it will highlight options with reduced risk.

[0737] 3. User Device:

[0738] Users can view this report on their devices and make optimal investment decisions through an interface that responds to their emotional state.

[0739] Example prompts to input to a generative AI model:

[0740] "The market size is large and profits are expected. Should I choose the company with the lowest risk as my investment target among Company A, Company B, or Company C?"

[0741] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0742] Step 1:

[0743] User Data Entry

[0744] Users (startup company representatives or investors) log into the system using their smartphones and enter data such as market size, marketing costs, delivery time, as well as information such as investment policy, past investment history, risk tolerance, etc. Based on this input, the system sends the data to the server.

[0745] Inputs: Business data such as market size, marketing costs, delivery time, investment policy, investment history, risk tolerance

[0746] Output: Input data sent to the server

[0747] Step 2:

[0748] Data collection and preprocessing

[0749] The server receives the data entered by the user and standardizes it as needed. For example, StandardScaler is used to standardize data such as market size, marketing costs, and delivery times.

[0750] Input: Received user data

[0751] Output: Standardized data

[0752] Step 3:

[0753] Revenue forecasting and risk assessment

[0754] The server uses the standardized data to run revenue forecasting and risk assessment models. Specifically, it uses Linear Regression to forecast revenue and obtains the model's prediction results. For risk assessment, it uses other statistical methods and machine learning algorithms.

[0755] Input: Standardized data

[0756] Output: Predicted revenue and risk assessment results

[0757] Step 4:

[0758] Recognition of emotional states

[0759] The server analyzes the user's text input using TextBlob to recognize the user's emotional state, which is classified into three categories: positive, neutral, and negative.

[0760] Input: User text input

[0761] Output: User's emotional state (positive, neutral, negative)

[0762] Step 5:

[0763] Reflecting emotional feedback

[0764] The server generates advice for revenue prediction and risk assessment results based on the recognized emotional state, for example, advising to take risks in the case of a positive emotional state and advising to refrain from risks in the case of a negative emotional state.

[0765] Inputs: Revenue forecast, risk assessment results, user emotional state

[0766] Output: Personalized advice

[0767] Step 6:

[0768] Generate a report of the results

[0769] The server combines revenue forecasts, risk assessments, and emotional state-based advice to generate a natural language report that includes the strengths and weaknesses of the business plan, as well as the reasons and risk factors for investment recommendations.

[0770] Inputs: Revenue forecast, risk assessment results, personalized advice

[0771] Output: Natural language report

[0772] Step 7:

[0773] User interface adjustments

[0774] The device displays the report received from the server to the user. Based on the analysis results of the emotion engine, the device adjusts the interface to present information appropriately according to the user's emotional state. For example, if the user is feeling stressed, the device displays brief information, and if the user is relaxed, the device displays detailed information.

[0775] Input: Report received from the server, analysis results of the emotion engine

[0776] Output: A tailored user interface

[0777] Example prompts to input to a generative AI model:

[0778] "The market size is large and profits are expected. Should I choose the company with the lowest risk as my investment target among Company A, Company B, or Company C?"

[0779] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0780] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0781] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0782] [Third embodiment]

[0783] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0784] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0785] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0786] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0787] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0788] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0789] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0790] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0791] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[0792] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0793] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0794] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[0795] This invention is a system that helps start-up companies develop effective business plans and allows investors to efficiently select the most suitable companies to invest in. This system consists of three elements: a server, a terminal, and a user.

[0796] System Configuration

[0797] 1. Data Collection

[0798] Server: Receives data from companies and investors. From startups, collects information such as business plans, financial data, market analysis reports, and team composition. From investors, collects information such as investment policy, past investment history, risk tolerance, desired investment return, and investment period.

[0799] 2. Data Analysis

[0800] Server: Analyzes collected data using machine learning algorithms and statistical methods. Applying revenue forecasting models and risk assessment models to startup company data to evaluate future revenue and risk. Applying portfolio optimization models to investor data to help select optimal investment targets.

[0801] 3. Business plan evaluation

[0802] Server: Evaluates the company's business plan based on the analysis results. The results of revenue forecasts, risk assessments, and SWOT analysis are compiled using business plan evaluation tools. This results in a report in natural language summarizing the company's strengths and weaknesses, which is then provided to the user (startup company representative).

[0803] 4. Investment recommendation

[0804] Server: Based on the investor's investment policy, the server selects the most suitable investment targets from the collected startup companies. It generates a detailed report including the reasons for the recommendation and risk factors and provides it to the user (investor).

[0805] 5. Providing an Interface

[0806] Terminal: Provides an interface that allows users to view evaluation results and recommendations. Users can request re-evaluation based on changes to conditions or new scenarios from the server via their terminal, and receive a new report.

[0807] Specific examples

[0808] Support for developing business plans for startups

[0809] 1. User (startup staff): Logs into the system using a terminal and enters information such as business plans, financial data, market analysis reports, and team composition.

[0810] 2. Server: Collects input data and performs data analysis, such as using linear regression models to forecast profits and Monte Carlo simulations to assess risk.

[0811] 3. Server: Based on the analysis results, the business plan evaluation instrument generates a natural language report including strengths and weaknesses.

[0812] 4. Terminal: This report is provided to the user (startup staff) so that it can be viewed on the screen.

[0813] Investor selection of investment companies

[0814] 1. User (Investor): Logs into the system using a terminal and provides information such as investment policy, past investment history, and risk tolerance.

[0815] 2. Server: Analyzes collected data on startups based on investment policies, and uses portfolio optimization models to forecast returns and assess risks.

[0816] 3. Server: Selects the best startups to invest in and generates a natural language report containing the reasons for the recommendation and risk factors.

[0817] 4. Terminal: This report is provided to the user (investor) so that it can be viewed on the screen.

[0818] This will enable startups to effectively develop business plans and investors to efficiently select the most suitable investment targets.

[0819] The processing flow will be explained below.

[0820] Step 1:

[0821] Users log in to the system using a terminal. If they log in as a startup company, they enter their company's business plan, financial data, market analysis report, team composition, etc. into the system. If they log in as an investor, they enter their investment policy, past investment history, risk tolerance, etc.

[0822] Step 2:

[0823] The server receives the information entered by the user and stores it in a database. The startup company data is classified as business plan-related data, including financial data and market analysis information. The investor data is classified as investment policy-related data, including investment history and risk tolerance.

[0824] Step 3:

[0825] The server cleans the collected data, filling in missing values ​​and standardizing the data format to make it analyzable. For example, it checks the consistency of numerical data and converts or fills in data as necessary.

[0826] Step 4:

[0827] The server applies revenue forecasting and risk assessment models to the startup company data. Specifically, it uses a linear regression model to forecast revenue based on past data and market analysis information, and performs risk assessment using Monte Carlo simulation.

[0828] Step 5:

[0829] The server applies a portfolio optimization model to the investor data, analyzing the investor's past investment patterns and taking into account current market conditions to generate a list of optimal investments.

[0830] Step 6:

[0831] The server converts the startup's business plan assessment into natural language and creates a detailed report including the company's strengths and weaknesses based on revenue forecasts, risk assessments, SWOT analysis, and other information.

[0832] Step 7:

[0833] The server then converts the list of recommended investments and the reasons for them into a natural language report for the investor, detailing each company's earnings forecast, risk assessment, and points that match the investor's investment policy.

[0834] Step 8:

[0835] The terminal provides an interface that allows users to view the evaluation results and recommendations. Users can also view detailed reports and input new conditions or scenarios to request a re-evaluation.

[0836] Step 9:

[0837] The system provides an interface through which users input new data and scenarios for revaluation, for example, new market conditions or investment strategies.

[0838] Step 10:

[0839] The server then re-analyzes the newly entered data and scenarios, applies revenue forecasting and risk assessment models, and generates updated reports.

[0840] Step 11:

[0841] The terminal provides the reevaluated results to the user, who then uses them to formulate a final business plan and decide on investment destinations.

[0842] Example 1

[0843] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0844] When startups develop effective business plans, there is no system that can efficiently collect and analyze large amounts of data and reduce the effort required for investors to select optimal investment targets.In addition, there is a lack of functionality to generate reports in natural language based on the collected data, which delays user understanding and decision-making.

[0845] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0846] In this invention, the server includes a data collection means, a data analysis means, a business plan evaluation means, an investment target recommendation means, an interface provision means, and a means for converting the data analysis results into a natural language report using a generative AI model, thereby enabling startup companies to formulate business plans and investors to efficiently select optimal investment targets.

[0847] "Data collection means" refers to means for collecting information such as business plans, financial data, market analysis information, investment policies, past investment history, and risk tolerance from organizations and investors.

[0848] "Data analysis means" refers to means for conducting analysis such as revenue forecasting and risk assessment based on collected data using machine learning algorithms and statistical methods.

[0849] The "business plan evaluation means" is a means for evaluating the business plans of startup companies based on the analysis results obtained by the data analysis means and compiling the results into a report.

[0850] The "investment recommendation means" is a means for selecting the most suitable investment based on the investor's investment policy and risk tolerance, and generating a report including the reasons for the recommendation and risk factors.

[0851] The "interface providing means" is a means for providing an interface that allows the user to view the evaluation results and the recommended contents.

[0852] "Means for converting data analysis results into natural language reports using generative AI models" refers to means for generating reports in a format that is easy for users to understand, based on collected and analyzed data, using natural language generation algorithms.

[0853] This invention is a system that helps start-up companies develop effective business plans and allows investors to efficiently select the most suitable companies to invest in. This system consists of three elements: a server, a terminal, and a user.

[0854] 1. Data Collection Methods

[0855] The server collects data from companies and investors. At the same time, it collects data such as business plans, financial data, market analysis reports, and team composition from organizations, and information such as investment policy, past investment history, risk tolerance, desired investment return, and investment period from investors. The data is stored in a relational database (e.g., MySQL or PostgreSQL). During the data collection phase, validation scripts are run to detect and complete input errors and missing values.

[0856] 2. Data analysis methods

[0857] The server analyzes the collected data using machine learning algorithms and statistical methods. Specifically, it preprocesses the data using Python's Pandas and NumPy. It then applies a linear regression model using Scikit-learn to predict future revenue. It also performs risk assessment using Monte Carlo simulation. The data analysis script is automatically executed periodically by a job scheduler (Cron or Airflow).

[0858] 3. Business plan evaluation tools

[0859] The server evaluates the business plan based on the analysis results. Specifically, it uses Python NLP libraries (e.g., generative AI models such as SpaCy and GPT-3) to compile revenue forecasts and risk assessment results into a natural language report. It also generates a template-based report that includes SWOT analysis results to clearly identify the company's strengths and weaknesses. The prompt for the generative AI model is, "Based on the revenue forecast results, please explain the strengths and weaknesses of this company."

[0860] 4. Investment Recommendation Methods

[0861] The server selects the best investment targets based on the investor's investment policy. It matches investor data with startup company analysis data and applies a portfolio optimization model. It uses libraries such as PyPortfolioOpt to select the best investment target companies. The prompt for the generative AI model is, "Select the best company for this investor's portfolio and explain why."

[0862] 5. Means of providing interface

[0863] The terminal provides an interface that allows users to view the evaluation results and recommendations. React.js and Vue.js are used as front-end technologies, while web frameworks such as Django and Flask are used for the back-end. Once users log in, they can access a dashboard screen where they can download or view the evaluation results and investment recommendation reports. A form for submitting a reevaluation request is also provided, allowing users to submit new data to the server.

[0864] The above configuration realizes a system that enables startup companies to effectively formulate business plans and investors to efficiently select optimal investment targets.

[0865] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0866] Step 1:

[0867] Data Entry

[0868] Users log in to the system using a terminal. Startup company representatives input data such as business plans, financial data, market analysis reports, and team composition. Investors input information such as investment policy, past investment history, risk tolerance, desired investment return, and investment period. The input data is saved in the system's database.

[0869] Step 2:

[0870] Data collection

[0871] The server receives data entered by users and stores it in a relational database (MySQL or PostgreSQL). During the data collection phase, validation scripts are run to verify the input data. Input errors and missing values ​​are detected and completed to ensure accurate data is collected.

[0872] Step 3:

[0873] Data analysis

[0874] The server analyzes the collected data. It preprocesses the data using Python's Pandas and NumPy. It then uses Scikit-learn to apply a linear regression model to predict future revenue. It also performs risk assessment using Monte Carlo simulation. The analysis script is automatically executed periodically using a job scheduler (Cron or Airflow). It uses the collected company data and investor data as input, and outputs revenue forecasts and risk assessment results.

[0875] Step 4:

[0876] Business plan evaluation

[0877] The server evaluates the company's business plan based on the results of the data analysis. It uses Python NLP libraries (e.g., SpaCy or generative AI models) to compile revenue forecasts and risk assessment results into natural language reports. It also adds SWOT analysis results to highlight strengths and weaknesses. Template-based reports are generated. The analysis results are used as input, and the natural language report is the output.

[0878] Step 5:

[0879] Investment recommendation

[0880] The server selects optimal investments based on the investor's investment policy and risk tolerance. It uses PyPortfolioOpt to run a portfolio optimization model and select appropriate investment companies. The generative AI model receives a prompt, "Select the best companies for this investor's portfolio and explain why," and generates a report. Investor data and company data are used as input, and a report of investment recommendations is obtained as output.

[0881] Step 6:

[0882] Interface provided

[0883] The terminal provides an interface that allows users to view evaluation results and recommendations. React.js and Vue.js are used as front-end technologies, while web frameworks such as Django and Flask are used for the back-end. Once users log in, they can view evaluation results and investment recommendation reports on the dashboard screen. A function to send re-evaluation requests is also provided. User input includes login information, and evaluation results and recommendations are provided as output.

[0884] (Application example 1)

[0885] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0886] Currently, many startups lack effective support when formulating their business plans, and investors face difficulties in efficiently selecting the most suitable investment targets. Furthermore, investors lack the means to obtain the latest investment information and risk assessments in real time, which can delay appropriate decision-making. This not only results in missed growth opportunities for startups, but also makes it difficult for investors to realize the investment returns they expect.

[0887] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0888] In this invention, the server includes a data collection means, a data analysis means, a business plan evaluation means, an investment target recommendation means, an interface provision means, a dashboard display means, a business plan evaluation report generation means, an alert notification means, and an AI assistant recommendation means, thereby enabling startup companies to effectively formulate business plans and investors to efficiently select optimal investment targets while also being able to grasp the latest investment information and risk assessments in real time.

[0889] "Data collection means" refers to means for collecting business plans, financial data, and market analysis information from companies, and investment policies, past investment history, and risk tolerance from investors.

[0890] "Data analysis means" refers to means for analyzing collected data using machine learning algorithms and statistical methods to forecast profits and assess risks.

[0891] The "business plan evaluation tool" is a tool that evaluates a company's business plan based on the analysis results and generates a report that includes strengths and weaknesses.

[0892] An "investment recommendation tool" is a tool that selects optimal investments based on an investor's investment policy and generates a detailed report including the reasons for the recommendation and risk factors.

[0893] The "interface providing means" is a means for providing an interface that allows the user to view the evaluation results and recommendations, and to request re-evaluation based on changes to conditions or a new scenario.

[0894] A "dashboard display" is a visual display that allows a user to manage their investment portfolio and see important information at a glance.

[0895] The "business plan evaluation report generating means" is a means for evaluating a company's business plan based on the collected and analyzed data and generating the results in the form of a report.

[0896] The "alert notification means" is a means for notifying the user when a new investment destination is found or when there is a change in the status of an investment destination.

[0897] "AI assistant recommendation method" is a recommendation method that uses artificial intelligence to propose optimal investment strategies to investors and predict risks and returns.

[0898] This invention is a system for enabling start-up companies to formulate effective business plans and for investors to efficiently select optimal companies to invest in. The system includes a data collection means, a data analysis means, a business plan evaluation means, an investment target recommendation means, an interface provision means, a dashboard display means, a business plan evaluation report generation means, an alert notification means, and an AI assistant recommendation means.

[0899] Hardware and Software Configuration

[0900] The system consists of three elements: a server, a terminal, and a user. The server uses machine learning libraries such as Python and scikit-learn to collect data, analyze it, and generate reports. The terminal is a smartphone, and the user enters information and views the evaluation results through an interface.

[0901] Operation explanation

[0902] Data collection methods

[0903] The server collects business plans, financial data, and market analysis information from companies, and investment policies, past investment history, and risk tolerance from investors, creating a comprehensive database.

[0904] Data Analysis Methods

[0905] The collected data is analyzed using machine learning algorithms and statistical methods, such as linear regression models for revenue forecasting and Monte Carlo simulations for risk assessment.

[0906] Business plan evaluation tools

[0907] Based on the analysis results, the company's business plan is evaluated and a report containing strengths and weaknesses is generated, which is then compiled in an easy-to-read format using natural language generation (NLG) technology.

[0908] Investment recommendation methods

[0909] Based on the investor's investment policy, the system selects the most suitable companies to invest in. A report is generated detailing the reasons for recommending the selected companies and the risk factors involved.

[0910] Interface provision means

[0911] It provides an interface for users to view evaluation results and recommendations, and users can request re-evaluation from the server via their terminal, changing conditions or using new scenarios.

[0912] Dashboard display method

[0913] It provides a dashboard that allows users to manage their investment portfolio and see key information at a glance, enabling them to make decisions instantly.

[0914] Business plan evaluation report generation tool

[0915] Based on the collected and analyzed data, the business plans of companies are evaluated and the results are generated in the form of a report, which is provided to startup companies to help them develop effective business plans.

[0916] Alert notification method

[0917] Users will receive alerts when new investments are discovered or when there is a change in the status of an investment, allowing them to stay informed of important information in real time.

[0918] AI assistant recommended methods

[0919] Using artificial intelligence, the company offers investors optimal investment strategies and predicts risks and returns.

[0920] Specific examples

[0921] Startup Company A enters its business plan and financial data into the system. The server analyzes the entered data, performs revenue forecasts and risk assessments, and compiles the results into a report. Investors can view this report on their devices and confirm that Company A has a high likelihood of generating revenue and low risk.

[0922] Prompt Sentence Examples

[0923] "Enter the business plan and financial data for startup company A below. Please provide a revenue forecast and risk assessment for this company.

[0924] Current earnings: 10,000

[0925] Future market growth rate: 20%

[0926] Expected cost: 25,000.”

[0927] These features enable startups to effectively develop business plans and investors to efficiently select the best investment targets.

[0928] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0929] Step 1:

[0930] A user logs into the system using a terminal. Depending on their role, the user can log in as a representative of the startup company or as an investor.

[0931] Step 2:

[0932] Users (startup staff) input business plans, financial data, and market analysis information through a terminal, which is then sent to a server and stored in a database.

[0933] Step 3:

[0934] The server analyzes the collected data. For example, to predict the revenue of a startup company, a linear regression model is used, taking data such as market growth rate and costs as inputs to predict future revenue. The output is the revenue forecast.

[0935] Step 4:

[0936] The server performs risk assessment using Monte Carlo simulation, using input data such as revenue forecasts and the standard deviation of market growth rates, and running multiple simulations to obtain a risk assessment value.

[0937] Step 5:

[0938] The server evaluates the business plan based on the revenue forecast results and risk assessment value, and generates a business plan evaluation report including its strengths and weaknesses. This report is created in text format using natural language generation technology and provided to the user (startup manager).

[0939] Step 6:

[0940] A user (investor) logs into the system through a terminal and provides their investment policy, past investment history, and risk tolerance. This data is sent to the server and stored in a database.

[0941] Step 7:

[0942] The server analyzes the collected data on startup companies based on the investor's investment policy, selects the most suitable investment target companies using a portfolio optimization model, and generates a report containing the reasons for the recommendation and risk factors using the company's revenue forecast and risk assessment value as input.

[0943] Step 8:

[0944] The server generates a recommendation report and provides it to the user (investor), who then views the report through their terminal and makes a decision on investment destinations.

[0945] Step 9:

[0946] The server sends alert notifications when new investments are discovered or when there is a change in the status of an investment. Alert notifications are sent in real time, providing users with the latest information.

[0947] Step 10:

[0948] The server uses its AI assistant function to propose optimal investment strategies to investors. The AI ​​model receives inputs such as the user's investment policy and past investment history, and outputs predicted risks and returns, as well as optimal investment strategies.

[0949] These processing steps create a system that allows startup companies to effectively develop business plans and investors to efficiently select the most suitable investment targets.

[0950] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0951] This invention combines a system that helps startup companies formulate effective business plans and helps investors efficiently select the most suitable companies to invest in with an emotion engine that recognizes the user's emotions. This system consists of four elements: a server, a terminal, a user, and an emotion engine.

[0952] System Configuration

[0953] 1. Data Collection

[0954] Server: Receives data from companies and investors. From startups, collects information such as business plans, financial data, market analysis reports, and team composition. From investors, collects information such as investment policy, past investment history, risk tolerance, desired investment return, and investment period.

[0955] 2. Data Analysis

[0956] Server: Analyzes collected data using machine learning algorithms and statistical methods. Applying revenue forecasting models and risk assessment models to startup company data to evaluate future revenue and risk. Applying portfolio optimization models to investor data to help select optimal investment targets.

[0957] 3. Business plan evaluation

[0958] Server: Evaluates the company's business plan based on the analysis results. The results of revenue forecasts, risk assessments, and SWOT analysis are compiled using business plan evaluation tools. This results in a report in natural language summarizing the company's strengths and weaknesses, which is then provided to the user (startup company representative).

[0959] 4. Investment recommendation

[0960] Server: Based on the investor's investment policy, the server selects the most suitable investment targets from the collected startup companies. It generates a detailed report including the reasons for the recommendation and risk factors and provides it to the user (investor).

[0961] 5. Providing an Interface

[0962] Terminal: Provides an interface that allows users to view evaluation results and recommendations. Users can request re-evaluation based on changes to conditions or new scenarios from the server via their terminal, and receive a new report.

[0963] 6. Adding an Emotion Engine

[0964] Emotion engine: Analyzes user input data and responses to recognize the user's emotional state. Includes algorithms that analyze emotions from voice and text data. The results of this analysis are reflected in ratings and recommendations, providing a more personalized service.

[0965] Server: Reflects the emotional data obtained from the emotion engine and takes the user's emotional state into account when evaluating business plans and recommending investment targets. For example, if a user is in a positive emotional state, it can present more risky options.

[0966] Device: Adjust the user interface based on feedback from the emotion engine. For example, if the user is feeling stressed, the interface may be simplified.

[0967] Specific examples

[0968] Support for developing business plans for startups

[0969] 1. User (startup staff): Logs into the system using a terminal and inputs information such as a business plan, financial data, market analysis reports, and team composition. The emotion engine analyzes the user's text input and voice instructions to recognize their emotional state.

[0970] 2. Server: Collects input data and performs data analysis. For example, it uses linear regression models to forecast profits and Monte Carlo simulations to assess risk. It also takes into account sentiment data from the sentiment engine and reflects it in the evaluation report.

[0971] 3. Server: Based on the analysis results, the business plan evaluator generates a natural language report containing strengths and weaknesses. Based on sentiment data, for example, it highlights risky options if the user is optimistic.

[0972] 4. Terminal: This report is provided to the user (startup staff) and can be viewed on the screen. An interface is provided that responds to the user's emotional state.

[0973] Investor selection of investment companies

[0974] 1. User (investor): Logs in to the system using a terminal and provides information such as investment policy, past investment history, risk tolerance, etc. The emotion engine analyzes the user's input data and reactions to recognize their emotional state.

[0975] 2. Server: Analyzes the collected data of startups based on the investment policy. Uses a portfolio optimization model to forecast returns and assess risks. Considers sentiment data from the sentiment engine and reflects it in recommendation reports.

[0976] 3. Server: Selects the best startups to invest in and generates a natural language report with recommendations and risk factors. Based on sentiment data, for example, if the user is feeling anxious, it will highlight options with reduced risk.

[0977] 4. Terminal: This report is provided to the user (investor) for viewing on the screen, and the interface is adjusted based on feedback from the sentiment engine.

[0978] This will enable startups to develop more precise business plans and investors to make optimal investment decisions that take into account their own emotional state.

[0979] The processing flow will be explained below.

[0980] Step 1:

[0981] Users log in to the system using a terminal. If they log in as a startup company, they enter their company's business plan, financial data, market analysis report, team composition, etc. into the system. If they log in as an investor, they enter their investment policy, past investment history, risk tolerance, etc.

[0982] Step 2:

[0983] The server receives the information entered by the user and stores it in a database. The startup company data is classified as business plan-related data, including financial data and market analysis information. The investor data is classified as investment policy-related data, including investment history and risk tolerance.

[0984] Step 3:

[0985] The server cleans the collected data, filling in missing values ​​and standardizing the data format to make it analyzable. For example, it checks the consistency of numerical data and converts or fills in data as necessary.

[0986] Step 4:

[0987] The emotion engine analyzes the user's input data and reactions. For example, it uses algorithms to analyze emotions from the language used when the user enters text and from voice data. The emotion engine recognizes the user's current emotional state (positive, negative, neutral) in real time.

[0988] Step 5:

[0989] The server applies revenue forecasting and risk assessment models to the startup company data. Specifically, it uses a linear regression model to predict revenue based on past data and market analysis information, and Monte Carlo simulation to assess risk. It also takes into account emotional data from the emotion engine, and adjusts the risk estimate slightly higher if the user is positive, for example.

[0990] Step 6:

[0991] The server applies a portfolio optimization model to the investor's data, analyzing their past investment patterns and taking into account current market conditions to generate a list of optimal investments. It also incorporates sentiment data from the sentiment engine, making recommendations to reduce risk, for example, if the user is feeling anxious.

[0992] Step 7:

[0993] The server converts the startup's business plan evaluation into natural language. It creates a detailed report including the company's strengths and weaknesses based on revenue forecasts, risk assessments, SWOT analysis, etc. It also makes personalized suggestions based on sentiment data, such as proposing aggressive strategies if the user is optimistic.

[0994] Step 8:

[0995] The server converts a list of recommended investments and the reasons for them into a natural language report for the investor. It details each company's revenue forecast and risk assessment, as well as points that match the investor's investment policy. Based on emotional data, for example, if the user is feeling stressed, it will recommend low-risk investments to give them a sense of security.

[0996] Step 9:

[0997] The device provides an interface where users can view the evaluation results and recommendations. Users can also input new conditions or scenarios to request a re-evaluation. Based on feedback from the emotion engine, the interface is adjusted to optimize the user experience.

[0998] Step 10:

[0999] The server then re-analyzes the newly entered data and scenarios, applies revenue forecasting and risk assessment models, and generates updated reports, incorporating sentiment data from the emotion engine and providing recommendations based on the latest user state.

[1000] Step 11:

[1001] The device then provides the reevaluated results to the user, who can then use them to formulate a final business plan and decide where to invest. Information is displayed in a way that is tailored to the user based on the emotional data.

[1002] Example 2

[1003] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1004] In the past, startups developed business plans and investors selected investment targets in a way that the analysis and evaluation of collected data was not efficient and accurate enough, and in particular, the emotional state of the user was not taken into consideration, which can lead to a decrease in the reliability and satisfaction of the results. Furthermore, in the past, the user experience was often inconsistent because the interface was not adjusted according to the emotional state of the user.

[1005] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a data collection means, a data analysis means, a business plan evaluation means, an investment destination recommendation means, an interface provision means, an emotion analysis means, and an emotion-based interface adjustment means. This allows startup companies to formulate business plans more precisely and enables investors to select optimal investments taking into account their emotional state.

[1006] "Data collection methods" are the means used to collect necessary information from companies and investors.

[1007] "Data analysis means" refers to means for analyzing collected data using machine learning algorithms and statistical methods.

[1008] A "business plan evaluation tool" is a tool for evaluating a company's business plan based on the results of data analysis.

[1009] "Investment recommendation tools" are tools for selecting and recommending optimal investments based on an investor's investment policy and risk tolerance.

[1010] "Interface providing means" refers to a means for providing an interface that allows users to view and operate evaluation results and recommendations.

[1011] The "emotion analysis means" is a means for analyzing the user's input data and reactions and recognizing the user's emotional state.

[1012] The "emotion-based interface adjustment means" is a means for adjusting the user interface based on the emotion data obtained from the emotion analysis means.

[1013] This invention combines a system that helps startup companies formulate effective business plans and helps investors efficiently select the most suitable companies to invest in with an emotion engine that recognizes the user's emotions. This system consists of four elements: a server, a terminal, a user, and an emotion engine.

[1014] First, the overall flow of the system will be described.

[1015] Data collection

[1016] The server collects data from companies and investors. Specifically, from startup companies, it collects information such as business plans, financial data, market analysis reports, and team composition. From investors, it collects information such as investment policy, past investment history, risk tolerance, desired investment return, and investment period. In this way, all necessary data is consolidated on the server.

[1017] Data analysis

[1018] The server analyzes the collected data using machine learning algorithms and statistical methods. It applies revenue prediction and risk assessment models to the startup company data to evaluate future revenue and risk. For example, it uses Python libraries such as Scikit-learn and TensorFlow to predict revenue using linear regression models and conduct risk assessments using Monte Carlo simulations. It applies portfolio optimization models to investor data to help select optimal investment targets.

[1019] Business plan evaluation

[1020] The server evaluates the company's business plan based on the analysis results. Specifically, the business plan evaluation tool generates a report based on revenue forecast results, risk assessment results, SWOT analysis results, etc. The report is created using natural language processing technology, allowing the user (startup company representative) to understand the company's strengths and weaknesses.

[1021] Investment recommendation

[1022] The server selects the most suitable startups based on the investor's investment policy and risk tolerance. It generates a detailed report including the reasons for the recommendation and risk factors and provides it to the user (investor), allowing the investor to make a more appropriate decision.

[1023] Providing an interface

[1024] The terminal provides an interface that allows users to view the evaluation results and recommendations. Users can also request re-evaluation based on changes to conditions or new scenarios from the server via the terminal, and receive a new report.

[1025] Adding an Emotion Engine

[1026] The emotion engine analyzes the user's input data and reactions to recognize the user's emotional state. This analysis uses algorithms that analyze emotions from text and voice data. For example, it can use Google Cloud Natural Language API or IBM Watson's emotion analysis tool.

[1027] The server reflects the emotional data obtained from the emotion engine and takes the user's emotional state into account when evaluating business plans and recommending investments. For example, if the user is in a positive emotional state, it can present more risk-taking options.

[1028] Emotion-based interface adjustment

[1029] The device adjusts the user interface based on feedback from the emotion engine. For example, if the user is feeling stressed, the device may simplify the interface.

[1030] Specific examples

[1031] Support for developing business plans for startups

[1032] 1. A user (startup representative) logs into the system using a terminal and inputs information such as a business plan, financial data, market analysis report, and team composition. The emotion engine analyzes the user's text input and voice instructions to recognize their emotional state.

[1033] 2. The server collects the input data and performs data analysis. For example, it uses a linear regression model to predict profits and a Monte Carlo simulation to assess risk. It also takes into account the sentiment data from the sentiment engine and reflects it in the evaluation report.

[1034] 3. Based on the analysis results, the server generates a natural language report containing the business plan evaluation tools' strengths and weaknesses. Based on the sentiment data, it highlights risk-taking options if the user is optimistic.

[1035] 4. The terminal provides this report to the user (startup staff) and allows them to view it on the screen, providing an interface that responds to the user's emotional state.

[1036] Investor selection of investment companies

[1037] 1. A user (investor) logs into the system using a terminal and provides information such as investment policy, past investment history, and risk tolerance. The emotion engine analyzes the user's input data and reactions to recognize their emotional state.

[1038] 2. Based on the investment policy, the server analyzes the collected data on startup companies using a portfolio optimization model to select the optimal investment targets. The server takes into account the sentiment data from the sentiment engine and reflects this in the recommendation report.

[1039] 3. The server selects the best startups to invest in and generates a natural language report with recommendations and risk factors. Based on sentiment data, it highlights lower-risk options if the user feels unsure.

[1040] 4. The terminal provides this report to the user (investor) for viewing on the screen, adjusting the interface based on feedback from the sentiment engine.

[1041] Prompt Sentence Examples

[1042] "Users input their business plan and financial data into the device, and the emotion engine analyzes their emotional state. The generated business plan report is adjusted based on the emotion analysis results."

[1043] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1044] Step 1: User logs into the system

[1045] A user accesses the system using a terminal and enters login information. The entered user ID and password are sent from the terminal to the server.

[1046] The server authenticates the received login information by checking it against a database. If authentication is successful, it identifies the user's type (startup or investor) and generates the appropriate dashboard, which becomes the gateway for the user to perform further operations.

[1047] Step 2: Data entry

[1048] After logging in, users enter information such as business plans, financial data, market analysis reports, and team composition into the terminal. This information is provided by the startup company's representatives. Investors also enter their investment policy, past investment history, risk tolerance, and other information.

[1049] The terminal temporarily stores the entered data and converts it into an appropriate format for transmission to the server.

[1050] Step 3: Data collection

[1051] The server receives the data sent from the terminal and stores it in a database. The server checks the consistency and completeness of the received data and detects missing information and input errors.

[1052] If the server detects missing data or errors, it notifies the user and prompts them to make corrections or enter additional information.

[1053] Step 4: Data analysis

[1054] The server analyzes the data stored in the database using machine learning algorithms and statistical methods, specifically using Python libraries such as Scikit-learn and TensorFlow.

[1055] The server uses a revenue forecasting model to predict the revenue of startup companies and performs risk assessment using Monte Carlo simulation. After the analysis, the server saves the results.

[1056] Step 5: Evaluate your business plan

[1057] The server evaluates the business plan based on the results of the data analysis. The business plan evaluation means generates a report based on the results of the revenue forecast, risk assessment, SWOT analysis, etc.

[1058] The server uses natural language processing technology to document the evaluation in a user-friendly format and stores the results on the server. This evaluation helps users make important decisions.

[1059] Step 6: Recommend investments

[1060] The server analyzes the collected startup company data using a portfolio optimization model based on the investor's investment policy and risk tolerance.

[1061] The server uses the analysis results to select the most suitable startups to invest in and generates a detailed report including the reasons for the recommendation and risk factors. The report is generated using natural language processing technology.

[1062] Step 7: Providing the resulting interface

[1063] The device displays the evaluation results and recommendations received from the server to the user, who can then review the information through a dashboard or report.

[1064] The user can request the server to reassess the results based on changes to the conditions or new scenarios via the terminal. The terminal sends these requests to the server, which then performs the reanalysis.

[1065] Step 8: Emotion Engine Analysis

[1066] The emotion engine analyzes user input data and reactions in real time to recognize emotional states, using Google Cloud Natural Language API and IBM Watson emotion analysis tools.

[1067] The emotion engine identifies positive and negative emotions from text and voice data and sends the results to the server.

[1068] Step 9: Emotion-Based Interface Adjustment

[1069] The server reflects the emotional data obtained from the emotion engine and takes the user's emotional state into account when evaluating business plans and recommending investment targets. For example, if the user is in a positive emotional state, it presents risk-taking options.

[1070] The device adjusts the user interface based on feedback from the emotion engine. For example, if the user is feeling stressed, the device may simplify the interface.

[1071] In this way, the system takes into account the user's emotional state to support startups in formulating business plans and investors in selecting investment targets, thereby improving user satisfaction and the accuracy of decision-making.

[1072] (Application example 2)

[1073] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1074] Conventional systems for developing business plans for startups and selecting investment targets for investors were unable to provide personalized advice that took into account the user's emotional state. This meant that users' emotional biases could affect their decision-making, making it difficult to select optimal business plans and investment targets. Furthermore, particularly in fields with volatile markets such as the food delivery business, rapid and appropriate responses in real time are required, but conventional systems were unable to adequately address this.

[1075] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1076] In this invention, the server includes a data collection means, a data analysis means, a business plan evaluation means, an investment recommendation means, an emotional state recognition means, an emotional feedback reflection means, and an interface provision means, thereby enabling highly accurate business plan formulation and investment selection while taking into account the emotional state of the user.

[1077] "Data collection means" is a function for collecting necessary information such as business plans, financial data, and investment policies from companies and investors.

[1078] "Data analysis means" is a function that analyzes collected data and performs profit forecasts and risk assessments.

[1079] The "business plan evaluation tool" is a function that evaluates a company's business plan based on the analysis results and compiles a report on its strengths and weaknesses.

[1080] "Investment recommendation tool" is a function that selects the most suitable investment based on the investor's investment policy and generates a report including the reasons for the recommendation and risk factors.

[1081] The "emotional state recognition means" is a function that analyzes the input data and reactions of the user and recognizes the user's emotional state.

[1082] The "emotion feedback reflection means" is a function that reflects the recognized user emotion data in the evaluation of business plans and the selection of investment targets.

[1083] The "interface providing means" is a function that provides an interface that allows the user to view the evaluation results and recommendations, and makes adjustments according to the user's emotional state.

[1084] This invention relates to a system that uses a smartphone application specialized for food delivery businesses to help startup companies formulate effective business plans and investors select optimal investment targets. The system of the present invention consists of three main components: a server, a user terminal, and an emotion engine.

[1085] System Configuration

[1086] 1. Server

[1087] Data collection methods:

[1088] The server collects data from startups, such as market size, marketing costs, and delivery time, as well as data from investors, such as investment policy, past investment history, and risk tolerance.

[1089] Data analysis methods:

[1090] The server analyzes the collected data using Scikit-Learn's LinearRegression and StandardScaler, which allows for profit forecasting and risk assessment.

[1091] Business plan evaluation tools:

[1092] The server evaluates the business plan based on the analysis results and generates a natural language report that includes the startup's strengths and weaknesses.

[1093] Recommended investment vehicles:

[1094] The server selects the most suitable investments based on the investor's investment policy and generates a detailed report including the reasons for the recommendation and risk factors.

[1095] Emotional state recognition means:

[1096] The server performs emotion analysis using TextBlob and recognizes the user's emotional state from input data and voice instructions.

[1097] Emotional feedback methods:

[1098] The server then reflects the recognized emotional data in its evaluations and recommendations, for example, emphasizing risk-taking options when the user has positive emotions and emphasizing risk-avoiding options when the user has negative emotions.

[1099] User terminal

[1100] The user terminal is provided with the following features:

[1101] Interface provided by:

[1102] Based on the analysis results of the emotion engine, a user-friendly interface is provided. The interface is adjusted according to the user's emotional state. For example, if the user is feeling stressed, the information displayed will be concise.

[1103] Specific examples

[1104] Support for developing business plans for startups

[1105] 1. User:

[1106] Startup company representatives log into the system using their smartphones and enter data such as market size, marketing costs, and delivery times. An emotion engine analyzes emotions from the user's text input.

[1107] 2. Server:

[1108] Analyze the input data, use LinearRegression to predict revenue, and perform sentiment analysis using TextBlob. Based on the prediction results and sentiment data, generate a business plan evaluation report. For example, if the market size is large and profits are expected, and positive sentiment is recognized, emphasize advice to take risks.

[1109] 3. User Device:

[1110] Users can view this report on their device and request a reassessment based on new scenarios through an intuitive interface.

[1111] Investor selection of investment companies

[1112] 1. User:

[1113] Investors log in to the system using their smartphones and enter data such as their investment policy, past investment history, risk tolerance, etc. The sentiment engine analyzes emotions from the user's input text.

[1114] 2. Server:

[1115] It analyzes the collected data based on the investment policy and selects the most suitable startups to invest in. It also takes into account sentiment data and generates a detailed report including the risks and reasons for recommendations. For example, if the user is feeling anxious, it will highlight options with reduced risk.

[1116] 3. User Device:

[1117] Users can view this report on their devices and make optimal investment decisions through an interface that responds to their emotional state.

[1118] Example prompts to input to a generative AI model:

[1119] "The market size is large and profits are expected. Should I choose the company with the lowest risk as my investment target among Company A, Company B, or Company C?"

[1120] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1121] Step 1:

[1122] User Data Entry

[1123] Users (startup company representatives or investors) log into the system using their smartphones and enter data such as market size, marketing costs, delivery time, as well as information such as investment policy, past investment history, risk tolerance, etc. Based on this input, the system sends the data to the server.

[1124] Inputs: Business data such as market size, marketing costs, delivery time, investment policy, investment history, risk tolerance

[1125] Output: Input data sent to the server

[1126] Step 2:

[1127] Data collection and preprocessing

[1128] The server receives the data entered by the user and standardizes it as needed. For example, StandardScaler is used to standardize data such as market size, marketing costs, and delivery times.

[1129] Input: Received user data

[1130] Output: Standardized data

[1131] Step 3:

[1132] Revenue forecasting and risk assessment

[1133] The server uses the standardized data to run revenue forecasting and risk assessment models. Specifically, it uses Linear Regression to forecast revenue and obtains the model's prediction results. For risk assessment, it uses other statistical methods and machine learning algorithms.

[1134] Input: Standardized data

[1135] Output: Predicted revenue and risk assessment results

[1136] Step 4:

[1137] Recognition of emotional states

[1138] The server analyzes the user's text input using TextBlob to recognize the user's emotional state, which is classified into three categories: positive, neutral, and negative.

[1139] Input: User text input

[1140] Output: User's emotional state (positive, neutral, negative)

[1141] Step 5:

[1142] Reflecting emotional feedback

[1143] The server generates advice for revenue prediction and risk assessment results based on the recognized emotional state, for example, advising to take risks in the case of a positive emotional state and advising to refrain from risks in the case of a negative emotional state.

[1144] Inputs: Revenue forecast, risk assessment results, user emotional state

[1145] Output: Personalized advice

[1146] Step 6:

[1147] Generate a report of the results

[1148] The server combines revenue forecasts, risk assessments, and emotional state-based advice to generate a natural language report that includes the strengths and weaknesses of the business plan, as well as the reasons and risk factors for investment recommendations.

[1149] Inputs: Revenue forecast, risk assessment results, personalized advice

[1150] Output: Natural language report

[1151] Step 7:

[1152] User interface adjustments

[1153] The device displays the report received from the server to the user. Based on the analysis results of the emotion engine, the device adjusts the interface to present information appropriately according to the user's emotional state. For example, if the user is feeling stressed, the device displays brief information, and if the user is relaxed, the device displays detailed information.

[1154] Input: Report received from the server, analysis results of the emotion engine

[1155] Output: A tailored user interface

[1156] Example prompts to input to a generative AI model:

[1157] "The market size is large and profits are expected. Should I choose the company with the lowest risk as my investment target among Company A, Company B, or Company C?"

[1158] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1159] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1160] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1161] [Fourth embodiment]

[1162] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1163] 7, a 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.

[1164] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1165] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1166] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1167] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1168] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1169] The control object 443 includes a display device, LEDs in the eyes, and motors for driving 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 emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1170] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1171] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[1172] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1173] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1174] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1175] This invention is a system that helps start-up companies develop effective business plans and allows investors to efficiently select the most suitable companies to invest in. This system consists of three elements: a server, a terminal, and a user.

[1176] System Configuration

[1177] 1. Data Collection

[1178] Server: Receives data from companies and investors. From startups, collects information such as business plans, financial data, market analysis reports, and team composition. From investors, collects information such as investment policy, past investment history, risk tolerance, desired investment return, and investment period.

[1179] 2. Data Analysis

[1180] Server: Analyzes collected data using machine learning algorithms and statistical methods. Applying revenue forecasting models and risk assessment models to startup company data to evaluate future revenue and risk. Applying portfolio optimization models to investor data to help select optimal investment targets.

[1181] 3. Business plan evaluation

[1182] Server: Evaluates the company's business plan based on the analysis results. The results of revenue forecasts, risk assessments, and SWOT analysis are compiled using business plan evaluation tools. This results in a report in natural language summarizing the company's strengths and weaknesses, which is then provided to the user (startup company representative).

[1183] 4. Investment recommendation

[1184] Server: Based on the investor's investment policy, the server selects the most suitable investment targets from the collected startup companies. It generates a detailed report including the reasons for the recommendation and risk factors and provides it to the user (investor).

[1185] 5. Providing an Interface

[1186] Terminal: Provides an interface that allows users to view evaluation results and recommendations. Users can request re-evaluation based on changes to conditions or new scenarios from the server via their terminal, and receive a new report.

[1187] Specific examples

[1188] Support for developing business plans for startups

[1189] 1. User (startup staff): Logs into the system using a terminal and enters information such as business plans, financial data, market analysis reports, and team composition.

[1190] 2. Server: Collects input data and performs data analysis, such as using linear regression models to forecast profits and Monte Carlo simulations to assess risk.

[1191] 3. Server: Based on the analysis results, the business plan evaluation instrument generates a natural language report including strengths and weaknesses.

[1192] 4. Terminal: This report is provided to the user (startup staff) so that it can be viewed on the screen.

[1193] Investor selection of investment companies

[1194] 1. User (Investor): Logs into the system using a terminal and provides information such as investment policy, past investment history, and risk tolerance.

[1195] 2. Server: Analyzes collected data on startups based on investment policies, and uses portfolio optimization models to forecast returns and assess risks.

[1196] 3. Server: Selects the best startups to invest in and generates a natural language report containing the reasons for the recommendation and risk factors.

[1197] 4. Terminal: This report is provided to the user (investor) so that it can be viewed on the screen.

[1198] This will enable startups to effectively develop business plans and investors to efficiently select the most suitable investment targets.

[1199] The processing flow will be explained below.

[1200] Step 1:

[1201] Users log in to the system using a terminal. If they log in as a startup company, they enter their company's business plan, financial data, market analysis report, team composition, etc. into the system. If they log in as an investor, they enter their investment policy, past investment history, risk tolerance, etc.

[1202] Step 2:

[1203] The server receives the information entered by the user and stores it in a database. The startup company data is classified as business plan-related data, including financial data and market analysis information. The investor data is classified as investment policy-related data, including investment history and risk tolerance.

[1204] Step 3:

[1205] The server cleans the collected data, filling in missing values ​​and standardizing the data format to make it analyzable. For example, it checks the consistency of numerical data and converts or fills in data as necessary.

[1206] Step 4:

[1207] The server applies revenue forecasting and risk assessment models to the startup company data. Specifically, it uses a linear regression model to forecast revenue based on past data and market analysis information, and performs risk assessment using Monte Carlo simulation.

[1208] Step 5:

[1209] The server applies a portfolio optimization model to the investor data, analyzing the investor's past investment patterns and taking into account current market conditions to generate a list of optimal investments.

[1210] Step 6:

[1211] The server converts the startup's business plan assessment into natural language and creates a detailed report including the company's strengths and weaknesses based on revenue forecasts, risk assessments, SWOT analysis, and other information.

[1212] Step 7:

[1213] The server then converts the list of recommended investments and the reasons for them into a natural language report for the investor, detailing each company's earnings forecast, risk assessment, and points that match the investor's investment policy.

[1214] Step 8:

[1215] The terminal provides an interface that allows users to view the evaluation results and recommendations. Users can also view detailed reports and input new conditions or scenarios to request a re-evaluation.

[1216] Step 9:

[1217] The system provides an interface through which users input new data and scenarios for revaluation, for example, new market conditions or investment strategies.

[1218] Step 10:

[1219] The server then re-analyzes the newly entered data and scenarios, applies revenue forecasting and risk assessment models, and generates updated reports.

[1220] Step 11:

[1221] The terminal provides the reevaluated results to the user, who then uses them to formulate a final business plan and decide on investment destinations.

[1222] Example 1

[1223] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1224] When startups develop effective business plans, there is no system that can efficiently collect and analyze large amounts of data and reduce the effort required for investors to select optimal investment targets.In addition, there is a lack of functionality to generate reports in natural language based on the collected data, which delays user understanding and decision-making.

[1225] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1226] In this invention, the server includes a data collection means, a data analysis means, a business plan evaluation means, an investment target recommendation means, an interface provision means, and a means for converting the data analysis results into a natural language report using a generative AI model, thereby enabling startup companies to formulate business plans and investors to efficiently select optimal investment targets.

[1227] "Data collection means" refers to means for collecting information such as business plans, financial data, market analysis information, investment policies, past investment history, and risk tolerance from organizations and investors.

[1228] "Data analysis means" refers to means for conducting analysis such as revenue forecasting and risk assessment based on collected data using machine learning algorithms and statistical methods.

[1229] The "business plan evaluation means" is a means for evaluating the business plans of startup companies based on the analysis results obtained by the data analysis means and compiling the results into a report.

[1230] The "investment recommendation means" is a means for selecting the most suitable investment based on the investor's investment policy and risk tolerance, and generating a report including the reasons for the recommendation and risk factors.

[1231] The "interface providing means" is a means for providing an interface that allows the user to view the evaluation results and the recommended contents.

[1232] "Means for converting data analysis results into natural language reports using generative AI models" refers to means for generating reports in a format that is easy for users to understand, based on collected and analyzed data, using natural language generation algorithms.

[1233] This invention is a system that helps start-up companies develop effective business plans and allows investors to efficiently select the most suitable companies to invest in. This system consists of three elements: a server, a terminal, and a user.

[1234] 1. Data Collection Methods

[1235] The server collects data from companies and investors. At the same time, it collects data such as business plans, financial data, market analysis reports, and team composition from organizations, and information such as investment policy, past investment history, risk tolerance, desired investment return, and investment period from investors. The data is stored in a relational database (e.g., MySQL or PostgreSQL). During the data collection phase, validation scripts are run to detect and complete input errors and missing values.

[1236] 2. Data analysis methods

[1237] The server analyzes the collected data using machine learning algorithms and statistical methods. Specifically, it preprocesses the data using Python's Pandas and NumPy. It then applies a linear regression model using Scikit-learn to predict future revenue. It also performs risk assessment using Monte Carlo simulation. The data analysis script is automatically executed periodically by a job scheduler (Cron or Airflow).

[1238] 3. Business plan evaluation tools

[1239] The server evaluates the business plan based on the analysis results. Specifically, it uses Python NLP libraries (e.g., generative AI models such as SpaCy and GPT-3) to compile revenue forecasts and risk assessment results into a natural language report. It also generates a template-based report that includes SWOT analysis results to clearly identify the company's strengths and weaknesses. The prompt for the generative AI model is, "Based on the revenue forecast results, please explain the strengths and weaknesses of this company."

[1240] 4. Investment Recommendation Methods

[1241] The server selects the best investment targets based on the investor's investment policy. It matches investor data with startup company analysis data and applies a portfolio optimization model. It uses libraries such as PyPortfolioOpt to select the best investment target companies. The prompt for the generative AI model is, "Select the best company for this investor's portfolio and explain why."

[1242] 5. Means of providing interface

[1243] The terminal provides an interface that allows users to view the evaluation results and recommendations. React.js and Vue.js are used as front-end technologies, while web frameworks such as Django and Flask are used for the back-end. Once users log in, they can access a dashboard screen where they can download or view the evaluation results and investment recommendation reports. A form for submitting a reevaluation request is also provided, allowing users to submit new data to the server.

[1244] The above configuration realizes a system that enables startup companies to effectively formulate business plans and investors to efficiently select optimal investment targets.

[1245] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1246] Step 1:

[1247] Data Entry

[1248] Users log in to the system using a terminal. Startup company representatives input data such as business plans, financial data, market analysis reports, and team composition. Investors input information such as investment policy, past investment history, risk tolerance, desired investment return, and investment period. The input data is saved in the system's database.

[1249] Step 2:

[1250] Data collection

[1251] The server receives data entered by users and stores it in a relational database (MySQL or PostgreSQL). During the data collection phase, validation scripts are run to verify the input data. Input errors and missing values ​​are detected and completed to ensure accurate data is collected.

[1252] Step 3:

[1253] Data analysis

[1254] The server analyzes the collected data. It preprocesses the data using Python's Pandas and NumPy. It then uses Scikit-learn to apply a linear regression model to predict future revenue. It also performs risk assessment using Monte Carlo simulation. The analysis script is automatically executed periodically using a job scheduler (Cron or Airflow). It uses the collected company data and investor data as input, and outputs revenue forecasts and risk assessment results.

[1255] Step 4:

[1256] Business plan evaluation

[1257] The server evaluates the company's business plan based on the results of the data analysis. It uses Python NLP libraries (e.g., SpaCy or generative AI models) to compile revenue forecasts and risk assessment results into natural language reports. It also adds SWOT analysis results to highlight strengths and weaknesses. Template-based reports are generated. The analysis results are used as input, and the natural language report is the output.

[1258] Step 5:

[1259] Investment recommendation

[1260] The server selects optimal investments based on the investor's investment policy and risk tolerance. It uses PyPortfolioOpt to run a portfolio optimization model and select appropriate investment companies. The generative AI model receives a prompt, "Select the best companies for this investor's portfolio and explain why," and generates a report. Investor data and company data are used as input, and a report of investment recommendations is obtained as output.

[1261] Step 6:

[1262] Interface provided

[1263] The terminal provides an interface that allows users to view evaluation results and recommendations. React.js and Vue.js are used as front-end technologies, while web frameworks such as Django and Flask are used for the back-end. Once users log in, they can view evaluation results and investment recommendation reports on the dashboard screen. A function to send re-evaluation requests is also provided. User input includes login information, and evaluation results and recommendations are provided as output.

[1264] (Application example 1)

[1265] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1266] Currently, many startups lack effective support when formulating their business plans, and investors face difficulties in efficiently selecting the most suitable investment targets. Furthermore, investors lack the means to obtain the latest investment information and risk assessments in real time, which can delay appropriate decision-making. This not only results in missed growth opportunities for startups, but also makes it difficult for investors to realize the investment returns they expect.

[1267] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1268] In this invention, the server includes a data collection means, a data analysis means, a business plan evaluation means, an investment target recommendation means, an interface provision means, a dashboard display means, a business plan evaluation report generation means, an alert notification means, and an AI assistant recommendation means, thereby enabling startup companies to effectively formulate business plans and investors to efficiently select optimal investment targets while also being able to grasp the latest investment information and risk assessments in real time.

[1269] "Data collection means" refers to means for collecting business plans, financial data, and market analysis information from companies, and investment policies, past investment history, and risk tolerance from investors.

[1270] "Data analysis means" refers to means for analyzing collected data using machine learning algorithms and statistical methods to forecast profits and assess risks.

[1271] The "business plan evaluation tool" is a tool that evaluates a company's business plan based on the analysis results and generates a report that includes strengths and weaknesses.

[1272] An "investment recommendation tool" is a tool that selects optimal investments based on an investor's investment policy and generates a detailed report including the reasons for the recommendation and risk factors.

[1273] The "interface providing means" is a means for providing an interface that allows the user to view the evaluation results and recommendations, and to request re-evaluation based on changes to conditions or a new scenario.

[1274] A "dashboard display" is a visual display that allows a user to manage their investment portfolio and see important information at a glance.

[1275] The "business plan evaluation report generating means" is a means for evaluating a company's business plan based on the collected and analyzed data and generating the results in the form of a report.

[1276] The "alert notification means" is a means for notifying the user when a new investment destination is found or when there is a change in the status of an investment destination.

[1277] "AI assistant recommendation method" is a recommendation method that uses artificial intelligence to propose optimal investment strategies to investors and predict risks and returns.

[1278] This invention is a system for enabling start-up companies to formulate effective business plans and for investors to efficiently select optimal companies to invest in. The system includes a data collection means, a data analysis means, a business plan evaluation means, an investment target recommendation means, an interface provision means, a dashboard display means, a business plan evaluation report generation means, an alert notification means, and an AI assistant recommendation means.

[1279] Hardware and Software Configuration

[1280] The system consists of three elements: a server, a terminal, and a user. The server uses machine learning libraries such as Python and scikit-learn to collect data, analyze it, and generate reports. The terminal is a smartphone, and the user enters information and views the evaluation results through an interface.

[1281] Operation explanation

[1282] Data collection methods

[1283] The server collects business plans, financial data, and market analysis information from companies, and investment policies, past investment history, and risk tolerance from investors, creating a comprehensive database.

[1284] Data Analysis Methods

[1285] The collected data is analyzed using machine learning algorithms and statistical methods, such as linear regression models for revenue forecasting and Monte Carlo simulations for risk assessment.

[1286] Business plan evaluation tools

[1287] Based on the analysis results, the company's business plan is evaluated and a report containing strengths and weaknesses is generated, which is then compiled in an easy-to-read format using natural language generation (NLG) technology.

[1288] Investment recommendation methods

[1289] Based on the investor's investment policy, the system selects the most suitable companies to invest in. A report is generated detailing the reasons for recommending the selected companies and the risk factors involved.

[1290] Interface provision means

[1291] It provides an interface for users to view evaluation results and recommendations, and users can request re-evaluation from the server via their terminal, changing conditions or using new scenarios.

[1292] Dashboard display method

[1293] It provides a dashboard that allows users to manage their investment portfolio and see key information at a glance, enabling them to make decisions instantly.

[1294] Business plan evaluation report generation tool

[1295] Based on the collected and analyzed data, the business plans of companies are evaluated and the results are generated in the form of a report, which is provided to startup companies to help them develop effective business plans.

[1296] Alert notification method

[1297] Users will receive alerts when new investments are discovered or when there is a change in the status of an investment, allowing them to stay informed of important information in real time.

[1298] AI assistant recommended methods

[1299] Using artificial intelligence, the company offers investors optimal investment strategies and predicts risks and returns.

[1300] Specific examples

[1301] Startup Company A enters its business plan and financial data into the system. The server analyzes the entered data, performs revenue forecasts and risk assessments, and compiles the results into a report. Investors can view this report on their devices and confirm that Company A has a high likelihood of generating revenue and low risk.

[1302] Prompt Sentence Examples

[1303] "Enter the business plan and financial data for startup company A below. Please provide a revenue forecast and risk assessment for this company.

[1304] Current earnings: 10,000

[1305] Future market growth rate: 20%

[1306] Expected cost: 25,000.”

[1307] These features enable startups to effectively develop business plans and investors to efficiently select the best investment targets.

[1308] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1309] Step 1:

[1310] A user logs into the system using a terminal. Depending on their role, the user can log in as a representative of the startup company or as an investor.

[1311] Step 2:

[1312] Users (startup staff) input business plans, financial data, and market analysis information through a terminal, which is then sent to a server and stored in a database.

[1313] Step 3:

[1314] The server analyzes the collected data. For example, to predict the revenue of a startup company, a linear regression model is used, taking data such as market growth rate and costs as inputs to predict future revenue. The output is the revenue forecast.

[1315] Step 4:

[1316] The server performs risk assessment using Monte Carlo simulation, using input data such as revenue forecasts and the standard deviation of market growth rates, and running multiple simulations to obtain a risk assessment value.

[1317] Step 5:

[1318] The server evaluates the business plan based on the revenue forecast results and risk assessment value, and generates a business plan evaluation report including its strengths and weaknesses. This report is created in text format using natural language generation technology and provided to the user (startup manager).

[1319] Step 6:

[1320] A user (investor) logs into the system through a terminal and provides their investment policy, past investment history, and risk tolerance. This data is sent to the server and stored in a database.

[1321] Step 7:

[1322] The server analyzes the collected data on startup companies based on the investor's investment policy, selects the most suitable investment target companies using a portfolio optimization model, and generates a report containing the reasons for the recommendation and risk factors using the company's revenue forecast and risk assessment value as input.

[1323] Step 8:

[1324] The server generates a recommendation report and provides it to the user (investor), who then views the report through their terminal and makes a decision on investment destinations.

[1325] Step 9:

[1326] The server sends alert notifications when new investments are discovered or when there is a change in the status of an investment. Alert notifications are sent in real time, providing users with the latest information.

[1327] Step 10:

[1328] The server uses its AI assistant function to propose optimal investment strategies to investors. The AI ​​model receives inputs such as the user's investment policy and past investment history, and outputs predicted risks and returns, as well as optimal investment strategies.

[1329] These processing steps create a system that allows startup companies to effectively develop business plans and investors to efficiently select the most suitable investment targets.

[1330] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1331] This invention combines a system that helps startup companies formulate effective business plans and helps investors efficiently select the most suitable companies to invest in with an emotion engine that recognizes the user's emotions. This system consists of four elements: a server, a terminal, a user, and an emotion engine.

[1332] System Configuration

[1333] 1. Data Collection

[1334] Server: Receives data from companies and investors. From startups, collects information such as business plans, financial data, market analysis reports, and team composition. From investors, collects information such as investment policy, past investment history, risk tolerance, desired investment return, and investment period.

[1335] 2. Data Analysis

[1336] Server: Analyzes collected data using machine learning algorithms and statistical methods. Applying revenue forecasting models and risk assessment models to startup company data to evaluate future revenue and risk. Applying portfolio optimization models to investor data to help select optimal investment targets.

[1337] 3. Business plan evaluation

[1338] Server: Evaluates the company's business plan based on the analysis results. The results of revenue forecasts, risk assessments, and SWOT analysis are compiled using business plan evaluation tools. This results in a report in natural language summarizing the company's strengths and weaknesses, which is then provided to the user (startup company representative).

[1339] 4. Investment recommendation

[1340] Server: Based on the investor's investment policy, the server selects the most suitable investment targets from the collected startup companies. It generates a detailed report including the reasons for the recommendation and risk factors and provides it to the user (investor).

[1341] 5. Providing an Interface

[1342] Terminal: Provides an interface that allows users to view evaluation results and recommendations. Users can request re-evaluation based on changes to conditions or new scenarios from the server via their terminal, and receive a new report.

[1343] 6. Adding an Emotion Engine

[1344] Emotion engine: Analyzes user input data and responses to recognize the user's emotional state. Includes algorithms that analyze emotions from voice and text data. The results of this analysis are reflected in ratings and recommendations, providing a more personalized service.

[1345] Server: Reflects the emotional data obtained from the emotion engine and takes the user's emotional state into account when evaluating business plans and recommending investment targets. For example, if a user is in a positive emotional state, it can present more risky options.

[1346] Device: Adjust the user interface based on feedback from the emotion engine. For example, if the user is feeling stressed, the interface may be simplified.

[1347] Specific examples

[1348] Support for developing business plans for startups

[1349] 1. User (startup staff): Logs into the system using a terminal and inputs information such as a business plan, financial data, market analysis reports, and team composition. The emotion engine analyzes the user's text input and voice instructions to recognize their emotional state.

[1350] 2. Server: Collects input data and performs data analysis. For example, it uses linear regression models to forecast profits and Monte Carlo simulations to assess risk. It also takes into account sentiment data from the sentiment engine and reflects it in the evaluation report.

[1351] 3. Server: Based on the analysis results, the business plan evaluator generates a natural language report containing strengths and weaknesses. Based on sentiment data, for example, it highlights risky options if the user is optimistic.

[1352] 4. Terminal: This report is provided to the user (startup staff) and can be viewed on the screen. An interface is provided that responds to the user's emotional state.

[1353] Investor selection of investment companies

[1354] 1. User (investor): Logs in to the system using a terminal and provides information such as investment policy, past investment history, risk tolerance, etc. The emotion engine analyzes the user's input data and reactions to recognize their emotional state.

[1355] 2. Server: Analyzes the collected data of startups based on the investment policy. Uses a portfolio optimization model to forecast returns and assess risks. Considers sentiment data from the sentiment engine and reflects it in recommendation reports.

[1356] 3. Server: Selects the best startups to invest in and generates a natural language report with recommendations and risk factors. Based on sentiment data, for example, if the user is feeling anxious, it will highlight options with reduced risk.

[1357] 4. Terminal: This report is provided to the user (investor) for viewing on the screen, and the interface is adjusted based on feedback from the sentiment engine.

[1358] This will enable startups to develop more precise business plans and investors to make optimal investment decisions that take into account their own emotional state.

[1359] The processing flow will be explained below.

[1360] Step 1:

[1361] Users log in to the system using a terminal. If they log in as a startup company, they enter their company's business plan, financial data, market analysis report, team composition, etc. into the system. If they log in as an investor, they enter their investment policy, past investment history, risk tolerance, etc.

[1362] Step 2:

[1363] The server receives the information entered by the user and stores it in a database. The startup company data is classified as business plan-related data, including financial data and market analysis information. The investor data is classified as investment policy-related data, including investment history and risk tolerance.

[1364] Step 3:

[1365] The server cleans the collected data, filling in missing values ​​and standardizing the data format to make it analyzable. For example, it checks the consistency of numerical data and converts or fills in data as necessary.

[1366] Step 4:

[1367] The emotion engine analyzes the user's input data and reactions. For example, it uses algorithms to analyze emotions from the language used when the user enters text and from voice data. The emotion engine recognizes the user's current emotional state (positive, negative, neutral) in real time.

[1368] Step 5:

[1369] The server applies revenue forecasting and risk assessment models to the startup company data. Specifically, it uses a linear regression model to predict revenue based on past data and market analysis information, and Monte Carlo simulation to assess risk. It also takes into account emotional data from the emotion engine, and adjusts the risk estimate slightly higher if the user is positive, for example.

[1370] Step 6:

[1371] The server applies a portfolio optimization model to the investor's data, analyzing their past investment patterns and taking into account current market conditions to generate a list of optimal investments. It also incorporates sentiment data from the sentiment engine, making recommendations to reduce risk, for example, if the user is feeling anxious.

[1372] Step 7:

[1373] The server converts the startup's business plan evaluation into natural language. It creates a detailed report including the company's strengths and weaknesses based on revenue forecasts, risk assessments, SWOT analysis, etc. It also makes personalized suggestions based on sentiment data, such as proposing aggressive strategies if the user is optimistic.

[1374] Step 8:

[1375] The server converts a list of recommended investments and the reasons for them into a natural language report for the investor. It details each company's revenue forecast and risk assessment, as well as points that match the investor's investment policy. Based on emotional data, for example, if the user is feeling stressed, it will recommend low-risk investments to give them a sense of security.

[1376] Step 9:

[1377] The device provides an interface where users can view the evaluation results and recommendations. Users can also input new conditions or scenarios to request a re-evaluation. Based on feedback from the emotion engine, the interface is adjusted to optimize the user experience.

[1378] Step 10:

[1379] The server then re-analyzes the newly entered data and scenarios, applies revenue forecasting and risk assessment models, and generates updated reports, incorporating sentiment data from the emotion engine and providing recommendations based on the latest user state.

[1380] Step 11:

[1381] The device then provides the reevaluated results to the user, who can then use them to formulate a final business plan and decide where to invest. Information is displayed in a way that is tailored to the user based on the emotional data.

[1382] Example 2

[1383] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1384] In the past, startups developed business plans and investors selected investment targets in a way that the analysis and evaluation of collected data was not efficient and accurate enough, and in particular, the emotional state of the user was not taken into consideration, which can lead to a decrease in the reliability and satisfaction of the results. Furthermore, in the past, the user experience was often inconsistent because the interface was not adjusted according to the emotional state of the user.

[1385] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a data collection means, a data analysis means, a business plan evaluation means, an investment destination recommendation means, an interface provision means, an emotion analysis means, and an emotion-based interface adjustment means. This allows startup companies to formulate business plans more precisely and enables investors to select optimal investments taking into account their emotional state.

[1386] "Data collection methods" are the means used to collect necessary information from companies and investors.

[1387] "Data analysis means" refers to means for analyzing collected data using machine learning algorithms and statistical methods.

[1388] A "business plan evaluation tool" is a tool for evaluating a company's business plan based on the results of data analysis.

[1389] "Investment recommendation tools" are tools for selecting and recommending optimal investments based on an investor's investment policy and risk tolerance.

[1390] "Interface providing means" refers to a means for providing an interface that allows users to view and operate evaluation results and recommendations.

[1391] The "emotion analysis means" is a means for analyzing the user's input data and reactions and recognizing the user's emotional state.

[1392] The "emotion-based interface adjustment means" is a means for adjusting the user interface based on the emotion data obtained from the emotion analysis means.

[1393] This invention combines a system that helps startup companies formulate effective business plans and helps investors efficiently select the most suitable companies to invest in with an emotion engine that recognizes the user's emotions. This system consists of four elements: a server, a terminal, a user, and an emotion engine.

[1394] First, the overall flow of the system will be described.

[1395] Data collection

[1396] The server collects data from companies and investors. Specifically, from startup companies, it collects information such as business plans, financial data, market analysis reports, and team composition. From investors, it collects information such as investment policy, past investment history, risk tolerance, desired investment return, and investment period. In this way, all necessary data is consolidated on the server.

[1397] Data analysis

[1398] The server analyzes the collected data using machine learning algorithms and statistical methods. It applies revenue prediction and risk assessment models to the startup company data to evaluate future revenue and risk. For example, it uses Python libraries such as Scikit-learn and TensorFlow to predict revenue using linear regression models and conduct risk assessments using Monte Carlo simulations. It applies portfolio optimization models to investor data to help select optimal investment targets.

[1399] Business plan evaluation

[1400] The server evaluates the company's business plan based on the analysis results. Specifically, the business plan evaluation tool generates a report based on revenue forecast results, risk assessment results, SWOT analysis results, etc. The report is created using natural language processing technology, allowing the user (startup company representative) to understand the company's strengths and weaknesses.

[1401] Investment recommendation

[1402] The server selects the most suitable startups based on the investor's investment policy and risk tolerance. It generates a detailed report including the reasons for the recommendation and risk factors and provides it to the user (investor), allowing the investor to make a more appropriate decision.

[1403] Providing an interface

[1404] The terminal provides an interface that allows users to view the evaluation results and recommendations. Users can also request re-evaluation based on changes to conditions or new scenarios from the server via the terminal, and receive a new report.

[1405] Adding an Emotion Engine

[1406] The emotion engine analyzes the user's input data and reactions to recognize the user's emotional state. This analysis uses algorithms that analyze emotions from text and voice data. For example, it can use Google Cloud Natural Language API or IBM Watson's emotion analysis tool.

[1407] The server reflects the emotional data obtained from the emotion engine and takes the user's emotional state into account when evaluating business plans and recommending investments. For example, if the user is in a positive emotional state, it can present more risk-taking options.

[1408] Emotion-based interface adjustment

[1409] The device adjusts the user interface based on feedback from the emotion engine. For example, if the user is feeling stressed, the device may simplify the interface.

[1410] Specific examples

[1411] Support for developing business plans for startups

[1412] 1. A user (startup representative) logs into the system using a terminal and inputs information such as a business plan, financial data, market analysis report, and team composition. The emotion engine analyzes the user's text input and voice instructions to recognize their emotional state.

[1413] 2. The server collects the input data and performs data analysis. For example, it uses a linear regression model to predict profits and a Monte Carlo simulation to assess risk. It also takes into account the sentiment data from the sentiment engine and reflects it in the evaluation report.

[1414] 3. Based on the analysis results, the server generates a natural language report containing the business plan evaluation tools' strengths and weaknesses. Based on the sentiment data, it highlights risk-taking options if the user is optimistic.

[1415] 4. The terminal provides this report to the user (startup staff) and allows them to view it on the screen, providing an interface that responds to the user's emotional state.

[1416] Investor selection of investment companies

[1417] 1. A user (investor) logs into the system using a terminal and provides information such as investment policy, past investment history, and risk tolerance. The emotion engine analyzes the user's input data and reactions to recognize their emotional state.

[1418] 2. Based on the investment policy, the server analyzes the collected data on startup companies using a portfolio optimization model to select the optimal investment targets. The server takes into account the sentiment data from the sentiment engine and reflects this in the recommendation report.

[1419] 3. The server selects the best startups to invest in and generates a natural language report with recommendations and risk factors. Based on sentiment data, it highlights lower-risk options if the user feels unsure.

[1420] 4. The terminal provides this report to the user (investor) for viewing on the screen, adjusting the interface based on feedback from the sentiment engine.

[1421] Prompt Sentence Examples

[1422] "Users input their business plan and financial data into the device, and the emotion engine analyzes their emotional state. The generated business plan report is adjusted based on the emotion analysis results."

[1423] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1424] Step 1: User logs into the system

[1425] A user accesses the system using a terminal and enters login information. The entered user ID and password are sent from the terminal to the server.

[1426] The server authenticates the received login information by checking it against a database. If authentication is successful, it identifies the user's type (startup or investor) and generates the appropriate dashboard, which becomes the gateway for the user to perform further operations.

[1427] Step 2: Data entry

[1428] After logging in, users enter information such as business plans, financial data, market analysis reports, and team composition into the terminal. This information is provided by the startup company's representatives. Investors also enter their investment policy, past investment history, risk tolerance, and other information.

[1429] The terminal temporarily stores the entered data and converts it into an appropriate format for transmission to the server.

[1430] Step 3: Data collection

[1431] The server receives the data sent from the terminal and stores it in a database. The server checks the consistency and completeness of the received data and detects missing information and input errors.

[1432] If the server detects missing data or errors, it notifies the user and prompts them to make corrections or enter additional information.

[1433] Step 4: Data analysis

[1434] The server analyzes the data stored in the database using machine learning algorithms and statistical methods, specifically using Python libraries such as Scikit-learn and TensorFlow.

[1435] The server uses a revenue forecasting model to predict the revenue of startup companies and performs risk assessment using Monte Carlo simulation. After the analysis, the server saves the results.

[1436] Step 5: Evaluate your business plan

[1437] The server evaluates the business plan based on the results of the data analysis. The business plan evaluation means generates a report based on the results of the revenue forecast, risk assessment, SWOT analysis, etc.

[1438] The server uses natural language processing technology to document the evaluation in a user-friendly format and stores the results on the server. This evaluation helps users make important decisions.

[1439] Step 6: Recommend investments

[1440] The server analyzes the collected startup company data using a portfolio optimization model based on the investor's investment policy and risk tolerance.

[1441] The server uses the analysis results to select the most suitable startups to invest in and generates a detailed report including the reasons for the recommendation and risk factors. The report is generated using natural language processing technology.

[1442] Step 7: Providing the resulting interface

[1443] The device displays the evaluation results and recommendations received from the server to the user, who can then review the information through a dashboard or report.

[1444] The user can request the server to reassess the results based on changes to the conditions or new scenarios via the terminal. The terminal sends these requests to the server, which then performs the reanalysis.

[1445] Step 8: Emotion Engine Analysis

[1446] The emotion engine analyzes user input data and reactions in real time to recognize emotional states, using Google Cloud Natural Language API and IBM Watson emotion analysis tools.

[1447] The emotion engine identifies positive and negative emotions from text and voice data and sends the results to the server.

[1448] Step 9: Emotion-Based Interface Adjustment

[1449] The server reflects the emotional data obtained from the emotion engine and takes the user's emotional state into account when evaluating business plans and recommending investment targets. For example, if the user is in a positive emotional state, it presents risk-taking options.

[1450] The device adjusts the user interface based on feedback from the emotion engine. For example, if the user is feeling stressed, the device may simplify the interface.

[1451] In this way, the system takes into account the user's emotional state to support startups in formulating business plans and investors in selecting investment targets, thereby improving user satisfaction and the accuracy of decision-making.

[1452] (Application example 2)

[1453] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1454] Conventional systems for developing business plans for startups and selecting investment targets for investors were unable to provide personalized advice that took into account the user's emotional state. This meant that users' emotional biases could affect their decision-making, making it difficult to select optimal business plans and investment targets. Furthermore, particularly in fields with volatile markets such as the food delivery business, rapid and appropriate responses in real time are required, but conventional systems were unable to adequately address this.

[1455] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1456] In this invention, the server includes a data collection means, a data analysis means, a business plan evaluation means, an investment recommendation means, an emotional state recognition means, an emotional feedback reflection means, and an interface provision means, thereby enabling highly accurate business plan formulation and investment selection while taking into account the emotional state of the user.

[1457] "Data collection means" is a function for collecting necessary information such as business plans, financial data, and investment policies from companies and investors.

[1458] "Data analysis means" is a function that analyzes collected data and performs profit forecasts and risk assessments.

[1459] The "business plan evaluation tool" is a function that evaluates a company's business plan based on the analysis results and compiles a report on its strengths and weaknesses.

[1460] "Investment recommendation tool" is a function that selects the most suitable investment based on the investor's investment policy and generates a report including the reasons for the recommendation and risk factors.

[1461] The "emotional state recognition means" is a function that analyzes the input data and reactions of the user and recognizes the user's emotional state.

[1462] The "emotion feedback reflection means" is a function that reflects the recognized user emotion data in the evaluation of business plans and the selection of investment targets.

[1463] The "interface providing means" is a function that provides an interface that allows the user to view the evaluation results and recommendations, and makes adjustments according to the user's emotional state.

[1464] This invention relates to a system that uses a smartphone application specialized for food delivery businesses to help startup companies formulate effective business plans and investors select optimal investment targets. The system of the present invention consists of three main components: a server, a user terminal, and an emotion engine.

[1465] System Configuration

[1466] 1. Server

[1467] Data collection methods:

[1468] The server collects data from startups, such as market size, marketing costs, and delivery time, as well as data from investors, such as investment policy, past investment history, and risk tolerance.

[1469] Data analysis methods:

[1470] The server analyzes the collected data using Scikit-Learn's LinearRegression and StandardScaler, which allows for profit forecasting and risk assessment.

[1471] Business plan evaluation tools:

[1472] The server evaluates the business plan based on the analysis results and generates a natural language report that includes the startup's strengths and weaknesses.

[1473] Recommended investment vehicles:

[1474] The server selects the most suitable investments based on the investor's investment policy and generates a detailed report including the reasons for the recommendation and risk factors.

[1475] Emotional state recognition means:

[1476] The server performs emotion analysis using TextBlob and recognizes the user's emotional state from input data and voice instructions.

[1477] Emotional feedback methods:

[1478] The server then reflects the recognized emotional data in its evaluations and recommendations, for example, emphasizing risk-taking options when the user has positive emotions and emphasizing risk-avoiding options when the user has negative emotions.

[1479] User terminal

[1480] The user terminal is provided with the following features:

[1481] Interface provided by:

[1482] Based on the analysis results of the emotion engine, a user-friendly interface is provided. The interface is adjusted according to the user's emotional state. For example, if the user is feeling stressed, the information displayed will be concise.

[1483] Specific examples

[1484] Support for developing business plans for startups

[1485] 1. User:

[1486] Startup company representatives log into the system using their smartphones and enter data such as market size, marketing costs, and delivery times. An emotion engine analyzes emotions from the user's text input.

[1487] 2. Server:

[1488] Analyze the input data, use LinearRegression to predict revenue, and perform sentiment analysis using TextBlob. Based on the prediction results and sentiment data, generate a business plan evaluation report. For example, if the market size is large and profits are expected, and positive sentiment is recognized, emphasize advice to take risks.

[1489] 3. User Device:

[1490] Users can view this report on their device and request a reassessment based on new scenarios through an intuitive interface.

[1491] Investor selection of investment companies

[1492] 1. User:

[1493] Investors log in to the system using their smartphones and enter data such as their investment policy, past investment history, risk tolerance, etc. The sentiment engine analyzes emotions from the user's input text.

[1494] 2. Server:

[1495] It analyzes the collected data based on the investment policy and selects the most suitable startups to invest in. It also takes into account sentiment data and generates a detailed report including the risks and reasons for recommendations. For example, if the user is feeling anxious, it will highlight options with reduced risk.

[1496] 3. User Device:

[1497] Users can view this report on their devices and make optimal investment decisions through an interface that responds to their emotional state.

[1498] Example prompts to input to a generative AI model:

[1499] "The market size is large and profits are expected. Should I choose the company with the lowest risk as my investment target among Company A, Company B, or Company C?"

[1500] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1501] Step 1:

[1502] User Data Entry

[1503] Users (startup company representatives or investors) log into the system using their smartphones and enter data such as market size, marketing costs, delivery time, as well as information such as investment policy, past investment history, risk tolerance, etc. Based on this input, the system sends the data to the server.

[1504] Inputs: Business data such as market size, marketing costs, delivery time, investment policy, investment history, risk tolerance

[1505] Output: Input data sent to the server

[1506] Step 2:

[1507] Data collection and preprocessing

[1508] The server receives the data entered by the user and standardizes it as needed. For example, StandardScaler is used to standardize data such as market size, marketing costs, and delivery times.

[1509] Input: Received user data

[1510] Output: Standardized data

[1511] Step 3:

[1512] Revenue forecasting and risk assessment

[1513] The server uses the standardized data to run revenue forecasting and risk assessment models. Specifically, it uses Linear Regression to forecast revenue and obtains the model's prediction results. For risk assessment, it uses other statistical methods and machine learning algorithms.

[1514] Input: Standardized data

[1515] Output: Predicted revenue and risk assessment results

[1516] Step 4:

[1517] Recognition of emotional states

[1518] The server analyzes the user's text input using TextBlob to recognize the user's emotional state, which is classified into three categories: positive, neutral, and negative.

[1519] Input: User text input

[1520] Output: User's emotional state (positive, neutral, negative)

[1521] Step 5:

[1522] Reflecting emotional feedback

[1523] The server generates advice for revenue prediction and risk assessment results based on the recognized emotional state, for example, advising to take risks in the case of a positive emotional state and advising to refrain from risks in the case of a negative emotional state.

[1524] Inputs: Revenue forecast, risk assessment results, user emotional state

[1525] Output: Personalized advice

[1526] Step 6:

[1527] Generate a report of the results

[1528] The server combines revenue forecasts, risk assessments, and emotional state-based advice to generate a natural language report that includes the strengths and weaknesses of the business plan, as well as the reasons and risk factors for investment recommendations.

[1529] Inputs: Revenue forecast, risk assessment results, personalized advice

[1530] Output: Natural language report

[1531] Step 7:

[1532] User interface adjustments

[1533] The device displays the report received from the server to the user. Based on the analysis results of the emotion engine, the device adjusts the interface to present information appropriately according to the user's emotional state. For example, if the user is feeling stressed, the device displays brief information, and if the user is relaxed, the device displays detailed information.

[1534] Input: Report received from the server, analysis results of the emotion engine

[1535] Output: A tailored user interface

[1536] Example prompts to input to a generative AI model:

[1537] "The market size is large and profits are expected. Should I choose the company with the lowest risk as my investment target among Company A, Company B, or Company C?"

[1538] 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 control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1539] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1540] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1541] The emotion identification model 59 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 an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1542] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1543] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1544] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1545] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1546] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs 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 a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1547] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1548] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1549] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1550] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1551] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1552] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1553] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1554] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1555] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1556] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1557] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1558] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1559] The following is further disclosed regarding the above embodiment.

[1560] (Claim 1)

[1561] data collection means;

[1562] data analysis means;

[1563] Business plan evaluation tools;

[1564] Investment recommendation measures,

[1565] an interface providing means;

[1566] A system including:

[1567] (Claim 2)

[1568] 10. The system of claim 1, wherein the data collection means collects business plans, financial data, and market analysis information from businesses.

[1569] (Claim 3)

[1570] 2. The system of claim 1, wherein the data collection means collects investment policies, past investment history, and risk tolerance from investors.

[1571] (Claim 4)

[1572] 2. The system of claim 1, wherein the data analysis means applies a revenue forecasting model and a risk assessment model to analyze the company data.

[1573] (Claim 5)

[1574] 2. The system according to claim 1, wherein the investment target recommendation means recommends optimal investment target companies based on the investor's policy.

[1575] (Claim 6)

[1576] 2. The system according to claim 1, wherein the interface providing means provides an interface that enables a user to view the evaluation results and the recommended contents.

[1577] "Example 1"

[1578] (Claim 1)

[1579] data collection means;

[1580] data analysis means;

[1581] Business plan evaluation tools;

[1582] Investment recommendation measures,

[1583] an interface providing means;

[1584] A means to translate data analysis results into natural language reports using generative AI models; and

[1585] A system including:

[1586] (Claim 2)

[1587] 10. The system of claim 1, wherein the data collection means collects business plans, financial data, and market analysis information from organizations.

[1588] (Claim 3)

[1589] 2. The system of claim 1, wherein the data collection means collects investment policies, past investment history, and risk tolerance from investors.

[1590] "Application Example 1"

[1591] (Claim 1)

[1592] data collection means;

[1593] data analysis means;

[1594] Business plan evaluation assessment instruments;

[1595] Investment recommendation measures,

[1596] an interface providing means;

[1597] a dashboard display means;

[1598] A business plan evaluation report generation means;

[1599] an alert notification means;

[1600] AI assistant recommended measures and

[1601] A system including:

[1602] (Claim 2)

[1603] 10. The system of claim 1, wherein the data collection means collects business plans, financial data, and market analysis information from businesses.

[1604] (Claim 3)

[1605] 2. The system of claim 1, wherein the data collection means collects investment policies, past investment history, and risk tolerance from investors.

[1606] "Example 2: Combining Emotion Engines"

[1607] (Claim 1)

[1608] data collection means;

[1609] data analysis means;

[1610] Business plan evaluation tools;

[1611] Investment recommendation measures,

[1612] an interface providing means;

[1613] A sentiment analysis means;

[1614] an emotion-based interface adjustment means;

[1615] A system including:

[1616] (Claim 2)

[1617] 10. The system of claim 1, wherein the data collection means collects business plans, financial information, and market analysis information from organizations.

[1618] (Claim 3)

[1619] 2. The system of claim 1, wherein the data collection means collects investment policies, past investment history, and risk tolerance from investors.

[1620] "Application example 2 when combining emotion engines"

[1621] (Claim 1)

[1622] data collection means;

[1623] data analysis means;

[1624] Business plan evaluation tools;

[1625] Investment recommendation measures,

[1626] emotional state recognition means;

[1627] Emotional feedback reflecting means;

[1628] an interface providing means;

[1629] A system including:

[1630] (Claim 2)

[1631] 10. The system of claim 1, wherein the data collection means collects business plans, financial data, and market analysis information from businesses.

[1632] (Claim 3)

[1633] 2. The system of claim 1, wherein the data collection means collects investment policies, past investment history, and risk tolerance from investors. [Explanation of symbols]

[1634] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. data collection means; data analysis means; Business plan evaluation tools; Investment recommendation measures, an interface providing means; A system including:

2. 10. The system of claim 1, wherein the data collection means collects business plans, financial data, and market analysis information from businesses.

3. 2. The system of claim 1, wherein the data collection means collects investment policies, past investment history, and risk tolerance from investors.

4. 2. The system of claim 1, wherein the data analysis means applies a revenue forecasting model and a risk assessment model to analyze the company data.

5. 2. The system according to claim 1, wherein the investment target recommendation means recommends optimal investment target companies based on the investor's policy.

6. 2. The system according to claim 1, wherein the interface providing means provides an interface that enables a user to view the evaluation results and the recommended contents.

Images