system

Abstract

We provide the system. [Solution] A terminal means for data entry, A server means for integrating and converting data in various formats received via the terminal means, A server means for cleaning the data integrated and converted by the aforementioned server means, A server means for performing feature engineering on the cleaned data, A server means that performs training and prediction of a predictive model based on the data obtained by the aforementioned feature engineering, A terminal means for visually displaying the aforementioned prediction results, A system that includes this.

Description

【Technical Field】 【0001】 The technology of the present disclosure relates to a system. 【Background Art】 【0002】 Patent Document 1 discloses a persona chatbot control method performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a 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 Application Laid-Open No. 2022-180282 【Summary of the Invention】 【Problems to be Solved by the Invention】 【0004】 Conventional financial data analysis systems have difficulty efficiently integrating various forms of data and providing advanced predictions and insights in real time. As a result, there are problems such as requiring a lot of time for financial data analysis and being unable to make appropriate decisions due to a shortage of human resources and resources. Furthermore, non-financial data cannot be effectively utilized to obtain new insights and contribute to improving the competitiveness of enterprises. 7]【Means for Solving the Problems】 【0005】 The present invention comprises a terminal means for data input, a server means for integrating and converting various formats of data received through the terminal means, and a server means for cleaning the integrated and converted data. In addition, it has a server means for performing feature engineering on the cleaned data and a server means for training and predicting a prediction model, thereby providing a terminal means that visually displays the prediction results obtained from the integrated financial and non-financial data, and thereby solves the above problem. 【0006】 "Data entry" is the process of supplying financial and non-financial data to a system via terminal devices. 【0007】 A "terminal device" is an interface device used by a user to input data into a system and receive the results. 【0008】 "Server means" refers to a computing device or its functions that perform data integration, transformation, cleaning, analysis, and prediction. 【0009】 "Integration" is the process of combining data obtained from different formats and sources into a single, consistent dataset. 【0010】 "Conversion" is the process of changing data from one format to another. 【0011】 "Cleaning" is the process of removing redundant information and missing values ​​from a dataset to improve its quality. 【0012】 Feature engineering is the process of creating new variables and metrics from data to improve the performance of machine learning models. 【0013】 A "predictive model" is a mathematical or statistical model used to predict future trends based on past and present data. 【0014】 "Prediction" is a process of estimating future events and performance using a trained model. 【0015】 "Non-financial data" refers to information other than financial data and indicates a dataset that may affect the business environment. 【0016】 "Visually display" means presenting the analysis results of data in a visually intuitive and understandable form using graphs, charts, etc. 【Brief Explanation of Drawings】 【0017】 [Figure 1] It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which multiple emotions are mapped. [Figure 10] It shows an emotion map to which multiple emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12]It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Embodiment 2 when combined with an emotion engine. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when combined with an emotion engine. 【Mode for Carrying Out the Invention】 【0018】 Hereinafter, an example of an embodiment of the system according to the technology of the present disclosure will be described with reference to the accompanying drawings. 【0019】 First, the language used in the following description will be explained. 【0020】 In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), APU (Accelerated Processing Unit), etc. 【0021】 In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor. 【0022】 In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes. 【0023】 In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark). 【0024】 In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or." 【0025】 [First Embodiment] 【0026】 Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment. 【0027】 As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server. 【0028】 The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network). 【0029】 The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52. 【0030】 The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input. 【0031】 The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor. 【0032】 Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54. 【0033】 Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14. 【0034】 As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30. 【0035】 The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. 【0036】 In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48. 【0037】 Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal". 【0038】 This invention is a system that integrates financial and non-financial data to provide advanced analysis and forecasting in real time. The entire system consists of terminal means for data input, server means for data processing and analysis, and terminal means that provide visualization functions for presenting analysis results to the user. 【0039】 First, the user inputs financial data and related non-financial data using a terminal device. The data format can be diverse, including CSV, PDF documents, and even audio and image data, but the terminal device provides an interface that accepts these various data formats. 【0040】 The server analyzes the data received through terminal devices and integrates it through appropriate processes. For example, it extracts text data from PDF documents using OCR, while transcribing audio data using speech recognition technology. Finally, all data is converted into a unified format and integrated into a single dataset. 【0041】 Next, the server performs data cleansing, removing or supplementing inappropriate or missing data. This improves data consistency and reliability, forming the foundation for highly accurate analysis. 【0042】 Furthermore, the server performs feature engineering to create new features suitable for training the machine learning model. This feature engineering shapes the data into a more useful form for the model, improving prediction accuracy. 【0043】 The server then uses the built predictive model to perform future financial forecasts. This makes it possible to predict a company's future sales and spending trends and provide insights for strategic decision-making. 【0044】 Ultimately, the terminal device visually displays the analysis results sent from the server, allowing the user to understand them intuitively. Using graphs and charts, users can grasp the information more quickly and accurately, and request further detailed analysis as needed. 【0045】 For example, if a user inputs the latest quarterly sales data along with data from related news articles, the server will use this information to calculate sales forecasts for the next quarter and analyze their impact on the market. The terminal will then visualize these results, allowing the user to smoothly engage in discussions to develop future business strategies. 【0046】 Thus, the system provided by this invention will be a powerful tool for efficiently and effectively utilizing data and creating new business opportunities in a digitized society. 【0047】 The following describes the processing flow. 【0048】 Step 1: 【0049】 Users upload various data formats (e.g., CSV files, PDF documents, audio data) to the server via a terminal. The terminal provides a user interface, allowing users to easily select and send data. 【0050】 Step 2: 【0051】 The server begins analyzing each piece of data it receives. For PDF documents, it uses OCR technology to extract text, and for audio data, it uses speech recognition technology to convert it into text information. 【0052】 Step 3: 【0053】 The server converts data in different formats into a unified format and integrates it into a consistent dataset. It automatically applies the necessary conversion process depending on the data type. 【0054】 Step 4: 【0055】 The server cleans the integrated data. Specifically, it removes duplicate data, imputes missing values, and detects outliers, handling them appropriately. 【0056】 Step 5: 【0057】 The server performs feature engineering on the cleaned data. This extracts new features and optimizes the dataset for use by machine learning models for training. 【0058】 Step 6: 【0059】 The server uses existing data to train a predictive model, which provides the foundation for predicting future trends. 【0060】 Step 7: 【0061】 The server uses a pre-trained model to make future predictions about the input data. These predictions might include, for example, sales or market trends for the next quarter. 【0062】 Step 8: 【0063】 The device visualizes the prediction results on a dashboard to provide them to the user. Using graphs and charts makes it easier for users to intuitively understand the analysis results. 【0064】 Step 9: 【0065】 Users can conduct further analysis and ask questions based on the presented results, and, if necessary, request additional analysis from the system based on their feedback. The server will then process the new data as appropriate in response to this feedback. 【0066】 (Example 1) 【0067】 Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal." 【0068】 In business, there is a need to efficiently analyze and integrate financial and non-financial information in different formats to make reliable forecasts. However, the diversity of data formats and the incompleteness of the information pose challenges, making it difficult to convert this information into a consistent format for use in forecasting. Furthermore, it is not easy for users to intuitively understand the analysis results obtained and translate them into concrete decision-making. 【0069】 The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means. 【0070】 In this invention, the server includes a communication device, a processing device, and a processing device for characteristic extraction. This allows for the conversion of diverse forms of information into a unified format, enabling consistent analysis and highly reliable predictions. Furthermore, users can intuitively grasp the prediction results and make quick decisions. 【0071】 "Communication device means" refers to a device that provides an interface for receiving input information from a user and transmitting it to a server. 【0072】 A "processing device" is a device that has the function of analyzing received information, standardizing data in different formats, and integrating it. 【0073】 "Feature extraction" is the process of generating appropriate features from integrated data to serve as input for a machine learning model. 【0074】 A "learning model" is an analytical method that provides algorithms for predicting future events based on past data. 【0075】 A "prediction module" is a software component that uses data obtained through characteristic extraction to predict future outcomes. 【0076】 "Analysis" is the process of investigating and examining the content of data and transforming it into meaningful information. 【0077】 "Visualization" is a technique that displays analysis results in the form of graphs, diagrams, and other visual representations, making them easier for users to understand visually. 【0078】 This invention is a data analysis system that effectively processes different types of information and enables advanced prediction. The system mainly consists of communication devices, processing devices, and characteristic extraction processing devices. 【0079】 First, users can input financial and non-financial information using a communication device. The communication device has an interface that accepts various information formats, including CSV files, PDF documents, audio files, and image files. This interface is designed to allow users to upload data smoothly. 【0080】 Next, the server analyzes the information received through the communication device. The processing unit extracts text data from PDF documents using OCR (optical character recognition) technology and transcribes audio files using speech recognition technology. The server then converts this diverse information into a unified format to create a single integrated dataset. 【0081】 Next, the server performs feature extraction based on the integrated dataset. This process derives meaningful features for the generative AI model. As a result, the data is formatted in a way that is useful for the prediction module, improving the accuracy of predictions. 【0082】 Ultimately, the prediction results generated by the server are visualized for the user via a communication device. This allows the user to intuitively understand the analysis results and utilize them in strategic business decision-making. 【0083】 As a concrete example, if a user inputs the latest quarterly sales data and related news article information, the server will use this information to predict sales for the next quarter. It will also analyze the market impact based on this prediction and visualize the results. An example prompt would be a request such as, "Input the latest quarterly sales data and related news to create a sales forecast for the next quarter." This allows the user to obtain the information necessary for future business strategies. 【0084】 The flow of the specific processing in Example 1 will be explained using Figure 11. 【0085】 Step 1: 【0086】 Users input financial and non-financial information using a communication device. The input data is diverse, including CSV files, PDF documents, audio files, and image files. The communication device provides an interface to accept these different information formats, enabling efficient data collection. The output is the initial data received by the server in the format required for analysis. 【0087】 Step 2: 【0088】 The server analyzes data in various formats received through the communication device. For example, it extracts text data from PDF documents using OCR technology and transcribes audio files using speech recognition technology. At this stage, the input is data in various formats, and the output is data in a unified text format. 【0089】 Step 3: 【0090】 The server organizes the data into a unified format and creates a unified dataset. Here, data cleansing is performed to remove inaccurate information and impute missing values ​​as needed. The input is the unified data from step 2, and the output is a cleaned and reliable dataset. 【0091】 Step 4: 【0092】 The server performs feature extraction and generates meaningful features for the learning model. It derives new features based on historical data to improve prediction accuracy. The input is the dataset obtained in step 3, and the output is feature-rich data. 【0093】 Step 5: 【0094】 The server makes predictions using a generative AI model. It uses the trained learning model to predict future sales, market trends, and other factors. The input here is the feature data generated in step 4, and the output is numerical values ​​and indicators representing the prediction results. 【0095】 Step 6: 【0096】 The terminal displays the prediction results sent from the server to the user in a visualized format. Graphs and charts allow users to easily interpret the results and apply them to their actual work. The input is predicted numerical data, and the output is a visually represented analysis. 【0097】 (Application Example 1) 【0098】 Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal." 【0099】 In today's economic environment, individuals and organizations need to organize, integrate, and forecast complex and diverse forms of financial information. Traditional systems require enormous time and effort to process, integrate, and forecast data from different formats, and often do not guarantee forecast accuracy. Furthermore, users seek comprehensive insights that take into account everyday economic activities and external factors, but there is a lack of tools to achieve this. Therefore, there is a need for new systems that can efficiently integrate data and provide reliable forecasts and recommendations in real time. 【0100】 The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means. 【0101】 In this invention, the server includes an information processing device for inputting data, a data processing device for integrating and converting various forms of information received via the information processing device, and a data processing device for purifying the information integrated and converted by the data processing device. This enables efficient integration and analysis of different forms of data, making it possible to propose highly accurate future predictions and economic plans. 【0102】 An "information processing device" is a device that receives data input from a user, processes the received information, and displays it. 【0103】 A "data processing device" is a device that has the function of integrating information received in various formats, and generating data suitable for predictive models by performing transformations and analyses. 【0104】 "Data integration" is the process of combining information obtained from different formats or sources into a single, consistent format. 【0105】 "Cleanup" is the process of removing or supplementing incomplete information or noise within data, and is performed to improve data quality. 【0106】 Feature analysis is the process of extracting useful features from data, and it is necessary to improve the performance of machine learning models. 【0107】 A "predictive model" is a mathematical or machine learning model used to predict future trends based on past data. 【0108】 "Future prediction" is the act of predicting future situations and trends based on current and past data. 【0109】 "Proposing economic plans" is a process that suggests strategies and actions that individuals and organizations should take based on forecast results. 【0110】 This application example aims to create a system that integrates personal financial and non-financial data to predict and propose future economic activities. This system primarily consists of information processing and data processing units, and processes data in multiple steps. 【0111】 First, the terminal receives user input. The information processing device uses a smartphone or other computing device to collect the user's transaction information and daily spending information, and inputs the data. Because this information is in various formats, open-source OCR (Optical Character Recognition) software is used to convert PDFs and audio information into text. 【0112】 Next, the server receives the information, and the data processing unit performs integration and cleansing. At this stage, data analysis libraries in Python or R (e.g., Pandas, NumPy) are used to integrate information from different formats, impute missing values, and remove noise. This improves the consistency and quality of the data. 【0113】 Subsequently, the data processing unit performs feature analysis. Using machine learning libraries such as scikit-learn and TENSORFLOW®, it analyzes user patterns and extracts the characteristics necessary for training the prediction model. Through this feature analysis, the information is organized into a form most suitable for prediction. 【0114】 Finally, the server uses a generative AI model to predict future trends and displays the results visually on the device. Users receive the visually transformed results and suggestions through a smartphone application. This allows users to create effective economic plans. 【0115】 As a concrete example, suppose a user enters the question, "If I spent a lot on entertainment this month, how will that affect my spending next month?" In response to this request, the device displays a prediction along with advice. 【0116】 Example of a prompt 【0117】 "Based on spending data from the past three months, please provide a forecast of the overall cash flow, taking into account next month's entertainment expenses." 【0118】 The flow of a specific process in Application Example 1 will be explained using Figure 12. 【0119】 Step 1: 【0120】 The terminal accepts user input. This is the process where the user enters expense and income information using an application on a smartphone. The input data is in the form of a CSV file, a photo receipt, or an audio memo. These different data formats are converted into text data using OCR or speech recognition technology. The output is standardized text-formatted economic data. 【0121】 Step 2: 【0122】 The server receives the information, and the data processing unit integrates and cleans the data. The server receives the input text data, removes duplicate data, standardizes the format, and infers and imputes missing data. At this stage, the Python Pandas library is used to generate a dataframe and create a consistent dataset. The output is a high-quality dataset in a unified format. 【0123】 Step 3: 【0124】 The data processing unit performs feature analysis. The server analyzes the unified dataset using the scikit-learn library and extracts features suitable for training a machine learning model. At this stage, information such as expenditure categories and monthly totals are generated as new features. The output is an analyzable dataset with added features. 【0125】 Step 4: 【0126】 The server uses a generated AI model to predict future trends. Based on the analyzed features, it uses existing predictive models (e.g., linear regression models or deep learning models) to predict future economic activity and fluctuations in revenue and expenditure. The output is a report containing specific prediction results. 【0127】 Step 5: 【0128】 The server sends the prediction results to the terminal, which then visualizes them. The user receives the prediction results and proposed economic plans based on them as graphs and charts through a smartphone application. The output is visualized information that is easy for the user to understand. 【0129】 Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions. 【0130】 This invention is a system that recognizes user emotions and optimizes data analysis and result presentation based on those emotions. The system consists of terminal means for data input, server means for data processing and analysis, emotion engine for emotion recognition, and terminal means that provide visualization functions for presenting analysis results to the user. 【0131】 First, the user inputs financial data and related non-financial data using a terminal device. This data can be in various formats such as CSV, PDF, and audio data, and the terminal device accepts it appropriately. 【0132】 The server analyzes the received data and, if necessary, applies OCR or speech recognition technology to standardize the data format. The integrated data is then cleaned by the server to ensure data consistency. This process includes imputation of missing values ​​and handling of outliers. 【0133】 Next, the server performs feature engineering to create a dataset suitable for training the predictive model. This step makes the data more useful for the machine learning model. 【0134】 Furthermore, the emotion engine recognizes the user's emotions from their facial expressions and voice, and generates analysis results in a format appropriate to the user's emotions. For example, if the user is feeling anxious, a report will be generated that emphasizes detailed information and explanations of risks. 【0135】 Using a pre-trained model, the server performs future financial forecasts. These forecasts include, for example, quarterly sales forecasts and market trend analyses. 【0136】 Ultimately, the terminal displays the results sent from the server on an interactive dashboard. Here, the user visualizes the results in an emotionally-driven, customized way, allowing them to understand the data more intuitively. 【0137】 For example, if a user inputs data to forecast sales of a new product, and the emotion engine simultaneously detects the user's stress level, the system will explain the credibility of the original data in a clean interface and highlight reassuring information. 【0138】 Thus, the system of the present invention takes user emotions into consideration, thereby providing a more fulfilling user experience and more effectively supporting decision-making. 【0139】 The following describes the processing flow. 【0140】 Step 1: 【0141】 Users input financial data and related non-financial data into the system via a terminal. The terminal provides an interface for transmitting data in various formats selected by the user. 【0142】 Step 2: 【0143】 The server receives the input data and performs initial analysis to standardize the format. It extracts text data from PDF files using OCR technology and converts speech data into text using speech recognition technology. 【0144】 Step 3: 【0145】 The server integrates the data and performs data cleaning to remove or correct redundant information. This process includes imputing missing values ​​and removing outliers. 【0146】 Step 4: 【0147】 The server applies feature engineering to the cleaned data to generate data suitable for machine learning models. This extracts useful features to maximize the model's performance. 【0148】 Step 5: 【0149】 The server activates an emotion engine to recognize the user's emotions in real time. It analyzes facial expressions and voices obtained from the user to evaluate the user's emotional state. 【0150】 Step 6: 【0151】 The server considers the acquired sentiment data and uses a predictive model to perform financial forecasts tailored to the user's emotional state. It then determines the optimal output format based on the sentiment data. 【0152】 Step 7: 【0153】 The device visualizes the analysis results on a dashboard to provide users with predictions. The format and explanations are automatically adjusted according to the user's emotions. 【0154】 Step 8: 【0155】 Users can review the displayed results and request additional questions or analysis as needed. The server receives user feedback and responds flexibly while referring to sentiment data. 【0156】 (Example 2) 【0157】 Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal." 【0158】 Traditional data analysis systems failed to consider user sentiment throughout the entire process, from data input to predictive model generation, making it difficult to provide optimal results for a deeper understanding of the user. Furthermore, insufficient data preparation during the integration and analysis of diverse data formats hindered the construction of precise predictive models and the generation of useful insights. Additionally, there was a lack of flexible means to respond to user inquiries and concerns. 【0159】 The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. 【0160】 In this invention, the server includes information processing means for analyzing emotions and generating analysis results based on those emotions; information processing means for analyzing non-financial information and integrating it with financial information to generate insights; and information processing means for providing additional analysis or advice in response to questions from the user. This enables the presentation of appropriate results that take into account the user's emotions, allowing the user to easily understand the data and make decisions with confidence. 【0161】 "Data input devices" are devices used by users to input financial and non-financial data, and are capable of appropriately accepting information in various formats. 【0162】 An "information processing device" is a device that possesses the technology to integrate, convert, organize, analyze, and train predictive models based on various forms of input information. 【0163】 Feature extraction is the process of selecting useful features from data to create a dataset that can be used to train a predictive model. 【0164】 An "information processing device that analyzes emotions" is a device that analyzes emotions based on the user's facial expressions and voice, and generates analysis results based on those emotions. 【0165】 A "visually displaying information device" is a device that presents prediction results transmitted from a server to the user in an easy-to-understand manner on a screen such as a dashboard. 【0166】 "Non-financial information" refers to supplementary information related to business and economics other than financial data, such as market trends and customer feedback. 【0167】 An "information processing device that provides additional analysis or advice" is a device that can provide further data analysis or specific advice in response to additional questions from the user. 【0168】 This invention is a data analysis system that takes user emotions into consideration, and its implementation utilizes an information input device, an information processing device, and a visualization device. 【0169】 Users input data in various formats using information input devices. These devices accept data in the form of CSV files, PDF documents, audio data, and other formats. The input data is then received by an information processing device, where OCR (optical character recognition) and speech recognition technologies are applied to convert it into text data. 【0170】 The server, which is an information processing device, integrates the received data and performs maintenance to maintain data consistency. This maintenance process includes filling in missing data and handling outliers. Furthermore, feature extraction techniques are used to extract significant features from the data and generate datasets for training predictive models. 【0171】 Furthermore, a device with emotion analysis capabilities analyzes the user's emotional state. For example, if the user is feeling anxious, this device detects this and generates a report that highlights and displays information related to risks. This result is input into the server's generated AI model, which precisely predicts future financial conditions. Next, the prediction results generated by the information processing device are displayed on an interactive dashboard, a visualization device. This dashboard allows the user to intuitively understand the flow of data and the results. 【0172】 For example, if a user wants to predict sales of a new product, they input the necessary data, and an emotion analysis device analyzes the user's emotional state at that time. Based on this information, the server checks the quality of the raw data and generates a report that emphasizes information to provide reassurance. 【0173】 An example of a prompt message would be, "Analyze the sales data and sentiment data entered by the user, and generate a report that includes reassuring risk information." In this way, the system of the present invention can enhance the user experience and more effectively support the decision-making process. 【0174】 The flow of the specific processing in Example 2 will be explained using Figure 13. 【0175】 Step 1: 【0176】 Users input data in various formats using input devices. These formats include CSV files, PDF documents, and audio data. The input device verifies the format of the entered data before accepting it. Once the user provides the data, the program prepares to send it to the next stage. 【0177】 Step 2: 【0178】 The server receives data transmitted from the information input device. The server uses OCR technology to extract text data from the PDF and speech recognition technology to convert speech data into text. Through these processes, the data format is standardized, and integrated data is generated for the next step. The output is the initial data integrated into text format. 【0179】 Step 3: 【0180】 The server organizes the integrated data. It performs data cleaning to maintain data consistency, including imputing missing data and removing outliers. For example, missing numerical data is imputed with the median, and extreme outliers are corrected to an appropriate range. This organized data is then sent to the next step. The output is a consistent dataset with cleaning completed. 【0181】 Step 4: 【0182】 The server uses feature extraction techniques to select useful features from the prepared data. Feature engineering is performed to create a dataset that is optimally suited as input for the predictive model. This process involves selecting highly relevant variables and generating new features, thereby improving the data's predictive accuracy. The output is a feature dataset optimized for training. 【0183】 Step 5: 【0184】 The server uses emotion analysis capabilities to determine the user's emotions from their facial expressions and voice. For example, if the user is feeling anxious, this information is used in the analysis, and the resulting report is generated with risk information emphasized. Subsequently, the analysis results corresponding to that emotion are used as input to a generating AI model, which then generates output appropriate to the user's emotions. 【0185】 Step 6: 【0186】 Ultimately, the server uses a trained generative AI model to make future financial forecasts. The forecasted data, including sales forecasts and market trend analysis for the next quarter, is generated by the information processing unit. This forecast result, created by the server, is sent to the information processing unit's dashboard. The output is presented as a detailed report containing the forecast results. 【0187】 Step 7: 【0188】 The device displays prediction results received from the server on an interactive dashboard. Through this dashboard, users can view emotionally tailored, customized visuals. This allows users to intuitively grasp the data and gain the insights necessary for decision-making. The dashboard output is a visually tuned display of information. 【0189】 (Application Example 2) 【0190】 Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal". 【0191】 The problem that this invention aims to solve lies in the limitations of existing systems that present data analysis results without taking into account the user's emotional state. In particular, when flexible responses that respond to the user's emotions and feelings are required, data visualization and advice presentation should be optimized for the user, rather than being a uniform method. Therefore, there is a need for a method that recognizes emotions and enables the presentation of data analysis results and advice in a way that takes these emotions into account. 【0192】 The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. 【0193】 In this invention, the server includes a device means for inputting data, a computing means for integrating and converting various forms of information received through the device means, and an emotion engine means for recognizing emotions and generating analysis results appropriate to the user's mood. This enables the visualization of customized data and the presentation of optimized advice according to the user's emotional state. 【0194】 "Data input device means" refers to a device for users to input information in various formats. 【0195】 "Information in various formats" refers to information in different formats such as CSV, PDF, and audio data. 【0196】 A "computational means for integrating and transforming" is a computing device for organizing information in various formats into a consistent format. 【0197】 A "cleaning computational means" is a computing device that removes noise and loss from integrated and transformed information to produce high-quality data. 【0198】 "Feature engineering" is a technique for extracting and structuring useful features from data for analysis and prediction. 【0199】 A "computational means for training and predicting predictive models" is a computing device that uses data obtained through feature engineering to predict future trends and results. 【0200】 "Visual display device means" refers to a device that visualizes and presents prediction results and analysis results obtained by calculation means to the user. 【0201】 An "emotion engine that recognizes emotions and generates analysis results appropriate to the user's feelings" is an engine that identifies emotions from the user's facial expressions, voice, etc., and generates results in an appropriate format according to those emotions. 【0202】 This invention is a system that optimizes data analysis results based on user emotions and presents them in an intuitively understandable format. This system consists of multiple components and primarily processes data through the following steps. 【0203】 First, the user provides information in various formats through a data entry device. This information can be in different formats such as CSV, PDF, or audio data, and the device is designed to accept these formats appropriately. Next, the server integrates and transforms this information and performs cleaning to maintain data consistency. In this step, computational software such as Python and pandas is used. 【0204】 Once the data is cleaned, the server performs feature engineering to build a dataset suitable for training a predictive model. This is where scikit-learn is used. This process prepares the data into a useful format. 【0205】 Furthermore, the emotion engine analyzes the user's facial expressions and voice to recognize their emotions. Emotion analysis software such as OpenFace is used for this emotion recognition. If the user is feeling anxious, the system displays data visualizations to provide reassurance. 【0206】 Finally, the server uses a trained generative AI model to visualize future predictions in an interactive format. The results are displayed using Plotly as a visualization tool, which users can view on their devices. 【0207】 As a concrete example, if a male user in his 40s operates the system after a long day of desk work, the emotion engine might detect an increased stress level. As a result, the robot might recommend "doing some light stretching" and display a stretching video. Another example of a prompt would be, "If a user is feeling stressed after a morning of desk work, what should you suggest?" 【0208】 The flow of a specific process in Application Example 2 will be explained using Figure 14. 【0209】 Step 1: 【0210】 The terminal receives data provided by the user. This input data includes various formats such as CSV, PDF, and audio data, which the terminal receives. Based on the data input, the system prepares a dataset for the next processing step. 【0211】 Step 2: 【0212】 The server integrates and transforms the data received from the terminals. Specifically, it uses OCR and speech recognition technologies to standardize and maintain consistency in the data format. The output is data in an integrated, standardized format. 【0213】 Step 3: 【0214】 The server cleans the integrated data. Specifically, it improves data quality by imputing missing values ​​and detecting and correcting outliers. This generates a clean, high-quality dataset. 【0215】 Step 4: 【0216】 The server performs feature engineering on the cleaned data. Here, it extracts useful features for machine learning and creates a new dataset. The output is data suitable for training a predictive model. 【0217】 Step 5: 【0218】 The server uses an emotion engine to recognize the user's emotions. It determines the emotional state through analysis of the user's facial expressions and voice, and uses that data for subsequent processing. 【0219】 Step 6: 【0220】 The server trains and predicts using a predictive model based on data obtained through feature engineering. Using a generative AI model, future predictions and recommendations are output. 【0221】 Step 7: 【0222】 The device visually displays the prediction results sent from the server. Users can review the results through an interactive dashboard optimized for their emotions. 【0223】 These processing steps enable data analysis and presentation of results that take user emotions into account. 【0224】 The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data. 【0225】 Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. 【0226】 In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14. 【0227】 [Second Embodiment] 【0228】 Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment. 【0229】 As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server. 【0230】 The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network). 【0231】 The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52. 【0232】 The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46. 【0233】 Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision). 【0234】 Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner. 【0235】 Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56. 【0236】 The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30. 【0237】 The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. 【0238】 In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48. 【0239】 Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal". 【0240】 This invention is a system that integrates financial and non-financial data to provide advanced analysis and forecasting in real time. The entire system consists of terminal means for data input, server means for data processing and analysis, and terminal means that provide visualization functions for presenting analysis results to the user. 【0241】 First, the user inputs financial data and related non-financial data using a terminal device. The data format can be diverse, including CSV, PDF documents, and even audio and image data, but the terminal device provides an interface that accepts these various data formats. 【0242】 The server analyzes the data received through terminal devices and integrates it through appropriate processes. For example, it extracts text data from PDF documents using OCR, while transcribing audio data using speech recognition technology. Finally, all data is converted into a unified format and integrated into a single dataset. 【0243】 Next, the server performs data cleansing, removing or supplementing inappropriate or missing data. This improves data consistency and reliability, forming the foundation for highly accurate analysis. 【0244】 Furthermore, the server performs feature engineering to create new features suitable for training the machine learning model. This feature engineering shapes the data into a more useful form for the model, improving prediction accuracy. 【0245】 The server then uses the built predictive model to perform future financial forecasts. This makes it possible to predict a company's future sales and spending trends and provide insights for strategic decision-making. 【0246】 Ultimately, the terminal device visually displays the analysis results sent from the server, allowing the user to understand them intuitively. Using graphs and charts, users can grasp the information more quickly and accurately, and request further detailed analysis as needed. 【0247】 For example, if a user inputs the latest quarterly sales data along with data from related news articles, the server will use this information to calculate sales forecasts for the next quarter and analyze their impact on the market. The terminal will then visualize these results, allowing the user to smoothly engage in discussions to develop future business strategies. 【0248】 Thus, the system provided by this invention will be a powerful tool for efficiently and effectively utilizing data and creating new business opportunities in a digitized society. 【0249】 The following describes the processing flow. 【0250】 Step 1: 【0251】 Users upload various data formats (e.g., CSV files, PDF documents, audio data) to the server via a terminal. The terminal provides a user interface, allowing users to easily select and send data. 【0252】 Step 2: 【0253】 The server begins analyzing each piece of data it receives. For PDF documents, it uses OCR technology to extract text, and for audio data, it uses speech recognition technology to convert it into text information. 【0254】 Step 3: 【0255】 The server converts data in different formats into a unified format and integrates it into a consistent dataset. It automatically applies the necessary conversion process depending on the data type. 【0256】 Step 4: 【0257】 The server cleans the integrated data. Specifically, it removes duplicate data, imputes missing values, and detects outliers, handling them appropriately. 【0258】 Step 5: 【0259】 The server performs feature engineering on the cleaned data. This extracts new features and optimizes the dataset for use by machine learning models for training. 【0260】 Step 6: 【0261】 The server uses existing data to train a predictive model, which provides the foundation for predicting future trends. 【0262】 Step 7: 【0263】 The server uses a pre-trained model to make future predictions about the input data. These predictions might include, for example, sales or market trends for the next quarter. 【0264】 Step 8: 【0265】 The device visualizes the prediction results on a dashboard to provide them to the user. Using graphs and charts makes it easier for users to intuitively understand the analysis results. 【0266】 Step 9: 【0267】 Users can conduct further analysis and ask questions based on the presented results, and, if necessary, request additional analysis from the system based on their feedback. The server will then process the new data as appropriate in response to this feedback. 【0268】 (Example 1) 【0269】 Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal." 【0270】 In business, there is a need to efficiently analyze and integrate financial and non-financial information in different formats to make reliable forecasts. However, the diversity of data formats and the incompleteness of the information pose challenges, making it difficult to convert this information into a consistent format for use in forecasting. Furthermore, it is not easy for users to intuitively understand the analysis results obtained and translate them into concrete decision-making. 【0271】 The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means. 【0272】 In this invention, the server includes a communication device, a processing device, and a processing device for characteristic extraction. This allows for the conversion of diverse forms of information into a unified format, enabling consistent analysis and highly reliable predictions. Furthermore, users can intuitively grasp the prediction results and make quick decisions. 【0273】 "Communication device means" refers to a device that provides an interface for receiving input information from a user and transmitting it to a server. 【0274】 A "processing device" is a device that has the function of analyzing received information, standardizing data in different formats, and integrating it. 【0275】 "Feature extraction" is the process of generating appropriate features from integrated data to serve as input for a machine learning model. 【0276】 A "learning model" is an analytical method that provides algorithms for predicting future events based on past data. 【0277】 A "prediction module" is a software component that uses data obtained through characteristic extraction to predict future outcomes. 【0278】 "Analysis" is the process of investigating and examining the content of data and transforming it into meaningful information. 【0279】 "Visualization" is a technique that displays analysis results in the form of graphs, diagrams, and other visual representations, making them easier for users to understand visually. 【0280】 This invention is a data analysis system that effectively processes different types of information and enables advanced prediction. The system mainly consists of communication devices, processing devices, and characteristic extraction processing devices. 【0281】 First, the user can use the communication device to input financial information and non-financial information. The communication device has an interface that can receive information in various formats, such as CSV files, PDF documents, audio files, and image files. This interface is designed to allow the user to upload data smoothly. 【0282】 Next, the server analyzes the information received through the communication device. The processing device extracts text data from a PDF document using OCR (Optical Character Recognition) technology and performs speech recognition on the audio file to convert speech to text. Then, the server converts these different types of information into a unified format and creates a single integrated dataset. 【0283】 Subsequently, the server performs feature extraction based on the integrated dataset. In this process, meaningful features for generating an AI model are derived. As a result, the data is organized into a form beneficial for the prediction module, improving the prediction accuracy. 【0284】 Finally, the prediction results generated by the server are visualized by the communication device for the user. This enables the user to intuitively understand the analysis results and utilize them for strategic business decision-making. 【0285】 As a specific example, when the user inputs the latest quarterly sales data and related news article information, the server predicts the sales for the next quarter based on this information. Additionally, based on this prediction, the server analyzes the impact on the market and visualizes the results. An example of a prompt sentence is a request such as "Input the latest quarterly sales data and related news and create a sales prediction for the next quarter." This allows the user to obtain the information necessary for future business strategies. 【0286】 The flow of the specific process in Example 1 will be described using FIG. 11. 【0287】 Step 1: 【0288】 Users input financial and non-financial information using a communication device. The input data is diverse, including CSV files, PDF documents, audio files, and image files. The communication device provides an interface to accept these different information formats, enabling efficient data collection. The output is the initial data received by the server in the format required for analysis. 【0289】 Step 2: 【0290】 The server analyzes data in various formats received through the communication device. For example, it extracts text data from PDF documents using OCR technology and transcribes audio files using speech recognition technology. At this stage, the input is data in various formats, and the output is data in a unified text format. 【0291】 Step 3: 【0292】 The server organizes the data into a unified format and creates a unified dataset. Here, data cleansing is performed to remove inaccurate information and impute missing values ​​as needed. The input is the unified data from step 2, and the output is a cleaned and reliable dataset. 【0293】 Step 4: 【0294】 The server performs feature extraction and generates meaningful features for the learning model. It derives new features based on historical data to improve prediction accuracy. The input is the dataset obtained in step 3, and the output is feature-rich data. 【0295】 Step 5: 【0296】 The server makes predictions using a generative AI model. It uses the trained learning model to predict future sales, market trends, and other factors. The input here is the feature data generated in step 4, and the output is numerical values ​​and indicators representing the prediction results. 【0297】 Step 6: 【0298】 The terminal displays the prediction results sent from the server to the user in a visualized format. Graphs and charts allow users to easily interpret the results and apply them to their actual work. The input is predicted numerical data, and the output is a visually represented analysis. 【0299】 (Application Example 1) 【0300】 Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal." 【0301】 In today's economic environment, individuals and organizations need to organize, integrate, and forecast complex and diverse forms of financial information. Traditional systems require enormous time and effort to process, integrate, and forecast data from different formats, and often do not guarantee forecast accuracy. Furthermore, users seek comprehensive insights that take into account everyday economic activities and external factors, but there is a lack of tools to achieve this. Therefore, there is a need for new systems that can efficiently integrate data and provide reliable forecasts and recommendations in real time. 【0302】 The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means. 【0303】 In this invention, the server includes information processing device means for performing data input, data processing device means for integrating and converting various forms of information received via the information processing device means, and data processing device means for cleaning the information integrated and converted by the data processing device means. As a result, it becomes possible to efficiently integrate and analyze data in different forms, and to make highly accurate future predictions and propose economic plans. 【0304】 An "information processing device" is a device that has the function of receiving data input from a user and processing and displaying the received information. 【0305】 A "data processing device" is a device that has the function of integrating information received in various forms, performing conversion and analysis, and generating data suitable for a prediction model. 【0306】 "Data integration" is a process of gathering information obtained from different forms or sources into a single consistent form. 【0307】 "Cleaning" is a process of removing or complementing incomplete information and noise in data, and is performed to improve the quality of the data. 【0308】 "Feature quantity analysis" is a process of extracting useful features from data, and is necessary to improve the performance of a machine learning model. 【0309】 A "prediction model" is a mathematical or machine learning model used to predict future trends based on past data. 【0310】 "Future prediction" is an act of predicting future situations and trends based on current and past data. 【0311】 "Proposing an economic plan" is a process of suggesting strategies and actions that individuals or organizations should take based on the prediction results. 【0312】 This application example aims to create a system that integrates personal financial and non-financial data to predict and propose future economic activities. This system primarily consists of information processing and data processing units, and processes data in multiple steps. 【0313】 First, the terminal receives user input. The information processing device uses a smartphone or other computing device to collect the user's transaction information and daily spending information, and inputs the data. Because this information is in various formats, open-source OCR (Optical Character Recognition) software is used to convert PDFs and audio information into text. 【0314】 Next, the server receives the information, and the data processing unit performs integration and cleansing. At this stage, data analysis libraries in Python or R (e.g., Pandas, NumPy) are used to integrate information from different formats, impute missing values, and remove noise. This improves the consistency and quality of the data. 【0315】 Subsequently, the data processing unit performs feature analysis. Using machine learning libraries such as scikit-learn and TensorFlow, it analyzes user patterns and extracts the characteristics necessary for training the prediction model. Through this feature analysis, the information is organized into a form most suitable for prediction. 【0316】 Finally, the server uses a generative AI model to predict future trends and displays the results visually on the device. Users receive the visually transformed results and suggestions through a smartphone application. This allows users to create effective economic plans. 【0317】 As a concrete example, suppose a user enters the question, "If I spent a lot on entertainment this month, how will that affect my spending next month?" In response to this request, the device displays a prediction along with advice. 【0318】 Example of a prompt 【0319】 "Based on spending data from the past three months, please provide a forecast of the overall cash flow, taking into account next month's entertainment expenses." 【0320】 The flow of a specific process in Application Example 1 will be explained using Figure 12. 【0321】 Step 1: 【0322】 The terminal accepts user input. This is the process where the user enters expense and income information using an application on a smartphone. The input data is in the form of a CSV file, a photo receipt, or an audio memo. These different data formats are converted into text data using OCR or speech recognition technology. The output is standardized text-formatted economic data. 【0323】 Step 2: 【0324】 The server receives the information, and the data processing unit integrates and cleans the data. The server receives the input text data, removes duplicate data, standardizes the format, and infers and imputes missing data. At this stage, the Python Pandas library is used to generate a dataframe and create a consistent dataset. The output is a high-quality dataset in a unified format. 【0325】 Step 3: 【0326】 The data processing unit performs feature analysis. The server analyzes the unified dataset using the scikit-learn library and extracts features suitable for training a machine learning model. At this stage, information such as expenditure categories and monthly totals are generated as new features. The output is an analyzable dataset with added features. 【0327】 Step 4: 【0328】 The server uses a generated AI model to predict future trends. Based on the analyzed features, it uses existing predictive models (e.g., linear regression models or deep learning models) to predict future economic activity and fluctuations in revenue and expenditure. The output is a report containing specific prediction results. 【0329】 Step 5: 【0330】 The server sends the prediction results to the terminal, which then visualizes them. The user receives the prediction results and proposed economic plans based on them as graphs and charts through a smartphone application. The output is visualized information that is easy for the user to understand. 【0331】 Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions. 【0332】 This invention is a system that recognizes user emotions and optimizes data analysis and result presentation based on those emotions. The system consists of terminal means for data input, server means for data processing and analysis, emotion engine for emotion recognition, and terminal means that provide visualization functions for presenting analysis results to the user. 【0333】 First, the user inputs financial data and related non-financial data using a terminal device. This data can be in various formats such as CSV, PDF, and audio data, and the terminal device accepts it appropriately. 【0334】 The server analyzes the received data and, if necessary, applies OCR or speech recognition technology to standardize the data format. The integrated data is then cleaned by the server to ensure data consistency. This process includes imputation of missing values ​​and handling of outliers. 【0335】 Next, the server performs feature engineering to create a dataset suitable for training the predictive model. This step makes the data more useful for the machine learning model. 【0336】 Furthermore, the emotion engine recognizes the user's emotions from their facial expressions and voice, and generates analysis results in a format appropriate to the user's emotions. For example, if the user is feeling anxious, a report will be generated that emphasizes detailed information and explanations of risks. 【0337】 Using a pre-trained model, the server performs future financial forecasts. These forecasts include, for example, quarterly sales forecasts and market trend analyses. 【0338】 Ultimately, the terminal displays the results sent from the server on an interactive dashboard. Here, the user visualizes the results in an emotionally-driven, customized way, allowing them to understand the data more intuitively. 【0339】 For example, if a user inputs data to forecast sales of a new product, and the emotion engine simultaneously detects the user's stress level, the system will explain the credibility of the original data in a clean interface and highlight reassuring information. 【0340】 Thus, the system of the present invention takes user emotions into consideration, thereby providing a more fulfilling user experience and more effectively supporting decision-making. 【0341】 The following describes the processing flow. 【0342】 Step 1: 【0343】 Users input financial data and related non-financial data into the system via a terminal. The terminal provides an interface for transmitting data in various formats selected by the user. 【0344】 Step 2: 【0345】 The server receives the input data and performs initial analysis to standardize the format. It extracts text data from PDF files using OCR technology and converts speech data into text using speech recognition technology. 【0346】 Step 3: 【0347】 The server integrates the data and performs data cleaning to remove or correct redundant information. This process includes imputing missing values ​​and removing outliers. 【0348】 Step 4: 【0349】 The server applies feature engineering to the cleaned data to generate data suitable for machine learning models. This extracts useful features to maximize the model's performance. 【0350】 Step 5: 【0351】 The server activates an emotion engine to recognize the user's emotions in real time. It analyzes facial expressions and voices obtained from the user to evaluate the user's emotional state. 【0352】 Step 6: 【0353】 The server considers the acquired sentiment data and uses a predictive model to perform financial forecasts tailored to the user's emotional state. It then determines the optimal output format based on the sentiment data. 【0354】 Step 7: 【0355】 The device visualizes the analysis results on a dashboard to provide users with predictions. The format and explanations are automatically adjusted according to the user's emotions. 【0356】 Step 8: 【0357】 Users can review the displayed results and request additional questions or analysis as needed. The server receives user feedback and responds flexibly while referring to sentiment data. 【0358】 (Example 2) 【0359】 Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal". 【0360】 Traditional data analysis systems failed to consider user sentiment throughout the entire process, from data input to predictive model generation, making it difficult to provide optimal results for a deeper understanding of the user. Furthermore, insufficient data preparation during the integration and analysis of diverse data formats hindered the construction of precise predictive models and the generation of useful insights. Additionally, there was a lack of flexible means to respond to user inquiries and concerns. 【0361】 The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. 【0362】 In this invention, the server includes information processing means for analyzing emotions and generating analysis results based on those emotions; information processing means for analyzing non-financial information and integrating it with financial information to generate insights; and information processing means for providing additional analysis or advice in response to questions from the user. This enables the presentation of appropriate results that take into account the user's emotions, allowing the user to easily understand the data and make decisions with confidence. 【0363】 "Data input devices" are devices used by users to input financial and non-financial data, and are capable of appropriately accepting information in various formats. 【0364】 An "information processing device" is a device that possesses the technology to integrate, convert, organize, analyze, and train predictive models based on various forms of input information. 【0365】 Feature extraction is the process of selecting useful features from data to create a dataset that can be used to train a predictive model. 【0366】 An "information processing device that analyzes emotions" is a device that analyzes emotions based on the user's facial expressions and voice, and generates analysis results based on those emotions. 【0367】 A "visually displaying information device" is a device that presents prediction results transmitted from a server to the user in an easy-to-understand manner on a screen such as a dashboard. 【0368】 "Non-financial information" refers to supplementary information related to business and economics other than financial data, such as market trends and customer feedback. 【0369】 An "information processing device that provides additional analysis or advice" is a device that can provide further data analysis or specific advice in response to additional questions from the user. 【0370】 This invention is a data analysis system that takes user emotions into consideration, and its implementation utilizes an information input device, an information processing device, and a visualization device. 【0371】 Users input data in various formats using information input devices. These devices accept data in the form of CSV files, PDF documents, audio data, and other formats. The input data is then received by an information processing device, where OCR (optical character recognition) and speech recognition technologies are applied to convert it into text data. 【0372】 The server, which is an information processing device, integrates the received data and performs maintenance to maintain data consistency. This maintenance process includes filling in missing data and handling outliers. Furthermore, feature extraction techniques are used to extract significant features from the data and generate datasets for training predictive models. 【0373】 Furthermore, a device with emotion analysis capabilities analyzes the user's emotional state. For example, if the user is feeling anxious, this device detects this and generates a report that highlights and displays information related to risks. This result is input into the server's generated AI model, which precisely predicts future financial conditions. Next, the prediction results generated by the information processing device are displayed on an interactive dashboard, a visualization device. This dashboard allows the user to intuitively understand the flow of data and the results. 【0374】 For example, if a user wants to predict sales of a new product, they input the necessary data, and an emotion analysis device analyzes the user's emotional state at that time. Based on this information, the server checks the quality of the raw data and generates a report that emphasizes information to provide reassurance. 【0375】 An example of a prompt message would be, "Analyze the sales data and sentiment data entered by the user, and generate a report that includes reassuring risk information." In this way, the system of the present invention can enhance the user experience and more effectively support the decision-making process. 【0376】 The flow of the specific processing in Example 2 will be explained using Figure 13. 【0377】 Step 1: 【0378】 Users input data in various formats using input devices. These formats include CSV files, PDF documents, and audio data. The input device verifies the format of the entered data before accepting it. Once the user provides the data, the program prepares to send it to the next stage. 【0379】 Step 2: 【0380】 The server receives data transmitted from the information input device. The server uses OCR technology to extract text data from the PDF and speech recognition technology to convert speech data into text. Through these processes, the data format is standardized, and integrated data is generated for the next step. The output is the initial data integrated into text format. 【0381】 Step 3: 【0382】 The server organizes the integrated data. It performs data cleaning to maintain data consistency, including imputing missing data and removing outliers. For example, missing numerical data is imputed with the median, and extreme outliers are corrected to an appropriate range. This organized data is then sent to the next step. The output is a consistent dataset with cleaning completed. 【0383】 Step 4: 【0384】 The server uses feature extraction techniques to select useful features from the prepared data. Feature engineering is performed to create a dataset that is optimally suited as input for the predictive model. This process involves selecting highly relevant variables and generating new features, thereby improving the data's predictive accuracy. The output is a feature dataset optimized for training. 【0385】 Step 5: 【0386】 The server uses emotion analysis capabilities to determine the user's emotions from their facial expressions and voice. For example, if the user is feeling anxious, this information is used in the analysis, and the resulting report is generated with risk information emphasized. Subsequently, the analysis results corresponding to that emotion are used as input to a generating AI model, which then generates output appropriate to the user's emotions. 【0387】 Step 6: 【0388】 Ultimately, the server uses a trained generative AI model to make future financial forecasts. The forecasted data, including sales forecasts and market trend analysis for the next quarter, is generated by the information processing unit. This forecast result, created by the server, is sent to the information processing unit's dashboard. The output is presented as a detailed report containing the forecast results. 【0389】 Step 7: 【0390】 The device displays prediction results received from the server on an interactive dashboard. Through this dashboard, users can view emotionally tailored, customized visuals. This allows users to intuitively grasp the data and gain the insights necessary for decision-making. The dashboard output is a visually tuned display of information. 【0391】 (Application Example 2) 【0392】 Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal." 【0393】 The problem that this invention aims to solve lies in the limitations of existing systems that present data analysis results without taking into account the user's emotional state. In particular, when flexible responses that respond to the user's emotions and feelings are required, data visualization and advice presentation should be optimized for the user, rather than being a uniform method. Therefore, there is a need for a method that recognizes emotions and enables the presentation of data analysis results and advice in a way that takes these emotions into account. 【0394】 The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. 【0395】 In this invention, the server includes a device means for inputting data, a computing means for integrating and converting various forms of information received through the device means, and an emotion engine means for recognizing emotions and generating analysis results appropriate to the user's mood. This enables the visualization of customized data and the presentation of optimized advice according to the user's emotional state. 【0396】 "Data input device means" refers to a device for users to input information in various formats. 【0397】 "Information in various formats" refers to information in different formats such as CSV, PDF, and audio data. 【0398】 A "computational means for integrating and transforming" is a computing device for organizing information in various formats into a consistent format. 【0399】 A "cleaning computational means" is a computing device that removes noise and loss from integrated and transformed information to produce high-quality data. 【0400】 "Feature engineering" is a technique for extracting and structuring useful features from data for analysis and prediction. 【0401】 A "computational means for training and predicting predictive models" is a computing device that uses data obtained through feature engineering to predict future trends and results. 【0402】 "Visual display device means" refers to a device that visualizes and presents prediction results and analysis results obtained by calculation means to the user. 【0403】 An "emotion engine that recognizes emotions and generates analysis results appropriate to the user's feelings" is an engine that identifies emotions from the user's facial expressions, voice, etc., and generates results in an appropriate format according to those emotions. 【0404】 This invention is a system that optimizes data analysis results based on user emotions and presents them in an intuitively understandable format. This system consists of multiple components and primarily processes data through the following steps. 【0405】 First, the user provides information in various formats through a data entry device. This information can be in different formats such as CSV, PDF, or audio data, and the device is designed to accept these formats appropriately. Next, the server integrates and transforms this information and performs cleaning to maintain data consistency. In this step, computational software such as Python and pandas is used. 【0406】 Once the data is cleaned, the server performs feature engineering to build a dataset suitable for training a predictive model. This is where scikit-learn is used. This process prepares the data into a useful format. 【0407】 Furthermore, the emotion engine analyzes the user's facial expressions and voice to recognize their emotions. Emotion analysis software such as OpenFace is used for this emotion recognition. If the user is feeling anxious, the system displays data visualizations to provide reassurance. 【0408】 Finally, the server uses a trained generative AI model to visualize future predictions in an interactive format. The results are displayed using Plotly as a visualization tool, which users can view on their devices. 【0409】 As a concrete example, if a male user in his 40s operates the system after a long day of desk work, the emotion engine might detect an increased stress level. As a result, the robot might recommend "doing some light stretching" and display a stretching video. Another example of a prompt would be, "If a user is feeling stressed after a morning of desk work, what should you suggest?" 【0410】 The flow of a specific process in Application Example 2 will be explained using Figure 14. 【0411】 Step 1: 【0412】 The terminal receives data provided by the user. This input data includes various formats such as CSV, PDF, and audio data, which the terminal receives. Based on the data input, the system prepares a dataset for the next processing step. 【0413】 Step 2: 【0414】 The server integrates and transforms the data received from the terminals. Specifically, it uses OCR and speech recognition technologies to standardize and maintain consistency in the data format. The output is data in an integrated, standardized format. 【0415】 Step 3: 【0416】 The server cleans the integrated data. Specifically, it improves data quality by imputing missing values ​​and detecting and correcting outliers. This generates a clean, high-quality dataset. 【0417】 Step 4: 【0418】 The server performs feature engineering on the cleaned data. Here, it extracts useful features for machine learning and creates a new dataset. The output is data suitable for training a predictive model. 【0419】 Step 5: 【0420】 The server uses an emotion engine to recognize the user's emotions. It determines the emotional state through analysis of the user's facial expressions and voice, and uses that data for subsequent processing. 【0421】 Step 6: 【0422】 The server trains and predicts using a predictive model based on data obtained through feature engineering. Using a generative AI model, future predictions and recommendations are output. 【0423】 Step 7: 【0424】 The device visually displays the prediction results sent from the server. Users can review the results through an interactive dashboard optimized for their emotions. 【0425】 These processing steps enable data analysis and presentation of results that take user emotions into account. 【0426】 The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data. 【0427】 Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. 【0428】 In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214. 【0429】 [Third Embodiment] 【0430】 Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment. 【0431】 As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server. 【0432】 The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network). 【0433】 The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52. 【0434】 The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46. 【0435】 Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision). 【0436】 Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner. 【0437】 Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56. 【0438】 The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30. 【0439】 The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. 【0440】 In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48. 【0441】 Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal". 【0442】 This invention is a system that integrates financial and non-financial data to provide advanced analysis and forecasting in real time. The entire system consists of terminal means for data input, server means for data processing and analysis, and terminal means that provide visualization functions for presenting analysis results to the user. 【0443】 First, the user inputs financial data and related non-financial data using a terminal device. The data format can be diverse, including CSV, PDF documents, and even audio and image data, but the terminal device provides an interface that accepts these various data formats. 【0444】 The server analyzes the data received through terminal devices and integrates it through appropriate processes. For example, it extracts text data from PDF documents using OCR, while transcribing audio data using speech recognition technology. Finally, all data is converted into a unified format and integrated into a single dataset. 【0445】 Next, the server performs data cleansing, removing or supplementing inappropriate or missing data. This improves data consistency and reliability, forming the foundation for highly accurate analysis. 【0446】 Furthermore, the server performs feature engineering to create new features suitable for training the machine learning model. This feature engineering shapes the data into a more useful form for the model, improving prediction accuracy. 【0447】 The server then uses the built predictive model to perform future financial forecasts. This makes it possible to predict a company's future sales and spending trends and provide insights for strategic decision-making. 【0448】 Ultimately, the terminal device visually displays the analysis results sent from the server, allowing the user to understand them intuitively. Using graphs and charts, users can grasp the information more quickly and accurately, and request further detailed analysis as needed. 【0449】 For example, if a user inputs the latest quarterly sales data along with data from related news articles, the server will use this information to calculate sales forecasts for the next quarter and analyze their impact on the market. The terminal will then visualize these results, allowing the user to smoothly engage in discussions to develop future business strategies. 【0450】 Thus, the system provided by this invention will be a powerful tool for efficiently and effectively utilizing data and creating new business opportunities in a digitized society. 【0451】 The following describes the processing flow. 【0452】 Step 1: 【0453】 Users upload various data formats (e.g., CSV files, PDF documents, audio data) to the server via a terminal. The terminal provides a user interface, allowing users to easily select and send data. 【0454】 Step 2: 【0455】 The server begins analyzing each piece of data it receives. For PDF documents, it uses OCR technology to extract text, and for audio data, it uses speech recognition technology to convert it into text information. 【0456】 Step 3: 【0457】 The server converts data in different formats into a unified format and integrates it into a consistent dataset. It automatically applies the necessary conversion process depending on the data type. 【0458】 Step 4: 【0459】 The server cleans the integrated data. Specifically, it removes duplicate data, imputes missing values, and detects outliers, handling them appropriately. 【0460】 Step 5: 【0461】 The server performs feature engineering on the cleaned data. This extracts new features and optimizes the dataset for use by machine learning models for training. 【0462】 Step 6: 【0463】 The server uses existing data to train a predictive model, which provides the foundation for predicting future trends. 【0464】 Step 7: 【0465】 The server uses a pre-trained model to make future predictions about the input data. These predictions might include, for example, sales or market trends for the next quarter. 【0466】 Step 8: 【0467】 The device visualizes the prediction results on a dashboard to provide them to the user. Using graphs and charts makes it easier for users to intuitively understand the analysis results. 【0468】 Step 9: 【0469】 Users can conduct further analysis and ask questions based on the presented results, and, if necessary, request additional analysis from the system based on their feedback. The server will then process the new data as appropriate in response to this feedback. 【0470】 (Example 1) 【0471】 Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal." 【0472】 In business, there is a need to efficiently analyze and integrate financial and non-financial information in different formats to make reliable forecasts. However, the diversity of data formats and the incompleteness of the information pose challenges, making it difficult to convert this information into a consistent format for use in forecasting. Furthermore, it is not easy for users to intuitively understand the analysis results obtained and translate them into concrete decision-making. 【0473】 The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means. 【0474】 In this invention, the server includes a communication device, a processing device, and a processing device for characteristic extraction. This allows for the conversion of diverse forms of information into a unified format, enabling consistent analysis and highly reliable predictions. Furthermore, users can intuitively grasp the prediction results and make quick decisions. 【0475】 "Communication device means" refers to a device that provides an interface for receiving input information from a user and transmitting it to a server. 【0476】 A "processing device" is a device that has the function of analyzing received information, standardizing data in different formats, and integrating it. 【0477】 "Feature extraction" is the process of generating appropriate features from integrated data to serve as input for a machine learning model. 【0478】 A "learning model" is an analytical method that provides algorithms for predicting future events based on past data. 【0479】 A "prediction module" is a software component that uses data obtained through characteristic extraction to predict future outcomes. 【0480】 "Analysis" is the process of investigating and examining the content of data and transforming it into meaningful information. 【0481】 "Visualization" is a technique that displays analysis results in the form of graphs, diagrams, and other visual representations, making them easier for users to understand visually. 【0482】 This invention is a data analysis system that effectively processes different types of information and enables advanced prediction. The system mainly consists of communication devices, processing devices, and characteristic extraction processing devices. 【0483】 First, users can input financial and non-financial information using a communication device. The communication device has an interface that accepts various information formats, including CSV files, PDF documents, audio files, and image files. This interface is designed to allow users to upload data smoothly. 【0484】 Next, the server analyzes the information received through the communication device. The processing unit extracts text data from PDF documents using OCR (optical character recognition) technology and transcribes audio files using speech recognition technology. The server then converts this diverse information into a unified format to create a single integrated dataset. 【0485】 Next, the server performs feature extraction based on the integrated dataset. This process derives meaningful features for the generative AI model. As a result, the data is formatted in a way that is useful for the prediction module, improving the accuracy of predictions. 【0486】 Ultimately, the prediction results generated by the server are visualized for the user via a communication device. This allows the user to intuitively understand the analysis results and utilize them in strategic business decision-making. 【0487】 As a concrete example, if a user inputs the latest quarterly sales data and related news article information, the server will use this information to predict sales for the next quarter. It will also analyze the market impact based on this prediction and visualize the results. An example prompt would be a request such as, "Input the latest quarterly sales data and related news to create a sales forecast for the next quarter." This allows the user to obtain the information necessary for future business strategies. 【0488】 The flow of the specific processing in Example 1 will be explained using Figure 11. 【0489】 Step 1: 【0490】 Users input financial and non-financial information using a communication device. The input data is diverse, including CSV files, PDF documents, audio files, and image files. The communication device provides an interface to accept these different information formats, enabling efficient data collection. The output is the initial data received by the server in the format required for analysis. 【0491】 Step 2: 【0492】 The server analyzes data in various formats received through the communication device. For example, it extracts text data from PDF documents using OCR technology and transcribes audio files using speech recognition technology. At this stage, the input is data in various formats, and the output is data in a unified text format. 【0493】 Step 3: 【0494】 The server organizes the data into a unified format and creates a unified dataset. Here, data cleansing is performed to remove inaccurate information and impute missing values ​​as needed. The input is the unified data from step 2, and the output is a cleaned and reliable dataset. 【0495】 Step 4: 【0496】 The server performs feature extraction and generates meaningful features for the learning model. It derives new features based on historical data to improve prediction accuracy. The input is the dataset obtained in step 3, and the output is feature-rich data. 【0497】 Step 5: 【0498】 The server makes predictions using a generative AI model. It uses the trained learning model to predict future sales, market trends, and other factors. The input here is the feature data generated in step 4, and the output is numerical values ​​and indicators representing the prediction results. 【0499】 Step 6: 【0500】 The terminal displays the prediction results sent from the server to the user in a visualized format. Graphs and charts allow users to easily interpret the results and apply them to their actual work. The input is predicted numerical data, and the output is a visually represented analysis. 【0501】 (Application Example 1) 【0502】 Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal." 【0503】 In today's economic environment, individuals and organizations need to organize, integrate, and forecast complex and diverse forms of financial information. Traditional systems require enormous time and effort to process, integrate, and forecast data from different formats, and often do not guarantee forecast accuracy. Furthermore, users seek comprehensive insights that take into account everyday economic activities and external factors, but there is a lack of tools to achieve this. Therefore, there is a need for new systems that can efficiently integrate data and provide reliable forecasts and recommendations in real time. 【0504】 The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means. 【0505】 In this invention, the server includes an information processing device for inputting data, a data processing device for integrating and converting various forms of information received via the information processing device, and a data processing device for purifying the information integrated and converted by the data processing device. This enables efficient integration and analysis of different forms of data, making it possible to propose highly accurate future predictions and economic plans. 【0506】 An "information processing device" is a device that receives data input from a user, processes the received information, and displays it. 【0507】 A "data processing device" is a device that has the function of integrating information received in various formats, and generating data suitable for predictive models by performing transformations and analyses. 【0508】 "Data integration" is the process of combining information obtained from different formats or sources into a single, consistent format. 【0509】 "Cleanup" is the process of removing or supplementing incomplete information or noise within data, and is performed to improve data quality. 【0510】 Feature analysis is the process of extracting useful features from data, and it is necessary to improve the performance of machine learning models. 【0511】 A "predictive model" is a mathematical or machine learning model used to predict future trends based on past data. 【0512】 "Future prediction" is the act of predicting future situations and trends based on current and past data. 【0513】 "Proposing economic plans" is a process that suggests strategies and actions that individuals and organizations should take based on forecast results. 【0514】 This application example aims to create a system that integrates personal financial and non-financial data to predict and propose future economic activities. This system primarily consists of information processing and data processing units, and processes data in multiple steps. 【0515】 First, the terminal receives user input. The information processing device uses a smartphone or other computing device to collect the user's transaction information and daily spending information, and inputs the data. Because this information is in various formats, open-source OCR (Optical Character Recognition) software is used to convert PDFs and audio information into text. 【0516】 Next, the server receives the information, and the data processing unit performs integration and cleansing. At this stage, data analysis libraries in Python or R (e.g., Pandas, NumPy) are used to integrate information from different formats, impute missing values, and remove noise. This improves the consistency and quality of the data. 【0517】 Subsequently, the data processing unit performs feature analysis. Using machine learning libraries such as scikit-learn and TensorFlow, it analyzes user patterns and extracts the characteristics necessary for training the prediction model. Through this feature analysis, the information is organized into a form most suitable for prediction. 【0518】 Finally, the server uses a generative AI model to predict future trends and displays the results visually on the device. Users receive the visually transformed results and suggestions through a smartphone application. This allows users to create effective economic plans. 【0519】 As a concrete example, suppose a user enters the question, "If I spent a lot on entertainment this month, how will that affect my spending next month?" In response to this request, the device displays a prediction along with advice. 【0520】 Example of a prompt 【0521】 "Based on spending data from the past three months, please provide a forecast of the overall cash flow, taking into account next month's entertainment expenses." 【0522】 The flow of a specific process in Application Example 1 will be explained using Figure 12. 【0523】 Step 1: 【0524】 The terminal accepts user input. This is the process where the user enters expense and income information using an application on a smartphone. The input data is in the form of a CSV file, a photo receipt, or an audio memo. These different data formats are converted into text data using OCR or speech recognition technology. The output is standardized text-formatted economic data. 【0525】 Step 2: 【0526】 The server receives the information, and the data processing unit integrates and cleans the data. The server receives the input text data, removes duplicate data, standardizes the format, and infers and imputes missing data. At this stage, the Python Pandas library is used to generate a dataframe and create a consistent dataset. The output is a high-quality dataset in a unified format. 【0527】 Step 3: 【0528】 The data processing unit performs feature analysis. The server analyzes the unified dataset using the scikit-learn library and extracts features suitable for training a machine learning model. At this stage, information such as expenditure categories and monthly totals are generated as new features. The output is an analyzable dataset with added features. 【0529】 Step 4: 【0530】 The server uses a generated AI model to predict future trends. Based on the analyzed features, it uses existing predictive models (e.g., linear regression models or deep learning models) to predict future economic activity and fluctuations in revenue and expenditure. The output is a report containing specific prediction results. 【0531】 Step 5: 【0532】 The server sends the prediction results to the terminal, which then visualizes them. The user receives the prediction results and proposed economic plans based on them as graphs and charts through a smartphone application. The output is visualized information that is easy for the user to understand. 【0533】 Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions. 【0534】 This invention is a system that recognizes user emotions and optimizes data analysis and result presentation based on those emotions. The system consists of terminal means for data input, server means for data processing and analysis, emotion engine for emotion recognition, and terminal means that provide visualization functions for presenting analysis results to the user. 【0535】 First, the user inputs financial data and related non-financial data using a terminal device. This data can be in various formats such as CSV, PDF, and audio data, and the terminal device accepts it appropriately. 【0536】 The server analyzes the received data and, if necessary, applies OCR or speech recognition technology to standardize the data format. The integrated data is then cleaned by the server to ensure data consistency. This process includes imputation of missing values ​​and handling of outliers. 【0537】 Next, the server performs feature engineering to create a dataset suitable for training the predictive model. This step makes the data more useful for the machine learning model. 【0538】 Furthermore, the emotion engine recognizes the user's emotions from their facial expressions and voice, and generates analysis results in a format appropriate to the user's emotions. For example, if the user is feeling anxious, a report will be generated that emphasizes detailed information and explanations of risks. 【0539】 Using a pre-trained model, the server performs future financial forecasts. These forecasts include, for example, quarterly sales forecasts and market trend analyses. 【0540】 Ultimately, the terminal displays the results sent from the server on an interactive dashboard. Here, the user visualizes the results in an emotionally-driven, customized way, allowing them to understand the data more intuitively. 【0541】 For example, if a user inputs data to forecast sales of a new product, and the emotion engine simultaneously detects the user's stress level, the system will explain the credibility of the original data in a clean interface and highlight reassuring information. 【0542】 Thus, the system of the present invention takes user emotions into consideration, thereby providing a more fulfilling user experience and more effectively supporting decision-making. 【0543】 The following describes the processing flow. 【0544】 Step 1: 【0545】 Users input financial data and related non-financial data into the system via a terminal. The terminal provides an interface for transmitting data in various formats selected by the user. 【0546】 Step 2: 【0547】 The server receives the input data and performs initial analysis to standardize the format. It extracts text data from PDF files using OCR technology and converts speech data into text using speech recognition technology. 【0548】 Step 3: 【0549】 The server integrates the data and performs data cleaning to remove or correct redundant information. This process includes imputing missing values ​​and removing outliers. 【0550】 Step 4: 【0551】 The server applies feature engineering to the cleaned data to generate data suitable for machine learning models. This extracts useful features to maximize the model's performance. 【0552】 Step 5: 【0553】 The server activates an emotion engine to recognize the user's emotions in real time. It analyzes facial expressions and voices obtained from the user to evaluate the user's emotional state. 【0554】 Step 6: 【0555】 The server considers the acquired sentiment data and uses a predictive model to perform financial forecasts tailored to the user's emotional state. It then determines the optimal output format based on the sentiment data. 【0556】 Step 7: 【0557】 The device visualizes the analysis results on a dashboard to provide users with predictions. The format and explanations are automatically adjusted according to the user's emotions. 【0558】 Step 8: 【0559】 Users can review the displayed results and request additional questions or analysis as needed. The server receives user feedback and responds flexibly while referring to sentiment data. 【0560】 (Example 2) 【0561】 Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal." 【0562】 Traditional data analysis systems failed to consider user sentiment throughout the entire process, from data input to predictive model generation, making it difficult to provide optimal results for a deeper understanding of the user. Furthermore, insufficient data preparation during the integration and analysis of diverse data formats hindered the construction of precise predictive models and the generation of useful insights. Additionally, there was a lack of flexible means to respond to user inquiries and concerns. 【0563】 The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. 【0564】 In this invention, the server includes information processing means for analyzing emotions and generating analysis results based on those emotions; information processing means for analyzing non-financial information and integrating it with financial information to generate insights; and information processing means for providing additional analysis or advice in response to questions from the user. This enables the presentation of appropriate results that take into account the user's emotions, allowing the user to easily understand the data and make decisions with confidence. 【0565】 "Data input devices" are devices used by users to input financial and non-financial data, and are capable of appropriately accepting information in various formats. 【0566】 An "information processing device" is a device that possesses the technology to integrate, convert, organize, analyze, and train predictive models based on various forms of input information. 【0567】 Feature extraction is the process of selecting useful features from data to create a dataset that can be used to train a predictive model. 【0568】 An "information processing device that analyzes emotions" is a device that analyzes emotions based on the user's facial expressions and voice, and generates analysis results based on those emotions. 【0569】 A "visually displaying information device" is a device that presents prediction results transmitted from a server to the user in an easy-to-understand manner on a screen such as a dashboard. 【0570】 "Non-financial information" refers to supplementary information related to business and economics other than financial data, such as market trends and customer feedback. 【0571】 An "information processing device that provides additional analysis or advice" is a device that can provide further data analysis or specific advice in response to additional questions from the user. 【0572】 This invention is a data analysis system that takes user emotions into consideration, and its implementation utilizes an information input device, an information processing device, and a visualization device. 【0573】 Users input data in various formats using information input devices. These devices accept data in the form of CSV files, PDF documents, audio data, and other formats. The input data is then received by an information processing device, where OCR (optical character recognition) and speech recognition technologies are applied to convert it into text data. 【0574】 The server, which is an information processing device, integrates the received data and performs maintenance to maintain data consistency. This maintenance process includes filling in missing data and handling outliers. Furthermore, feature extraction techniques are used to extract significant features from the data and generate datasets for training predictive models. 【0575】 Furthermore, a device with emotion analysis capabilities analyzes the user's emotional state. For example, if the user is feeling anxious, this device detects this and generates a report that highlights and displays information related to risks. This result is input into the server's generated AI model, which precisely predicts future financial conditions. Next, the prediction results generated by the information processing device are displayed on an interactive dashboard, a visualization device. This dashboard allows the user to intuitively understand the flow of data and the results. 【0576】 For example, if a user wants to predict sales of a new product, they input the necessary data, and an emotion analysis device analyzes the user's emotional state at that time. Based on this information, the server checks the quality of the raw data and generates a report that emphasizes information to provide reassurance. 【0577】 An example of a prompt message would be, "Analyze the sales data and sentiment data entered by the user, and generate a report that includes reassuring risk information." In this way, the system of the present invention can enhance the user experience and more effectively support the decision-making process. 【0578】 The flow of the specific processing in Example 2 will be explained using Figure 13. 【0579】 Step 1: 【0580】 Users input data in various formats using input devices. These formats include CSV files, PDF documents, and audio data. The input device verifies the format of the entered data before accepting it. Once the user provides the data, the program prepares to send it to the next stage. 【0581】 Step 2: 【0582】 The server receives data transmitted from the information input device. The server uses OCR technology to extract text data from the PDF and speech recognition technology to convert speech data into text. Through these processes, the data format is standardized, and integrated data is generated for the next step. The output is the initial data integrated into text format. 【0583】 Step 3: 【0584】 The server organizes the integrated data. It performs data cleaning to maintain data consistency, including imputing missing data and removing outliers. For example, missing numerical data is imputed with the median, and extreme outliers are corrected to an appropriate range. This organized data is then sent to the next step. The output is a consistent dataset with cleaning completed. 【0585】 Step 4: 【0586】 The server uses feature extraction techniques to select useful features from the prepared data. Feature engineering is performed to create a dataset that is optimally suited as input for the predictive model. This process involves selecting highly relevant variables and generating new features, thereby improving the data's predictive accuracy. The output is a feature dataset optimized for training. 【0587】 Step 5: 【0588】 The server uses emotion analysis capabilities to determine the user's emotions from their facial expressions and voice. For example, if the user is feeling anxious, this information is used in the analysis, and the resulting report is generated with risk information emphasized. Subsequently, the analysis results corresponding to that emotion are used as input to a generating AI model, which then generates output appropriate to the user's emotions. 【0589】 Step 6: 【0590】 Ultimately, the server uses a trained generative AI model to make future financial forecasts. The forecasted data, including sales forecasts and market trend analysis for the next quarter, is generated by the information processing unit. This forecast result, created by the server, is sent to the information processing unit's dashboard. The output is presented as a detailed report containing the forecast results. 【0591】 Step 7: 【0592】 The device displays prediction results received from the server on an interactive dashboard. Through this dashboard, users can view emotionally tailored, customized visuals. This allows users to intuitively grasp the data and gain the insights necessary for decision-making. The dashboard output is a visually tuned display of information. 【0593】 (Application Example 2) 【0594】 Next, we will explain Application Example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal." 【0595】 The problem that this invention aims to solve lies in the limitations of existing systems that present data analysis results without taking into account the user's emotional state. In particular, when flexible responses that respond to the user's emotions and feelings are required, data visualization and advice presentation should be optimized for the user, rather than being a uniform method. Therefore, there is a need for a method that recognizes emotions and enables the presentation of data analysis results and advice in a way that takes these emotions into account. 【0596】 The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. 【0597】 In this invention, the server includes a device means for inputting data, a computing means for integrating and converting various forms of information received through the device means, and an emotion engine means for recognizing emotions and generating analysis results appropriate to the user's mood. This enables the visualization of customized data and the presentation of optimized advice according to the user's emotional state. 【0598】 "Data input device means" refers to a device for users to input information in various formats. 【0599】 "Information in various formats" refers to information in different formats such as CSV, PDF, and audio data. 【0600】 A "computational means for integrating and transforming" is a computing device for organizing information in various formats into a consistent format. 【0601】 A "cleaning computational means" is a computing device that removes noise and loss from integrated and transformed information to produce high-quality data. 【0602】 "Feature engineering" is a technique for extracting and structuring useful features from data for analysis and prediction. 【0603】 A "computational means for training and predicting predictive models" is a computing device that uses data obtained through feature engineering to predict future trends and results. 【0604】 "Visual display device means" refers to a device that visualizes and presents prediction results and analysis results obtained by calculation means to the user. 【0605】 An "emotion engine that recognizes emotions and generates analysis results appropriate to the user's feelings" is an engine that identifies emotions from the user's facial expressions, voice, etc., and generates results in an appropriate format according to those emotions. 【0606】 This invention is a system that optimizes data analysis results based on user emotions and presents them in an intuitively understandable format. This system consists of multiple components and primarily processes data through the following steps. 【0607】 First, the user provides information in various formats through a data entry device. This information can be in different formats such as CSV, PDF, or audio data, and the device is designed to accept these formats appropriately. Next, the server integrates and transforms this information and performs cleaning to maintain data consistency. In this step, computational software such as Python and pandas is used. 【0608】 Once the data is cleaned, the server performs feature engineering to build a dataset suitable for training a predictive model. This is where scikit-learn is used. This process prepares the data into a useful format. 【0609】 Furthermore, the emotion engine analyzes the user's facial expressions and voice to recognize their emotions. Emotion analysis software such as OpenFace is used for this emotion recognition. If the user is feeling anxious, the system displays data visualizations to provide reassurance. 【0610】 Finally, the server uses a trained generative AI model to visualize future predictions in an interactive format. The results are displayed using Plotly as a visualization tool, which users can view on their devices. 【0611】 As a concrete example, if a male user in his 40s operates the system after a long day of desk work, the emotion engine might detect an increased stress level. As a result, the robot might recommend "doing some light stretching" and display a stretching video. Another example of a prompt would be, "If a user is feeling stressed after a morning of desk work, what should you suggest?" 【0612】 The flow of a specific process in Application Example 2 will be explained using Figure 14. 【0613】 Step 1: 【0614】 The terminal receives data provided by the user. This input data includes various formats such as CSV, PDF, and audio data, which the terminal receives. Based on the data input, the system prepares a dataset for the next processing step. 【0615】 Step 2: 【0616】 The server integrates and transforms the data received from the terminals. Specifically, it uses OCR and speech recognition technologies to standardize and maintain consistency in the data format. The output is data in an integrated, standardized format. 【0617】 Step 3: 【0618】 The server cleans the integrated data. Specifically, it improves data quality by imputing missing values ​​and detecting and correcting outliers. This generates a clean, high-quality dataset. 【0619】 Step 4: 【0620】 The server performs feature engineering on the cleaned data. Here, it extracts useful features for machine learning and creates a new dataset. The output is data suitable for training a predictive model. 【0621】 Step 5: 【0622】 The server uses an emotion engine to recognize the user's emotions. It determines the emotional state through analysis of the user's facial expressions and voice, and uses that data for subsequent processing. 【0623】 Step 6: 【0624】 The server trains and predicts using a predictive model based on data obtained through feature engineering. Using a generative AI model, future predictions and recommendations are output. 【0625】 Step 7: 【0626】 The device visually displays the prediction results sent from the server. Users can review the results through an interactive dashboard optimized for their emotions. 【0627】 These processing steps enable data analysis and presentation of results that take user emotions into account. 【0628】 The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data. 【0629】 Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. 【0630】 In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314. 【0631】 [Fourth Embodiment] 【0632】 Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment. 【0633】 As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server. 【0634】 The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network). 【0635】 The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52. 【0636】 The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46. 【0637】 Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision). 【0638】 Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner. 【0639】 The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes. 【0640】 Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56. 【0641】 The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30. 【0642】 The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. 【0643】 In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48. 【0644】 Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal". 【0645】 This invention is a system that integrates financial and non-financial data to provide advanced analysis and forecasting in real time. The entire system consists of terminal means for data input, server means for data processing and analysis, and terminal means that provide visualization functions for presenting analysis results to the user. 【0646】 First, the user inputs financial data and related non-financial data using a terminal device. The data format can be diverse, including CSV, PDF documents, and even audio and image data, but the terminal device provides an interface that accepts these various data formats. 【0647】 The server analyzes the data received through terminal devices and integrates it through appropriate processes. For example, it extracts text data from PDF documents using OCR, while transcribing audio data using speech recognition technology. Finally, all data is converted into a unified format and integrated into a single dataset. 【0648】 Next, the server performs data cleansing, removing or supplementing inappropriate or missing data. This improves data consistency and reliability, forming the foundation for highly accurate analysis. 【0649】 Furthermore, the server performs feature engineering to create new features suitable for training the machine learning model. This feature engineering shapes the data into a more useful form for the model, improving prediction accuracy. 【0650】 The server then uses the built predictive model to perform future financial forecasts. This makes it possible to predict a company's future sales and spending trends and provide insights for strategic decision-making. 【0651】 Ultimately, the terminal device visually displays the analysis results sent from the server, allowing the user to understand them intuitively. Using graphs and charts, users can grasp the information more quickly and accurately, and request further detailed analysis as needed. 【0652】 For example, if a user inputs the latest quarterly sales data along with data from related news articles, the server will use this information to calculate sales forecasts for the next quarter and analyze their impact on the market. The terminal will then visualize these results, allowing the user to smoothly engage in discussions to develop future business strategies. 【0653】 Thus, the system provided by this invention will be a powerful tool for efficiently and effectively utilizing data and creating new business opportunities in a digitized society. 【0654】 The following describes the processing flow. 【0655】 Step 1: 【0656】 Users upload various data formats (e.g., CSV files, PDF documents, audio data) to the server via a terminal. The terminal provides a user interface, allowing users to easily select and send data. 【0657】 Step 2: 【0658】 The server begins analyzing each piece of data it receives. For PDF documents, it uses OCR technology to extract text, and for audio data, it uses speech recognition technology to convert it into text information. 【0659】 Step 3: 【0660】 The server converts data in different formats into a unified format and integrates it into a consistent dataset. It automatically applies the necessary conversion process depending on the data type. 【0661】 Step 4: 【0662】 The server cleans the integrated data. Specifically, it removes duplicate data, imputes missing values, and detects outliers, handling them appropriately. 【0663】 Step 5: 【0664】 The server performs feature engineering on the cleaned data. This extracts new features and optimizes the dataset for use by machine learning models for training. 【0665】 Step 6: 【0666】 The server uses existing data to train a predictive model, which provides the foundation for predicting future trends. 【0667】 Step 7: 【0668】 The server uses a pre-trained model to make future predictions about the input data. These predictions might include, for example, sales or market trends for the next quarter. 【0669】 Step 8: 【0670】 The device visualizes the prediction results on a dashboard to provide them to the user. Using graphs and charts makes it easier for users to intuitively understand the analysis results. 【0671】 Step 9: 【0672】 Users can conduct further analysis and ask questions based on the presented results, and, if necessary, request additional analysis from the system based on their feedback. The server will then process the new data as appropriate in response to this feedback. 【0673】 (Example 1) 【0674】 Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal". 【0675】 In business, there is a need to efficiently analyze and integrate financial and non-financial information in different formats to make reliable forecasts. However, the diversity of data formats and the incompleteness of the information pose challenges, making it difficult to convert this information into a consistent format for use in forecasting. Furthermore, it is not easy for users to intuitively understand the analysis results obtained and translate them into concrete decision-making. 【0676】 The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means. 【0677】 In this invention, the server includes a communication device, a processing device, and a processing device for characteristic extraction. This allows for the conversion of diverse forms of information into a unified format, enabling consistent analysis and highly reliable predictions. Furthermore, users can intuitively grasp the prediction results and make quick decisions. 【0678】 "Communication device means" refers to a device that provides an interface for receiving input information from a user and transmitting it to a server. 【0679】 A "processing device" is a device that has the function of analyzing received information, standardizing data in different formats, and integrating it. 【0680】 "Feature extraction" is the process of generating appropriate features from integrated data to serve as input for a machine learning model. 【0681】 A "learning model" is an analytical method that provides algorithms for predicting future events based on past data. 【0682】 A "prediction module" is a software component that uses data obtained through characteristic extraction to predict future outcomes. 【0683】 "Analysis" is the process of investigating and examining the content of data and transforming it into meaningful information. 【0684】 "Visualization" is a technique that displays analysis results in the form of graphs, diagrams, and other visual representations, making them easier for users to understand visually. 【0685】 This invention is a data analysis system that effectively processes different types of information and enables advanced prediction. The system mainly consists of communication devices, processing devices, and characteristic extraction processing devices. 【0686】 First, users can input financial and non-financial information using a communication device. The communication device has an interface that accepts various information formats, including CSV files, PDF documents, audio files, and image files. This interface is designed to allow users to upload data smoothly. 【0687】 Next, the server analyzes the information received through the communication device. The processing unit extracts text data from PDF documents using OCR (optical character recognition) technology and transcribes audio files using speech recognition technology. The server then converts this diverse information into a unified format to create a single integrated dataset. 【0688】 Next, the server performs feature extraction based on the integrated dataset. This process derives meaningful features for the generative AI model. As a result, the data is formatted in a way that is useful for the prediction module, improving the accuracy of predictions. 【0689】 Ultimately, the prediction results generated by the server are visualized for the user via a communication device. This allows the user to intuitively understand the analysis results and utilize them in strategic business decision-making. 【0690】 As a concrete example, if a user inputs the latest quarterly sales data and related news article information, the server will use this information to predict sales for the next quarter. It will also analyze the market impact based on this prediction and visualize the results. An example prompt would be a request such as, "Input the latest quarterly sales data and related news to create a sales forecast for the next quarter." This allows the user to obtain the information necessary for future business strategies. 【0691】 The flow of the specific processing in Example 1 will be explained using Figure 11. 【0692】 Step 1: 【0693】 Users input financial and non-financial information using a communication device. The input data is diverse, including CSV files, PDF documents, audio files, and image files. The communication device provides an interface to accept these different information formats, enabling efficient data collection. The output is the initial data received by the server in the format required for analysis. 【0694】 Step 2: 【0695】 The server analyzes data in various formats received through the communication device. For example, it extracts text data from PDF documents using OCR technology and transcribes audio files using speech recognition technology. At this stage, the input is data in various formats, and the output is data in a unified text format. 【0696】 Step 3: 【0697】 The server organizes the data into a unified format and creates a unified dataset. Here, data cleansing is performed to remove inaccurate information and impute missing values ​​as needed. The input is the unified data from step 2, and the output is a cleaned and reliable dataset. 【0698】 Step 4: 【0699】 The server performs feature extraction and generates meaningful features for the learning model. It derives new features based on historical data to improve prediction accuracy. The input is the dataset obtained in step 3, and the output is feature-rich data. 【0700】 Step 5: 【0701】 The server makes predictions using a generative AI model. It uses the trained learning model to predict future sales, market trends, and other factors. The input here is the feature data generated in step 4, and the output is numerical values ​​and indicators representing the prediction results. 【0702】 Step 6: 【0703】 The terminal displays the prediction results sent from the server to the user in a visualized format. Graphs and charts allow users to easily interpret the results and apply them to their actual work. The input is predicted numerical data, and the output is a visually represented analysis. 【0704】 (Application Example 1) 【0705】 Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal". 【0706】 In today's economic environment, individuals and organizations need to organize, integrate, and forecast complex and diverse forms of financial information. Traditional systems require enormous time and effort to process, integrate, and forecast data from different formats, and often do not guarantee forecast accuracy. Furthermore, users seek comprehensive insights that take into account everyday economic activities and external factors, but there is a lack of tools to achieve this. Therefore, there is a need for new systems that can efficiently integrate data and provide reliable forecasts and recommendations in real time. 【0707】 The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means. 【0708】 In this invention, the server includes an information processing device for inputting data, a data processing device for integrating and converting various forms of information received via the information processing device, and a data processing device for purifying the information integrated and converted by the data processing device. This enables efficient integration and analysis of different forms of data, making it possible to propose highly accurate future predictions and economic plans. 【0709】 An "information processing device" is a device that receives data input from a user, processes the received information, and displays it. 【0710】 A "data processing device" is a device that has the function of integrating information received in various formats, and generating data suitable for predictive models by performing transformations and analyses. 【0711】 "Data integration" is the process of combining information obtained from different formats or sources into a single, consistent format. 【0712】 "Cleanup" is the process of removing or supplementing incomplete information or noise within data, and is performed to improve data quality. 【0713】 Feature analysis is the process of extracting useful features from data, and it is necessary to improve the performance of machine learning models. 【0714】 A "predictive model" is a mathematical or machine learning model used to predict future trends based on past data. 【0715】 "Future prediction" is the act of predicting future situations and trends based on current and past data. 【0716】 "Proposing economic plans" is a process that suggests strategies and actions that individuals and organizations should take based on forecast results. 【0717】 This application example aims to create a system that integrates personal financial and non-financial data to predict and propose future economic activities. This system primarily consists of information processing and data processing units, and processes data in multiple steps. 【0718】 First, the terminal receives user input. The information processing device uses a smartphone or other computing device to collect the user's transaction information and daily spending information, and inputs the data. Because this information is in various formats, open-source OCR (Optical Character Recognition) software is used to convert PDFs and audio information into text. 【0719】 Next, the server receives the information, and the data processing unit performs integration and cleansing. At this stage, data analysis libraries in Python or R (e.g., Pandas, NumPy) are used to integrate information from different formats, impute missing values, and remove noise. This improves the consistency and quality of the data. 【0720】 Subsequently, the data processing unit performs feature analysis. Using machine learning libraries such as scikit-learn and TensorFlow, it analyzes user patterns and extracts the characteristics necessary for training the prediction model. Through this feature analysis, the information is organized into a form most suitable for prediction. 【0721】 Finally, the server uses a generative AI model to predict future trends and displays the results visually on the device. Users receive the visually transformed results and suggestions through a smartphone application. This allows users to create effective economic plans. 【0722】 As a concrete example, suppose a user enters the question, "If I spent a lot on entertainment this month, how will that affect my spending next month?" In response to this request, the device displays a prediction along with advice. 【0723】 Example of a prompt 【0724】 "Based on spending data from the past three months, please provide a forecast of the overall cash flow, taking into account next month's entertainment expenses." 【0725】 The flow of a specific process in Application Example 1 will be explained using Figure 12. 【0726】 Step 1: 【0727】 The terminal accepts user input. This is the process where the user enters expense and income information using an application on a smartphone. The input data is in the form of a CSV file, a photo receipt, or an audio memo. These different data formats are converted into text data using OCR or speech recognition technology. The output is standardized text-formatted economic data. 【0728】 Step 2: 【0729】 The server receives the information, and the data processing unit integrates and cleans the data. The server receives the input text data, removes duplicate data, standardizes the format, and infers and imputes missing data. At this stage, the Python Pandas library is used to generate a dataframe and create a consistent dataset. The output is a high-quality dataset in a unified format. 【0730】 Step 3: 【0731】 The data processing unit performs feature analysis. The server analyzes the unified dataset using the scikit-learn library and extracts features suitable for training a machine learning model. At this stage, information such as expenditure categories and monthly totals are generated as new features. The output is an analyzable dataset with added features. 【0732】 Step 4: 【0733】 The server uses a generated AI model to predict future trends. Based on the analyzed features, it uses existing predictive models (e.g., linear regression models or deep learning models) to predict future economic activity and fluctuations in revenue and expenditure. The output is a report containing specific prediction results. 【0734】 Step 5: 【0735】 The server sends the prediction results to the terminal, which then visualizes them. The user receives the prediction results and proposed economic plans based on them as graphs and charts through a smartphone application. The output is visualized information that is easy for the user to understand. 【0736】 Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions. 【0737】 This invention is a system that recognizes user emotions and optimizes data analysis and result presentation based on those emotions. The system consists of terminal means for data input, server means for data processing and analysis, emotion engine for emotion recognition, and terminal means that provide visualization functions for presenting analysis results to the user. 【0738】 First, the user inputs financial data and related non-financial data using a terminal device. This data can be in various formats such as CSV, PDF, and audio data, and the terminal device accepts it appropriately. 【0739】 The server analyzes the received data and, if necessary, applies OCR or speech recognition technology to standardize the data format. The integrated data is then cleaned by the server to ensure data consistency. This process includes imputation of missing values ​​and handling of outliers. 【0740】 Next, the server performs feature engineering to create a dataset suitable for training the predictive model. This step makes the data more useful for the machine learning model. 【0741】 Furthermore, the emotion engine recognizes the user's emotions from their facial expressions and voice, and generates analysis results in a format appropriate to the user's emotions. For example, if the user is feeling anxious, a report will be generated that emphasizes detailed information and explanations of risks. 【0742】 Using a pre-trained model, the server performs future financial forecasts. These forecasts include, for example, quarterly sales forecasts and market trend analyses. 【0743】 Ultimately, the terminal displays the results sent from the server on an interactive dashboard. Here, the user visualizes the results in an emotionally-driven, customized way, allowing them to understand the data more intuitively. 【0744】 For example, if a user inputs data to forecast sales of a new product, and the emotion engine simultaneously detects the user's stress level, the system will explain the credibility of the original data in a clean interface and highlight reassuring information. 【0745】 Thus, the system of the present invention takes user emotions into consideration, thereby providing a more fulfilling user experience and more effectively supporting decision-making. 【0746】 The following describes the processing flow. 【0747】 Step 1: 【0748】 Users input financial data and related non-financial data into the system via a terminal. The terminal provides an interface for transmitting data in various formats selected by the user. 【0749】 Step 2: 【0750】 The server receives the input data and performs initial analysis to standardize the format. It extracts text data from PDF files using OCR technology and converts speech data into text using speech recognition technology. 【0751】 Step 3: 【0752】 The server integrates the data and performs data cleaning to remove or correct redundant information. This process includes imputing missing values ​​and removing outliers. 【0753】 Step 4: 【0754】 The server applies feature engineering to the cleaned data to generate data suitable for machine learning models. This extracts useful features to maximize the model's performance. 【0755】 Step 5: 【0756】 The server activates an emotion engine to recognize the user's emotions in real time. It analyzes facial expressions and voices obtained from the user to evaluate the user's emotional state. 【0757】 Step 6: 【0758】 The server considers the acquired sentiment data and uses a predictive model to perform financial forecasts tailored to the user's emotional state. It then determines the optimal output format based on the sentiment data. 【0759】 Step 7: 【0760】 The device visualizes the analysis results on a dashboard to provide users with predictions. The format and explanations are automatically adjusted according to the user's emotions. 【0761】 Step 8: 【0762】 Users can review the displayed results and request additional questions or analysis as needed. The server receives user feedback and responds flexibly while referring to sentiment data. 【0763】 (Example 2) 【0764】 Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal". 【0765】 Traditional data analysis systems failed to consider user sentiment throughout the entire process, from data input to predictive model generation, making it difficult to provide optimal results for a deeper understanding of the user. Furthermore, insufficient data preparation during the integration and analysis of diverse data formats hindered the construction of precise predictive models and the generation of useful insights. Additionally, there was a lack of flexible means to respond to user inquiries and concerns. 【0766】 The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. 【0767】 In this invention, the server includes information processing means for analyzing emotions and generating analysis results based on those emotions; information processing means for analyzing non-financial information and integrating it with financial information to generate insights; and information processing means for providing additional analysis or advice in response to questions from the user. This enables the presentation of appropriate results that take into account the user's emotions, allowing the user to easily understand the data and make decisions with confidence. 【0768】 "Data input devices" are devices used by users to input financial and non-financial data, and are capable of appropriately accepting information in various formats. 【0769】 An "information processing device" is a device that possesses the technology to integrate, convert, organize, analyze, and train predictive models based on various input formats. 【0770】 Feature extraction is the process of selecting useful features from data to create a dataset that can be used to train a predictive model. 【0771】 An "information processing device that analyzes emotions" is a device that analyzes emotions based on the user's facial expressions and voice, and generates analysis results based on those emotions. 【0772】 A "visually displaying information device" is a device that presents prediction results transmitted from a server to the user in an easy-to-understand manner on a screen such as a dashboard. 【0773】 "Non-financial information" refers to supplementary information related to business and economics other than financial data, such as market trends and customer feedback. 【0774】 An "information processing device that provides additional analysis or advice" is a device that can provide further data analysis or specific advice in response to additional questions from the user. 【0775】 This invention is a data analysis system that takes user emotions into consideration, and its implementation utilizes an information input device, an information processing device, and a visualization device. 【0776】 Users input data in various formats using information input devices. These devices accept data in the form of CSV files, PDF documents, audio data, and other formats. The input data is then received by an information processing device, where OCR (optical character recognition) and speech recognition technologies are applied to convert it into text data. 【0777】 The server, which is an information processing device, integrates the received data and performs maintenance to maintain data consistency. This maintenance process includes filling in missing data and handling outliers. Furthermore, feature extraction techniques are used to extract significant features from the data and generate datasets for training predictive models. 【0778】 Furthermore, a device with emotion analysis capabilities analyzes the user's emotional state. For example, if the user is feeling anxious, this device detects this and generates a report that highlights and displays information related to risks. This result is input into the server's generated AI model, which precisely predicts future financial conditions. Next, the prediction results generated by the information processing device are displayed on an interactive dashboard, a visualization device. This dashboard allows the user to intuitively understand the flow of data and the results. 【0779】 For example, if a user wants to predict sales of a new product, they input the necessary data, and an emotion analysis device analyzes the user's emotional state at that time. Based on this information, the server checks the quality of the raw data and generates a report that emphasizes information to provide reassurance. 【0780】 An example of a prompt message would be, "Analyze the sales data and sentiment data entered by the user, and generate a report that includes reassuring risk information." In this way, the system of the present invention can enhance the user experience and more effectively support the decision-making process. 【0781】 The flow of the specific processing in Example 2 will be explained using Figure 13. 【0782】 Step 1: 【0783】 Users input data in various formats using input devices. These formats include CSV files, PDF documents, and audio data. The input device verifies the format of the entered data before accepting it. Once the user provides the data, the program prepares to send it to the next stage. 【0784】 Step 2: 【0785】 The server receives data transmitted from the information input device. The server uses OCR technology to extract text data from the PDF and speech recognition technology to convert speech data into text. Through these processes, the data format is standardized, and integrated data is generated for the next step. The output is the initial data integrated into text format. 【0786】 Step 3: 【0787】 The server organizes the integrated data. It performs data cleaning to maintain data consistency, including imputing missing data and removing outliers. For example, missing numerical data is imputed with the median, and extreme outliers are corrected to an appropriate range. This organized data is then sent to the next step. The output is a consistent dataset with cleaning completed. 【0788】 Step 4: 【0789】 The server uses feature extraction techniques to select useful features from the prepared data. Feature engineering is performed to create a dataset that is optimally suited as input for the predictive model. This process involves selecting highly relevant variables and generating new features, thereby improving the data's predictive accuracy. The output is a feature dataset optimized for training. 【0790】 Step 5: 【0791】 The server uses emotion analysis capabilities to determine the user's emotions from their facial expressions and voice. For example, if the user is feeling anxious, this information is used in the analysis, and the resulting report is generated with risk information emphasized. Subsequently, the analysis results corresponding to that emotion are used as input to a generating AI model, which then generates output appropriate to the user's emotions. 【0792】 Step 6: 【0793】 Ultimately, the server uses a trained generative AI model to make future financial forecasts. The forecasted data, including sales forecasts and market trend analysis for the next quarter, is generated by the information processing unit. This forecast result, created by the server, is sent to the information processing unit's dashboard. The output is presented as a detailed report containing the forecast results. 【0794】 Step 7: 【0795】 The device displays prediction results received from the server on an interactive dashboard. Through this dashboard, users can view emotionally tailored, customized visuals. This allows users to intuitively grasp the data and gain the insights necessary for decision-making. The dashboard output is a visually tuned display of information. 【0796】 (Application Example 2) 【0797】 Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal". 【0798】 The problem that this invention aims to solve lies in the limitations of existing systems that present data analysis results without taking into account the user's emotional state. In particular, when flexible responses that respond to the user's emotions and feelings are required, data visualization and advice presentation should be optimized for the user, rather than being a uniform method. Therefore, there is a need for a method that recognizes emotions and enables the presentation of data analysis results and advice in a way that takes these emotions into account. 【0799】 The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. 【0800】 In this invention, the server includes a device means for inputting data, a computing means for integrating and converting various forms of information received through the device means, and an emotion engine means for recognizing emotions and generating analysis results appropriate to the user's mood. This enables the visualization of customized data and the presentation of optimized advice according to the user's emotional state. 【0801】 "Data input device means" refers to a device for users to input information in various formats. 【0802】 "Information in various formats" refers to information in different formats such as CSV, PDF, and audio data. 【0803】 A "computational means for integrating and transforming" is a computing device for organizing information in various formats into a consistent format. 【0804】 A "cleaning computational means" is a computing device that removes noise and loss from integrated and transformed information to produce high-quality data. 【0805】 "Feature engineering" is a technique for extracting and structuring useful features from data for analysis and prediction. 【0806】 A "computational means for training and predicting predictive models" is a computing device that uses data obtained through feature engineering to predict future trends and results. 【0807】 "Visual display device means" refers to a device that visualizes and presents prediction results and analysis results obtained by calculation means to the user. 【0808】 An "emotion engine that recognizes emotions and generates analysis results appropriate to the user's feelings" is an engine that identifies emotions from the user's facial expressions, voice, etc., and generates results in an appropriate format according to those emotions. 【0809】 This invention is a system that optimizes data analysis results based on user emotions and presents them in an intuitively understandable format. This system consists of multiple components and primarily processes data through the following steps. 【0810】 First, the user provides information in various formats through a data entry device. This information can be in different formats such as CSV, PDF, or audio data, and the device is designed to accept these formats appropriately. Next, the server integrates and transforms this information and performs cleaning to maintain data consistency. In this step, computational software such as Python and pandas is used. 【0811】 Once the data is cleaned, the server performs feature engineering to build a dataset suitable for training a predictive model. This is where scikit-learn is used. This process prepares the data into a useful format. 【0812】 Furthermore, the emotion engine analyzes the user's facial expressions and voice to recognize their emotions. Emotion analysis software such as OpenFace is used for this emotion recognition. If the user is feeling anxious, the system displays data visualizations to provide reassurance. 【0813】 Finally, the server uses a trained generative AI model to visualize future predictions in an interactive format. The results are displayed using Plotly as a visualization tool, which users can view on their devices. 【0814】 As a concrete example, if a male user in his 40s operates the system after a long day of desk work, the emotion engine might detect an increased stress level. As a result, the robot might recommend "doing some light stretching" and display a stretching video. Another example of a prompt would be, "If a user is feeling stressed after a morning of desk work, what should you suggest?" 【0815】 The flow of a specific process in Application Example 2 will be explained using Figure 14. 【0816】 Step 1: 【0817】 The terminal receives data provided by the user. This input data includes various formats such as CSV, PDF, and audio data, which the terminal receives. Based on the data input, the system prepares a dataset for the next processing step. 【0818】 Step 2: 【0819】 The server integrates and transforms the data received from the terminals. Specifically, it uses OCR and speech recognition technologies to standardize and maintain consistency in the data format. The output is data in an integrated, standardized format. 【0820】 Step 3: 【0821】 The server cleans the integrated data. Specifically, it improves data quality by imputing missing values ​​and detecting and correcting outliers. This generates a clean, high-quality dataset. 【0822】 Step 4: 【0823】 The server performs feature engineering on the cleaned data. Here, it extracts useful features for machine learning and creates a new dataset. The output is data suitable for training a predictive model. 【0824】 Step 5: 【0825】 The server uses an emotion engine to recognize the user's emotions. It determines the emotional state through analysis of the user's facial expressions and voice, and uses that data for subsequent processing. 【0826】 Step 6: 【0827】 The server trains and predicts using a predictive model based on data obtained through feature engineering. Using a generative AI model, future predictions and recommendations are output. 【0828】 Step 7: 【0829】 The device visually displays the prediction results sent from the server. Users can review the results through an interactive dashboard optimized for their emotions. 【0830】 These processing steps enable data analysis and presentation of results that take user emotions into account. 【0831】 The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data. 【0832】 Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. 【0833】 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 this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414. 【0834】 Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion. 【0835】 Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together. 【0836】 These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression. 【0837】 The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become. 【0838】 Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant. 【0839】 The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more." 【0840】 The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values. 【0841】 The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format. 【0842】 In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data. 【0843】 In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56. 【0844】 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. 【0845】 Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56. 【0846】 The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory. 【0847】 The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor. 【0848】 Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources. 【0849】 Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose. 【0850】 The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above. 【0851】 All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference. 【0852】 The following is further disclosed regarding the embodiments described above. 【0853】 (Claim 1) 【0854】 A terminal means for data entry, 【0855】 A server means for integrating and converting data in various formats received via the terminal means, 【0856】 A server means for cleaning the data integrated and converted by the aforementioned server means, 【0857】 A server means for performing feature engineering on the cleaned data, 【0858】 A server means that performs training and prediction of a predictive model based on the data obtained by the aforementioned feature engineering, 【0859】 A terminal means for visually displaying the aforementioned prediction results, 【0860】 A system that includes this. 【0861】 (Claim 2) 【0862】 The system according to claim 1, further comprising server means for analyzing non-financial data and integrating it with financial data to generate insights. 【0863】 (Claim 3) 【0864】 The system according to claim 1, further comprising server means for providing additional analysis or advice in response to user inquiries. 【0865】 "Example 1" 【0866】 (Claim 1) 【0867】 A communication device means for receiving input information, 【0868】 Processing device means that analyzes information in various formats received via the aforementioned communication device means, converts it into a unified format, and aggregates it; 【0869】 Processing means for organizing the integrated information constructed by the aforementioned processing means and correcting or supplementing incomplete information, 【0870】 A processing device that extracts characteristics from the organized information and generates input for a learning model, 【0871】 A processing device means that performs training of a prediction module and future predictions based on the information obtained by the characteristic extraction, 【0872】 A communication device means that displays the aforementioned prediction results in a format that can be intuitively interpreted, 【0873】 A system that includes this. 【0874】 (Claim 2) 【0875】 The system according to claim 1, further comprising a processing device for analyzing non-financial information and combining it with financial information to generate insights. 【0876】 (Claim 3) 【0877】 The system according to claim 1, further comprising processing means for providing further analysis or guidance in response to inquiries from the user. 【0878】 "Application Example 1" 【0879】 (Claim 1) 【0880】 Information processing device means for inputting data, 【0881】 A data processing device that integrates and converts information in various formats received via the aforementioned information processing device, 【0882】 A data processing device for purifying information integrated and converted by the aforementioned data processing device, 【0883】 A data processing device means for performing feature analysis on the purified information, 【0884】 A data processing device means that performs training and prediction of a prediction model based on the information obtained by the feature analysis described above, 【0885】 Information processing device means for visually displaying the prediction results, 【0886】 An information processing device that allows users to input data on their daily economic activities and proposes future economic plans based on the prediction results, 【0887】 A system that includes this. 【0888】 (Claim 2) 【0889】 The system according to claim 1, further comprising data processing means for analyzing non-financial information and integrating it with financial information to generate insights. 【0890】 (Claim 3) 【0891】 The system according to claim 1, further comprising data processing means for providing additional analysis or advice in response to inquiries from users. 【0892】 "Example 2 of combining an emotion engine" 【0893】 (Claim 1) 【0894】 Information equipment for inputting data, 【0895】 An information processing device that integrates and converts various forms of information received via the aforementioned information device, 【0896】 An information processing device for organizing the information integrated and converted by the aforementioned information processing device, 【0897】 An information processing device that performs feature extraction on the prepared information, 【0898】 An information processing device that performs training and prediction of a predictive model based on the information obtained by the feature extraction described above, 【0899】 An information processing device that analyzes emotions and generates analysis results based on those emotions, 【0900】 An information device that visually displays the aforementioned prediction results, 【0901】 A system that includes this. 【0902】 (Claim 2) 【0903】 The system according to claim 1, further comprising an information processing device that analyzes non-financial information and integrates it with financial information to generate insights. 【0904】 (Claim 3) 【0905】 The system according to claim 1, further comprising an information processing device that provides additional analysis or advice in response to a question from a user. 【0906】 "Application example 2 when combining with an emotional engine" 【0907】 (Claim 1) 【0908】 A device means for inputting data, 【0909】 A computing means for integrating and converting various forms of information received through the aforementioned device means, 【0910】 A calculation means for cleaning the information integrated and transformed by the aforementioned calculation means, 【0911】 A computational means for performing feature engineering on the cleaned information, 【0912】 A computation means for training and predicting a predictive model based on the information obtained by the aforementioned feature engineering, 【0913】 A device for visually displaying the aforementioned prediction results, 【0914】 An emotion engine that recognizes emotions and generates analysis results appropriate to the user's feelings, 【0915】 A system that includes this. 【0916】 (Claim 2) 【0917】 The system according to claim 1, further comprising computational means for analyzing non-financial information and integrating it with financial information to generate insights. 【0918】 (Claim 3) 【0919】 The system according to claim 1, further comprising computational means for providing additional analysis or advice in response to questions from the user. [Explanation of symbols] 【0920】 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

[Claim 1] A terminal means for data entry, A server means for integrating and converting data in various formats received via the terminal means, A server means for cleaning the data integrated and converted by the aforementioned server means, A server means for performing feature engineering on the cleaned data, A server means that performs training and prediction of a predictive model based on the data obtained by the aforementioned feature engineering, A terminal means for visually displaying the aforementioned prediction results, A system that includes this. [Claim 2] The system according to claim 1, further comprising server means for analyzing non-financial data and integrating it with financial data to generate insights. [Claim 3] The system according to claim 1, further comprising server means for providing additional analysis or advice in response to user inquiries.

Images