system

Abstract

We provide the system. [Solution] Methods for entering data within a company, A means of automatically collecting market information from external data sources, A means of performing preprocessing to prepare the data, Methods for performing financial analysis, market forecasting, and competitive analysis using generative models, Means of presenting analysis results to the user, A means of collecting user feedback and updating the generative model, 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 Unexamined Patent Application Publication No. 2022-180282 【Summary of the Invention】 【Problems to be Solved by the Invention】 【0004】 In small and medium-sized enterprises, access to specialized consulting services is often costly, which is a factor hindering rapid business decisions. In conventional approaches, there is often a reliance on subjective advice, so objective and data-based analysis has not been fully carried out. It is necessary to solve such problems and provide an effective business strategy at low cost. 【Means for Solving the Problems】 【0005】 This invention provides a system that automatically performs analysis using a generative model based on data obtained from within a company and information acquired from external data sources. The system has functions to perform data preprocessing, financial analysis, market forecasting, and competitive analysis, and to present the analysis results to the user. Furthermore, by continuously updating the generative model using user feedback, it realizes highly accurate management proposals. In this way, it becomes possible to provide small and medium-sized enterprises with low-cost and highly effective consulting services. 【0006】 "Internal company data" refers to data owned internally by a company that serves as the basis for management decisions, such as financial information, sales information, and customer information. 【0007】 An "external data source" is an information provider that exists outside of a company and provides publicly or commercially available market information, competitive information, economic indicators, and other data. 【0008】 A "generative model" is an artificial intelligence model used to automatically generate specific outputs, i.e., analytical results, based on data from within and outside a company. 【0009】 "Preprocessing" refers to the process of cleaning, shaping, and standardizing data in order to perform analysis in a format suitable for the model. 【0010】 "Financial analysis" is an analytical method that evaluates profitability, soundness, efficiency, etc., based on a company's financial data, and supports management decisions. 【0011】 "Market forecasting" is an analysis that predicts future market trends and needs based on past data and trend information. 【0012】 "Competitive analysis" is an analysis that evaluates the activities and market positions of competitors in the same industry, and is used to formulate strategies for a company to gain a competitive advantage. 【0013】 "Feedback" is the process by which users report the results and evaluations obtained after implementing the proposed business strategy to the system. [Brief explanation of the drawing] 【0014】 [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This 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] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This 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] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14]It is a sequence diagram showing the processing flow of a data processing system in Application Example 2 when a sentiment engine is combined. 【Embodiments for Carrying Out the Invention】 【0015】 Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings. 【0016】 First, the terms used in the following description will be explained. 【0017】 In the following embodiments, a 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 a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like. 【0018】 In the following embodiments, a numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor. 【0019】 In the following embodiments, a numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc. 【0020】 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). 【0021】 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." 【0022】 [First Embodiment] 【0023】 Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment. 【0024】 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. 【0025】 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). 【0026】 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. 【0027】 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. 【0028】 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. 【0029】 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. 【0030】 Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14. 【0031】 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. 【0032】 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. 【0033】 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. 【0034】 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". 【0035】 This invention relates to a management support system that can be easily used by small and medium-sized enterprises, and aims to provide objective analysis results by utilizing data from both inside and outside the company. This system mainly consists of a server, terminals, and a user interface. 【0036】 The server collects and centrally manages corporate data and information from external data sources in real time. The collected data is first pre-processed on the server, including standardization and cleaning. Once pre-processed, the data is analyzed by a generative model. The generative model parametrically analyzes the data and provides insights from different perspectives, such as financial analysis, market forecasting, and competitive analysis. 【0037】 The generated analysis results are presented to the user via a terminal. Based on this information, the user can determine business strategies and policies. Furthermore, by inputting the results of the strategies implemented by the user into the terminal as feedback, the server utilizes the collected feedback to update the generative model. This increases the accuracy of the analysis, enabling more precise business support. 【0038】 As a concrete example, if a small or medium-sized enterprise (SME) is planning to launch a new product, the user inputs existing product data, market trends, and competitor product information. The server then uses this data to run a generative model and recommend target market segments and pricing. Based on these recommendations, the user's performance is evaluated and fed back into the system, allowing for more refined analysis in the future. This feedback loop enables decision-making support that always reflects the latest market information. 【0039】 The following describes the processing flow. 【0040】 Step 1: 【0041】 Users input relevant information, such as company financial data and sales data, into a terminal. This information is sent to a server to form a dataset that will serve as the basis for future analysis. 【0042】 Step 2: 【0043】 The server automatically collects market trends, competitive information, and economic indicators from external data sources. This includes accessing databases using APIs to retrieve the latest information. 【0044】 Step 3: 【0045】 The server performs preprocessing on the collected internal and external corporate data. This preprocessing involves cleaning the data, imputing missing values, and standardizing it to prepare it for the model. 【0046】 Step 4: 【0047】 The server inputs pre-processed data into a generative model. The generative model performs financial analysis, market forecasting, and competitive analysis, ultimately generating analytical results that contribute to business management. 【0048】 Step 5: 【0049】 The server sends the generated analysis results to the terminal. The terminal visualizes these results and displays them in a format that is easy for the user to understand. 【0050】 Step 6: 【0051】 Users make business decisions based on the analysis results and input feedback on the implementation status and results via their terminals. This feedback is sent to the server and used to improve the performance of the generative model. 【0052】 Step 7: 【0053】 The server uses user feedback data to adjust and update the generative model. The model is improved so that more accurate results can be obtained in the next analysis. 【0054】 (Example 1) 【0055】 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." 【0056】 For small and medium-sized enterprises (SMEs), it is crucial to easily collect internal and external data and utilize it for objective analysis in order to make quick and accurate management decisions. However, there is a lack of technical means to efficiently acquire, organize, and provide appropriate analytical results for this data. Furthermore, there is a need to utilize feedback information from the implementation of management strategies and update generation algorithms to make more precise decisions in the future. 【0057】 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. 【0058】 In this invention, the server includes a device for inputting information, a device for automatically acquiring data from external information sources, and a device for performing preliminary processing to prepare the data. This enables centralized management of data both inside and outside the company and efficient preprocessing. Furthermore, by including a device for performing financial evaluations, economic forecasts, and competitor analysis using a generation algorithm, and a device for displaying the generated evaluation results to the user, the user can make management decisions quickly. In addition, by providing a device for collecting user feedback and updating the generation algorithm, improved accuracy in subsequent decisions can be expected. 【0059】 A "device for inputting information" is a function that provides an interface for importing internal company data and external data into a system. 【0060】 A "device that automatically acquires data from external sources" is a system that efficiently collects market information, competitive information, and other data via the internet or other networks. 【0061】 "Devices that perform preliminary processing to prepare data" refer to technologies that provide standardization and cleaning processes to resolve inconsistencies in collected data. 【0062】 A "device that performs financial evaluation, economic forecasting, and competitive analysis using generation algorithms" is a processor that extracts various business insights through algorithms and generates information useful for management. 【0063】 A "device for displaying generated evaluation results to the user" is a device that has a graphical user interface for visually presenting analysis results to the user. 【0064】 A "device that collects user feedback and updates the generation algorithm" is a mechanism that improves the algorithm based on the results of actual business decisions and uses that information for future analysis. 【0065】 This invention is a system for companies to efficiently formulate and execute their business strategies. This system integrates internal and external information and performs analysis using a generative AI model to provide various business insights. 【0066】 The server acts as an input device, acquiring data from internal sales management systems and customer management systems within the company. It also automatically collects data from external sources, such as online databases and market research sites. This process utilizes APIs implemented in programming languages ​​such as Python and Java (registered trademark). 【0067】 The collected data is first processed on the server. This preliminary stage involves data standardization and cleaning. Specifically, this includes imputing missing data and removing outliers. This improves the accuracy of analysis by the generative AI model. 【0068】 The server executes generation algorithms using the prepared data. Analysis includes financial valuation, market forecasting, and competitive analysis. Python libraries such as Pandas and NumPy are applied to the company's financial data, and deep learning models for market forecasting are run using Tensorflow® and PyTorch. 【0069】 The terminal visually presents the analysis results obtained from the server to the user. The graphical user interface is provided by front-end frameworks such as React and Vue.js, and D3.js is used for data visualization. Specifically, sales forecasts are displayed as line graphs, and competitor analysis is displayed as bar graphs. 【0070】 Users make business decisions based on the presented analysis results. For example, when launching a new product, they formulate a strategy based on a prompt from the generating AI model: "Recommend the optimal pricing and market segment for the launch of new product A." The results of implementing this strategy are input into the server as feedback and used for subsequent model updates. This feedback loop improves the accuracy of the generating AI model, enabling decision-making support that always reflects the latest market information. 【0071】 The flow of the specific processing in Example 1 will be explained using Figure 11. 【0072】 Step 1: 【0073】 The server retrieves sales data and customer information from internal company systems as input. It also automatically collects market data and competitor information from external sources. Specifically, the server uses APIs to gather this data and store it in a database. This collected data is then used in the next preprocessing step. 【0074】 Step 2: 【0075】 The server processes the collected data. It converts the raw input data into a standard format and appropriately imputes missing values. Specifically, it manipulates the data frame using Python libraries to detect and remove outliers. The output of this preprocessing is a clean and consistent dataset, which is used as input data for the generative AI model. 【0076】 Step 3: 【0077】 The server runs a generative AI model using preprocessed data. Based on the input data, it performs financial analysis, market forecasting, and competitor research. Specifically, it runs an economic forecasting model using TensorFlow and calculates financial indicators using Pandas. The output is an analysis result containing various business insights. 【0078】 Step 4: 【0079】 The terminal presents the user with the analysis results obtained from the generated AI model. It visualizes the analysis results received as input on a graphical user interface. Specifically, it uses D3.js to display sales forecasts as line graphs and competitor analysis as bar graphs. The output is visualized information to support business decision-making. 【0080】 Step 5: 【0081】 The user formulates a business strategy based on the analysis results presented through the terminal. For example, they act based on a prompt to the generating AI model: "Recommend the optimal pricing and market segment for the market launch of new product A." Based on the information presented as input, they execute the actual business strategy and input the results back into the terminal as formatted data. 【0082】 Step 6: 【0083】 The server receives user feedback as input and updates the generative AI model. It adjusts the model's parameters using past strategy execution results and retrains it with a new dataset. Specifically, it minimizes the model's errors based on the input feedback and improves the accuracy of the next analysis. The output obtained at this stage is a more refined, next-generation generative AI model. 【0084】 (Application Example 1) 【0085】 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." 【0086】 Amidst the growing demand for improved operational efficiency and service quality in care facilities and similar settings, there is a need for a system that can monitor the health status of individual residents in real time and provide prompt and appropriate service recommendations based on that information. However, current systems have challenges in real-time analysis of health status and providing service recommendations optimized for specific individuals. Against this backdrop, there is a need for a system that enables facility operators to make decisions based on accurate information and improve services. 【0087】 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. 【0088】 In this invention, the server includes means for inputting information within a company, means for automatically collecting market data from external information sources, means for pre-processing information to organize it, means for performing economic analysis, market forecasting, and competitive analysis using generative models, means for analyzing information from a device for collecting individual health status in real time, and means for making optimal service suggestions based on individual health status. This enables operators of nursing care facilities to quickly provide optimal care services tailored to the individual health status of each resident. 【0089】 "In-house information" refers to the collective term for data and records generated and stored within a company. 【0090】 "External information sources" refer to information such as market data and industry trends obtained from environments outside the company. 【0091】 "Preprocessing" is a general term for various processes that prepare raw data into an analyzable format. 【0092】 A "generative model" is an algorithm that analyzes patterns and trends based on collected data to provide new insights and predictions. 【0093】 "Economic analysis" is the process of analyzing the financial condition of companies and organizations, as well as market trends, based on economic indicators and data. 【0094】 Market forecasting is the process of analyzing past and present market data to estimate future market trends. 【0095】 "Competitive analysis" is the process of investigating the actions of competitors and their position in the market. 【0096】 "A device for collecting personal health information in real time" refers to equipment or systems that instantly acquire health-related data from individuals. 【0097】 "Means of analyzing information" refers to various methods and techniques for gaining useful insights from acquired data. 【0098】 "Optimal service proposals" refer to the most effective methods of service delivery, designed to meet the specific needs and circumstances of a particular individual. 【0099】 This invention involves a system in which a server plays a central role in efficiently collecting, analyzing, and presenting information from both within and outside a company. First, the server retrieves information from within the company's database and collects market data from external sources via the internet. In this process, Python libraries can be used to automate data collection. 【0100】 The server preprocesses the obtained data using the Python Pandas library to remove noise and standardize it. Data collected from devices that collect personal health information in real time, such as smartwatches and IoT devices, is also integrated. The server then prepares the data and inputs it into the generative model. 【0101】 The generative model utilizes TensorFlow or PyTorch to analyze collected data and provide insights such as economic analysis, market forecasting, and competitive analysis. This model functions as a tool for providing optimal service recommendations based on an individual's health status, visualizing data analysis results and presenting suggestions to the user. 【0102】 The generative model is constantly being improved by inputting the results of the strategies implemented by users as feedback to the server. This feedback loop automatically adjusts the model, further improving the accuracy of the next suggestions. 【0103】 For example, in a nursing home, if data on a resident's body temperature and heart rate is collected and shows values ​​that are different from the normal range, the server immediately uses a generative model to suggest appropriate health checks. Users can then take quick action based on these suggestions. Furthermore, if the strategy is successful, inputting the results into the system further optimizes suggestions for similar situations in the future. 【0104】 An example of a prompt message might be, "Based on the resident's health status data, please create a proposal for necessary care services." This allows the system to generate a readily applicable proposal and support the user's decision-making. 【0105】 The flow of a specific process in Application Example 1 will be explained using Figure 12. 【0106】 Step 1: 【0107】 The server retrieves internal company information from its internal database and collects market data from external sources. It takes authentication information from the internal database and external data via APIs as input. During this process, it extracts information from the database using SQL queries and retrieves market data from the internet via HTTP requests. As output, it generates a set of the retrieved raw data. 【0108】 Step 2: 【0109】 The server preprocesses the raw data obtained using the Pandas library. It uses the raw data obtained from step 1 as input to clean the data. Specifically, it performs data imputation, removes outliers, and standardizes the data. This results in outputting a dataset in a unified format suitable for analysis. 【0110】 Step 3: 【0111】 The server collects personal health data in real time from smartwatches and IoT devices. It uses BLE (Bluetooth Low Energy) as input to obtain feeds from each device. The data is stored row by row in the format of time, heart rate, and body temperature. The server generates a health dataset organized for each individual as output. 【0112】 Step 4: 【0113】 The server uses TensorFlow to analyze pre-processed company information, external market data, and health data using a generative model. The datasets obtained from steps 2 and 3 are used as input. Here, the generative AI model analyzes data patterns and trends, generating economic analysis and service recommendations tailored to individual health conditions. The output includes analysis results and specific service recommendations. 【0114】 Step 5: 【0115】 The system presents the user with suggested analysis results and service information via the terminal. It receives analysis results from the server as input and displays them in a GUI (Graphical User Interface). The user can view the suggestions and make decisions based on the situation. As output, it generates an analysis results screen in a format viewable by the user. 【0116】 Step 6: 【0117】 Based on their own judgment, users input feedback to the server regarding the implementation of their proposals and the results. This feedback includes comments on verification and decisions, as well as selected actions. The server then uses this feedback to improve the accuracy of the generative model in subsequent analyses. The updated generative model is generated as output. This process uses the prompt "Create proposals for necessary care services based on the residents' health status data" to improve the accuracy of the next step. 【0118】 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. 【0119】 This invention relates to a system that combines data analysis functions with an emotion engine, with the aim of supporting business management in companies. The system is configured to recognize user emotions in addition to predictive analysis using corporate data and external information, and to help support business decisions. 【0120】 First, information collected from internal company data and external data sources is input to the server via terminals. The server automatically preprocesses this data, correcting for outliers and normalizing the data. Once preprocessed, the data is analyzed by generative models residing on the server, and financial analysis, market forecasting, and competitive analysis are performed. 【0121】 The analysis results are sent to the user's device, and the emotion engine receives and operates based on this information. The emotion engine recognizes emotions from information such as the user's facial expressions and voice, and adjusts how the results are presented. This process allows the user to receive information in a format optimized for them. The emotion data is sent from the device to the server as feedback after the session and serves as input for data correction in the generative model. 【0122】 As a concrete example, if a company is considering entering a new business field, the user inputs market information, competitor information, and internal company data from a terminal. The server preprocesses the collected data, performs analysis using a generative model, and predicts market trends and competitive strategies. When presenting the analysis results, the emotion engine analyzes the user's reaction, providing more detailed information if the user shows curiosity or excitement, and conversely, concise and easy-to-understand information if the user shows confusion or anxiety. In this way, responses are tailored to the user's emotions, enabling them to make more efficient business decisions. As a result, the feedback data is used to further improve the generative model, allowing the system to provide more accurate support in subsequent analyses. 【0123】 The following describes the processing flow. 【0124】 Step 1: 【0125】 Users input company financial data, sales data, product information, and other data into the terminal. Users can also input external market data and competitor information as needed. 【0126】 Step 2: 【0127】 The terminal sends the entered data to the server. The server retrieves the received data and prepares it for the analysis process. 【0128】 Step 3: 【0129】 The server accesses external data sources to collect market trends and competitor information. It uses external APIs to retrieve the latest data. This data is integrated with internal enterprise data to form a comprehensive dataset. 【0130】 Step 4: 【0131】 The server performs preprocessing on the integrated data. It cleans the data, imputes missing values, and standardizes it to prepare it for the generative model. 【0132】 Step 5: 【0133】 The server inputs pre-processed data into a generative model to perform financial analysis, market forecasting, and competitive analysis. The generative model analyzes each data point and outputs analytical results that contribute to business strategy. 【0134】 Step 6: 【0135】 The server sends the analysis results to the terminal. The terminal displays the results in a user-friendly, visualized format. At this point, the emotion engine is activated and prepares to sense the user's reaction. 【0136】 Step 7: 【0137】 When a user views the analysis results, the emotion engine recognizes the user's facial expressions, tone of voice, and other characteristics. The emotion engine analyzes the emotional data and adjusts the way information is presented based on the user's current state. 【0138】 Step 8: 【0139】 Users make decisions based on the analysis results and input the results and feedback obtained after implementation into their devices. This feedback includes emotionally driven responses. 【0140】 Step 9: 【0141】 The device sends feedback to the server. The server uses the feedback data to update the generative model. This improves the accuracy and sophistication of the next analysis. 【0142】 (Example 2) 【0143】 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." 【0144】 In corporate management decisions, a key challenge is how to effectively utilize vast amounts of internal and external information. In particular, there is a need to integrate diverse data, perform highly accurate analysis, and present the results in a format that is optimal to the manager's needs. However, conventional systems lacked flexibility in data preprocessing and presentation of analysis results, resulting in limitations in their ability to support management decisions. 【0145】 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. 【0146】 In this invention, the server includes means for inputting information within the company, means for automatically collecting market-related information from external sources, means for performing numerical analysis, predictive analysis, and competitive analysis using a generative model, and means for presenting the analysis results to the user and adjusting the presentation content using an emotion engine. This makes it possible to analyze data accurately and quickly and to provide the analysis results in a way that matches the user's emotions. 【0147】 "Internal company information" refers to a variety of information generated within a company, such as sales figures, employee numbers, financial information, and operational data. 【0148】 "External information sources" refer to information obtained from outside the company, such as market reports, news, and publicly available statistics. 【0149】 "Preprocessing" refers to the process of preparing raw data before analysis, and includes operations such as outlier correction and data normalization. 【0150】 A "generative model" refers to a pre-trained algorithm used to analyze input data and perform tasks such as financial analysis, predictive analytics, and competitive analysis. 【0151】 An "emotion engine" refers to a technology that recognizes a user's emotional state from information such as their facial expressions and voice, and adjusts the way the results are presented accordingly. 【0152】 "Feedback" refers to opinions, impressions, and evaluation data obtained from users, and is information used to improve and adjust the system. 【0153】 This invention is a system designed to support corporate management decisions, providing a mechanism for integrating internal corporate information with data from external sources to perform advanced analysis. The system primarily utilizes terminals, servers, and an emotion engine. 【0154】 The terminal first receives internal company information entered by the user and external information collected based on prompt messages. An example of a prompt message might be, "Analyze competitive information and market trends regarding new market entry." The terminal then sends this data to the server. 【0155】 The server preprocesses the received data. This preprocessing includes correcting for data anomalies and normalizing the scale. The preprocessed data is then fed into a trained generative AI model, which performs numerical analysis, predictive analysis, and competitive analysis. This generative AI model is used to analyze large amounts of data and provide predictions and insights. 【0156】 Once the analysis is complete, the data is sent from the server to the user's device. The emotion engine on the device uses the camera and microphone to recognize the user's emotions in real time and dynamically adjusts how the analysis results are presented based on this. For example, if the user shows interest, detailed information is provided; if they show anxiety, simplified information is provided. 【0157】 As a concrete example, when a company using the system wants to understand competitive trends in the technology industry, the user inputs internal data related to their terminal (e.g., historical sales data) and obtains external market information through prompt messages. This information is analyzed on the server, and the results are provided to the user in a format requested by the emotion engine. This enables companies to make more accurate and emotionally responsive business decisions. 【0158】 Thus, the system implementing the present invention effectively and efficiently provides important information in a company's management decision-making process and realizes information presentation optimized for the user. 【0159】 The flow of the specific processing in Example 2 will be explained using Figure 13. 【0160】 Step 1: 【0161】 The user inputs company information and prompt messages into the terminal. In this example, sales data and employee numbers are entered as company information, and the prompt message "Analyze competitive information and market trends regarding new market entry" is used. The terminal receives this data as input and sends it to the server. 【0162】 Step 2: 【0163】 The server begins processing the internal company information and market information received from the terminal as input. First, it performs data anomaly correction, replacing or removing any existing anomalies with appropriate values. Then, it performs data normalization, converting data expressed on different scales to a unified scale. This process yields pre-processed data. 【0164】 Step 3: 【0165】 The server inputs pre-processed data into a generating AI model. The generating AI model analyzes the data and performs financial analysis, market forecasting, and competitive analysis of companies. In this process, it generates future predictions based on patterns and trends identified from the data. The output is information on the analysis results. 【0166】 Step 4: 【0167】 The server sends the generated analysis results to the user's device. The device then activates its built-in emotion engine based on the received analysis results. The emotion engine analyzes the user's emotions in real time using the user's facial recognition camera and voice input function. The method of presenting the analysis results is adjusted based on these emotion recognition results. 【0168】 Step 5: 【0169】 The device utilizes the results of an emotion engine analysis to provide more detailed information if the user shows interest, and present concise information if they show anxiety. This ensures appropriate information is presented. As output, the user receives information that corresponds to their emotions. 【0170】 Step 6: 【0171】 The user inputs feedback on the analysis results into the terminal. This feedback is sent back to the server and used to train the generative AI model. Through this feedback, the accuracy of subsequent analyses is improved. The output is an improved generative AI model. 【0172】 (Application Example 2) 【0173】 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". 【0174】 In modern business management, accurate management decisions based on vast amounts of data are required. While proper management of security risks is crucial, conventional data analysis systems are unable to optimize information presentation based on user emotions. As a result, the user understanding and decision-making processes can become inefficient, and there is a need for solutions to improve this. 【0175】 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. 【0176】 In this invention, the server includes means for inputting data from within the company, means for automatically collecting market information from external data sources, means for pre-processing data to prepare it, means for performing financial analysis, market forecasting, and competitive analysis using a generative model, means for presenting the analysis results to the user, means for analyzing the user's emotions and adjusting the information display, and means for collecting feedback and updating the generative model. This makes it possible to optimize the presentation of information according to the user's emotional state, improving the efficiency and accuracy of management decisions. 【0177】 "Internal company data" refers to information such as statistical data, financial records, and personnel documents that are generated or acquired within a company. 【0178】 "External data sources" refer to information sources that exist outside of a company, providing market trends, competitive information, economic indicators, and so on. 【0179】 "Preprocessing" refers to the process of preparing data for analysis, including correcting for outliers and normalizing the data. 【0180】 A "generative model" is a machine learning model used to analyze economic conditions and competitive landscapes based on data and to make future predictions. 【0181】 "Analysis results" refer to conclusions and suggestions derived from data processed by a generative model. 【0182】 "Means of analyzing user emotions and adjusting information display" refers to technology that recognizes user emotions from facial expressions, voice, etc., and changes the way information is displayed according to that state. 【0183】 "Methods for collecting feedback and updating generative models" refers to the process of gathering user responses and implementation results, and improving the generative model based on that information. 【0184】 The system for realizing this invention integrates and analyzes internal and external corporate data, presenting information based on the user's emotions. First, the terminal securely collects internal corporate data and automatically acquires external market information. The acquired data is sent to a server, where it undergoes preprocessing such as anomaly correction and normalization. The preprocessed data is then analyzed using a generative AI model to perform financial analysis, market forecasting, and competitive landscape predictions. 【0185】 Before sending the analysis results to the terminal, the server uses an emotion engine to analyze the user's facial expressions and voice, and adjusts how information is presented according to their emotional state. For example, if the user shows anxiety, clear and concise information is prioritized, while if they show interest, more detailed and in-depth information is presented. 【0186】 This process utilizes smartphones and tablets as hardware, and employs Python for data analysis, TensorFlow and Keras for generative AI models, and OpenCV for emotion recognition. Feedback information is stored on a server and used to improve the generative model, resulting in more accurate and useful information being provided in subsequent analyses. 【0187】 As a concrete example, consider a case where a company uses this system to manage security risks. The system analyzes the latest threat intelligence and internal security data to assess the risks faced by management. If management requests more details, it will provide detailed information on new countermeasures and industry averages. An example of a prompt message could be: "Based on the latest security threat intelligence, please provide countermeasures to help management decisions. Also, please use user sentiment data to adjust the information display format." 【0188】 The flow of a specific process in Application Example 2 will be explained using Figure 14. 【0189】 Step 1: 【0190】 The terminal collects data within the company and automatically retrieves external market information. This input data includes statistical information, financial data, and market indicators. This data is temporarily stored on the terminal and then transmitted to the server. 【0191】 Step 2: 【0192】 The server performs preprocessing on the received data. This process detects and corrects outliers in the data, as well as normalizing numerical data. As a result of the preprocessing, the data is prepared in a format suitable for analysis. 【0193】 Step 3: 【0194】 Using pre-processed data, an AI model performs analysis. The server conducts financial analysis, market forecasting, and competitive analysis to identify specific risks and opportunities. The analysis results are generated as numerical and text data outputs. 【0195】 Step 4: 【0196】 The analysis results are processed by an emotion engine on the server before being sent to the user's device. The system analyzes the user's provided facial expression images and audio data to detect the user's emotions. Based on the detected emotions, the displayed information and format are optimized. 【0197】 Step 5: 【0198】 The device presents optimized information to the user. The user makes business decisions based on the presented data. User reactions and additional feedback information are collected and used to improve the model later. 【0199】 Step 6: 【0200】 The feedback data is sent to the server and used to further improve the generative model. This ensures that subsequent analyses provide more accurate information that better meets user needs. 【0201】 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. 【0202】 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. 【0203】 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. 【0204】 [Second Embodiment] 【0205】 Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment. 【0206】 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. 【0207】 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). 【0208】 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. 【0209】 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. 【0210】 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). 【0211】 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. 【0212】 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. 【0213】 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. 【0214】 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. 【0215】 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. 【0216】 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". 【0217】 This invention relates to a management support system that can be easily used by small and medium-sized enterprises, and aims to provide objective analysis results by utilizing data from both inside and outside the company. This system mainly consists of a server, terminals, and a user interface. 【0218】 The server collects and centrally manages corporate data and information from external data sources in real time. The collected data is first pre-processed on the server, including standardization and cleaning. Once pre-processed, the data is analyzed by a generative model. The generative model parametrically analyzes the data and provides insights from different perspectives, such as financial analysis, market forecasting, and competitive analysis. 【0219】 The generated analysis results are presented to the user via a terminal. Based on this information, the user can determine business strategies and policies. Furthermore, by inputting the results of the strategies implemented by the user into the terminal as feedback, the server utilizes the collected feedback to update the generative model. This increases the accuracy of the analysis, enabling more precise business support. 【0220】 As a concrete example, if a small or medium-sized enterprise (SME) is planning to launch a new product, the user inputs existing product data, market trends, and competitor product information. The server then uses this data to run a generative model and recommend target market segments and pricing. Based on these recommendations, the user's performance is evaluated and fed back into the system, allowing for more refined analysis in the future. This feedback loop enables decision-making support that always reflects the latest market information. 【0221】 The following describes the processing flow. 【0222】 Step 1: 【0223】 Users input relevant information, such as company financial data and sales data, into a terminal. This information is sent to a server to form a dataset that will serve as the basis for future analysis. 【0224】 Step 2: 【0225】 The server automatically collects market trends, competitive information, and economic indicators from external data sources. This includes accessing databases using APIs to retrieve the latest information. 【0226】 Step 3: 【0227】 The server performs preprocessing on the collected internal and external corporate data. This preprocessing involves cleaning the data, imputing missing values, and standardizing it to prepare it for the model. 【0228】 Step 4: 【0229】 The server inputs pre-processed data into a generative model. The generative model performs financial analysis, market forecasting, and competitive analysis, ultimately generating analytical results that contribute to business management. 【0230】 Step 5: 【0231】 The server sends the generated analysis results to the terminal. The terminal visualizes these results and displays them in a format that is easy for the user to understand. 【0232】 Step 6: 【0233】 Users make business decisions based on the analysis results and input feedback on the implementation status and results via their terminals. This feedback is sent to the server and used to improve the performance of the generative model. 【0234】 Step 7: 【0235】 The server uses user feedback data to adjust and update the generative model. The model is improved so that more accurate results can be obtained in the next analysis. 【0236】 (Example 1) 【0237】 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." 【0238】 For small and medium-sized enterprises (SMEs), it is crucial to easily collect internal and external data and utilize it for objective analysis in order to make quick and accurate management decisions. However, there is a lack of technical means to efficiently acquire, organize, and provide appropriate analytical results for this data. Furthermore, there is a need to utilize feedback information from the implementation of management strategies and update generation algorithms to make more precise decisions in the future. 【0239】 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. 【0240】 In this invention, the server includes a device for inputting information, a device for automatically acquiring data from external information sources, and a device for performing preliminary processing to prepare the data. This enables centralized management of data both inside and outside the company and efficient preprocessing. Furthermore, by including a device for performing financial evaluations, economic forecasts, and competitor analysis using a generation algorithm, and a device for displaying the generated evaluation results to the user, the user can make management decisions quickly. In addition, by providing a device for collecting user feedback and updating the generation algorithm, improved accuracy in subsequent decisions can be expected. 【0241】 A "device for inputting information" is a function that provides an interface for importing internal company data and external data into a system. 【0242】 A "device that automatically acquires data from external sources" is a system that efficiently collects market information, competitive information, and other data via the internet or other networks. 【0243】 "Devices that perform preliminary processing to prepare data" refer to technologies that provide standardization and cleaning processes to resolve inconsistencies in collected data. 【0244】 A "device that performs financial evaluation, economic forecasting, and competitive analysis using generation algorithms" is a processor that extracts various business insights through algorithms and generates information useful for management. 【0245】 A "device for displaying generated evaluation results to the user" is a device that has a graphical user interface for visually presenting analysis results to the user. 【0246】 A "device that collects user feedback and updates the generation algorithm" is a mechanism that improves the algorithm based on the results of actual business decisions and uses that information for future analysis. 【0247】 This invention is a system for companies to efficiently formulate and execute their business strategies. This system integrates internal and external information and performs analysis using a generative AI model to provide various business insights. 【0248】 The server acts as an input device, acquiring data from internal sales management systems and customer management systems within the company. It also automatically collects data from external sources, such as online databases and market research sites. This process utilizes APIs implemented in programming languages ​​such as Python and Java. 【0249】 The collected data is first processed on the server. This preliminary stage involves data standardization and cleaning. Specifically, this includes imputing missing data and removing outliers. This improves the accuracy of analysis by the generative AI model. 【0250】 The server executes generative algorithms using the prepared data. Analysis includes financial valuation, market forecasting, and competitive analysis. Python libraries such as Pandas and NumPy are applied to the company's financial data, and deep learning models for market forecasting are run using TensorFlow and PyTorch. 【0251】 The terminal visually presents the analysis results obtained from the server to the user. The graphical user interface is provided by front-end frameworks such as React and Vue.js, and D3.js is used for data visualization. Specifically, sales forecasts are displayed as line graphs, and competitor analysis is displayed as bar graphs. 【0252】 Users make business decisions based on the presented analysis results. For example, when launching a new product, they formulate a strategy based on a prompt from the generating AI model: "Recommend the optimal pricing and market segment for the launch of new product A." The results of implementing this strategy are input into the server as feedback and used for subsequent model updates. This feedback loop improves the accuracy of the generating AI model, enabling decision-making support that always reflects the latest market information. 【0253】 The flow of the specific processing in Example 1 will be explained using Figure 11. 【0254】 Step 1: 【0255】 The server retrieves sales data and customer information from internal company systems as input. It also automatically collects market data and competitor information from external sources. Specifically, the server uses APIs to gather this data and store it in a database. This collected data is then used in the next preprocessing step. 【0256】 Step 2: 【0257】 The server processes the collected data. It converts the raw input data into a standard format and appropriately imputes missing values. Specifically, it manipulates the data frame using Python libraries to detect and remove outliers. The output of this preprocessing is a clean and consistent dataset, which is used as input data for the generative AI model. 【0258】 Step 3: 【0259】 The server runs a generative AI model using preprocessed data. Based on the input data, it performs financial analysis, market forecasting, and competitor research. Specifically, it runs an economic forecasting model using TensorFlow and calculates financial indicators using Pandas. The output is an analysis result containing various business insights. 【0260】 Step 4: 【0261】 The terminal presents the user with the analysis results obtained from the generated AI model. It visualizes the analysis results received as input on a graphical user interface. Specifically, it uses D3.js to display sales forecasts as line graphs and competitor analysis as bar graphs. The output is visualized information to support business decision-making. 【0262】 Step 5: 【0263】 The user formulates a business strategy based on the analysis results presented through the terminal. For example, they act based on a prompt to the generating AI model: "Recommend the optimal pricing and market segment for the market launch of new product A." Based on the information presented as input, they execute the actual business strategy and input the results back into the terminal as formatted data. 【0264】 Step 6: 【0265】 The server receives user feedback as input and updates the generative AI model. It adjusts the model's parameters using past strategy execution results and retrains it with a new dataset. Specifically, it minimizes the model's errors based on the input feedback and improves the accuracy of the next analysis. The output obtained at this stage is a more refined, next-generation generative AI model. 【0266】 (Application Example 1) 【0267】 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." 【0268】 Amidst the growing demand for improved operational efficiency and service quality in care facilities and similar settings, there is a need for a system that can monitor the health status of individual residents in real time and provide prompt and appropriate service recommendations based on that information. However, current systems have challenges in real-time analysis of health status and providing service recommendations optimized for specific individuals. Against this backdrop, there is a need for a system that enables facility operators to make decisions based on accurate information and improve services. 【0269】 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. 【0270】 In this invention, the server includes means for inputting information within a company, means for automatically collecting market data from external information sources, means for pre-processing information to organize it, means for performing economic analysis, market forecasting, and competitive analysis using generative models, means for analyzing information from a device for collecting individual health status in real time, and means for making optimal service suggestions based on individual health status. This enables operators of nursing care facilities to quickly provide optimal care services tailored to the individual health status of each resident. 【0271】 "In-house information" refers to the collective term for data and records generated and stored within a company. 【0272】 "External information sources" refer to information such as market data and industry trends obtained from environments outside the company. 【0273】 "Preprocessing" is a general term for various processes that prepare raw data into an analyzable format. 【0274】 A "generative model" is an algorithm that analyzes patterns and trends based on collected data to provide new insights and predictions. 【0275】 "Economic analysis" is the process of analyzing the financial condition of companies and organizations, as well as market trends, based on economic indicators and data. 【0276】 Market forecasting is the process of analyzing past and present market data to estimate future market trends. 【0277】 "Competitive analysis" is the process of investigating the actions of competitors and their position in the market. 【0278】 "A device for collecting personal health information in real time" refers to equipment or systems that instantly acquire health-related data from individuals. 【0279】 "Means of analyzing information" refers to various methods and techniques for gaining useful insights from acquired data. 【0280】 "Optimal service proposals" refer to the most effective methods of service delivery, designed to meet the specific needs and circumstances of a particular individual. 【0281】 This invention involves a system in which a server plays a central role in efficiently collecting, analyzing, and presenting information from both within and outside a company. First, the server retrieves information from within the company's database and collects market data from external sources via the internet. In this process, Python libraries can be used to automate data collection. 【0282】 The server preprocesses the obtained data using the Pandas library in Python to remove noise and perform standardization. Data collected from devices for real-time collection of personal health status, such as smartwatches and IoT devices, is also integrated. Thereby, the server organizes the data and inputs it into the generation model. 【0283】 By using TensorFlow or PyTorch for the generation model, the collected data is analyzed to provide insights such as economic analysis, market prediction, and competitive analysis. This model functions as a tool for making optimal service proposals based on an individual's health status, and plays a role in visualizing the data analysis results and presenting proposals to the user. 【0284】 The generation model is continuously improved by inputting the results of the strategies implemented by the user as feedback to the server. This feedback loop automatically adjusts the model to further improve the accuracy of the next proposal. 【0285】 For example, in a nursing facility, if data on the body temperature and heart rate of a certain resident is collected and shows values different from normal, the server immediately utilizes the generation model to make an appropriate health check proposal. The user can respond promptly based on this proposal. Also, if the strategy is successful, by inputting the result into the system, the next proposal in a similar situation will be further optimized. 【0286】 As an example of a prompt sentence, an input such as "Please create a proposal for the necessary nursing services based on the health status data of the resident." can be considered. Thereby, the system generates a proposal that can be immediately responded to and serves to support the user's judgment. 【0287】 The flow of the specific process in Application Example 1 will be described using FIG. 12. 【0288】 Step 1: 【0289】 The server retrieves internal company information from its internal database and collects market data from external sources. It takes authentication information from the internal database and external data via APIs as input. During this process, it extracts information from the database using SQL queries and retrieves market data from the internet via HTTP requests. As output, it generates a set of the retrieved raw data. 【0290】 Step 2: 【0291】 The server preprocesses the raw data obtained using the Pandas library. It uses the raw data obtained from step 1 as input to clean the data. Specifically, it performs data imputation, removes outliers, and standardizes the data. This results in outputting a dataset in a unified format suitable for analysis. 【0292】 Step 3: 【0293】 The server collects personal health data in real time from smartwatches and IoT devices. It uses BLE (Bluetooth Low Energy) as input to obtain feeds from each device. The data is stored row by row in the format of time, heart rate, and body temperature. The server generates a health dataset organized for each individual as output. 【0294】 Step 4: 【0295】 The server uses TensorFlow to analyze pre-processed company information, external market data, and health data using a generative model. The datasets obtained from steps 2 and 3 are used as input. Here, the generative AI model analyzes data patterns and trends, generating economic analysis and service recommendations tailored to individual health conditions. The output includes analysis results and specific service recommendations. 【0296】 Step 5: 【0297】 The system presents the user with suggested analysis results and service information via the terminal. It receives analysis results from the server as input and displays them in a GUI (Graphical User Interface). The user can view the suggestions and make decisions based on the situation. As output, it generates an analysis results screen in a format viewable by the user. 【0298】 Step 6: 【0299】 Based on their own judgment, users input feedback to the server regarding the implementation of their proposals and the results. This feedback includes comments on verification and decisions, as well as selected actions. The server then uses this feedback to improve the accuracy of the generative model in subsequent analyses. The updated generative model is generated as output. This process uses the prompt "Create proposals for necessary care services based on the residents' health status data" to improve the accuracy of the next step. 【0300】 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. 【0301】 This invention relates to a system that combines data analysis functions with an emotion engine, with the aim of supporting business management in companies. The system is configured to recognize user emotions in addition to predictive analysis using corporate data and external information, and to help support business decisions. 【0302】 First, information collected from internal company data and external data sources is input to the server via terminals. The server automatically preprocesses this data, correcting for outliers and normalizing the data. Once preprocessed, the data is analyzed by generative models residing on the server, and financial analysis, market forecasting, and competitive analysis are performed. 【0303】 The analysis results are sent to the user's terminal, and the emotion engine operates based on this. The emotion engine recognizes emotions from information such as the user's expression and voice, and adjusts the way of presenting the results. Through this process, the user can receive information in a form optimized for themselves. The emotion data is sent from the terminal to the server as feedback after implementation, and serves as input for data correction in the generation model. 【0304】 As a specific example, when a certain company is considering entering a new business field, the user inputs market information, competitive information, and the company's internal data from the terminal. The server preprocesses the collected data, analyzes it using the generation model, and predicts market trends and competitive strategies. When presenting the analysis results, the emotion engine analyzes the user's reaction and provides more detailed information when showing curiosity or excitement, and concise and easy-to-understand information when showing confusion or anxiety instead. By making responses according to emotions in this way, the user can make business judgments more efficiently. As a result, the feedback data is used for further improvement of the generation model, and the system can provide more accurate support even in subsequent analyses. 【0305】 The following describes the processing flow. 【0306】 Step 1: 【0307】 The user inputs the company's financial data, sales data, product information, etc. into the terminal. The user can also input external market data and competitive information as needed. 【0308】 Step 2: 【0309】 The terminal sends the input data to the server. The server acquires the received data and prepares for the analysis process. 【0310】 Step 3: 【0311】 The server accesses external data sources to collect market trends and competitor information. It uses external APIs to retrieve the latest data. This data is integrated with internal enterprise data to form a comprehensive dataset. 【0312】 Step 4: 【0313】 The server performs preprocessing on the integrated data. It cleans the data, imputes missing values, and standardizes it to prepare it for the generative model. 【0314】 Step 5: 【0315】 The server inputs pre-processed data into a generative model to perform financial analysis, market forecasting, and competitive analysis. The generative model analyzes each data point and outputs analytical results that contribute to business strategy. 【0316】 Step 6: 【0317】 The server sends the analysis results to the terminal. The terminal displays the results in a user-friendly, visualized format. At this point, the emotion engine is activated and prepares to sense the user's reaction. 【0318】 Step 7: 【0319】 When a user views the analysis results, the emotion engine recognizes the user's facial expressions, tone of voice, and other characteristics. The emotion engine analyzes the emotional data and adjusts the way information is presented based on the user's current state. 【0320】 Step 8: 【0321】 Users make decisions based on the analysis results and input the results and feedback obtained after implementation into their devices. This feedback includes emotionally driven responses. 【0322】 Step 9: 【0323】 The device sends feedback to the server. The server uses the feedback data to update the generative model. This improves the accuracy and sophistication of the next analysis. 【0324】 (Example 2) 【0325】 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". 【0326】 In corporate management decisions, a key challenge is how to effectively utilize vast amounts of internal and external information. In particular, there is a need to integrate diverse data, perform highly accurate analysis, and present the results in a format that is optimal to the manager's needs. However, conventional systems lacked flexibility in data preprocessing and presentation of analysis results, resulting in limitations in their ability to support management decisions. 【0327】 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. 【0328】 In this invention, the server includes means for inputting information within the company, means for automatically collecting market-related information from external sources, means for performing numerical analysis, predictive analysis, and competitive analysis using a generative model, and means for presenting the analysis results to the user and adjusting the presentation content using an emotion engine. This makes it possible to analyze data accurately and quickly and to provide the analysis results in a way that matches the user's emotions. 【0329】 "Internal company information" refers to a variety of information generated within a company, such as sales figures, employee numbers, financial information, and operational data. 【0330】 "External information sources" refer to information obtained from outside the company, such as market reports, news, and publicly available statistics. 【0331】 "Preprocessing" refers to the process of preparing raw data before analysis, and includes operations such as outlier correction and data normalization. 【0332】 A "generative model" refers to a pre-trained algorithm used to analyze input data and perform tasks such as financial analysis, predictive analytics, and competitive analysis. 【0333】 An "emotion engine" refers to a technology that recognizes a user's emotional state from information such as their facial expressions and voice, and adjusts the way the results are presented accordingly. 【0334】 "Feedback" refers to opinions, impressions, and evaluation data obtained from users, and is information used to improve and adjust the system. 【0335】 This invention is a system designed to support corporate management decisions, providing a mechanism for integrating internal corporate information with data from external sources to perform advanced analysis. The system primarily utilizes terminals, servers, and an emotion engine. 【0336】 The terminal first receives internal company information entered by the user and external information collected based on prompt messages. An example of a prompt message might be, "Analyze competitive information and market trends regarding new market entry." The terminal then sends this data to the server. 【0337】 The server preprocesses the received data. This preprocessing includes correcting for data anomalies and normalizing the scale. The preprocessed data is then fed into a trained generative AI model, which performs numerical analysis, predictive analysis, and competitive analysis. This generative AI model is used to analyze large amounts of data and provide predictions and insights. 【0338】 Once the analysis is complete, the data is sent from the server to the user's device. The emotion engine on the device uses the camera and microphone to recognize the user's emotions in real time and dynamically adjusts how the analysis results are presented based on this. For example, if the user shows interest, detailed information is provided; if they show anxiety, simplified information is provided. 【0339】 As a concrete example, when a company using the system wants to understand competitive trends in the technology industry, the user inputs internal data related to their terminal (e.g., historical sales data) and obtains external market information through prompt messages. This information is analyzed on the server, and the results are provided to the user in a format requested by the emotion engine. This enables companies to make more accurate and emotionally responsive business decisions. 【0340】 Thus, the system implementing the present invention effectively and efficiently provides important information in a company's management decision-making process and realizes information presentation optimized for the user. 【0341】 The flow of the specific processing in Example 2 will be explained using Figure 13. 【0342】 Step 1: 【0343】 The user inputs company information and prompt messages into the terminal. In this example, sales data and employee numbers are entered as company information, and the prompt message "Analyze competitive information and market trends regarding new market entry" is used. The terminal receives this data as input and sends it to the server. 【0344】 Step 2: 【0345】 The server begins processing the internal company information and market information received from the terminal as input. First, it performs data anomaly correction, replacing or removing any existing anomalies with appropriate values. Then, it performs data normalization, converting data expressed on different scales to a unified scale. This process yields pre-processed data. 【0346】 Step 3: 【0347】 The server inputs pre-processed data into a generating AI model. The generating AI model analyzes the data and performs financial analysis, market forecasting, and competitive analysis of companies. In this process, it generates future predictions based on patterns and trends identified from the data. The output is information on the analysis results. 【0348】 Step 4: 【0349】 The server sends the generated analysis results to the user's device. The device then activates its built-in emotion engine based on the received analysis results. The emotion engine analyzes the user's emotions in real time using the user's facial recognition camera and voice input function. The method of presenting the analysis results is adjusted based on these emotion recognition results. 【0350】 Step 5: 【0351】 The device utilizes the results of an emotion engine analysis to provide more detailed information if the user shows interest, and present concise information if they show anxiety. This ensures appropriate information is presented. As output, the user receives information that corresponds to their emotions. 【0352】 Step 6: 【0353】 The user inputs feedback on the analysis results into the terminal. This feedback is sent back to the server and used to train the generative AI model. Through this feedback, the accuracy of subsequent analyses is improved. The output is an improved generative AI model. 【0354】 (Application Example 2) 【0355】 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." 【0356】 In modern business management, accurate management decisions based on vast amounts of data are required. While proper management of security risks is crucial, conventional data analysis systems are unable to optimize information presentation based on user emotions. As a result, the user understanding and decision-making processes can become inefficient, and there is a need for solutions to improve this. 【0357】 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. 【0358】 In this invention, the server includes means for inputting data from within the company, means for automatically collecting market information from external data sources, means for pre-processing data to prepare it, means for performing financial analysis, market forecasting, and competitive analysis using a generative model, means for presenting the analysis results to the user, means for analyzing the user's emotions and adjusting the information display, and means for collecting feedback and updating the generative model. This makes it possible to optimize the presentation of information according to the user's emotional state, improving the efficiency and accuracy of management decisions. 【0359】 "Internal company data" refers to information such as statistical data, financial records, and personnel documents that are generated or acquired within a company. 【0360】 "External data sources" refer to information sources that exist outside of a company, providing market trends, competitive information, economic indicators, and so on. 【0361】 "Preprocessing" refers to the process of preparing data for analysis, including correcting for outliers and normalizing the data. 【0362】 A "generative model" is a machine learning model used to analyze economic conditions and competitive landscapes based on data and to make future predictions. 【0363】 "Analysis results" refer to conclusions and suggestions derived from data processed by a generative model. 【0364】 "Means of analyzing user emotions and adjusting information display" refers to technology that recognizes user emotions from facial expressions, voice, etc., and changes the way information is displayed according to that state. 【0365】 "Methods for collecting feedback and updating generative models" refers to the process of gathering user responses and implementation results, and improving the generative model based on that information. 【0366】 The system for realizing this invention integrates and analyzes internal and external corporate data, presenting information based on the user's emotions. First, the terminal securely collects internal corporate data and automatically acquires external market information. The acquired data is sent to a server, where it undergoes preprocessing such as anomaly correction and normalization. The preprocessed data is then analyzed using a generative AI model to perform financial analysis, market forecasting, and competitive landscape predictions. 【0367】 Before sending the analysis results to the terminal, the server uses an emotion engine to analyze the user's facial expressions and voice, and adjusts how information is presented according to their emotional state. For example, if the user shows anxiety, clear and concise information is prioritized, while if they show interest, more detailed and in-depth information is presented. 【0368】 This process utilizes smartphones and tablets as hardware, and employs Python for data analysis, TensorFlow and Keras for generative AI models, and OpenCV for emotion recognition. Feedback information is stored on a server and used to improve the generative model, resulting in more accurate and useful information being provided in subsequent analyses. 【0369】 As a concrete example, consider a case where a company uses this system to manage security risks. The system analyzes the latest threat intelligence and internal security data to assess the risks faced by management. If management requests more details, it will provide detailed information on new countermeasures and industry averages. An example of a prompt message could be: "Based on the latest security threat intelligence, please provide countermeasures to help management decisions. Also, please use user sentiment data to adjust the information display format." 【0370】 The flow of a specific process in Application Example 2 will be explained using Figure 14. 【0371】 Step 1: 【0372】 The terminal collects data within the company and automatically retrieves external market information. This input data includes statistical information, financial data, and market indicators. This data is temporarily stored on the terminal and then transmitted to the server. 【0373】 Step 2: 【0374】 The server performs preprocessing on the received data. This process detects and corrects outliers in the data, as well as normalizing numerical data. As a result of the preprocessing, the data is prepared in a format suitable for analysis. 【0375】 Step 3: 【0376】 Using pre-processed data, an AI model performs analysis. The server conducts financial analysis, market forecasting, and competitive analysis to identify specific risks and opportunities. The analysis results are generated as numerical and text data outputs. 【0377】 Step 4: 【0378】 The analysis results are processed by an emotion engine on the server before being sent to the user's device. The system analyzes the user's provided facial expression images and audio data to detect the user's emotions. Based on the detected emotions, the displayed information and format are optimized. 【0379】 Step 5: 【0380】 The device presents optimized information to the user. The user makes business decisions based on the presented data. User reactions and additional feedback information are collected and used to improve the model later. 【0381】 Step 6: 【0382】 The feedback data is sent to the server and used to further improve the generative model. This ensures that subsequent analyses provide more accurate information that better meets user needs. 【0383】 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. 【0384】 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. 【0385】 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. 【0386】 [Third Embodiment] 【0387】 Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment. 【0388】 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. 【0389】 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). 【0390】 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. 【0391】 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. 【0392】 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). 【0393】 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. 【0394】 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. 【0395】 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. 【0396】 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. 【0397】 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. 【0398】 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". 【0399】 This invention relates to a management support system that can be easily used by small and medium-sized enterprises, and aims to provide objective analysis results by utilizing data from both inside and outside the company. This system mainly consists of a server, terminals, and a user interface. 【0400】 The server collects and centrally manages corporate data and information from external data sources in real time. The collected data is first pre-processed on the server, including standardization and cleaning. Once pre-processed, the data is analyzed by a generative model. The generative model parametrically analyzes the data and provides insights from different perspectives, such as financial analysis, market forecasting, and competitive analysis. 【0401】 The generated analysis results are presented to the user via a terminal. Based on this information, the user can determine business strategies and policies. Furthermore, by inputting the results of the strategies implemented by the user into the terminal as feedback, the server utilizes the collected feedback to update the generative model. This increases the accuracy of the analysis, enabling more precise business support. 【0402】 As a concrete example, if a small or medium-sized enterprise (SME) is planning to launch a new product, the user inputs existing product data, market trends, and competitor product information. The server then uses this data to run a generative model and recommend target market segments and pricing. Based on these recommendations, the user's performance is evaluated and fed back into the system, allowing for more refined analysis in the future. This feedback loop enables decision-making support that always reflects the latest market information. 【0403】 The following describes the processing flow. 【0404】 Step 1: 【0405】 Users input relevant information, such as company financial data and sales data, into a terminal. This information is sent to a server to form a dataset that will serve as the basis for future analysis. 【0406】 Step 2: 【0407】 The server automatically collects market trends, competitive information, and economic indicators from external data sources. This includes accessing databases using APIs to retrieve the latest information. 【0408】 Step 3: 【0409】 The server performs preprocessing on the collected internal and external corporate data. This preprocessing involves cleaning the data, imputing missing values, and standardizing it to prepare it for the model. 【0410】 Step 4: 【0411】 The server inputs pre-processed data into a generative model. The generative model performs financial analysis, market forecasting, and competitive analysis, ultimately generating analytical results that contribute to business management. 【0412】 Step 5: 【0413】 The server sends the generated analysis results to the terminal. The terminal visualizes these results and displays them in a format that is easy for the user to understand. 【0414】 Step 6: 【0415】 Users make business decisions based on the analysis results and input feedback on the implementation status and results via their terminals. This feedback is sent to the server and used to improve the performance of the generative model. 【0416】 Step 7: 【0417】 The server uses user feedback data to adjust and update the generative model. The model is improved so that more accurate results can be obtained in the next analysis. 【0418】 (Example 1) 【0419】 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." 【0420】 For small and medium-sized enterprises (SMEs), it is crucial to easily collect internal and external data and utilize it for objective analysis in order to make quick and accurate management decisions. However, there is a lack of technical means to efficiently acquire, organize, and provide appropriate analytical results for this data. Furthermore, there is a need to utilize feedback information from the implementation of management strategies and update generation algorithms to make more precise decisions in the future. 【0421】 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. 【0422】 In this invention, the server includes a device for inputting information, a device for automatically acquiring data from external information sources, and a device for performing preliminary processing to prepare the data. This enables centralized management of data both inside and outside the company and efficient preprocessing. Furthermore, by including a device for performing financial evaluations, economic forecasts, and competitor analysis using a generation algorithm, and a device for displaying the generated evaluation results to the user, the user can make management decisions quickly. In addition, by providing a device for collecting user feedback and updating the generation algorithm, improved accuracy in subsequent decisions can be expected. 【0423】 A "device for inputting information" is a function that provides an interface for importing internal company data and external data into a system. 【0424】 A "device that automatically acquires data from external sources" is a system that efficiently collects market information, competitive information, and other data via the internet or other networks. 【0425】 "Devices that perform preliminary processing to prepare data" refer to technologies that provide standardization and cleaning processes to resolve inconsistencies in collected data. 【0426】 A "device that performs financial evaluation, economic forecasting, and competitive analysis using generation algorithms" is a processor that extracts various business insights through algorithms and generates information useful for management. 【0427】 A "device for displaying generated evaluation results to the user" is a device that has a graphical user interface for visually presenting analysis results to the user. 【0428】 A "device that collects user feedback and updates the generation algorithm" is a mechanism that improves the algorithm based on the results of actual business decisions and uses that information for future analysis. 【0429】 This invention is a system for companies to efficiently formulate and execute their business strategies. This system integrates internal and external information and performs analysis using a generative AI model to provide various business insights. 【0430】 The server acts as an input device, acquiring data from internal sales management systems and customer management systems within the company. It also automatically collects data from external sources, such as online databases and market research sites. This process utilizes APIs implemented in programming languages ​​such as Python and Java. 【0431】 The collected data is first processed on the server. This preliminary stage involves data standardization and cleaning. Specifically, this includes imputing missing data and removing outliers. This improves the accuracy of analysis by the generative AI model. 【0432】 The server executes generative algorithms using the prepared data. Analysis includes financial valuation, market forecasting, and competitive analysis. Python libraries such as Pandas and NumPy are applied to the company's financial data, and deep learning models for market forecasting are run using TensorFlow and PyTorch. 【0433】 The terminal visually presents the analysis results obtained from the server to the user. The graphical user interface is provided by front-end frameworks such as React and Vue.js, and D3.js is used for data visualization. Specifically, sales forecasts are displayed as line graphs, and competitor analysis is displayed as bar graphs. 【0434】 Users make business decisions based on the presented analysis results. For example, when launching a new product, they formulate a strategy based on a prompt from the generating AI model: "Recommend the optimal pricing and market segment for the launch of new product A." The results of implementing this strategy are input into the server as feedback and used for subsequent model updates. This feedback loop improves the accuracy of the generating AI model, enabling decision-making support that always reflects the latest market information. 【0435】 The flow of the specific processing in Example 1 will be explained using Figure 11. 【0436】 Step 1: 【0437】 The server retrieves sales data and customer information from internal company systems as input. It also automatically collects market data and competitor information from external sources. Specifically, the server uses APIs to gather this data and store it in a database. This collected data is then used in the next preprocessing step. 【0438】 Step 2: 【0439】 The server processes the collected data. It converts the raw input data into a standard format and appropriately imputes missing values. Specifically, it manipulates the data frame using Python libraries to detect and remove outliers. The output of this preprocessing is a clean and consistent dataset, which is used as input data for the generative AI model. 【0440】 Step 3: 【0441】 The server runs a generative AI model using preprocessed data. Based on the input data, it performs financial analysis, market forecasting, and competitor research. Specifically, it runs an economic forecasting model using TensorFlow and calculates financial indicators using Pandas. The output is an analysis result containing various business insights. 【0442】 Step 4: 【0443】 The terminal presents the user with the analysis results obtained from the generated AI model. It visualizes the analysis results received as input on a graphical user interface. Specifically, it uses D3.js to display sales forecasts as line graphs and competitor analysis as bar graphs. The output is visualized information to support business decision-making. 【0444】 Step 5: 【0445】 The user formulates a business strategy based on the analysis results presented through the terminal. For example, they act based on a prompt to the generating AI model: "Recommend the optimal pricing and market segment for the market launch of new product A." Based on the information presented as input, they execute the actual business strategy and input the results back into the terminal as formatted data. 【0446】 Step 6: 【0447】 The server receives user feedback as input and updates the generative AI model. It adjusts the model's parameters using past strategy execution results and retrains it with a new dataset. Specifically, it minimizes the model's errors based on the input feedback and improves the accuracy of the next analysis. The output obtained at this stage is a more refined, next-generation generative AI model. 【0448】 (Application Example 1) 【0449】 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." 【0450】 Amidst the growing demand for improved operational efficiency and service quality in care facilities and similar settings, there is a need for a system that can monitor the health status of individual residents in real time and provide prompt and appropriate service recommendations based on that information. However, current systems have challenges in real-time analysis of health status and providing service recommendations optimized for specific individuals. Against this backdrop, there is a need for a system that enables facility operators to make decisions based on accurate information and improve services. 【0451】 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. 【0452】 In this invention, the server includes means for inputting information within a company, means for automatically collecting market data from external information sources, means for pre-processing information to organize it, means for performing economic analysis, market forecasting, and competitive analysis using generative models, means for analyzing information from a device for collecting individual health status in real time, and means for making optimal service suggestions based on individual health status. This enables operators of nursing care facilities to quickly provide optimal care services tailored to the individual health status of each resident. 【0453】 "In-house information" refers to the collective term for data and records generated and stored within a company. 【0454】 "External information sources" refer to information such as market data and industry trends obtained from environments outside the company. 【0455】 "Preprocessing" is a general term for various processes that prepare raw data into an analyzable format. 【0456】 A "generative model" is an algorithm that analyzes patterns and trends based on collected data to provide new insights and predictions. 【0457】 "Economic analysis" is the process of analyzing the financial condition of companies and organizations, as well as market trends, based on economic indicators and data. 【0458】 Market forecasting is the process of analyzing past and present market data to estimate future market trends. 【0459】 "Competitive analysis" is the process of investigating the actions of competitors and their position in the market. 【0460】 "A device for collecting personal health information in real time" refers to equipment or systems that instantly acquire health-related data from individuals. 【0461】 "Means of analyzing information" refers to various methods and techniques for gaining useful insights from acquired data. 【0462】 "Optimal service proposals" refer to the most effective methods of service delivery, designed to meet the specific needs and circumstances of a particular individual. 【0463】 This invention involves a system in which a server plays a central role in efficiently collecting, analyzing, and presenting information from both within and outside a company. First, the server retrieves information from within the company's database and collects market data from external sources via the internet. In this process, Python libraries can be used to automate data collection. 【0464】 The server preprocesses the obtained data using the Python Pandas library to remove noise and standardize it. Data collected from devices that collect personal health information in real time, such as smartwatches and IoT devices, is also integrated. The server then prepares the data and inputs it into the generative model. 【0465】 The generative model utilizes TensorFlow or PyTorch to analyze collected data and provide insights such as economic analysis, market forecasting, and competitive analysis. This model functions as a tool for providing optimal service recommendations based on an individual's health status, visualizing data analysis results and presenting suggestions to the user. 【0466】 The generative model is constantly being improved by inputting the results of the strategies implemented by users as feedback to the server. This feedback loop automatically adjusts the model, further improving the accuracy of the next suggestions. 【0467】 For example, in a nursing home, if data on a resident's body temperature and heart rate is collected and shows values ​​that are different from the normal range, the server immediately uses a generative model to suggest appropriate health checks. Users can then take quick action based on these suggestions. Furthermore, if the strategy is successful, inputting the results into the system further optimizes suggestions for similar situations in the future. 【0468】 An example of a prompt message might be, "Based on the resident's health status data, please create a proposal for necessary care services." This allows the system to generate a readily applicable proposal and support the user's decision-making. 【0469】 The flow of a specific process in Application Example 1 will be explained using Figure 12. 【0470】 Step 1: 【0471】 The server retrieves internal company information from its internal database and collects market data from external sources. It takes authentication information from the internal database and external data via APIs as input. During this process, it extracts information from the database using SQL queries and retrieves market data from the internet via HTTP requests. As output, it generates a set of the retrieved raw data. 【0472】 Step 2: 【0473】 The server preprocesses the raw data obtained using the Pandas library. It uses the raw data obtained from step 1 as input to clean the data. Specifically, it performs data imputation, removes outliers, and standardizes the data. This results in outputting a dataset in a unified format suitable for analysis. 【0474】 Step 3: 【0475】 The server collects personal health data in real time from smartwatches and IoT devices. It uses BLE (Bluetooth Low Energy) as input to obtain feeds from each device. The data is stored row by row in the format of time, heart rate, and body temperature. The server generates a health dataset organized for each individual as output. 【0476】 Step 4: 【0477】 The server uses TensorFlow to analyze pre-processed company information, external market data, and health data using a generative model. The datasets obtained from steps 2 and 3 are used as input. Here, the generative AI model analyzes data patterns and trends, generating economic analysis and service recommendations tailored to individual health conditions. The output includes analysis results and specific service recommendations. 【0478】 Step 5: 【0479】 The system presents the user with suggested analysis results and service information via the terminal. It receives analysis results from the server as input and displays them in a GUI (Graphical User Interface). The user can view the suggestions and make decisions based on the situation. As output, it generates an analysis results screen in a format viewable by the user. 【0480】 Step 6: 【0481】 Based on their own judgment, users input feedback to the server regarding the implementation of their proposals and the results. This feedback includes comments on verification and decisions, as well as selected actions. The server then uses this feedback to improve the accuracy of the generative model in subsequent analyses. The updated generative model is generated as output. This process uses the prompt "Create proposals for necessary care services based on the residents' health status data" to improve the accuracy of the next step. 【0482】 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. 【0483】 This invention relates to a system that combines data analysis functions with an emotion engine, with the aim of supporting business management in companies. The system is configured to recognize user emotions in addition to predictive analysis using corporate data and external information, and to help support business decisions. 【0484】 First, information collected from internal company data and external data sources is input to the server via terminals. The server automatically preprocesses this data, correcting for outliers and normalizing the data. Once preprocessed, the data is analyzed by generative models residing on the server, and financial analysis, market forecasting, and competitive analysis are performed. 【0485】 The analysis results are sent to the user's device, and the emotion engine receives and operates based on this information. The emotion engine recognizes emotions from information such as the user's facial expressions and voice, and adjusts how the results are presented. This process allows the user to receive information in a format optimized for them. The emotion data is sent from the device to the server as feedback after the session and serves as input for data correction in the generative model. 【0486】 As a concrete example, if a company is considering entering a new business field, the user inputs market information, competitor information, and internal company data from a terminal. The server preprocesses the collected data, performs analysis using a generative model, and predicts market trends and competitive strategies. When presenting the analysis results, the emotion engine analyzes the user's reaction, providing more detailed information if the user shows curiosity or excitement, and conversely, concise and easy-to-understand information if the user shows confusion or anxiety. In this way, responses are tailored to the user's emotions, enabling them to make more efficient business decisions. As a result, the feedback data is used to further improve the generative model, allowing the system to provide more accurate support in subsequent analyses. 【0487】 The following describes the processing flow. 【0488】 Step 1: 【0489】 Users input company financial data, sales data, product information, and other data into the terminal. Users can also input external market data and competitor information as needed. 【0490】 Step 2: 【0491】 The terminal sends the entered data to the server. The server retrieves the received data and prepares it for the analysis process. 【0492】 Step 3: 【0493】 The server accesses external data sources to collect market trends and competitor information. It uses external APIs to retrieve the latest data. This data is integrated with internal enterprise data to form a comprehensive dataset. 【0494】 Step 4: 【0495】 The server performs preprocessing on the integrated data. It cleans the data, imputes missing values, and standardizes it to prepare it for the generative model. 【0496】 Step 5: 【0497】 The server inputs pre-processed data into a generative model to perform financial analysis, market forecasting, and competitive analysis. The generative model analyzes each data point and outputs analytical results that contribute to business strategy. 【0498】 Step 6: 【0499】 The server sends the analysis results to the terminal. The terminal displays the results in a user-friendly, visualized format. At this point, the emotion engine is activated and prepares to sense the user's reaction. 【0500】 Step 7: 【0501】 When a user views the analysis results, the emotion engine recognizes the user's facial expressions, tone of voice, and other characteristics. The emotion engine analyzes the emotional data and adjusts the way information is presented based on the user's current state. 【0502】 Step 8: 【0503】 Users make decisions based on the analysis results and input the results and feedback obtained after implementation into their devices. This feedback includes emotionally driven responses. 【0504】 Step 9: 【0505】 The device sends feedback to the server. The server uses the feedback data to update the generative model. This improves the accuracy and sophistication of the next analysis. 【0506】 (Example 2) 【0507】 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." 【0508】 In corporate management decisions, a key challenge is how to effectively utilize vast amounts of internal and external information. In particular, there is a need to integrate diverse data, perform highly accurate analysis, and present the results in a format that is optimal to the manager's needs. However, conventional systems lacked flexibility in data preprocessing and presentation of analysis results, resulting in limitations in their ability to support management decisions. 【0509】 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. 【0510】 In this invention, the server includes means for inputting information within the company, means for automatically collecting market-related information from external sources, means for performing numerical analysis, predictive analysis, and competitive analysis using a generative model, and means for presenting the analysis results to the user and adjusting the presentation content using an emotion engine. This makes it possible to analyze data accurately and quickly and to provide the analysis results in a way that matches the user's emotions. 【0511】 "Internal company information" refers to a variety of information generated within a company, such as sales figures, employee numbers, financial information, and operational data. 【0512】 "External information sources" refer to information obtained from outside the company, such as market reports, news, and publicly available statistics. 【0513】 "Preprocessing" refers to the process of preparing raw data before analysis, and includes operations such as outlier correction and data normalization. 【0514】 A "generative model" refers to a pre-trained algorithm used to analyze input data and perform tasks such as financial analysis, predictive analytics, and competitive analysis. 【0515】 An "emotion engine" refers to a technology that recognizes a user's emotional state from information such as their facial expressions and voice, and adjusts the way the results are presented accordingly. 【0516】 "Feedback" refers to opinions, impressions, and evaluation data obtained from users, and is information used to improve and adjust the system. 【0517】 This invention is a system designed to support corporate management decisions, providing a mechanism for integrating internal corporate information with data from external sources to perform advanced analysis. The system primarily utilizes terminals, servers, and an emotion engine. 【0518】 The terminal first receives internal company information entered by the user and external information collected based on prompt messages. An example of a prompt message might be, "Analyze competitive information and market trends regarding new market entry." The terminal then sends this data to the server. 【0519】 The server preprocesses the received data. This preprocessing includes correcting for data anomalies and normalizing the scale. The preprocessed data is then fed into a trained generative AI model, which performs numerical analysis, predictive analysis, and competitive analysis. This generative AI model is used to analyze large amounts of data and provide predictions and insights. 【0520】 Once the analysis is complete, the data is sent from the server to the user's device. The emotion engine on the device uses the camera and microphone to recognize the user's emotions in real time and dynamically adjusts how the analysis results are presented based on this. For example, if the user shows interest, detailed information is provided; if they show anxiety, simplified information is provided. 【0521】 As a concrete example, when a company using the system wants to understand competitive trends in the technology industry, the user inputs internal data related to their terminal (e.g., historical sales data) and obtains external market information through prompt messages. This information is analyzed on the server, and the results are provided to the user in a format requested by the emotion engine. This enables companies to make more accurate and emotionally responsive business decisions. 【0522】 Thus, the system implementing the present invention effectively and efficiently provides important information in a company's management decision-making process and realizes information presentation optimized for the user. 【0523】 The flow of the specific processing in Example 2 will be explained using Figure 13. 【0524】 Step 1: 【0525】 The user inputs company information and prompt messages into the terminal. In this example, sales data and employee numbers are entered as company information, and the prompt message "Analyze competitive information and market trends regarding new market entry" is used. The terminal receives this data as input and sends it to the server. 【0526】 Step 2: 【0527】 The server begins processing the internal company information and market information received from the terminal as input. First, it performs data anomaly correction, replacing or removing any existing anomalies with appropriate values. Then, it performs data normalization, converting data expressed on different scales to a unified scale. This process yields pre-processed data. 【0528】 Step 3: 【0529】 The server inputs pre-processed data into a generating AI model. The generating AI model analyzes the data and performs financial analysis, market forecasting, and competitive analysis of companies. In this process, it generates future predictions based on patterns and trends identified from the data. The output is information on the analysis results. 【0530】 Step 4: 【0531】 The server sends the generated analysis results to the user's device. The device then activates its built-in emotion engine based on the received analysis results. The emotion engine analyzes the user's emotions in real time using the user's facial recognition camera and voice input function. The method of presenting the analysis results is adjusted based on these emotion recognition results. 【0532】 Step 5: 【0533】 The device utilizes the results of an emotion engine analysis to provide more detailed information if the user shows interest, and present concise information if they show anxiety. This ensures appropriate information is presented. As output, the user receives information that corresponds to their emotions. 【0534】 Step 6: 【0535】 The user inputs feedback on the analysis results into the terminal. This feedback is sent back to the server and used to train the generative AI model. Through this feedback, the accuracy of subsequent analyses is improved. The output is an improved generative AI model. 【0536】 (Application Example 2) 【0537】 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." 【0538】 In modern business management, accurate management decisions based on vast amounts of data are required. While proper management of security risks is crucial, conventional data analysis systems are unable to optimize information presentation based on user emotions. As a result, the user understanding and decision-making processes can become inefficient, and there is a need for solutions to improve this. 【0539】 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. 【0540】 In this invention, the server includes means for inputting data from within the company, means for automatically collecting market information from external data sources, means for pre-processing data to prepare it, means for performing financial analysis, market forecasting, and competitive analysis using a generative model, means for presenting the analysis results to the user, means for analyzing the user's emotions and adjusting the information display, and means for collecting feedback and updating the generative model. This makes it possible to optimize the presentation of information according to the user's emotional state, improving the efficiency and accuracy of management decisions. 【0541】 "Internal company data" refers to information such as statistical data, financial records, and personnel documents that are generated or acquired within a company. 【0542】 "External data sources" refer to information sources that exist outside of a company, providing market trends, competitive information, economic indicators, and so on. 【0543】 "Preprocessing" refers to the process of preparing data for analysis, including correcting for outliers and normalizing the data. 【0544】 A "generative model" is a machine learning model used to analyze economic conditions and competitive landscapes based on data and to make future predictions. 【0545】 "Analysis results" refer to conclusions and suggestions derived from data processed by a generative model. 【0546】 "Means of analyzing user emotions and adjusting information display" refers to technology that recognizes user emotions from facial expressions, voice, etc., and changes the way information is displayed according to that state. 【0547】 "Methods for collecting feedback and updating generative models" refers to the process of gathering user responses and implementation results, and improving the generative model based on that information. 【0548】 The system for realizing this invention integrates and analyzes internal and external corporate data, presenting information based on the user's emotions. First, the terminal securely collects internal corporate data and automatically acquires external market information. The acquired data is sent to a server, where it undergoes preprocessing such as anomaly correction and normalization. The preprocessed data is then analyzed using a generative AI model to perform financial analysis, market forecasting, and competitive landscape predictions. 【0549】 Before sending the analysis results to the terminal, the server uses an emotion engine to analyze the user's facial expressions and voice, and adjusts how information is presented according to their emotional state. For example, if the user shows anxiety, clear and concise information is prioritized, while if they show interest, more detailed and in-depth information is presented. 【0550】 This process utilizes smartphones and tablets as hardware, and employs Python for data analysis, TensorFlow and Keras for generative AI models, and OpenCV for emotion recognition. Feedback information is stored on a server and used to improve the generative model, resulting in more accurate and useful information being provided in subsequent analyses. 【0551】 As a concrete example, consider a case where a company uses this system to manage security risks. The system analyzes the latest threat intelligence and internal security data to assess the risks faced by management. If management requests more details, it will provide detailed information on new countermeasures and industry averages. An example of a prompt message could be: "Based on the latest security threat intelligence, please provide countermeasures to help management decisions. Also, please use user sentiment data to adjust the information display format." 【0552】 The flow of a specific process in Application Example 2 will be explained using Figure 14. 【0553】 Step 1: 【0554】 The terminal collects data within the company and automatically retrieves external market information. This input data includes statistical information, financial data, and market indicators. This data is temporarily stored on the terminal and then transmitted to the server. 【0555】 Step 2: 【0556】 The server performs preprocessing on the received data. This process detects and corrects outliers in the data, as well as normalizing numerical data. As a result of the preprocessing, the data is prepared in a format suitable for analysis. 【0557】 Step 3: 【0558】 Using pre-processed data, an AI model performs analysis. The server conducts financial analysis, market forecasting, and competitive analysis to identify specific risks and opportunities. The analysis results are generated as numerical and text data outputs. 【0559】 Step 4: 【0560】 The analysis results are processed by an emotion engine on the server before being sent to the user's device. The system analyzes the user's provided facial expression images and audio data to detect the user's emotions. Based on the detected emotions, the displayed information and format are optimized. 【0561】 Step 5: 【0562】 The device presents optimized information to the user. The user makes business decisions based on the presented data. User reactions and additional feedback information are collected and used to improve the model later. 【0563】 Step 6: 【0564】 The feedback data is sent to the server and used to further improve the generative model. This ensures that subsequent analyses provide more accurate information that better meets user needs. 【0565】 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. 【0566】 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. 【0567】 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. 【0568】 [Fourth Embodiment] 【0569】 Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment. 【0570】 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. 【0571】 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). 【0572】 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. 【0573】 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. 【0574】 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). 【0575】 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. 【0576】 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. 【0577】 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. 【0578】 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. 【0579】 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. 【0580】 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. 【0581】 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". 【0582】 This invention relates to a management support system that can be easily used by small and medium-sized enterprises, and aims to provide objective analysis results by utilizing data from both inside and outside the company. This system mainly consists of a server, terminals, and a user interface. 【0583】 The server collects and centrally manages corporate data and information from external data sources in real time. The collected data is first pre-processed on the server, including standardization and cleaning. Once pre-processed, the data is analyzed by a generative model. The generative model parametrically analyzes the data and provides insights from different perspectives, such as financial analysis, market forecasting, and competitive analysis. 【0584】 The generated analysis results are presented to the user via a terminal. Based on this information, the user can determine business strategies and policies. Furthermore, by inputting the results of the strategies implemented by the user into the terminal as feedback, the server utilizes the collected feedback to update the generative model. This increases the accuracy of the analysis, enabling more precise business support. 【0585】 As a concrete example, if a small or medium-sized enterprise (SME) is planning to launch a new product, the user inputs existing product data, market trends, and competitor product information. The server then uses this data to run a generative model and recommend target market segments and pricing. Based on these recommendations, the user's performance is evaluated and fed back into the system, allowing for more refined analysis in the future. This feedback loop enables decision-making support that always reflects the latest market information. 【0586】 The following describes the processing flow. 【0587】 Step 1: 【0588】 Users input relevant information, such as company financial data and sales data, into a terminal. This information is sent to a server to form a dataset that will serve as the basis for future analysis. 【0589】 Step 2: 【0590】 The server automatically collects market trends, competitive information, and economic indicators from external data sources. This includes accessing databases using APIs to retrieve the latest information. 【0591】 Step 3: 【0592】 The server performs preprocessing on the collected internal and external corporate data. This preprocessing involves cleaning the data, imputing missing values, and standardizing it to prepare it for the model. 【0593】 Step 4: 【0594】 The server inputs pre-processed data into a generative model. The generative model performs financial analysis, market forecasting, and competitive analysis, ultimately generating analytical results that contribute to business management. 【0595】 Step 5: 【0596】 The server sends the generated analysis results to the terminal. The terminal visualizes these results and displays them in a format that is easy for the user to understand. 【0597】 Step 6: 【0598】 Users make business decisions based on the analysis results and input feedback on the implementation status and results via their terminals. This feedback is sent to the server and used to improve the performance of the generative model. 【0599】 Step 7: 【0600】 The server uses user feedback data to adjust and update the generative model. The model is improved so that more accurate results can be obtained in the next analysis. 【0601】 (Example 1) 【0602】 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". 【0603】 For small and medium-sized enterprises (SMEs), it is crucial to easily collect internal and external data and utilize it for objective analysis in order to make quick and accurate management decisions. However, there is a lack of technical means to efficiently acquire, organize, and provide appropriate analytical results for this data. Furthermore, there is a need to utilize feedback information from the implementation of management strategies and update generation algorithms to make more precise decisions in the future. 【0604】 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. 【0605】 In this invention, the server includes a device for inputting information, a device for automatically acquiring data from external information sources, and a device for performing preliminary processing to prepare the data. This enables centralized management of data both inside and outside the company and efficient preprocessing. Furthermore, by including a device for performing financial evaluations, economic forecasts, and competitor analysis using a generation algorithm, and a device for displaying the generated evaluation results to the user, the user can make management decisions quickly. In addition, by providing a device for collecting user feedback and updating the generation algorithm, improved accuracy in subsequent decisions can be expected. 【0606】 A "device for inputting information" is a function that provides an interface for importing internal company data and external data into a system. 【0607】 A "device that automatically acquires data from external sources" is a system that efficiently collects market information, competitive information, and other data via the internet or other networks. 【0608】 "Devices that perform preliminary processing to prepare data" refer to technologies that provide standardization and cleaning processes to resolve inconsistencies in collected data. 【0609】 A "device that performs financial evaluation, economic forecasting, and competitive analysis using generation algorithms" is a processor that extracts various business insights through algorithms and generates information useful for management. 【0610】 A "device for displaying generated evaluation results to the user" is a device that has a graphical user interface for visually presenting analysis results to the user. 【0611】 A "device that collects user feedback and updates the generation algorithm" is a mechanism that improves the algorithm based on the results of actual business decisions and uses that information for future analysis. 【0612】 This invention is a system for companies to efficiently formulate and execute their business strategies. This system integrates internal and external information and performs analysis using a generative AI model to provide various business insights. 【0613】 The server acts as an input device, acquiring data from internal sales management systems and customer management systems within the company. It also automatically collects data from external sources, such as online databases and market research sites. This process utilizes APIs implemented in programming languages ​​such as Python and Java. 【0614】 The collected data is first processed on the server. This preliminary stage involves data standardization and cleaning. Specifically, this includes imputing missing data and removing outliers. This improves the accuracy of analysis by the generative AI model. 【0615】 The server executes generative algorithms using the prepared data. Analysis includes financial valuation, market forecasting, and competitive analysis. Python libraries such as Pandas and NumPy are applied to the company's financial data, and deep learning models for market forecasting are run using TensorFlow and PyTorch. 【0616】 The terminal visually presents the analysis results obtained from the server to the user. The graphical user interface is provided by front-end frameworks such as React and Vue.js, and D3.js is used for data visualization. Specifically, sales forecasts are displayed as line graphs, and competitor analysis is displayed as bar graphs. 【0617】 Users make business decisions based on the presented analysis results. For example, when launching a new product, they formulate a strategy based on a prompt from the generating AI model: "Recommend the optimal pricing and market segment for the launch of new product A." The results of implementing this strategy are input into the server as feedback and used for subsequent model updates. This feedback loop improves the accuracy of the generating AI model, enabling decision-making support that always reflects the latest market information. 【0618】 The flow of the specific processing in Example 1 will be explained using Figure 11. 【0619】 Step 1: 【0620】 The server retrieves sales data and customer information from internal company systems as input. It also automatically collects market data and competitor information from external sources. Specifically, the server uses APIs to gather this data and store it in a database. This collected data is then used in the next preprocessing step. 【0621】 Step 2: 【0622】 The server processes the collected data. It converts the raw input data into a standard format and appropriately imputes missing values. Specifically, it manipulates the data frame using Python libraries to detect and remove outliers. The output of this preprocessing is a clean and consistent dataset, which is used as input data for the generative AI model. 【0623】 Step 3: 【0624】 The server runs a generative AI model using preprocessed data. Based on the input data, it performs financial analysis, market forecasting, and competitor research. Specifically, it runs an economic forecasting model using TensorFlow and calculates financial indicators using Pandas. The output is an analysis result containing various business insights. 【0625】 Step 4: 【0626】 The terminal presents the user with the analysis results obtained from the generated AI model. It visualizes the analysis results received as input on a graphical user interface. Specifically, it uses D3.js to display sales forecasts as line graphs and competitor analysis as bar graphs. The output is visualized information to support business decision-making. 【0627】 Step 5: 【0628】 The user formulates a business strategy based on the analysis results presented through the terminal. For example, they act based on a prompt to the generating AI model: "Recommend the optimal pricing and market segment for the market launch of new product A." Based on the information presented as input, they execute the actual business strategy and input the results back into the terminal as formatted data. 【0629】 Step 6: 【0630】 The server receives user feedback as input and updates the generative AI model. It adjusts the model's parameters using past strategy execution results and retrains it with a new dataset. Specifically, it minimizes the model's errors based on the input feedback and improves the accuracy of the next analysis. The output obtained at this stage is a more refined, next-generation generative AI model. 【0631】 (Application Example 1) 【0632】 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". 【0633】 Amidst the growing demand for improved operational efficiency and service quality in care facilities and similar settings, there is a need for a system that can monitor the health status of individual residents in real time and provide prompt and appropriate service recommendations based on that information. However, current systems have challenges in real-time analysis of health status and providing service recommendations optimized for specific individuals. Against this backdrop, there is a need for a system that enables facility operators to make decisions based on accurate information and improve services. 【0634】 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. 【0635】 In this invention, the server includes means for inputting information within a company, means for automatically collecting market data from external information sources, means for pre-processing information to organize it, means for performing economic analysis, market forecasting, and competitive analysis using generative models, means for analyzing information from a device for collecting individual health status in real time, and means for making optimal service suggestions based on individual health status. This enables operators of nursing care facilities to quickly provide optimal care services tailored to the individual health status of each resident. 【0636】 "In-house information" refers to the collective term for data and records generated and stored within a company. 【0637】 "External information sources" refer to information such as market data and industry trends obtained from environments outside the company. 【0638】 "Preprocessing" is a general term for various processes that prepare raw data into an analyzable format. 【0639】 A "generative model" is an algorithm that analyzes patterns and trends based on collected data to provide new insights and predictions. 【0640】 "Economic analysis" is the process of analyzing the financial condition of companies and organizations, as well as market trends, based on economic indicators and data. 【0641】 Market forecasting is the process of analyzing past and present market data to estimate future market trends. 【0642】 "Competitive analysis" is the process of investigating the actions of competitors and their position in the market. 【0643】 "A device for collecting personal health information in real time" refers to equipment or systems that instantly acquire health-related data from individuals. 【0644】 "Means of analyzing information" refers to various methods and techniques for gaining useful insights from acquired data. 【0645】 "Optimal service proposals" refer to the most effective methods of service delivery, designed to meet the specific needs and circumstances of a particular individual. 【0646】 This invention involves a system in which a server plays a central role in efficiently collecting, analyzing, and presenting information from both within and outside a company. First, the server retrieves information from within the company's database and collects market data from external sources via the internet. In this process, Python libraries can be used to automate data collection. 【0647】 The server preprocesses the obtained data using the Python Pandas library to remove noise and standardize it. Data collected from devices that collect personal health information in real time, such as smartwatches and IoT devices, is also integrated. The server then prepares the data and inputs it into the generative model. 【0648】 The generative model utilizes TensorFlow or PyTorch to analyze collected data and provide insights such as economic analysis, market forecasting, and competitive analysis. This model functions as a tool for providing optimal service recommendations based on an individual's health status, visualizing data analysis results and presenting suggestions to the user. 【0649】 The generative model is constantly being improved by inputting the results of the strategies implemented by users as feedback to the server. This feedback loop automatically adjusts the model, further improving the accuracy of the next suggestions. 【0650】 For example, in a nursing home, if data on a resident's body temperature and heart rate is collected and shows values ​​that are different from the normal range, the server immediately uses a generative model to suggest appropriate health checks. Users can then take quick action based on these suggestions. Furthermore, if the strategy is successful, inputting the results into the system further optimizes suggestions for similar situations in the future. 【0651】 An example of a prompt message might be, "Based on the resident's health status data, please create a proposal for necessary care services." This allows the system to generate a readily applicable proposal and support the user's decision-making. 【0652】 The flow of a specific process in Application Example 1 will be explained using Figure 12. 【0653】 Step 1: 【0654】 The server retrieves internal company information from its internal database and collects market data from external sources. It takes authentication information from the internal database and external data via APIs as input. During this process, it extracts information from the database using SQL queries and retrieves market data from the internet via HTTP requests. As output, it generates a set of the retrieved raw data. 【0655】 Step 2: 【0656】 The server preprocesses the raw data obtained using the Pandas library. It uses the raw data obtained from step 1 as input to clean the data. Specifically, it performs data imputation, removes outliers, and standardizes the data. This results in outputting a dataset in a unified format suitable for analysis. 【0657】 Step 3: 【0658】 The server collects personal health data in real time from smartwatches and IoT devices. It uses BLE (Bluetooth Low Energy) as input to obtain feeds from each device. The data is stored row by row in the format of time, heart rate, and body temperature. The server generates a health dataset organized for each individual as output. 【0659】 Step 4: 【0660】 The server uses TensorFlow to analyze pre-processed company information, external market data, and health data using a generative model. The datasets obtained from steps 2 and 3 are used as input. Here, the generative AI model analyzes data patterns and trends, generating economic analysis and service recommendations tailored to individual health conditions. The output includes analysis results and specific service recommendations. 【0661】 Step 5: 【0662】 The system presents the user with suggested analysis results and service information via the terminal. It receives analysis results from the server as input and displays them in a GUI (Graphical User Interface). The user can view the suggestions and make decisions based on the situation. As output, it generates an analysis results screen in a format viewable by the user. 【0663】 Step 6: 【0664】 Based on their own judgment, users input feedback to the server regarding the implementation of their proposals and the results. This feedback includes comments on verification and decisions, as well as selected actions. The server then uses this feedback to improve the accuracy of the generative model in subsequent analyses. The updated generative model is generated as output. This process uses the prompt "Create proposals for necessary care services based on the residents' health status data" to improve the accuracy of the next step. 【0665】 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. 【0666】 This invention relates to a system that combines data analysis functions with an emotion engine, with the aim of supporting business management in companies. The system is configured to recognize user emotions in addition to predictive analysis using corporate data and external information, and to help support business decisions. 【0667】 First, information collected from internal company data and external data sources is input to the server via terminals. The server automatically preprocesses this data, correcting for outliers and normalizing the data. Once preprocessed, the data is analyzed by generative models residing on the server, and financial analysis, market forecasting, and competitive analysis are performed. 【0668】 The analysis results are sent to the user's device, and the emotion engine receives and operates based on this information. The emotion engine recognizes emotions from information such as the user's facial expressions and voice, and adjusts how the results are presented. This process allows the user to receive information in a format optimized for them. The emotion data is sent from the device to the server as feedback after the session and serves as input for data correction in the generative model. 【0669】 As a concrete example, if a company is considering entering a new business field, the user inputs market information, competitor information, and internal company data from a terminal. The server preprocesses the collected data, performs analysis using a generative model, and predicts market trends and competitive strategies. When presenting the analysis results, the emotion engine analyzes the user's reaction, providing more detailed information if the user shows curiosity or excitement, and conversely, concise and easy-to-understand information if the user shows confusion or anxiety. In this way, responses are tailored to the user's emotions, enabling them to make more efficient business decisions. As a result, the feedback data is used to further improve the generative model, allowing the system to provide more accurate support in subsequent analyses. 【0670】 The following describes the processing flow. 【0671】 Step 1: 【0672】 Users input company financial data, sales data, product information, and other data into the terminal. Users can also input external market data and competitor information as needed. 【0673】 Step 2: 【0674】 The terminal sends the entered data to the server. The server retrieves the received data and prepares it for the analysis process. 【0675】 Step 3: 【0676】 The server accesses external data sources to collect market trends and competitor information. It uses external APIs to retrieve the latest data. This data is integrated with internal enterprise data to form a comprehensive dataset. 【0677】 Step 4: 【0678】 The server performs preprocessing on the integrated data. It cleans the data, imputes missing values, and standardizes it to prepare it for the generative model. 【0679】 Step 5: 【0680】 The server inputs pre-processed data into a generative model to perform financial analysis, market forecasting, and competitive analysis. The generative model analyzes each data point and outputs analytical results that contribute to business strategy. 【0681】 Step 6: 【0682】 The server sends the analysis results to the terminal. The terminal displays the results in a user-friendly, visualized format. At this point, the emotion engine is activated and prepares to sense the user's reaction. 【0683】 Step 7: 【0684】 When a user views the analysis results, the emotion engine recognizes the user's facial expressions, tone of voice, and other characteristics. The emotion engine analyzes the emotional data and adjusts the way information is presented based on the user's current state. 【0685】 Step 8: 【0686】 Users make decisions based on the analysis results and input the results and feedback obtained after implementation into their devices. This feedback includes emotionally driven responses. 【0687】 Step 9: 【0688】 The device sends feedback to the server. The server uses the feedback data to update the generative model. This improves the accuracy and sophistication of the next analysis. 【0689】 (Example 2) 【0690】 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". 【0691】 In corporate management decisions, a key challenge is how to effectively utilize vast amounts of internal and external information. In particular, there is a need to integrate diverse data, perform highly accurate analysis, and present the results in a format that is optimal to the manager's needs. However, conventional systems lacked flexibility in data preprocessing and presentation of analysis results, resulting in limitations in their ability to support management decisions. 【0692】 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. 【0693】 In this invention, the server includes means for inputting information within the company, means for automatically collecting market-related information from external sources, means for performing numerical analysis, predictive analysis, and competitive analysis using a generative model, and means for presenting the analysis results to the user and adjusting the presentation content using an emotion engine. This makes it possible to analyze data accurately and quickly and to provide the analysis results in a way that matches the user's emotions. 【0694】 "Internal company information" refers to a variety of information generated within a company, such as sales figures, employee numbers, financial information, and operational data. 【0695】 "External information sources" refer to information obtained from outside the company, such as market reports, news, and publicly available statistics. 【0696】 "Preprocessing" refers to the process of preparing raw data before analysis, and includes operations such as outlier correction and data normalization. 【0697】 A "generative model" refers to a pre-trained algorithm used to analyze input data and perform tasks such as financial analysis, predictive analytics, and competitive analysis. 【0698】 An "emotion engine" refers to a technology that recognizes a user's emotional state from information such as their facial expressions and voice, and adjusts the way the results are presented accordingly. 【0699】 "Feedback" refers to opinions, impressions, and evaluation data obtained from users, and is information used to improve and adjust the system. 【0700】 This invention is a system designed to support corporate management decisions, providing a mechanism for integrating internal corporate information with data from external sources to perform advanced analysis. The system primarily utilizes terminals, servers, and an emotion engine. 【0701】 The terminal first receives internal company information entered by the user and external information collected based on prompt messages. An example of a prompt message might be, "Analyze competitive information and market trends regarding new market entry." The terminal then sends this data to the server. 【0702】 The server preprocesses the received data. This preprocessing includes correcting for data anomalies and normalizing the scale. The preprocessed data is then fed into a trained generative AI model, which performs numerical analysis, predictive analysis, and competitive analysis. This generative AI model is used to analyze large amounts of data and provide predictions and insights. 【0703】 Once the analysis is complete, the data is sent from the server to the user's device. The emotion engine on the device uses the camera and microphone to recognize the user's emotions in real time and dynamically adjusts how the analysis results are presented based on this. For example, if the user shows interest, detailed information is provided; if they show anxiety, simplified information is provided. 【0704】 As a concrete example, when a company using the system wants to understand competitive trends in the technology industry, the user inputs internal data related to their terminal (e.g., historical sales data) and obtains external market information through prompt messages. This information is analyzed on the server, and the results are provided to the user in a format requested by the emotion engine. This enables companies to make more accurate and emotionally responsive business decisions. 【0705】 Thus, the system implementing the present invention effectively and efficiently provides important information in a company's management decision-making process and realizes information presentation optimized for the user. 【0706】 The flow of the specific processing in Example 2 will be explained using Figure 13. 【0707】 Step 1: 【0708】 The user inputs company information and prompt messages into the terminal. In this example, sales data and employee numbers are entered as company information, and the prompt message "Analyze competitive information and market trends regarding new market entry" is used. The terminal receives this data as input and sends it to the server. 【0709】 Step 2: 【0710】 The server begins processing the internal company information and market information received from the terminal as input. First, it performs data anomaly correction, replacing or removing any existing anomalies with appropriate values. Then, it performs data normalization, converting data expressed on different scales to a unified scale. This process yields pre-processed data. 【0711】 Step 3: 【0712】 The server inputs pre-processed data into a generating AI model. The generating AI model analyzes the data and performs financial analysis, market forecasting, and competitive analysis of companies. In this process, it generates future predictions based on patterns and trends identified from the data. The output is information on the analysis results. 【0713】 Step 4: 【0714】 The server sends the generated analysis results to the user's device. The device then activates its built-in emotion engine based on the received analysis results. The emotion engine analyzes the user's emotions in real time using the user's facial recognition camera and voice input function. The method of presenting the analysis results is adjusted based on these emotion recognition results. 【0715】 Step 5: 【0716】 The device utilizes the results of an emotion engine analysis to provide more detailed information if the user shows interest, and present concise information if they show anxiety. This ensures appropriate information is presented. As output, the user receives information that corresponds to their emotions. 【0717】 Step 6: 【0718】 The user inputs feedback on the analysis results into the terminal. This feedback is sent back to the server and used to train the generative AI model. Through this feedback, the accuracy of subsequent analyses is improved. The output is an improved generative AI model. 【0719】 (Application Example 2) 【0720】 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". 【0721】 In modern business management, accurate management decisions based on vast amounts of data are required. While proper management of security risks is crucial, conventional data analysis systems are unable to optimize information presentation based on user emotions. As a result, the user understanding and decision-making processes can become inefficient, and there is a need for solutions to improve this. 【0722】 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. 【0723】 In this invention, the server includes means for inputting data from within the company, means for automatically collecting market information from external data sources, means for pre-processing data to prepare it, means for performing financial analysis, market forecasting, and competitive analysis using a generative model, means for presenting the analysis results to the user, means for analyzing the user's emotions and adjusting the information display, and means for collecting feedback and updating the generative model. This makes it possible to optimize the presentation of information according to the user's emotional state, improving the efficiency and accuracy of management decisions. 【0724】 "Internal company data" refers to information such as statistical data, financial records, and personnel documents that are generated or acquired within a company. 【0725】 "External data sources" refer to information sources that exist outside of a company, providing market trends, competitive information, economic indicators, and so on. 【0726】 "Preprocessing" refers to the process of preparing data for analysis, including correcting for outliers and normalizing the data. 【0727】 A "generative model" is a machine learning model used to analyze economic conditions and competitive landscapes based on data and to make future predictions. 【0728】 "Analysis results" refer to conclusions and suggestions derived from data processed by a generative model. 【0729】 "Means of analyzing user emotions and adjusting information display" refers to technology that recognizes user emotions from facial expressions, voice, etc., and changes the way information is displayed according to that state. 【0730】 "Methods for collecting feedback and updating generative models" refers to the process of gathering user responses and implementation results, and improving the generative model based on that information. 【0731】 The system for realizing this invention integrates and analyzes internal and external corporate data, presenting information based on the user's emotions. First, the terminal securely collects internal corporate data and automatically acquires external market information. The acquired data is sent to a server, where it undergoes preprocessing such as anomaly correction and normalization. The preprocessed data is then analyzed using a generative AI model to perform financial analysis, market forecasting, and competitive landscape predictions. 【0732】 Before sending the analysis results to the terminal, the server uses an emotion engine to analyze the user's facial expressions and voice, and adjusts how information is presented according to their emotional state. For example, if the user shows anxiety, clear and concise information is prioritized, while if they show interest, more detailed and in-depth information is presented. 【0733】 This process utilizes smartphones and tablets as hardware, and employs Python for data analysis, TensorFlow and Keras for generative AI models, and OpenCV for emotion recognition. Feedback information is stored on a server and used to improve the generative model, resulting in more accurate and useful information being provided in subsequent analyses. 【0734】 As a concrete example, consider a case where a company uses this system to manage security risks. The system analyzes the latest threat intelligence and internal security data to assess the risks faced by management. If management requests more details, it will provide detailed information on new countermeasures and industry averages. An example of a prompt message could be: "Based on the latest security threat intelligence, please provide countermeasures to help management decisions. Also, please use user sentiment data to adjust the information display format." 【0735】 The flow of a specific process in Application Example 2 will be explained using Figure 14. 【0736】 Step 1: 【0737】 The terminal collects data within the company and automatically retrieves external market information. This input data includes statistical information, financial data, and market indicators. This data is temporarily stored on the terminal and then transmitted to the server. 【0738】 Step 2: 【0739】 The server performs preprocessing on the received data. This process detects and corrects outliers in the data, as well as normalizing numerical data. As a result of the preprocessing, the data is prepared in a format suitable for analysis. 【0740】 Step 3: 【0741】 Using pre-processed data, an AI model performs analysis. The server conducts financial analysis, market forecasting, and competitive analysis to identify specific risks and opportunities. The analysis results are generated as numerical and text data outputs. 【0742】 Step 4: 【0743】 The analysis results are processed by an emotion engine on the server before being sent to the user's device. The system analyzes the user's provided facial expression images and audio data to detect the user's emotions. Based on the detected emotions, the displayed information and format are optimized. 【0744】 Step 5: 【0745】 The device presents optimized information to the user. The user makes business decisions based on the presented data. User reactions and additional feedback information are collected and used to improve the model later. 【0746】 Step 6: 【0747】 The feedback data is sent to the server and used to further improve the generative model. This ensures that subsequent analyses provide more accurate information that better meets user needs. 【0748】 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. 【0749】 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. 【0750】 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. 【0751】 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. 【0752】 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. 【0753】 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. 【0754】 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. 【0755】 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. 【0756】 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." 【0757】 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. 【0758】 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. 【0759】 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. 【0760】 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. 【0761】 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. 【0762】 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. 【0763】 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. 【0764】 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. 【0765】 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. 【0766】 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. 【0767】 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. 【0768】 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. 【0769】 The following is further disclosed regarding the embodiments described above. 【0770】 (Claim 1) 【0771】 Methods for entering data within a company, 【0772】 A means of automatically collecting market information from external data sources, 【0773】 A means of performing preprocessing to prepare the data, 【0774】 Methods for performing financial analysis, market forecasting, and competitive analysis using generative models, 【0775】 Means of presenting analysis results to the user, 【0776】 A means of collecting user feedback and updating the generative model, 【0777】 A system that includes this. 【0778】 (Claim 2) 【0779】 The system according to claim 1, further comprising means for inputting the results of implementing the management strategy proposed by the generative model as feedback and adjusting the generative model. 【0780】 (Claim 3) 【0781】 The system according to claim 1, comprising means for visualizing analysis results obtained by a generative model and supporting strategic proposals based on management decisions. 【0782】 "Example 1" 【0783】 (Claim 1) 【0784】 A device for inputting information, 【0785】 A device that automatically acquires data from external information sources, 【0786】 A device that performs preliminary processing to prepare the data, 【0787】 A device that performs financial evaluation, economic forecasting, and competitive analysis using a generation algorithm, 【0788】 A device that displays the generated evaluation results to the user, 【0789】 A device that collects user feedback and updates the generation algorithm, 【0790】 A system that includes this. 【0791】 (Claim 2) 【0792】 The system according to claim 1, further comprising a device that inputs the results of implementation of management policies indicated by a generation algorithm as feedback and adjusts the generation algorithm. 【0793】 (Claim 3) 【0794】 The system according to claim 1, comprising a device that visualizes evaluation results obtained by a generation algorithm and supports policy proposals based on management decisions. 【0795】 "Application Example 1" 【0796】 (Claim 1) 【0797】 Means of entering information within a company, 【0798】 A means of automatically collecting market data from external sources, 【0799】 Means for preprocessing information to organize it, 【0800】 Methods for performing economic analysis, market forecasting, and competitive analysis using generative models, 【0801】 Means of presenting analysis results to users, 【0802】 A means of collecting user feedback and updating the generative model, 【0803】 A means of analyzing information from a device that collects an individual's health status in real time, 【0804】 A means of providing optimal service suggestions based on an individual's health condition, 【0805】 A system that includes this. 【0806】 (Claim 2) 【0807】 The system according to claim 1, further comprising means for inputting the results of implementation of the operational strategy proposed by the generative model as feedback and adjusting the generative model. 【0808】 (Claim 3) 【0809】 The system according to claim 1, comprising means for visualizing analysis results obtained by a generative model and supporting strategic proposals based on operational decisions. 【0810】 "Example 2 of combining an emotion engine" 【0811】 (Claim 1) 【0812】 Means of entering information within a company, 【0813】 A means of automatically collecting market-related information from external sources, 【0814】 A means of performing preprocessing to prepare the data, 【0815】 A means of performing numerical analysis, predictive analysis, and competitive analysis using generative models, 【0816】 A means of presenting analysis results to the user and adjusting the content of the presentation using an emotion engine, 【0817】 A means of collecting user feedback and updating the generative model, 【0818】 A system that includes this. 【0819】 (Claim 2) 【0820】 The system according to claim 1, further comprising means for inputting the results of implementation of a business strategy proposed by a generative model as feedback and adjusting the generative model. 【0821】 (Claim 3) 【0822】 The system according to claim 1, comprising means for visualizing analysis results obtained by a generative model, supporting strategic proposals based on management decisions, and presenting information according to the user's emotions using an emotion engine. 【0823】 "Application example 2 when combining with an emotional engine" 【0824】 (Claim 1) 【0825】 Methods for entering data within a company, 【0826】 A means of automatically collecting market information from external data sources, 【0827】 A means of performing preprocessing to prepare the data, 【0828】 Methods for performing financial analysis, market forecasting, and competitive analysis using generative models, 【0829】 Means of presenting analysis results to the user, 【0830】 A means of analyzing user emotions and adjusting information display, 【0831】 A means of collecting feedback and updating the generative model, 【0832】 A system that includes this. 【0833】 (Claim 2) 【0834】 The system according to claim 1, further comprising means for inputting the results of implementing the management strategy proposed by the generative model as feedback and adjusting the generative model. 【0835】 (Claim 3) 【0836】 A means to visualize the analysis results obtained by generative models and support strategic proposals based on management decisions, 【0837】 The system according to claim 1, comprising means for visualizing risk information and adapting the displayed content through sentiment analysis. [Explanation of symbols] 【0838】 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] Methods for entering data within a company, A means of automatically collecting market information from external data sources, A means of performing preprocessing to prepare the data, Methods for performing financial analysis, market forecasting, and competitive analysis using generative models, Means of presenting analysis results to the user, A means of collecting user feedback and updating the generative model, A system that includes this. [Claim 2] The system according to claim 1, further comprising means for inputting the results of implementing the management strategy proposed by the generative model as feedback and adjusting the generative model. [Claim 3] The system according to claim 1, comprising means for visualizing analysis results obtained by a generative model and supporting strategic proposals based on management decisions.

Images