System

Abstract

A system is provided.SOLUTION: The system of claim 1, further comprising: means for automatically generating a strategic report based on the generated growth strategy and risk management AI; means for providing the report to the user device; and means for receiving feedback and additional analysis requests from the user and performing re-analysis based on the feedback and the additional analysis requests received from the user device, wherein the generated growth strategy and risk management AI are based on the financial metrics.SELECTED DRAWING: Figure 1

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] Companies face challenges in analyzing financial data appropriately and efficiently and providing information to investors quickly. It is particularly difficult for mid-sized companies and those in charge to create effective IR information with limited time and resources, and in many cases they lack the necessary expertise. For this reason, there is a demand for a system that can automatically and efficiently generate reports that include corporate growth strategies and risk management. [Means for solving the problem]

[0005] This invention provides a means for aggregating and formatting a company's financial data, analyzing the financial data using a generative AI model, and calculating financial indicators. It also provides a system that includes a means for generating a growth strategy and risk management measures based on the analysis results using the generative AI model, a means for automatically generating a strategic report based on the generated growth strategy and risk management measures, a means for providing the report to a user terminal, and a means for receiving feedback and additional analysis requests from users and performing reanalysis. This enables companies to quickly and effectively create IR information and improve communication with investors.

[0006] "Financial data" refers to data that includes information such as a company's revenues, liabilities, assets, and cash flow.

[0007] A "generative AI model" is a model that uses artificial intelligence to analyze financial data, calculate financial indicators, and generate growth strategies and risk management measures.

[0008] "Financial indicators" are indicators calculated from financial data, and specific examples include PBR (Price to Book Ratio), ROE (Return on Equity), and ROA (Return on Assets).

[0009] "Growth strategies" are strategies such as market entry and cost reduction measures proposed by a generated AI model based on a company's financial data.

[0010] "Risk management measures" are measures a company can take to mitigate financial risk, including liquidity risk mitigation measures and debt management suggested by the generative AI model.

[0011] A "strategic report" is a report created for use by a company's investor relations personnel and management team based on insights into growth strategies and risk management measures generated by a generative AI model.

[0012] A "user terminal" is an electronic device that can be accessed by a company's investor relations personnel or management, and that can view reports and send feedback.

[0013] "Feedback" is any opinion or request for further analysis provided by a user to a server.

[0014] "Additional analysis" is the process in which the generative AI model performs analysis again based on new data and conditions, based on a user request. [Brief explanation of the drawings]

[0015] [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

[0016] 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.

[0017] First, the terms used in the following description will be explained.

[0018] 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).

[0019] 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.

[0020] 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.

[0021] 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.

[0022] 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."

[0023] [First embodiment]

[0024] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0025] 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.

[0026] 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).

[0027] 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.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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."

[0036] This invention relates to a system that enables companies to efficiently analyze financial data and automatically generate reports that include strategies and risk management. An embodiment of this system and specific program processing will be described in detail below.

[0037] Data Collection Phase

[0038] server

[0039] The server accesses the company's financial database to obtain the necessary revenue, liability, asset, and cash flow information, connecting to authorized databases via access authentication.

[0040] The acquired data is formatted into a standard format, such as CSV or data frame, making it suitable for analysis.

[0041] Data analysis phase

[0042] server

[0043] The formatted data is sent from the server to the generative AI model, which analyzes it and calculates each financial indicator.

[0044] Generative AI Models

[0045] Based on the data received, the generative AI model calculates key financial indicators such as PBR (Price to Book Ratio), ROE (Return on Equity), and ROA (Return on Assets).

[0046] Furthermore, based on the analysis results, the generative AI model generates corporate growth strategies (e.g., entry into new markets and cost reduction measures) and risk management measures (e.g., measures to reduce liquidity risk and debt management).

[0047] Report generation phase

[0048] server

[0049] The server automatically generates strategic reports based on insights provided by the generative AI model, including explanations and interpretations of financial metrics, suggested growth strategies, and risk management measures.

[0050] Convert the generated reports into a format that can be accessed by the company's investor relations personnel and management (e.g., PDF format or a dedicated web dashboard).

[0051] Information provision phase

[0052] server

[0053] The reports are then sent to the devices of the company's IR staff and management, often via email or cloud services.

[0054] Terminal

[0055] The device has a dedicated dashboard where users can view reports and gain insights.

[0056] Feedback and further analysis phase

[0057] User

[0058] Users (IR staff and management) review the report and, if necessary, can send feedback to the server and request additional analysis.

[0059] server

[0060] The server receives feedback and requests for additional analysis from users, sends the data to the generative AI model again, and performs additional analysis.

[0061] Generative AI Models

[0062] The generative AI model performs reanalysis based on new conditions and data and sends updated insights back to the server.

[0063] server

[0064] The server regenerates the report based on the updated insights and sends it to the user terminal.

[0065] Specific examples

[0066] Case Study: Medium-sized Manufacturing Company X

[0067] background

[0068] As Company X's revenues increase, it needs to provide accurate and timely information to investors, but analyzing financial data and compiling strategic proposals takes a lot of time and effort.

[0069] introduction

[0070] Company X introduces this system and uploads its financial data to the server.

[0071] Processing flow

[0072] The server accesses Company X's database and aggregates and formats the necessary financial data.

[0073] The server sends the data to a generative AI model, which calculates financial indicators and generates growth strategies and risk management measures.

[0074] Based on the generated insights, the server creates a strategic report and sends it to the terminal of Company X's IR officer.

[0075] The user (IR officer) checks the report on the dashboard and submits additional analysis requests to the server.

[0076] The server receives the request, performs the reanalysis, and provides an updated report to the user's terminal.

[0077] result

[0078] Company X was able to quickly obtain insights and provide effective IR information to investors, which improved communication with investors and increased its reputation in the capital market.

[0079] The above is a detailed description of the system's implementation and processing. This invention can help companies use AI to efficiently analyze financial data and quickly provide high-quality IR information.

[0080] The processing flow will be explained below.

[0081] Step 1:

[0082] The server accesses the company's financial database to retrieve the necessary financial data such as revenue, liabilities, assets, cash flow, etc. This data retrieval process involves proper access authentication to ensure data security.

[0083] Step 2:

[0084] The server formats the acquired financial data into a standard format (e.g., CSV file or data frame format). Data cleaning is also performed at this stage to remove incomplete or duplicate data.

[0085] Step 3:

[0086] The server inputs the formatted data into the generative AI model, which receives the data and begins analyzing it.

[0087] Step 4:

[0088] The generative AI model analyzes the input data and calculates key financial indicators, such as PBR (Price to Book Ratio), ROE (Return on Equity), and ROA (Return on Assets).

[0089] Step 5:

[0090] Based on the analysis results, the generative AI model generates corporate growth strategies (e.g., entry into new markets and cost reduction measures) and risk management measures (e.g., measures to reduce liquidity risk and debt management).

[0091] Step 6:

[0092] The server automatically generates strategic reports based on insights provided by the generative AI model, including explanations and interpretations of financial metrics, suggested growth strategies, and risk management measures.

[0093] Step 7:

[0094] The server formats the generated reports into a format (e.g., PDF or dedicated web dashboard) that can be accessed by the company's investor relations personnel and management.

[0095] Step 8:

[0096] The server then sends the generated reports to the terminals of the company's IR staff and management via email or cloud services.

[0097] Step 9:

[0098] The device has a dedicated dashboard where users can view reports and gain insights.

[0099] Step 10:

[0100] Users (IR personnel or management) review the report and, if necessary, send feedback to the server and request additional analysis.

[0101] Step 11:

[0102] The server receives feedback and requests for additional analysis from users, and sends the data back to the generative AI model for additional analysis.

[0103] Step 12:

[0104] The generative AI model performs reanalysis based on new conditions and data and provides updated insights to the server.

[0105] Step 13:

[0106] The server updates the report based on the new insights and sends it back to the user's device.

[0107] These are the specific processing steps of this system. At each step, the server, generative AI model, terminal, and user play their respective roles to achieve efficient and accurate analysis and reporting of financial data.

[0108] Example 1

[0109] 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."

[0110] In today's business environment, it is important for companies to efficiently analyze financial data and quickly provide high-quality reports, including those for strategy and risk management. However, traditional methods require a significant amount of time and effort to aggregate data, analyze it, and create reports, straining corporate resources. In particular, it is difficult to quickly and accurately handle large amounts of financial data and obtain appropriate insights to support strategic decision-making.

[0111] 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.

[0112] In this invention, the server includes means for aggregating and formatting a company's financial data, means for analyzing the financial data using a generative AI model to calculate financial indicators, means for generating a growth strategy and risk management measures based on the analysis results using the generative AI model, means for providing the generated report to a user terminal via email or a cloud service, means for displaying the report via a dedicated dashboard, and means for receiving feedback and requests for additional analysis from users and performing reanalysis, thereby enabling companies to efficiently analyze financial data and quickly provide high-quality reports that support strategic decision-making.

[0113] "Corporate financial data" refers to financial information that a company generates and holds in the course of its economic activities, and includes revenue data, liability data, asset data, cash flow information, and the like.

[0114] "Aggregation and formatting means" refers to methods or tools used to convert data from different formats or sources into a unified format suitable for analysis.

[0115] A "generative AI model" refers to a system that uses artificial intelligence technology to automatically perform complex calculations and analyses based on input data.

[0116] "Financial indicators" refer to numerical values ​​calculated using formulas to evaluate a company's financial condition and performance, and include, for example, PBR (price-to-book ratio), ROE (return on equity), and ROA (return on assets).

[0117] A "growth strategy" refers to the plans and policies that a company implements in order to achieve sustainable development, and includes measures such as entering new markets and cost-cutting measures.

[0118] "Risk management measures" refer to the plans and measures adopted to identify, assess and mitigate potential risks faced by an entity, including liquidity risk mitigation measures and debt management.

[0119] A "strategic report" refers to a document in which a company summarizes its future strategies and risk management based on the analysis of financial data.

[0120] "Means of providing via email or cloud service" refers to a method of using an email system or cloud service to quickly and securely distribute the generated report to the user.

[0121] A "dedicated dashboard" refers to a specialized interface, typically provided as a web application, that allows users to view reports and gain insights.

[0122] "Means for receiving feedback or requests for additional analysis and performing re-analysis" refers to methods or tools for receiving user opinions or requests and conducting additional data analysis based on those opinions or requests to generate new insights.

[0123] The present invention relates to a system that enables a company to efficiently analyze financial data and automatically generate reports that include strategies and risk management. Specific embodiments of this system will be described in detail below.

[0124] Data Collection Phase

[0125] server

[0126] The server accesses the company's financial database to retrieve the necessary revenue, liability, asset, and cash flow information. It connects to the database through secure access authentication using a database management system such as MySQL or PostgreSQL. The retrieved data is then formatted into CSV or dataframe format using the Python pandas library.

[0127] Data analysis phase

[0128] server

[0129] The formatted data is sent from the server to the generative AI model using an HTTP POST request to send the data to the AI ​​model's endpoint.

[0130] Generative AI Models

[0131] Based on the data it receives, the generative AI model calculates financial indicators such as PBR (Price to Book Ratio), ROE (Return on Equity), and ROA (Return on Assets). Specifically, it uses a formula such as "PBR = market_price / book_value." It also performs scenario-based analysis to generate growth strategies (e.g., new market entry, cost reduction measures) and risk management measures (e.g., liquidity risk mitigation measures, debt management).

[0132] Report generation phase

[0133] server

[0134] The server automatically generates strategic reports in PDF format using LaTeX templates based on insights from the generative AI model. The reports include explanations and interpretations of financial metrics, proposed growth strategies, and risk management measures. The generated reports are converted to PDF format using the Python reportlab library.

[0135] Information provision phase

[0136] server

[0137] The created report is sent to the company's IR personnel or management via email or cloud services (e.g., AWS S3 or Google Drive).

[0138] Terminal

[0139] The device has a dedicated dashboard where users can view reports and gain insights, and a dedicated web application allows users to access the dashboard from a browser and view the report contents.

[0140] Feedback and further analysis phase

[0141] User

[0142] Users (IR staff and management) review the report and submit feedback or requests for additional analysis to the server as needed. These requests are sent using a feedback form on the dashboard.

[0143] server

[0144] The server receives feedback and requests for additional analysis from users, and then sends the data to the generative AI model again to perform reanalysis.

[0145] Generative AI Models

[0146] The generative AI model performs reanalysis based on new conditions and data and returns updated insights to the server.

[0147] server

[0148] The server regenerates strategic reports based on the updated insights and sends them back to the user's device, allowing businesses to continuously obtain the latest information and strategic proposals.

[0149] Examples of prompt statements

[0150] "Please calculate financial indicators such as PBR, ROE, and ROA based on the company's financial data for the first quarter of fiscal year 2022. Also, please propose growth strategies such as entering new markets and cost reduction measures, as well as risk management measures such as measures to reduce liquidity risk and debt management."

[0151] This invention enables companies to use AI to efficiently analyze financial data and quickly provide high-quality IR information.

[0152] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0153] Step 1:

[0154] Database Connection

[0155] The server connects to the company's financial database, taking the database URL, username, and password as input, and getting a database connection object as output, specifically using a database management system such as MySQL or PostgreSQL, for secure access authentication.

[0156] Step 2:

[0157] Obtaining financial data

[0158] The server retrieves the necessary financial data, such as revenue data, liability data, asset data, and cash flow information. It uses a database connection object as input and gets the raw data as output. Specifically, it executes an SQL query (e.g., "SELECT FROM financial_data") and converts the resulting data into a Python pandas data frame.

[0159] Step 3:

[0160] Data Formatting

[0161] The server formats the acquired raw data into a format suitable for analysis (for example, CSV format or data frame format). It uses the acquired raw data as input and obtains formatted data as output. Specifically, it uses the pandas function to convert the format, such as "data.to_csv('output.csv')".

[0162] Step 4:

[0163] Sending data to a generative AI model

[0164] The server sends the formatted data to the generative AI model. It uses the formatted data as input and gets the status of the HTTP POST request to the generative AI model as output. Specifically, it converts the data into JSON format, creates an HTTP request, and sends it.

[0165] Step 5:

[0166] Calculation of financial indicators

[0167] The generative AI model calculates financial metrics such as PBR, ROE, and ROA based on the data sent to it. It uses formatted data as input and obtains various financial metrics as output. Specifically, it applies a formula such as "PBR = market_price / book_value."

[0168] Step 6:

[0169] Generate growth strategies and risk management measures

[0170] The generative AI model generates growth strategies and risk management measures based on the results of financial indicator analysis. It uses financial indicator data as input and obtains growth strategies and risk management measures as output. Specifically, it performs scenario analysis and generates proposals for "entering new markets" and "reducing costs."

[0171] Step 7:

[0172] Automatic report generation

[0173] The server automatically generates strategic reports based on insights from the generative AI model. It uses growth strategy and risk management data as input and obtains the generated report as output. Specifically, it creates a PDF report using a LaTeX template.

[0174] Step 8:

[0175] Report format conversion

[0176] The server converts the generated reports into a user-accessible format (PDF or a dedicated web dashboard), using the generated reports as input and obtaining the converted reports as output. Specifically, it uses the Python reportlab library to generate PDFs.

[0177] Step 9:

[0178] Report distribution

[0179] The server sends the created report to the terminals of the company's investor relations officer or management. It uses the converted report as input and gets the delivery status as output. Specifically, it sends the report by email using the SMTP protocol.

[0180] Step 10:

[0181] Review the report

[0182] The terminal has a dedicated dashboard where users can check reports and gain insights. The report URL and dashboard access information are used as input, and the report viewing screen is obtained as output. Specifically, the dashboard is accessed using a web browser.

[0183] Step 11:

[0184] Send Feedback

[0185] The user checks the report contents and submits feedback or additional analysis requests to the server as needed. The feedback contents are used as input and the feedback submission status is obtained as output. The specific operation is to submit the request using a form on the dashboard.

[0186] Step 12:

[0187] Receiving and analyzing feedback

[0188] The server receives feedback and requests for additional analysis from the user, and then resubmits the data to the generative AI model for reanalysis. It uses the feedback as input and obtains the reanalyzed data as output. Specifically, it sends the new data and conditions to the generative AI model via an HTTP POST request.

[0189] Step 13:

[0190] Run a reanalysis

[0191] The generative AI model performs re-analysis based on new conditions and data and returns updated insights to the server. It uses new data and conditions as input and obtains updated insights as output. Specifically, it re-calculates financial indicators and generates strategic recommendations.

[0192] Step 14:

[0193] Regenerating an updated report

[0194] The server regenerates the strategic report based on the updated insights and sends it back to the user terminal. It uses the updated insights as input and obtains the regenerated report as output. Specifically, it creates the report again using the LaTeX template and sends it via the SMTP protocol.

[0195] (Application example 1)

[0196] 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."

[0197] Currently, store managers spend a great deal of time and effort managing inventory, analyzing financial data, and planning sales promotion strategies. However, this often hinders fast and accurate decision-making. It can also lead to inventory shortages or excess inventory, reducing business efficiency. Furthermore, the preparation of reports and processing feedback can be time-consuming, leading to delayed action. It is necessary to improve this situation and enable store managers to make decisions based on fast and accurate information.

[0198] 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.

[0199] In this invention, the server includes a means for aggregating and formatting a company's financial data and inventory data, a means for analyzing the financial data and inventory data using a generative AI model to calculate financial indicators and sales trends, and a means for generating growth strategies, risk management measures, inventory management measures, and sales promotion measures based on the analysis results using the generative AI model. This enables brick-and-mortar store managers to efficiently obtain real-time analysis results of financial data and inventory data and strategic reports based on them.

[0200] "Corporate financial data" is a general term for data that indicates a company's business status and financial condition, such as its revenue, liabilities, assets, and cash flow.

[0201] "Inventory data" is a general term for data related to inventory management, such as the quantity and type of products a company owns, inventory history, and sales prices.

[0202] "Generative AI model" is a general term for artificial intelligence models that automatically analyze specific patterns and trends from large data sets and provide insights into financial indicators, growth strategies, sales promotion measures, and more.

[0203] "Financial indicators" is a general term for statistical values ​​and ratios used to evaluate a company's business condition and financial status, and includes, for example, PBR, ROE, and ROA.

[0204] "Sales trends" is a general term for data that shows sales trends and fluctuations in demand for products and services over a specific period of time.

[0205] A "growth strategy" is a general term for the plans and measures that a company sets in place to achieve sustainable growth, and includes things like entering new markets and cost-cutting measures.

[0206] "Risk management measures" is a general term for measures and policies to predict risks that a company may face and respond to them.

[0207] "Inventory management" is the process of maintaining and efficiently managing the appropriate quantity, type, and storage location of inventory held by a company.

[0208] "Sales promotion measures" is a general term for measures such as advertising, promotions, and pricing strategies implemented to increase product sales.

[0209] A "report" is a document that compiles analysis results, strategic proposals, risk management measures, etc., and is a general term for information provided to management and users.

[0210] "User terminal" is a general term for devices used by managers and users to obtain information, including smart glasses and smartphones.

[0211] "Additional Analysis Request" means a user's request for more detailed analysis based on specific conditions or data.

[0212] This invention relates to a system that enables store managers to efficiently analyze financial and inventory data and automatically generate strategic reports that include growth strategies, risk management measures, and sales promotion measures. The system is configured as follows.

[0213] System Configuration

[0214] Hardware

[0215] 1. Server:

[0216] Acquire, format, and analyze financial and inventory data.

[0217] Responsible for analysis using generative AI models and automatic report generation.

[0218] 2. User Device:

[0219] Smart glasses or smartphone.

[0220] It provides a means for users to review reports and make decisions based on the analysis results.

[0221] software

[0222] 1. Database Management System (DBMS):

[0223] Example: MySQL

[0224] Store and manage financial and inventory data.

[0225] 2. Generative AI Model:

[0226] Example: PyTorch or TensorFlow

[0227] Analyze financial and inventory data to generate necessary metrics and insights.

[0228] 3. Cloud Services:

[0229] Example: AWS Lambda

[0230] Used to efficiently execute server-side processing.

[0231] Specific examples of processing

[0232] 1. Data Collection Phase

[0233] The server retrieves sales data, inventory data, and customer data from the physical store's POS system and inventory management system.

[0234] The data is formatted into a standard format and made suitable for analysis.

[0235] 2. Data analysis phase

[0236] The formatted data is sent to a generative AI model, which analyzes financial indicators, sales trends, and more.

[0237] Based on the analysis results, growth strategies, risk management measures, and inventory management and sales promotion measures are generated.

[0238] 3. Report generation phase

[0239] The server automatically generates strategic reports based on the insights provided by the generative AI model.

[0240] The reports are converted into PDF format and displayed on a dedicated dashboard.

[0241] 4. Information provision phase

[0242] The created report is sent to the user's device (smart glasses or smartphone).

[0243] Users can view reports on a dedicated dashboard and gain real-time insights.

[0244] 5. Feedback and further analysis phase

[0245] Users can review the report and submit requests for additional analysis.

[0246] The server re-analyzes the data through the generative AI model and provides an updated report to the user's device.

[0247] Specific examples

[0248] For example, if a brick-and-mortar store owner is struggling with inventory management, they can use this system to analyze inventory data in real time and display sales trends and optimal stock levels. For example, by entering a prompt such as "Calculate the optimal stock level for the next three months based on last month's sales," the AI ​​will instantly provide the analysis results.

[0249] Using this system, store managers can quickly gain insights and implement effective inventory management and sales promotion strategies.

[0250] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0251] Step 1:

[0252] The server retrieves sales data, inventory data, and customer data from the physical store's POS system and inventory management system. Specifically, the server periodically fetches data through each system's API. Sales information from the POS system and inventory information from the inventory management system are used as input, and data processed into a unified format (e.g., CSV format or data frame format) is obtained as output.

[0253] Step 2:

[0254] The server formats the acquired data into a standard format. Specifically, it converts the acquired sales and inventory data into a data frame using the Python pandas library and cleanses it to maintain consistency and integrity. Raw data (unformatted data) is used as input, and a formatted data frame is obtained as output.

[0255] Step 3:

[0256] The server sends the formatted data to a generative AI model, which analyzes the data and calculates financial indicators and sales trends. Specifically, the data is fed into an AI model built using Python's PyTorch or TensorFlow, and the trained model makes predictions. The formatted data frame is used as input, and the calculated results of financial indicators and sales trends are obtained as output.

[0257] Step 4:

[0258] The server generates growth strategies, risk management measures, and inventory management / sales promotion measures based on the analysis results obtained from the generative AI model. Specifically, a Python script is used to analyze the output of the AI ​​model and document strategic proposals. The output of the AI ​​model is used as input, and growth strategies, risk management measures, and inventory management / sales promotion measures are obtained as output.

[0259] Step 5:

[0260] The server automatically generates strategic reports based on the generated growth strategies, risk management measures, and inventory management and sales promotion measures. Specifically, it creates reports in PDF format using Python's FPDF library. The strategic proposals are used as input, and the PDF report is obtained as output.

[0261] Step 6:

[0262] The server sends the created report to the user's device. Specifically, it sends the report by email using SMTP or uploads it to cloud storage. The input is a PDF report, and the output is either emailed to the user or saved in cloud storage.

[0263] Step 7:

[0264] Users use a dedicated dashboard to check reports and send additional analysis requests. Specifically, they access the dashboard via a web application and enter additional analysis requests. The input is the request entered by the user into the dashboard, and the output is the request sent to the server.

[0265] Step 8:

[0266] The server receives user feedback and requests for additional analysis, and then resubmits the data to the generative AI model for reanalysis. Specifically, the data is fed back into the AI ​​model and reanalyzed based on the new conditions. The user request and existing data are used as input, and updated analysis results are output.

[0267] Step 9:

[0268] The server regenerates the report based on the results of the reanalysis and provides it to the user's device. Specifically, it regenerates the report in PDF format and sends it to the user. The reanalysis results are used as input, and an updated PDF report is obtained as output.

[0269] 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.

[0270] This invention relates to a system that enables companies to efficiently analyze financial data and automatically generate reports including strategies and risk management by combining an emotion engine with a system that can provide more appropriate feedback and requests for additional analysis based on the user's emotions. Below, an embodiment of this system and specific program processing are described in detail.

[0271] Data Collection Phase

[0272] server

[0273] The server accesses the company's financial database to retrieve the necessary financial data, such as revenue, liabilities, assets, cash flow, etc. The data retrieval process involves proper access authentication to ensure data security.

[0274] The acquired data is formatted into a standard format (e.g., CSV or data frame format) and data cleaning is performed.

[0275] Data analysis phase

[0276] server

[0277] The formatted data is fed into a generative AI model, which receives this data and calculates key financial metrics (PBR, ROE, ROA, etc.).

[0278] Based on the analysis results, the generative AI model generates corporate growth strategies (e.g., entering new markets and cost reduction measures) and risk management measures (e.g., measures to reduce liquidity risk and debt management).

[0279] Report generation phase

[0280] server

[0281] The generative AI model delivers insights that automatically generate strategic reports, including explanations and interpretations of financial metrics, suggested growth strategies, and risk management measures.

[0282] The generated reports are converted into PDF format or a dedicated web dashboard, and provided in a format that can be accessed by the company's investor relations personnel and management.

[0283] Information provision phase

[0284] server

[0285] The created report is sent to the devices of the company's IR staff and management via email or cloud services.

[0286] Terminal

[0287] The device has a dedicated dashboard where users can view reports and gain insights.

[0288] Feedback and further analysis phase

[0289] User

[0290] Users (IR personnel or management) review the report contents and send feedback or requests for additional analysis to the server.

[0291] server

[0292] The server receives feedback and requests for additional analysis from users, and sends the data back to the generative AI model for additional analysis.

[0293] The generative AI model reanalyzes based on new conditions and data and provides updated insights to the server.

[0294] server

[0295] The report is updated based on the new insights and sent back to the user's device.

[0296] Emotion engine integration phase

[0297] User terminal

[0298] A user device equipped with an emotion engine recognizes emotions from the user's facial expressions, voice, text input, etc. while the user is viewing a report.

[0299] The emotion engine analyzes the recognized user's emotional data and evaluates their stress level and interests.

[0300] server

[0301] The server optimizes the report display and additional explanations based on the emotion data received from the emotion engine. For example, if the user is feeling stressed, it will automatically provide more detailed explanations and supplementary information.

[0302] Based on the needs indicated by the user's emotional data, specific analysis requests are automatically generated to the generative AI model, expanding the user's options.

[0303] Specific examples

[0304] Case Study: Medium-sized Manufacturing Company Y

[0305] background

[0306] Company Y has experienced a recent increase in revenue and needs to provide accurate and timely information to investors. However, its traditional process required a significant amount of time and effort to analyze financial data and create proposals.

[0307] introduction

[0308] Company Y will introduce this system and upload its financial data to the server. It will also integrate an emotion engine into user devices.

[0309] Processing flow

[0310] The server accesses Company Y's database and aggregates and formats the necessary financial data.

[0311] The server sends the data to a generative AI model, which calculates financial indicators and generates growth strategies and risk management measures.

[0312] The server creates a strategic report based on the generated insights and sends it to the terminal of Company Y's IR officer.

[0313] The user (IR staff) checks the report on the dashboard, and the emotional data recognized by the emotion engine is analyzed, and feedback and additional analysis are automatically optimized.

[0314] result

[0315] Company Y was able to quickly obtain insights and provide reports optimized by the sentiment engine, enabling it to provide effective IR information to investors, which improved communication with investors and increased its reputation in the capital markets.

[0316] The above is a specific embodiment and processing content of this system. By integrating an emotion engine, customization based on the user's emotions becomes possible, realizing the construction of a more effective and user-friendly system.

[0317] The processing flow will be explained below.

[0318] Step 1:

[0319] The server accesses the company's financial database to retrieve the required financial data such as revenue, liabilities, assets, cash flow, etc. The data retrieval process involves proper access authentication and ensures a secure connection.

[0320] Step 2:

[0321] The server formats the acquired financial data into a standard format (e.g., CSV file or data frame format), and this process also involves data cleaning to remove incomplete and duplicate data.

[0322] Step 3:

[0323] The server sends the formatted data to the generative AI model, which then begins analyzing the input data.

[0324] Step 4:

[0325] The generative AI model analyzes the data and calculates key financial metrics (PBR, ROE, ROA, etc.), which are important metrics for understanding a company's financial situation.

[0326] Step 5:

[0327] Based on the analysis results, the generative AI model generates growth strategies (e.g., new market entry, cost reduction measures) and risk management measures (e.g., liquidity risk mitigation, debt management) for the company. At this stage, the AI ​​may also perform multiple scenario analysis.

[0328] Step 6:

[0329] The server automatically generates strategic reports based on the insights provided by the generative AI model, including interpretations of financial indicators, proposed growth strategies, and recommended risk management measures.

[0330] Step 7:

[0331] The server converts the generated reports into PDF format, Excel sheets, dedicated web dashboards, etc., making them accessible to the company's investor relations personnel and management.

[0332] Step 8:

[0333] The server then sends the generated reports to the terminals of the company's investor relations staff and management, and the reports are provided via email or cloud storage.

[0334] Step 9:

[0335] The device is integrated with a dedicated dashboard where users can view generated reports and gain insights into financial performance and strategic proposals.

[0336] Step 10:

[0337] The user device, which is integrated with the emotion engine, recognizes emotions in real time from facial expressions, voice, and input text while the user is reviewing a report, thereby assessing the user's stress level, interest level, etc.

[0338] Step 11:

[0339] Users (IR staff or management) review the report content and AI proposals, and provide feedback or request additional analysis based on the emotional data at the time. If the emotion engine is feeling stressed, it will optimize the report by adding a simple explanation or providing detailed data.

[0340] Step 12:

[0341] The server receives feedback and requests for additional analysis from the user and sends the data to the generative AI model again. The AI ​​model is given new analysis scenarios and conditions, and re-analysis is performed.

[0342] Step 13:

[0343] The generative AI model performs additional analysis and generates new insights, including specific metrics that users have expressed interest in and new strategic recommendations.

[0344] Step 14:

[0345] The server updates the report based on the new insights and sends it back to the user's device, where the latest report is displayed in real time on the dashboard.

[0346] These are the specific processing steps of this system. At each step, the server, generative AI model, terminal, and user play their respective roles to achieve efficient and accurate analysis and reporting of financial data. The integration of an emotion engine enables customization based on user emotions, resulting in a more user-friendly system.

[0347] Example 2

[0348] 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."

[0349] Analyzing financial information and generating reports in companies requires a great deal of time and effort using conventional methods. Furthermore, if the generated reports do not reflect the specific needs and feelings of users, effective decision-making becomes difficult. Therefore, there is a need for efficient analysis of financial information, automatic generation of highly accurate reports, and provision of reports whose content is optimized based on user feelings.

[0350] The specification processing by the specification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for aggregating and formatting a company's financial information, means for analyzing the financial information using a generative AI model and calculating financial indicators, means for generating a growth strategy and a risk management measure based on the analysis results using the generative AI model, means for automatically generating a strategic report based on the generated growth strategy and the risk management measure, means for providing the report to a user terminal, means for receiving feedback and additional analysis requests from a user and performing reanalysis, and means for collecting and analyzing user emotion data using an emotion engine and optimizing the report content. This enables efficient analysis of financial information, rapid generation of reports, and provision of optimal content based on the user's emotions.

[0351] "Financial information" refers to data that shows a company's financial status, such as its revenue, liabilities, assets, and cash flow.

[0352] A "generative AI model" is an artificial intelligence model that uses machine learning and deep learning technologies to analyze financial information and calculate financial indicators.

[0353] "Financial indicators" are indicators used to quantitatively evaluate a company's financial condition, and include, for example, PBR (price-to-book ratio), ROE (return on equity), and ROA (return on assets).

[0354] A "growth strategy" is a general term for the plans and measures that a company implements in order to achieve sustainable growth.

[0355] "Risk management measures" are specific policies and measures to assess the risks that a company may face and reduce or manage them.

[0356] A "strategic report" is a document that summarizes financial indicators, growth strategies, and risk management measures generated based on financial information, and compiles proposals and views on management strategies.

[0357] "User terminal" refers to a device, such as a computer or mobile device, used by a company's investor relations personnel or management to view reports and submit feedback.

[0358] "Feedback and further analysis requests" are comments provided by users regarding the contents of a report or requests for further data analysis.

[0359] An "emotion engine" is a technology that recognizes and analyzes emotions from a user's facial expressions, voice, text input, etc.

[0360] "Emotion data" refers to data that indicates the user's emotional state as recognized and analyzed by the emotion engine.

[0361] Optimization is the adjustment and improvement of system or process parameters to efficiently achieve a specific objective.

[0362] MODE FOR CARRYING OUT THE INVENTION

[0363] This invention relates to a system that enables companies to efficiently analyze financial information and automatically generate reports including strategies and risk management, by combining an emotion engine with a system that can provide more appropriate feedback and requests for additional analysis based on the user's emotions. Below, an embodiment of this system and specific program processing are described in detail.

[0364] Data Collection Phase

[0365] server

[0366] The server accesses the company's financial database and retrieves the required financial information such as revenue, liabilities, assets, cash flow, etc. The data retrieval process involves authentication using an API key and / or authentication token for database connection.

[0367] The server formats the acquired data into a standard format (e.g., CSV or data frame format) using the Python Pandas library.

[0368] Furthermore, missing values ​​and outliers are handled by filling in the missing values ​​with the mean value and excluding outliers.

[0369] Data analysis phase

[0370] server

[0371] The server inputs the formatted financial information into the generative AI model, sending the data to the generative AI model via the API as a POST request.

[0372] A prompt sentence is generated and fed into the generative AI model along with financial information retrieved from the database. An example prompt sentence is as follows:

[0373] "Please suggest the optimal growth strategy based on the company's revenue data."

[0374] The generative AI model analyzes input data and calculates key financial metrics (PBR, ROE, ROA, etc.) based on pre-defined formulas and algorithms.

[0375] The generative AI model generates corporate growth strategies and risk management measures based on the results of analyzing financial indicators.

[0376] Report generation phase

[0377] server

[0378] The server automatically generates strategic reports based on the insights returned by the generative AI model, including explanations and interpretations of financial metrics, suggested growth strategies, and risk management measures.

[0379] A template engine (e.g., Jinja2) is used to generate reports and output formats such as HTML and PDF.

[0380] Convert the generated report into PDF format or a dedicated web dashboard. For example, use a PDF generation tool to convert an HTML template into a PDF.

[0381] Information provision phase

[0382] server

[0383] The server then sends the created reports to the devices of the company's investor relations staff or management. In some cases, the reports are sent as PDF attachments via email, or a link to a cloud service is shared.

[0384] Terminal

[0385] The device has a dedicated dashboard where users can view reports and gain various insights.

[0386] Feedback and further analysis phase

[0387] User

[0388] Users (IR staff and management) check the contents of the report and send feedback or requests for additional analysis to the server. The dashboard provides input fields for feedback forms and requests for additional analysis.

[0389] server

[0390] The server receives feedback and requests for additional analysis from the user, sends the data to the generative AI model again for additional analysis, and creates a new prompt sentence and inputs it to the generative AI model.

[0391] It reanalyzes the data based on new conditions and data, and provides updated insights to the server.

[0392] The server updates the report based on the new insights and sends it back to the user's device.

[0393] Emotion engine integration phase

[0394] User terminal

[0395] The user device equipped with the emotion engine recognizes emotions from the user's facial expressions, voice, text input, etc. while the user is viewing a report. This requires a device equipped with a camera and microphone.

[0396] The emotion engine analyzes the recognized user's emotional data and evaluates their stress level and interests.

[0397] server

[0398] The server optimizes the report display and additional explanations based on the emotion data received from the emotion engine. For example, if the user is feeling stressed, it will automatically provide more detailed explanations and supplementary information.

[0399] Based on the needs indicated by the user's emotional data, specific analysis requests are automatically generated to the generative AI model, expanding the user's options.

[0400] Examples and prompts

[0401] Examples:

[0402] Case Study: Medium-sized Manufacturing Company Y

[0403] With the recent increase in revenue, Company Y needs to provide accurate and prompt information to investors. However, in the conventional process, analyzing financial information and creating proposals required a great deal of time and effort. Company Y will introduce this system and upload its financial information to a server. It will also integrate an emotion engine into user devices.

[0404] Process flow:

[0405] The server accesses Company Y's database and aggregates and formats the necessary financial information.

[0406] The server sends the data to a generative AI model, which calculates financial indicators and generates growth strategies and risk management measures.

[0407] The server creates a strategic report based on the generated insights and sends it to the terminal of Company Y's IR officer.

[0408] The user (IR staff) checks the report on the dashboard, and the emotional data recognized by the emotion engine is analyzed, and feedback and additional analysis are automatically optimized.

[0409] Example prompt sentence:

[0410] "Based on Company Y's financial data, please calculate the latest financial indicators (PBR, ROE, ROA, etc.) and propose growth strategies and risk management measures. Also, please use an emotion engine to optimize the report content based on user feedback."

[0411] The above is a specific embodiment and processing content of this system. By integrating an emotion engine, customization based on the user's emotions becomes possible, realizing the construction of a more effective and user-friendly system.

[0412] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0413] Program processing steps

[0414] Data Collection Phase

[0415] Step 1:

[0416] server

[0417] The server accesses the company's financial database and retrieves the required financial information such as revenue, liabilities, assets, cash flow, etc. The input is the database authentication information and the output is the retrieved financial information.

[0418] Specifically, it uses an API key or authentication token for database connection to execute an SQL query to retrieve data.

[0419] Step 2:

[0420] server

[0421] The server formats the financial information it retrieves into a standard format (CSV or data frame). The input is the raw data it retrieves, and the output is the formatted data.

[0422] For example, use Python's Pandas library to convert the data into a data frame, organize the necessary columns, and convert data types.

[0423] Step 3:

[0424] server

[0425] The server cleans the financial information: the input is formatted data, and the output is cleaned data.

[0426] Specifically, the process involves filling in missing values ​​with the average value and excluding outliers.

[0427] Data analysis phase

[0428] Step 4:

[0429] server

[0430] The server sends the formatted and cleaned financial information to a generative AI model, whose inputs are the cleaned data and generated prompts, and whose output is financial metrics and insights.

[0431] Specifically, the data is sent to the generative AI model via an API as a POST request. An example prompt might be: "Based on the company's revenue data, please propose the optimal growth strategy."

[0432] Step 5:

[0433] Generative AI Models

[0434] The generative AI model analyzes input data and calculates key financial indicators (PBR, ROE, ROA, etc.) The input is the cleaned data and prompt statements, and the output is the calculated financial indicators.

[0435] Financial indicators are calculated using pre-defined formulas and algorithms.

[0436] Step 6:

[0437] Generative AI Models

[0438] The generative AI model generates a company's growth strategy and risk management measures from the results of analyzing financial indicators. The input is the calculated financial indicators, and the output is the generated growth strategy and risk management measures.

[0439] Specifically, the generated text data is inserted into a report template.

[0440] Report generation phase

[0441] Step 7:

[0442] server

[0443] The server automatically generates strategic reports based on the insights returned by the generative AI model. The input is the generated growth strategy and risk management measures, and the output is the completed report.

[0444] A template engine (e.g., Jinja2) is used to generate reports and convert them into formats such as HTML and PDF.

[0445] Step 8:

[0446] server

[0447] The server converts the generated report into PDF format or a dedicated web dashboard. The input is the generated report and the output is the converted file format.

[0448] As a specific operation, for example, a PDF generation tool is used to convert the HTML template into a PDF.

[0449] Information provision phase

[0450] Step 9:

[0451] server

[0452] The server then sends the created report to the terminals of the company's IR staff and management. The input is a report in PDF format or web dashboard format, and the output is a report sent to the user's terminal.

[0453] Specific actions include sending a PDF as an attachment via email or sharing a link to a cloud service.

[0454] Step 10:

[0455] Terminal

[0456] The terminal has a dedicated dashboard where users can check reports. The input is a report in PDF format or web dashboard format, and the output is the checked report.

[0457] You can access reports and gain various insights through the dashboard.

[0458] Feedback and further analysis phase

[0459] Step 11:

[0460] User

[0461] Users (IR staff or management) check the contents of the report and send feedback or requests for additional analysis to the server. The input is feedback on the report or requests for additional analysis, and the output is the feedback sent to the server.

[0462] Provide a feedback form or input field for additional analysis requests on the dashboard.

[0463] Step 12:

[0464] server

[0465] The server receives feedback and requests for additional analysis from users and sends the data to the generative AI model again for further analysis. The input is the received feedback and requests for additional analysis, and the output is the reanalyzed insights.

[0466] Create new prompts and feed them into the generative AI model, which then reanalyzes them and generates new insights.

[0467] Step 13:

[0468] server

[0469] The server updates the report based on the new insights and sends it back to the user's device. The input is the reanalyzed insights and the updated report, and the output is the updated report.

[0470] Allow users to view updated reports.

[0471] Emotion engine integration phase

[0472] Step 14:

[0473] User terminal

[0474] A user device equipped with an emotion engine recognizes emotions from the user's facial expressions, voice, text input, etc. while the user is viewing a report. The input is the user's facial expressions, voice, and text data, and the output is emotion data.

[0475] This requires a device with a camera and microphone.

[0476] Step 15:

[0477] server

[0478] The server optimizes the display content of the report and additional explanations based on the emotion data received from the emotion engine. The input is emotion data, and the output is an optimized report.

[0479] If the user is feeling stressed, more detailed explanations and supplementary information will be automatically provided.

[0480] Step 16:

[0481] server

[0482] The server automatically generates specific analysis requests to the generative AI model based on the needs indicated by the user's emotional data, expanding the user's options. The input is the emotional data and the generated prompt, and the output is the additional analysis results.

[0483] Specifically, it generates a new prompt sentence based on the emotional data and sends that prompt sentence to the generative AI model.

[0484] The above is the specific processing flow of this system and the operation at each step. By clearly explaining the specific operations and data processing methods, the details of the system will become clearer.

[0485] (Application example 2)

[0486] 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."

[0487] Traditional financial data analysis systems required a great deal of time and effort for companies to quickly and efficiently understand their financial situation and make strategic decisions. Furthermore, they lacked feedback based on user emotions and intuition, making it difficult for users to gain a deeper understanding of reports and appropriately request additional analysis. Furthermore, in brick-and-mortar store operations, understanding the emotions of staff and customers in real time and providing optimal service was a challenge.

[0488] 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.

[0489] In this invention, the server includes a means for aggregating and formatting a company's financial data, a means for analyzing the financial data using a generative AI model to calculate financial indicators, and a means for generating growth strategies and risk management measures. This enables companies to gain quick and accurate insights. Furthermore, the user terminal is equipped with an emotion engine, providing a means for recognizing user emotions and optimizing report content based on the recognition results. Furthermore, the system includes a means for displaying reports via a dedicated dashboard and automatically optimizing report content based on the emotion recognition results. This enables efficient user feedback and highly accurate requests for additional analysis, enabling optimal service provision even in brick-and-mortar store operations.

[0490] "Financial data" refers to financial information held by a company, such as revenues, liabilities, assets, and cash flow.

[0491] A "generative AI model" is an artificial intelligence model that analyzes input data and automatically calculates financial indicators, generates growth strategies, and generates risk management measures.

[0492] A "user terminal" is a device used to check reports, send feedback, and provide information based on emotion recognition results.

[0493] An "emotion engine" is a technology for recognizing and analyzing emotions from a user's facial expressions, voice, text input, etc.

[0494] "Financial indicators" are indicators used to evaluate a company's financial condition and performance, and include PBR, ROE, ROA, etc.

[0495] A "growth strategy" is a plan or policy for a company to achieve sustainable growth.

[0496] "Risk management measures" are strategies and measures used to mitigate or avoid risks that a company may face.

[0497] A "strategic report" is a document that includes explanations and interpretations of financial indicators, proposed growth strategies, and risk management measures.

[0498] A "dedicated dashboard" is an interface that visually displays generated reports and is easily accessible to users.

[0499] "Feedback" refers to the reactions and opinions users provide to reports.

[0500] An "additional analysis request" is an action in which a user requests the server to perform further analysis based on a report or analysis result.

[0501] This section describes a specific system for implementing this invention. The system aggregates and formats a company's financial data, analyzes it using a generative AI model, and calculates various financial indicators. Furthermore, it generates growth strategies and risk management measures based on the analysis results, and automatically generates strategic reports. Additionally, it can recognize user emotions using a user device equipped with an emotion engine and optimize the content of the report.

[0502] Data collection and formatting

[0503] The server accesses the company's financial database and retrieves the necessary financial data, such as revenue, liabilities, assets, cash flow, etc. The data is retrieved with appropriate access authentication and then formatted into a standard format. During this process, the data is also cleaned to remove missing or outlier values.

[0504] Data analysis

[0505] The server inputs the formatted financial data into a generative AI model to calculate key financial indicators (e.g., PBR, ROE, ROA, etc.). This model can use OpenAI's GPT-4 or Google's BERT. Based on the analysis results, the server generates insights that suggest growth strategies and risk management measures for the company.

[0506] report generation

[0507] Based on the insights generated, strategic reports are automatically generated, including explanations and interpretations of financial indicators, proposed growth strategies, and risk management measures, and can be viewed in PDF format or on a dedicated web dashboard.

[0508] Input and Feedback

[0509] The server sends automatically generated reports to the terminals of the company's investor relations personnel and management via email or cloud services. Users can use a dashboard to check the reports and send feedback or requests for additional analysis. The server receives this feedback and requests and performs reanalysis.

[0510] Emotion Engine Integration

[0511] The emotion engine installed on the user's device recognizes emotions from the user's facial expressions, voice, and text input while viewing the report. For example, it uses Affectiva's SDK or Microsoft's Emotion API. This emotion data is sent to the server to optimize the report content. For example, if the user is feeling stressed, it will provide more detailed explanations and additional information.

[0512] Specific examples

[0513] For example, a mid-sized manufacturing company might prompt their generative AI model with the following:

[0514] Prompt: "Analyze store sales data and generate future growth and risk management strategies. For example, which products are selling the best and which products are likely to be low in stock?"

[0515] Based on this prompt, the generative AI model analyzes financial data and proposes growth strategies and risk management measures. Based on these insights, a strategic report is generated. This report is optimized according to the user's emotions through an emotion engine, making it more user-friendly and providing useful information.

[0516] This will enable companies to analyze financial data quickly and accurately and make strategic decisions, while also enabling brick-and-mortar stores to provide optimal services that are tailored to the emotions of staff and customers.

[0517] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0518] Step 1:

[0519] The server accesses the company's financial database to retrieve the required financial data, such as revenue, liabilities, assets, cash flow, etc. The input is the authentication information of the company's financial database, and the output is the retrieved financial data. This data retrieval process is subject to appropriate access authentication to ensure data security.

[0520] Step 2:

[0521] The server formats the acquired financial data into a standard format (CSV or data frame format) and performs data cleaning. The input is the acquired financial data, and the output is the formatted and cleaned financial data. During this process, missing values ​​and outliers are processed and the data is formatted in a format suitable for analysis.

[0522] Step 3:

[0523] The server inputs the formatted financial data into a generative AI model. The generative AI model calculates key financial indicators (PBR, ROE, ROA, etc.). The input is the formatted financial data, and the output is the calculated financial indicators. The generative AI model (e.g., OpenAI GPT-4) analyzes the financial data and generates the required indicators.

[0524] Step 4:

[0525] The server automatically generates growth strategies and risk management measures based on the analysis results of the generative AI model. The input is the calculated financial indicators, and the output is the growth strategies and risk management measures. In this step, a strategic action plan for the company is created based on the analysis results.

[0526] Step 5:

[0527] The server automatically generates a strategic report based on the generated growth strategy and risk management measures. The input is data on growth strategies and risk management measures, and the output is a strategic report (e.g., in PDF format or data for display on a dedicated web dashboard). This report includes explanations and interpretations of financial indicators, proposed growth strategies, and risk management measures.

[0528] Step 6:

[0529] The server sends the automatically generated report to the terminals of the company's IR personnel and management via email or cloud services. The input is the strategic report, and the output is the sent report. The report can then be viewed on the user's terminal.

[0530] Step 7:

[0531] Users can use a dedicated dashboard to check reports and, if necessary, send feedback or requests for additional analysis to the server. The input is the user's feedback or requests for additional analysis, and the output is re-requested analysis data. Each item in the report is visually displayed on the dashboard.

[0532] Step 8:

[0533] The server receives feedback and requests for additional analysis from users and sends the data back to the generative AI model to perform the additional analysis. The input is the feedback and requests for additional analysis, and the output is the results of the reanalysis. New insights are generated and the report is updated.

[0534] Step 9:

[0535] The emotion engine installed on the user's device recognizes emotions from the user's facial expressions, voice, text input, etc. while viewing the report, and sends that data to the server. The input is the user's emotion data, and the output is the emotion recognition results. The data is analyzed by the emotion engine (e.g., Affectiva SDK).

[0536] Step 10:

[0537] The server optimizes the report content based on the emotion data received from the emotion engine. The input is the emotion recognition result, and the output is the optimized report. If the user is feeling stressed, the report is automatically updated to provide more detailed explanations and supplementary information.

[0538] Specific examples

[0539] For example, a mid-sized manufacturing company might prompt their generative AI model with the following:

[0540] "Analyze store sales data and generate future growth and risk management strategies. For example, tell me which products are selling the best and which products are likely to be low in stock."

[0541] 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.

[0542] 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.

[0543] 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.

[0544] [Second embodiment]

[0545] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0546] 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.

[0547] 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).

[0548] 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.

[0549] 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.

[0550] 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).

[0551] 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.

[0552] 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.

[0553] 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.

[0554] 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.

[0555] 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.

[0556] 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."

[0557] This invention relates to a system that enables companies to efficiently analyze financial data and automatically generate reports that include strategies and risk management. An embodiment of this system and specific program processing will be described in detail below.

[0558] Data Collection Phase

[0559] server

[0560] The server accesses the company's financial database to obtain the necessary revenue, liability, asset, and cash flow information, connecting to authorized databases via access authentication.

[0561] The acquired data is formatted into a standard format, such as CSV or data frame, making it suitable for analysis.

[0562] Data analysis phase

[0563] server

[0564] The formatted data is sent from the server to the generative AI model, which analyzes it and calculates each financial indicator.

[0565] Generative AI Models

[0566] Based on the data received, the generative AI model calculates key financial indicators such as PBR (Price to Book Ratio), ROE (Return on Equity), and ROA (Return on Assets).

[0567] Furthermore, based on the analysis results, the generative AI model generates corporate growth strategies (e.g., entry into new markets and cost reduction measures) and risk management measures (e.g., measures to reduce liquidity risk and debt management).

[0568] Report generation phase

[0569] server

[0570] The server automatically generates strategic reports based on insights provided by the generative AI model, including explanations and interpretations of financial metrics, suggested growth strategies, and risk management measures.

[0571] Convert the generated reports into a format that can be accessed by the company's investor relations personnel and management (e.g., PDF format or a dedicated web dashboard).

[0572] Information provision phase

[0573] server

[0574] The reports are then sent to the devices of the company's IR staff and management, often via email or cloud services.

[0575] Terminal

[0576] The device has a dedicated dashboard where users can view reports and gain insights.

[0577] Feedback and further analysis phase

[0578] User

[0579] Users (IR staff and management) review the report and, if necessary, can send feedback to the server and request additional analysis.

[0580] server

[0581] The server receives feedback and requests for additional analysis from users, sends the data to the generative AI model again, and performs additional analysis.

[0582] Generative AI Models

[0583] The generative AI model performs reanalysis based on new conditions and data and sends updated insights back to the server.

[0584] server

[0585] The server regenerates the report based on the updated insights and sends it to the user terminal.

[0586] Specific examples

[0587] Case Study: Medium-sized Manufacturing Company X

[0588] background

[0589] As Company X's revenues increase, it needs to provide accurate and timely information to investors, but analyzing financial data and compiling strategic proposals takes a lot of time and effort.

[0590] introduction

[0591] Company X introduces this system and uploads its financial data to the server.

[0592] Processing flow

[0593] The server accesses Company X's database and aggregates and formats the necessary financial data.

[0594] The server sends the data to a generative AI model, which calculates financial indicators and generates growth strategies and risk management measures.

[0595] Based on the generated insights, the server creates a strategic report and sends it to the terminal of Company X's IR officer.

[0596] The user (IR officer) checks the report on the dashboard and submits additional analysis requests to the server.

[0597] The server receives the request, performs the reanalysis, and provides an updated report to the user's terminal.

[0598] result

[0599] Company X was able to quickly obtain insights and provide effective IR information to investors, which improved communication with investors and increased its reputation in the capital market.

[0600] The above is a detailed description of the system's implementation and processing. This invention can help companies use AI to efficiently analyze financial data and quickly provide high-quality IR information.

[0601] The processing flow will be explained below.

[0602] Step 1:

[0603] The server accesses the company's financial database to retrieve the necessary financial data such as revenue, liabilities, assets, cash flow, etc. This data retrieval process involves proper access authentication to ensure data security.

[0604] Step 2:

[0605] The server formats the acquired financial data into a standard format (e.g., CSV file or data frame format). Data cleaning is also performed at this stage to remove incomplete or duplicate data.

[0606] Step 3:

[0607] The server inputs the formatted data into the generative AI model, which receives the data and begins analyzing it.

[0608] Step 4:

[0609] The generative AI model analyzes the input data and calculates key financial indicators, such as PBR (Price to Book Ratio), ROE (Return on Equity), and ROA (Return on Assets).

[0610] Step 5:

[0611] Based on the analysis results, the generative AI model generates corporate growth strategies (e.g., entry into new markets and cost reduction measures) and risk management measures (e.g., measures to reduce liquidity risk and debt management).

[0612] Step 6:

[0613] The server automatically generates strategic reports based on insights provided by the generative AI model, including explanations and interpretations of financial metrics, suggested growth strategies, and risk management measures.

[0614] Step 7:

[0615] The server formats the generated reports into a format (e.g., PDF or dedicated web dashboard) that can be accessed by the company's investor relations personnel and management.

[0616] Step 8:

[0617] The server then sends the generated reports to the terminals of the company's IR staff and management via email or cloud services.

[0618] Step 9:

[0619] The device has a dedicated dashboard where users can view reports and gain insights.

[0620] Step 10:

[0621] Users (IR personnel or management) review the report and, if necessary, send feedback to the server and request additional analysis.

[0622] Step 11:

[0623] The server receives feedback and requests for additional analysis from users, and sends the data back to the generative AI model for additional analysis.

[0624] Step 12:

[0625] The generative AI model performs reanalysis based on new conditions and data and provides updated insights to the server.

[0626] Step 13:

[0627] The server updates the report based on the new insights and sends it back to the user's device.

[0628] These are the specific processing steps of this system. At each step, the server, generative AI model, terminal, and user play their respective roles to achieve efficient and accurate analysis and reporting of financial data.

[0629] Example 1

[0630] 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."

[0631] In today's business environment, it is important for companies to efficiently analyze financial data and quickly provide high-quality reports, including those for strategy and risk management. However, traditional methods require a significant amount of time and effort to aggregate data, analyze it, and create reports, straining corporate resources. In particular, it is difficult to quickly and accurately handle large amounts of financial data and obtain appropriate insights to support strategic decision-making.

[0632] 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.

[0633] In this invention, the server includes means for aggregating and formatting a company's financial data, means for analyzing the financial data using a generative AI model to calculate financial indicators, means for generating a growth strategy and risk management measures based on the analysis results using the generative AI model, means for providing the generated report to a user terminal via email or a cloud service, means for displaying the report via a dedicated dashboard, and means for receiving feedback and requests for additional analysis from users and performing reanalysis, thereby enabling companies to efficiently analyze financial data and quickly provide high-quality reports that support strategic decision-making.

[0634] "Corporate financial data" refers to financial information that a company generates and holds in the course of its economic activities, and includes revenue data, liability data, asset data, cash flow information, and the like.

[0635] "Aggregation and formatting means" refers to methods or tools used to convert data from different formats or sources into a unified format suitable for analysis.

[0636] A "generative AI model" refers to a system that uses artificial intelligence technology to automatically perform complex calculations and analyses based on input data.

[0637] "Financial indicators" refer to numerical values ​​calculated using formulas to evaluate a company's financial condition and performance, and include, for example, PBR (price-to-book ratio), ROE (return on equity), and ROA (return on assets).

[0638] A "growth strategy" refers to the plans and policies that a company implements in order to achieve sustainable development, and includes measures such as entering new markets and cost-cutting measures.

[0639] "Risk management measures" refer to the plans and measures adopted to identify, assess and mitigate potential risks faced by an entity, including liquidity risk mitigation measures and debt management.

[0640] A "strategic report" refers to a document in which a company summarizes its future strategies and risk management based on the analysis of financial data.

[0641] "Means of providing via email or cloud service" refers to a method of using an email system or cloud service to quickly and securely distribute the generated report to the user.

[0642] A "dedicated dashboard" refers to a specialized interface, typically provided as a web application, that allows users to view reports and gain insights.

[0643] "Means for receiving feedback or requests for additional analysis and performing re-analysis" refers to methods or tools for receiving user opinions or requests and conducting additional data analysis based on those opinions or requests to generate new insights.

[0644] The present invention relates to a system that enables a company to efficiently analyze financial data and automatically generate reports that include strategies and risk management. Specific embodiments of this system will be described in detail below.

[0645] Data Collection Phase

[0646] server

[0647] The server accesses the company's financial database to retrieve the necessary revenue, liability, asset, and cash flow information. It connects to the database through secure access authentication using a database management system such as MySQL or PostgreSQL. The retrieved data is then formatted into CSV or dataframe format using the Python pandas library.

[0648] Data analysis phase

[0649] server

[0650] The formatted data is sent from the server to the generative AI model using an HTTP POST request to send the data to the AI ​​model's endpoint.

[0651] Generative AI Models

[0652] Based on the data it receives, the generative AI model calculates financial indicators such as PBR (Price to Book Ratio), ROE (Return on Equity), and ROA (Return on Assets). Specifically, it uses a formula such as "PBR = market_price / book_value." It also performs scenario-based analysis to generate growth strategies (e.g., new market entry, cost reduction measures) and risk management measures (e.g., liquidity risk mitigation measures, debt management).

[0653] Report generation phase

[0654] server

[0655] The server automatically generates strategic reports in PDF format using LaTeX templates based on insights from the generative AI model. The reports include explanations and interpretations of financial metrics, proposed growth strategies, and risk management measures. The generated reports are converted to PDF format using the Python reportlab library.

[0656] Information provision phase

[0657] server

[0658] The created report is sent to the company's IR personnel or management via email or cloud services (e.g., AWS S3 or Google Drive).

[0659] Terminal

[0660] The device has a dedicated dashboard where users can view reports and gain insights, and a dedicated web application allows users to access the dashboard from a browser and view the report contents.

[0661] Feedback and further analysis phase

[0662] User

[0663] Users (IR staff and management) review the report and submit feedback or requests for additional analysis to the server as needed. These requests are sent using a feedback form on the dashboard.

[0664] server

[0665] The server receives feedback and requests for additional analysis from users, and then sends the data to the generative AI model again to perform reanalysis.

[0666] Generative AI Models

[0667] The generative AI model performs reanalysis based on new conditions and data and returns updated insights to the server.

[0668] server

[0669] The server regenerates strategic reports based on the updated insights and sends them back to the user's device, allowing businesses to continuously obtain the latest information and strategic proposals.

[0670] Examples of prompt statements

[0671] "Please calculate financial indicators such as PBR, ROE, and ROA based on the company's financial data for the first quarter of fiscal year 2022. Also, please propose growth strategies such as entering new markets and cost reduction measures, as well as risk management measures such as measures to reduce liquidity risk and debt management."

[0672] This invention enables companies to use AI to efficiently analyze financial data and quickly provide high-quality IR information.

[0673] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0674] Step 1:

[0675] Database Connection

[0676] The server connects to the company's financial database, taking the database URL, username, and password as input, and getting a database connection object as output, specifically using a database management system such as MySQL or PostgreSQL, for secure access authentication.

[0677] Step 2:

[0678] Obtaining financial data

[0679] The server retrieves the necessary financial data, such as revenue data, liability data, asset data, and cash flow information. It uses a database connection object as input and gets the raw data as output. Specifically, it executes an SQL query (e.g., "SELECT FROM financial_data") and converts the resulting data into a Python pandas data frame.

[0680] Step 3:

[0681] Data Formatting

[0682] The server formats the acquired raw data into a format suitable for analysis (for example, CSV format or data frame format). It uses the acquired raw data as input and obtains formatted data as output. Specifically, it uses the pandas function to convert the format, such as "data.to_csv('output.csv')".

[0683] Step 4:

[0684] Sending data to a generative AI model

[0685] The server sends the formatted data to the generative AI model. It uses the formatted data as input and gets the status of the HTTP POST request to the generative AI model as output. Specifically, it converts the data into JSON format, creates an HTTP request, and sends it.

[0686] Step 5:

[0687] Calculation of financial indicators

[0688] The generative AI model calculates financial metrics such as PBR, ROE, and ROA based on the data sent to it. It uses formatted data as input and obtains various financial metrics as output. Specifically, it applies a formula such as "PBR = market_price / book_value."

[0689] Step 6:

[0690] Generate growth strategies and risk management measures

[0691] The generative AI model generates growth strategies and risk management measures based on the results of financial indicator analysis. It uses financial indicator data as input and obtains growth strategies and risk management measures as output. Specifically, it performs scenario analysis and generates proposals for "entering new markets" and "reducing costs."

[0692] Step 7:

[0693] Automatic report generation

[0694] The server automatically generates strategic reports based on insights from the generative AI model. It uses growth strategy and risk management data as input and obtains the generated report as output. Specifically, it creates a PDF report using a LaTeX template.

[0695] Step 8:

[0696] Report format conversion

[0697] The server converts the generated reports into a user-accessible format (PDF or a dedicated web dashboard), using the generated reports as input and obtaining the converted reports as output. Specifically, it uses the Python reportlab library to generate PDFs.

[0698] Step 9:

[0699] Report distribution

[0700] The server sends the created report to the terminals of the company's investor relations officer or management. It uses the converted report as input and gets the delivery status as output. Specifically, it sends the report by email using the SMTP protocol.

[0701] Step 10:

[0702] Review the report

[0703] The terminal has a dedicated dashboard where users can check reports and gain insights. The report URL and dashboard access information are used as input, and the report viewing screen is obtained as output. Specifically, the dashboard is accessed using a web browser.

[0704] Step 11:

[0705] Send Feedback

[0706] The user checks the report contents and submits feedback or additional analysis requests to the server as needed. The feedback contents are used as input and the feedback submission status is obtained as output. The specific operation is to submit the request using a form on the dashboard.

[0707] Step 12:

[0708] Receiving and analyzing feedback

[0709] The server receives feedback and requests for additional analysis from the user, and then resubmits the data to the generative AI model for reanalysis. It uses the feedback as input and obtains the reanalyzed data as output. Specifically, it sends the new data and conditions to the generative AI model via an HTTP POST request.

[0710] Step 13:

[0711] Run a reanalysis

[0712] The generative AI model performs re-analysis based on new conditions and data and returns updated insights to the server. It uses new data and conditions as input and obtains updated insights as output. Specifically, it re-calculates financial indicators and generates strategic recommendations.

[0713] Step 14:

[0714] Regenerating an updated report

[0715] The server regenerates the strategic report based on the updated insights and sends it back to the user terminal. It uses the updated insights as input and obtains the regenerated report as output. Specifically, it creates the report again using the LaTeX template and sends it via the SMTP protocol.

[0716] (Application example 1)

[0717] 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."

[0718] Currently, store managers spend a great deal of time and effort managing inventory, analyzing financial data, and planning sales promotion strategies. However, this often hinders fast and accurate decision-making. It can also lead to inventory shortages or excess inventory, reducing business efficiency. Furthermore, the preparation of reports and processing feedback can be time-consuming, leading to delayed action. It is necessary to improve this situation and enable store managers to make decisions based on fast and accurate information.

[0719] 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.

[0720] In this invention, the server includes a means for aggregating and formatting a company's financial data and inventory data, a means for analyzing the financial data and inventory data using a generative AI model to calculate financial indicators and sales trends, and a means for generating growth strategies, risk management measures, inventory management measures, and sales promotion measures based on the analysis results using the generative AI model. This enables brick-and-mortar store managers to efficiently obtain real-time analysis results of financial data and inventory data and strategic reports based on them.

[0721] "Corporate financial data" is a general term for data that indicates a company's business status and financial condition, such as its revenue, liabilities, assets, and cash flow.

[0722] "Inventory data" is a general term for data related to inventory management, such as the quantity and type of products a company owns, inventory history, and sales prices.

[0723] "Generative AI model" is a general term for artificial intelligence models that automatically analyze specific patterns and trends from large data sets and provide insights into financial indicators, growth strategies, sales promotion measures, and more.

[0724] "Financial indicators" is a general term for statistical values ​​and ratios used to evaluate a company's business condition and financial status, and includes, for example, PBR, ROE, and ROA.

[0725] "Sales trends" is a general term for data that shows sales trends and fluctuations in demand for products and services over a specific period of time.

[0726] A "growth strategy" is a general term for the plans and measures that a company sets in place to achieve sustainable growth, and includes things like entering new markets and cost-cutting measures.

[0727] "Risk management measures" is a general term for measures and policies to predict risks that a company may face and respond to them.

[0728] "Inventory management" is the process of maintaining and efficiently managing the appropriate quantity, type, and storage location of inventory held by a company.

[0729] "Sales promotion measures" is a general term for measures such as advertising, promotions, and pricing strategies implemented to increase product sales.

[0730] A "report" is a document that compiles analysis results, strategic proposals, risk management measures, etc., and is a general term for information provided to management and users.

[0731] "User terminal" is a general term for devices used by managers and users to obtain information, including smart glasses and smartphones.

[0732] "Additional Analysis Request" means a user's request for more detailed analysis based on specific conditions or data.

[0733] This invention relates to a system that enables store managers to efficiently analyze financial and inventory data and automatically generate strategic reports that include growth strategies, risk management measures, and sales promotion measures. The system is configured as follows.

[0734] System Configuration

[0735] Hardware

[0736] 1. Server:

[0737] Acquire, format, and analyze financial and inventory data.

[0738] Responsible for analysis using generative AI models and automatic report generation.

[0739] 2. User Device:

[0740] Smart glasses or smartphone.

[0741] It provides a means for users to review reports and make decisions based on the analysis results.

[0742] software

[0743] 1. Database Management System (DBMS):

[0744] Example: MySQL

[0745] Store and manage financial and inventory data.

[0746] 2. Generative AI Model:

[0747] Example: PyTorch or TensorFlow

[0748] Analyze financial and inventory data to generate necessary metrics and insights.

[0749] 3. Cloud Services:

[0750] Example: AWS Lambda

[0751] Used to efficiently execute server-side processing.

[0752] Specific examples of processing

[0753] 1. Data Collection Phase

[0754] The server retrieves sales data, inventory data, and customer data from the physical store's POS system and inventory management system.

[0755] The data is formatted into a standard format and made suitable for analysis.

[0756] 2. Data analysis phase

[0757] The formatted data is sent to a generative AI model, which analyzes financial indicators, sales trends, and more.

[0758] Based on the analysis results, growth strategies, risk management measures, and inventory management and sales promotion measures are generated.

[0759] 3. Report generation phase

[0760] The server automatically generates strategic reports based on the insights provided by the generative AI model.

[0761] The reports are converted into PDF format and displayed on a dedicated dashboard.

[0762] 4. Information provision phase

[0763] The created report is sent to the user's device (smart glasses or smartphone).

[0764] Users can view reports on a dedicated dashboard and gain real-time insights.

[0765] 5. Feedback and further analysis phase

[0766] Users can review the report and submit requests for additional analysis.

[0767] The server re-analyzes the data through the generative AI model and provides an updated report to the user's device.

[0768] Specific examples

[0769] For example, if a brick-and-mortar store owner is struggling with inventory management, they can use this system to analyze inventory data in real time and display sales trends and optimal stock levels. For example, by entering a prompt such as "Calculate the optimal stock level for the next three months based on last month's sales," the AI ​​will instantly provide the analysis results.

[0770] Using this system, store managers can quickly gain insights and implement effective inventory management and sales promotion strategies.

[0771] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0772] Step 1:

[0773] The server retrieves sales data, inventory data, and customer data from the physical store's POS system and inventory management system. Specifically, the server periodically fetches data through each system's API. Sales information from the POS system and inventory information from the inventory management system are used as input, and data processed into a unified format (e.g., CSV format or data frame format) is obtained as output.

[0774] Step 2:

[0775] The server formats the acquired data into a standard format. Specifically, it converts the acquired sales and inventory data into a data frame using the Python pandas library and cleanses it to maintain consistency and integrity. Raw data (unformatted data) is used as input, and a formatted data frame is obtained as output.

[0776] Step 3:

[0777] The server sends the formatted data to a generative AI model, which analyzes the data and calculates financial indicators and sales trends. Specifically, the data is fed into an AI model built using Python's PyTorch or TensorFlow, and the trained model makes predictions. The formatted data frame is used as input, and the calculated results of financial indicators and sales trends are obtained as output.

[0778] Step 4:

[0779] The server generates growth strategies, risk management measures, and inventory management / sales promotion measures based on the analysis results obtained from the generative AI model. Specifically, a Python script is used to analyze the output of the AI ​​model and document strategic proposals. The output of the AI ​​model is used as input, and growth strategies, risk management measures, and inventory management / sales promotion measures are obtained as output.

[0780] Step 5:

[0781] The server automatically generates strategic reports based on the generated growth strategies, risk management measures, and inventory management and sales promotion measures. Specifically, it creates reports in PDF format using Python's FPDF library. The strategic proposals are used as input, and the PDF report is obtained as output.

[0782] Step 6:

[0783] The server sends the created report to the user's device. Specifically, it sends the report by email using SMTP or uploads it to cloud storage. The input is a PDF report, and the output is either emailed to the user or saved in cloud storage.

[0784] Step 7:

[0785] Users use a dedicated dashboard to check reports and send additional analysis requests. Specifically, they access the dashboard via a web application and enter additional analysis requests. The input is the request entered by the user into the dashboard, and the output is the request sent to the server.

[0786] Step 8:

[0787] The server receives user feedback and requests for additional analysis, and then resubmits the data to the generative AI model for reanalysis. Specifically, the data is fed back into the AI ​​model and reanalyzed based on the new conditions. The user request and existing data are used as input, and updated analysis results are output.

[0788] Step 9:

[0789] The server regenerates the report based on the results of the reanalysis and provides it to the user's device. Specifically, it regenerates the report in PDF format and sends it to the user. The reanalysis results are used as input, and an updated PDF report is obtained as output.

[0790] 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.

[0791] This invention relates to a system that enables companies to efficiently analyze financial data and automatically generate reports including strategies and risk management by combining an emotion engine with a system that can provide more appropriate feedback and requests for additional analysis based on the user's emotions. Below, an embodiment of this system and specific program processing are described in detail.

[0792] Data Collection Phase

[0793] server

[0794] The server accesses the company's financial database to retrieve the necessary financial data, such as revenue, liabilities, assets, cash flow, etc. The data retrieval process involves proper access authentication to ensure data security.

[0795] The acquired data is formatted into a standard format (e.g., CSV or data frame format) and data cleaning is performed.

[0796] Data analysis phase

[0797] server

[0798] The formatted data is fed into a generative AI model, which receives this data and calculates key financial metrics (PBR, ROE, ROA, etc.).

[0799] Based on the analysis results, the generative AI model generates corporate growth strategies (e.g., entering new markets and cost reduction measures) and risk management measures (e.g., measures to reduce liquidity risk and debt management).

[0800] Report generation phase

[0801] server

[0802] The generative AI model delivers insights that automatically generate strategic reports, including explanations and interpretations of financial metrics, suggested growth strategies, and risk management measures.

[0803] The generated reports are converted into PDF format or a dedicated web dashboard, and provided in a format that can be accessed by the company's investor relations personnel and management.

[0804] Information provision phase

[0805] server

[0806] The created report is sent to the devices of the company's IR staff and management via email or cloud services.

[0807] Terminal

[0808] The device has a dedicated dashboard where users can view reports and gain insights.

[0809] Feedback and further analysis phase

[0810] User

[0811] Users (IR personnel or management) review the report contents and send feedback or requests for additional analysis to the server.

[0812] server

[0813] The server receives feedback and requests for additional analysis from users, and sends the data back to the generative AI model for additional analysis.

[0814] The generative AI model reanalyzes based on new conditions and data and provides updated insights to the server.

[0815] server

[0816] The report is updated based on the new insights and sent back to the user's device.

[0817] Emotion engine integration phase

[0818] User terminal

[0819] A user device equipped with an emotion engine recognizes emotions from the user's facial expressions, voice, text input, etc. while the user is viewing a report.

[0820] The emotion engine analyzes the recognized user's emotional data and evaluates their stress level and interests.

[0821] server

[0822] The server optimizes the report display and additional explanations based on the emotion data received from the emotion engine. For example, if the user is feeling stressed, it will automatically provide more detailed explanations and supplementary information.

[0823] Based on the needs indicated by the user's emotional data, specific analysis requests are automatically generated to the generative AI model, expanding the user's options.

[0824] Specific examples

[0825] Case Study: Medium-sized Manufacturing Company Y

[0826] background

[0827] Company Y has experienced a recent increase in revenue and needs to provide accurate and timely information to investors. However, its traditional process required a significant amount of time and effort to analyze financial data and create proposals.

[0828] introduction

[0829] Company Y will introduce this system and upload its financial data to the server. It will also integrate an emotion engine into user devices.

[0830] Processing flow

[0831] The server accesses Company Y's database and aggregates and formats the necessary financial data.

[0832] The server sends the data to a generative AI model, which calculates financial indicators and generates growth strategies and risk management measures.

[0833] The server creates a strategic report based on the generated insights and sends it to the terminal of Company Y's IR officer.

[0834] The user (IR staff) checks the report on the dashboard, and the emotional data recognized by the emotion engine is analyzed, and feedback and additional analysis are automatically optimized.

[0835] result

[0836] Company Y was able to quickly obtain insights and provide reports optimized by the sentiment engine, enabling it to provide effective IR information to investors, which improved communication with investors and increased its reputation in the capital markets.

[0837] The above is a specific embodiment and processing content of this system. By integrating an emotion engine, customization based on the user's emotions becomes possible, realizing the construction of a more effective and user-friendly system.

[0838] The processing flow will be explained below.

[0839] Step 1:

[0840] The server accesses the company's financial database to retrieve the required financial data such as revenue, liabilities, assets, cash flow, etc. The data retrieval process involves proper access authentication and ensures a secure connection.

[0841] Step 2:

[0842] The server formats the acquired financial data into a standard format (e.g., CSV file or data frame format), and this process also involves data cleaning to remove incomplete and duplicate data.

[0843] Step 3:

[0844] The server sends the formatted data to the generative AI model, which then begins analyzing the input data.

[0845] Step 4:

[0846] The generative AI model analyzes the data and calculates key financial metrics (PBR, ROE, ROA, etc.), which are important metrics for understanding a company's financial situation.

[0847] Step 5:

[0848] Based on the analysis results, the generative AI model generates growth strategies (e.g., new market entry, cost reduction measures) and risk management measures (e.g., liquidity risk mitigation, debt management) for the company. At this stage, the AI ​​may also perform multiple scenario analysis.

[0849] Step 6:

[0850] The server automatically generates strategic reports based on the insights provided by the generative AI model, including interpretations of financial indicators, proposed growth strategies, and recommended risk management measures.

[0851] Step 7:

[0852] The server converts the generated reports into PDF format, Excel sheets, dedicated web dashboards, etc., making them accessible to the company's investor relations personnel and management.

[0853] Step 8:

[0854] The server then sends the generated reports to the terminals of the company's investor relations staff and management, and the reports are provided via email or cloud storage.

[0855] Step 9:

[0856] The device is integrated with a dedicated dashboard where users can view generated reports and gain insights into financial performance and strategic proposals.

[0857] Step 10:

[0858] The user device, which is integrated with the emotion engine, recognizes emotions in real time from facial expressions, voice, and input text while the user is reviewing a report, thereby assessing the user's stress level, interest level, etc.

[0859] Step 11:

[0860] Users (IR staff or management) review the report content and AI proposals, and provide feedback or request additional analysis based on the emotional data at the time. If the emotion engine is feeling stressed, it will optimize the report by adding a simple explanation or providing detailed data.

[0861] Step 12:

[0862] The server receives feedback and requests for additional analysis from the user and sends the data to the generative AI model again. The AI ​​model is given new analysis scenarios and conditions, and re-analysis is performed.

[0863] Step 13:

[0864] The generative AI model performs additional analysis and generates new insights, including specific metrics that users have expressed interest in and new strategic recommendations.

[0865] Step 14:

[0866] The server updates the report based on the new insights and sends it back to the user's device, where the latest report is displayed in real time on the dashboard.

[0867] These are the specific processing steps of this system. At each step, the server, generative AI model, terminal, and user play their respective roles to achieve efficient and accurate analysis and reporting of financial data. The integration of an emotion engine enables customization based on user emotions, resulting in a more user-friendly system.

[0868] Example 2

[0869] 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."

[0870] Analyzing financial information and generating reports in companies requires a great deal of time and effort using conventional methods. Furthermore, if the generated reports do not reflect the specific needs and feelings of users, effective decision-making becomes difficult. Therefore, there is a need for efficient analysis of financial information, automatic generation of highly accurate reports, and provision of reports whose content is optimized based on user feelings.

[0871] The specification processing by the specification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for aggregating and formatting a company's financial information, means for analyzing the financial information using a generative AI model and calculating financial indicators, means for generating a growth strategy and a risk management measure based on the analysis results using the generative AI model, means for automatically generating a strategic report based on the generated growth strategy and the risk management measure, means for providing the report to a user terminal, means for receiving feedback and additional analysis requests from a user and performing reanalysis, and means for collecting and analyzing user emotion data using an emotion engine and optimizing the report content. This enables efficient analysis of financial information, rapid generation of reports, and provision of optimal content based on the user's emotions.

[0872] "Financial information" refers to data that shows a company's financial status, such as its revenue, liabilities, assets, and cash flow.

[0873] A "generative AI model" is an artificial intelligence model that uses machine learning and deep learning technologies to analyze financial information and calculate financial indicators.

[0874] "Financial indicators" are indicators used to quantitatively evaluate a company's financial condition, and include, for example, PBR (price-to-book ratio), ROE (return on equity), and ROA (return on assets).

[0875] A "growth strategy" is a general term for the plans and measures that a company implements in order to achieve sustainable growth.

[0876] "Risk management measures" are specific policies and measures to assess the risks that a company may face and reduce or manage them.

[0877] A "strategic report" is a document that summarizes financial indicators, growth strategies, and risk management measures generated based on financial information, and compiles proposals and views on management strategies.

[0878] "User terminal" refers to a device, such as a computer or mobile device, used by a company's investor relations personnel or management to view reports and submit feedback.

[0879] "Feedback and further analysis requests" are comments provided by users regarding the contents of a report or requests for further data analysis.

[0880] An "emotion engine" is a technology that recognizes and analyzes emotions from a user's facial expressions, voice, text input, etc.

[0881] "Emotion data" refers to data that indicates the user's emotional state as recognized and analyzed by the emotion engine.

[0882] Optimization is the adjustment and improvement of system or process parameters to efficiently achieve a specific objective.

[0883] MODE FOR CARRYING OUT THE INVENTION

[0884] This invention relates to a system that enables companies to efficiently analyze financial information and automatically generate reports including strategies and risk management, by combining an emotion engine with a system that can provide more appropriate feedback and requests for additional analysis based on the user's emotions. Below, an embodiment of this system and specific program processing are described in detail.

[0885] Data Collection Phase

[0886] server

[0887] The server accesses the company's financial database and retrieves the required financial information such as revenue, liabilities, assets, cash flow, etc. The data retrieval process involves authentication using an API key and / or authentication token for database connection.

[0888] The server formats the acquired data into a standard format (e.g., CSV or data frame format) using the Python Pandas library.

[0889] Furthermore, missing values ​​and outliers are handled by filling in the missing values ​​with the mean value and excluding outliers.

[0890] Data analysis phase

[0891] server

[0892] The server inputs the formatted financial information into the generative AI model, sending the data to the generative AI model via the API as a POST request.

[0893] A prompt sentence is generated and fed into the generative AI model along with financial information retrieved from the database. An example prompt sentence is as follows:

[0894] "Please suggest the optimal growth strategy based on the company's revenue data."

[0895] The generative AI model analyzes input data and calculates key financial metrics (PBR, ROE, ROA, etc.) based on pre-defined formulas and algorithms.

[0896] The generative AI model generates corporate growth strategies and risk management measures based on the results of analyzing financial indicators.

[0897] Report generation phase

[0898] server

[0899] The server automatically generates strategic reports based on the insights returned by the generative AI model, including explanations and interpretations of financial metrics, suggested growth strategies, and risk management measures.

[0900] A template engine (e.g., Jinja2) is used to generate reports and output formats such as HTML and PDF.

[0901] Convert the generated report into PDF format or a dedicated web dashboard. For example, use a PDF generation tool to convert an HTML template into a PDF.

[0902] Information provision phase

[0903] server

[0904] The server then sends the created reports to the devices of the company's investor relations staff or management. In some cases, the reports are sent as PDF attachments via email, or a link to a cloud service is shared.

[0905] Terminal

[0906] The device has a dedicated dashboard where users can view reports and gain various insights.

[0907] Feedback and further analysis phase

[0908] User

[0909] Users (IR staff and management) check the contents of the report and send feedback or requests for additional analysis to the server. The dashboard provides input fields for feedback forms and requests for additional analysis.

[0910] server

[0911] The server receives feedback and requests for additional analysis from the user, sends the data to the generative AI model again for additional analysis, and creates a new prompt sentence and inputs it to the generative AI model.

[0912] It reanalyzes the data based on new conditions and data, and provides updated insights to the server.

[0913] The server updates the report based on the new insights and sends it back to the user's device.

[0914] Emotion engine integration phase

[0915] User terminal

[0916] The user device equipped with the emotion engine recognizes emotions from the user's facial expressions, voice, text input, etc. while the user is viewing a report. This requires a device equipped with a camera and microphone.

[0917] The emotion engine analyzes the recognized user's emotional data and evaluates their stress level and interests.

[0918] server

[0919] The server optimizes the report display and additional explanations based on the emotion data received from the emotion engine. For example, if the user is feeling stressed, it will automatically provide more detailed explanations and supplementary information.

[0920] Based on the needs indicated by the user's emotional data, specific analysis requests are automatically generated to the generative AI model, expanding the user's options.

[0921] Examples and prompts

[0922] Examples:

[0923] Case Study: Medium-sized Manufacturing Company Y

[0924] With the recent increase in revenue, Company Y needs to provide accurate and prompt information to investors. However, in the conventional process, analyzing financial information and creating proposals required a great deal of time and effort. Company Y will introduce this system and upload its financial information to a server. It will also integrate an emotion engine into user devices.

[0925] Process flow:

[0926] The server accesses Company Y's database and aggregates and formats the necessary financial information.

[0927] The server sends the data to a generative AI model, which calculates financial indicators and generates growth strategies and risk management measures.

[0928] The server creates a strategic report based on the generated insights and sends it to the terminal of Company Y's IR officer.

[0929] The user (IR staff) checks the report on the dashboard, and the emotional data recognized by the emotion engine is analyzed, and feedback and additional analysis are automatically optimized.

[0930] Example prompt sentence:

[0931] "Based on Company Y's financial data, please calculate the latest financial indicators (PBR, ROE, ROA, etc.) and propose growth strategies and risk management measures. Also, please use an emotion engine to optimize the report content based on user feedback."

[0932] The above is a specific embodiment and processing content of this system. By integrating an emotion engine, customization based on the user's emotions becomes possible, realizing the construction of a more effective and user-friendly system.

[0933] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0934] Program processing steps

[0935] Data Collection Phase

[0936] Step 1:

[0937] server

[0938] The server accesses the company's financial database and retrieves the required financial information such as revenue, liabilities, assets, cash flow, etc. The input is the database authentication information and the output is the retrieved financial information.

[0939] Specifically, it uses an API key or authentication token for database connection to execute an SQL query to retrieve data.

[0940] Step 2:

[0941] server

[0942] The server formats the financial information it retrieves into a standard format (CSV or data frame). The input is the raw data it retrieves, and the output is the formatted data.

[0943] For example, use Python's Pandas library to convert the data into a data frame, organize the necessary columns, and convert data types.

[0944] Step 3:

[0945] server

[0946] The server cleans the financial information: the input is formatted data, and the output is cleaned data.

[0947] Specifically, the process involves filling in missing values ​​with the average value and excluding outliers.

[0948] Data analysis phase

[0949] Step 4:

[0950] server

[0951] The server sends the formatted and cleaned financial information to a generative AI model, whose inputs are the cleaned data and generated prompts, and whose output is financial metrics and insights.

[0952] Specifically, the data is sent to the generative AI model via an API as a POST request. An example prompt might be: "Based on the company's revenue data, please propose the optimal growth strategy."

[0953] Step 5:

[0954] Generative AI Models

[0955] The generative AI model analyzes input data and calculates key financial indicators (PBR, ROE, ROA, etc.) The input is the cleaned data and prompt statements, and the output is the calculated financial indicators.

[0956] Financial indicators are calculated using pre-defined formulas and algorithms.

[0957] Step 6:

[0958] Generative AI Models

[0959] The generative AI model generates a company's growth strategy and risk management measures from the results of analyzing financial indicators. The input is the calculated financial indicators, and the output is the generated growth strategy and risk management measures.

[0960] Specifically, the generated text data is inserted into a report template.

[0961] Report generation phase

[0962] Step 7:

[0963] server

[0964] The server automatically generates strategic reports based on the insights returned by the generative AI model. The input is the generated growth strategy and risk management measures, and the output is the completed report.

[0965] A template engine (e.g., Jinja2) is used to generate reports and convert them into formats such as HTML and PDF.

[0966] Step 8:

[0967] server

[0968] The server converts the generated report into PDF format or a dedicated web dashboard. The input is the generated report and the output is the converted file format.

[0969] As a specific operation, for example, a PDF generation tool is used to convert the HTML template into a PDF.

[0970] Information provision phase

[0971] Step 9:

[0972] server

[0973] The server then sends the created report to the terminals of the company's IR staff and management. The input is a report in PDF format or web dashboard format, and the output is a report sent to the user's terminal.

[0974] Specific actions include sending a PDF as an attachment via email or sharing a link to a cloud service.

[0975] Step 10:

[0976] Terminal

[0977] The terminal has a dedicated dashboard where users can check reports. The input is a report in PDF format or web dashboard format, and the output is the checked report.

[0978] You can access reports and gain various insights through the dashboard.

[0979] Feedback and further analysis phase

[0980] Step 11:

[0981] User

[0982] Users (IR staff or management) check the contents of the report and send feedback or requests for additional analysis to the server. The input is feedback on the report or requests for additional analysis, and the output is the feedback sent to the server.

[0983] Provide a feedback form or input field for additional analysis requests on the dashboard.

[0984] Step 12:

[0985] server

[0986] The server receives feedback and requests for additional analysis from users and sends the data to the generative AI model again for further analysis. The input is the received feedback and requests for additional analysis, and the output is the reanalyzed insights.

[0987] Create new prompts and feed them into the generative AI model, which then reanalyzes them and generates new insights.

[0988] Step 13:

[0989] server

[0990] The server updates the report based on the new insights and sends it back to the user's device. The input is the reanalyzed insights and the updated report, and the output is the updated report.

[0991] Allow users to view updated reports.

[0992] Emotion engine integration phase

[0993] Step 14:

[0994] User terminal

[0995] A user device equipped with an emotion engine recognizes emotions from the user's facial expressions, voice, text input, etc. while the user is viewing a report. The input is the user's facial expressions, voice, and text data, and the output is emotion data.

[0996] This requires a device with a camera and microphone.

[0997] Step 15:

[0998] server

[0999] The server optimizes the display content of the report and additional explanations based on the emotion data received from the emotion engine. The input is emotion data, and the output is an optimized report.

[1000] If the user is feeling stressed, more detailed explanations and supplementary information will be automatically provided.

[1001] Step 16:

[1002] server

[1003] The server automatically generates specific analysis requests to the generative AI model based on the needs indicated by the user's emotional data, expanding the user's options. The input is the emotional data and the generated prompt, and the output is the additional analysis results.

[1004] Specifically, it generates a new prompt sentence based on the emotional data and sends that prompt sentence to the generative AI model.

[1005] The above is the specific processing flow of this system and the operation at each step. By clearly explaining the specific operations and data processing methods, the details of the system will become clearer.

[1006] (Application example 2)

[1007] 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."

[1008] Traditional financial data analysis systems required a great deal of time and effort for companies to quickly and efficiently understand their financial situation and make strategic decisions. Furthermore, they lacked feedback based on user emotions and intuition, making it difficult for users to gain a deeper understanding of reports and appropriately request additional analysis. Furthermore, in brick-and-mortar store operations, understanding the emotions of staff and customers in real time and providing optimal service was a challenge.

[1009] 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.

[1010] In this invention, the server includes a means for aggregating and formatting a company's financial data, a means for analyzing the financial data using a generative AI model to calculate financial indicators, and a means for generating growth strategies and risk management measures. This enables companies to gain quick and accurate insights. Furthermore, the user terminal is equipped with an emotion engine, providing a means for recognizing user emotions and optimizing report content based on the recognition results. Furthermore, the system includes a means for displaying reports via a dedicated dashboard and automatically optimizing report content based on the emotion recognition results. This enables efficient user feedback and highly accurate requests for additional analysis, enabling optimal service provision even in brick-and-mortar store operations.

[1011] "Financial data" refers to financial information held by a company, such as revenues, liabilities, assets, and cash flow.

[1012] A "generative AI model" is an artificial intelligence model that analyzes input data and automatically calculates financial indicators, generates growth strategies, and generates risk management measures.

[1013] A "user terminal" is a device used to check reports, send feedback, and provide information based on emotion recognition results.

[1014] An "emotion engine" is a technology for recognizing and analyzing emotions from a user's facial expressions, voice, text input, etc.

[1015] "Financial indicators" are indicators used to evaluate a company's financial condition and performance, and include PBR, ROE, ROA, etc.

[1016] A "growth strategy" is a plan or policy for a company to achieve sustainable growth.

[1017] "Risk management measures" are strategies and measures used to mitigate or avoid risks that a company may face.

[1018] A "strategic report" is a document that includes explanations and interpretations of financial indicators, proposed growth strategies, and risk management measures.

[1019] A "dedicated dashboard" is an interface that visually displays generated reports and is easily accessible to users.

[1020] "Feedback" refers to the reactions and opinions users provide to reports.

[1021] An "additional analysis request" is an action in which a user requests the server to perform further analysis based on a report or analysis result.

[1022] This section describes a specific system for implementing this invention. The system aggregates and formats a company's financial data, analyzes it using a generative AI model, and calculates various financial indicators. Furthermore, it generates growth strategies and risk management measures based on the analysis results, and automatically generates strategic reports. Additionally, it can recognize user emotions using a user device equipped with an emotion engine and optimize the content of the report.

[1023] Data collection and formatting

[1024] The server accesses the company's financial database and retrieves the necessary financial data, such as revenue, liabilities, assets, cash flow, etc. The data is retrieved with appropriate access authentication and then formatted into a standard format. During this process, the data is also cleaned to remove missing or outlier values.

[1025] Data analysis

[1026] The server inputs the formatted financial data into a generative AI model to calculate key financial indicators (e.g., PBR, ROE, ROA, etc.). This model can use OpenAI's GPT-4 or Google's BERT. Based on the analysis results, the server generates insights that suggest growth strategies and risk management measures for the company.

[1027] report generation

[1028] Based on the insights generated, strategic reports are automatically generated, including explanations and interpretations of financial indicators, proposed growth strategies, and risk management measures, and can be viewed in PDF format or on a dedicated web dashboard.

[1029] Input and Feedback

[1030] The server sends automatically generated reports to the terminals of the company's investor relations personnel and management via email or cloud services. Users can use a dashboard to check the reports and send feedback or requests for additional analysis. The server receives this feedback and requests and performs reanalysis.

[1031] Emotion Engine Integration

[1032] The emotion engine installed on the user's device recognizes emotions from the user's facial expressions, voice, and text input while viewing the report. For example, it uses Affectiva's SDK or Microsoft's Emotion API. This emotion data is sent to the server to optimize the report content. For example, if the user is feeling stressed, it will provide more detailed explanations and additional information.

[1033] Specific examples

[1034] For example, a mid-sized manufacturing company might prompt their generative AI model with the following:

[1035] Prompt: "Analyze store sales data and generate future growth and risk management strategies. For example, which products are selling the best and which products are likely to be low in stock?"

[1036] Based on this prompt, the generative AI model analyzes financial data and proposes growth strategies and risk management measures. Based on these insights, a strategic report is generated. This report is optimized according to the user's emotions through an emotion engine, making it more user-friendly and providing useful information.

[1037] This will enable companies to analyze financial data quickly and accurately and make strategic decisions, while also enabling brick-and-mortar stores to provide optimal services that are tailored to the emotions of staff and customers.

[1038] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1039] Step 1:

[1040] The server accesses the company's financial database to retrieve the required financial data, such as revenue, liabilities, assets, cash flow, etc. The input is the authentication information of the company's financial database, and the output is the retrieved financial data. This data retrieval process is subject to appropriate access authentication to ensure data security.

[1041] Step 2:

[1042] The server formats the acquired financial data into a standard format (CSV or data frame format) and performs data cleaning. The input is the acquired financial data, and the output is the formatted and cleaned financial data. During this process, missing values ​​and outliers are processed and the data is formatted in a format suitable for analysis.

[1043] Step 3:

[1044] The server inputs the formatted financial data into a generative AI model. The generative AI model calculates key financial indicators (PBR, ROE, ROA, etc.). The input is the formatted financial data, and the output is the calculated financial indicators. The generative AI model (e.g., OpenAI GPT-4) analyzes the financial data and generates the required indicators.

[1045] Step 4:

[1046] The server automatically generates growth strategies and risk management measures based on the analysis results of the generative AI model. The input is the calculated financial indicators, and the output is the growth strategies and risk management measures. In this step, a strategic action plan for the company is created based on the analysis results.

[1047] Step 5:

[1048] The server automatically generates a strategic report based on the generated growth strategy and risk management measures. The input is data on growth strategies and risk management measures, and the output is a strategic report (e.g., in PDF format or data for display on a dedicated web dashboard). This report includes explanations and interpretations of financial indicators, proposed growth strategies, and risk management measures.

[1049] Step 6:

[1050] The server sends the automatically generated report to the terminals of the company's IR personnel and management via email or cloud services. The input is the strategic report, and the output is the sent report. The report can then be viewed on the user's terminal.

[1051] Step 7:

[1052] Users can use a dedicated dashboard to check reports and, if necessary, send feedback or requests for additional analysis to the server. The input is the user's feedback or requests for additional analysis, and the output is re-requested analysis data. Each item in the report is visually displayed on the dashboard.

[1053] Step 8:

[1054] The server receives feedback and requests for additional analysis from users and sends the data back to the generative AI model to perform the additional analysis. The input is the feedback and requests for additional analysis, and the output is the results of the reanalysis. New insights are generated and the report is updated.

[1055] Step 9:

[1056] The emotion engine installed on the user's device recognizes emotions from the user's facial expressions, voice, text input, etc. while viewing the report, and sends that data to the server. The input is the user's emotion data, and the output is the emotion recognition results. The data is analyzed by the emotion engine (e.g., Affectiva SDK).

[1057] Step 10:

[1058] The server optimizes the report content based on the emotion data received from the emotion engine. The input is the emotion recognition result, and the output is the optimized report. If the user is feeling stressed, the report is automatically updated to provide more detailed explanations and supplementary information.

[1059] Specific examples

[1060] For example, a mid-sized manufacturing company might prompt their generative AI model with the following:

[1061] "Analyze store sales data and generate future growth and risk management strategies. For example, tell me which products are selling the best and which products are likely to be low in stock."

[1062] 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.

[1063] 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.

[1064] 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.

[1065] [Third embodiment]

[1066] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1067] 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.

[1068] 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).

[1069] 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.

[1070] 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.

[1071] 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).

[1072] 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.

[1073] 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.

[1074] 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.

[1075] 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.

[1076] 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.

[1077] 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."

[1078] This invention relates to a system that enables companies to efficiently analyze financial data and automatically generate reports that include strategies and risk management. An embodiment of this system and specific program processing will be described in detail below.

[1079] Data Collection Phase

[1080] server

[1081] The server accesses the company's financial database to obtain the necessary revenue, liability, asset, and cash flow information, connecting to authorized databases via access authentication.

[1082] The acquired data is formatted into a standard format, such as CSV or data frame, making it suitable for analysis.

[1083] Data analysis phase

[1084] server

[1085] The formatted data is sent from the server to the generative AI model, which analyzes it and calculates each financial indicator.

[1086] Generative AI Models

[1087] Based on the data received, the generative AI model calculates key financial indicators such as PBR (Price to Book Ratio), ROE (Return on Equity), and ROA (Return on Assets).

[1088] Furthermore, based on the analysis results, the generative AI model generates corporate growth strategies (e.g., entry into new markets and cost reduction measures) and risk management measures (e.g., measures to reduce liquidity risk and debt management).

[1089] Report generation phase

[1090] server

[1091] The server automatically generates strategic reports based on insights provided by the generative AI model, including explanations and interpretations of financial metrics, suggested growth strategies, and risk management measures.

[1092] Convert the generated reports into a format that can be accessed by the company's investor relations personnel and management (e.g., PDF format or a dedicated web dashboard).

[1093] Information provision phase

[1094] server

[1095] The reports are then sent to the devices of the company's IR staff and management, often via email or cloud services.

[1096] Terminal

[1097] The device has a dedicated dashboard where users can view reports and gain insights.

[1098] Feedback and further analysis phase

[1099] User

[1100] Users (IR staff and management) review the report and, if necessary, can send feedback to the server and request additional analysis.

[1101] server

[1102] The server receives feedback and requests for additional analysis from users, sends the data to the generative AI model again, and performs additional analysis.

[1103] Generative AI Models

[1104] The generative AI model performs reanalysis based on new conditions and data and sends updated insights back to the server.

[1105] server

[1106] The server regenerates the report based on the updated insights and sends it to the user terminal.

[1107] Specific examples

[1108] Case Study: Medium-sized Manufacturing Company X

[1109] background

[1110] As Company X's revenues increase, it needs to provide accurate and timely information to investors, but analyzing financial data and compiling strategic proposals takes a lot of time and effort.

[1111] introduction

[1112] Company X introduces this system and uploads its financial data to the server.

[1113] Processing flow

[1114] The server accesses Company X's database and aggregates and formats the necessary financial data.

[1115] The server sends the data to a generative AI model, which calculates financial indicators and generates growth strategies and risk management measures.

[1116] Based on the generated insights, the server creates a strategic report and sends it to the terminal of Company X's IR officer.

[1117] The user (IR officer) checks the report on the dashboard and submits additional analysis requests to the server.

[1118] The server receives the request, performs the reanalysis, and provides an updated report to the user's terminal.

[1119] result

[1120] Company X was able to quickly obtain insights and provide effective IR information to investors, which improved communication with investors and increased its reputation in the capital market.

[1121] The above is a detailed description of the system's implementation and processing. This invention can help companies use AI to efficiently analyze financial data and quickly provide high-quality IR information.

[1122] The processing flow will be explained below.

[1123] Step 1:

[1124] The server accesses the company's financial database to retrieve the necessary financial data such as revenue, liabilities, assets, cash flow, etc. This data retrieval process involves proper access authentication to ensure data security.

[1125] Step 2:

[1126] The server formats the acquired financial data into a standard format (e.g., CSV file or data frame format). Data cleaning is also performed at this stage to remove incomplete or duplicate data.

[1127] Step 3:

[1128] The server inputs the formatted data into the generative AI model, which receives the data and begins analyzing it.

[1129] Step 4:

[1130] The generative AI model analyzes the input data and calculates key financial indicators, such as PBR (Price to Book Ratio), ROE (Return on Equity), and ROA (Return on Assets).

[1131] Step 5:

[1132] Based on the analysis results, the generative AI model generates corporate growth strategies (e.g., entry into new markets and cost reduction measures) and risk management measures (e.g., measures to reduce liquidity risk and debt management).

[1133] Step 6:

[1134] The server automatically generates strategic reports based on insights provided by the generative AI model, including explanations and interpretations of financial metrics, suggested growth strategies, and risk management measures.

[1135] Step 7:

[1136] The server formats the generated reports into a format (e.g., PDF or dedicated web dashboard) that can be accessed by the company's investor relations personnel and management.

[1137] Step 8:

[1138] The server then sends the generated reports to the terminals of the company's IR staff and management via email or cloud services.

[1139] Step 9:

[1140] The device has a dedicated dashboard where users can view reports and gain insights.

[1141] Step 10:

[1142] Users (IR personnel or management) review the report and, if necessary, send feedback to the server and request additional analysis.

[1143] Step 11:

[1144] The server receives feedback and requests for additional analysis from users, and sends the data back to the generative AI model for additional analysis.

[1145] Step 12:

[1146] The generative AI model performs reanalysis based on new conditions and data and provides updated insights to the server.

[1147] Step 13:

[1148] The server updates the report based on the new insights and sends it back to the user's device.

[1149] These are the specific processing steps of this system. At each step, the server, generative AI model, terminal, and user play their respective roles to achieve efficient and accurate analysis and reporting of financial data.

[1150] Example 1

[1151] 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."

[1152] In today's business environment, it is important for companies to efficiently analyze financial data and quickly provide high-quality reports, including those for strategy and risk management. However, traditional methods require a significant amount of time and effort to aggregate data, analyze it, and create reports, straining corporate resources. In particular, it is difficult to quickly and accurately handle large amounts of financial data and obtain appropriate insights to support strategic decision-making.

[1153] 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.

[1154] In this invention, the server includes means for aggregating and formatting a company's financial data, means for analyzing the financial data using a generative AI model to calculate financial indicators, means for generating a growth strategy and risk management measures based on the analysis results using the generative AI model, means for providing the generated report to a user terminal via email or a cloud service, means for displaying the report via a dedicated dashboard, and means for receiving feedback and requests for additional analysis from users and performing reanalysis, thereby enabling companies to efficiently analyze financial data and quickly provide high-quality reports that support strategic decision-making.

[1155] "Corporate financial data" refers to financial information that a company generates and holds in the course of its economic activities, and includes revenue data, liability data, asset data, cash flow information, and the like.

[1156] "Aggregation and formatting means" refers to methods or tools used to convert data from different formats or sources into a unified format suitable for analysis.

[1157] A "generative AI model" refers to a system that uses artificial intelligence technology to automatically perform complex calculations and analyses based on input data.

[1158] "Financial indicators" refer to numerical values ​​calculated using formulas to evaluate a company's financial condition and performance, and include, for example, PBR (price-to-book ratio), ROE (return on equity), and ROA (return on assets).

[1159] A "growth strategy" refers to the plans and policies that a company implements in order to achieve sustainable development, and includes measures such as entering new markets and cost-cutting measures.

[1160] "Risk management measures" refer to the plans and measures adopted to identify, assess and mitigate potential risks faced by an entity, including liquidity risk mitigation measures and debt management.

[1161] A "strategic report" refers to a document in which a company summarizes its future strategies and risk management based on the analysis of financial data.

[1162] "Means of providing via email or cloud service" refers to a method of using an email system or cloud service to quickly and securely distribute the generated report to the user.

[1163] A "dedicated dashboard" refers to a specialized interface, typically provided as a web application, that allows users to view reports and gain insights.

[1164] "Means for receiving feedback or requests for additional analysis and performing re-analysis" refers to methods or tools for receiving user opinions or requests and conducting additional data analysis based on those opinions or requests to generate new insights.

[1165] The present invention relates to a system that enables a company to efficiently analyze financial data and automatically generate reports that include strategies and risk management. Specific embodiments of this system will be described in detail below.

[1166] Data Collection Phase

[1167] server

[1168] The server accesses the company's financial database to retrieve the necessary revenue, liability, asset, and cash flow information. It connects to the database through secure access authentication using a database management system such as MySQL or PostgreSQL. The retrieved data is then formatted into CSV or dataframe format using the Python pandas library.

[1169] Data analysis phase

[1170] server

[1171] The formatted data is sent from the server to the generative AI model using an HTTP POST request to send the data to the AI ​​model's endpoint.

[1172] Generative AI Models

[1173] Based on the data it receives, the generative AI model calculates financial indicators such as PBR (Price to Book Ratio), ROE (Return on Equity), and ROA (Return on Assets). Specifically, it uses a formula such as "PBR = market_price / book_value." It also performs scenario-based analysis to generate growth strategies (e.g., new market entry, cost reduction measures) and risk management measures (e.g., liquidity risk mitigation measures, debt management).

[1174] Report generation phase

[1175] server

[1176] The server automatically generates strategic reports in PDF format using LaTeX templates based on insights from the generative AI model. The reports include explanations and interpretations of financial metrics, proposed growth strategies, and risk management measures. The generated reports are converted to PDF format using the Python reportlab library.

[1177] Information provision phase

[1178] server

[1179] The created report is sent to the company's IR personnel or management via email or cloud services (e.g., AWS S3 or Google Drive).

[1180] Terminal

[1181] The device has a dedicated dashboard where users can view reports and gain insights, and a dedicated web application allows users to access the dashboard from a browser and view the report contents.

[1182] Feedback and further analysis phase

[1183] User

[1184] Users (IR staff and management) review the report and submit feedback or requests for additional analysis to the server as needed. These requests are sent using a feedback form on the dashboard.

[1185] server

[1186] The server receives feedback and requests for additional analysis from users, and then sends the data to the generative AI model again to perform reanalysis.

[1187] Generative AI Models

[1188] The generative AI model performs reanalysis based on new conditions and data and returns updated insights to the server.

[1189] server

[1190] The server regenerates strategic reports based on the updated insights and sends them back to the user's device, allowing businesses to continuously obtain the latest information and strategic proposals.

[1191] Examples of prompt statements

[1192] "Please calculate financial indicators such as PBR, ROE, and ROA based on the company's financial data for the first quarter of fiscal year 2022. Also, please propose growth strategies such as entering new markets and cost reduction measures, as well as risk management measures such as measures to reduce liquidity risk and debt management."

[1193] This invention enables companies to use AI to efficiently analyze financial data and quickly provide high-quality IR information.

[1194] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1195] Step 1:

[1196] Database Connection

[1197] The server connects to the company's financial database, taking the database URL, username, and password as input, and getting a database connection object as output, specifically using a database management system such as MySQL or PostgreSQL, for secure access authentication.

[1198] Step 2:

[1199] Obtaining financial data

[1200] The server retrieves the necessary financial data, such as revenue data, liability data, asset data, and cash flow information. It uses a database connection object as input and gets the raw data as output. Specifically, it executes an SQL query (e.g., "SELECT FROM financial_data") and converts the resulting data into a Python pandas data frame.

[1201] Step 3:

[1202] Data Formatting

[1203] The server formats the acquired raw data into a format suitable for analysis (for example, CSV format or data frame format). It uses the acquired raw data as input and obtains formatted data as output. Specifically, it uses the pandas function to convert the format, such as "data.to_csv('output.csv')".

[1204] Step 4:

[1205] Sending data to a generative AI model

[1206] The server sends the formatted data to the generative AI model. It uses the formatted data as input and gets the status of the HTTP POST request to the generative AI model as output. Specifically, it converts the data into JSON format, creates an HTTP request, and sends it.

[1207] Step 5:

[1208] Calculation of financial indicators

[1209] The generative AI model calculates financial metrics such as PBR, ROE, and ROA based on the data sent to it. It uses formatted data as input and obtains various financial metrics as output. Specifically, it applies a formula such as "PBR = market_price / book_value."

[1210] Step 6:

[1211] Generate growth strategies and risk management measures

[1212] The generative AI model generates growth strategies and risk management measures based on the results of financial indicator analysis. It uses financial indicator data as input and obtains growth strategies and risk management measures as output. Specifically, it performs scenario analysis and generates proposals for "entering new markets" and "reducing costs."

[1213] Step 7:

[1214] Automatic report generation

[1215] The server automatically generates strategic reports based on insights from the generative AI model. It uses growth strategy and risk management data as input and obtains the generated report as output. Specifically, it creates a PDF report using a LaTeX template.

[1216] Step 8:

[1217] Report format conversion

[1218] The server converts the generated reports into a user-accessible format (PDF or a dedicated web dashboard), using the generated reports as input and obtaining the converted reports as output. Specifically, it uses the Python reportlab library to generate PDFs.

[1219] Step 9:

[1220] Report distribution

[1221] The server sends the created report to the terminals of the company's investor relations officer or management. It uses the converted report as input and gets the delivery status as output. Specifically, it sends the report by email using the SMTP protocol.

[1222] Step 10:

[1223] Review the report

[1224] The terminal has a dedicated dashboard where users can check reports and gain insights. The report URL and dashboard access information are used as input, and the report viewing screen is obtained as output. Specifically, the dashboard is accessed using a web browser.

[1225] Step 11:

[1226] Send Feedback

[1227] The user checks the report contents and submits feedback or additional analysis requests to the server as needed. The feedback contents are used as input and the feedback submission status is obtained as output. The specific operation is to submit the request using a form on the dashboard.

[1228] Step 12:

[1229] Receiving and analyzing feedback

[1230] The server receives feedback and requests for additional analysis from the user, and then resubmits the data to the generative AI model for reanalysis. It uses the feedback as input and obtains the reanalyzed data as output. Specifically, it sends the new data and conditions to the generative AI model via an HTTP POST request.

[1231] Step 13:

[1232] Run a reanalysis

[1233] The generative AI model performs re-analysis based on new conditions and data and returns updated insights to the server. It uses new data and conditions as input and obtains updated insights as output. Specifically, it re-calculates financial indicators and generates strategic recommendations.

[1234] Step 14:

[1235] Regenerating an updated report

[1236] The server regenerates the strategic report based on the updated insights and sends it back to the user terminal. It uses the updated insights as input and obtains the regenerated report as output. Specifically, it creates the report again using the LaTeX template and sends it via the SMTP protocol.

[1237] (Application example 1)

[1238] 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."

[1239] Currently, store managers spend a great deal of time and effort managing inventory, analyzing financial data, and planning sales promotion strategies. However, this often hinders fast and accurate decision-making. It can also lead to inventory shortages or excess inventory, reducing business efficiency. Furthermore, the preparation of reports and processing feedback can be time-consuming, leading to delayed action. It is necessary to improve this situation and enable store managers to make decisions based on fast and accurate information.

[1240] 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.

[1241] In this invention, the server includes a means for aggregating and formatting a company's financial data and inventory data, a means for analyzing the financial data and inventory data using a generative AI model to calculate financial indicators and sales trends, and a means for generating growth strategies, risk management measures, inventory management measures, and sales promotion measures based on the analysis results using the generative AI model. This enables brick-and-mortar store managers to efficiently obtain real-time analysis results of financial data and inventory data and strategic reports based on them.

[1242] "Corporate financial data" is a general term for data that indicates a company's business status and financial condition, such as its revenue, liabilities, assets, and cash flow.

[1243] "Inventory data" is a general term for data related to inventory management, such as the quantity and type of products a company owns, inventory history, and sales prices.

[1244] "Generative AI model" is a general term for artificial intelligence models that automatically analyze specific patterns and trends from large data sets and provide insights into financial indicators, growth strategies, sales promotion measures, and more.

[1245] "Financial indicators" is a general term for statistical values ​​and ratios used to evaluate a company's business condition and financial status, and includes, for example, PBR, ROE, and ROA.

[1246] "Sales trends" is a general term for data that shows sales trends and fluctuations in demand for products and services over a specific period of time.

[1247] A "growth strategy" is a general term for the plans and measures that a company sets in place to achieve sustainable growth, and includes things like entering new markets and cost-cutting measures.

[1248] "Risk management measures" is a general term for measures and policies to predict risks that a company may face and respond to them.

[1249] "Inventory management" is the process of maintaining and efficiently managing the appropriate quantity, type, and storage location of inventory held by a company.

[1250] "Sales promotion measures" is a general term for measures such as advertising, promotions, and pricing strategies implemented to increase product sales.

[1251] A "report" is a document that compiles analysis results, strategic proposals, risk management measures, etc., and is a general term for information provided to management and users.

[1252] "User terminal" is a general term for devices used by managers and users to obtain information, including smart glasses and smartphones.

[1253] "Additional Analysis Request" means a user's request for more detailed analysis based on specific conditions or data.

[1254] This invention relates to a system that enables store managers to efficiently analyze financial and inventory data and automatically generate strategic reports that include growth strategies, risk management measures, and sales promotion measures. The system is configured as follows.

[1255] System Configuration

[1256] Hardware

[1257] 1. Server:

[1258] Acquire, format, and analyze financial and inventory data.

[1259] Responsible for analysis using generative AI models and automatic report generation.

[1260] 2. User Device:

[1261] Smart glasses or smartphone.

[1262] It provides a means for users to review reports and make decisions based on the analysis results.

[1263] software

[1264] 1. Database Management System (DBMS):

[1265] Example: MySQL

[1266] Store and manage financial and inventory data.

[1267] 2. Generative AI Model:

[1268] Example: PyTorch or TensorFlow

[1269] Analyze financial and inventory data to generate necessary metrics and insights.

[1270] 3. Cloud Services:

[1271] Example: AWS Lambda

[1272] Used to efficiently execute server-side processing.

[1273] Specific examples of processing

[1274] 1. Data Collection Phase

[1275] The server retrieves sales data, inventory data, and customer data from the physical store's POS system and inventory management system.

[1276] The data is formatted into a standard format and made suitable for analysis.

[1277] 2. Data analysis phase

[1278] The formatted data is sent to a generative AI model, which analyzes financial indicators, sales trends, and more.

[1279] Based on the analysis results, growth strategies, risk management measures, and inventory management and sales promotion measures are generated.

[1280] 3. Report generation phase

[1281] The server automatically generates strategic reports based on the insights provided by the generative AI model.

[1282] The reports are converted into PDF format and displayed on a dedicated dashboard.

[1283] 4. Information provision phase

[1284] The created report is sent to the user's device (smart glasses or smartphone).

[1285] Users can view reports on a dedicated dashboard and gain real-time insights.

[1286] 5. Feedback and further analysis phase

[1287] Users can review the report and submit requests for additional analysis.

[1288] The server re-analyzes the data through the generative AI model and provides an updated report to the user's device.

[1289] Specific examples

[1290] For example, if a brick-and-mortar store owner is struggling with inventory management, they can use this system to analyze inventory data in real time and display sales trends and optimal stock levels. For example, by entering a prompt such as "Calculate the optimal stock level for the next three months based on last month's sales," the AI ​​will instantly provide the analysis results.

[1291] Using this system, store managers can quickly gain insights and implement effective inventory management and sales promotion strategies.

[1292] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1293] Step 1:

[1294] The server retrieves sales data, inventory data, and customer data from the physical store's POS system and inventory management system. Specifically, the server periodically fetches data through each system's API. Sales information from the POS system and inventory information from the inventory management system are used as input, and data processed into a unified format (e.g., CSV format or data frame format) is obtained as output.

[1295] Step 2:

[1296] The server formats the acquired data into a standard format. Specifically, it converts the acquired sales and inventory data into a data frame using the Python pandas library and cleanses it to maintain consistency and integrity. Raw data (unformatted data) is used as input, and a formatted data frame is obtained as output.

[1297] Step 3:

[1298] The server sends the formatted data to a generative AI model, which analyzes the data and calculates financial indicators and sales trends. Specifically, the data is fed into an AI model built using Python's PyTorch or TensorFlow, and the trained model makes predictions. The formatted data frame is used as input, and the calculated results of financial indicators and sales trends are obtained as output.

[1299] Step 4:

[1300] The server generates growth strategies, risk management measures, and inventory management / sales promotion measures based on the analysis results obtained from the generative AI model. Specifically, a Python script is used to analyze the output of the AI ​​model and document strategic proposals. The output of the AI ​​model is used as input, and growth strategies, risk management measures, and inventory management / sales promotion measures are obtained as output.

[1301] Step 5:

[1302] The server automatically generates strategic reports based on the generated growth strategies, risk management measures, and inventory management and sales promotion measures. Specifically, it creates reports in PDF format using Python's FPDF library. The strategic proposals are used as input, and the PDF report is obtained as output.

[1303] Step 6:

[1304] The server sends the created report to the user's device. Specifically, it sends the report by email using SMTP or uploads it to cloud storage. The input is a PDF report, and the output is either emailed to the user or saved in cloud storage.

[1305] Step 7:

[1306] Users use a dedicated dashboard to check reports and send additional analysis requests. Specifically, they access the dashboard via a web application and enter additional analysis requests. The input is the request entered by the user into the dashboard, and the output is the request sent to the server.

[1307] Step 8:

[1308] The server receives user feedback and requests for additional analysis, and then resubmits the data to the generative AI model for reanalysis. Specifically, the data is fed back into the AI ​​model and reanalyzed based on the new conditions. The user request and existing data are used as input, and updated analysis results are output.

[1309] Step 9:

[1310] The server regenerates the report based on the results of the reanalysis and provides it to the user's device. Specifically, it regenerates the report in PDF format and sends it to the user. The reanalysis results are used as input, and an updated PDF report is obtained as output.

[1311] 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.

[1312] This invention relates to a system that enables companies to efficiently analyze financial data and automatically generate reports including strategies and risk management by combining an emotion engine with a system that can provide more appropriate feedback and requests for additional analysis based on the user's emotions. Below, an embodiment of this system and specific program processing are described in detail.

[1313] Data Collection Phase

[1314] server

[1315] The server accesses the company's financial database to retrieve the necessary financial data, such as revenue, liabilities, assets, cash flow, etc. The data retrieval process involves proper access authentication to ensure data security.

[1316] The acquired data is formatted into a standard format (e.g., CSV or data frame format) and data cleaning is performed.

[1317] Data analysis phase

[1318] server

[1319] The formatted data is fed into a generative AI model, which receives this data and calculates key financial metrics (PBR, ROE, ROA, etc.).

[1320] Based on the analysis results, the generative AI model generates corporate growth strategies (e.g., entering new markets and cost reduction measures) and risk management measures (e.g., measures to reduce liquidity risk and debt management).

[1321] Report generation phase

[1322] server

[1323] The generative AI model delivers insights that automatically generate strategic reports, including explanations and interpretations of financial metrics, suggested growth strategies, and risk management measures.

[1324] The generated reports are converted into PDF format or a dedicated web dashboard, and provided in a format that can be accessed by the company's investor relations personnel and management.

[1325] Information provision phase

[1326] server

[1327] The created report is sent to the devices of the company's IR staff and management via email or cloud services.

[1328] Terminal

[1329] The device has a dedicated dashboard where users can view reports and gain insights.

[1330] Feedback and further analysis phase

[1331] User

[1332] Users (IR personnel or management) review the report contents and send feedback or requests for additional analysis to the server.

[1333] server

[1334] The server receives feedback and requests for additional analysis from users, and sends the data back to the generative AI model for additional analysis.

[1335] The generative AI model reanalyzes based on new conditions and data and provides updated insights to the server.

[1336] server

[1337] The report is updated based on the new insights and sent back to the user's device.

[1338] Emotion engine integration phase

[1339] User terminal

[1340] A user device equipped with an emotion engine recognizes emotions from the user's facial expressions, voice, text input, etc. while the user is viewing a report.

[1341] The emotion engine analyzes the recognized user's emotional data and evaluates their stress level and interests.

[1342] server

[1343] The server optimizes the report display and additional explanations based on the emotion data received from the emotion engine. For example, if the user is feeling stressed, it will automatically provide more detailed explanations and supplementary information.

[1344] Based on the needs indicated by the user's emotional data, specific analysis requests are automatically generated to the generative AI model, expanding the user's options.

[1345] Specific examples

[1346] Case Study: Medium-sized Manufacturing Company Y

[1347] background

[1348] Company Y has experienced a recent increase in revenue and needs to provide accurate and timely information to investors. However, its traditional process required a significant amount of time and effort to analyze financial data and create proposals.

[1349] introduction

[1350] Company Y will introduce this system and upload its financial data to the server. It will also integrate an emotion engine into user devices.

[1351] Processing flow

[1352] The server accesses Company Y's database and aggregates and formats the necessary financial data.

[1353] The server sends the data to a generative AI model, which calculates financial indicators and generates growth strategies and risk management measures.

[1354] The server creates a strategic report based on the generated insights and sends it to the terminal of Company Y's IR officer.

[1355] The user (IR staff) checks the report on the dashboard, and the emotional data recognized by the emotion engine is analyzed, and feedback and additional analysis are automatically optimized.

[1356] result

[1357] Company Y was able to quickly obtain insights and provide reports optimized by the sentiment engine, enabling it to provide effective IR information to investors, which improved communication with investors and increased its reputation in the capital markets.

[1358] The above is a specific embodiment and processing content of this system. By integrating an emotion engine, customization based on the user's emotions becomes possible, realizing the construction of a more effective and user-friendly system.

[1359] The processing flow will be explained below.

[1360] Step 1:

[1361] The server accesses the company's financial database to retrieve the required financial data such as revenue, liabilities, assets, cash flow, etc. The data retrieval process involves proper access authentication and ensures a secure connection.

[1362] Step 2:

[1363] The server formats the acquired financial data into a standard format (e.g., CSV file or data frame format), and this process also involves data cleaning to remove incomplete and duplicate data.

[1364] Step 3:

[1365] The server sends the formatted data to the generative AI model, which then begins analyzing the input data.

[1366] Step 4:

[1367] The generative AI model analyzes the data and calculates key financial metrics (PBR, ROE, ROA, etc.), which are important metrics for understanding a company's financial situation.

[1368] Step 5:

[1369] Based on the analysis results, the generative AI model generates growth strategies (e.g., new market entry, cost reduction measures) and risk management measures (e.g., liquidity risk mitigation, debt management) for the company. At this stage, the AI ​​may also perform multiple scenario analysis.

[1370] Step 6:

[1371] The server automatically generates strategic reports based on the insights provided by the generative AI model, including interpretations of financial indicators, proposed growth strategies, and recommended risk management measures.

[1372] Step 7:

[1373] The server converts the generated reports into PDF format, Excel sheets, dedicated web dashboards, etc., making them accessible to the company's investor relations personnel and management.

[1374] Step 8:

[1375] The server then sends the generated reports to the terminals of the company's investor relations staff and management, and the reports are provided via email or cloud storage.

[1376] Step 9:

[1377] The device is integrated with a dedicated dashboard where users can view generated reports and gain insights into financial performance and strategic proposals.

[1378] Step 10:

[1379] The user device, which is integrated with the emotion engine, recognizes emotions in real time from facial expressions, voice, and input text while the user is reviewing a report, thereby assessing the user's stress level, interest level, etc.

[1380] Step 11:

[1381] Users (IR staff or management) review the report content and AI proposals, and provide feedback or request additional analysis based on the emotional data at the time. If the emotion engine is feeling stressed, it will optimize the report by adding a simple explanation or providing detailed data.

[1382] Step 12:

[1383] The server receives feedback and requests for additional analysis from the user and sends the data to the generative AI model again. The AI ​​model is given new analysis scenarios and conditions, and re-analysis is performed.

[1384] Step 13:

[1385] The generative AI model performs additional analysis and generates new insights, including specific metrics that users have expressed interest in and new strategic recommendations.

[1386] Step 14:

[1387] The server updates the report based on the new insights and sends it back to the user's device, where the latest report is displayed in real time on the dashboard.

[1388] These are the specific processing steps of this system. At each step, the server, generative AI model, terminal, and user play their respective roles to achieve efficient and accurate analysis and reporting of financial data. The integration of an emotion engine enables customization based on user emotions, resulting in a more user-friendly system.

[1389] Example 2

[1390] 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."

[1391] Analyzing financial information and generating reports in companies requires a great deal of time and effort using conventional methods. Furthermore, if the generated reports do not reflect the specific needs and feelings of users, effective decision-making becomes difficult. Therefore, there is a need for efficient analysis of financial information, automatic generation of highly accurate reports, and provision of reports whose content is optimized based on user feelings.

[1392] The specification processing by the specification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for aggregating and formatting a company's financial information, means for analyzing the financial information using a generative AI model and calculating financial indicators, means for generating a growth strategy and a risk management measure based on the analysis results using the generative AI model, means for automatically generating a strategic report based on the generated growth strategy and the risk management measure, means for providing the report to a user terminal, means for receiving feedback and additional analysis requests from a user and performing reanalysis, and means for collecting and analyzing user emotion data using an emotion engine and optimizing the report content. This enables efficient analysis of financial information, rapid generation of reports, and provision of optimal content based on the user's emotions.

[1393] "Financial information" refers to data that shows a company's financial status, such as its revenue, liabilities, assets, and cash flow.

[1394] A "generative AI model" is an artificial intelligence model that uses machine learning and deep learning technologies to analyze financial information and calculate financial indicators.

[1395] "Financial indicators" are indicators used to quantitatively evaluate a company's financial condition, and include, for example, PBR (price-to-book ratio), ROE (return on equity), and ROA (return on assets).

[1396] A "growth strategy" is a general term for the plans and measures that a company implements in order to achieve sustainable growth.

[1397] "Risk management measures" are specific policies and measures to assess the risks that a company may face and reduce or manage them.

[1398] A "strategic report" is a document that summarizes financial indicators, growth strategies, and risk management measures generated based on financial information, and compiles proposals and views on management strategies.

[1399] "User terminal" refers to a device, such as a computer or mobile device, used by a company's investor relations personnel or management to view reports and submit feedback.

[1400] "Feedback and further analysis requests" are comments provided by users regarding the contents of a report or requests for further data analysis.

[1401] An "emotion engine" is a technology that recognizes and analyzes emotions from a user's facial expressions, voice, text input, etc.

[1402] "Emotion data" refers to data that indicates the user's emotional state as recognized and analyzed by the emotion engine.

[1403] Optimization is the adjustment and improvement of system or process parameters to efficiently achieve a specific objective.

[1404] MODE FOR CARRYING OUT THE INVENTION

[1405] This invention relates to a system that enables companies to efficiently analyze financial information and automatically generate reports including strategies and risk management, by combining an emotion engine with a system that can provide more appropriate feedback and requests for additional analysis based on the user's emotions. Below, an embodiment of this system and specific program processing are described in detail.

[1406] Data Collection Phase

[1407] server

[1408] The server accesses the company's financial database and retrieves the required financial information such as revenue, liabilities, assets, cash flow, etc. The data retrieval process involves authentication using an API key and / or authentication token for database connection.

[1409] The server formats the acquired data into a standard format (e.g., CSV or data frame format) using the Python Pandas library.

[1410] Furthermore, missing values ​​and outliers are handled by filling in the missing values ​​with the mean value and excluding outliers.

[1411] Data analysis phase

[1412] server

[1413] The server inputs the formatted financial information into the generative AI model, sending the data to the generative AI model via the API as a POST request.

[1414] A prompt sentence is generated and fed into the generative AI model along with financial information retrieved from the database. An example prompt sentence is as follows:

[1415] "Please suggest the optimal growth strategy based on the company's revenue data."

[1416] The generative AI model analyzes input data and calculates key financial metrics (PBR, ROE, ROA, etc.) based on pre-defined formulas and algorithms.

[1417] The generative AI model generates corporate growth strategies and risk management measures based on the results of analyzing financial indicators.

[1418] Report generation phase

[1419] server

[1420] The server automatically generates strategic reports based on the insights returned by the generative AI model, including explanations and interpretations of financial metrics, suggested growth strategies, and risk management measures.

[1421] A template engine (e.g., Jinja2) is used to generate reports and output formats such as HTML and PDF.

[1422] Convert the generated report into PDF format or a dedicated web dashboard. For example, use a PDF generation tool to convert an HTML template into a PDF.

[1423] Information provision phase

[1424] server

[1425] The server then sends the created reports to the devices of the company's investor relations staff or management. In some cases, the reports are sent as PDF attachments via email, or a link to a cloud service is shared.

[1426] Terminal

[1427] The device has a dedicated dashboard where users can view reports and gain various insights.

[1428] Feedback and further analysis phase

[1429] User

[1430] Users (IR staff and management) check the contents of the report and send feedback or requests for additional analysis to the server. The dashboard provides input fields for feedback forms and requests for additional analysis.

[1431] server

[1432] The server receives feedback and requests for additional analysis from the user, sends the data to the generative AI model again for additional analysis, and creates a new prompt sentence and inputs it to the generative AI model.

[1433] It reanalyzes the data based on new conditions and data, and provides updated insights to the server.

[1434] The server updates the report based on the new insights and sends it back to the user's device.

[1435] Emotion engine integration phase

[1436] User terminal

[1437] The user device equipped with the emotion engine recognizes emotions from the user's facial expressions, voice, text input, etc. while the user is viewing a report. This requires a device equipped with a camera and microphone.

[1438] The emotion engine analyzes the recognized user's emotional data and evaluates their stress level and interests.

[1439] server

[1440] The server optimizes the report display and additional explanations based on the emotion data received from the emotion engine. For example, if the user is feeling stressed, it will automatically provide more detailed explanations and supplementary information.

[1441] Based on the needs indicated by the user's emotional data, specific analysis requests are automatically generated to the generative AI model, expanding the user's options.

[1442] Examples and prompts

[1443] Examples:

[1444] Case Study: Medium-sized Manufacturing Company Y

[1445] With the recent increase in revenue, Company Y needs to provide accurate and prompt information to investors. However, in the conventional process, analyzing financial information and creating proposals required a great deal of time and effort. Company Y will introduce this system and upload its financial information to a server. It will also integrate an emotion engine into user devices.

[1446] Process flow:

[1447] The server accesses Company Y's database and aggregates and formats the necessary financial information.

[1448] The server sends the data to a generative AI model, which calculates financial indicators and generates growth strategies and risk management measures.

[1449] The server creates a strategic report based on the generated insights and sends it to the terminal of Company Y's IR officer.

[1450] The user (IR staff) checks the report on the dashboard, and the emotional data recognized by the emotion engine is analyzed, and feedback and additional analysis are automatically optimized.

[1451] Example prompt sentence:

[1452] "Based on Company Y's financial data, please calculate the latest financial indicators (PBR, ROE, ROA, etc.) and propose growth strategies and risk management measures. Also, please use an emotion engine to optimize the report content based on user feedback."

[1453] The above is a specific embodiment and processing content of this system. By integrating an emotion engine, customization based on the user's emotions becomes possible, realizing the construction of a more effective and user-friendly system.

[1454] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1455] Program processing steps

[1456] Data Collection Phase

[1457] Step 1:

[1458] server

[1459] The server accesses the company's financial database and retrieves the required financial information such as revenue, liabilities, assets, cash flow, etc. The input is the database authentication information and the output is the retrieved financial information.

[1460] Specifically, it uses an API key or authentication token for database connection to execute an SQL query to retrieve data.

[1461] Step 2:

[1462] server

[1463] The server formats the financial information it retrieves into a standard format (CSV or data frame). The input is the raw data it retrieves, and the output is the formatted data.

[1464] For example, use Python's Pandas library to convert the data into a data frame, organize the necessary columns, and convert data types.

[1465] Step 3:

[1466] server

[1467] The server cleans the financial information: the input is formatted data, and the output is cleaned data.

[1468] Specifically, the process involves filling in missing values ​​with the average value and excluding outliers.

[1469] Data analysis phase

[1470] Step 4:

[1471] server

[1472] The server sends the formatted and cleaned financial information to a generative AI model, whose inputs are the cleaned data and generated prompts, and whose output is financial metrics and insights.

[1473] Specifically, the data is sent to the generative AI model via an API as a POST request. An example prompt might be: "Based on the company's revenue data, please propose the optimal growth strategy."

[1474] Step 5:

[1475] Generative AI Models

[1476] The generative AI model analyzes input data and calculates key financial indicators (PBR, ROE, ROA, etc.) The input is the cleaned data and prompt statements, and the output is the calculated financial indicators.

[1477] Financial indicators are calculated using pre-defined formulas and algorithms.

[1478] Step 6:

[1479] Generative AI Models

[1480] The generative AI model generates a company's growth strategy and risk management measures from the results of analyzing financial indicators. The input is the calculated financial indicators, and the output is the generated growth strategy and risk management measures.

[1481] Specifically, the generated text data is inserted into a report template.

[1482] Report generation phase

[1483] Step 7:

[1484] server

[1485] The server automatically generates strategic reports based on the insights returned by the generative AI model. The input is the generated growth strategy and risk management measures, and the output is the completed report.

[1486] A template engine (e.g., Jinja2) is used to generate reports and convert them into formats such as HTML and PDF.

[1487] Step 8:

[1488] server

[1489] The server converts the generated report into PDF format or a dedicated web dashboard. The input is the generated report and the output is the converted file format.

[1490] As a specific operation, for example, a PDF generation tool is used to convert the HTML template into a PDF.

[1491] Information provision phase

[1492] Step 9:

[1493] server

[1494] The server then sends the created report to the terminals of the company's IR staff and management. The input is a report in PDF format or web dashboard format, and the output is a report sent to the user's terminal.

[1495] Specific actions include sending a PDF as an attachment via email or sharing a link to a cloud service.

[1496] Step 10:

[1497] Terminal

[1498] The terminal has a dedicated dashboard where users can check reports. The input is a report in PDF format or web dashboard format, and the output is the checked report.

[1499] You can access reports and gain various insights through the dashboard.

[1500] Feedback and further analysis phase

[1501] Step 11:

[1502] User

[1503] Users (IR staff or management) check the contents of the report and send feedback or requests for additional analysis to the server. The input is feedback on the report or requests for additional analysis, and the output is the feedback sent to the server.

[1504] Provide a feedback form or input field for additional analysis requests on the dashboard.

[1505] Step 12:

[1506] server

[1507] The server receives feedback and requests for additional analysis from users and sends the data to the generative AI model again for further analysis. The input is the received feedback and requests for additional analysis, and the output is the reanalyzed insights.

[1508] Create new prompts and feed them into the generative AI model, which then reanalyzes them and generates new insights.

[1509] Step 13:

[1510] server

[1511] The server updates the report based on the new insights and sends it back to the user's device. The input is the reanalyzed insights and the updated report, and the output is the updated report.

[1512] Allow users to view updated reports.

[1513] Emotion engine integration phase

[1514] Step 14:

[1515] User terminal

[1516] A user device equipped with an emotion engine recognizes emotions from the user's facial expressions, voice, text input, etc. while the user is viewing a report. The input is the user's facial expressions, voice, and text data, and the output is emotion data.

[1517] This requires a device with a camera and microphone.

[1518] Step 15:

[1519] server

[1520] The server optimizes the display content of the report and additional explanations based on the emotion data received from the emotion engine. The input is emotion data, and the output is an optimized report.

[1521] If the user is feeling stressed, more detailed explanations and supplementary information will be automatically provided.

[1522] Step 16:

[1523] server

[1524] The server automatically generates specific analysis requests to the generative AI model based on the needs indicated by the user's emotional data, expanding the user's options. The input is the emotional data and the generated prompt, and the output is the additional analysis results.

[1525] Specifically, it generates a new prompt sentence based on the emotional data and sends that prompt sentence to the generative AI model.

[1526] The above is the specific processing flow of this system and the operation at each step. By clearly explaining the specific operations and data processing methods, the details of the system will become clearer.

[1527] (Application example 2)

[1528] 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."

[1529] Traditional financial data analysis systems required a great deal of time and effort for companies to quickly and efficiently understand their financial situation and make strategic decisions. Furthermore, they lacked feedback based on user emotions and intuition, making it difficult for users to gain a deeper understanding of reports and appropriately request additional analysis. Furthermore, in brick-and-mortar store operations, understanding the emotions of staff and customers in real time and providing optimal service was a challenge.

[1530] 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.

[1531] In this invention, the server includes a means for aggregating and formatting a company's financial data, a means for analyzing the financial data using a generative AI model to calculate financial indicators, and a means for generating growth strategies and risk management measures. This enables companies to gain quick and accurate insights. Furthermore, the user terminal is equipped with an emotion engine, providing a means for recognizing user emotions and optimizing report content based on the recognition results. Furthermore, the system includes a means for displaying reports via a dedicated dashboard and automatically optimizing report content based on the emotion recognition results. This enables efficient user feedback and highly accurate requests for additional analysis, enabling optimal service provision even in brick-and-mortar store operations.

[1532] "Financial data" refers to financial information held by a company, such as revenues, liabilities, assets, and cash flow.

[1533] A "generative AI model" is an artificial intelligence model that analyzes input data and automatically calculates financial indicators, generates growth strategies, and generates risk management measures.

[1534] A "user terminal" is a device used to check reports, send feedback, and provide information based on emotion recognition results.

[1535] An "emotion engine" is a technology for recognizing and analyzing emotions from a user's facial expressions, voice, text input, etc.

[1536] "Financial indicators" are indicators used to evaluate a company's financial condition and performance, and include PBR, ROE, ROA, etc.

[1537] A "growth strategy" is a plan or policy for a company to achieve sustainable growth.

[1538] "Risk management measures" are strategies and measures used to mitigate or avoid risks that a company may face.

[1539] A "strategic report" is a document that includes explanations and interpretations of financial indicators, proposed growth strategies, and risk management measures.

[1540] A "dedicated dashboard" is an interface that visually displays generated reports and is easily accessible to users.

[1541] "Feedback" refers to the reactions and opinions users provide to reports.

[1542] An "additional analysis request" is an action in which a user requests the server to perform further analysis based on a report or analysis result.

[1543] This section describes a specific system for implementing this invention. The system aggregates and formats a company's financial data, analyzes it using a generative AI model, and calculates various financial indicators. Furthermore, it generates growth strategies and risk management measures based on the analysis results, and automatically generates strategic reports. Additionally, it can recognize user emotions using a user device equipped with an emotion engine and optimize the content of the report.

[1544] Data collection and formatting

[1545] The server accesses the company's financial database and retrieves the necessary financial data, such as revenue, liabilities, assets, cash flow, etc. The data is retrieved with appropriate access authentication and then formatted into a standard format. During this process, the data is also cleaned to remove missing or outlier values.

[1546] Data analysis

[1547] The server inputs the formatted financial data into a generative AI model to calculate key financial indicators (e.g., PBR, ROE, ROA, etc.). This model can use OpenAI's GPT-4 or Google's BERT. Based on the analysis results, the server generates insights that suggest growth strategies and risk management measures for the company.

[1548] report generation

[1549] Based on the insights generated, strategic reports are automatically generated, including explanations and interpretations of financial indicators, proposed growth strategies, and risk management measures, and can be viewed in PDF format or on a dedicated web dashboard.

[1550] Input and Feedback

[1551] The server sends automatically generated reports to the terminals of the company's investor relations personnel and management via email or cloud services. Users can use a dashboard to check the reports and send feedback or requests for additional analysis. The server receives this feedback and requests and performs reanalysis.

[1552] Emotion Engine Integration

[1553] The emotion engine installed on the user's device recognizes emotions from the user's facial expressions, voice, and text input while viewing the report. For example, it uses Affectiva's SDK or Microsoft's Emotion API. This emotion data is sent to the server to optimize the report content. For example, if the user is feeling stressed, it will provide more detailed explanations and additional information.

[1554] Specific examples

[1555] For example, a mid-sized manufacturing company might prompt their generative AI model with the following:

[1556] Prompt: "Analyze store sales data and generate future growth and risk management strategies. For example, which products are selling the best and which products are likely to be low in stock?"

[1557] Based on this prompt, the generative AI model analyzes financial data and proposes growth strategies and risk management measures. Based on these insights, a strategic report is generated. This report is optimized according to the user's emotions through an emotion engine, making it more user-friendly and providing useful information.

[1558] This will enable companies to analyze financial data quickly and accurately and make strategic decisions, while also enabling brick-and-mortar stores to provide optimal services that are tailored to the emotions of staff and customers.

[1559] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1560] Step 1:

[1561] The server accesses the company's financial database to retrieve the required financial data, such as revenue, liabilities, assets, cash flow, etc. The input is the authentication information of the company's financial database, and the output is the retrieved financial data. This data retrieval process is subject to appropriate access authentication to ensure data security.

[1562] Step 2:

[1563] The server formats the acquired financial data into a standard format (CSV or data frame format) and performs data cleaning. The input is the acquired financial data, and the output is the formatted and cleaned financial data. During this process, missing values ​​and outliers are processed and the data is formatted in a format suitable for analysis.

[1564] Step 3:

[1565] The server inputs the formatted financial data into a generative AI model. The generative AI model calculates key financial indicators (PBR, ROE, ROA, etc.). The input is the formatted financial data, and the output is the calculated financial indicators. The generative AI model (e.g., OpenAI GPT-4) analyzes the financial data and generates the required indicators.

[1566] Step 4:

[1567] The server automatically generates growth strategies and risk management measures based on the analysis results of the generative AI model. The input is the calculated financial indicators, and the output is the growth strategies and risk management measures. In this step, a strategic action plan for the company is created based on the analysis results.

[1568] Step 5:

[1569] The server automatically generates a strategic report based on the generated growth strategy and risk management measures. The input is data on growth strategies and risk management measures, and the output is a strategic report (e.g., in PDF format or data for display on a dedicated web dashboard). This report includes explanations and interpretations of financial indicators, proposed growth strategies, and risk management measures.

[1570] Step 6:

[1571] The server sends the automatically generated report to the terminals of the company's IR personnel and management via email or cloud services. The input is the strategic report, and the output is the sent report. The report can then be viewed on the user's terminal.

[1572] Step 7:

[1573] Users can use a dedicated dashboard to check reports and, if necessary, send feedback or requests for additional analysis to the server. The input is the user's feedback or requests for additional analysis, and the output is re-requested analysis data. Each item in the report is visually displayed on the dashboard.

[1574] Step 8:

[1575] The server receives feedback and requests for additional analysis from users and sends the data back to the generative AI model to perform the additional analysis. The input is the feedback and requests for additional analysis, and the output is the results of the reanalysis. New insights are generated and the report is updated.

[1576] Step 9:

[1577] The emotion engine installed on the user's device recognizes emotions from the user's facial expressions, voice, text input, etc. while viewing the report, and sends that data to the server. The input is the user's emotion data, and the output is the emotion recognition results. The data is analyzed by the emotion engine (e.g., Affectiva SDK).

[1578] Step 10:

[1579] The server optimizes the report content based on the emotion data received from the emotion engine. The input is the emotion recognition result, and the output is the optimized report. If the user is feeling stressed, the report is automatically updated to provide more detailed explanations and supplementary information.

[1580] Specific examples

[1581] For example, a mid-sized manufacturing company might prompt their generative AI model with the following:

[1582] "Analyze store sales data and generate future growth and risk management strategies. For example, tell me which products are selling the best and which products are likely to be low in stock."

[1583] 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.

[1584] 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.

[1585] 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.

[1586] [Fourth embodiment]

[1587] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1588] 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.

[1589] 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).

[1590] 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.

[1591] 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.

[1592] 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).

[1593] 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.

[1594] 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.

[1595] 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.

[1596] 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.

[1597] 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.

[1598] 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.

[1599] 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."

[1600] This invention relates to a system that enables companies to efficiently analyze financial data and automatically generate reports that include strategies and risk management. An embodiment of this system and specific program processing will be described in detail below.

[1601] Data Collection Phase

[1602] server

[1603] The server accesses the company's financial database to obtain the necessary revenue, liability, asset, and cash flow information, connecting to authorized databases via access authentication.

[1604] The acquired data is formatted into a standard format, such as CSV or data frame, making it suitable for analysis.

[1605] Data analysis phase

[1606] server

[1607] The formatted data is sent from the server to the generative AI model, which analyzes it and calculates each financial indicator.

[1608] Generative AI Models

[1609] Based on the data received, the generative AI model calculates key financial indicators such as PBR (Price to Book Ratio), ROE (Return on Equity), and ROA (Return on Assets).

[1610] Furthermore, based on the analysis results, the generative AI model generates corporate growth strategies (e.g., entry into new markets and cost reduction measures) and risk management measures (e.g., measures to reduce liquidity risk and debt management).

[1611] Report generation phase

[1612] server

[1613] The server automatically generates strategic reports based on insights provided by the generative AI model, including explanations and interpretations of financial metrics, suggested growth strategies, and risk management measures.

[1614] Convert the generated reports into a format that can be accessed by the company's investor relations personnel and management (e.g., PDF format or a dedicated web dashboard).

[1615] Information provision phase

[1616] server

[1617] The reports are then sent to the devices of the company's IR staff and management, often via email or cloud services.

[1618] Terminal

[1619] The device has a dedicated dashboard where users can view reports and gain insights.

[1620] Feedback and further analysis phase

[1621] User

[1622] Users (IR staff and management) review the report and, if necessary, can send feedback to the server and request additional analysis.

[1623] server

[1624] The server receives feedback and requests for additional analysis from users, sends the data to the generative AI model again, and performs additional analysis.

[1625] Generative AI Models

[1626] The generative AI model performs reanalysis based on new conditions and data and sends updated insights back to the server.

[1627] server

[1628] The server regenerates the report based on the updated insights and sends it to the user terminal.

[1629] Specific examples

[1630] Case Study: Medium-sized Manufacturing Company X

[1631] background

[1632] As Company X's revenues increase, it needs to provide accurate and timely information to investors, but analyzing financial data and compiling strategic proposals takes a lot of time and effort.

[1633] introduction

[1634] Company X introduces this system and uploads its financial data to the server.

[1635] Processing flow

[1636] The server accesses Company X's database and aggregates and formats the necessary financial data.

[1637] The server sends the data to a generative AI model, which calculates financial indicators and generates growth strategies and risk management measures.

[1638] Based on the generated insights, the server creates a strategic report and sends it to the terminal of Company X's IR officer.

[1639] The user (IR officer) checks the report on the dashboard and submits additional analysis requests to the server.

[1640] The server receives the request, performs the reanalysis, and provides an updated report to the user's terminal.

[1641] result

[1642] Company X was able to quickly obtain insights and provide effective IR information to investors, which improved communication with investors and increased its reputation in the capital market.

[1643] The above is a detailed description of the system's implementation and processing. This invention can help companies use AI to efficiently analyze financial data and quickly provide high-quality IR information.

[1644] The processing flow will be explained below.

[1645] Step 1:

[1646] The server accesses the company's financial database to retrieve the necessary financial data such as revenue, liabilities, assets, cash flow, etc. This data retrieval process involves proper access authentication to ensure data security.

[1647] Step 2:

[1648] The server formats the acquired financial data into a standard format (e.g., CSV file or data frame format). Data cleaning is also performed at this stage to remove incomplete or duplicate data.

[1649] Step 3:

[1650] The server inputs the formatted data into the generative AI model, which receives the data and begins analyzing it.

[1651] Step 4:

[1652] The generative AI model analyzes the input data and calculates key financial indicators, such as PBR (Price to Book Ratio), ROE (Return on Equity), and ROA (Return on Assets).

[1653] Step 5:

[1654] Based on the analysis results, the generative AI model generates corporate growth strategies (e.g., entry into new markets and cost reduction measures) and risk management measures (e.g., measures to reduce liquidity risk and debt management).

[1655] Step 6:

[1656] The server automatically generates strategic reports based on insights provided by the generative AI model, including explanations and interpretations of financial metrics, suggested growth strategies, and risk management measures.

[1657] Step 7:

[1658] The server formats the generated reports into a format (e.g., PDF or dedicated web dashboard) that can be accessed by the company's investor relations personnel and management.

[1659] Step 8:

[1660] The server then sends the generated reports to the terminals of the company's IR staff and management via email or cloud services.

[1661] Step 9:

[1662] The device has a dedicated dashboard where users can view reports and gain insights.

[1663] Step 10:

[1664] Users (IR personnel or management) review the report and, if necessary, send feedback to the server and request additional analysis.

[1665] Step 11:

[1666] The server receives feedback and requests for additional analysis from users, and sends the data back to the generative AI model for additional analysis.

[1667] Step 12:

[1668] The generative AI model performs reanalysis based on new conditions and data and provides updated insights to the server.

[1669] Step 13:

[1670] The server updates the report based on the new insights and sends it back to the user's device.

[1671] These are the specific processing steps of this system. At each step, the server, generative AI model, terminal, and user play their respective roles to achieve efficient and accurate analysis and reporting of financial data.

[1672] Example 1

[1673] 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."

[1674] In today's business environment, it is important for companies to efficiently analyze financial data and quickly provide high-quality reports, including those for strategy and risk management. However, traditional methods require a significant amount of time and effort to aggregate data, analyze it, and create reports, straining corporate resources. In particular, it is difficult to quickly and accurately handle large amounts of financial data and obtain appropriate insights to support strategic decision-making.

[1675] 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.

[1676] In this invention, the server includes means for aggregating and formatting a company's financial data, means for analyzing the financial data using a generative AI model to calculate financial indicators, means for generating a growth strategy and risk management measures based on the analysis results using the generative AI model, means for providing the generated report to a user terminal via email or a cloud service, means for displaying the report via a dedicated dashboard, and means for receiving feedback and requests for additional analysis from users and performing reanalysis, thereby enabling companies to efficiently analyze financial data and quickly provide high-quality reports that support strategic decision-making.

[1677] "Corporate financial data" refers to financial information that a company generates and holds in the course of its economic activities, and includes revenue data, liability data, asset data, cash flow information, and the like.

[1678] "Aggregation and formatting means" refers to methods or tools used to convert data from different formats or sources into a unified format suitable for analysis.

[1679] A "generative AI model" refers to a system that uses artificial intelligence technology to automatically perform complex calculations and analyses based on input data.

[1680] "Financial indicators" refer to numerical values ​​calculated using formulas to evaluate a company's financial condition and performance, and include, for example, PBR (price-to-book ratio), ROE (return on equity), and ROA (return on assets).

[1681] A "growth strategy" refers to the plans and policies that a company implements in order to achieve sustainable development, and includes measures such as entering new markets and cost-cutting measures.

[1682] "Risk management measures" refer to the plans and measures adopted to identify, assess and mitigate potential risks faced by an entity, including liquidity risk mitigation measures and debt management.

[1683] A "strategic report" refers to a document in which a company summarizes its future strategies and risk management based on the analysis of financial data.

[1684] "Means of providing via email or cloud service" refers to a method of using an email system or cloud service to quickly and securely distribute the generated report to the user.

[1685] A "dedicated dashboard" refers to a specialized interface, typically provided as a web application, that allows users to view reports and gain insights.

[1686] "Means for receiving feedback or requests for additional analysis and performing re-analysis" refers to methods or tools for receiving user opinions or requests and conducting additional data analysis based on those opinions or requests to generate new insights.

[1687] The present invention relates to a system that enables a company to efficiently analyze financial data and automatically generate reports that include strategies and risk management. Specific embodiments of this system will be described in detail below.

[1688] Data Collection Phase

[1689] server

[1690] The server accesses the company's financial database to retrieve the necessary revenue, liability, asset, and cash flow information. It connects to the database through secure access authentication using a database management system such as MySQL or PostgreSQL. The retrieved data is then formatted into CSV or dataframe format using the Python pandas library.

[1691] Data analysis phase

[1692] server

[1693] The formatted data is sent from the server to the generative AI model using an HTTP POST request to send the data to the AI ​​model's endpoint.

[1694] Generative AI Models

[1695] Based on the data it receives, the generative AI model calculates financial indicators such as PBR (Price to Book Ratio), ROE (Return on Equity), and ROA (Return on Assets). Specifically, it uses a formula such as "PBR = market_price / book_value." It also performs scenario-based analysis to generate growth strategies (e.g., new market entry, cost reduction measures) and risk management measures (e.g., liquidity risk mitigation measures, debt management).

[1696] Report generation phase

[1697] server

[1698] The server automatically generates strategic reports in PDF format using LaTeX templates based on insights from the generative AI model. The reports include explanations and interpretations of financial metrics, proposed growth strategies, and risk management measures. The generated reports are converted to PDF format using the Python reportlab library.

[1699] Information provision phase

[1700] server

[1701] The created report is sent to the company's IR personnel or management via email or cloud services (e.g., AWS S3 or Google Drive).

[1702] Terminal

[1703] The device has a dedicated dashboard where users can view reports and gain insights, and a dedicated web application allows users to access the dashboard from a browser and view the report contents.

[1704] Feedback and further analysis phase

[1705] User

[1706] Users (IR staff and management) review the report and submit feedback or requests for additional analysis to the server as needed. These requests are sent using a feedback form on the dashboard.

[1707] server

[1708] The server receives feedback and requests for additional analysis from users, and then sends the data to the generative AI model again to perform reanalysis.

[1709] Generative AI Models

[1710] The generative AI model performs reanalysis based on new conditions and data and returns updated insights to the server.

[1711] server

[1712] The server regenerates strategic reports based on the updated insights and sends them back to the user's device, allowing businesses to continuously obtain the latest information and strategic proposals.

[1713] Examples of prompt statements

[1714] "Please calculate financial indicators such as PBR, ROE, and ROA based on the company's financial data for the first quarter of fiscal year 2022. Also, please propose growth strategies such as entering new markets and cost reduction measures, as well as risk management measures such as measures to reduce liquidity risk and debt management."

[1715] This invention enables companies to use AI to efficiently analyze financial data and quickly provide high-quality IR information.

[1716] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1717] Step 1:

[1718] Database Connection

[1719] The server connects to the company's financial database, taking the database URL, username, and password as input, and getting a database connection object as output, specifically using a database management system such as MySQL or PostgreSQL, for secure access authentication.

[1720] Step 2:

[1721] Obtaining financial data

[1722] The server retrieves the necessary financial data, such as revenue data, liability data, asset data, and cash flow information. It uses a database connection object as input and gets the raw data as output. Specifically, it executes an SQL query (e.g., "SELECT FROM financial_data") and converts the resulting data into a Python pandas data frame.

[1723] Step 3:

[1724] Data Formatting

[1725] The server formats the acquired raw data into a format suitable for analysis (for example, CSV format or data frame format). It uses the acquired raw data as input and obtains formatted data as output. Specifically, it uses the pandas function to convert the format, such as "data.to_csv('output.csv')".

[1726] Step 4:

[1727] Sending data to a generative AI model

[1728] The server sends the formatted data to the generative AI model. It uses the formatted data as input and gets the status of the HTTP POST request to the generative AI model as output. Specifically, it converts the data into JSON format, creates an HTTP request, and sends it.

[1729] Step 5:

[1730] Calculation of financial indicators

[1731] The generative AI model calculates financial metrics such as PBR, ROE, and ROA based on the data sent to it. It uses formatted data as input and obtains various financial metrics as output. Specifically, it applies a formula such as "PBR = market_price / book_value."

[1732] Step 6:

[1733] Generate growth strategies and risk management measures

[1734] The generative AI model generates growth strategies and risk management measures based on the results of financial indicator analysis. It uses financial indicator data as input and obtains growth strategies and risk management measures as output. Specifically, it performs scenario analysis and generates proposals for "entering new markets" and "reducing costs."

[1735] Step 7:

[1736] Automatic report generation

[1737] The server automatically generates strategic reports based on insights from the generative AI model. It uses growth strategy and risk management data as input and obtains the generated report as output. Specifically, it creates a PDF report using a LaTeX template.

[1738] Step 8:

[1739] Report format conversion

[1740] The server converts the generated reports into a user-accessible format (PDF or a dedicated web dashboard), using the generated reports as input and obtaining the converted reports as output. Specifically, it uses the Python reportlab library to generate PDFs.

[1741] Step 9:

[1742] Report distribution

[1743] The server sends the created report to the terminals of the company's investor relations officer or management. It uses the converted report as input and gets the delivery status as output. Specifically, it sends the report by email using the SMTP protocol.

[1744] Step 10:

[1745] Review the report

[1746] The terminal has a dedicated dashboard where users can check reports and gain insights. The report URL and dashboard access information are used as input, and the report viewing screen is obtained as output. Specifically, the dashboard is accessed using a web browser.

[1747] Step 11:

[1748] Send Feedback

[1749] The user checks the report contents and submits feedback or additional analysis requests to the server as needed. The feedback contents are used as input and the feedback submission status is obtained as output. The specific operation is to submit the request using a form on the dashboard.

[1750] Step 12:

[1751] Receiving and analyzing feedback

[1752] The server receives feedback and requests for additional analysis from the user, and then resubmits the data to the generative AI model for reanalysis. It uses the feedback as input and obtains the reanalyzed data as output. Specifically, it sends the new data and conditions to the generative AI model via an HTTP POST request.

[1753] Step 13:

[1754] Run a reanalysis

[1755] The generative AI model performs re-analysis based on new conditions and data and returns updated insights to the server. It uses new data and conditions as input and obtains updated insights as output. Specifically, it re-calculates financial indicators and generates strategic recommendations.

[1756] Step 14:

[1757] Regenerating an updated report

[1758] The server regenerates the strategic report based on the updated insights and sends it back to the user terminal. It uses the updated insights as input and obtains the regenerated report as output. Specifically, it creates the report again using the LaTeX template and sends it via the SMTP protocol.

[1759] (Application example 1)

[1760] 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."

[1761] Currently, store managers spend a great deal of time and effort managing inventory, analyzing financial data, and planning sales promotion strategies. However, this often hinders fast and accurate decision-making. It can also lead to inventory shortages or excess inventory, reducing business efficiency. Furthermore, the preparation of reports and processing feedback can be time-consuming, leading to delayed action. It is necessary to improve this situation and enable store managers to make decisions based on fast and accurate information.

[1762] 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.

[1763] In this invention, the server includes a means for aggregating and formatting a company's financial data and inventory data, a means for analyzing the financial data and inventory data using a generative AI model to calculate financial indicators and sales trends, and a means for generating growth strategies, risk management measures, inventory management measures, and sales promotion measures based on the analysis results using the generative AI model. This enables brick-and-mortar store managers to efficiently obtain real-time analysis results of financial data and inventory data and strategic reports based on them.

[1764] "Corporate financial data" is a general term for data that indicates a company's business status and financial condition, such as its revenue, liabilities, assets, and cash flow.

[1765] "Inventory data" is a general term for data related to inventory management, such as the quantity and type of products a company owns, inventory history, and sales prices.

[1766] "Generative AI model" is a general term for artificial intelligence models that automatically analyze specific patterns and trends from large data sets and provide insights into financial indicators, growth strategies, sales promotion measures, and more.

[1767] "Financial indicators" is a general term for statistical values ​​and ratios used to evaluate a company's business condition and financial status, and includes, for example, PBR, ROE, and ROA.

[1768] "Sales trends" is a general term for data that shows sales trends and fluctuations in demand for products and services over a specific period of time.

[1769] A "growth strategy" is a general term for the plans and measures that a company sets in place to achieve sustainable growth, and includes things like entering new markets and cost-cutting measures.

[1770] "Risk management measures" is a general term for measures and policies to predict risks that a company may face and respond to them.

[1771] "Inventory management" is the process of maintaining and efficiently managing the appropriate quantity, type, and storage location of inventory held by a company.

[1772] "Sales promotion measures" is a general term for measures such as advertising, promotions, and pricing strategies implemented to increase product sales.

[1773] A "report" is a document that compiles analysis results, strategic proposals, risk management measures, etc., and is a general term for information provided to management and users.

[1774] "User terminal" is a general term for devices used by managers and users to obtain information, including smart glasses and smartphones.

[1775] "Additional Analysis Request" means a user's request for more detailed analysis based on specific conditions or data.

[1776] This invention relates to a system that enables store managers to efficiently analyze financial and inventory data and automatically generate strategic reports that include growth strategies, risk management measures, and sales promotion measures. The system is configured as follows.

[1777] System Configuration

[1778] Hardware

[1779] 1. Server:

[1780] Acquire, format, and analyze financial and inventory data.

[1781] Responsible for analysis using generative AI models and automatic report generation.

[1782] 2. User Device:

[1783] Smart glasses or smartphone.

[1784] It provides a means for users to review reports and make decisions based on the analysis results.

[1785] software

[1786] 1. Database Management System (DBMS):

[1787] Example: MySQL

[1788] Store and manage financial and inventory data.

[1789] 2. Generative AI Model:

[1790] Example: PyTorch or TensorFlow

[1791] Analyze financial and inventory data to generate necessary metrics and insights.

[1792] 3. Cloud Services:

[1793] Example: AWS Lambda

[1794] Used to efficiently execute server-side processing.

[1795] Specific examples of processing

[1796] 1. Data Collection Phase

[1797] The server retrieves sales data, inventory data, and customer data from the physical store's POS system and inventory management system.

[1798] The data is formatted into a standard format and made suitable for analysis.

[1799] 2. Data analysis phase

[1800] The formatted data is sent to a generative AI model, which analyzes financial indicators, sales trends, and more.

[1801] Based on the analysis results, growth strategies, risk management measures, and inventory management and sales promotion measures are generated.

[1802] 3. Report generation phase

[1803] The server automatically generates strategic reports based on the insights provided by the generative AI model.

[1804] The reports are converted into PDF format and displayed on a dedicated dashboard.

[1805] 4. Information provision phase

[1806] The created report is sent to the user's device (smart glasses or smartphone).

[1807] Users can view reports on a dedicated dashboard and gain real-time insights.

[1808] 5. Feedback and further analysis phase

[1809] Users can review the report and submit requests for additional analysis.

[1810] The server re-analyzes the data through the generative AI model and provides an updated report to the user's device.

[1811] Specific examples

[1812] For example, if a brick-and-mortar store owner is struggling with inventory management, they can use this system to analyze inventory data in real time and display sales trends and optimal stock levels. For example, by entering a prompt such as "Calculate the optimal stock level for the next three months based on last month's sales," the AI ​​will instantly provide the analysis results.

[1813] Using this system, store managers can quickly gain insights and implement effective inventory management and sales promotion strategies.

[1814] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1815] Step 1:

[1816] The server retrieves sales data, inventory data, and customer data from the physical store's POS system and inventory management system. Specifically, the server periodically fetches data through each system's API. Sales information from the POS system and inventory information from the inventory management system are used as input, and data processed into a unified format (e.g., CSV format or data frame format) is obtained as output.

[1817] Step 2:

[1818] The server formats the acquired data into a standard format. Specifically, it converts the acquired sales and inventory data into a data frame using the Python pandas library and cleanses it to maintain consistency and integrity. Raw data (unformatted data) is used as input, and a formatted data frame is obtained as output.

[1819] Step 3:

[1820] The server sends the formatted data to a generative AI model, which analyzes the data and calculates financial indicators and sales trends. Specifically, the data is fed into an AI model built using Python's PyTorch or TensorFlow, and the trained model makes predictions. The formatted data frame is used as input, and the calculated results of financial indicators and sales trends are obtained as output.

[1821] Step 4:

[1822] The server generates growth strategies, risk management measures, and inventory management / sales promotion measures based on the analysis results obtained from the generative AI model. Specifically, a Python script is used to analyze the output of the AI ​​model and document strategic proposals. The output of the AI ​​model is used as input, and growth strategies, risk management measures, and inventory management / sales promotion measures are obtained as output.

[1823] Step 5:

[1824] The server automatically generates strategic reports based on the generated growth strategies, risk management measures, and inventory management and sales promotion measures. Specifically, it creates reports in PDF format using Python's FPDF library. The strategic proposals are used as input, and the PDF report is obtained as output.

[1825] Step 6:

[1826] The server sends the created report to the user's device. Specifically, it sends the report by email using SMTP or uploads it to cloud storage. The input is a PDF report, and the output is either emailed to the user or saved in cloud storage.

[1827] Step 7:

[1828] Users use a dedicated dashboard to check reports and send additional analysis requests. Specifically, they access the dashboard via a web application and enter additional analysis requests. The input is the request entered by the user into the dashboard, and the output is the request sent to the server.

[1829] Step 8:

[1830] The server receives user feedback and requests for additional analysis, and then resubmits the data to the generative AI model for reanalysis. Specifically, the data is fed back into the AI ​​model and reanalyzed based on the new conditions. The user request and existing data are used as input, and updated analysis results are output.

[1831] Step 9:

[1832] The server regenerates the report based on the results of the reanalysis and provides it to the user's device. Specifically, it regenerates the report in PDF format and sends it to the user. The reanalysis results are used as input, and an updated PDF report is obtained as output.

[1833] 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.

[1834] This invention relates to a system that enables companies to efficiently analyze financial data and automatically generate reports including strategies and risk management, by combining an emotion engine with a system that can provide more appropriate feedback and requests for additional analysis based on the user's emotions. Below, an embodiment of this system and specific program processing will be described in detail.

[1835] Data Collection Phase

[1836] server

[1837] The server accesses the company's financial database to retrieve the necessary financial data, such as revenue, liabilities, assets, cash flow, etc. The data retrieval process involves proper access authentication to ensure data security.

[1838] The acquired data is formatted into a standard format (e.g., CSV or data frame format) and data cleaning is performed.

[1839] Data analysis phase

[1840] server

[1841] The formatted data is fed into a generative AI model, which receives this data and calculates key financial metrics (PBR, ROE, ROA, etc.).

[1842] Based on the analysis results, the generative AI model generates corporate growth strategies (e.g., entering new markets and cost reduction measures) and risk management measures (e.g., measures to reduce liquidity risk and debt management).

[1843] Report generation phase

[1844] server

[1845] The generative AI model delivers insights that automatically generate strategic reports, including explanations and interpretations of financial metrics, suggested growth strategies, and risk management measures.

[1846] The generated reports are converted into PDF format or a dedicated web dashboard, and provided in a format that can be accessed by the company's investor relations personnel and management.

[1847] Information provision phase

[1848] server

[1849] The created report is sent to the devices of the company's IR staff and management via email or cloud services.

[1850] Terminal

[1851] The device has a dedicated dashboard where users can view reports and gain insights.

[1852] Feedback and further analysis phase

[1853] User

[1854] Users (IR personnel or management) review the report contents and send feedback or requests for additional analysis to the server.

[1855] server

[1856] The server receives feedback and requests for additional analysis from users, and sends the data back to the generative AI model for additional analysis.

[1857] The generative AI model reanalyzes based on new conditions and data and provides updated insights to the server.

[1858] server

[1859] The report is updated based on the new insights and sent back to the user's device.

[1860] Emotion engine integration phase

[1861] User terminal

[1862] A user device equipped with an emotion engine recognizes emotions from the user's facial expressions, voice, text input, etc. while the user is viewing a report.

[1863] The emotion engine analyzes the recognized user's emotional data and evaluates their stress level and interests.

[1864] server

[1865] The server optimizes the report display and additional explanations based on the emotion data received from the emotion engine. For example, if the user is feeling stressed, it automatically provides more detailed explanations and supplementary information.

[1866] Based on the needs indicated by the user's emotional data, specific analysis requests are automatically generated to the generative AI model, expanding the user's options.

[1867] Specific examples

[1868] Case Study: Medium-sized Manufacturing Company Y

[1869] background

[1870] Company Y has experienced a recent increase in revenue and needs to provide accurate and prompt information to investors. However, its traditional process required a significant amount of time and effort to analyze financial data and create proposals.

[1871] introduction

[1872] Company Y will introduce this system and upload its financial data to the server. It will also integrate an emotion engine into user devices.

[1873] Processing flow

[1874] The server accesses Company Y's database and aggregates and formats the necessary financial data.

[1875] The server sends the data to a generative AI model, which calculates financial indicators and generates growth strategies and risk management measures.

[1876] The server creates a strategic report based on the generated insights and sends it to the terminal of Company Y's IR officer.

[1877] The user (IR staff) checks the report on the dashboard, and the emotional data recognized by the emotion engine is analyzed, and feedback and additional analysis are automatically optimized.

[1878] result

[1879] Company Y was able to quickly obtain insights and provide reports optimized by the sentiment engine, enabling it to provide effective IR information to investors, which improved communication with investors and increased its reputation in the capital markets.

[1880] The above is a specific embodiment and processing content of this system. By integrating an emotion engine, customization based on the user's emotions becomes possible, realizing the construction of a more effective and user-friendly system.

[1881] The processing flow will be explained below.

[1882] Step 1:

[1883] The server accesses the company's financial database to retrieve the required financial data such as revenue, liabilities, assets, cash flow, etc. The data retrieval process involves proper access authentication and ensures a secure connection.

[1884] Step 2:

[1885] The server formats the acquired financial data into a standard format (e.g., CSV file or data frame format), and this process also involves data cleaning to remove incomplete and duplicate data.

[1886] Step 3:

[1887] The server sends the formatted data to the generative AI model, which then begins analyzing the input data.

[1888] Step 4:

[1889] The generative AI model analyzes the data and calculates key financial metrics (PBR, ROE, ROA, etc.), which are important metrics for understanding a company's financial situation.

[1890] Step 5:

[1891] Based on the analysis results, the generative AI model generates growth strategies (e.g., new market entry, cost reduction measures) and risk management measures (e.g., liquidity risk mitigation, debt management) for the company. At this stage, the AI ​​may also perform multiple scenario analysis.

[1892] Step 6:

[1893] The server automatically generates strategic reports based on the insights provided by the generative AI model, including interpretations of financial metrics, proposed growth strategies, and recommended risk management measures.

[1894] Step 7:

[1895] The server converts the generated reports into PDF format, Excel sheets, dedicated web dashboards, etc., making them accessible to the company's investor relations personnel and management.

[1896] Step 8:

[1897] The server then sends the generated reports to the terminals of the company's investor relations staff and management, and the reports are provided via email or cloud storage.

[1898] Step 9:

[1899] The device is integrated with a dedicated dashboard where users can view generated reports and gain insights into financial performance and strategic proposals.

[1900] Step 10:

[1901] The user device, which is integrated with the emotion engine, recognizes emotions in real time from facial expressions, voice, and input text while the user is reviewing a report, thereby assessing the user's stress level, interest level, etc.

[1902] Step 11:

[1903] Users (IR staff or management) review the report content and AI proposals, and provide feedback or request additional analysis based on the emotional data at the time. If the emotion engine is feeling stressed, it will optimize the report by adding a simple explanation or providing detailed data.

[1904] Step 12:

[1905] The server receives feedback and requests for additional analysis from the user and sends the data to the generative AI model again. The AI ​​model is given new analysis scenarios and conditions, and re-analysis is performed.

[1906] Step 13:

[1907] The generative AI model performs additional analysis and generates new insights, including specific metrics that users have expressed interest in and new strategic recommendations.

[1908] Step 14:

[1909] The server updates the report based on the new insights and sends it back to the user's device, where the latest report is displayed in real time on the dashboard.

[1910] These are the specific processing steps of this system. At each step, the server, generative AI model, terminal, and user play their respective roles to achieve efficient and accurate analysis and reporting of financial data. The integration of an emotion engine enables customization based on user emotions, resulting in a more user-friendly system.

[1911] Example 2

[1912] 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."

[1913] Analyzing financial information and generating reports in companies requires a great deal of time and effort using conventional methods. Furthermore, if the generated reports do not reflect the specific needs and feelings of users, effective decision-making becomes difficult. Therefore, there is a need for efficient analysis of financial information, automatic generation of highly accurate reports, and provision of reports whose content is optimized based on user feelings.

[1914] The specification processing by the specification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for aggregating and formatting a company's financial information, means for analyzing the financial information using a generative AI model and calculating financial indicators, means for generating a growth strategy and a risk management measure based on the analysis results using the generative AI model, means for automatically generating a strategic report based on the generated growth strategy and the risk management measure, means for providing the report to a user terminal, means for receiving feedback and additional analysis requests from the user and performing reanalysis, and means for collecting and analyzing user emotion data using an emotion engine and optimizing the report content. This enables efficient analysis of financial information, rapid generation of reports, and provision of optimal content based on the user's emotions.

[1915] "Financial information" refers to data that shows a company's financial status, such as its revenue, liabilities, assets, and cash flow.

[1916] A "generative AI model" is an artificial intelligence model that uses machine learning and deep learning technologies to analyze financial information and calculate financial indicators.

[1917] "Financial indicators" are indicators used to quantitatively evaluate a company's financial condition, and include, for example, PBR (price-to-book ratio), ROE (return on equity), and ROA (return on assets).

[1918] A "growth strategy" is a general term for the plans and measures that a company implements in order to achieve sustainable growth.

[1919] "Risk management measures" are specific policies and measures to assess the risks that a company may face and reduce or manage them.

[1920] A "strategic report" is a document that summarizes financial indicators, growth strategies, and risk management measures generated based on financial information, and compiles proposals and views on management strategies.

[1921] "User terminal" refers to a device, such as a computer or mobile device, used by a company's investor relations personnel or management to view reports and submit feedback.

[1922] "Feedback and further analysis requests" are comments provided by users regarding the contents of a report or requests for further data analysis.

[1923] An "emotion engine" is a technology that recognizes and analyzes emotions from a user's facial expressions, voice, text input, etc.

[1924] "Emotion data" refers to data that indicates the user's emotional state as recognized and analyzed by the emotion engine.

[1925] Optimization is the adjustment and improvement of system or process parameters to efficiently achieve a specific objective.

[1926] MODE FOR CARRYING OUT THE INVENTION

[1927] This invention relates to a system that enables companies to efficiently analyze financial information and automatically generate reports including strategies and risk management, by combining an emotion engine with a system that can provide more appropriate feedback and requests for additional analysis based on the user's emotions. Below, an embodiment of this system and specific program processing are described in detail.

[1928] Data Collection Phase

[1929] server

[1930] The server accesses the company's financial database and retrieves the required financial information such as revenue, liabilities, assets, cash flow, etc. The data retrieval process involves authentication using an API key and / or authentication token for database connection.

[1931] The server formats the acquired data into a standard format (e.g., CSV or data frame format) using the Python Pandas library.

[1932] Furthermore, missing values ​​and outliers are handled by filling in the missing values ​​with the mean value and excluding outliers.

[1933] Data analysis phase

[1934] server

[1935] The server inputs the formatted financial information into the generative AI model, sending the data to the generative AI model via the API as a POST request.

[1936] A prompt sentence is generated and fed into the generative AI model along with financial information retrieved from the database. An example prompt sentence is as follows:

[1937] "Please suggest the optimal growth strategy based on the company's revenue data."

[1938] The generative AI model analyzes input data and calculates key financial metrics (PBR, ROE, ROA, etc.) based on pre-defined formulas and algorithms.

[1939] The generative AI model generates corporate growth strategies and risk management measures based on the results of analyzing financial indicators.

[1940] Report generation phase

[1941] server

[1942] The server automatically generates strategic reports based on the insights returned by the generative AI model, including explanations and interpretations of financial metrics, suggested growth strategies, and risk management measures.

[1943] A template engine (e.g., Jinja2) is used to generate reports and output formats such as HTML and PDF.

[1944] Convert the generated report into PDF format or a dedicated web dashboard. For example, use a PDF generation tool to convert an HTML template into a PDF.

[1945] Information provision phase

[1946] server

[1947] The server then sends the created reports to the devices of the company's investor relations staff or management. In some cases, the reports are sent as PDF attachments via email, or a link to a cloud service is shared.

[1948] Terminal

[1949] The device has a dedicated dashboard where users can view reports and gain various insights.

[1950] Feedback and further analysis phase

[1951] User

[1952] Users (IR staff and management) check the contents of the report and send feedback or requests for additional analysis to the server. The dashboard provides input fields for feedback forms and requests for additional analysis.

[1953] server

[1954] The server receives feedback and requests for additional analysis from the user, sends the data to the generative AI model again for additional analysis, and creates a new prompt sentence and inputs it to the generative AI model.

[1955] It reanalyzes the data based on new conditions and data, and provides updated insights to the server.

[1956] The server updates the report based on the new insights and sends it back to the user's device.

[1957] Emotion engine integration phase

[1958] User terminal

[1959] The user device equipped with the emotion engine recognizes emotions from the user's facial expressions, voice, text input, etc. while viewing a report. This requires a device equipped with a camera and microphone.

[1960] The emotion engine analyzes the recognized user's emotional data and evaluates their stress level and interests.

[1961] server

[1962] The server optimizes the report display and additional explanations based on the emotion data received from the emotion engine. For example, if the user is feeling stressed, it automatically provides more detailed explanations and supplementary information.

[1963] Based on the needs indicated by the user's emotional data, specific analysis requests are automatically generated to the generative AI model, expanding the user's options.

[1964] Examples and prompts

[1965] Examples:

[1966] Case Study: Medium-sized Manufacturing Company Y

[1967] With the recent increase in revenue, Company Y needs to provide accurate and prompt information to investors. However, in the conventional process, analyzing financial information and creating proposals required a great deal of time and effort. Company Y will introduce this system and upload its financial information to a server. It will also integrate an emotion engine into user devices.

[1968] Process flow:

[1969] The server accesses Company Y's database and aggregates and formats the necessary financial information.

[1970] The server sends the data to a generative AI model, which calculates financial indicators and generates growth strategies and risk management measures.

[1971] The server creates a strategic report based on the generated insights and sends it to the terminal of Company Y's IR officer.

[1972] The user (IR staff) checks the report on the dashboard, and the emotional data recognized by the emotion engine is analyzed, and feedback and additional analysis are automatically optimized.

[1973] Example prompt sentence:

[1974] "Based on Company Y's financial data, please calculate the latest financial indicators (PBR, ROE, ROA, etc.) and propose growth strategies and risk management measures. Also, please use an emotion engine to optimize the report content based on user feedback."

[1975] The above is a specific embodiment and processing content of this system. By integrating an emotion engine, customization based on the user's emotions becomes possible, realizing the construction of a more effective and user-friendly system.

[1976] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1977] Program processing steps

[1978] Data Collection Phase

[1979] Step 1:

[1980] server

[1981] The server accesses the company's financial database and retrieves the required financial information such as revenue, liabilities, assets, cash flow, etc. The input is the database authentication information and the output is the retrieved financial information.

[1982] Specifically, it uses an API key or authentication token for database connection to execute an SQL query to retrieve data.

[1983] Step 2:

[1984] server

[1985] The server formats the retrieved financial information into a standard format (CSV or data frame format). The input is the retrieved raw data, and the output is the formatted data.

[1986] For example, use Python's Pandas library to convert the data into a data frame, organize the necessary columns, and convert data types.

[1987] Step 3:

[1988] server

[1989] The server cleans the financial information: the input is formatted data, and the output is cleaned data.

[1990] Specifically, the process involves filling in missing values ​​with the average value and excluding outliers.

[1991] Data analysis phase

[1992] Step 4:

[1993] server

[1994] The server sends the formatted and cleaned financial information to a generative AI model, whose inputs are the cleaned data and generated prompts, and whose output is financial metrics and insights.

[1995] Specifically, the data is sent to the generative AI model via an API as a POST request. An example prompt might be: "Based on the company's revenue data, please propose the optimal growth strategy."

[1996] Step 5:

[1997] Generative AI Models

[1998] The generative AI model analyzes input data and calculates key financial indicators (PBR, ROE, ROA, etc.) The input is the cleaned data and prompt statements, and the output is the calculated financial indicators.

[1999] Financial indicators are calculated using pre-defined formulas and algorithms.

[2000] Step 6:

[2001] Generative AI Models

[2002] The generative AI model generates a company's growth strategy and risk management measures from the results of analyzing financial indicators. The input is the calculated financial indicators, and the output is the generated growth strategy and risk management measures.

[2003] Specifically, the generated text data is inserted into a report template.

[2004] Report generation phase

[2005] Step 7:

[2006] server

[2007] The server automatically generates strategic reports based on the insights returned by the generative AI model. The input is the generated growth strategy and risk management measures, and the output is the completed report.

[2008] A template engine (e.g., Jinja2) is used to generate reports and convert them into formats such as HTML and PDF.

[2009] Step 8:

[2010] server

[2011] The server converts the generated report into PDF format or a dedicated web dashboard. The input is the generated report and the output is the converted file format.

[2012] As a specific operation, for example, a PDF generation tool is used to convert the HTML template into a PDF.

[2013] Information provision phase

[2014] Step 9:

[2015] server

[2016] The server then sends the created report to the terminals of the company's IR staff and management. The input is a report in PDF format or web dashboard format, and the output is a report sent to the user's terminal.

[2017] Specific actions include sending a PDF as an attachment via email or sharing a link to a cloud service.

[2018] Step 10:

[2019] Terminal

[2020] The terminal has a dedicated dashboard where users can check reports. The input is a report in PDF format or web dashboard format, and the output is the checked report.

[2021] You can access reports and gain various insights through the dashboard.

[2022] Feedback and further analysis phase

[2023] Step 11:

[2024] User

[2025] Users (IR staff or management) check the contents of the report and send feedback or requests for additional analysis to the server. The input is feedback on the report or requests for additional analysis, and the output is the feedback sent to the server.

[2026] Provide a feedback form or input field for additional analysis requests on the dashboard.

[2027] Step 12:

[2028] server

[2029] The server receives feedback and requests for additional analysis from users and sends the data to the generative AI model again for further analysis. The input is the received feedback and requests for additional analysis, and the output is the reanalyzed insights.

[2030] Create new prompts and feed them into the generative AI model, which then reanalyzes them and generates new insights.

[2031] Step 13:

[2032] server

[2033] The server updates the report based on the new insights and sends it back to the user's device. The input is the reanalyzed insights and the updated report, and the output is the updated report.

[2034] Allow users to view updated reports.

[2035] Emotion engine integration phase

[2036] Step 14:

[2037] User terminal

[2038] A user device equipped with an emotion engine recognizes emotions from the user's facial expressions, voice, text input, etc. while the user is viewing a report. The input is the user's facial expressions, voice, and text data, and the output is emotion data.

[2039] This requires a device with a camera and microphone.

[2040] Step 15:

[2041] server

[2042] The server optimizes the display content of the report and additional explanations based on the emotion data received from the emotion engine. The input is emotion data, and the output is an optimized report.

[2043] If the user is feeling stressed, more detailed explanations and supplementary information will be automatically provided.

[2044] Step 16:

[2045] server

[2046] The server automatically generates specific analysis requests to the generative AI model based on the needs indicated by the user's emotional data, expanding the user's options. The input is the emotional data and the generated prompt, and the output is the additional analysis results.

[2047] Specifically, it generates a new prompt sentence based on the emotional data and sends that prompt sentence to the generative AI model.

[2048] The above is the specific processing flow of this system and the operation at each step. By clearly explaining the specific operations and data processing methods, the details of the system will become clearer.

[2049] (Application example 2)

[2050] 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."

[2051] Traditional financial data analysis systems required a great deal of time and effort for companies to quickly and efficiently understand their financial situation and make strategic decisions. Furthermore, they lacked feedback based on user emotions and intuition, making it difficult for users to gain a deeper understanding of reports and appropriately request additional analysis. Furthermore, in brick-and-mortar store operations, understanding the emotions of staff and customers in real time and providing optimal service was a challenge.

[2052] 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.

[2053] In this invention, the server includes a means for aggregating and formatting a company's financial data, a means for analyzing the financial data using a generative AI model to calculate financial indicators, and a means for generating growth strategies and risk management measures. This enables companies to gain quick and accurate insights. Furthermore, the user terminal is equipped with an emotion engine, providing a means for recognizing user emotions and optimizing report content based on the recognition results. Furthermore, the system includes a means for displaying reports via a dedicated dashboard and automatically optimizing report content based on the emotion recognition results. This enables efficient user feedback and highly accurate requests for additional analysis, enabling optimal service provision even in brick-and-mortar store operations.

[2054] "Financial data" refers to financial information held by a company, such as revenues, liabilities, assets, and cash flow.

[2055] A "generative AI model" is an artificial intelligence model that analyzes input data and automatically calculates financial indicators, generates growth strategies, and generates risk management measures.

[2056] A "user terminal" is a device used to check reports, send feedback, and provide information based on emotion recognition results.

[2057] An "emotion engine" is a technology for recognizing and analyzing emotions from a user's facial expressions, voice, text input, etc.

[2058] "Financial indicators" are indicators used to evaluate a company's financial condition and performance, and include PBR, ROE, ROA, etc.

[2059] A "growth strategy" is a plan or policy for a company to achieve sustainable growth.

[2060] "Risk management measures" are strategies and measures used to mitigate or avoid risks that a company may face.

[2061] A "strategic report" is a document that includes explanations and interpretations of financial indicators, proposed growth strategies, and risk management measures.

[2062] A "dedicated dashboard" is an interface that visually displays generated reports and is easily accessible to users.

[2063] "Feedback" refers to the reactions and opinions users provide to reports.

[2064] An "additional analysis request" is an action in which a user requests the server to perform further analysis based on a report or analysis results.

[2065] This section describes a specific system for implementing this invention. The system aggregates and formats a company's financial data, analyzes it using a generative AI model, and calculates various financial indicators. Furthermore, it generates growth strategies and risk management measures based on the analysis results, and automatically generates strategic reports. Additionally, it can recognize user emotions using a user device equipped with an emotion engine and optimize the content of the report.

[2066] Data collection and formatting

[2067] The server accesses the company's financial database and retrieves the necessary financial data, such as revenue, liabilities, assets, cash flow, etc. The data is retrieved with appropriate access authentication and then formatted into a standard format. During this process, the data is also cleaned to remove missing or outlier values.

[2068] Data analysis

[2069] The server inputs the formatted financial data into a generative AI model to calculate key financial indicators (e.g., PBR, ROE, ROA, etc.). This model can use OpenAI's GPT-4 or Google's BERT. Based on the analysis results, the server generates insights that suggest growth strategies and risk management measures for the company.

[2070] report generation

[2071] Based on the insights generated, strategic reports are automatically generated, including explanations and interpretations of financial indicators, proposed growth strategies, and risk management measures, and can be viewed in PDF format or on a dedicated web dashboard.

[2072] Input and Feedback

[2073] The server sends aut...

Claims

1. A means of aggregating and formatting corporate financial data; A means for analyzing financial data using a generative AI model to calculate financial indicators; A means for generating growth strategies and risk management measures based on the analysis results using a generative AI model; a means for automatically generating a strategic report based on the generated growth strategy and risk management measures; means for providing said report to a user terminal; a means for receiving feedback or additional analysis requests from users and performing reanalysis; A system including:

2. The system of claim 1 , wherein the generative AI model comprises means for calculating financial indicators such as PBR, ROE, and ROA from financial data.

3. The system of claim 1 , wherein the means for providing the report to the user comprises means for displaying the report via a dedicated dashboard.

Images