System

Abstract

A system is provided.SOLUTION: A system comprising means for obtaining historical dividend data, financial information, market trend data and shareholder benefits, means for predicting future dividends using a generative AI model trained based on the historical dividend data and the financial information, means for analyzing the shareholder benefits and scoring the results based on user preferences, and means for displaying the predicted dividends and the results to the user.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] In recent years, extremely low interest rates on bank deposits have led to rising prices and a decline in asset value. As a result, many people are seeking ways to effectively manage their assets, and stock investment is gaining attention as a new investment method. However, beginners to stock investing find it difficult to interpret charts and financial statements, creating a high barrier to entry. Furthermore, with the launch of the new NISA system in 2024, an increase in first-time stock investors is expected, but many of them lack specialized knowledge. This has led to a demand for a simple tool specifically designed to provide information on dividends and shareholder benefits. [Means for solving the problem]

[0005] The present invention is a system that includes a means for acquiring past dividend data, financial information, market trend data, and shareholder benefit details; a means for training a generative AI model based on this data to predict future dividends; a means for analyzing the details of shareholder benefits and scoring the results based on user preferences; and a means for displaying the predicted dividends and analysis results to the user. This allows even novice stock investors to intuitively grasp information about dividends and shareholder benefits, making investment decision-making easier. Furthermore, the system achieves high prediction accuracy by collecting data using an external API and analyzing the data with a generative AI model using a linear regression model.

[0006] "Past dividend data" is historical information about dividends that a company has paid to shareholders in the past.

[0007] "Financial information" refers to data that indicates a company's financial status, including revenue, liabilities, assets, cash flow, and the like.

[0008] "Market trend data" refers to data that shows market activity such as price fluctuations and volume of the stock market as a whole and individual stocks.

[0009] "Shareholder benefits" refers to the perks and services that a company provides to its shareholders, as well as detailed information about them.

[0010] A "generative AI model" is an algorithmic model of artificial intelligence used to make specific predictions or analyses based on acquired data.

[0011] "Dividend forecasting" is the act of predicting future dividend amounts based on past data and current financial conditions.

[0012] "Analysis results" refers to the conclusions and insights obtained after analyzing data, and is information that specifically supports user decision-making.

[0013] "Scoring" is the act of assigning a score to data or objects based on specific evaluation criteria.

[0014] An "external API" is a program interface for using external data and functions, and is a means of accessing data from services provided by third parties.

[0015] A "linear regression model" is a model used in statistics and machine learning that expresses the relationship between given data using simple or multiple straight lines. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

[0024] [First embodiment]

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

[0026] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

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

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

[0029] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

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

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

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

[0033] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

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

[0035] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

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

[0037] This invention is a system that enables beginners to make effective investment decisions in stock investments, and includes functions for predicting dividends and analyzing shareholder benefits. The system is composed of a server and a terminal, and is designed to allow users to easily obtain and understand investment information.

[0038] 1. Data Acquisition

[0039] server:

[0040] The server retrieves historical dividend data, financial information, market trend data, and shareholder benefits from external APIs. This data consists of historical information on dividends paid by companies in the past, financial status including revenue, liabilities, assets, and cash flow, as well as market activity data such as overall market price fluctuations and volume.

[0041] 2. Training and Predicting the Dividend Prediction Model

[0042] server:

[0043] The server trains a generative AI model using the acquired historical dividend data and financial information. This model uses machine learning algorithms such as linear regression models to predict a company's future dividends with high accuracy. To do this, the data is first divided into training data and test data, and the model is then built and trained. The trained model is then used to predict dividends based on new financial information.

[0044] 3. Shareholder Benefit Analysis

[0045] server:

[0046] The server analyzes the content of the shareholder perks and evaluates their value and attractiveness. This evaluation also takes into account the user's preferences. For example, if a user prefers perks in a particular category, such as food or travel, a high score will be assigned to perks in that category. Also, if the value of a perk exceeds the user's minimum expectations, an additional score will be assigned to that perk.

[0047] 4. Displaying Information

[0048] Device:

[0049] The terminal displays the predicted dividends and analyzed shareholder benefit information received from the server to the user. The user makes investment decisions based on this information. The displayed information is presented in a visually easy-to-understand format, including predicted dividend amounts by year, benefit details, and scores.

[0050] Specific use cases

[0051] User:

[0052] For example, when User A uses this system to make an investment decision, he or she first inputs his or her basic investment preferences (e.g., he or she likes shareholder benefits in the food category, and wants benefits worth at least 1,000 yen).Then, the device sends this information to the server, which retrieves the necessary data from an external API, trains a generative AI model, and performs dividend prediction and shareholder benefit analysis.

[0053] The terminal displays predicted dividend information and a list of shareholder benefits scored based on User A's preferences. Based on this, User A can easily decide which stocks to invest in. In this way, even beginners can significantly lower the investment hurdles and support efficient investment decisions.

[0054] The above describes a dividend forecasting and shareholder benefit analysis system for beginners in stock investment as an embodiment of the present invention. This system is designed to lower the barrier to investment and enable even beginners to easily make investment decisions.

[0055] The processing flow will be explained below.

[0056] Step 1:

[0057] The server retrieves historical dividend data, financial information, market trend data, and shareholder benefits from external APIs, including historical information on dividends paid by companies, financial status including revenue, liabilities, assets, and cash flow, as well as data showing market activity such as overall market price fluctuations and volume.

[0058] Step 2:

[0059] The server trains a generative AI model using the acquired historical dividend data and financial information. The data is divided into training data and test data, and training is performed using a generative AI model (e.g., a linear regression model). Once trained, the model is used to predict future dividends based on new financial information.

[0060] Step 3:

[0061] The server uses the trained generative AI model to predict future dividends based on new financial information data. This process uses the latest market trend data and the company's financial situation as inputs to predict future dividend amounts.

[0062] Step 4:

[0063] The server analyzes the content of shareholder benefits. It analyzes the shareholder benefit data and scores it based on the preferences and conditions entered by the user (e.g., preferred benefit categories and expected minimum value). This allows it to extract attractive benefit information that matches the user's preferences.

[0064] Step 5:

[0065] The terminal displays the predicted dividend information and scored shareholder benefit information received from the server to the user. The displayed information is presented in a visually easy-to-understand format, including the predicted dividend amount for each fiscal year and the scored benefit details.

[0066] Step 6:

[0067] Users make investment decisions based on the information provided by the terminal. They can use the predicted dividend amount and analyzed preferential treatment information as a reference to invest in the stocks that are most suitable for them.

[0068] Step 7:

[0069] The device sends feedback on the user's investment history and new preferences to the server, which then updates the model based on this information to further improve prediction accuracy in future rounds, thereby continuously improving the user's investment experience.

[0070] Example 1

[0071] 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."

[0072] Beginners in stock investment often find it difficult to predict corporate dividends and evaluate shareholder benefits. In particular, because information is not provided that meets the preferences or minimum desired value of individual investors, there is a lack of information to make decisions and it is difficult to make appropriate investment decisions.

[0073] 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.

[0074] In this invention, the server includes means for acquiring past dividend data, financial information, market trend data, and shareholder benefit details, means for storing data acquired from an external API in a database, means for dividing the data into training data and test data, means for predicting future dividends using a generative AI model trained on the past dividend data and financial information, means for analyzing the details of shareholder benefits and scoring the analysis results based on user preferences, means for displaying the predicted dividends and the analysis results to the user, and means for collecting user preferences and minimum desired values. This provides appropriate information that even beginners can use to easily make investment decisions, enabling efficient investment decisions.

[0075] "Past dividend data" is historical information about dividends paid by a company within a certain period of time, and indicates the company's dividend payment trends and history.

[0076] "Financial information" is data that represents a company's financial position and performance, such as its revenues, liabilities, assets, and cash flow.

[0077] "Market trend data" refers to data that indicates market trends, such as price fluctuations and trading volume across the market, and is used for investment decisions.

[0078] "Shareholder benefits" refers to the specific perks and benefits that a company provides to shareholders, and includes a variety of categories such as food and travel vouchers.

[0079] An "External API" is an application programming interface for communicating with external data sources and obtaining required data.

[0080] A "generative AI model" is a computational model that uses machine learning algorithms to learn from specific datasets and make predictions and analyses.

[0081] "User preferences" are the preferences and desires that individual investors have regarding specific categories and values, and are information that influences investment decisions.

[0082] "Minimum desired value" refers to the minimum value that users expect from shareholder benefits, and is a standard below which they will not be satisfied.

[0083] "Training data" is a dataset used to build and optimize a machine learning model, improving its accuracy.

[0084] "Test data" is a dataset used to evaluate the performance of a trained model and to confirm the model's predictive accuracy.

[0085] A database is a system that efficiently manages and stores structured data and allows quick access when needed.

[0086] This invention is a system that enables beginners to make effective investment decisions. The system includes functions for predicting dividends and analyzing shareholder benefits, and is composed of a server and a terminal. It is designed to allow users to easily obtain and understand investment information.

[0087] Data Acquisition

[0088] The server uses a RESTful API to retrieve historical dividend data, financial information, market trend data, and shareholder benefits from external APIs. The data is received in JSON format and stored in a MySQL database.

[0089] Examples:

[0090] The server retrieves historical dividend data from http: / / api.marketdata.com / dividends and inserts it into a "Company Dividend Table."

[0091] Model training and prediction

[0092] The server splits the acquired data into training data and test data. For example, 80% of the data is used for training and 20% for testing. The server then uses a machine learning library such as Scikit-learn to train a linear regression model based on the training data.

[0093] Examples:

[0094] The server builds a model to predict dividends using data such as revenue, liabilities, and assets of "Company A."

[0095] Analysis of shareholder benefits

[0096] The server scores the shareholder benefits based on user preference information (e.g., specific benefit categories and minimum desired value). This scoring is adjusted according to the user's individual preferences.

[0097] Examples:

[0098] The server gives a high score to a special offer worth 5,000 yen in the food category, and adds an additional score if the value exceeds the user's minimum desired value.

[0099] Displaying Information

[0100] The terminal displays the predicted dividend information and scoring results sent from the server to the user in a visually easy-to-understand format, allowing the user to make investment decisions based on this information.

[0101] Examples:

[0102] The terminal will display "Company A's projected dividend amount for 2023: 120 yen" and "Company A's shareholder benefits in the food category: score 90 points."

[0103] Usage example

[0104] The specific steps for a user to use the system are as follows: First, the user enters their basic investment preferences (e.g., they like shareholder benefits in the food category and want benefits worth at least 1,000 yen). The device sends this information to the server, which then collects the necessary data from external APIs, trains a generative AI model, and analyzes dividend predictions and shareholder benefits. The device then displays a list of shareholder benefits scored based on the predicted dividend information and the user's preferences.

[0105] Example prompts for generative AI models

[0106] "Based on the following financial data, predict the company's dividend for next year."

[0107] "Please score the benefits in the food category based on the shareholder benefits information."

[0108] This system allows even beginners to make investment decisions easily and effectively, supporting efficient investment decisions.

[0109] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0110] Step 1:

[0111] The server retrieves past dividend data, financial information, market trend data, and shareholder benefits details from an external API. It sends an HTTP request to the API endpoint and receives JSON-formatted data in response. This process aggregates the necessary investment data on the server.

[0112] Specific behavior:

[0113] The server sends an HTTP GET request to http: / / api.marketdata.com / dividends to retrieve the dividend amount for each company by year.

[0114] input:

[0115] External API Endpoints

[0116] output:

[0117] Investment data in JSON format

[0118] Step 2:

[0119] The server parses the received JSON data and saves it in a MySQL database. When saving the data to the database, the data is converted and formatted as necessary.

[0120] Specific behavior:

[0121] The server inserts "Company A's 2022 dividend amount: 100 yen" into the "Company Dividend Table."

[0122] input:

[0123] Investment data in JSON format

[0124] output:

[0125] Formatted data stored in a database

[0126] Step 3:

[0127] The server extracts historical dividend data and financial information from the database and splits it into training and test data, typically 80% as training data and 20% as test data.

[0128] Specific behavior:

[0129] The server extracts dividend data from 2010 to 2019 from the database as training data and data from 2020 as test data.

[0130] input:

[0131] Historical dividend data and financial information in the database

[0132] output:

[0133] training dataset, test dataset

[0134] Step 4:

[0135] The server uses the training data to train a generative AI model, which is a linear regression model built using libraries such as Scikit-learn.

[0136] Specific behavior:

[0137] The server trains the model based on specific financial metrics such as revenue, liabilities, and assets.

[0138] input:

[0139] Training dataset

[0140] output:

[0141] Pre-trained generative AI models

[0142] Step 5:

[0143] The server feeds new financial information into the trained generative AI model to predict future dividends, which are then compared to test data to confirm accuracy.

[0144] Specific behavior:

[0145] The server inputs the new financial information into the model to predict next year's dividends.

[0146] input:

[0147] New Financial Information

[0148] output:

[0149] Projected dividend amount

[0150] Step 6:

[0151] The terminal collects the user's preferences and minimum desired value and sends this information to the server, allowing the system to respond to the user's individual preferences.

[0152] Specific behavior:

[0153] The user inputs that he / she likes shareholder benefits in the food category and wants benefits worth at least 1,000 yen.

[0154] input:

[0155] User preferences, minimum desired value

[0156] output:

[0157] User information sent to the server

[0158] Step 7:

[0159] The server scores shareholder benefit information based on the user's preferences. It analyzes the content of a company's shareholder benefits and calculates a score by comparing it with the user's preferences.

[0160] Specific behavior:

[0161] The server will give a high score to perks worth 5,000 yen in the food category, and will add more points if the minimum desired value is exceeded.

[0162] input:

[0163] User information, shareholder benefits

[0164] output:

[0165] Scored shareholder benefits information

[0166] Step 8:

[0167] The terminal displays the predicted dividend information and scoring results sent from the server to the user in a visually easy-to-understand format, allowing the user to make investment decisions based on this information.

[0168] Specific behavior:

[0169] The terminal will display "Company A's projected dividend amount for 2023: 120 yen" and "Company A's shareholder benefits in the food category: score 90 points."

[0170] input:

[0171] Predicted dividend information and scoring results from the server

[0172] output:

[0173] Investment information displayed to the user

[0174] (Application example 1)

[0175] 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."

[0176] For beginners in stock investment, collecting and analyzing the information necessary to make effective investment decisions is extremely difficult. In particular, predicting dividends and evaluating shareholder benefits are complex and require specialized knowledge and experience. Providing investment information tailored to user preferences is also important, but achieving this poses many technical challenges. A system that solves these problems and allows even beginners to easily make investment decisions is needed.

[0177] 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.

[0178] In this invention, the server includes means for acquiring past dividend data, financial information, market trend data, and shareholder benefit details, means for predicting future dividends using a generative AI model trained on the past dividend data and financial information, means for analyzing the details of shareholder benefits and scoring the analysis results based on user preferences, means for displaying the predicted dividends and the analysis results to the user, and a smartphone application means for visually presenting dividend forecasts and shareholder benefit evaluation information based on a user profile. This allows even beginners to stock investment to easily make effective investment decisions.

[0179] "Past dividend data" is historical information about dividends paid by a company in the past.

[0180] "Financial information" is data about a company's financial condition, including its revenues, liabilities, assets, and cash flow.

[0181] "Market trend data" refers to data that indicates market activity such as price fluctuations and trading volume across the market.

[0182] "Shareholder benefits" refers to detailed information about the perks and services that a company provides to its shareholders.

[0183] A "generative AI model" is a model that contains machine learning algorithms that are trained using historical data and designed to predict future values.

[0184] "User preferences" are personal evaluation criteria or preferences that a user has for a particular shareholder benefit category or minimum value.

[0185] A "smartphone application means" is a software application that is installed on a smartphone device and provides functionality through a user interface.

[0186] "Scoring" is the process of assigning a rating based on specific criteria.

[0187] "Visually presenting" refers to displaying data and information in an easy-to-understand manner using graphs, charts, etc.

[0188] A "user profile" is individualized settings information that includes a user's preferences and history information.

[0189] An "external API" is an application programming interface for obtaining data from external systems or services.

[0190] A "linear regression model" is a statistical machine learning model that makes predictions using linear relationships between variables.

[0191] This invention is a system that enables beginners to make effective investment decisions in stock investments, and includes functions for predicting dividends and analyzing shareholder benefits. The system is composed of a server and a smartphone terminal, and is designed to allow users to easily obtain and understand investment information.

[0192] Data Acquisition

[0193] First, the server uses an external API to retrieve historical dividend data, financial information, market trend data, and shareholder benefits. This data includes historical information on dividends paid by companies, financial status such as revenue, liabilities, assets, and cash flow, as well as market activity data such as overall market price fluctuations and trading volume.

[0194] Training and predicting dividend prediction models

[0195] Next, the server trains a generative AI model using the acquired historical dividend data and financial information. A linear regression model is used for this model. The model is built using separate training and test data, and the trained model is used to make dividend predictions based on new financial information.

[0196] Shareholder Benefit Analysis

[0197] The server then analyzes the content of the shareholder benefits and scores the analysis results based on the user's preferences, taking into account the user's preferences for specific categories (e.g., food, travel) and minimum value criteria (e.g., 1,000 yen or more).

[0198] Displaying Information

[0199] The acquired information and forecast results are provided visually to users through a smartphone application. The application displays dividend forecasts and shareholder benefit evaluation information based on the user profile. Users can visually check the forecast dividend amount and benefit details for each year, as well as their scores, and make investment decisions.

[0200] Hardware and software used

[0201] This system is implemented using Python and its main libraries (requests, numpy, sklearn). The hardware required is a server computer and a smartphone.

[0202] Examples and prompts

[0203] For example, a user may specify that they like shareholder benefits in the food category and would like them to be worth at least 1,000 yen. The server uses a model to predict dividends based on new financial information and scores the benefits. The prediction results and evaluation are then provided to the user via a smartphone application.

[0204] Example prompt sentence:

[0205] User preference: Food, Minimum desired value: 1000 yen

[0206] Dividend forecast:

[0207] Financial Data: New Financial Data

[0208] Shareholder Benefit Analysis:

[0209] Priority Category: Food

[0210] Calculating shareholder benefits score

[0211] In this way, even beginners can easily make effective investment decisions.

[0212] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0213] Step 1: Data Acquisition

[0214] The server uses an external API to obtain historical dividend data, financial information, market trend data, and shareholder benefits. The input is the data request from the API, and the output is the obtained data. Specifically, the server accesses the API endpoint and obtains the required data in JSON format.

[0215] Step 2: Data Preprocessing

[0216] The server preprocesses the acquired data. The input is the data acquired in step 1, and the output is the preprocessed data. Specifically, it complements missing values, removes outliers, and normalizes the data.

[0217] Step 3: Train the dividend prediction model

[0218] The server uses the preprocessed data to train a generative AI model (linear regression model). The input is the preprocessed data, and the output is the trained AI model. Specifically, the model is trained using financial information as features and dividend data as target values.

[0219] Step 4: Dividend Forecast

[0220] The server inputs new financial information and uses the trained AI model to predict future dividends. The inputs are new financial information and the trained model, and the output is the predicted dividend. Specifically, new financial data is input into the model and dividends are predicted.

[0221] Step 5: Shareholder Benefit Analysis and Scoring

[0222] The server analyzes the content of shareholder benefits and scores them based on the user's preferences. The input is shareholder benefit data and user preference data, and the output is the scoring result. Specifically, the server evaluates the benefits based on the categories and value criteria specified by the user and calculates a score.

[0223] Step 6: Get User Information

[0224] The terminal acquires the user's preferences and investment goals. The input is the user's input data, and the output is the user profile. Specifically, the user sets the preferred categories and minimum value through the interface.

[0225] Step 7: Viewing information

[0226] The terminal visually displays the predicted payouts and analysis results received from the server to the user. The input is data from the server, and the output is what is displayed on the user's screen. Specifically, the predicted payout amounts and preferential treatment scores are displayed in graphs and tables. The terminal also provides an interface that is easy for the user to understand.

[0227] Step 8: Recording User Actions

[0228] The terminal records the user's actions, such as investment decisions and setting changes. The input is the user's action data, and the output is the recorded log data. Specifically, various operations performed by the user are recorded in a log and used for future data analysis and improvements.

[0229] 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.

[0230] This invention is a system that recognizes and analyzes users' emotions when it comes to stock investment, and supports investment decisions based on that information. In particular, by combining an emotion engine with dividend forecasting and shareholder benefit analysis, it provides personalized investment advice tailored to the individual needs of each user.

[0231] 1. Data Acquisition

[0232] server:

[0233] The server retrieves historical dividend data, financial information, market trend data, and shareholder benefits from external APIs, including historical information on dividends paid by companies, financial status such as revenue, liabilities, assets, and cash flow of companies, and data showing market activity such as overall market price fluctuations and volume.

[0234] 2. Training and Predicting the Dividend Prediction Model

[0235] server:

[0236] The server trains a generative AI model using the acquired historical dividend data and financial information. This model is trained using machine learning algorithms such as linear regression models to predict future dividends for companies. To do this, the data is first divided into training data and test data, and the model is then built and trained. The trained model is then used to predict dividends based on new financial information.

[0237] 3. Shareholder Benefit Analysis

[0238] server:

[0239] The server analyzes the content of the shareholder benefits and evaluates their value and attractiveness. This involves analyzing the shareholder benefit data and scoring them based on the preferences and conditions entered by the user (e.g., preferred benefit categories and expected minimum value).

[0240] 4. Implementing the Emotion Engine

[0241] server:

[0242] The server includes an emotion engine that analyzes the user's emotions. The emotion engine analyzes the user's facial expressions, voice tone, and input text as input data to recognize the user's emotions in real time. This emotion data is used to personalize the results of dividend forecasts and shareholder benefit analysis.

[0243] 5. Display of Information

[0244] Device:

[0245] The terminal displays the predicted dividend information and scored shareholder benefit information received from the server to the user. The displayed information is presented in a visually easy-to-understand format, including predicted dividend amounts for each fiscal year and scored benefit details. Furthermore, the emotional results analyzed by the emotion engine are reflected, allowing the user to receive the information in a relaxed state.

[0246] Specific use cases

[0247] User:

[0248] For example, when User A uses this system to make an investment decision, he or she first inputs basic investment preferences (e.g., he or she likes shareholder benefits in the food category and wants benefits worth at least 1,000 yen). The device then sends this information to the server. The server retrieves the necessary data from an external API and trains a generative AI model to predict dividends and analyze shareholder benefits. At the same time, the emotion engine analyzes the user's emotional state in real time and personalizes the displayed information based on the obtained emotional data.

[0249] As a result, the device displays predicted dividend information and shareholder benefit information scored based on User A's preferences. Furthermore, the information display is adjusted according to User A's emotional state, allowing him or her to make investment decisions in a more comfortable environment. Based on this, User A considers which stocks to invest in and actually makes the investment.

[0250] Continuous improvement of the investment experience

[0251] server:

[0252] The user's investment history and new feedback are sent to the server and the model is continually updated, which allows for even higher prediction accuracy in future investments and continuously improves the user's investment experience.

[0253] As an embodiment of the present invention, we have described a dividend forecasting and shareholder benefit analysis system that combines an emotion engine for beginners in stock investing. This system is designed to lower the barrier to investment and enable even beginners to easily make investment decisions.

[0254] The processing flow will be explained below.

[0255] Step 1:

[0256] The server retrieves past dividend data, financial information, market trend data, and shareholder benefits details from external APIs. Specifically, this includes historical information on dividends paid by companies in the past, financial information such as corporate revenue, liabilities, assets, and cash flow, and market activity data such as overall market price fluctuations and volume.

[0257] Step 2:

[0258] The server trains a generative AI model using the acquired historical dividend data and financial information. During this training process, the data is divided into training data and test data, and a machine learning algorithm such as a linear regression model is used to build a model. This model is used to predict a company's future dividends with high accuracy.

[0259] Step 3:

[0260] The server uses the trained generative AI model to predict future dividends based on new financial information. Specifically, it uses the latest market trend data and the company's financial situation as input data and uses the generative AI model to predict future dividend amounts.

[0261] Step 4:

[0262] The server analyzes the content of shareholder benefits. It analyzes the shareholder benefit data and scores it based on the preferences and conditions entered by the user (e.g., preferred benefit categories and expected minimum value). This allows it to extract attractive benefit information that matches the user's preferences.

[0263] Step 5:

[0264] The server uses an emotion engine to analyze the user's emotions based on the user's facial expressions, voice tone, input text, etc. The emotion engine recognizes the user's emotional state in real time and analyzes the results.

[0265] Step 6:

[0266] The server then personalizes the dividend forecast and shareholder benefit information based on the analyzed emotional data, adjusting the priority and format of the displayed information according to the user's emotional state.

[0267] Step 7:

[0268] The terminal displays the predicted dividend information and scored shareholder benefit information received from the server to the user. This information is provided in a visually easy-to-understand format, including predicted dividend amounts for each fiscal year and scored benefit details. The display is also adjusted to take into account the user's emotional state.

[0269] Step 8:

[0270] The user makes investment decisions based on the information provided by the terminal, and invests in the stocks that are most suitable for them, taking into account the predicted dividend amount and analyzed preferential treatment information.

[0271] Step 9:

[0272] The device sends feedback on the user's investment history and new preferences to the server, which then updates the model to further improve prediction accuracy in future rounds. This process continuously improves the user's investment experience.

[0273] As a result, a system has been realized that recognizes the user's emotions and provides personalized investment advice based on them, allowing even beginners to stock investment to easily make investment decisions.

[0274] Example 2

[0275] 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."

[0276] In stock investment, there is no system yet available that can meet the needs of users who want to make investment decisions that reflect their own emotional state. In particular, there is a demand for personalized information that takes into account the user's emotions when predicting dividends and analyzing shareholder benefits, but conventional technologies do not provide a concrete method for achieving this.

[0277] The specific processing by the specific 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 acquiring past distribution data, economic information, market trend data, and shareholder benefit information, means for predicting future dividends using a generative AI model trained on the past distribution data and economic information, means for analyzing the content of shareholder benefits and evaluating the analysis results based on the user's preferences, means for analyzing and recognizing the user's emotional state in real time, and means for adjusting the display of the predicted dividends and the analysis results based on the user's emotional state. This allows users to make investment decisions that reflect their own emotional state.

[0278] "Past distribution data" refers to historical data on the amount and dates of dividends paid by a company in the past.

[0279] "Economic information" refers to information that indicates financial data and economic indicators, including a company's revenue, liabilities, assets, cash flow, etc.

[0280] "Market trend data" refers to data that shows price fluctuations, trading volume, trends, etc. across the market.

[0281] "Shareholder benefit information" is information regarding the content and value of benefits that companies offer to shareholders.

[0282] A "generative AI model" is an artificial intelligence model trained using machine learning algorithms to make predictions or classifications based on input data.

[0283] A "regression model" is a model used in statistics and machine learning that represents the relationship between input variables and output variables and is used to predict future outputs.

[0284] "User preferences" refers to the user's individual tastes and desires, such as the categories and conditions that the user prefers.

[0285] An "emotional state" represents a user's current emotion (e.g., joy, sadness, surprise, etc.).

[0286] An "external API" is an application programming interface provided by an external system or service, and is a means for retrieving and manipulating data.

[0287] "Personalization" means providing information and services tailored to the individual needs and preferences of each user.

[0288] This invention is a system that supports decision-making in stock investment, particularly by taking into account the user's emotional state and providing personalized investment advice. The system acquires historical dividend data, corporate financial information, market trend data, and shareholder benefit information, and uses this data to train a generative AI model to predict future dividends. It also analyzes the content of shareholder benefits and evaluates them based on the user's preferences. Furthermore, it analyzes the user's emotional state in real time and uses that information to personalize investment advice.

[0289] Hardware and software used

[0290] server:

[0291] The server is primarily responsible for:

[0292] Data Acquisition: The server collects historical dividend data, company financial information, market trend data, and shareholder benefit information through external APIs. The hardware includes a high-performance CPU and large storage capacity, and the software uses a database (e.g., MySQL, PostgreSQL) and a REST API library (e.g., the Requests library).

[0293] Data storage: Collected data is stored in a database for smooth access.

[0294] Training a generative AI model: A machine learning library (e.g., scikit-learn) is used to train a generative AI model, such as a regression model, which may use a GPU to efficiently process large datasets.

[0295] Emotion analysis: Use emotion recognition APIs (e.g., Microsoft Azure's Face API, Google Cloud's Speech-to-Text API) to analyze the user's emotional state from their facial expressions, voice tone, and input text.

[0296] Device:

[0297] The terminal displays the information received from the server to the user:

[0298] Data display: The terminal uses a front-end framework (e.g., React, Vue.js) to display predicted dividend information and scored shareholder benefit information in a visually easy-to-understand format.

[0299] Emotional adjustment: The device personalizes the information displayed based on the user's emotional state, adjusting the device to receive the information in a more relaxed state.

[0300] User:

[0301] The user interacts with the system as follows:

[0302] Input of investment preferences: The user inputs their investment preferences and conditions into the terminal (e.g., "I like shareholder benefits in the food category, and I would like benefits worth at least 1,000 yen").

[0303] Provide feedback: Based on your investment results and experience, provide feedback to the system to help improve the model.

[0304] Specific examples

[0305] When a user uses this system to make an investment decision, they first enter their basic investment preferences. For example, User A might enter, "I like shareholder benefits in the food category, and I would like benefits worth at least 1,000 yen." The device then sends this information to the server. The server obtains the necessary data from an external API and trains a generative AI model to predict dividends and analyze shareholder benefits. At the same time, the emotion engine analyzes the user's emotional state in real time and personalizes the information display based on the obtained emotional data. The device displays predicted dividend information and shareholder benefit information scored based on User A's preferences, and the information display is adjusted according to User A's emotional state. User A then considers which stocks to invest in based on this information and makes the actual investment.

[0306] Prompt Sentence Examples

[0307] "Based on the dividend forecast and shareholder benefit analysis, please recommend the next stock I should buy. I like shareholder benefits in the food category and would like benefits worth at least 1,000 yen."

[0308] As described above, this system supports stock investment decision-making by providing accurate investment advice while taking into account the user's emotional state.

[0309] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0310] Step 1:

[0311] Data Acquisition

[0312] server:

[0313] Specifically, the server sends an HTTP GET request to an external API to retrieve historical distribution data, economic information, market trend data, and shareholder benefit information. The API endpoint URL and key are used as input. The output is JSON-formatted data. After retrieving this data, the server stores it in a database (e.g., MySQL), inserting the data into the appropriate table using the SQL INSERT statement.

[0314] Step 2:

[0315] Training a dividend prediction model

[0316] server:

[0317] The server extracts historical distribution data and economic information from the database. Specifically, it retrieves the data using a SELECT statement. The input is the database connection information and SQL query, and the output is a training dataset. Then, using a machine learning library (e.g., scikit-learn), it splits the dataset into training data and test data. This split is performed using the train_test_split function. Next, it trains a linear regression model using the fit method. The input is the training dataset, and the output is the trained model.

[0318] Step 3:

[0319] Dividend forecast

[0320] server:

[0321] New economic information is input into the model to predict future dividends. Specific operations use the predict method to obtain a predicted value. The input is a dataset of new economic information, and the output is the predicted dividend value. This prediction result is stored in a database.

[0322] Step 4:

[0323] Shareholder Benefit Analysis and Scoring

[0324] server:

[0325] It receives user preferences and conditions, analyzes shareholder benefit data, and performs evaluation. Specifically, it receives user input (e.g., preferred benefit category, expected minimum value) in JSON format and filters the shareholder benefit data using an SQL query. The input is the user preferences and shareholder benefit data, and the output is the score of the benefits based on the user conditions. It runs the scoring algorithm and calculates a score for each benefit.

[0326] Step 5:

[0327] Emotional state analysis

[0328] server:

[0329] The emotion recognition API is used to analyze the user's facial expression, voice tone, and input text. Specifically, an HTTP request is sent to the emotion recognition API to obtain the analysis results. The input is the user's facial expression image, voice data, and text data, and the output is the emotional state (e.g., joy, sadness, surprise). The analysis results are stored in a database and used for further processing.

[0330] Step 6:

[0331] Displaying Information

[0332] Device:

[0333] Predicted dividend information and scored shareholder benefit information are displayed to the user. Specifically, a front-end framework (e.g., React, Vue.js) is used to generate an interface that displays information in data table and graph format. The input is the dividend prediction and scoring results received from the server, and the output is a visually easy-to-understand display format. In addition, the display content is adjusted according to the user's emotional state based on the results of the emotion engine. For example, the display color and layout can be changed based on the emotional state.

[0334] Step 7:

[0335] Providing Feedback

[0336] User:

[0337] Feedback is sent to the system based on investment results and experience. Specifically, users enter information into a feedback form from their device and send it to the server. The input is the user's feedback, and the output is data that can be used to improve the system. The server stores this feedback in a database and uses it to update the model.

[0338] Through these steps, the system takes into account the user's emotional state, provides accurate investment advice, and supports stock investment decision-making.

[0339] (Application example 2)

[0340] 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."

[0341] Conventional stock investment support systems provide investment advice based on simple data analysis without considering the user's emotional state, resulting in a lack of psychological satisfaction and personalized recommendations. Therefore, there is a need for investment decision support that takes into account the user's emotional state. Furthermore, there is no adequate method for performing real-time emotional analysis and providing optimal investment information to users based on specific conditions.

[0342] 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.

[0343] In this invention, the server includes: means for acquiring past dividend data, financial information, market trend data, and shareholder benefit details; means for predicting future dividends using a generative AI model trained on the past dividend data and financial information; means for analyzing the details of shareholder benefits and scoring the analysis results based on the user's preferences; an emotion engine for recognizing and analyzing the user's emotional state; and means for displaying personalized information optimal for the user based on the emotional state. This makes it possible to provide personalized investment advice in real time according to the user's emotional state.

[0344] "Past dividend data" refers to historical information about dividends paid by a company.

[0345] "Financial information" is data that shows a company's financial status, such as revenue, liabilities, assets, and cash flow.

[0346] "Market trend data" is data that indicates market activity, such as price fluctuations and trading volume across the market.

[0347] "Shareholder benefits" refers to information about the perks and services that a company provides to its shareholders.

[0348] A "generative AI model" is an artificial intelligence model that is trained to predict future outputs based on input data.

[0349] An "emotion engine" is a system that recognizes emotions by analyzing a user's facial expressions, voice tone, input text, etc.

[0350] "Personalization" means optimizing information and services according to the preferences and emotional state of individual users.

[0351] "Scoring" is the process of assigning an evaluation or score based on certain criteria.

[0352] "Means for displaying information" refers to an interface that visually presents analysis results and predicted data to users.

[0353] An "external API" is an external application program interface for connecting with other services or databases.

[0354] This invention is a system that recognizes and analyzes user emotions in food delivery services and makes personalized meal recommendations based on that information. This system can be accessed by users through a smartphone application.

[0355] Data acquisition and analysis

[0356] The server uses an external API to retrieve the user's past order history and menu information. For example, the data retrieved from the API includes order details (price, rating, order frequency, etc.).

[0357] Emotion analysis

[0358] The emotion analysis module analyzes the user's real-time emotional state. It uses OpenCV for facial expression analysis and TextBlob for voice tone analysis. It also analyzes the input text to comprehensively evaluate the user's emotional state.

[0359] Recommendation Algorithm

[0360] The server trains a generative AI model based on the user's past order history and real-time emotional state to predict the optimal meal menu. The generative AI model uses a linear regression model and is trained based on past data.

[0361] Displaying personalized information

[0362] The device receives the recommendation results from the server and displays optimized menu information to the user, including menu names, prices, ratings, etc. Furthermore, the information display is adjusted taking into account the user's emotional state.

[0363] Specific examples

[0364] For example, when User B launches a food delivery app on his smartphone, he enters the following prompt:

[0365] text:

[0366] I'm feeling a bit tired today and want to relieve stress. What meals would you recommend?

[0367] The server analyzes this prompt, recognizes User B's current emotional state, and can then suggest relaxing, healthy meals or their favorite sweets, allowing the user to choose the optimal meal according to their emotions at the time.

[0368] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0369] Step 1:

[0370] The server uses an external API to retrieve the user's past order history and menu information. It uses the API endpoint and the user's ID as input, and obtains the order history data and menu information data as output. This data retrieval involves sending an HTTP request and receiving the data in JSON format.

[0371] Step 2:

[0372] The server preprocesses the acquired order history data. Specifically, it cleans the data, handles missing values, and selects features. It uses the acquired order history data as input and obtains clean training data as output. This preprocessing includes operations that perform data frame operations within the program.

[0373] Step 3:

[0374] The server uses an emotion analysis module to analyze the user's emotional state. It uses facial expression images, voice samples, and text inputs obtained from the user as inputs, and obtains the user's emotion score as output. Specifically, it analyzes facial expression images using OpenCV, and voice samples and text inputs using TextBlob.

[0375] Step 4:

[0376] The server uses a generative AI model to predict the optimal menu for a user based on the preprocessed order history data and real-time sentiment scores. It uses the preprocessed order history data and sentiment scores as input and obtains a list of recommended menu items as output. This prediction involves applying a Linear Regression model and obtaining the model's prediction results.

[0377] Step 5:

[0378] The terminal receives the recommendation results from the server and displays them to the user. It uses the list of recommended menus as input and obtains menu information visually displayed to the user as output. Specifically, it includes the operation of displaying information such as menu name, price, and rating to the user in list form.

[0379] Step 6:

[0380] The user selects and orders a meal from the recommended menu displayed on the device. The input is a menu selected from the list of recommended menus, and the output is a confirmation of the order. Specifically, this involves selecting and ordering a meal through button operations within the app.

[0381] 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.

[0382] 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.

[0383] 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.

[0384] [Second embodiment]

[0385] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0386] 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.

[0387] 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).

[0388] 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.

[0389] 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.

[0390] 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).

[0391] 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.

[0392] 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.

[0393] 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.

[0394] 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.

[0395] 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.

[0396] 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."

[0397] This invention is a system that enables beginners to make effective investment decisions in stock investments, and includes functions for predicting dividends and analyzing shareholder benefits. The system is composed of a server and a terminal, and is designed to allow users to easily obtain and understand investment information.

[0398] 1. Data Acquisition

[0399] server:

[0400] The server retrieves historical dividend data, financial information, market trend data, and shareholder benefits from external APIs. This data consists of historical information on dividends paid by companies in the past, financial status including revenue, liabilities, assets, and cash flow, as well as market activity data such as overall market price fluctuations and volume.

[0401] 2. Training and Predicting the Dividend Prediction Model

[0402] server:

[0403] The server trains a generative AI model using the acquired historical dividend data and financial information. This model uses machine learning algorithms such as linear regression models to predict a company's future dividends with high accuracy. To do this, the data is first divided into training data and test data, and the model is then built and trained. The trained model is then used to predict dividends based on new financial information.

[0404] 3. Shareholder Benefit Analysis

[0405] server:

[0406] The server analyzes the content of the shareholder perks and evaluates their value and attractiveness. This evaluation also takes into account the user's preferences. For example, if a user prefers perks in a particular category, such as food or travel, a high score will be assigned to perks in that category. Also, if the value of a perk exceeds the user's minimum expectations, an additional score will be assigned to that perk.

[0407] 4. Displaying Information

[0408] Device:

[0409] The terminal displays the predicted dividends and analyzed shareholder benefit information received from the server to the user. The user makes investment decisions based on this information. The displayed information is presented in a visually easy-to-understand format, including predicted dividend amounts by year, benefit details, and scores.

[0410] Specific use cases

[0411] User:

[0412] For example, when User A uses this system to make an investment decision, he or she first inputs his or her basic investment preferences (e.g., he or she likes shareholder benefits in the food category, and wants benefits worth at least 1,000 yen).Then, the device sends this information to the server, which retrieves the necessary data from an external API, trains a generative AI model, and performs dividend prediction and shareholder benefit analysis.

[0413] The terminal displays predicted dividend information and a list of shareholder benefits scored based on User A's preferences. Based on this, User A can easily decide which stocks to invest in. In this way, even beginners can significantly lower the investment hurdles and support efficient investment decisions.

[0414] The above describes a dividend forecasting and shareholder benefit analysis system for beginners in stock investment as an embodiment of the present invention. This system is designed to lower the barrier to investment and enable even beginners to easily make investment decisions.

[0415] The processing flow will be explained below.

[0416] Step 1:

[0417] The server retrieves historical dividend data, financial information, market trend data, and shareholder benefits from external APIs, including historical information on dividends paid by companies, financial status including revenue, liabilities, assets, and cash flow, as well as data showing market activity such as overall market price fluctuations and volume.

[0418] Step 2:

[0419] The server trains a generative AI model using the acquired historical dividend data and financial information. The data is divided into training data and test data, and training is performed using a generative AI model (e.g., a linear regression model). Once trained, the model is used to predict future dividends based on new financial information.

[0420] Step 3:

[0421] The server uses the trained generative AI model to predict future dividends based on new financial information data. This process uses the latest market trend data and the company's financial situation as inputs to predict future dividend amounts.

[0422] Step 4:

[0423] The server analyzes the content of shareholder benefits. It analyzes the shareholder benefit data and scores it based on the preferences and conditions entered by the user (e.g., preferred benefit categories and expected minimum value). This allows it to extract attractive benefit information that matches the user's preferences.

[0424] Step 5:

[0425] The terminal displays the predicted dividend information and scored shareholder benefit information received from the server to the user. The displayed information is presented in a visually easy-to-understand format, including the predicted dividend amount for each fiscal year and the scored benefit details.

[0426] Step 6:

[0427] Users make investment decisions based on the information provided by the terminal. They can use the predicted dividend amount and analyzed preferential treatment information as a reference to invest in the stocks that are most suitable for them.

[0428] Step 7:

[0429] The device sends feedback on the user's investment history and new preferences to the server, which then updates the model based on this information to further improve prediction accuracy in future rounds, thereby continuously improving the user's investment experience.

[0430] Example 1

[0431] 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."

[0432] Beginners in stock investment often find it difficult to predict corporate dividends and evaluate shareholder benefits. In particular, because information is not provided that meets the preferences or minimum desired value of individual investors, there is a lack of information to make decisions and it is difficult to make appropriate investment decisions.

[0433] 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.

[0434] In this invention, the server includes means for acquiring past dividend data, financial information, market trend data, and shareholder benefit details, means for storing data acquired from an external API in a database, means for dividing the data into training data and test data, means for predicting future dividends using a generative AI model trained on the past dividend data and financial information, means for analyzing the details of shareholder benefits and scoring the analysis results based on user preferences, means for displaying the predicted dividends and the analysis results to the user, and means for collecting user preferences and minimum desired values. This provides appropriate information that even beginners can use to easily make investment decisions, enabling efficient investment decisions.

[0435] "Past dividend data" is historical information about dividends paid by a company within a certain period of time, and indicates the company's dividend payment trends and history.

[0436] "Financial information" is data that represents a company's financial position and performance, such as its revenues, liabilities, assets, and cash flow.

[0437] "Market trend data" refers to data that indicates market trends, such as price fluctuations and trading volume across the market, and is used for investment decisions.

[0438] "Shareholder benefits" refers to the specific perks and benefits that a company provides to shareholders, and includes a variety of categories such as food and travel vouchers.

[0439] An "External API" is an application programming interface for communicating with external data sources and obtaining required data.

[0440] A "generative AI model" is a computational model that uses machine learning algorithms to learn from specific datasets and make predictions and analyses.

[0441] "User preferences" are the preferences and desires that individual investors have regarding specific categories and values, and are information that influences investment decisions.

[0442] "Minimum desired value" refers to the minimum value that users expect from shareholder benefits, and is a standard below which they will not be satisfied.

[0443] "Training data" is a dataset used to build and optimize a machine learning model, improving its accuracy.

[0444] "Test data" is a dataset used to evaluate the performance of a trained model and to confirm the model's predictive accuracy.

[0445] A database is a system that efficiently manages and stores structured data and allows quick access when needed.

[0446] This invention is a system that enables beginners to make effective investment decisions. The system includes functions for predicting dividends and analyzing shareholder benefits, and is composed of a server and a terminal. It is designed to allow users to easily obtain and understand investment information.

[0447] Data Acquisition

[0448] The server uses a RESTful API to retrieve historical dividend data, financial information, market trend data, and shareholder benefits from external APIs. The data is received in JSON format and stored in a MySQL database.

[0449] Examples:

[0450] The server retrieves historical dividend data from http: / / api.marketdata.com / dividends and inserts it into a "Company Dividend Table."

[0451] Model training and prediction

[0452] The server splits the acquired data into training data and test data. For example, 80% of the data is used for training and 20% for testing. The server then uses a machine learning library such as Scikit-learn to train a linear regression model based on the training data.

[0453] Examples:

[0454] The server builds a model to predict dividends using data such as revenue, liabilities, and assets of "Company A."

[0455] Analysis of shareholder benefits

[0456] The server scores the shareholder benefits based on user preference information (e.g., specific benefit categories and minimum desired value). This scoring is adjusted according to the user's individual preferences.

[0457] Examples:

[0458] The server gives a high score to a special offer worth 5,000 yen in the food category, and adds an additional score if the value exceeds the user's minimum desired value.

[0459] Displaying Information

[0460] The terminal displays the predicted dividend information and scoring results sent from the server to the user in a visually easy-to-understand format, allowing the user to make investment decisions based on this information.

[0461] Examples:

[0462] The terminal will display "Company A's projected dividend amount for 2023: 120 yen" and "Company A's shareholder benefits in the food category: score 90 points."

[0463] Usage example

[0464] The specific steps for a user to use the system are as follows: First, the user enters their basic investment preferences (e.g., they like shareholder benefits in the food category and want benefits worth at least 1,000 yen). The device sends this information to the server, which then collects the necessary data from external APIs, trains a generative AI model, and analyzes dividend predictions and shareholder benefits. The device then displays a list of shareholder benefits scored based on the predicted dividend information and the user's preferences.

[0465] Example prompts for generative AI models

[0466] "Based on the following financial data, predict the company's dividend for next year."

[0467] "Please score the benefits in the food category based on the shareholder benefits information."

[0468] This system allows even beginners to make investment decisions easily and effectively, supporting efficient investment decisions.

[0469] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0470] Step 1:

[0471] The server retrieves past dividend data, financial information, market trend data, and shareholder benefits details from an external API. It sends an HTTP request to the API endpoint and receives JSON-formatted data in response. This process aggregates the necessary investment data on the server.

[0472] Specific behavior:

[0473] The server sends an HTTP GET request to http: / / api.marketdata.com / dividends to retrieve the dividend amount for each company by year.

[0474] input:

[0475] External API Endpoints

[0476] output:

[0477] Investment data in JSON format

[0478] Step 2:

[0479] The server parses the received JSON data and saves it in a MySQL database. When saving the data to the database, the data is converted and formatted as necessary.

[0480] Specific behavior:

[0481] The server inserts "Company A's 2022 dividend amount: 100 yen" into the "Company Dividend Table."

[0482] input:

[0483] Investment data in JSON format

[0484] output:

[0485] Formatted data stored in a database

[0486] Step 3:

[0487] The server extracts historical dividend data and financial information from the database and splits it into training and test data, typically 80% as training data and 20% as test data.

[0488] Specific behavior:

[0489] The server extracts dividend data from 2010 to 2019 from the database as training data and data from 2020 as test data.

[0490] input:

[0491] Historical dividend data and financial information in the database

[0492] output:

[0493] training dataset, test dataset

[0494] Step 4:

[0495] The server uses the training data to train a generative AI model, which is a linear regression model built using libraries such as Scikit-learn.

[0496] Specific behavior:

[0497] The server trains the model based on specific financial metrics such as revenue, liabilities, and assets.

[0498] input:

[0499] Training dataset

[0500] output:

[0501] Pre-trained generative AI models

[0502] Step 5:

[0503] The server feeds new financial information into the trained generative AI model to predict future dividends, which are then compared to test data to confirm accuracy.

[0504] Specific behavior:

[0505] The server inputs the new financial information into the model to predict next year's dividends.

[0506] input:

[0507] New Financial Information

[0508] output:

[0509] Projected dividend amount

[0510] Step 6:

[0511] The terminal collects the user's preferences and minimum desired value and sends this information to the server, allowing the system to respond to the user's individual preferences.

[0512] Specific behavior:

[0513] The user inputs that he / she likes shareholder benefits in the food category and wants benefits worth at least 1,000 yen.

[0514] input:

[0515] User preferences, minimum desired value

[0516] output:

[0517] User information sent to the server

[0518] Step 7:

[0519] The server scores shareholder benefit information based on the user's preferences. It analyzes the content of a company's shareholder benefits and calculates a score by comparing it with the user's preferences.

[0520] Specific behavior:

[0521] The server will give a high score to perks worth 5,000 yen in the food category, and will add more points if the minimum desired value is exceeded.

[0522] input:

[0523] User information, shareholder benefits

[0524] output:

[0525] Scored shareholder benefits information

[0526] Step 8:

[0527] The terminal displays the predicted dividend information and scoring results sent from the server to the user in a visually easy-to-understand format, allowing the user to make investment decisions based on this information.

[0528] Specific behavior:

[0529] The terminal will display "Company A's projected dividend amount for 2023: 120 yen" and "Company A's shareholder benefits in the food category: score 90 points."

[0530] input:

[0531] Predicted dividend information and scoring results from the server

[0532] output:

[0533] Investment information displayed to the user

[0534] (Application example 1)

[0535] 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."

[0536] For beginners in stock investment, collecting and analyzing the information necessary to make effective investment decisions is extremely difficult. In particular, predicting dividends and evaluating shareholder benefits are complex and require specialized knowledge and experience. Providing investment information tailored to user preferences is also important, but achieving this poses many technical challenges. A system that solves these problems and allows even beginners to easily make investment decisions is needed.

[0537] 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.

[0538] In this invention, the server includes means for acquiring past dividend data, financial information, market trend data, and shareholder benefit details, means for predicting future dividends using a generative AI model trained on the past dividend data and financial information, means for analyzing the details of shareholder benefits and scoring the analysis results based on user preferences, means for displaying the predicted dividends and the analysis results to the user, and a smartphone application means for visually presenting dividend forecasts and shareholder benefit evaluation information based on a user profile. This allows even beginners to stock investment to easily make effective investment decisions.

[0539] "Past dividend data" is historical information about dividends paid by a company in the past.

[0540] "Financial information" is data about a company's financial condition, including its revenues, liabilities, assets, and cash flow.

[0541] "Market trend data" refers to data that indicates market activity such as price fluctuations and trading volume across the market.

[0542] "Shareholder benefits" refers to detailed information about the perks and services that a company provides to its shareholders.

[0543] A "generative AI model" is a model that contains machine learning algorithms that are trained using historical data and designed to predict future values.

[0544] "User preferences" are personal evaluation criteria or preferences that a user has for a particular shareholder benefit category or minimum value.

[0545] A "smartphone application means" is a software application that is installed on a smartphone device and provides functionality through a user interface.

[0546] "Scoring" is the process of assigning a rating based on specific criteria.

[0547] "Visually presenting" refers to displaying data and information in an easy-to-understand manner using graphs, charts, etc.

[0548] A "user profile" is individualized settings information that includes a user's preferences and history information.

[0549] An "external API" is an application programming interface for obtaining data from external systems or services.

[0550] A "linear regression model" is a statistical machine learning model that makes predictions using linear relationships between variables.

[0551] This invention is a system that enables beginners to make effective investment decisions in stock investments, and includes functions for predicting dividends and analyzing shareholder benefits. The system is composed of a server and a smartphone terminal, and is designed to allow users to easily obtain and understand investment information.

[0552] Data Acquisition

[0553] First, the server uses an external API to retrieve historical dividend data, financial information, market trend data, and shareholder benefits. This data includes historical information on dividends paid by companies, financial status such as revenue, liabilities, assets, and cash flow, as well as market activity data such as overall market price fluctuations and trading volume.

[0554] Training and predicting dividend prediction models

[0555] Next, the server trains a generative AI model using the acquired historical dividend data and financial information. A linear regression model is used for this model. The model is built using separate training and test data, and the trained model is used to make dividend predictions based on new financial information.

[0556] Shareholder Benefit Analysis

[0557] The server then analyzes the content of the shareholder benefits and scores the analysis results based on the user's preferences, taking into account the user's preferences for specific categories (e.g., food, travel) and minimum value criteria (e.g., 1,000 yen or more).

[0558] Displaying Information

[0559] The acquired information and forecast results are provided visually to users through a smartphone application. The application displays dividend forecasts and shareholder benefit evaluation information based on the user profile. Users can visually check the forecast dividend amount and benefit details for each year, as well as their scores, and make investment decisions.

[0560] Hardware and software used

[0561] This system is implemented using Python and its main libraries (requests, numpy, sklearn). The hardware required is a server computer and a smartphone.

[0562] Examples and prompts

[0563] For example, a user may specify that they like shareholder benefits in the food category and would like them to be worth at least 1,000 yen. The server uses a model to predict dividends based on new financial information and scores the benefits. The prediction results and evaluation are then provided to the user via a smartphone application.

[0564] Example prompt sentence:

[0565] User preference: Food, Minimum desired value: 1000 yen

[0566] Dividend forecast:

[0567] Financial Data: New Financial Data

[0568] Shareholder Benefit Analysis:

[0569] Priority Category: Food

[0570] Calculating shareholder benefits score

[0571] In this way, even beginners can easily make effective investment decisions.

[0572] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0573] Step 1: Data Acquisition

[0574] The server uses an external API to obtain historical dividend data, financial information, market trend data, and shareholder benefits. The input is the data request from the API, and the output is the obtained data. Specifically, the server accesses the API endpoint and obtains the required data in JSON format.

[0575] Step 2: Data Preprocessing

[0576] The server preprocesses the acquired data. The input is the data acquired in step 1, and the output is the preprocessed data. Specifically, it complements missing values, removes outliers, and normalizes the data.

[0577] Step 3: Train the dividend prediction model

[0578] The server uses the preprocessed data to train a generative AI model (linear regression model). The input is the preprocessed data, and the output is the trained AI model. Specifically, the model is trained using financial information as features and dividend data as target values.

[0579] Step 4: Dividend Forecast

[0580] The server inputs new financial information and uses the trained AI model to predict future dividends. The inputs are new financial information and the trained model, and the output is the predicted dividend. Specifically, new financial data is input into the model and dividends are predicted.

[0581] Step 5: Shareholder Benefit Analysis and Scoring

[0582] The server analyzes the content of shareholder benefits and scores them based on the user's preferences. The input is shareholder benefit data and user preference data, and the output is the scoring result. Specifically, the server evaluates the benefits based on the categories and value criteria specified by the user and calculates a score.

[0583] Step 6: Get User Information

[0584] The terminal acquires the user's preferences and investment goals. The input is the user's input data, and the output is the user profile. Specifically, the user sets the preferred categories and minimum value through the interface.

[0585] Step 7: Viewing information

[0586] The terminal visually displays the predicted payouts and analysis results received from the server to the user. The input is data from the server, and the output is what is displayed on the user's screen. Specifically, the predicted payout amounts and preferential treatment scores are displayed in graphs and tables. The terminal also provides an interface that is easy for the user to understand.

[0587] Step 8: Recording User Actions

[0588] The terminal records the user's actions, such as investment decisions and setting changes. The input is the user's action data, and the output is the recorded log data. Specifically, various operations performed by the user are recorded in a log and used for future data analysis and improvements.

[0589] 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.

[0590] This invention is a system that recognizes and analyzes users' emotions when it comes to stock investment, and supports investment decisions based on that information. In particular, by combining an emotion engine with dividend forecasting and shareholder benefit analysis, it provides personalized investment advice tailored to the individual needs of each user.

[0591] 1. Data Acquisition

[0592] server:

[0593] The server retrieves historical dividend data, financial information, market trend data, and shareholder benefits from external APIs, including historical information on dividends paid by companies, financial status such as revenue, liabilities, assets, and cash flow of companies, and data showing market activity such as overall market price fluctuations and volume.

[0594] 2. Training and Predicting the Dividend Prediction Model

[0595] server:

[0596] The server trains a generative AI model using the acquired historical dividend data and financial information. This model is trained using machine learning algorithms such as linear regression models to predict future dividends for companies. To do this, the data is first divided into training data and test data, and the model is then built and trained. The trained model is then used to predict dividends based on new financial information.

[0597] 3. Shareholder Benefit Analysis

[0598] server:

[0599] The server analyzes the content of the shareholder benefits and evaluates their value and attractiveness. This involves analyzing the shareholder benefit data and scoring them based on the preferences and conditions entered by the user (e.g., preferred benefit categories and expected minimum value).

[0600] 4. Implementing the Emotion Engine

[0601] server:

[0602] The server includes an emotion engine that analyzes the user's emotions. The emotion engine analyzes the user's facial expressions, voice tone, and input text as input data to recognize the user's emotions in real time. This emotion data is used to personalize the results of dividend forecasts and shareholder benefit analysis.

[0603] 5. Display of Information

[0604] Device:

[0605] The terminal displays the predicted dividend information and scored shareholder benefit information received from the server to the user. The displayed information is presented in a visually easy-to-understand format, including predicted dividend amounts for each fiscal year and scored benefit details. Furthermore, the emotional results analyzed by the emotion engine are reflected, allowing the user to receive the information in a relaxed state.

[0606] Specific use cases

[0607] User:

[0608] For example, when User A uses this system to make an investment decision, he or she first inputs basic investment preferences (e.g., he or she likes shareholder benefits in the food category and wants benefits worth at least 1,000 yen). The device then sends this information to the server. The server retrieves the necessary data from an external API and trains a generative AI model to predict dividends and analyze shareholder benefits. At the same time, the emotion engine analyzes the user's emotional state in real time and personalizes the displayed information based on the obtained emotional data.

[0609] As a result, the device displays predicted dividend information and shareholder benefit information scored based on User A's preferences. Furthermore, the information display is adjusted according to User A's emotional state, allowing him or her to make investment decisions in a more comfortable environment. Based on this, User A considers which stocks to invest in and actually makes the investment.

[0610] Continuous improvement of the investment experience

[0611] server:

[0612] The user's investment history and new feedback are sent to the server and the model is continually updated, which allows for even higher prediction accuracy in future investments and continuously improves the user's investment experience.

[0613] As an embodiment of the present invention, we have described a dividend forecasting and shareholder benefit analysis system that combines an emotion engine for beginners in stock investing. This system is designed to lower the barrier to investment and enable even beginners to easily make investment decisions.

[0614] The processing flow will be explained below.

[0615] Step 1:

[0616] The server retrieves past dividend data, financial information, market trend data, and shareholder benefits details from external APIs. Specifically, this includes historical information on dividends paid by companies in the past, financial information such as corporate revenue, liabilities, assets, and cash flow, and market activity data such as overall market price fluctuations and volume.

[0617] Step 2:

[0618] The server trains a generative AI model using the acquired historical dividend data and financial information. During this training process, the data is divided into training data and test data, and a machine learning algorithm such as a linear regression model is used to build a model. This model is used to predict a company's future dividends with high accuracy.

[0619] Step 3:

[0620] The server uses the trained generative AI model to predict future dividends based on new financial information. Specifically, it uses the latest market trend data and the company's financial situation as input data and uses the generative AI model to predict future dividend amounts.

[0621] Step 4:

[0622] The server analyzes the content of shareholder benefits. It analyzes the shareholder benefit data and scores it based on the preferences and conditions entered by the user (e.g., preferred benefit categories and expected minimum value). This allows it to extract attractive benefit information that matches the user's preferences.

[0623] Step 5:

[0624] The server uses an emotion engine to analyze the user's emotions based on the user's facial expressions, voice tone, input text, etc. The emotion engine recognizes the user's emotional state in real time and analyzes the results.

[0625] Step 6:

[0626] The server then personalizes the dividend forecast and shareholder benefit information based on the analyzed emotional data, adjusting the priority and format of the displayed information according to the user's emotional state.

[0627] Step 7:

[0628] The terminal displays the predicted dividend information and scored shareholder benefit information received from the server to the user. This information is provided in a visually easy-to-understand format, including predicted dividend amounts for each fiscal year and scored benefit details. The display is also adjusted to take into account the user's emotional state.

[0629] Step 8:

[0630] The user makes investment decisions based on the information provided by the terminal, and invests in the stocks that are most suitable for them, taking into account the predicted dividend amount and analyzed preferential treatment information.

[0631] Step 9:

[0632] The device sends feedback on the user's investment history and new preferences to the server, which then updates the model to further improve prediction accuracy in future rounds. This process continuously improves the user's investment experience.

[0633] As a result, a system has been realized that recognizes the user's emotions and provides personalized investment advice based on them, allowing even beginners to stock investment to easily make investment decisions.

[0634] Example 2

[0635] 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."

[0636] In stock investment, there is no system yet available that can meet the needs of users who want to make investment decisions that reflect their own emotional state. In particular, there is a demand for personalized information that takes into account the user's emotions when predicting dividends and analyzing shareholder benefits, but conventional technologies do not provide a concrete method for achieving this.

[0637] The specific processing by the specific 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 acquiring past distribution data, economic information, market trend data, and shareholder benefit information, means for predicting future dividends using a generative AI model trained on the past distribution data and economic information, means for analyzing the content of shareholder benefits and evaluating the analysis results based on the user's preferences, means for analyzing and recognizing the user's emotional state in real time, and means for adjusting the display of the predicted dividends and the analysis results based on the user's emotional state. This allows users to make investment decisions that reflect their own emotional state.

[0638] "Past distribution data" refers to historical data on the amount and dates of dividends paid by a company in the past.

[0639] "Economic information" refers to information that indicates financial data and economic indicators, including a company's revenue, liabilities, assets, cash flow, etc.

[0640] "Market trend data" refers to data that shows price fluctuations, trading volume, trends, etc. across the market.

[0641] "Shareholder benefit information" is information regarding the content and value of benefits that companies offer to shareholders.

[0642] A "generative AI model" is an artificial intelligence model trained using machine learning algorithms to make predictions or classifications based on input data.

[0643] A "regression model" is a model used in statistics and machine learning that represents the relationship between input variables and output variables and is used to predict future outputs.

[0644] "User preferences" refers to the user's individual tastes and desires, such as the categories and conditions that the user prefers.

[0645] An "emotional state" represents a user's current emotion (e.g., joy, sadness, surprise, etc.).

[0646] An "external API" is an application programming interface provided by an external system or service, and is a means for retrieving and manipulating data.

[0647] "Personalization" means providing information and services tailored to the individual needs and preferences of each user.

[0648] This invention is a system that supports decision-making in stock investment, particularly by taking into account the user's emotional state and providing personalized investment advice. The system acquires historical dividend data, corporate financial information, market trend data, and shareholder benefit information, and uses this data to train a generative AI model to predict future dividends. It also analyzes the content of shareholder benefits and evaluates them based on the user's preferences. Furthermore, it analyzes the user's emotional state in real time and uses that information to personalize investment advice.

[0649] Hardware and software used

[0650] server:

[0651] The server is primarily responsible for:

[0652] Data Acquisition: The server collects historical dividend data, company financial information, market trend data, and shareholder benefit information through external APIs. The hardware includes a high-performance CPU and large storage capacity, and the software uses a database (e.g., MySQL, PostgreSQL) and a REST API library (e.g., the Requests library).

[0653] Data storage: Collected data is stored in a database for smooth access.

[0654] Training a generative AI model: A machine learning library (e.g., scikit-learn) is used to train a generative AI model, such as a regression model, which may use a GPU to efficiently process large datasets.

[0655] Emotion analysis: Use emotion recognition APIs (e.g., Microsoft Azure's Face API, Google Cloud's Speech-to-Text API) to analyze the user's emotional state from their facial expressions, voice tone, and input text.

[0656] Device:

[0657] The terminal displays the information received from the server to the user:

[0658] Data display: The terminal uses a front-end framework (e.g., React, Vue.js) to display predicted dividend information and scored shareholder benefit information in a visually easy-to-understand format.

[0659] Emotional adjustment: The device personalizes the information displayed based on the user's emotional state, adjusting the device to receive the information in a more relaxed state.

[0660] User:

[0661] The user interacts with the system as follows:

[0662] Input of investment preferences: The user inputs their investment preferences and conditions into the terminal (e.g., "I like shareholder benefits in the food category, and I would like benefits worth at least 1,000 yen").

[0663] Provide feedback: Based on your investment results and experience, provide feedback to the system to help improve the model.

[0664] Specific examples

[0665] When a user uses this system to make an investment decision, they first enter their basic investment preferences. For example, User A might enter, "I like shareholder benefits in the food category, and I would like benefits worth at least 1,000 yen." The device then sends this information to the server. The server obtains the necessary data from an external API and trains a generative AI model to predict dividends and analyze shareholder benefits. At the same time, the emotion engine analyzes the user's emotional state in real time and personalizes the information display based on the obtained emotional data. The device displays predicted dividend information and shareholder benefit information scored based on User A's preferences, and the information display is adjusted according to User A's emotional state. User A then considers which stocks to invest in based on this information and makes the actual investment.

[0666] Prompt Sentence Examples

[0667] "Based on the dividend forecast and shareholder benefit analysis, please recommend the next stock I should buy. I like shareholder benefits in the food category and would like benefits worth at least 1,000 yen."

[0668] As described above, this system supports stock investment decision-making by providing accurate investment advice while taking into account the user's emotional state.

[0669] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0670] Step 1:

[0671] Data Acquisition

[0672] server:

[0673] Specifically, the server sends an HTTP GET request to an external API to retrieve historical distribution data, economic information, market trend data, and shareholder benefit information. The API endpoint URL and key are used as input. The output is JSON-formatted data. After retrieving this data, the server stores it in a database (e.g., MySQL), inserting the data into the appropriate table using the SQL INSERT statement.

[0674] Step 2:

[0675] Training a dividend prediction model

[0676] server:

[0677] The server extracts historical distribution data and economic information from the database. Specifically, it retrieves the data using a SELECT statement. The input is the database connection information and SQL query, and the output is a training dataset. Then, using a machine learning library (e.g., scikit-learn), it splits the dataset into training data and test data. This split is performed using the train_test_split function. Next, it trains a linear regression model using the fit method. The input is the training dataset, and the output is the trained model.

[0678] Step 3:

[0679] Dividend forecast

[0680] server:

[0681] New economic information is input into the model to predict future dividends. Specific operations use the predict method to obtain a predicted value. The input is a dataset of new economic information, and the output is the predicted dividend value. This prediction result is stored in a database.

[0682] Step 4:

[0683] Shareholder Benefit Analysis and Scoring

[0684] server:

[0685] It receives user preferences and conditions, analyzes shareholder benefit data, and performs evaluation. Specifically, it receives user input (e.g., preferred benefit category, expected minimum value) in JSON format and filters the shareholder benefit data using an SQL query. The input is the user preferences and shareholder benefit data, and the output is the score of the benefits based on the user conditions. It runs the scoring algorithm and calculates a score for each benefit.

[0686] Step 5:

[0687] Emotional state analysis

[0688] server:

[0689] The emotion recognition API is used to analyze the user's facial expression, voice tone, and input text. Specifically, an HTTP request is sent to the emotion recognition API to obtain the analysis results. The input is the user's facial expression image, voice data, and text data, and the output is the emotional state (e.g., joy, sadness, surprise). The analysis results are stored in a database and used for further processing.

[0690] Step 6:

[0691] Displaying Information

[0692] Device:

[0693] Predicted dividend information and scored shareholder benefit information are displayed to the user. Specifically, a front-end framework (e.g., React, Vue.js) is used to generate an interface that displays information in data table and graph format. The input is the dividend prediction and scoring results received from the server, and the output is a visually easy-to-understand display format. In addition, the display content is adjusted according to the user's emotional state based on the results of the emotion engine. For example, the display color and layout can be changed based on the emotional state.

[0694] Step 7:

[0695] Providing Feedback

[0696] User:

[0697] Feedback is sent to the system based on investment results and experience. Specifically, users enter information into a feedback form from their device and send it to the server. The input is the user's feedback, and the output is data that can be used to improve the system. The server stores this feedback in a database and uses it to update the model.

[0698] Through these steps, the system takes into account the user's emotional state, provides accurate investment advice, and supports stock investment decision-making.

[0699] (Application example 2)

[0700] 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."

[0701] Conventional stock investment support systems provide investment advice based on simple data analysis without considering the user's emotional state, resulting in a lack of psychological satisfaction and personalized recommendations. Therefore, there is a need for investment decision support that takes into account the user's emotional state. Furthermore, there is no adequate method for performing real-time emotional analysis and providing optimal investment information to users based on specific conditions.

[0702] 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.

[0703] In this invention, the server includes: means for acquiring past dividend data, financial information, market trend data, and shareholder benefit details; means for predicting future dividends using a generative AI model trained on the past dividend data and financial information; means for analyzing the details of shareholder benefits and scoring the analysis results based on the user's preferences; an emotion engine for recognizing and analyzing the user's emotional state; and means for displaying personalized information optimal for the user based on the emotional state. This makes it possible to provide personalized investment advice in real time according to the user's emotional state.

[0704] "Past dividend data" refers to historical information about dividends paid by a company.

[0705] "Financial information" is data that shows a company's financial status, such as revenue, liabilities, assets, and cash flow.

[0706] "Market trend data" is data that indicates market activity, such as price fluctuations and trading volume across the market.

[0707] "Shareholder benefits" refers to information about the perks and services that a company provides to its shareholders.

[0708] A "generative AI model" is an artificial intelligence model that is trained to predict future outputs based on input data.

[0709] An "emotion engine" is a system that recognizes emotions by analyzing a user's facial expressions, voice tone, input text, etc.

[0710] "Personalization" means optimizing information and services according to the preferences and emotional state of individual users.

[0711] "Scoring" is the process of assigning an evaluation or score based on certain criteria.

[0712] "Means for displaying information" refers to an interface that visually presents analysis results and predicted data to users.

[0713] An "external API" is an external application program interface for connecting with other services or databases.

[0714] This invention is a system that recognizes and analyzes user emotions in food delivery services and makes personalized meal recommendations based on that information. This system can be accessed by users through a smartphone application.

[0715] Data acquisition and analysis

[0716] The server uses an external API to retrieve the user's past order history and menu information. For example, the data retrieved from the API includes order details (price, rating, order frequency, etc.).

[0717] Emotion analysis

[0718] The emotion analysis module analyzes the user's real-time emotional state. It uses OpenCV for facial expression analysis and TextBlob for voice tone analysis. It also analyzes the input text to comprehensively evaluate the user's emotional state.

[0719] Recommendation Algorithm

[0720] The server trains a generative AI model based on the user's past order history and real-time emotional state to predict the optimal meal menu. The generative AI model uses a linear regression model and is trained based on past data.

[0721] Displaying personalized information

[0722] The device receives the recommendation results from the server and displays optimized menu information to the user, including menu names, prices, ratings, etc. Furthermore, the information display is adjusted taking into account the user's emotional state.

[0723] Specific examples

[0724] For example, when User B launches a food delivery app on his smartphone, he enters the following prompt:

[0725] text:

[0726] I'm feeling a bit tired today and want to relieve stress. What meals would you recommend?

[0727] The server analyzes this prompt, recognizes User B's current emotional state, and can then suggest relaxing, healthy meals or their favorite sweets, allowing the user to choose the optimal meal according to their emotions at the time.

[0728] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0729] Step 1:

[0730] The server uses an external API to retrieve the user's past order history and menu information. It uses the API endpoint and the user's ID as input, and obtains the order history data and menu information data as output. This data retrieval involves sending an HTTP request and receiving the data in JSON format.

[0731] Step 2:

[0732] The server preprocesses the acquired order history data. Specifically, it cleans the data, handles missing values, and selects features. It uses the acquired order history data as input and obtains clean training data as output. This preprocessing includes operations that perform data frame operations within the program.

[0733] Step 3:

[0734] The server uses an emotion analysis module to analyze the user's emotional state. It uses facial expression images, voice samples, and text inputs obtained from the user as inputs, and obtains the user's emotion score as output. Specifically, it analyzes facial expression images using OpenCV, and voice samples and text inputs using TextBlob.

[0735] Step 4:

[0736] The server uses a generative AI model to predict the optimal menu for a user based on the preprocessed order history data and real-time sentiment scores. It uses the preprocessed order history data and sentiment scores as input and obtains a list of recommended menu items as output. This prediction involves applying a Linear Regression model and obtaining the model's prediction results.

[0737] Step 5:

[0738] The terminal receives the recommendation results from the server and displays them to the user. It uses the list of recommended menus as input and obtains menu information visually displayed to the user as output. Specifically, it includes the operation of displaying information such as menu name, price, and rating to the user in list form.

[0739] Step 6:

[0740] The user selects and orders a meal from the recommended menu displayed on the device. The input is a menu selected from the list of recommended menus, and the output is a confirmation of the order. Specifically, this involves selecting and ordering a meal through button operations within the app.

[0741] 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.

[0742] 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.

[0743] 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.

[0744] [Third embodiment]

[0745] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0746] 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.

[0747] 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).

[0748] 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.

[0749] 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.

[0750] 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).

[0751] 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.

[0752] 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.

[0753] 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.

[0754] 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.

[0755] 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.

[0756] 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."

[0757] This invention is a system that enables beginners to make effective investment decisions in stock investments, and includes functions for predicting dividends and analyzing shareholder benefits. The system is composed of a server and a terminal, and is designed to allow users to easily obtain and understand investment information.

[0758] 1. Data Acquisition

[0759] server:

[0760] The server retrieves historical dividend data, financial information, market trend data, and shareholder benefits from external APIs. This data consists of historical information on dividends paid by companies in the past, financial status including revenue, liabilities, assets, and cash flow, as well as market activity data such as overall market price fluctuations and volume.

[0761] 2. Training and Predicting the Dividend Prediction Model

[0762] server:

[0763] The server trains a generative AI model using the acquired historical dividend data and financial information. This model uses machine learning algorithms such as linear regression models to predict a company's future dividends with high accuracy. To do this, the data is first divided into training data and test data, and the model is then built and trained. The trained model is then used to predict dividends based on new financial information.

[0764] 3. Shareholder Benefit Analysis

[0765] server:

[0766] The server analyzes the content of the shareholder perks and evaluates their value and attractiveness. This evaluation also takes into account the user's preferences. For example, if a user prefers perks in a particular category, such as food or travel, a high score will be assigned to perks in that category. Also, if the value of a perk exceeds the user's minimum expectations, an additional score will be assigned to that perk.

[0767] 4. Displaying Information

[0768] Device:

[0769] The terminal displays the predicted dividends and analyzed shareholder benefit information received from the server to the user. The user makes investment decisions based on this information. The displayed information is presented in a visually easy-to-understand format, including predicted dividend amounts by year, benefit details, and scores.

[0770] Specific use cases

[0771] User:

[0772] For example, when User A uses this system to make an investment decision, he or she first inputs his or her basic investment preferences (e.g., he or she likes shareholder benefits in the food category, and wants benefits worth at least 1,000 yen).Then, the device sends this information to the server, which retrieves the necessary data from an external API, trains a generative AI model, and performs dividend prediction and shareholder benefit analysis.

[0773] The terminal displays predicted dividend information and a list of shareholder benefits scored based on User A's preferences. Based on this, User A can easily decide which stocks to invest in. In this way, even beginners can significantly lower the investment hurdles and support efficient investment decisions.

[0774] The above describes a dividend forecasting and shareholder benefit analysis system for beginners in stock investment as an embodiment of the present invention. This system is designed to lower the barrier to investment and enable even beginners to easily make investment decisions.

[0775] The processing flow will be explained below.

[0776] Step 1:

[0777] The server retrieves historical dividend data, financial information, market trend data, and shareholder benefits from external APIs, including historical information on dividends paid by companies, financial status including revenue, liabilities, assets, and cash flow, as well as data showing market activity such as overall market price fluctuations and volume.

[0778] Step 2:

[0779] The server trains a generative AI model using the acquired historical dividend data and financial information. The data is divided into training data and test data, and training is performed using a generative AI model (e.g., a linear regression model). Once trained, the model is used to predict future dividends based on new financial information.

[0780] Step 3:

[0781] The server uses the trained generative AI model to predict future dividends based on new financial information data. This process uses the latest market trend data and the company's financial situation as inputs to predict future dividend amounts.

[0782] Step 4:

[0783] The server analyzes the content of shareholder benefits. It analyzes the shareholder benefit data and scores it based on the preferences and conditions entered by the user (e.g., preferred benefit categories and expected minimum value). This allows it to extract attractive benefit information that matches the user's preferences.

[0784] Step 5:

[0785] The terminal displays the predicted dividend information and scored shareholder benefit information received from the server to the user. The displayed information is presented in a visually easy-to-understand format, including the predicted dividend amount for each fiscal year and the scored benefit details.

[0786] Step 6:

[0787] Users make investment decisions based on the information provided by the terminal. They can use the predicted dividend amount and analyzed preferential treatment information as a reference to invest in the stocks that are most suitable for them.

[0788] Step 7:

[0789] The device sends feedback on the user's investment history and new preferences to the server, which then updates the model based on this information to further improve prediction accuracy in future rounds, thereby continuously improving the user's investment experience.

[0790] Example 1

[0791] 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."

[0792] Beginners in stock investment often find it difficult to predict corporate dividends and evaluate shareholder benefits. In particular, because information is not provided that meets the preferences or minimum desired value of individual investors, there is a lack of information to make decisions and it is difficult to make appropriate investment decisions.

[0793] 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.

[0794] In this invention, the server includes means for acquiring past dividend data, financial information, market trend data, and shareholder benefit details, means for storing data acquired from an external API in a database, means for dividing the data into training data and test data, means for predicting future dividends using a generative AI model trained on the past dividend data and financial information, means for analyzing the details of shareholder benefits and scoring the analysis results based on user preferences, means for displaying the predicted dividends and the analysis results to the user, and means for collecting user preferences and minimum desired values. This provides appropriate information that even beginners can use to easily make investment decisions, enabling efficient investment decisions.

[0795] "Past dividend data" is historical information about dividends paid by a company within a certain period of time, and indicates the company's dividend payment trends and history.

[0796] "Financial information" is data that represents a company's financial position and performance, such as its revenues, liabilities, assets, and cash flow.

[0797] "Market trend data" refers to data that indicates market trends, such as price fluctuations and trading volume across the market, and is used for investment decisions.

[0798] "Shareholder benefits" refers to the specific perks and benefits that a company provides to shareholders, and includes a variety of categories such as food and travel vouchers.

[0799] An "External API" is an application programming interface for communicating with external data sources and obtaining required data.

[0800] A "generative AI model" is a computational model that uses machine learning algorithms to learn from specific datasets and make predictions and analyses.

[0801] "User preferences" are the preferences and desires that individual investors have regarding specific categories and values, and are information that influences investment decisions.

[0802] "Minimum desired value" refers to the minimum value that users expect from shareholder benefits, and is a standard below which they will not be satisfied.

[0803] "Training data" is a dataset used to build and optimize a machine learning model, improving its accuracy.

[0804] "Test data" is a dataset used to evaluate the performance of a trained model and to confirm the model's predictive accuracy.

[0805] A database is a system that efficiently manages and stores structured data and allows quick access when needed.

[0806] This invention is a system that enables beginners to make effective investment decisions. The system includes functions for predicting dividends and analyzing shareholder benefits, and is composed of a server and a terminal. It is designed to allow users to easily obtain and understand investment information.

[0807] Data Acquisition

[0808] The server uses a RESTful API to retrieve historical dividend data, financial information, market trend data, and shareholder benefits from external APIs. The data is received in JSON format and stored in a MySQL database.

[0809] Examples:

[0810] The server retrieves historical dividend data from http: / / api.marketdata.com / dividends and inserts it into a "Company Dividend Table."

[0811] Model training and prediction

[0812] The server splits the acquired data into training data and test data. For example, 80% of the data is used for training and 20% for testing. The server then uses a machine learning library such as Scikit-learn to train a linear regression model based on the training data.

[0813] Examples:

[0814] The server builds a model to predict dividends using data such as revenue, liabilities, and assets of "Company A."

[0815] Analysis of shareholder benefits

[0816] The server scores the shareholder benefits based on user preference information (e.g., specific benefit categories and minimum desired value). This scoring is adjusted according to the user's individual preferences.

[0817] Examples:

[0818] The server gives a high score to a special offer worth 5,000 yen in the food category, and adds an additional score if the value exceeds the user's minimum desired value.

[0819] Displaying Information

[0820] The terminal displays the predicted dividend information and scoring results sent from the server to the user in a visually easy-to-understand format, allowing the user to make investment decisions based on this information.

[0821] Examples:

[0822] The terminal will display "Company A's projected dividend amount for 2023: 120 yen" and "Company A's shareholder benefits in the food category: score 90 points."

[0823] Usage example

[0824] The specific steps for a user to use the system are as follows: First, the user enters their basic investment preferences (e.g., they like shareholder benefits in the food category and want benefits worth at least 1,000 yen). The device sends this information to the server, which then collects the necessary data from external APIs, trains a generative AI model, and analyzes dividend predictions and shareholder benefits. The device then displays a list of shareholder benefits scored based on the predicted dividend information and the user's preferences.

[0825] Example prompts for generative AI models

[0826] "Based on the following financial data, predict the company's dividend for next year."

[0827] "Please score the benefits in the food category based on the shareholder benefits information."

[0828] This system allows even beginners to make investment decisions easily and effectively, supporting efficient investment decisions.

[0829] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0830] Step 1:

[0831] The server retrieves past dividend data, financial information, market trend data, and shareholder benefits details from an external API. It sends an HTTP request to the API endpoint and receives JSON-formatted data in response. This process aggregates the necessary investment data on the server.

[0832] Specific behavior:

[0833] The server sends an HTTP GET request to http: / / api.marketdata.com / dividends to retrieve the dividend amount for each company by year.

[0834] input:

[0835] External API Endpoints

[0836] output:

[0837] Investment data in JSON format

[0838] Step 2:

[0839] The server parses the received JSON data and saves it in a MySQL database. When saving the data to the database, the data is converted and formatted as necessary.

[0840] Specific behavior:

[0841] The server inserts "Company A's 2022 dividend amount: 100 yen" into the "Company Dividend Table."

[0842] input:

[0843] Investment data in JSON format

[0844] output:

[0845] Formatted data stored in a database

[0846] Step 3:

[0847] The server extracts historical dividend data and financial information from the database and splits it into training and test data, typically 80% as training data and 20% as test data.

[0848] Specific behavior:

[0849] The server extracts dividend data from 2010 to 2019 from the database as training data and data from 2020 as test data.

[0850] input:

[0851] Historical dividend data and financial information in the database

[0852] output:

[0853] training dataset, test dataset

[0854] Step 4:

[0855] The server uses the training data to train a generative AI model, which is a linear regression model built using libraries such as Scikit-learn.

[0856] Specific behavior:

[0857] The server trains the model based on specific financial metrics such as revenue, liabilities, and assets.

[0858] input:

[0859] Training dataset

[0860] output:

[0861] Pre-trained generative AI models

[0862] Step 5:

[0863] The server feeds new financial information into the trained generative AI model to predict future dividends, which are then compared to test data to confirm accuracy.

[0864] Specific behavior:

[0865] The server inputs the new financial information into the model to predict next year's dividends.

[0866] input:

[0867] New Financial Information

[0868] output:

[0869] Projected dividend amount

[0870] Step 6:

[0871] The terminal collects the user's preferences and minimum desired value and sends this information to the server, allowing the system to respond to the user's individual preferences.

[0872] Specific behavior:

[0873] The user inputs that he / she likes shareholder benefits in the food category and wants benefits worth at least 1,000 yen.

[0874] input:

[0875] User preferences, minimum desired value

[0876] output:

[0877] User information sent to the server

[0878] Step 7:

[0879] The server scores shareholder benefit information based on the user's preferences. It analyzes the content of a company's shareholder benefits and calculates a score by comparing it with the user's preferences.

[0880] Specific behavior:

[0881] The server will give a high score to perks worth 5,000 yen in the food category, and will add more points if the minimum desired value is exceeded.

[0882] input:

[0883] User information, shareholder benefits

[0884] output:

[0885] Scored shareholder benefits information

[0886] Step 8:

[0887] The terminal displays the predicted dividend information and scoring results sent from the server to the user in a visually easy-to-understand format, allowing the user to make investment decisions based on this information.

[0888] Specific behavior:

[0889] The terminal will display "Company A's projected dividend amount for 2023: 120 yen" and "Company A's shareholder benefits in the food category: score 90 points."

[0890] input:

[0891] Predicted dividend information and scoring results from the server

[0892] output:

[0893] Investment information displayed to the user

[0894] (Application example 1)

[0895] 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."

[0896] For beginners in stock investment, collecting and analyzing the information necessary to make effective investment decisions is extremely difficult. In particular, predicting dividends and evaluating shareholder benefits are complex and require specialized knowledge and experience. Providing investment information tailored to user preferences is also important, but achieving this poses many technical challenges. A system that solves these problems and allows even beginners to easily make investment decisions is needed.

[0897] 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.

[0898] In this invention, the server includes means for acquiring past dividend data, financial information, market trend data, and shareholder benefit details, means for predicting future dividends using a generative AI model trained on the past dividend data and financial information, means for analyzing the details of shareholder benefits and scoring the analysis results based on user preferences, means for displaying the predicted dividends and the analysis results to the user, and a smartphone application means for visually presenting dividend forecasts and shareholder benefit evaluation information based on a user profile. This allows even beginners to stock investment to easily make effective investment decisions.

[0899] "Past dividend data" is historical information about dividends paid by a company in the past.

[0900] "Financial information" is data about a company's financial condition, including its revenues, liabilities, assets, and cash flow.

[0901] "Market trend data" refers to data that indicates market activity such as price fluctuations and trading volume across the market.

[0902] "Shareholder benefits" refers to detailed information about the perks and services that a company provides to its shareholders.

[0903] A "generative AI model" is a model that contains machine learning algorithms that are trained using historical data and designed to predict future values.

[0904] "User preferences" are personal evaluation criteria or preferences that a user has for a particular shareholder benefit category or minimum value.

[0905] A "smartphone application means" is a software application that is installed on a smartphone device and provides functionality through a user interface.

[0906] "Scoring" is the process of assigning a rating based on specific criteria.

[0907] "Visually presenting" refers to displaying data and information in an easy-to-understand manner using graphs, charts, etc.

[0908] A "user profile" is individualized settings information that includes a user's preferences and history information.

[0909] An "external API" is an application programming interface for obtaining data from external systems or services.

[0910] A "linear regression model" is a statistical machine learning model that makes predictions using linear relationships between variables.

[0911] This invention is a system that enables beginners to make effective investment decisions in stock investments, and includes functions for predicting dividends and analyzing shareholder benefits. The system is composed of a server and a smartphone terminal, and is designed to allow users to easily obtain and understand investment information.

[0912] Data Acquisition

[0913] First, the server uses an external API to retrieve historical dividend data, financial information, market trend data, and shareholder benefits. This data includes historical information on dividends paid by companies, financial status such as revenue, liabilities, assets, and cash flow, as well as market activity data such as overall market price fluctuations and trading volume.

[0914] Training and predicting dividend prediction models

[0915] Next, the server trains a generative AI model using the acquired historical dividend data and financial information. A linear regression model is used for this model. The model is built using separate training and test data, and the trained model is used to make dividend predictions based on new financial information.

[0916] Shareholder Benefit Analysis

[0917] The server then analyzes the content of the shareholder benefits and scores the analysis results based on the user's preferences, taking into account the user's preferences for specific categories (e.g., food, travel) and minimum value criteria (e.g., 1,000 yen or more).

[0918] Displaying Information

[0919] The acquired information and forecast results are provided visually to users through a smartphone application. The application displays dividend forecasts and shareholder benefit evaluation information based on the user profile. Users can visually check the forecast dividend amount and benefit details for each year, as well as their scores, and make investment decisions.

[0920] Hardware and software used

[0921] This system is implemented using Python and its main libraries (requests, numpy, sklearn). The hardware required is a server computer and a smartphone.

[0922] Examples and prompts

[0923] For example, a user may specify that they like shareholder benefits in the food category and would like them to be worth at least 1,000 yen. The server uses a model to predict dividends based on new financial information and scores the benefits. The prediction results and evaluation are then provided to the user via a smartphone application.

[0924] Example prompt sentence:

[0925] User preference: Food, Minimum desired value: 1000 yen

[0926] Dividend forecast:

[0927] Financial Data: New Financial Data

[0928] Shareholder Benefit Analysis:

[0929] Priority Category: Food

[0930] Calculating shareholder benefits score

[0931] In this way, even beginners can easily make effective investment decisions.

[0932] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0933] Step 1: Data Acquisition

[0934] The server uses an external API to obtain historical dividend data, financial information, market trend data, and shareholder benefits. The input is the data request from the API, and the output is the obtained data. Specifically, the server accesses the API endpoint and obtains the required data in JSON format.

[0935] Step 2: Data Preprocessing

[0936] The server preprocesses the acquired data. The input is the data acquired in step 1, and the output is the preprocessed data. Specifically, it complements missing values, removes outliers, and normalizes the data.

[0937] Step 3: Train the dividend prediction model

[0938] The server uses the preprocessed data to train a generative AI model (linear regression model). The input is the preprocessed data, and the output is the trained AI model. Specifically, the model is trained using financial information as features and dividend data as target values.

[0939] Step 4: Dividend Forecast

[0940] The server inputs new financial information and uses the trained AI model to predict future dividends. The inputs are new financial information and the trained model, and the output is the predicted dividend. Specifically, new financial data is input into the model and dividends are predicted.

[0941] Step 5: Shareholder Benefit Analysis and Scoring

[0942] The server analyzes the content of shareholder benefits and scores them based on the user's preferences. The input is shareholder benefit data and user preference data, and the output is the scoring result. Specifically, the server evaluates the benefits based on the categories and value criteria specified by the user and calculates a score.

[0943] Step 6: Get User Information

[0944] The terminal acquires the user's preferences and investment goals. The input is the user's input data, and the output is the user profile. Specifically, the user sets the preferred categories and minimum value through the interface.

[0945] Step 7: Viewing information

[0946] The terminal visually displays the predicted payouts and analysis results received from the server to the user. The input is data from the server, and the output is what is displayed on the user's screen. Specifically, the predicted payout amounts and preferential treatment scores are displayed in graphs and tables. The terminal also provides an interface that is easy for the user to understand.

[0947] Step 8: Recording User Actions

[0948] The terminal records the user's actions, such as investment decisions and setting changes. The input is the user's action data, and the output is the recorded log data. Specifically, various operations performed by the user are recorded in a log and used for future data analysis and improvements.

[0949] 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.

[0950] This invention is a system that recognizes and analyzes users' emotions when it comes to stock investment, and supports investment decisions based on that information. In particular, by combining an emotion engine with dividend forecasting and shareholder benefit analysis, it provides personalized investment advice tailored to the individual needs of each user.

[0951] 1. Data Acquisition

[0952] server:

[0953] The server retrieves historical dividend data, financial information, market trend data, and shareholder benefits from external APIs, including historical information on dividends paid by companies, financial status such as revenue, liabilities, assets, and cash flow of companies, and data showing market activity such as overall market price fluctuations and volume.

[0954] 2. Training and Predicting the Dividend Prediction Model

[0955] server:

[0956] The server trains a generative AI model using the acquired historical dividend data and financial information. This model is trained using machine learning algorithms such as linear regression models to predict future dividends for companies. To do this, the data is first divided into training data and test data, and the model is then built and trained. The trained model is then used to predict dividends based on new financial information.

[0957] 3. Shareholder Benefit Analysis

[0958] server:

[0959] The server analyzes the content of the shareholder benefits and evaluates their value and attractiveness. This involves analyzing the shareholder benefit data and scoring them based on the preferences and conditions entered by the user (e.g., preferred benefit categories and expected minimum value).

[0960] 4. Implementing the Emotion Engine

[0961] server:

[0962] The server includes an emotion engine that analyzes the user's emotions. The emotion engine analyzes the user's facial expressions, voice tone, and input text as input data to recognize the user's emotions in real time. This emotion data is used to personalize the results of dividend forecasts and shareholder benefit analysis.

[0963] 5. Display of Information

[0964] Device:

[0965] The terminal displays the predicted dividend information and scored shareholder benefit information received from the server to the user. The displayed information is presented in a visually easy-to-understand format, including predicted dividend amounts for each fiscal year and scored benefit details. Furthermore, the emotional results analyzed by the emotion engine are reflected, allowing the user to receive the information in a relaxed state.

[0966] Specific use cases

[0967] User:

[0968] For example, when User A uses this system to make an investment decision, he or she first inputs basic investment preferences (e.g., he or she likes shareholder benefits in the food category and wants benefits worth at least 1,000 yen). The device then sends this information to the server. The server retrieves the necessary data from an external API and trains a generative AI model to predict dividends and analyze shareholder benefits. At the same time, the emotion engine analyzes the user's emotional state in real time and personalizes the displayed information based on the obtained emotional data.

[0969] As a result, the device displays predicted dividend information and shareholder benefit information scored based on User A's preferences. Furthermore, the information display is adjusted according to User A's emotional state, allowing him or her to make investment decisions in a more comfortable environment. Based on this, User A considers which stocks to invest in and actually makes the investment.

[0970] Continuous improvement of the investment experience

[0971] server:

[0972] The user's investment history and new feedback are sent to the server and the model is continually updated, which allows for even higher prediction accuracy in future investments and continuously improves the user's investment experience.

[0973] As an embodiment of the present invention, we have described a dividend forecasting and shareholder benefit analysis system that combines an emotion engine for beginners in stock investing. This system is designed to lower the barrier to investment and enable even beginners to easily make investment decisions.

[0974] The processing flow will be explained below.

[0975] Step 1:

[0976] The server retrieves past dividend data, financial information, market trend data, and shareholder benefits details from external APIs. Specifically, this includes historical information on dividends paid by companies in the past, financial information such as corporate revenue, liabilities, assets, and cash flow, and market activity data such as overall market price fluctuations and volume.

[0977] Step 2:

[0978] The server trains a generative AI model using the acquired historical dividend data and financial information. During this training process, the data is divided into training data and test data, and a machine learning algorithm such as a linear regression model is used to build a model. This model is used to predict a company's future dividends with high accuracy.

[0979] Step 3:

[0980] The server uses the trained generative AI model to predict future dividends based on new financial information. Specifically, it uses the latest market trend data and the company's financial situation as input data and uses the generative AI model to predict future dividend amounts.

[0981] Step 4:

[0982] The server analyzes the content of shareholder benefits. It analyzes the shareholder benefit data and scores it based on the preferences and conditions entered by the user (e.g., preferred benefit categories and expected minimum value). This allows it to extract attractive benefit information that matches the user's preferences.

[0983] Step 5:

[0984] The server uses an emotion engine to analyze the user's emotions based on the user's facial expressions, voice tone, input text, etc. The emotion engine recognizes the user's emotional state in real time and analyzes the results.

[0985] Step 6:

[0986] The server then personalizes the dividend forecast and shareholder benefit information based on the analyzed emotional data, adjusting the priority and format of the displayed information according to the user's emotional state.

[0987] Step 7:

[0988] The terminal displays the predicted dividend information and scored shareholder benefit information received from the server to the user. This information is provided in a visually easy-to-understand format, including predicted dividend amounts for each fiscal year and scored benefit details. The display is also adjusted to take into account the user's emotional state.

[0989] Step 8:

[0990] The user makes investment decisions based on the information provided by the terminal, and invests in the stocks that are most suitable for them, taking into account the predicted dividend amount and analyzed preferential treatment information.

[0991] Step 9:

[0992] The device sends feedback on the user's investment history and new preferences to the server, which then updates the model to further improve prediction accuracy in future rounds. This process continuously improves the user's investment experience.

[0993] As a result, a system has been realized that recognizes the user's emotions and provides personalized investment advice based on them, allowing even beginners to stock investment to easily make investment decisions.

[0994] Example 2

[0995] 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."

[0996] In stock investment, there is no system yet available that can meet the needs of users who want to make investment decisions that reflect their own emotional state. In particular, there is a demand for personalized information that takes into account the user's emotions when predicting dividends and analyzing shareholder benefits, but conventional technologies do not provide a concrete method for achieving this.

[0997] The specific processing by the specific 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 acquiring past distribution data, economic information, market trend data, and shareholder benefit information, means for predicting future dividends using a generative AI model trained on the past distribution data and economic information, means for analyzing the content of shareholder benefits and evaluating the analysis results based on the user's preferences, means for analyzing and recognizing the user's emotional state in real time, and means for adjusting the display of the predicted dividends and the analysis results based on the user's emotional state. This allows users to make investment decisions that reflect their own emotional state.

[0998] "Past distribution data" refers to historical data on the amount and dates of dividends paid by a company in the past.

[0999] "Economic information" refers to information that indicates financial data and economic indicators, including a company's revenue, liabilities, assets, cash flow, etc.

[1000] "Market trend data" refers to data that shows price fluctuations, trading volume, trends, etc. across the market.

[1001] "Shareholder benefit information" is information regarding the content and value of benefits that companies offer to shareholders.

[1002] A "generative AI model" is an artificial intelligence model trained using machine learning algorithms to make predictions or classifications based on input data.

[1003] A "regression model" is a model used in statistics and machine learning that represents the relationship between input variables and output variables and is used to predict future outputs.

[1004] "User preferences" refers to the user's individual tastes and desires, such as the categories and conditions that the user prefers.

[1005] An "emotional state" represents a user's current emotion (e.g., joy, sadness, surprise, etc.).

[1006] An "external API" is an application programming interface provided by an external system or service, and is a means for retrieving and manipulating data.

[1007] "Personalization" means providing information and services tailored to the individual needs and preferences of each user.

[1008] This invention is a system that supports decision-making in stock investment, particularly by taking into account the user's emotional state and providing personalized investment advice. The system acquires historical dividend data, corporate financial information, market trend data, and shareholder benefit information, and uses this data to train a generative AI model to predict future dividends. It also analyzes the content of shareholder benefits and evaluates them based on the user's preferences. Furthermore, it analyzes the user's emotional state in real time and uses that information to personalize investment advice.

[1009] Hardware and software used

[1010] server:

[1011] The server is primarily responsible for:

[1012] Data Acquisition: The server collects historical dividend data, company financial information, market trend data, and shareholder benefit information through external APIs. The hardware includes a high-performance CPU and large storage capacity, and the software uses a database (e.g., MySQL, PostgreSQL) and a REST API library (e.g., the Requests library).

[1013] Data storage: Collected data is stored in a database for smooth access.

[1014] Training a generative AI model: A machine learning library (e.g., scikit-learn) is used to train a generative AI model, such as a regression model, which may use a GPU to efficiently process large datasets.

[1015] Emotion analysis: Use emotion recognition APIs (e.g., Microsoft Azure's Face API, Google Cloud's Speech-to-Text API) to analyze the user's emotional state from their facial expressions, voice tone, and input text.

[1016] Device:

[1017] The terminal displays the information received from the server to the user:

[1018] Data display: The terminal uses a front-end framework (e.g., React, Vue.js) to display predicted dividend information and scored shareholder benefit information in a visually easy-to-understand format.

[1019] Emotional adjustment: The device personalizes the information displayed based on the user's emotional state, adjusting the device to receive the information in a more relaxed state.

[1020] User:

[1021] The user interacts with the system as follows:

[1022] Input of investment preferences: The user inputs their investment preferences and conditions into the terminal (e.g., "I like shareholder benefits in the food category, and I would like benefits worth at least 1,000 yen").

[1023] Provide feedback: Based on your investment results and experience, provide feedback to the system to help improve the model.

[1024] Specific examples

[1025] When a user uses this system to make an investment decision, they first enter their basic investment preferences. For example, User A might enter, "I like shareholder benefits in the food category, and I would like benefits worth at least 1,000 yen." The device then sends this information to the server. The server obtains the necessary data from an external API and trains a generative AI model to predict dividends and analyze shareholder benefits. At the same time, the emotion engine analyzes the user's emotional state in real time and personalizes the information display based on the obtained emotional data. The device displays predicted dividend information and shareholder benefit information scored based on User A's preferences, and the information display is adjusted according to User A's emotional state. User A then considers which stocks to invest in based on this information and makes the actual investment.

[1026] Prompt Sentence Examples

[1027] "Based on the dividend forecast and shareholder benefit analysis, please recommend the next stock I should buy. I like shareholder benefits in the food category and would like benefits worth at least 1,000 yen."

[1028] As described above, this system supports stock investment decision-making by providing accurate investment advice while taking into account the user's emotional state.

[1029] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1030] Step 1:

[1031] Data Acquisition

[1032] server:

[1033] Specifically, the server sends an HTTP GET request to an external API to retrieve historical distribution data, economic information, market trend data, and shareholder benefit information. The API endpoint URL and key are used as input. The output is JSON-formatted data. After retrieving this data, the server stores it in a database (e.g., MySQL), inserting the data into the appropriate table using the SQL INSERT statement.

[1034] Step 2:

[1035] Training a dividend prediction model

[1036] server:

[1037] The server extracts historical distribution data and economic information from the database. Specifically, it retrieves the data using a SELECT statement. The input is the database connection information and SQL query, and the output is a training dataset. Then, using a machine learning library (e.g., scikit-learn), it splits the dataset into training data and test data. This split is performed using the train_test_split function. Next, it trains a linear regression model using the fit method. The input is the training dataset, and the output is the trained model.

[1038] Step 3:

[1039] Dividend forecast

[1040] server:

[1041] New economic information is input into the model to predict future dividends. Specific operations use the predict method to obtain a predicted value. The input is a dataset of new economic information, and the output is the predicted dividend value. This prediction result is stored in a database.

[1042] Step 4:

[1043] Shareholder Benefit Analysis and Scoring

[1044] server:

[1045] It receives user preferences and conditions, analyzes shareholder benefit data, and performs evaluation. Specifically, it receives user input (e.g., preferred benefit category, expected minimum value) in JSON format and filters the shareholder benefit data using an SQL query. The input is the user preferences and shareholder benefit data, and the output is the score of the benefits based on the user conditions. It runs the scoring algorithm and calculates a score for each benefit.

[1046] Step 5:

[1047] Emotional state analysis

[1048] server:

[1049] The emotion recognition API is used to analyze the user's facial expression, voice tone, and input text. Specifically, an HTTP request is sent to the emotion recognition API to obtain the analysis results. The input is the user's facial expression image, voice data, and text data, and the output is the emotional state (e.g., joy, sadness, surprise). The analysis results are stored in a database and used for further processing.

[1050] Step 6:

[1051] Displaying Information

[1052] Device:

[1053] Predicted dividend information and scored shareholder benefit information are displayed to the user. Specifically, a front-end framework (e.g., React, Vue.js) is used to generate an interface that displays information in data table and graph format. The input is the dividend prediction and scoring results received from the server, and the output is a visually easy-to-understand display format. In addition, the display content is adjusted according to the user's emotional state based on the results of the emotion engine. For example, the display color and layout can be changed based on the emotional state.

[1054] Step 7:

[1055] Providing Feedback

[1056] User:

[1057] Feedback is sent to the system based on investment results and experience. Specifically, users enter information into a feedback form from their device and send it to the server. The input is the user's feedback, and the output is data that can be used to improve the system. The server stores this feedback in a database and uses it to update the model.

[1058] Through these steps, the system takes into account the user's emotional state, provides accurate investment advice, and supports stock investment decision-making.

[1059] (Application example 2)

[1060] 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."

[1061] Conventional stock investment support systems provide investment advice based on simple data analysis without considering the user's emotional state, resulting in a lack of psychological satisfaction and personalized recommendations. Therefore, there is a need for investment decision support that takes into account the user's emotional state. Furthermore, there is no adequate method for performing real-time emotional analysis and providing optimal investment information to users based on specific conditions.

[1062] 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.

[1063] In this invention, the server includes: means for acquiring past dividend data, financial information, market trend data, and shareholder benefit details; means for predicting future dividends using a generative AI model trained on the past dividend data and financial information; means for analyzing the details of shareholder benefits and scoring the analysis results based on the user's preferences; an emotion engine for recognizing and analyzing the user's emotional state; and means for displaying personalized information optimal for the user based on the emotional state. This makes it possible to provide personalized investment advice in real time according to the user's emotional state.

[1064] "Past dividend data" refers to historical information about dividends paid by a company.

[1065] "Financial information" is data that shows a company's financial status, such as revenue, liabilities, assets, and cash flow.

[1066] "Market trend data" is data that indicates market activity, such as price fluctuations and trading volume across the market.

[1067] "Shareholder benefits" refers to information about the perks and services that a company provides to its shareholders.

[1068] A "generative AI model" is an artificial intelligence model that is trained to predict future outputs based on input data.

[1069] An "emotion engine" is a system that recognizes emotions by analyzing a user's facial expressions, voice tone, input text, etc.

[1070] "Personalization" means optimizing information and services according to the preferences and emotional state of individual users.

[1071] "Scoring" is the process of assigning an evaluation or score based on certain criteria.

[1072] "Means for displaying information" refers to an interface that visually presents analysis results and predicted data to users.

[1073] An "external API" is an external application program interface for connecting with other services or databases.

[1074] This invention is a system that recognizes and analyzes user emotions in food delivery services and makes personalized meal recommendations based on that information. This system can be accessed by users through a smartphone application.

[1075] Data acquisition and analysis

[1076] The server uses an external API to retrieve the user's past order history and menu information. For example, the data retrieved from the API includes order details (price, rating, order frequency, etc.).

[1077] Emotion analysis

[1078] The emotion analysis module analyzes the user's real-time emotional state. It uses OpenCV for facial expression analysis and TextBlob for voice tone analysis. It also analyzes the input text to comprehensively evaluate the user's emotional state.

[1079] Recommendation Algorithm

[1080] The server trains a generative AI model based on the user's past order history and real-time emotional state to predict the optimal meal menu. The generative AI model uses a linear regression model and is trained based on past data.

[1081] Displaying personalized information

[1082] The device receives the recommendation results from the server and displays optimized menu information to the user, including menu names, prices, ratings, etc. Furthermore, the information display is adjusted taking into account the user's emotional state.

[1083] Specific examples

[1084] For example, when User B launches a food delivery app on his smartphone, he enters the following prompt:

[1085] text:

[1086] I'm feeling a bit tired today and want to relieve stress. What meals would you recommend?

[1087] The server analyzes this prompt, recognizes User B's current emotional state, and can then suggest relaxing, healthy meals or their favorite sweets, allowing the user to choose the optimal meal according to their emotions at the time.

[1088] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1089] Step 1:

[1090] The server uses an external API to retrieve the user's past order history and menu information. It uses the API endpoint and the user's ID as input, and obtains the order history data and menu information data as output. This data retrieval involves sending an HTTP request and receiving the data in JSON format.

[1091] Step 2:

[1092] The server preprocesses the acquired order history data. Specifically, it cleans the data, handles missing values, and selects features. It uses the acquired order history data as input and obtains clean training data as output. This preprocessing includes operations that perform data frame operations within the program.

[1093] Step 3:

[1094] The server uses an emotion analysis module to analyze the user's emotional state. It uses facial expression images, voice samples, and text inputs obtained from the user as inputs, and obtains the user's emotion score as output. Specifically, it analyzes facial expression images using OpenCV, and voice samples and text inputs using TextBlob.

[1095] Step 4:

[1096] The server uses a generative AI model to predict the optimal menu for a user based on the preprocessed order history data and real-time sentiment scores. It uses the preprocessed order history data and sentiment scores as input and obtains a list of recommended menu items as output. This prediction involves applying a Linear Regression model and obtaining the model's prediction results.

[1097] Step 5:

[1098] The terminal receives the recommendation results from the server and displays them to the user. It uses the list of recommended menus as input and obtains menu information visually displayed to the user as output. Specifically, it includes the operation of displaying information such as menu name, price, and rating to the user in list form.

[1099] Step 6:

[1100] The user selects and orders a meal from the recommended menu displayed on the device. The input is a menu selected from the list of recommended menus, and the output is a confirmation of the order. Specifically, this involves selecting and ordering a meal through button operations within the app.

[1101] 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.

[1102] 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.

[1103] 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.

[1104] [Fourth embodiment]

[1105] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1106] 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.

[1107] 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).

[1108] 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.

[1109] 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.

[1110] 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).

[1111] 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.

[1112] 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.

[1113] 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.

[1114] 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.

[1115] 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.

[1116] 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.

[1117] 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."

[1118] This invention is a system that enables beginners to make effective investment decisions in stock investments, and includes functions for predicting dividends and analyzing shareholder benefits. The system is composed of a server and a terminal, and is designed to allow users to easily obtain and understand investment information.

[1119] 1. Data Acquisition

[1120] server:

[1121] The server retrieves historical dividend data, financial information, market trend data, and shareholder benefits from external APIs. This data consists of historical information on dividends paid by companies in the past, financial status including revenue, liabilities, assets, and cash flow, as well as market activity data such as overall market price fluctuations and volume.

[1122] 2. Training and Predicting the Dividend Prediction Model

[1123] server:

[1124] The server trains a generative AI model using the acquired historical dividend data and financial information. This model uses machine learning algorithms such as linear regression models to predict a company's future dividends with high accuracy. To do this, the data is first divided into training data and test data, and the model is then built and trained. The trained model is then used to predict dividends based on new financial information.

[1125] 3. Shareholder Benefit Analysis

[1126] server:

[1127] The server analyzes the content of the shareholder perks and evaluates their value and attractiveness. This evaluation also takes into account the user's preferences. For example, if a user prefers perks in a particular category, such as food or travel, a high score will be assigned to perks in that category. Also, if the value of a perk exceeds the user's minimum expectations, an additional score will be assigned to that perk.

[1128] 4. Displaying Information

[1129] Device:

[1130] The terminal displays the predicted dividends and analyzed shareholder benefit information received from the server to the user. The user makes investment decisions based on this information. The displayed information is presented in a visually easy-to-understand format, including predicted dividend amounts by year, benefit details, and scores.

[1131] Specific use cases

[1132] User:

[1133] For example, when User A uses this system to make an investment decision, he or she first inputs his or her basic investment preferences (e.g., he or she likes shareholder benefits in the food category, and wants benefits worth at least 1,000 yen).Then, the device sends this information to the server, which retrieves the necessary data from an external API, trains a generative AI model, and performs dividend prediction and shareholder benefit analysis.

[1134] The terminal displays predicted dividend information and a list of shareholder benefits scored based on User A's preferences. Based on this, User A can easily decide which stocks to invest in. In this way, even beginners can significantly lower the investment hurdles and support efficient investment decisions.

[1135] The above describes a dividend forecasting and shareholder benefit analysis system for beginners in stock investment as an embodiment of the present invention. This system is designed to lower the barrier to investment and enable even beginners to easily make investment decisions.

[1136] The processing flow will be explained below.

[1137] Step 1:

[1138] The server retrieves historical dividend data, financial information, market trend data, and shareholder benefits from external APIs, including historical information on dividends paid by companies, financial status including revenue, liabilities, assets, and cash flow, as well as data showing market activity such as overall market price fluctuations and volume.

[1139] Step 2:

[1140] The server trains a generative AI model using the acquired historical dividend data and financial information. The data is divided into training data and test data, and training is performed using a generative AI model (e.g., a linear regression model). Once trained, the model is used to predict future dividends based on new financial information.

[1141] Step 3:

[1142] The server uses the trained generative AI model to predict future dividends based on new financial information data. This process uses the latest market trend data and the company's financial situation as inputs to predict future dividend amounts.

[1143] Step 4:

[1144] The server analyzes the content of shareholder benefits. It analyzes the shareholder benefit data and scores it based on the preferences and conditions entered by the user (e.g., preferred benefit categories and expected minimum value). This allows it to extract attractive benefit information that matches the user's preferences.

[1145] Step 5:

[1146] The terminal displays the predicted dividend information and scored shareholder benefit information received from the server to the user. The displayed information is presented in a visually easy-to-understand format, including the predicted dividend amount for each fiscal year and the scored benefit details.

[1147] Step 6:

[1148] Users make investment decisions based on the information provided by the terminal. They can use the predicted dividend amount and analyzed preferential treatment information as a reference to invest in the stocks that are most suitable for them.

[1149] Step 7:

[1150] The device sends feedback on the user's investment history and new preferences to the server, which then updates the model based on this information to further improve prediction accuracy in future rounds, thereby continuously improving the user's investment experience.

[1151] Example 1

[1152] 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."

[1153] Beginners in stock investment often find it difficult to predict corporate dividends and evaluate shareholder benefits. In particular, because information is not provided that meets the preferences or minimum desired value of individual investors, there is a lack of information to make decisions and it is difficult to make appropriate investment decisions.

[1154] 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.

[1155] In this invention, the server includes means for acquiring past dividend data, financial information, market trend data, and shareholder benefit details, means for storing data acquired from an external API in a database, means for dividing the data into training data and test data, means for predicting future dividends using a generative AI model trained on the past dividend data and financial information, means for analyzing the details of shareholder benefits and scoring the analysis results based on user preferences, means for displaying the predicted dividends and the analysis results to the user, and means for collecting user preferences and minimum desired values. This provides appropriate information that even beginners can use to easily make investment decisions, enabling efficient investment decisions.

[1156] "Past dividend data" is historical information about dividends paid by a company within a certain period of time, and indicates the company's dividend payment trends and history.

[1157] "Financial information" is data that represents a company's financial position and performance, such as its revenues, liabilities, assets, and cash flow.

[1158] "Market trend data" refers to data that indicates market trends, such as price fluctuations and trading volume across the market, and is used for investment decisions.

[1159] "Shareholder benefits" refers to the specific perks and benefits that a company provides to shareholders, and includes a variety of categories such as food and travel vouchers.

[1160] An "External API" is an application programming interface for communicating with external data sources and obtaining required data.

[1161] A "generative AI model" is a computational model that uses machine learning algorithms to learn from specific datasets and make predictions and analyses.

[1162] "User preferences" are the preferences and desires that individual investors have regarding specific categories and values, and are information that influences investment decisions.

[1163] "Minimum desired value" refers to the minimum value that users expect from shareholder benefits, and is a standard below which they will not be satisfied.

[1164] "Training data" is a dataset used to build and optimize a machine learning model, improving its accuracy.

[1165] "Test data" is a dataset used to evaluate the performance of a trained model and to confirm the model's predictive accuracy.

[1166] A database is a system that efficiently manages and stores structured data and allows quick access when needed.

[1167] This invention is a system that enables beginners to make effective investment decisions. The system includes functions for predicting dividends and analyzing shareholder benefits, and is composed of a server and a terminal. It is designed to allow users to easily obtain and understand investment information.

[1168] Data Acquisition

[1169] The server uses a RESTful API to retrieve historical dividend data, financial information, market trend data, and shareholder benefits from external APIs. The data is received in JSON format and stored in a MySQL database.

[1170] Examples:

[1171] The server retrieves historical dividend data from http: / / api.marketdata.com / dividends and inserts it into a "Company Dividend Table."

[1172] Model training and prediction

[1173] The server splits the acquired data into training data and test data. For example, 80% of the data is used for training and 20% for testing. The server then uses a machine learning library such as Scikit-learn to train a linear regression model based on the training data.

[1174] Examples:

[1175] The server builds a model to predict dividends using data such as revenue, liabilities, and assets of "Company A."

[1176] Analysis of shareholder benefits

[1177] The server scores the shareholder benefits based on user preference information (e.g., specific benefit categories and minimum desired value). This scoring is adjusted according to the user's individual preferences.

[1178] Examples:

[1179] The server gives a high score to a special offer worth 5,000 yen in the food category, and adds an additional score if the value exceeds the user's minimum desired value.

[1180] Displaying Information

[1181] The terminal displays the predicted dividend information and scoring results sent from the server to the user in a visually easy-to-understand format, allowing the user to make investment decisions based on this information.

[1182] Examples:

[1183] The terminal will display "Company A's projected dividend amount for 2023: 120 yen" and "Company A's shareholder benefits in the food category: score 90 points."

[1184] Usage example

[1185] The specific steps for a user to use the system are as follows: First, the user enters their basic investment preferences (e.g., they like shareholder benefits in the food category and want benefits worth at least 1,000 yen). The device sends this information to the server, which then collects the necessary data from external APIs, trains a generative AI model, and analyzes dividend predictions and shareholder benefits. The device then displays a list of shareholder benefits scored based on the predicted dividend information and the user's preferences.

[1186] Example prompts for generative AI models

[1187] "Based on the following financial data, predict the company's dividend for next year."

[1188] "Please score the benefits in the food category based on the shareholder benefits information."

[1189] This system allows even beginners to make investment decisions easily and effectively, supporting efficient investment decisions.

[1190] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1191] Step 1:

[1192] The server retrieves past dividend data, financial information, market trend data, and shareholder benefits details from an external API. It sends an HTTP request to the API endpoint and receives JSON-formatted data in response. This process aggregates the necessary investment data on the server.

[1193] Specific behavior:

[1194] The server sends an HTTP GET request to http: / / api.marketdata.com / dividends to retrieve the dividend amount for each company by year.

[1195] input:

[1196] External API Endpoints

[1197] output:

[1198] Investment data in JSON format

[1199] Step 2:

[1200] The server parses the received JSON data and saves it in a MySQL database. When saving the data to the database, the data is converted and formatted as necessary.

[1201] Specific behavior:

[1202] The server inserts "Company A's 2022 dividend amount: 100 yen" into the "Company Dividend Table."

[1203] input:

[1204] Investment data in JSON format

[1205] output:

[1206] Formatted data stored in a database

[1207] Step 3:

[1208] The server extracts historical dividend data and financial information from the database and splits it into training and test data, typically 80% as training data and 20% as test data.

[1209] Specific behavior:

[1210] The server extracts dividend data from 2010 to 2019 from the database as training data and data from 2020 as test data.

[1211] input:

[1212] Historical dividend data and financial information in the database

[1213] output:

[1214] training dataset, test dataset

[1215] Step 4:

[1216] The server uses the training data to train a generative AI model, which is a linear regression model built using libraries such as Scikit-learn.

[1217] Specific behavior:

[1218] The server trains the model based on specific financial metrics such as revenue, liabilities, and assets.

[1219] input:

[1220] Training dataset

[1221] output:

[1222] Pre-trained generative AI models

[1223] Step 5:

[1224] The server feeds new financial information into the trained generative AI model to predict future dividends, which are then compared to test data to confirm accuracy.

[1225] Specific behavior:

[1226] The server inputs the new financial information into the model to predict next year's dividends.

[1227] input:

[1228] New Financial Information

[1229] output:

[1230] Projected dividend amount

[1231] Step 6:

[1232] The terminal collects the user's preferences and minimum desired value and sends this information to the server, allowing the system to respond to the user's individual preferences.

[1233] Specific behavior:

[1234] The user inputs that he / she likes shareholder benefits in the food category and wants benefits worth at least 1,000 yen.

[1235] input:

[1236] User preferences, minimum desired value

[1237] output:

[1238] User information sent to the server

[1239] Step 7:

[1240] The server scores shareholder benefit information based on the user's preferences. It analyzes the content of a company's shareholder benefits and calculates a score by comparing it with the user's preferences.

[1241] Specific behavior:

[1242] The server will give a high score to perks worth 5,000 yen in the food category, and will add more points if the minimum desired value is exceeded.

[1243] input:

[1244] User information, shareholder benefits

[1245] output:

[1246] Scored shareholder benefits information

[1247] Step 8:

[1248] The terminal displays the predicted dividend information and scoring results sent from the server to the user in a visually easy-to-understand format, allowing the user to make investment decisions based on this information.

[1249] Specific behavior:

[1250] The terminal will display "Company A's projected dividend amount for 2023: 120 yen" and "Company A's shareholder benefits in the food category: score 90 points."

[1251] input:

[1252] Predicted dividend information and scoring results from the server

[1253] output:

[1254] Investment information displayed to the user

[1255] (Application example 1)

[1256] 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."

[1257] For beginners in stock investment, collecting and analyzing the information necessary to make effective investment decisions is extremely difficult. In particular, predicting dividends and evaluating shareholder benefits are complex and require specialized knowledge and experience. Providing investment information tailored to user preferences is also important, but achieving this poses many technical challenges. A system that solves these problems and allows even beginners to easily make investment decisions is needed.

[1258] 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.

[1259] In this invention, the server includes means for acquiring past dividend data, financial information, market trend data, and shareholder benefit details, means for predicting future dividends using a generative AI model trained on the past dividend data and financial information, means for analyzing the details of shareholder benefits and scoring the analysis results based on user preferences, means for displaying the predicted dividends and the analysis results to the user, and a smartphone application means for visually presenting dividend forecasts and shareholder benefit evaluation information based on a user profile. This allows even beginners to stock investment to easily make effective investment decisions.

[1260] "Past dividend data" is historical information about dividends paid by a company in the past.

[1261] "Financial information" is data about a company's financial condition, including its revenues, liabilities, assets, and cash flow.

[1262] "Market trend data" refers to data that indicates market activity such as price fluctuations and trading volume across the market.

[1263] "Shareholder benefits" refers to detailed information about the perks and services that a company provides to its shareholders.

[1264] A "generative AI model" is a model that contains machine learning algorithms that are trained using historical data and designed to predict future values.

[1265] "User preferences" are personal evaluation criteria or preferences that a user has for a particular shareholder benefit category or minimum value.

[1266] A "smartphone application means" is a software application that is installed on a smartphone device and provides functionality through a user interface.

[1267] "Scoring" is the process of assigning a rating based on specific criteria.

[1268] "Visually presenting" refers to displaying data and information in an easy-to-understand manner using graphs, charts, etc.

[1269] A "user profile" is individualized settings information that includes a user's preferences and history information.

[1270] An "external API" is an application programming interface for obtaining data from external systems or services.

[1271] A "linear regression model" is a statistical machine learning model that makes predictions using linear relationships between variables.

[1272] This invention is a system that enables beginners to make effective investment decisions in stock investments, and includes functions for predicting dividends and analyzing shareholder benefits. The system is composed of a server and a smartphone terminal, and is designed to allow users to easily obtain and understand investment information.

[1273] Data Acquisition

[1274] First, the server uses an external API to retrieve historical dividend data, financial information, market trend data, and shareholder benefits. This data includes historical information on dividends paid by companies, financial status such as revenue, liabilities, assets, and cash flow, as well as market activity data such as overall market price fluctuations and trading volume.

[1275] Training and predicting dividend prediction models

[1276] Next, the server trains a generative AI model using the acquired historical dividend data and financial information. A linear regression model is used for this model. The model is built using separate training and test data, and the trained model is used to make dividend predictions based on new financial information.

[1277] Shareholder Benefit Analysis

[1278] The server then analyzes the content of the shareholder benefits and scores the analysis results based on the user's preferences, taking into account the user's preferences for specific categories (e.g., food, travel) and minimum value criteria (e.g., 1,000 yen or more).

[1279] Displaying Information

[1280] The acquired information and forecast results are provided visually to users through a smartphone application. The application displays dividend forecasts and shareholder benefit evaluation information based on the user profile. Users can visually check the forecast dividend amount and benefit details for each year, as well as their scores, and make investment decisions.

[1281] Hardware and software used

[1282] This system is implemented using Python and its main libraries (requests, numpy, sklearn). The hardware required is a server computer and a smartphone.

[1283] Examples and prompts

[1284] For example, a user may specify that they like shareholder benefits in the food category and would like them to be worth at least 1,000 yen. The server uses a model to predict dividends based on new financial information and scores the benefits. The prediction results and evaluation are then provided to the user via a smartphone application.

[1285] Example prompt sentence:

[1286] User preference: Food, Minimum desired value: 1000 yen

[1287] Dividend forecast:

[1288] Financial Data: New Financial Data

[1289] Shareholder Benefit Analysis:

[1290] Priority Category: Food

[1291] Calculating shareholder benefits score

[1292] In this way, even beginners can easily make effective investment decisions.

[1293] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1294] Step 1: Data Acquisition

[1295] The server uses an external API to obtain historical dividend data, financial information, market trend data, and shareholder benefits. The input is the data request from the API, and the output is the obtained data. Specifically, the server accesses the API endpoint and obtains the required data in JSON format.

[1296] Step 2: Data Preprocessing

[1297] The server preprocesses the acquired data. The input is the data acquired in step 1, and the output is the preprocessed data. Specifically, it complements missing values, removes outliers, and normalizes the data.

[1298] Step 3: Train the dividend prediction model

[1299] The server uses the preprocessed data to train a generative AI model (linear regression model). The input is the preprocessed data, and the output is the trained AI model. Specifically, the model is trained using financial information as features and dividend data as target values.

[1300] Step 4: Dividend Forecast

[1301] The server inputs new financial information and uses the trained AI model to predict future dividends. The inputs are new financial information and the trained model, and the output is the predicted dividend. Specifically, new financial data is input into the model and dividends are predicted.

[1302] Step 5: Shareholder Benefit Analysis and Scoring

[1303] The server analyzes the content of shareholder benefits and scores them based on the user's preferences. The input is shareholder benefit data and user preference data, and the output is the scoring result. Specifically, the server evaluates the benefits based on the categories and value criteria specified by the user and calculates a score.

[1304] Step 6: Get User Information

[1305] The terminal acquires the user's preferences and investment goals. The input is the user's input data, and the output is the user profile. Specifically, the user sets the preferred categories and minimum value through the interface.

[1306] Step 7: Viewing information

[1307] The terminal visually displays the predicted payouts and analysis results received from the server to the user. The input is data from the server, and the output is what is displayed on the user's screen. Specifically, the predicted payout amounts and preferential treatment scores are displayed in graphs and tables. The terminal also provides an interface that is easy for the user to understand.

[1308] Step 8: Recording User Actions

[1309] The terminal records the user's actions, such as investment decisions and setting changes. The input is the user's action data, and the output is the recorded log data. Specifically, various operations performed by the user are recorded in a log and used for future data analysis and improvements.

[1310] 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.

[1311] This invention is a system that recognizes and analyzes users' emotions when it comes to stock investment, and supports investment decisions based on that information. In particular, by combining an emotion engine with dividend forecasting and shareholder benefit analysis, it provides personalized investment advice tailored to the individual needs of each user.

[1312] 1. Data Acquisition

[1313] server:

[1314] The server retrieves historical dividend data, financial information, market trend data, and shareholder benefits from external APIs, including historical information on dividends paid by companies, financial status such as revenue, liabilities, assets, and cash flow of companies, and data showing market activity such as overall market price fluctuations and volume.

[1315] 2. Training and Predicting the Dividend Prediction Model

[1316] server:

[1317] The server trains a generative AI model using the acquired historical dividend data and financial information. This model is trained using machine learning algorithms such as linear regression models to predict future dividends for companies. To do this, the data is first divided into training data and test data, and the model is then built and trained. The trained model is then used to predict dividends based on new financial information.

[1318] 3. Shareholder Benefit Analysis

[1319] server:

[1320] The server analyzes the content of the shareholder benefits and evaluates their value and attractiveness. This involves analyzing the shareholder benefit data and scoring them based on the preferences and conditions entered by the user (e.g., preferred benefit categories and expected minimum value).

[1321] 4. Implementing the Emotion Engine

[1322] server:

[1323] The server includes an emotion engine that analyzes the user's emotions. The emotion engine analyzes the user's facial expressions, voice tone, and input text as input data to recognize the user's emotions in real time. This emotion data is used to personalize the results of dividend forecasts and shareholder benefit analysis.

[1324] 5. Display of Information

[1325] Device:

[1326] The terminal displays the predicted dividend information and scored shareholder benefit information received from the server to the user. The displayed information is presented in a visually easy-to-understand format, including predicted dividend amounts for each fiscal year and scored benefit details. Furthermore, the emotional results analyzed by the emotion engine are reflected, allowing the user to receive the information in a relaxed state.

[1327] Specific use cases

[1328] User:

[1329] For example, when User A uses this system to make an investment decision, he or she first inputs basic investment preferences (e.g., he or she likes shareholder benefits in the food category and wants benefits worth at least 1,000 yen). The device then sends this information to the server. The server retrieves the necessary data from an external API and trains a generative AI model to predict dividends and analyze shareholder benefits. At the same time, the emotion engine analyzes the user's emotional state in real time and personalizes the displayed information based on the obtained emotional data.

[1330] As a result, the device displays predicted dividend information and shareholder benefit information scored based on User A's preferences. Furthermore, the information display is adjusted according to User A's emotional state, allowing him or her to make investment decisions in a more comfortable environment. Based on this, User A considers which stocks to invest in and actually makes the investment.

[1331] Continuous improvement of the investment experience

[1332] server:

[1333] The user's investment history and new feedback are sent to the server and the model is continually updated, which allows for even higher prediction accuracy in future investments and continuously improves the user's investment experience.

[1334] As an embodiment of the present invention, we have described a dividend forecasting and shareholder benefit analysis system that combines an emotion engine for beginners in stock investing. This system is designed to lower the barrier to investment and enable even beginners to easily make investment decisions.

[1335] The processing flow will be explained below.

[1336] Step 1:

[1337] The server retrieves past dividend data, financial information, market trend data, and shareholder benefits details from external APIs. Specifically, this includes historical information on dividends paid by companies in the past, financial information such as corporate revenue, liabilities, assets, and cash flow, and market activity data such as overall market price fluctuations and volume.

[1338] Step 2:

[1339] The server trains a generative AI model using the acquired historical dividend data and financial information. During this training process, the data is divided into training data and test data, and a machine learning algorithm such as a linear regression model is used to build a model. This model is used to predict a company's future dividends with high accuracy.

[1340] Step 3:

[1341] The server uses the trained generative AI model to predict future dividends based on new financial information. Specifically, it uses the latest market trend data and the company's financial situation as input data and uses the generative AI model to predict future dividend amounts.

[1342] Step 4:

[1343] The server analyzes the content of shareholder benefits. It analyzes the shareholder benefit data and scores it based on the preferences and conditions entered by the user (e.g., preferred benefit categories and expected minimum value). This allows it to extract attractive benefit information that matches the user's preferences.

[1344] Step 5:

[1345] The server uses an emotion engine to analyze the user's emotions based on the user's facial expressions, voice tone, input text, etc. The emotion engine recognizes the user's emotional state in real time and analyzes the results.

[1346] Step 6:

[1347] The server then personalizes the dividend forecast and shareholder benefit information based on the analyzed emotional data, adjusting the priority and format of the displayed information according to the user's emotional state.

[1348] Step 7:

[1349] The terminal displays the predicted dividend information and scored shareholder benefit information received from the server to the user. This information is provided in a visually easy-to-understand format, including predicted dividend amounts for each fiscal year and scored benefit details. The display is also adjusted to take into account the user's emotional state.

[1350] Step 8:

[1351] The user makes investment decisions based on the information provided by the terminal, and invests in the stocks that are most suitable for them, taking into account the predicted dividend amount and analyzed preferential treatment information.

[1352] Step 9:

[1353] The device sends feedback on the user's investment history and new preferences to the server, which then updates the model to further improve prediction accuracy in future rounds. This process continuously improves the user's investment experience.

[1354] As a result, a system has been realized that recognizes the user's emotions and provides personalized investment advice based on them, allowing even beginners to stock investment to easily make investment decisions.

[1355] Example 2

[1356] 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."

[1357] In stock investment, there is no system yet available that can meet the needs of users who want to make investment decisions that reflect their own emotional state. In particular, there is a demand for personalized information that takes into account the user's emotions when predicting dividends and analyzing shareholder benefits, but conventional technologies do not provide a concrete method for achieving this.

[1358] The specific processing by the specific 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 acquiring past distribution data, economic information, market trend data, and shareholder benefit information, means for predicting future dividends using a generative AI model trained on the past distribution data and economic information, means for analyzing the content of shareholder benefits and evaluating the analysis results based on the user's preferences, means for analyzing and recognizing the user's emotional state in real time, and means for adjusting the display of the predicted dividends and the analysis results based on the user's emotional state. This allows users to make investment decisions that reflect their own emotional state.

[1359] "Past distribution data" refers to historical data on the amount and dates of dividends paid by a company in the past.

[1360] "Economic information" refers to information that indicates financial data and economic indicators, including a company's revenue, liabilities, assets, cash flow, etc.

[1361] "Market trend data" refers to data that shows price fluctuations, trading volume, trends, etc. across the market.

[1362] "Shareholder benefit information" is information regarding the content and value of benefits that companies offer to shareholders.

[1363] A "generative AI model" is an artificial intelligence model trained using machine learning algorithms to make predictions or classifications based on input data.

[1364] A "regression model" is a model used in statistics and machine learning that represents the relationship between input variables and output variables and is used to predict future outputs.

[1365] "User preferences" refers to the user's individual tastes and desires, such as the categories and conditions that the user prefers.

[1366] An "emotional state" represents a user's current emotion (e.g., joy, sadness, surprise, etc.).

[1367] An "external API" is an application programming interface provided by an external system or service, and is a means for retrieving and manipulating data.

[1368] "Personalization" means providing information and services tailored to the individual needs and preferences of each user.

[1369] This invention is a system that supports decision-making in stock investment, particularly by taking into account the user's emotional state and providing personalized investment advice. The system acquires historical dividend data, corporate financial information, market trend data, and shareholder benefit information, and uses this data to train a generative AI model to predict future dividends. It also analyzes the content of shareholder benefits and evaluates them based on the user's preferences. Furthermore, it analyzes the user's emotional state in real time and uses that information to personalize investment advice.

[1370] Hardware and software used

[1371] server:

[1372] The server is primarily responsible for:

[1373] Data Acquisition: The server collects historical dividend data, company financial information, market trend data, and shareholder benefit information through external APIs. The hardware includes a high-performance CPU and large storage capacity, and the software uses a database (e.g., MySQL, PostgreSQL) and a REST API library (e.g., the Requests library).

[1374] Data storage: Collected data is stored in a database for smooth access.

[1375] Training a generative AI model: A machine learning library (e.g., scikit-learn) is used to train a generative AI model, such as a regression model, which may use a GPU to efficiently process large datasets.

[1376] Emotion analysis: Use emotion recognition APIs (e.g., Microsoft Azure's Face API, Google Cloud's Speech-to-Text API) to analyze the user's emotional state from their facial expressions, voice tone, and input text.

[1377] Device:

[1378] The terminal displays the information received from the server to the user:

[1379] Data display: The terminal uses a front-end framework (e.g., React, Vue.js) to display predicted dividend information and scored shareholder benefit information in a visually easy-to-understand format.

[1380] Emotional adjustment: The device personalizes the information displayed based on the user's emotional state, adjusting the device to receive the information in a more relaxed state.

[1381] User:

[1382] The user interacts with the system as follows:

[1383] Input of investment preferences: The user inputs their investment preferences and conditions into the terminal (e.g., "I like shareholder benefits in the food category, and I would like benefits worth at least 1,000 yen").

[1384] Provide feedback: Based on your investment results and experience, provide feedback to the system to help improve the model.

[1385] Specific examples

[1386] When a user uses this system to make an investment decision, they first enter their basic investment preferences. For example, User A might enter, "I like shareholder benefits in the food category, and I would like benefits worth at least 1,000 yen." The device then sends this information to the server. The server obtains the necessary data from an external API and trains a generative AI model to predict dividends and analyze shareholder benefits. At the same time, the emotion engine analyzes the user's emotional state in real time and personalizes the information display based on the obtained emotional data. The device displays predicted dividend information and shareholder benefit information scored based on User A's preferences, and the information display is adjusted according to User A's emotional state. User A then considers which stocks to invest in based on this information and makes the actual investment.

[1387] Prompt Sentence Examples

[1388] "Based on the dividend forecast and shareholder benefit analysis, please recommend the next stock I should buy. I like shareholder benefits in the food category and would like benefits worth at least 1,000 yen."

[1389] As described above, this system supports stock investment decision-making by providing accurate investment advice while taking into account the user's emotional state.

[1390] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1391] Step 1:

[1392] Data Acquisition

[1393] server:

[1394] Specifically, the server sends an HTTP GET request to an external API to retrieve historical distribution data, economic information, market trend data, and shareholder benefit information. The API endpoint URL and key are used as input. The output is JSON-formatted data. After retrieving this data, the server stores it in a database (e.g., MySQL), inserting the data into the appropriate table using the SQL INSERT statement.

[1395] Step 2:

[1396] Training a dividend prediction model

[1397] server:

[1398] The server extracts historical distribution data and economic information from the database. Specifically, it retrieves the data using a SELECT statement. The input is the database connection information and SQL query, and the output is a training dataset. Then, using a machine learning library (e.g., scikit-learn), it splits the dataset into training data and test data. This split is performed using the train_test_split function. Next, it trains a linear regression model using the fit method. The input is the training dataset, and the output is the trained model.

[1399] Step 3:

[1400] Dividend forecast

[1401] server:

[1402] New economic information is input into the model to predict future dividends. Specific operations use the predict method to obtain a predicted value. The input is a dataset of new economic information, and the output is the predicted dividend value. This prediction result is stored in a database.

[1403] Step 4:

[1404] Shareholder Benefit Analysis and Scoring

[1405] server:

[1406] It receives user preferences and conditions, analyzes shareholder benefit data, and performs evaluation. Specifically, it receives user input (e.g., preferred benefit category, expected minimum value) in JSON format and filters the shareholder benefit data using an SQL query. The input is the user preferences and shareholder benefit data, and the output is the score of the benefits based on the user conditions. It runs the scoring algorithm and calculates a score for each benefit.

[1407] Step 5:

[1408] Emotional state analysis

[1409] server:

[1410] The emotion recognition API is used to analyze the user's facial expression, voice tone, and input text. Specifically, an HTTP request is sent to the emotion recognition API to obtain the analysis results. The input is the user's facial expression image, voice data, and text data, and the output is the emotional state (e.g., joy, sadness, surprise). The analysis results are stored in a database and used for further processing.

[1411] Step 6:

[1412] Displaying Information

[1413] Device:

[1414] Predicted dividend information and scored shareholder benefit information are displayed to the user. Specifically, a front-end framework (e.g., React, Vue.js) is used to generate an interface that displays information in data table and graph format. The input is the dividend prediction and scoring results received from the server, and the output is a visually easy-to-understand display format. In addition, the display content is adjusted according to the user's emotional state based on the results of the emotion engine. For example, the display color and layout can be changed based on the emotional state.

[1415] Step 7:

[1416] Providing Feedback

[1417] User:

[1418] Feedback is sent to the system based on investment results and experience. Specifically, users enter information into a feedback form from their device and send it to the server. The input is the user's feedback, and the output is data that can be used to improve the system. The server stores this feedback in a database and uses it to update the model.

[1419] Through these steps, the system takes into account the user's emotional state, provides accurate investment advice, and supports stock investment decision-making.

[1420] (Application example 2)

[1421] 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."

[1422] Conventional stock investment support systems provide investment advice based on simple data analysis without considering the user's emotional state, resulting in a lack of psychological satisfaction and personalized recommendations. Therefore, there is a need for investment decision support that takes into account the user's emotional state. Furthermore, there is no adequate method for performing real-time emotional analysis and providing optimal investment information to users based on specific conditions.

[1423] 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.

[1424] In this invention, the server includes: means for acquiring past dividend data, financial information, market trend data, and shareholder benefit details; means for predicting future dividends using a generative AI model trained on the past dividend data and financial information; means for analyzing the details of shareholder benefits and scoring the analysis results based on the user's preferences; an emotion engine for recognizing and analyzing the user's emotional state; and means for displaying personalized information optimal for the user based on the emotional state. This makes it possible to provide personalized investment advice in real time according to the user's emotional state.

[1425] "Past dividend data" refers to historical information about dividends paid by a company.

[1426] "Financial information" is data that shows a company's financial status, such as revenue, liabilities, assets, and cash flow.

[1427] "Market trend data" is data that indicates market activity, such as price fluctuations and trading volume across the market.

[1428] "Shareholder benefits" refers to information about the perks and services that a company provides to its shareholders.

[1429] A "generative AI model" is an artificial intelligence model that is trained to predict future outputs based on input data.

[1430] An "emotion engine" is a system that recognizes emotions by analyzing a user's facial expressions, voice tone, input text, etc.

[1431] "Personalization" means optimizing information and services according to the preferences and emotional state of individual users.

[1432] "Scoring" is the process of assigning an evaluation or score based on certain criteria.

[1433] "Means for displaying information" refers to an interface that visually presents analysis results and predicted data to users.

[1434] An "external API" is an external application program interface for connecting with other services or databases.

[1435] This invention is a system that recognizes and analyzes user emotions in food delivery services and makes personalized meal recommendations based on that information. This system can be accessed by users through a smartphone application.

[1436] Data acquisition and analysis

[1437] The server uses an external API to retrieve the user's past order history and menu information. For example, the data retrieved from the API includes order details (price, rating, order frequency, etc.).

[1438] Emotion analysis

[1439] The emotion analysis module analyzes the user's real-time emotional state. It uses OpenCV for facial expression analysis and TextBlob for voice tone analysis. It also analyzes the input text to comprehensively evaluate the user's emotional state.

[1440] Recommendation Algorithm

[1441] The server trains a generative AI model based on the user's past order history and real-time emotional state to predict the optimal meal menu. The generative AI model uses a linear regression model and is trained based on past data.

[1442] Displaying personalized information

[1443] The device receives the recommendation results from the server and displays optimized menu information to the user, including menu names, prices, ratings, etc. Furthermore, the information display is adjusted taking into account the user's emotional state.

[1444] Specific examples

[1445] For example, when User B launches a food delivery app on his smartphone, he enters the following prompt:

[1446] text:

[1447] I'm feeling a bit tired today and want to relieve stress. What meals would you recommend?

[1448] The server analyzes this prompt, recognizes User B's current emotional state, and can then suggest relaxing, healthy meals or their favorite sweets, allowing the user to choose the optimal meal according to their emotions at the time.

[1449] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1450] Step 1:

[1451] The server uses an external API to retrieve the user's past order history and menu information. It uses the API endpoint and the user's ID as input, and obtains the order history data and menu information data as output. This data retrieval involves sending an HTTP request and receiving the data in JSON format.

[1452] Step 2:

[1453] The server preprocesses the acquired order history data. Specifically, it cleans the data, handles missing values, and selects features. It uses the acquired order history data as input and obtains clean training data as output. This preprocessing includes operations that perform data frame operations within the program.

[1454] Step 3:

[1455] The server uses an emotion analysis module to analyze the user's emotional state. It uses facial expression images, voice samples, and text inputs obtained from the user as inputs, and obtains the user's emotion score as output. Specifically, it analyzes facial expression images using OpenCV, and voice samples and text inputs using TextBlob.

[1456] Step 4:

[1457] The server uses a generative AI model to predict the optimal menu for a user based on the preprocessed order history data and real-time sentiment scores. It uses the preprocessed order history data and sentiment scores as input and obtains a list of recommended menu items as output. This prediction involves applying a Linear Regression model and obtaining the model's prediction results.

[1458] Step 5:

[1459] The terminal receives the recommendation results from the server and displays them to the user. It uses the list of recommended menus as input and obtains menu information visually displayed to the user as output. Specifically, it includes the operation of displaying information such as menu name, price, and rating to the user in list form.

[1460] Step 6:

[1461] The user selects and orders a meal from the recommended menu displayed on the device. The input is a menu selected from the list of recommended menus, and the output is a confirmation of the order. Specifically, this involves selecting and ordering a meal through button operations within the app.

[1462] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1463] 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.

[1464] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1465] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1466] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1467] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1468] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1469] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1470] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1471] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1472] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1473] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1474] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1475] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1476] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1477] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1478] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1479] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1480] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1481] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1482] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1483] The following is further disclosed regarding the above embodiment.

[1484] (Claim 1)

[1485] A means of obtaining past dividend data, financial information, market trend data and shareholder benefits details;

[1486] means for forecasting future dividends using a generative AI model trained on the historical dividend data and financial information;

[1487] A means for analyzing the content of shareholder benefits and scoring the analysis results based on user preferences;

[1488] a means for displaying the predicted dividend and the analysis result to a user;

[1489] A system including:

[1490] (Claim 2)

[1491] 2. The system according to claim 1, wherein the means for acquiring the past dividend data, financial information, market trend data, and shareholder benefits details collects the data from an external API.

[1492] (Claim 3)

[1493] 10. The system of claim 1, wherein the trained generative AI model comprises a linear regression model.

[1494] "Example 1"

[1495] (Claim 1)

[1496] A means of obtaining past dividend data, financial information, market trend data and shareholder benefits details;

[1497] means for forecasting future dividends using a generative AI model trained on the historical dividend data and financial information;

[1498] A means for analyzing the content of shareholder benefits and scoring the analysis results based on user preferences;

[1499] a means for displaying the predicted dividend and the analysis result to a user;

[1500] a means for collecting user preferences and minimum desired values;

[1501] A means of saving data obtained from external APIs to a database,

[1502] a means for splitting the data into training data and test data;

[1503] A system including:

[1504] (Claim 2)

[1505] 2. The system according to claim 1, wherein the means for acquiring the past dividend data, financial information, market trend data, and shareholder benefits details collects the data from an external API.

[1506] (Claim 3)

[1507] 10. The system of claim 1, wherein the trained generative AI model comprises a linear regression model.

[1508] "Application Example 1"

[1509] (Claim 1)

[1510] A means of obtaining past dividend data, financial information, market trend data and shareholder benefits details;

[1511] means for forecasting future dividends using a generative AI model trained on the historical dividend data and financial information;

[1512] A means for analyzing the content of shareholder benefits and scoring the analysis results based on user preferences;

[1513] a means for displaying the predicted dividend and the analysis result to a user;

[1514] a smartphone application means for visually providing dividend forecasts and shareholder benefit evaluation information based on a user profile;

[1515] A system including:

[1516] (Claim 2)

[1517] 2. The system according to claim 1, wherein the means for acquiring the past dividend data, financial information, market trend data, and shareholder benefits details collects the data from an external API.

[1518] (Claim 3)

[1519] 10. The system of claim 1, wherein the trained generative AI model comprises a linear regression model.

[1520] "Example 2: Combining Emotion Engines"

[1521] (Claim 1)

[1522] a means of obtaining historical distribution data, economic information, market trend data and shareholder benefit information;

[1523] means for predicting future distributions using a generative AI model trained based on the historical distribution data and economic information;

[1524] means for analyzing the content of shareholder benefits and evaluating the analysis results based on user preferences;

[1525] A means of analyzing and recognizing the user's emotional state in real time;

[1526] a means for adjusting the display of the predicted distribution amount and the analysis result based on the emotional state of the user;

[1527] A system including:

[1528] (Claim 2)

[1529] 2. The system of claim 1, wherein the means for obtaining the historical distribution data, economic information, market trend data, and shareholder benefit information collects the data from an external API.

[1530] (Claim 3)

[1531] 10. The system of claim 1, wherein the trained generative AI model comprises a regression model.

[1532] "Application example 2 when combining emotion engines"

[1533] (Claim 1)

[1534] A means of obtaining past dividend data, financial information, market trend data and shareholder benefits details;

[1535] means for forecasting future dividends using a generative AI model trained on the historical dividend data and financial information;

[1536] A means for analyzing the content of shareholder benefits and scoring the analysis results based on user preferences;

[1537] An emotion engine that recognizes and analyzes the user's emotional state;

[1538] means for personalizing and displaying optimal information to the user based on the emotional state;

[1539] A system including:

[1540] (Claim 2)

[1541] 2. The system according to claim 1, wherein the means for acquiring the past dividend data, financial information, market trend data, and shareholder benefits details collects the data from an external API.

[1542] (Claim 3)

[1543] 10. The system of claim 1, wherein the trained generative AI model comprises a linear regression model. [Explanation of symbols]

[1544] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of obtaining past dividend data, financial information, market trend data and shareholder benefits details; means for forecasting future dividends using a generative AI model trained on the historical dividend data and financial information; A means for analyzing the content of shareholder benefits and scoring the analysis results based on user preferences; a means for displaying the predicted dividend and the analysis result to a user; A system including:

2. 2. The system according to claim 1, wherein the means for acquiring the past dividend data, financial information, market trend data, and shareholder benefits details collects the data from an external API.

3. The system of claim 1 , wherein the trained generative AI model comprises a linear regression model.

Images