system

Abstract

We provide the system. [Solution] Methods for collecting and cleansing corporate data and external market data, Methods for analyzing copyrighted works and speeches to extract the thought patterns of business leaders, A means of building machine learning models and predicting future business scenarios, A means of generating answers to questions from executives in real time, A means of proposing topics to be discussed based on past decision history and industry trends, Means of providing customized strategic proposals, 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 as a response to the user utterance. 【Prior Art Documents】 【Patent Documents】 【0003】 【Patent Document 1】 Japanese Patent Application Laid-Open No. 2022-180282 【Summary of the Invention】 【Problems to be Solved by the Invention】 【0004】 In modern enterprise management, it is extremely important to accurately analyze a huge amount of internal data and external market data and make rapid strategic decisions, but it is difficult to effectively achieve this with conventional methods. Furthermore, there is no integrated support system for making strategic proposals tailored to the actual situation by leveraging past successful cases and the thinking patterns of famous managers. As a result, enterprises may not be able to quickly respond to market changes and may be hindered from achieving sustainable growth. 【Means for Solving the Problems】 【0005】 This invention provides a means for collecting and cleansing data from both internal and external sources within a company, and for learning executive thought patterns by analyzing copyrighted works and speeches. It also enables the prediction of future business scenarios using machine learning and the generation of optimal answers to executive questions in real time. Furthermore, it realizes a system that supports rapid and appropriate decision-making by suggesting key issues to be discussed at board meetings and other meetings based on past decision history and industry trends, and by providing customized strategic suggestions based on user profiles. 【0006】 "Corporate data" refers to information generated within a company, and includes sales data, customer feedback, employee data, and so on. 【0007】 "External market data" refers to market-related information collected from factors other than companies, and includes economic indicators, market trends, and competitive information. 【0008】 "Data cleansing" is the process of preparing collected data into a format that is easy to analyze, and includes removing duplicate data, correcting outliers, and handling missing values. 【0009】 A "copyrighted work" is a document such as a book or paper written by a business executive, and it serves as a source of information from which thought patterns can be extracted. 【0010】 A "speech" refers to the content of a lecture or presentation given by a business leader, and serves as a source of information for analyzing the important themes and strategies contained within it. 【0011】 A "thinking pattern" refers to the criteria and tendencies of thinking that managers and decision-makers use to act and make judgments based on their past experiences and knowledge. 【0012】 A "machine learning model" is an algorithm that learns from past data and is used to predict future trends. 【0013】 A "business scenario" is a hypothetical plan used to predict future economic activities and market trends, and to plan management strategies based on those predictions. 【0014】 "Real-time" means processing data with virtually no delay and providing results, thereby supporting decision-making with immediacy. 【0015】 A "strategic proposal" is advice or recommendations to corporate decision-makers that provide concrete action plans and directions, thereby supporting the achievement of the company's objectives. [Brief explanation of the drawing] 【0016】 [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]It is a sequence diagram showing the processing flow of the data processing system in Embodiment 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Embodiment 2 when the emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when the emotion engine is combined. 【Mode for Carrying Out the Invention】 【0017】 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. 【0018】 First, the language used in the following description will be explained. 【0019】 In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include 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. 【0020】 In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor. 【0021】 In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes. 【0022】 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). 【0023】 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." 【0024】 [First Embodiment] 【0025】 Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment. 【0026】 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. 【0027】 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). 【0028】 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. 【0029】 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. 【0030】 The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form 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. 【0031】 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. 【0032】 Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14. 【0033】 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. 【0034】 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. 【0035】 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. 【0036】 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". 【0037】 This invention is a system for supporting strategic planning in corporate management, providing strategic advice to managers using internal and external corporate data. Embodiments of this invention primarily function through the interaction of servers, terminals, and users. 【0038】 First, the server automatically collects information such as sales data, customer feedback, and employee data from the company's internal systems. In parallel, it acquires market trends, competitor information, and economic indicators from external data sources. This creates a comprehensive dataset of the company's current situation and market environment. 【0039】 Next, the server performs data cleansing to prepare the collected data for analysis. This includes removing duplicate data, correcting outliers, and properly imputing missing values. This improves the accuracy and reliability of the data. 【0040】 Furthermore, the server analyzes copyrighted works and speeches to extract the thought patterns of prominent business leaders. This involves using natural language processing technology to identify and learn keywords and themes related to the strategic decisions of these leaders. This provides insights that can be used to formulate new strategies. 【0041】 The server builds a machine learning model based on historical data and learned thought patterns. This model predicts future business scenarios for a company and estimates increases or decreases in sales and changes in market trends. This allows managers to quantitatively evaluate future trends. 【0042】 During meetings and board meetings, the terminal receives questions from users and enables real-time responses. The server quickly searches for relevant data and similar past cases, generates appropriate strategic recommendations, and sends them back to the terminal. In this way, executives can receive immediate support in making important decisions. 【0043】 Furthermore, the server analyzes past decision history and industry trends to suggest topics for discussion in meetings. This allows users to focus on important issues and enables efficient meeting management. 【0044】 Finally, the server provides customized strategic recommendations based on the user's individual requirements and profile. This enables optimized decision-making support for each user. For example, for a company considering entering a new market, it provides a detailed report on the risks and opportunities of entry, based on past success stories, to support management decisions. 【0045】 Through these functions, the system of the present invention provides powerful support for companies to make data-driven strategic decisions. 【0046】 The following describes the processing flow. 【0047】 Step 1: 【0048】 The server collects data from the company's internal systems and external data sources. Internal data includes sales data and customer feedback, while external data includes market trends and economic indicators. This creates a comprehensive dataset of the company's current situation and external environment. 【0049】 Step 2: 【0050】 The server performs data cleansing on the collected data. Duplicate data is removed, outliers are corrected, and missing values ​​are appropriately imputed. This increases the accuracy and reliability of the data used for analysis. 【0051】 Step 3: 【0052】 The server analyzes copyrighted works and speeches using natural language processing technology. This allows it to identify keywords related to the thought patterns and strategic decisions of prominent business leaders, and then uses this information to learn from them. 【0053】 Step 4: 【0054】 The server builds a machine learning model based on historical data and learned thought patterns. Using this model, it predicts future business scenarios for companies and estimates increases or decreases in sales and changes in market trends. 【0055】 Step 5: 【0056】 When a user enters a question using a terminal during a meeting or board meeting, the server instantly searches for relevant data and similar past cases to generate an appropriate answer. This answer is then sent back to the terminal and displayed to the user. 【0057】 Step 6: 【0058】 The server analyzes past decision history and industry trends, and supports user decision-making by suggesting key agenda items to discuss in meetings. This process improves meeting efficiency. 【0059】 Step 7: 【0060】 The server provides customized strategic suggestions based on the user's individual profile. This enables decision-making support that is adapted to the different requirements and conditions of each user. 【0061】 (Example 1) 【0062】 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." 【0063】 In corporate management, it is essential to accurately grasp both internal information and the external environment to make swift and accurate decisions. However, the process of extracting and analyzing necessary information from vast amounts of data is cumbersome, making efficient strategy formulation difficult. Furthermore, while it is important to learn from past decision-making patterns and utilize them in future operations, few systems can effectively do this. To solve these problems, a system that supports integrated and real-time strategic decision-making is necessary. 【0064】 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. 【0065】 In this invention, the server includes means for collecting and preprocessing internal and external environmental information of a company; means for analyzing the information using natural language processing technology and identifying management decision patterns; and means for simulating future business scenarios using predictive algorithms. This enables companies to make rapid and strategic decisions based on comprehensive information. 【0066】 "Internal company information" refers to information related to the operation of a company, such as sales data, customer feedback, and employee data, which are generated within the organization. 【0067】 "External environmental information" refers to data obtained from external sources, such as information on competing companies, market trends, and economic indicators. 【0068】 "Preprocessing" is a process that improves the accuracy and reliability of collected data by removing duplicate data, correcting outliers, and imputing missing values. 【0069】 "Natural language processing technology" is a technology that enables computers to understand and analyze text data written in human language. 【0070】 "Management decision patterns" refer to the tendencies in decision-making and strategic judgment criteria of past managers. 【0071】 A "predictive algorithm" is a computational method used to predict future business and market trends based on past data. 【0072】 "Simulating business scenarios" is a process for virtually trying out future business developments based on hypotheses and analyzing the results. 【0073】 This invention is a system that supports strategic decision-making within a company. This system operates in a manner in which three entities—a server, a terminal, and a user—interact with each other. 【0074】 First, the server collects data from various sources. Specifically, it obtains internal information from a company's ERP system, customer relationship management system, and HR system, and also collects market trends and competitor data via external APIs. This information is preprocessed on the server, with duplicates and outliers removed and missing values ​​imputed. This processing improves the accuracy of the data. 【0075】 Next, the server uses natural language processing technology to analyze past management documents and speeches and extract patterns in the managers' decision-making. This technology utilizes existing natural language processing libraries. Specifically, Python libraries such as NLTK and spaCy are used for this purpose. 【0076】 Furthermore, the server builds models to predict future business scenarios through machine learning algorithms. For example, it uses scikit-learn and TENSORFLOW® to perform regression models and time series analysis to predict future business trends. 【0077】 Users interact with the server via their devices. When a user enters a question from their device during a meeting, the server uses a generative AI model to generate the best possible answer to the question and responds to the device in real time. An example of a prompt sentence that a user might enter is, "I request a risk analysis and strategic proposal based on success stories related to entering a new market." 【0078】 Furthermore, the server analyzes past decision-making history to provide strategic proposals tailored to individual user requests and industry changes. For example, for companies considering entering new markets, it provides detailed reports based on past success stories and risk analyses to support their decision-making. 【0079】 This means the system functions as a powerful tool for companies to make strategic and efficient decisions based on data. 【0080】 The flow of the specific processing in Example 1 will be explained using Figure 11. 【0081】 Step 1: 【0082】 The server collects data from both inside and outside the company. Inputs include sales data from the company's ERP system, feedback from customer relationship management (CRM) systems, employee data from HR systems, and market trends and economic indicators via external APIs. The server retrieves and integrates this input data to output a comprehensive dataset. 【0083】 Step 2: 【0084】 The server preprocesses the collected data. To improve data accuracy, it performs data cleansing, such as removing duplicate data, correcting outliers, and imputing missing values. Specifically, it uses statistical methods and imputation algorithms based on historical data to reshape the data. This results in clean data that can be analyzed. 【0085】 Step 3: 【0086】 The server analyzes data using natural language processing techniques. The input is clean data, which is then analyzed to identify patterns in managers' decision-making. Specifically, it uses Python's natural language processing library to extract keywords and themes from text data. The output of this step is knowledge and insights related to business strategy. 【0087】 Step 4: 【0088】 The server builds machine learning models and predicts future business scenarios. Inputs include historical data and learned business patterns. The server uses scikit-learn and TensorFlow to execute predictive algorithms and simulate future market trends and sales forecasts. Outputs include quantitative estimates and scenarios for future trends. 【0089】 Step 5: 【0090】 The user enters a question into the server via their terminal. The input is received as a prompt, which includes questions related to business decision-making. A specific example is, "We request a risk analysis and strategic proposal based on successful case studies for entering a new market." Based on this input, the server uses a generative AI model to generate the optimal answer and sends it back to the terminal as output. 【0091】 Step 6: 【0092】 The server analyzes past decision-making history and industry changes to provide customized strategic recommendations to the user. Input includes user profiles and historical data. The server analyzes this data and generates specific recommendations. The output is a strategic report tailored to the user's specific requirements. 【0093】 (Application Example 1) 【0094】 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." 【0095】 In corporate management, formulating effective strategies is crucial, but this presents the challenge of comprehensively analyzing vast amounts of internal and external data. Furthermore, a system is needed to provide appropriate strategic proposals in real time to support rapid decision-making. In urban management, too, it is necessary to efficiently utilize vast amounts of infrastructure data to formulate strategies for realizing smart cities. 【0096】 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. 【0097】 In this invention, the server includes means for collecting and cleansing corporate data and external market data, means for analyzing copyrighted works and audio to extract thought patterns, and means for building machine learning models to predict future business scenarios. This enables efficient data analysis and real-time strategic proposals in companies and cities. 【0098】 "Corporate data" refers to information about sales, customers, and employees generated within a company. 【0099】 "External market data" refers to information obtained from outside the company, such as market trends, competitor information, and economic indicators. 【0100】 "Data cleansing" refers to the process of preparing data for analysis by correcting duplicates and outliers, and imputing missing values. 【0101】 "Analyzing copyrighted works and audio" refers to extracting useful information and patterns from documents and audio using natural language processing technology. 【0102】 "Extracting thought patterns" refers to identifying and learning characteristics related to the strategic judgments of authors or speakers from documents or audio recordings. 【0103】 A "machine learning model" refers to a statistical model used to predict future trends and scenarios based on large amounts of data. 【0104】 "Generating answers to questions in real time" means immediately providing answers based on relevant information in response to user inquiries. 【0105】 "Providing strategic proposals" means recommending specific action plans and policies based on collected data and analysis results. 【0106】 "Urban infrastructure data" refers to information related to urban functions such as transportation, energy, and public safety. 【0107】 "Data aggregation and analysis" refers to the process of gathering diverse data in one place and analyzing its trends and patterns using statistical methods. 【0108】 The system for realizing this invention includes a series of processes for effectively processing and analyzing large amounts of data to support strategic decision-making. In particular, it has the function of supporting the formulation of management strategies using internal corporate data and external market data. Furthermore, it also has the function of analyzing urban infrastructure data for smart city management and providing strategic advice to urban planners. 【0109】 The server first collects data such as sales, customers, employees, market trends, and competitor information from the company's internal systems and external sources. Next, it cleans the collected data by removing duplicates, correcting outliers, and imputing data. This is done using data processing libraries such as Python. 【0110】 The server uses natural language processing techniques to extract thought patterns from copyrighted works and audio recordings. This process utilizes machine learning frameworks such as TensorFlow and PyTorch. Next, these thought patterns and historical data are used to build a machine learning model that predicts future business scenarios. 【0111】 The terminal receives questions from users during meetings and conferences, searches for information to enable the server to respond quickly, and generates answers. For example, it can refer to similar past cases and trends to provide real-time strategic suggestions. In this way, users can receive quick and accurate support for important decision-making. 【0112】 A concrete example is the efficient management of urban functions in preparation for an approaching typhoon. Based on historical data and current weather forecasts, an appropriate allocation of energy resources is proposed. By using generative AI models in conjunction, the accuracy of the planning can be improved. 【0113】 An example of a prompt might be a specific question such as, "In preparation for the typhoon approaching this weekend, please propose a strategic operational plan for urban infrastructure to minimize typhoon damage." 【0114】 The flow of a specific process in Application Example 1 will be explained using Figure 12. 【0115】 Step 1: 【0116】 First, the server collects corporate and market data from the company's internal systems and external sources. Inputs include sales data, customer information, employee information, and external sources such as market trends and competitor information. The output is a set of raw data. This data forms the basis for subsequent processing. Specifically, necessary data is extracted using APIs and database connectors. 【0117】 Step 2: 【0118】 The server cleanses the collected data. The raw data collected in step 1 is used as input. Data processing includes removing duplicates, correcting outliers, and imputing missing values, resulting in a formatted dataset as output. This process utilizes data processing libraries such as Python's Pandas to improve data reliability. 【0119】 Step 3: 【0120】 The server uses natural language processing technology to analyze copyrighted works and audio to extract the thought patterns of business leaders. It uses text and audio data as input. The data processing involves identifying keywords and themes from the text and audio, and obtaining the extracted patterns as output. Specifically, it utilizes TensorFlow to execute a text classification model. 【0121】 Step 4: 【0122】 The server builds a machine learning model based on these thought patterns and historical data to predict future business scenarios. It uses cleansed data and extracted thought patterns as input. For data computation, it performs predictive analytics and generates predicted scenarios as output. This process utilizes machine learning frameworks such as TensorFlow or PyTorch. 【0123】 Step 5: 【0124】 The terminal receives questions from users during a meeting, the server searches for relevant information, and generates appropriate answers. It uses user questions and scenarios as input and provides real-time strategic suggestions as output. Specifically, it performs rapid responses using database queries and natural language generation technologies. 【0125】 Step 6: 【0126】 This system provides an interface for users to make strategic decisions based on suggestions. Input is suggestion data from the terminal, and output is the display of information necessary for decision-making. Specifically, it visually presents information using a GUI on the terminal. 【0127】 Step 7: 【0128】 The server collects urban infrastructure data and creates operational plans for smart cities. It uses urban data such as transportation, energy, and public safety as input and proposes operational plans for each area as output. Specifically, it uses a generative AI model to visualize future scenarios. An example of a prompt is: "In preparation for the typhoon approaching this weekend, please propose a strategic operational plan for urban infrastructure to minimize typhoon damage." 【0129】 Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions. 【0130】 This invention is a system that supports strategic planning in corporate management, and further incorporates an emotion engine that recognizes user emotions. This system, which understands user emotions and the background of decision-making in real time and supports strategic decision-making, consists of the following elements. 【0131】 First, the server collects comprehensive internal and external datasets from the company and manages them in the cloud. This includes sales data, customer feedback, employee data, and even external market trends and economic indicators. The server cleanses this data and prepares it for analysis. 【0132】 Next, the emotion engine recognizes emotions from the user's voice, text tone, facial expressions, and other data. Data received via the device's camera and microphone is sent to a server and processed in real time. It recognizes emotional patterns and understands the user's current emotional state. 【0133】 The server further analyzes the writings and speeches of prominent business leaders to learn thought patterns related to business decisions. This involves utilizing natural language processing techniques to extract key keywords and strategies from the documents. 【0134】 Next, the server builds a machine learning model based on the collected data and sentiment information to predict future business scenarios. This model takes into account the current emotional state and can tailor optimal strategic suggestions to the user. 【0135】 When users want to ask a question during a meeting or other setting, they can interact through their device and input their question instantly. The server processes this information and generates an answer that takes into account the user's emotional state. This ensures that the question is answered at the most appropriate time and with the most suitable approach. 【0136】 For example, if a user is considering entering the stock market, the server will create a comprehensive report that includes risk analysis and recommended actions, taking into account historical data, market information, and even the user's current anxieties and expectations—the emotional aspects of the situation. Furthermore, by providing individually tailored suggestions, it will support decision-making that is adapted to the user's situation, including their emotions. 【0137】 Thus, the system of the present invention strongly supports effective decision-making by integrating data analysis and sentiment recognition technologies to provide managers with more personalized strategic proposals. 【0138】 The following describes the processing flow. 【0139】 Step 1: 【0140】 The server automatically collects sales data, customer feedback, employee data, and even market trends and economic indicators from internal corporate systems and external data sources. This creates a comprehensive dataset of the company's current situation and its external environment. 【0141】 Step 2: 【0142】 The server cleanses the collected data. Specifically, it improves the accuracy and reliability of the data by removing duplicate data, correcting outliers, and imputing missing values. This process is an important preparatory step for data analysis. 【0143】 Step 3: 【0144】 The device acquires data through its camera and microphone to input user voice and facial expression data. This data is sent to a server in real time for further processing. 【0145】 Step 4: 【0146】 The server uses an emotion engine to analyze voice, text, and facial expression data acquired from the user to recognize emotions. By evaluating the emotional patterns, it understands the user's current emotional state. 【0147】 Step 5: 【0148】 The server analyzes collected executive writings and speeches using natural language processing technology to learn thought patterns related to business decisions. This allows it to extract information useful for executives' strategic decision-making. 【0149】 Step 6: 【0150】 The server builds a machine learning model based on historical data and sentiment recognition results. This model is used to predict future business scenarios for companies and enables the adjustment of strategic recommendations that take into account the user's emotional state. 【0151】 Step 7: 【0152】 When users wish to interact during a meeting or board meeting, they can enter questions on a terminal. Based on the entered questions, the server generates answers considering relevant data, similar past cases, and even sentiment information, and sends them back to the terminal. 【0153】 Step 8: 【0154】 The server provides customized strategic suggestions based on the user's individual profile and emotion recognition results. This enables decision-making support that is adapted to the specific situation and emotions the user is facing. 【0155】 In this way, this system, which combines an emotion engine, provides deeper insights and personalized advice in supporting corporate decision-making. 【0156】 (Example 2) 【0157】 Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal". 【0158】 In modern business management, managers need to analyze vast amounts of internal and external data to make effective decisions. However, the complexity of organizing and analyzing this data makes it difficult to make quick and appropriate decisions. Furthermore, managers' emotions often influence decision-making, and there is a lack of approaches that take this into account. In addition, learning from past decision-making history is insufficient, limiting the ability to effectively predict future scenarios. 【0159】 The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. 【0160】 In this invention, the server includes means for collecting and organizing information, means for analyzing documents to extract thought processes related to management decisions, means for predicting future scenarios using a learning algorithm, and means for recognizing and considering emotional states. This enables the effective organization and analysis of vast amounts of data, and realizes decision-making support that takes emotions into account. Furthermore, it becomes possible to learn past decision-making patterns and propose optimal management strategies based on them. 【0161】 "Means for collecting and organizing information" refers to the technology of acquiring diverse data from both inside and outside a company, and then scrutinizing and transforming it into a format that can be analyzed. 【0162】 "Methods for analyzing documents and extracting thought processes related to management decisions" refers to techniques for identifying thought patterns that drive management decisions from texts such as books and speeches on management. 【0163】 "Methods for predicting future scenarios using learning algorithms" refer to techniques that analyze past data and current circumstances to build machine learning models for predicting future business environments. 【0164】 "Means for recognizing and considering emotional states" refers to technologies that recognize a user's emotions from voice, text, and facial expressions, and reflect that in decision-making support. 【0165】 This invention is a system designed to support decision-making in corporate management. Its embodiments are described below. 【0166】 The server collects and organizes a wide variety of information from both internal and external sources within the company. Internal information includes sales data and employee information, while external information includes market trends and economic indicators. This information is stored on a cloud storage service and organized by a database management system. The server utilizes the Python Pandas library for data formatting and analysis. 【0167】 Furthermore, the server extracts thought processes related to management decisions through document analysis. This utilizes natural language processing technology, employing open-source libraries (e.g., NLTK and SpaCy) to extract important keywords and strategies from management-related books and speeches. 【0168】 Furthermore, the server uses machine learning algorithms to predict future business scenarios. In this process, frameworks such as Scikit-learn and TensorFlow are used to build models based on historical data and make predictions to inform business strategies. 【0169】 The device will collect the user's voice, text, and facial expressions captured by the camera. Input data obtained from the microphone and camera will be sent to the server in real time. The server will use APIs from Google® and other general AI platforms to perform emotion recognition and understand the user's emotional state in real time. 【0170】 A concrete example of this system is a scenario where a user enters a prompt such as, "Please tell me about the latest trends in the stock market and an analysis of the risks of entering the market. I'm feeling a bit anxious right now, but I'd like suggestions based on concrete data." Based on this prompt, the server performs a comprehensive data analysis and immediately presents strategic suggestions that take emotions into account. In this way, useful decision-making support is provided to the user. 【0171】 The flow of the specific processing in Example 2 will be explained using Figure 13. 【0172】 Step 1: 【0173】 The server collects diverse information from both internal and external sources within the company. It utilizes databases and APIs as input, including sales data, employee information, market trends, and economic indicators. Specifically, it retrieves information through periodic database queries and external data feeds. Based on this information, the data is stored in cloud storage. 【0174】 Step 2: 【0175】 The server cleanses the collected data and formats it for analysis. The raw data collected in step 1 is used as input. Here, the Python Pandas library is used to remove noisy data and extract the necessary information. The output is a clean and organized dataset. Specific operations include imputing missing values, normalization, and data format conversion. 【0176】 Step 3: 【0177】 The device collects user voice, text, and facial expressions and sends them to the server. This includes user actions via camera and microphone input. Inputs include audio files, text input, and video footage. As output, this data is sent to the server in real time. 【0178】 Step 4: 【0179】 The server processes the user's voice, text, and facial expression data in real time to recognize their emotional state. This process uses data from step 3 as input and utilizes Google Cloud and general APIs for emotion recognition. The output is the user's emotional status. Specific processing includes tone analysis, keyword emotion weighting, and facial expression analysis. 【0180】 Step 5: 【0181】 The server analyzes documents to extract data related to business decisions. The input is text data from copyrighted works and speeches. Using natural language processing techniques, it extracts important keywords and business strategies as output. Specific operations include text mining, keyword extraction, and document classification. 【0182】 Step 6: 【0183】 The server builds a machine learning model using historical data and the current user's emotional state to predict business scenarios. The input is the dataset formatted in step 2 and the emotional data from step 4. Using Python's Scikit-learn, the output is a prediction tailored to a specific business situation. The specific operation involves data modeling, training, and prediction processes. 【0184】 Step 7: 【0185】 The user interacts with the server by entering a question via a terminal. The input is in text format. Based on the content of the question, the server generates an answer that takes into account the user's emotional state. The output is emotionally balanced strategic advice. The specific operations include query analysis, sentiment adjustment, and answer generation processes. 【0186】 Through this series of steps, the system achieves effective data processing and strategic proposals that take user emotions into consideration. 【0187】 (Application Example 2) 【0188】 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". 【0189】 In modern business management, decision-making that considers diverse information and emotional aspects is crucial. However, existing systems have struggled to adequately integrate and utilize these factors, making it impossible to provide personalized strategic proposals that take emotions and individual circumstances into account. Furthermore, in citizen-participatory policymaking, the insufficient reflection of citizens' emotions and opinions has been a challenge. In addition, achieving high-quality, real-time interaction during decision-making has not been easy. 【0190】 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. 【0191】 In this invention, the server includes means for collecting and cleansing corporate information and external market information, means for analyzing copyrighted works and audio content to extract decision-makers' thought patterns, and means for building machine learning models to predict future business scenarios. This enables the integrated use of data and emotions in corporate management and real-time strategic support based on sentiment analysis in citizen participation policies. Furthermore, customized strategic proposals are delivered to users, improving the quality of decision-making. 【0192】 "Corporate information" refers to internal data about a company, and the information necessary for management decision-making. 【0193】 "External market information" refers to market data collected from sources outside the company, including industry trends and economic indicators. 【0194】 "Cleansing" refers to the process of preparing raw data into an analyzable format, correcting or deleting inaccurate or duplicate data. 【0195】 "Copyrighted works" refer to intellectual creations such as books and papers on management and business. 【0196】 "Audio content" refers to audio data uttered as part of communication, and includes information about the words and tones used within it. 【0197】 "Extracting thought patterns" refers to analyzing important concepts and trends from copyrighted works or audio content to identify a foundation for decision-making that is useful in achieving specific goals. 【0198】 A "machine learning model" refers to an algorithm or mathematical model that uses large amounts of data to discover patterns and predict future situations and outcomes. 【0199】 "Predicting business scenarios" means statistically estimating future possibilities and outcomes related to management and policy decisions. 【0200】 "Analyzing emotional state" means identifying the user's emotional state based on inputs such as facial expressions and voice. 【0201】 "Summarizing policy proposals" means condensing suggestions from citizens and decision-makers and clearly presenting the key elements. 【0202】 A "customized strategy proposal" involves presenting a strategy tailored to individual needs and conditions, based on the information received and the user's current situation. 【0203】 In this invention, a server collects corporate and external market information, cleanses it, and converts it into an analyzable format. For example, data including sales data, customer feedback, employee data, and external market trends and economic indicators are centrally managed on the cloud. The server also analyzes copyrighted works and audio content to extract the thought patterns of decision-makers. In this process, natural language processing technology is used to efficiently extract keywords and strategies from documents. 【0204】 The server further builds machine learning models based on collected data and emotional information to predict future business scenarios. This enables the integrated use of real-time data and emotions in corporate management. In particular, in citizen-participatory policy proposals, it analyzes emotional states to identify emotions from the user's facial expressions and voice, and then summarizes and provides policy proposals based on that. 【0205】 Users can interact in real time through their smartphones or smart glasses. When users submit suggestions or questions, the system quickly generates more personalized strategic suggestions based on sentiment analysis and provides feedback to the user. This feedback is customized to suit the individual user's needs and circumstances. 【0206】 For example, if a user suggests "I want more lighting in the park," the emotion engine analyzes the user's anxieties and expectations. Based on this analysis, policymakers are provided with a summary such as "There is an emotional background of wanting improved public safety." In this way, the system makes optimized suggestions while taking emotional data into consideration. 【0207】 An example of a prompt for a generative AI model might be: "Based on the sentiment analysis results of the user's suggestion, 'We want more lights in the park,' generate a summary that should be conveyed to policymakers. Please consider the emotional context and also suggest possible solutions." 【0208】 The flow of a specific process in Application Example 2 will be explained using Figure 14. 【0209】 Step 1: 【0210】 The server collects corporate and external market information. It receives data such as sales data, customer feedback, employee data, external market trends, and economic indicators as input. This data is then cleansed and converted into an analyzable format. Specifically, it corrects and removes inaccuracies and duplicates, and consolidates them into a unified format. 【0211】 Step 2: 【0212】 The server analyzes copyrighted material and audio content to extract the thought patterns of decision-makers. It accepts books and audio data related to business management as input. Using natural language processing techniques, it extracts important keywords and statements from the documents and generates a model of thought patterns. Specifically, it uses document analysis algorithms to perform vocabulary frequency analysis and contextual understanding. 【0213】 Step 3: 【0214】 Based on data and sentiment information collected by the server, a machine learning model is built to predict future business scenarios. Input includes cleansed data and sentiment states. The model analyzes the data using relevant statistical methods and algorithms to predict future changes. Specifically, it performs the training and evaluation processes of the predictive model. 【0215】 Step 4: 【0216】 Users submit policy proposals and questions through their devices. The devices take user text and voice data as input. The devices then transfer this information to a server in real time for analysis by an emotion engine. Specifically, they use APIs for speech recognition and emotion analysis as interfaces. 【0217】 Step 5: 【0218】 The server analyzes the user's emotional state and identifies emotional patterns. It processes voice and text data sent from the terminal as input and applies an emotion recognition algorithm. The identified emotional state is generated as output. Specific operations include voice tone analysis and text sentiment analysis. 【0219】 Step 6: 【0220】 The server summarizes policy proposals and generates strategic proposals based on the analysis results. It uses emotional states and data analysis results obtained in steps 1 through 3 as input. The output consists of user-optimized policy proposals and strategic proposals, which are sent to the user and policymakers. Specifically, it utilizes a generative AI model to automatically generate expert prompts. 【0221】 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. 【0222】 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. 【0223】 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. 【0224】 [Second Embodiment] 【0225】 Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment. 【0226】 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. 【0227】 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). 【0228】 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. 【0229】 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. 【0230】 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). 【0231】 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. 【0232】 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. 【0233】 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. 【0234】 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. 【0235】 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. 【0236】 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". 【0237】 This invention is a system for supporting strategic planning in corporate management, providing strategic advice to managers using internal and external corporate data. Embodiments of this invention primarily function through the interaction of servers, terminals, and users. 【0238】 First, the server automatically collects information such as sales data, customer feedback, and employee data from the company's internal systems. In parallel, it acquires market trends, competitor information, and economic indicators from external data sources. This creates a comprehensive dataset of the company's current situation and market environment. 【0239】 Next, the server performs data cleansing to prepare the collected data for analysis. This includes removing duplicate data, correcting outliers, and properly imputing missing values. This improves the accuracy and reliability of the data. 【0240】 Furthermore, the server analyzes copyrighted works and speeches to extract the thought patterns of prominent business leaders. This involves using natural language processing technology to identify and learn keywords and themes related to the strategic decisions of these leaders. This provides insights that can be used to formulate new strategies. 【0241】 The server builds a machine learning model based on historical data and learned thought patterns. This model predicts future business scenarios for a company and estimates increases or decreases in sales and changes in market trends. This allows managers to quantitatively evaluate future trends. 【0242】 During meetings and board meetings, the terminal receives questions from users and enables real-time responses. The server quickly searches for relevant data and similar past cases, generates appropriate strategic recommendations, and sends them back to the terminal. In this way, executives can receive immediate support in making important decisions. 【0243】 Furthermore, the server analyzes past decision history and industry trends to suggest topics for discussion in meetings. This allows users to focus on important issues and enables efficient meeting management. 【0244】 Finally, the server provides customized strategic recommendations based on the user's individual requirements and profile. This enables optimized decision-making support for each user. For example, for a company considering entering a new market, it provides a detailed report on the risks and opportunities of entry, based on past success stories, to support management decisions. 【0245】 Through these functions, the system of the present invention provides powerful support for companies to make data-driven strategic decisions. 【0246】 The following describes the processing flow. 【0247】 Step 1: 【0248】 The server collects data from the company's internal systems and external data sources. Internal data includes sales data and customer feedback, while external data includes market trends and economic indicators. This creates a comprehensive dataset of the company's current situation and external environment. 【0249】 Step 2: 【0250】 The server performs data cleansing on the collected data. Duplicate data is removed, outliers are corrected, and missing values ​​are appropriately imputed. This increases the accuracy and reliability of the data used for analysis. 【0251】 Step 3: 【0252】 The server analyzes copyrighted works and speeches using natural language processing technology. This allows it to identify keywords related to the thought patterns and strategic decisions of prominent business leaders, and then uses this information to learn from them. 【0253】 Step 4: 【0254】 The server builds a machine learning model based on historical data and learned thought patterns. Using this model, it predicts future business scenarios for companies and estimates increases or decreases in sales and changes in market trends. 【0255】 Step 5: 【0256】 When a user enters a question using a terminal during a meeting or board meeting, the server instantly searches for relevant data and similar past cases to generate an appropriate answer. This answer is then sent back to the terminal and displayed to the user. 【0257】 Step 6: 【0258】 The server analyzes past decision history and industry trends, and supports user decision-making by suggesting key agenda items to discuss in meetings. This process improves meeting efficiency. 【0259】 Step 7: 【0260】 The server provides customized strategic suggestions based on the user's individual profile. This enables decision-making support that is adapted to the different requirements and conditions of each user. 【0261】 (Example 1) 【0262】 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." 【0263】 In corporate management, it is essential to accurately grasp both internal information and the external environment to make swift and accurate decisions. However, the process of extracting and analyzing necessary information from vast amounts of data is cumbersome, making efficient strategy formulation difficult. Furthermore, while it is important to learn from past decision-making patterns and utilize them in future operations, few systems can effectively do this. To solve these problems, a system that supports integrated and real-time strategic decision-making is necessary. 【0264】 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. 【0265】 In this invention, the server includes means for collecting and preprocessing internal and external environmental information of a company; means for analyzing the information using natural language processing technology and identifying management decision patterns; and means for simulating future business scenarios using predictive algorithms. This enables companies to make rapid and strategic decisions based on comprehensive information. 【0266】 "Internal company information" refers to information related to the operation of a company, such as sales data, customer feedback, and employee data, which are generated within the organization. 【0267】 "External environmental information" refers to data obtained from external sources, such as information on competing companies, market trends, and economic indicators. 【0268】 "Preprocessing" is a process that improves the accuracy and reliability of collected data by removing duplicate data, correcting outliers, and imputing missing values. 【0269】 "Natural language processing technology" is a technology that enables computers to understand and analyze text data written in human language. 【0270】 "Management decision patterns" refer to the tendencies in decision-making and strategic judgment criteria of past managers. 【0271】 A "predictive algorithm" is a computational method used to predict future business and market trends based on past data. 【0272】 "Simulating business scenarios" is a process for virtually trying out future business developments based on hypotheses and analyzing the results. 【0273】 This invention is a system that supports strategic decision-making within a company. This system operates in a manner in which three entities—a server, a terminal, and a user—interact with each other. 【0274】 First, the server collects data from various sources. Specifically, it obtains internal information from a company's ERP system, customer relationship management system, and HR system, and also collects market trends and competitor data via external APIs. This information is preprocessed on the server, with duplicates and outliers removed and missing values ​​imputed. This processing improves the accuracy of the data. 【0275】 Next, the server uses natural language processing technology to analyze past management documents and speeches and extract patterns in the managers' decision-making. This technology utilizes existing natural language processing libraries. Specifically, Python libraries such as NLTK and spaCy are used for this purpose. 【0276】 Furthermore, the server builds models to predict future business scenarios through machine learning algorithms. For example, it uses scikit-learn and TensorFlow to perform regression models and time series analysis to predict future business trends. 【0277】 Users interact with the server via their devices. When a user enters a question from their device during a meeting, the server uses a generative AI model to generate the best possible answer to the question and responds to the device in real time. An example of a prompt sentence that a user might enter is, "I request a risk analysis and strategic proposal based on success stories related to entering a new market." 【0278】 Furthermore, the server analyzes past decision-making history to provide strategic proposals tailored to individual user requests and industry changes. For example, for companies considering entering new markets, it provides detailed reports based on past success stories and risk analyses to support their decision-making. 【0279】 This means the system functions as a powerful tool for companies to make strategic and efficient decisions based on data. 【0280】 The flow of the specific processing in Example 1 will be explained using Figure 11. 【0281】 Step 1: 【0282】 The server collects data from both inside and outside the company. The inputs include sales data from the company's ERP system, feedback from the customer management system, employee data from the HR system, and market trends and economic indicators through external APIs. The server obtains and integrates these input data to output a comprehensive dataset. 【0283】 Step 2: 【0284】 The server preprocesses the collected data. To improve the accuracy of the data, data cleansing such as removing duplicate data, correcting outliers, and filling in missing values is carried out. As specific operations, statistical methods and complementation algorithms based on past data are used to shape the data. As a result, clean data that can be analyzed is output. 【0285】 Step 3: 【0286】 The server analyzes the data using natural language processing techniques. The input is the clean data, and this is analyzed to identify the decision-making patterns of managers. Specifically, a natural language processing library in Python is used to extract keywords and themes from the text data. As the output of this step, knowledge and insights related to business strategies are obtained. 【0287】 Step 4: 【0288】 The server constructs a machine learning model to predict future business scenarios. The inputs include past data and learned business patterns. The server uses scikit-learn or TensorFlow to execute prediction algorithms and simulate future market trends and sales forecasts. As the output, quantitative estimates and scenarios for future trends are generated. 【0289】 Step 5: 【0290】 The user enters a question into the server via their terminal. The input is received as a prompt, which includes questions related to business decision-making. A specific example is, "We request a risk analysis and strategic proposal based on successful case studies for entering a new market." Based on this input, the server uses a generative AI model to generate the optimal answer and sends it back to the terminal as output. 【0291】 Step 6: 【0292】 The server analyzes past decision-making history and industry changes to provide customized strategic recommendations to the user. Input includes user profiles and historical data. The server analyzes this data and generates specific recommendations. The output is a strategic report tailored to the user's specific requirements. 【0293】 (Application Example 1) 【0294】 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." 【0295】 In corporate management, formulating effective strategies is crucial, but this presents the challenge of comprehensively analyzing vast amounts of internal and external data. Furthermore, a system is needed to provide appropriate strategic proposals in real time to support rapid decision-making. In urban management, too, it is necessary to efficiently utilize vast amounts of infrastructure data to formulate strategies for realizing smart cities. 【0296】 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. 【0297】 In this invention, the server includes means for collecting and cleansing corporate data and external market data, means for analyzing copyrighted works and audio to extract thought patterns, and means for building machine learning models to predict future business scenarios. This enables efficient data analysis and real-time strategic proposals in companies and cities. 【0298】 "Corporate data" refers to information about sales, customers, and employees generated within a company. 【0299】 "External market data" refers to information obtained from outside the company, such as market trends, competitor information, and economic indicators. 【0300】 "Data cleansing" refers to the process of preparing data for analysis by correcting duplicates and outliers, and imputing missing values. 【0301】 "Analyzing copyrighted works and audio" refers to extracting useful information and patterns from documents and audio using natural language processing technology. 【0302】 "Extracting thought patterns" refers to identifying and learning characteristics related to the strategic judgments of authors or speakers from documents or audio recordings. 【0303】 A "machine learning model" refers to a statistical model used to predict future trends and scenarios based on large amounts of data. 【0304】 "Generating answers to questions in real time" means immediately providing answers based on relevant information in response to user inquiries. 【0305】 "Providing strategic proposals" means recommending specific action plans and policies based on collected data and analysis results. 【0306】 "Urban infrastructure data" refers to information related to urban functions such as transportation, energy, and public safety. 【0307】 "Integration and analysis" refers to gathering various data in one place and analyzing its trends and patterns using statistical methods and the like. 【0308】 The system for realizing this invention includes a series of processes for effectively processing and analyzing a large amount of data and supporting strategic decision-making. In particular, it has a function of supporting the formulation of business strategies by using internal corporate data and external market data. Furthermore, it also has a function of analyzing urban infrastructure data for smart city operation and providing strategic advice to urban planners. 【0309】 The server first collects data such as sales, customers, employees, and market trends and competitive information from the enterprise's internal systems and external information sources. Next, in order to clean the collected data, duplicate removal, outlier correction, and data completion are performed. For this, data processing libraries such as Python are used. 【0310】 The server uses natural language processing technology to extract the thinking patterns of managers from writings and voices. In this process, machine learning frameworks such as TensorFlow and PyTorch are used. Next, a machine learning model for predicting future business scenarios is constructed by utilizing these thinking patterns and past data. 【0311】 The terminal receives questions from users during meetings and gatherings, searches for information for the server to respond quickly, and generates answers. For example, by referring to past similar cases and trends, strategic proposals are provided in real time. In this way, users can receive quick and accurate support for important decision-making. 【0312】 As a specific example, efficient management of urban functions in preparation for the approach of a typhoon can be mentioned. Based on past data and current weather forecasts, appropriate allocation of energy resources is proposed. By also using a generative AI model, the accuracy of planning can be improved. 【0313】 An example of a prompt might be a specific question such as, "In preparation for the typhoon approaching this weekend, please propose a strategic operational plan for urban infrastructure to minimize typhoon damage." 【0314】 The flow of a specific process in Application Example 1 will be explained using Figure 12. 【0315】 Step 1: 【0316】 First, the server collects corporate and market data from the company's internal systems and external sources. Inputs include sales data, customer information, employee information, and external sources such as market trends and competitor information. The output is a set of raw data. This data forms the basis for subsequent processing. Specifically, necessary data is extracted using APIs and database connectors. 【0317】 Step 2: 【0318】 The server cleanses the collected data. The raw data collected in step 1 is used as input. Data processing includes removing duplicates, correcting outliers, and imputing missing values, resulting in a formatted dataset as output. This process utilizes data processing libraries such as Python's Pandas to improve data reliability. 【0319】 Step 3: 【0320】 The server uses natural language processing technology to analyze copyrighted works and audio to extract the thought patterns of business leaders. It uses text and audio data as input. The data processing involves identifying keywords and themes from the text and audio, and obtaining the extracted patterns as output. Specifically, it utilizes TensorFlow to execute a text classification model. 【0321】 Step 4: 【0322】 The server builds a machine learning model based on these thought patterns and historical data to predict future business scenarios. It uses cleansed data and extracted thought patterns as input. For data computation, it performs predictive analytics and generates predicted scenarios as output. This process utilizes machine learning frameworks such as TensorFlow or PyTorch. 【0323】 Step 5: 【0324】 The terminal receives questions from users during a meeting, the server searches for relevant information, and generates appropriate answers. It uses user questions and scenarios as input and provides real-time strategic suggestions as output. Specifically, it performs rapid responses using database queries and natural language generation technologies. 【0325】 Step 6: 【0326】 This system provides an interface for users to make strategic decisions based on suggestions. Input is suggestion data from the terminal, and output is the display of information necessary for decision-making. Specifically, it visually presents information using a GUI on the terminal. 【0327】 Step 7: 【0328】 The server collects urban infrastructure data and creates operational plans for smart cities. It uses urban data such as transportation, energy, and public safety as input and proposes operational plans for each area as output. Specifically, it uses a generative AI model to visualize future scenarios. An example of a prompt is: "In preparation for the typhoon approaching this weekend, please propose a strategic operational plan for urban infrastructure to minimize typhoon damage." 【0329】 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. 【0330】 This invention is a system that supports strategic planning in corporate management, and further incorporates an emotion engine that recognizes user emotions. This system, which understands user emotions and the background of decision-making in real time and supports strategic decision-making, consists of the following elements. 【0331】 First, the server collects comprehensive internal and external datasets from the company and manages them in the cloud. This includes sales data, customer feedback, employee data, and even external market trends and economic indicators. The server cleanses this data and prepares it for analysis. 【0332】 Next, the emotion engine recognizes emotions from the user's voice, text tone, facial expressions, and other data. Data received via the device's camera and microphone is sent to a server and processed in real time. It recognizes emotional patterns and understands the user's current emotional state. 【0333】 The server further analyzes the writings and speeches of prominent business leaders to learn thought patterns related to business decisions. This involves utilizing natural language processing techniques to extract key keywords and strategies from the documents. 【0334】 Next, the server builds a machine learning model based on the collected data and sentiment information to predict future business scenarios. This model takes into account the current emotional state and can tailor optimal strategic suggestions to the user. 【0335】 When users want to ask a question during a meeting or other setting, they can interact through their device and input their question instantly. The server processes this information and generates an answer that takes into account the user's emotional state. This ensures that the question is answered at the most appropriate time and with the most suitable approach. 【0336】 For example, if a user is considering entering the stock market, the server will create a comprehensive report that includes risk analysis and recommended actions, taking into account historical data, market information, and even the user's current anxieties and expectations—the emotional aspects of the situation. Furthermore, by providing individually tailored suggestions, it will support decision-making that is adapted to the user's situation, including their emotions. 【0337】 Thus, the system of the present invention strongly supports effective decision-making by integrating data analysis and sentiment recognition technologies to provide managers with more personalized strategic proposals. 【0338】 The following describes the processing flow. 【0339】 Step 1: 【0340】 The server automatically collects sales data, customer feedback, employee data, and even market trends and economic indicators from internal corporate systems and external data sources. This creates a comprehensive dataset of the company's current situation and its external environment. 【0341】 Step 2: 【0342】 The server cleanses the collected data. Specifically, it improves the accuracy and reliability of the data by removing duplicate data, correcting outliers, and imputing missing values. This process is an important preparatory step for data analysis. 【0343】 Step 3: 【0344】 The device acquires data through its camera and microphone to input user voice and facial expression data. This data is sent to a server in real time for further processing. 【0345】 Step 4: 【0346】 The server uses an emotion engine to analyze voice, text, and facial expression data acquired from the user to recognize emotions. By evaluating the emotional patterns, it understands the user's current emotional state. 【0347】 Step 5: 【0348】 The server analyzes collected executive writings and speeches using natural language processing technology to learn thought patterns related to business decisions. This allows it to extract information useful for executives' strategic decision-making. 【0349】 Step 6: 【0350】 The server builds a machine learning model based on historical data and sentiment recognition results. This model is used to predict future business scenarios for companies and enables the adjustment of strategic recommendations that take into account the user's emotional state. 【0351】 Step 7: 【0352】 When users wish to interact during a meeting or board meeting, they can enter questions on a terminal. Based on the entered questions, the server generates answers considering relevant data, similar past cases, and even sentiment information, and sends them back to the terminal. 【0353】 Step 8: 【0354】 The server provides customized strategic suggestions based on the user's individual profile and emotion recognition results. This enables decision-making support that is adapted to the specific situation and emotions the user is facing. 【0355】 In this way, this system, which combines an emotion engine, provides deeper insights and personalized advice in supporting corporate decision-making. 【0356】 (Example 2) 【0357】 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". 【0358】 In modern business management, managers need to analyze vast amounts of internal and external data to make effective decisions. However, the complexity of organizing and analyzing this data makes it difficult to make quick and appropriate decisions. Furthermore, managers' emotions often influence decision-making, and there is a lack of approaches that take this into account. In addition, learning from past decision-making history is insufficient, limiting the ability to effectively predict future scenarios. 【0359】 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. 【0360】 In this invention, the server includes means for collecting and organizing information, means for analyzing documents to extract thought processes related to management decisions, means for predicting future scenarios using a learning algorithm, and means for recognizing and considering emotional states. This enables the effective organization and analysis of vast amounts of data, and realizes decision-making support that takes emotions into account. Furthermore, it becomes possible to learn past decision-making patterns and propose optimal management strategies based on them. 【0361】 "Means for collecting and organizing information" refers to the technology of acquiring diverse data from both inside and outside a company, and then scrutinizing and transforming it into a format that can be analyzed. 【0362】 "Methods for analyzing documents and extracting thought processes related to management decisions" refers to techniques for identifying thought patterns that drive management decisions from texts such as books and speeches on management. 【0363】 "Methods for predicting future scenarios using learning algorithms" refer to techniques that analyze past data and current circumstances to build machine learning models for predicting future business environments. 【0364】 "Means for recognizing and considering emotional states" refers to technologies that recognize a user's emotions from voice, text, and facial expressions, and reflect that in decision-making support. 【0365】 This invention is a system designed to support decision-making in corporate management. Its embodiments are described below. 【0366】 The server collects and organizes a wide variety of information from both internal and external sources within the company. Internal information includes sales data and employee information, while external information includes market trends and economic indicators. This information is stored on a cloud storage service and organized by a database management system. The server utilizes the Python Pandas library for data formatting and analysis. 【0367】 Furthermore, the server extracts thought processes related to management decisions through document analysis. This utilizes natural language processing technology, employing open-source libraries (e.g., NLTK and SpaCy) to extract important keywords and strategies from management-related books and speeches. 【0368】 Furthermore, the server uses machine learning algorithms to predict future business scenarios. In this process, frameworks such as Scikit-learn and TensorFlow are used to build models based on historical data and make predictions to inform business strategies. 【0369】 The device will collect the user's voice, text, and facial expressions captured by the camera. Input data obtained from the microphone and camera will be sent to a server in real time. The server will use APIs from Google and other general AI platforms to perform emotion recognition and understand the user's emotional state in real time. 【0370】 A concrete example of this system is a scenario where a user enters a prompt such as, "Please tell me about the latest trends in the stock market and an analysis of the risks of entering the market. I'm feeling a bit anxious right now, but I'd like suggestions based on concrete data." Based on this prompt, the server performs a comprehensive data analysis and immediately presents strategic suggestions that take emotions into account. In this way, useful decision-making support is provided to the user. 【0371】 The flow of the specific processing in Example 2 will be explained using Figure 13. 【0372】 Step 1: 【0373】 The server collects diverse information from both internal and external sources within the company. It utilizes databases and APIs as input, including sales data, employee information, market trends, and economic indicators. Specifically, it retrieves information through periodic database queries and external data feeds. Based on this information, the data is stored in cloud storage. 【0374】 Step 2: 【0375】 The server cleanses the collected data and formats it for analysis. The raw data collected in step 1 is used as input. Here, the Python Pandas library is used to remove noisy data and extract the necessary information. The output is a clean and organized dataset. Specific operations include imputing missing values, normalization, and data format conversion. 【0376】 Step 3: 【0377】 The device collects user voice, text, and facial expressions and sends them to the server. This includes user actions via camera and microphone input. Inputs include audio files, text input, and video footage. As output, this data is sent to the server in real time. 【0378】 Step 4: 【0379】 The server processes the user's voice, text, and facial expression data in real time to recognize their emotional state. This process uses data from step 3 as input and utilizes Google Cloud and general APIs for emotion recognition. The output is the user's emotional status. Specific processing includes tone analysis, keyword emotion weighting, and facial expression analysis. 【0380】 Step 5: 【0381】 The server analyzes documents to extract data related to business decisions. The input is text data from copyrighted works and speeches. Using natural language processing techniques, it extracts important keywords and business strategies as output. Specific operations include text mining, keyword extraction, and document classification. 【0382】 Step 6: 【0383】 The server builds a machine learning model using historical data and the current user's emotional state to predict business scenarios. The input is the dataset formatted in step 2 and the emotional data from step 4. Using Python's Scikit-learn, the output is a prediction tailored to a specific business situation. The specific operation involves data modeling, training, and prediction processes. 【0384】 Step 7: 【0385】 The user interacts with the server by entering a question via a terminal. The input is in text format. Based on the content of the question, the server generates an answer that takes into account the user's emotional state. The output is emotionally balanced strategic advice. The specific operations include query analysis, sentiment adjustment, and answer generation processes. 【0386】 Through this series of steps, the system achieves effective data processing and strategic proposals that take user emotions into consideration. 【0387】 (Application Example 2) 【0388】 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." 【0389】 In modern business management, decision-making that considers diverse information and emotional aspects is crucial. However, existing systems have struggled to adequately integrate and utilize these factors, making it impossible to provide personalized strategic proposals that take emotions and individual circumstances into account. Furthermore, in citizen-participatory policymaking, the insufficient reflection of citizens' emotions and opinions has been a challenge. In addition, achieving high-quality, real-time interaction during decision-making has not been easy. 【0390】 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. 【0391】 In this invention, the server includes means for collecting and cleansing corporate information and external market information, means for analyzing copyrighted works and audio content to extract decision-makers' thought patterns, and means for building machine learning models to predict future business scenarios. This enables the integrated use of data and emotions in corporate management and real-time strategic support based on sentiment analysis in citizen participation policies. Furthermore, customized strategic proposals are delivered to users, improving the quality of decision-making. 【0392】 "Corporate information" refers to internal data about a company, and the information necessary for management decision-making. 【0393】 "External market information" refers to market data collected from sources outside the company, including industry trends and economic indicators. 【0394】 "Cleansing" refers to the process of preparing raw data into an analyzable format, correcting or deleting inaccurate or duplicate data. 【0395】 "Copyrighted works" refer to intellectual creations such as books and papers on management and business. 【0396】 "Audio content" refers to audio data uttered as part of communication, and includes information about the words and tones used within it. 【0397】 "Extracting thought patterns" refers to analyzing important concepts and trends from copyrighted works or audio content to identify a foundation for decision-making that is useful in achieving specific goals. 【0398】 A "machine learning model" refers to an algorithm or mathematical model that uses large amounts of data to discover patterns and predict future situations and outcomes. 【0399】 "Predicting business scenarios" means statistically estimating future possibilities and outcomes related to management and policy decisions. 【0400】 "Analyzing emotional state" means identifying the user's emotional state based on inputs such as facial expressions and voice. 【0401】 "Summarizing policy proposals" means condensing suggestions from citizens and decision-makers and clearly presenting the key elements. 【0402】 A "customized strategy proposal" involves presenting a strategy tailored to individual needs and conditions, based on the information received and the user's current situation. 【0403】 In this invention, a server collects corporate and external market information, cleanses it, and converts it into an analyzable format. For example, data including sales data, customer feedback, employee data, and external market trends and economic indicators are centrally managed on the cloud. The server also analyzes copyrighted works and audio content to extract the thought patterns of decision-makers. In this process, natural language processing technology is used to efficiently extract keywords and strategies from documents. 【0404】 The server further builds machine learning models based on collected data and emotional information to predict future business scenarios. This enables the integrated use of real-time data and emotions in corporate management. In particular, in citizen-participatory policy proposals, it analyzes emotional states to identify emotions from the user's facial expressions and voice, and then summarizes and provides policy proposals based on that. 【0405】 Users can interact in real time through their smartphones or smart glasses. When users submit suggestions or questions, the system quickly generates more personalized strategic suggestions based on sentiment analysis and provides feedback to the user. This feedback is customized to suit the individual user's needs and circumstances. 【0406】 For example, if a user suggests "I want more lighting in the park," the emotion engine analyzes the user's anxieties and expectations. Based on this analysis, policymakers are provided with a summary such as "There is an emotional background of wanting improved public safety." In this way, the system makes optimized suggestions while taking emotional data into consideration. 【0407】 An example of a prompt for a generative AI model might be: "Based on the sentiment analysis results of the user's suggestion, 'We want more lights in the park,' generate a summary that should be conveyed to policymakers. Please consider the emotional context and also suggest possible solutions." 【0408】 The flow of a specific process in Application Example 2 will be explained using Figure 14. 【0409】 Step 1: 【0410】 The server collects corporate and external market information. It receives data such as sales data, customer feedback, employee data, external market trends, and economic indicators as input. This data is then cleansed and converted into an analyzable format. Specifically, it corrects and removes inaccuracies and duplicates, and consolidates them into a unified format. 【0411】 Step 2: 【0412】 The server analyzes copyrighted material and audio content to extract the thought patterns of decision-makers. It accepts books and audio data related to business management as input. Using natural language processing techniques, it extracts important keywords and statements from the documents and generates a model of thought patterns. Specifically, it uses document analysis algorithms to perform vocabulary frequency analysis and contextual understanding. 【0413】 Step 3: 【0414】 Based on data and sentiment information collected by the server, a machine learning model is built to predict future business scenarios. Input includes cleansed data and sentiment states. The model analyzes the data using relevant statistical methods and algorithms to predict future changes. Specifically, it performs the training and evaluation processes of the predictive model. 【0415】 Step 4: 【0416】 Users submit policy proposals and questions through their devices. The devices take user text and voice data as input. The devices then transfer this information to a server in real time for analysis by an emotion engine. Specifically, they use APIs for speech recognition and emotion analysis as interfaces. 【0417】 Step 5: 【0418】 The server analyzes the user's emotional state and identifies emotional patterns. It processes voice and text data sent from the terminal as input and applies an emotion recognition algorithm. The identified emotional state is generated as output. Specific operations include voice tone analysis and text sentiment analysis. 【0419】 Step 6: 【0420】 The server summarizes policy proposals and generates strategic proposals based on the analysis results. It uses emotional states and data analysis results obtained in steps 1 through 3 as input. The output consists of user-optimized policy proposals and strategic proposals, which are sent to the user and policymakers. Specifically, it utilizes a generative AI model to automatically generate expert prompts. 【0421】 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. 【0422】 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. 【0423】 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. 【0424】 [Third Embodiment] 【0425】 Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment. 【0426】 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. 【0427】 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). 【0428】 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. 【0429】 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. 【0430】 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). 【0431】 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. 【0432】 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. 【0433】 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. 【0434】 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. 【0435】 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. 【0436】 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". 【0437】 This invention is a system for supporting strategic planning in corporate management, providing strategic advice to managers using internal and external corporate data. Embodiments of this invention primarily function through the interaction of servers, terminals, and users. 【0438】 First, the server automatically collects information such as sales data, customer feedback, and employee data from the company's internal systems. In parallel, it acquires market trends, competitor information, and economic indicators from external data sources. This creates a comprehensive dataset of the company's current situation and market environment. 【0439】 Next, the server performs data cleansing to prepare the collected data for analysis. This includes removing duplicate data, correcting outliers, and properly imputing missing values. This improves the accuracy and reliability of the data. 【0440】 Furthermore, the server analyzes copyrighted works and speeches to extract the thought patterns of prominent business leaders. This involves using natural language processing technology to identify and learn keywords and themes related to the strategic decisions of these leaders. This provides insights that can be used to formulate new strategies. 【0441】 The server builds a machine learning model based on historical data and learned thought patterns. This model predicts future business scenarios for a company and estimates increases or decreases in sales and changes in market trends. This allows managers to quantitatively evaluate future trends. 【0442】 During meetings and board meetings, the terminal receives questions from users and enables real-time responses. The server quickly searches for relevant data and similar past cases, generates appropriate strategic recommendations, and sends them back to the terminal. In this way, executives can receive immediate support in making important decisions. 【0443】 Furthermore, the server analyzes past decision history and industry trends to suggest topics for discussion in meetings. This allows users to focus on important issues and enables efficient meeting management. 【0444】 Finally, the server provides customized strategic recommendations based on the user's individual requirements and profile. This enables optimized decision-making support for each user. For example, for a company considering entering a new market, it provides a detailed report on the risks and opportunities of entry, based on past success stories, to support management decisions. 【0445】 Through these functions, the system of the present invention provides powerful support for companies to make data-driven strategic decisions. 【0446】 The following describes the processing flow. 【0447】 Step 1: 【0448】 The server collects data from the company's internal systems and external data sources. Internal data includes sales data and customer feedback, while external data includes market trends and economic indicators. This creates a comprehensive dataset of the company's current situation and external environment. 【0449】 Step 2: 【0450】 The server performs data cleansing on the collected data. Duplicate data is removed, outliers are corrected, and missing values ​​are appropriately imputed. This increases the accuracy and reliability of the data used for analysis. 【0451】 Step 3: 【0452】 The server analyzes copyrighted works and speeches using natural language processing technology. This allows it to identify keywords related to the thought patterns and strategic decisions of prominent business leaders, and then uses this information to learn from them. 【0453】 Step 4: 【0454】 The server builds a machine learning model based on historical data and learned thought patterns. Using this model, it predicts future business scenarios for companies and estimates increases or decreases in sales and changes in market trends. 【0455】 Step 5: 【0456】 When a user enters a question using a terminal during a meeting or board meeting, the server instantly searches for relevant data and similar past cases to generate an appropriate answer. This answer is then sent back to the terminal and displayed to the user. 【0457】 Step 6: 【0458】 The server analyzes past decision history and industry trends, and supports user decision-making by suggesting key agenda items to discuss in meetings. This process improves meeting efficiency. 【0459】 Step 7: 【0460】 The server provides customized strategic suggestions based on the user's individual profile. This enables decision-making support that is adapted to the different requirements and conditions of each user. 【0461】 (Example 1) 【0462】 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." 【0463】 In corporate management, it is essential to accurately grasp both internal information and the external environment to make swift and accurate decisions. However, the process of extracting and analyzing necessary information from vast amounts of data is cumbersome, making efficient strategy formulation difficult. Furthermore, while it is important to learn from past decision-making patterns and utilize them in future operations, few systems can effectively do this. To solve these problems, a system that supports integrated and real-time strategic decision-making is necessary. 【0464】 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. 【0465】 In this invention, the server includes means for collecting and preprocessing internal and external environmental information of a company; means for analyzing the information using natural language processing technology and identifying management decision patterns; and means for simulating future business scenarios using predictive algorithms. This enables companies to make rapid and strategic decisions based on comprehensive information. 【0466】 "Internal company information" refers to information related to the operation of a company, such as sales data, customer feedback, and employee data, which are generated within the organization. 【0467】 "External environmental information" refers to data obtained from external sources, such as information on competing companies, market trends, and economic indicators. 【0468】 "Preprocessing" is a process that improves the accuracy and reliability of collected data by removing duplicate data, correcting outliers, and imputing missing values. 【0469】 "Natural language processing technology" is a technology that enables computers to understand and analyze text data written in human language. 【0470】 "Management decision patterns" refer to the tendencies in decision-making and strategic judgment criteria of past managers. 【0471】 A "predictive algorithm" is a computational method used to predict future business and market trends based on past data. 【0472】 "Simulating business scenarios" is a process for virtually trying out future business developments based on hypotheses and analyzing the results. 【0473】 This invention is a system that supports strategic decision-making within a company. This system operates in a manner in which three entities—a server, a terminal, and a user—interact with each other. 【0474】 First, the server collects data from various sources. Specifically, it obtains internal information from a company's ERP system, customer relationship management system, and HR system, and also collects market trends and competitor data via external APIs. This information is preprocessed on the server, with duplicates and outliers removed and missing values ​​imputed. This processing improves the accuracy of the data. 【0475】 Next, the server uses natural language processing technology to analyze past management documents and speeches and extract patterns in the managers' decision-making. This technology utilizes existing natural language processing libraries. Specifically, Python libraries such as NLTK and spaCy are used for this purpose. 【0476】 Furthermore, the server builds models to predict future business scenarios through machine learning algorithms. For example, it uses scikit-learn and TensorFlow to perform regression models and time series analysis to predict future business trends. 【0477】 Users interact with the server via their devices. When a user enters a question from their device during a meeting, the server uses a generative AI model to generate the best possible answer to the question and responds to the device in real time. An example of a prompt sentence that a user might enter is, "I request a risk analysis and strategic proposal based on success stories related to entering a new market." 【0478】 Furthermore, the server analyzes past decision-making history to provide strategic proposals tailored to individual user requests and industry changes. For example, for companies considering entering new markets, it provides detailed reports based on past success stories and risk analyses to support their decision-making. 【0479】 This means the system functions as a powerful tool for companies to make strategic and efficient decisions based on data. 【0480】 The flow of the specific processing in Example 1 will be explained using Figure 11. 【0481】 Step 1: 【0482】 The server collects data from both inside and outside the company. Inputs include sales data from the company's ERP system, feedback from customer relationship management (CRM) systems, employee data from HR systems, and market trends and economic indicators via external APIs. The server retrieves and integrates this input data to output a comprehensive dataset. 【0483】 Step 2: 【0484】 The server preprocesses the collected data. To improve data accuracy, it performs data cleansing, such as removing duplicate data, correcting outliers, and imputing missing values. Specifically, it uses statistical methods and imputation algorithms based on historical data to reshape the data. This results in clean data that can be analyzed. 【0485】 Step 3: 【0486】 The server analyzes data using natural language processing techniques. The input is clean data, which is then analyzed to identify patterns in managers' decision-making. Specifically, it uses Python's natural language processing library to extract keywords and themes from text data. The output of this step is knowledge and insights related to business strategy. 【0487】 Step 4: 【0488】 The server builds machine learning models and predicts future business scenarios. Inputs include historical data and learned business patterns. The server uses scikit-learn and TensorFlow to execute predictive algorithms and simulate future market trends and sales forecasts. Outputs include quantitative estimates and scenarios for future trends. 【0489】 Step 5: 【0490】 The user enters a question into the server via their terminal. The input is received as a prompt, which includes questions related to business decision-making. A specific example is, "We request a risk analysis and strategic proposal based on successful case studies for entering a new market." Based on this input, the server uses a generative AI model to generate the optimal answer and sends it back to the terminal as output. 【0491】 Step 6: 【0492】 The server analyzes past decision-making history and industry changes to provide customized strategic recommendations to the user. Input includes user profiles and historical data. The server analyzes this data and generates specific recommendations. The output is a strategic report tailored to the user's specific requirements. 【0493】 (Application Example 1) 【0494】 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." 【0495】 In corporate management, formulating effective strategies is crucial, but this presents the challenge of comprehensively analyzing vast amounts of internal and external data. Furthermore, a system is needed to provide appropriate strategic proposals in real time to support rapid decision-making. In urban management, too, it is necessary to efficiently utilize vast amounts of infrastructure data to formulate strategies for realizing smart cities. 【0496】 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. 【0497】 In this invention, the server includes means for collecting and cleansing corporate data and external market data, means for analyzing copyrighted works and audio to extract thought patterns, and means for building machine learning models to predict future business scenarios. This enables efficient data analysis and real-time strategic proposals in companies and cities. 【0498】 "Corporate data" refers to information about sales, customers, and employees generated within a company. 【0499】 "External market data" refers to information obtained from outside the company, such as market trends, competitor information, and economic indicators. 【0500】 "Data cleansing" refers to the process of preparing data for analysis by correcting duplicates and outliers, and imputing missing values. 【0501】 "Analyzing copyrighted works and audio" refers to extracting useful information and patterns from documents and audio using natural language processing technology. 【0502】 "Extracting thought patterns" refers to identifying and learning characteristics related to the strategic judgments of authors or speakers from documents or audio recordings. 【0503】 A "machine learning model" refers to a statistical model used to predict future trends and scenarios based on large amounts of data. 【0504】 "Generating answers to questions in real time" means immediately providing answers based on relevant information in response to user inquiries. 【0505】 "Providing strategic proposals" means recommending specific action plans and policies based on collected data and analysis results. 【0506】 "Urban infrastructure data" refers to information related to urban functions such as transportation, energy, and public safety. 【0507】 "Data aggregation and analysis" refers to the process of gathering diverse data in one place and analyzing its trends and patterns using statistical methods. 【0508】 The system for realizing this invention includes a series of processes for effectively processing and analyzing large amounts of data to support strategic decision-making. In particular, it has the function of supporting the formulation of management strategies using internal corporate data and external market data. Furthermore, it also has the function of analyzing urban infrastructure data for smart city management and providing strategic advice to urban planners. 【0509】 The server first collects data such as sales, customers, employees, market trends, and competitor information from the company's internal systems and external sources. Next, it cleans the collected data by removing duplicates, correcting outliers, and imputing data. This is done using data processing libraries such as Python. 【0510】 The server uses natural language processing techniques to extract thought patterns from copyrighted works and audio recordings. This process utilizes machine learning frameworks such as TensorFlow and PyTorch. Next, these thought patterns and historical data are used to build a machine learning model that predicts future business scenarios. 【0511】 The terminal receives questions from users during meetings and conferences, searches for information to enable the server to respond quickly, and generates answers. For example, it can refer to similar past cases and trends to provide real-time strategic suggestions. In this way, users can receive quick and accurate support for important decision-making. 【0512】 A concrete example is the efficient management of urban functions in preparation for an approaching typhoon. Based on historical data and current weather forecasts, an appropriate allocation of energy resources is proposed. By using generative AI models in conjunction, the accuracy of the planning can be improved. 【0513】 An example of a prompt might be a specific question such as, "In preparation for the typhoon approaching this weekend, please propose a strategic operational plan for urban infrastructure to minimize typhoon damage." 【0514】 The flow of a specific process in Application Example 1 will be explained using Figure 12. 【0515】 Step 1: 【0516】 First, the server collects corporate and market data from the company's internal systems and external sources. Inputs include sales data, customer information, employee information, and external sources such as market trends and competitor information. The output is a set of raw data. This data forms the basis for subsequent processing. Specifically, necessary data is extracted using APIs and database connectors. 【0517】 Step 2: 【0518】 The server cleanses the collected data. The raw data collected in step 1 is used as input. Data processing includes removing duplicates, correcting outliers, and imputing missing values, resulting in a formatted dataset as output. This process utilizes data processing libraries such as Python's Pandas to improve data reliability. 【0519】 Step 3: 【0520】 The server uses natural language processing technology to analyze copyrighted works and audio to extract the thought patterns of business leaders. It uses text and audio data as input. The data processing involves identifying keywords and themes from the text and audio, and obtaining the extracted patterns as output. Specifically, it utilizes TensorFlow to execute a text classification model. 【0521】 Step 4: 【0522】 The server builds a machine learning model based on these thought patterns and historical data to predict future business scenarios. It uses cleansed data and extracted thought patterns as input. For data computation, it performs predictive analytics and generates predicted scenarios as output. This process utilizes machine learning frameworks such as TensorFlow or PyTorch. 【0523】 Step 5: 【0524】 The terminal receives questions from users during a meeting, the server searches for relevant information, and generates appropriate answers. It uses user questions and scenarios as input and provides real-time strategic suggestions as output. Specifically, it performs rapid responses using database queries and natural language generation technologies. 【0525】 Step 6: 【0526】 This system provides an interface for users to make strategic decisions based on suggestions. Input is suggestion data from the terminal, and output is the display of information necessary for decision-making. Specifically, it visually presents information using a GUI on the terminal. 【0527】 Step 7: 【0528】 The server collects urban infrastructure data and creates operational plans for smart cities. It uses urban data such as transportation, energy, and public safety as input and proposes operational plans for each area as output. Specifically, it uses a generative AI model to visualize future scenarios. An example of a prompt is: "In preparation for the typhoon approaching this weekend, please propose a strategic operational plan for urban infrastructure to minimize typhoon damage." 【0529】 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. 【0530】 This invention is a system that supports strategic planning in corporate management, and further incorporates an emotion engine that recognizes user emotions. This system, which understands user emotions and the background of decision-making in real time and supports strategic decision-making, consists of the following elements. 【0531】 First, the server collects comprehensive internal and external datasets from the company and manages them in the cloud. This includes sales data, customer feedback, employee data, and even external market trends and economic indicators. The server cleanses this data and prepares it for analysis. 【0532】 Next, the emotion engine recognizes emotions from the user's voice, text tone, facial expressions, and other data. Data received via the device's camera and microphone is sent to a server and processed in real time. It recognizes emotional patterns and understands the user's current emotional state. 【0533】 The server further analyzes the writings and speeches of prominent business leaders to learn thought patterns related to business decisions. This involves utilizing natural language processing techniques to extract key keywords and strategies from the documents. 【0534】 Next, the server builds a machine learning model based on the collected data and sentiment information to predict future business scenarios. This model takes into account the current emotional state and can tailor optimal strategic suggestions to the user. 【0535】 When users want to ask a question during a meeting or other setting, they can interact through their device and input their question instantly. The server processes this information and generates an answer that takes into account the user's emotional state. This ensures that the question is answered at the most appropriate time and with the most suitable approach. 【0536】 For example, if a user is considering entering the stock market, the server will create a comprehensive report that includes risk analysis and recommended actions, taking into account historical data, market information, and even the user's current anxieties and expectations—the emotional aspects of the situation. Furthermore, by providing individually tailored suggestions, it will support decision-making that is adapted to the user's situation, including their emotions. 【0537】 Thus, the system of the present invention strongly supports effective decision-making by integrating data analysis and sentiment recognition technologies to provide managers with more personalized strategic proposals. 【0538】 The following describes the processing flow. 【0539】 Step 1: 【0540】 The server automatically collects sales data, customer feedback, employee data, and even market trends and economic indicators from internal corporate systems and external data sources. This creates a comprehensive dataset of the company's current situation and its external environment. 【0541】 Step 2: 【0542】 The server cleanses the collected data. Specifically, it improves the accuracy and reliability of the data by removing duplicate data, correcting outliers, and imputing missing values. This process is an important preparatory step for data analysis. 【0543】 Step 3: 【0544】 The device acquires data through its camera and microphone to input user voice and facial expression data. This data is sent to a server in real time for further processing. 【0545】 Step 4: 【0546】 The server uses an emotion engine to analyze voice, text, and facial expression data acquired from the user to recognize emotions. By evaluating the emotional patterns, it understands the user's current emotional state. 【0547】 Step 5: 【0548】 The server analyzes collected executive writings and speeches using natural language processing technology to learn thought patterns related to business decisions. This allows it to extract information useful for executives' strategic decision-making. 【0549】 Step 6: 【0550】 The server builds a machine learning model based on historical data and sentiment recognition results. This model is used to predict future business scenarios for companies and enables the adjustment of strategic recommendations that take into account the user's emotional state. 【0551】 Step 7: 【0552】 When users wish to interact during a meeting or board meeting, they can enter questions on a terminal. Based on the entered questions, the server generates answers considering relevant data, similar past cases, and even sentiment information, and sends them back to the terminal. 【0553】 Step 8: 【0554】 The server provides customized strategic suggestions based on the user's individual profile and emotion recognition results. This enables decision-making support that is adapted to the specific situation and emotions the user is facing. 【0555】 In this way, this system, which combines an emotion engine, provides deeper insights and personalized advice in supporting corporate decision-making. 【0556】 (Example 2) 【0557】 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." 【0558】 In modern business management, managers need to analyze vast amounts of internal and external data to make effective decisions. However, the complexity of organizing and analyzing this data makes it difficult to make quick and appropriate decisions. Furthermore, managers' emotions often influence decision-making, and there is a lack of approaches that take this into account. In addition, learning from past decision-making history is insufficient, limiting the ability to effectively predict future scenarios. 【0559】 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. 【0560】 In this invention, the server includes means for collecting and organizing information, means for analyzing documents to extract thought processes related to management decisions, means for predicting future scenarios using a learning algorithm, and means for recognizing and considering emotional states. This enables the effective organization and analysis of vast amounts of data, and realizes decision-making support that takes emotions into account. Furthermore, it becomes possible to learn past decision-making patterns and propose optimal management strategies based on them. 【0561】 "Means for collecting and organizing information" refers to the technology of acquiring diverse data from both inside and outside a company, and then scrutinizing and transforming it into a format that can be analyzed. 【0562】 "Methods for analyzing documents and extracting thought processes related to management decisions" refers to techniques for identifying thought patterns that drive management decisions from texts such as books and speeches on management. 【0563】 "Methods for predicting future scenarios using learning algorithms" refer to techniques that analyze past data and current circumstances to build machine learning models for predicting future business environments. 【0564】 "Means for recognizing and considering emotional states" refers to technologies that recognize a user's emotions from voice, text, and facial expressions, and reflect that in decision-making support. 【0565】 This invention is a system designed to support decision-making in corporate management. Its embodiments are described below. 【0566】 The server collects and organizes a wide variety of information from both internal and external sources within the company. Internal information includes sales data and employee information, while external information includes market trends and economic indicators. This information is stored on a cloud storage service and organized by a database management system. The server utilizes the Python Pandas library for data formatting and analysis. 【0567】 Furthermore, the server extracts thought processes related to management decisions through document analysis. This utilizes natural language processing technology, employing open-source libraries (e.g., NLTK and SpaCy) to extract important keywords and strategies from management-related books and speeches. 【0568】 Furthermore, the server uses machine learning algorithms to predict future business scenarios. In this process, frameworks such as Scikit-learn and TensorFlow are used to build models based on historical data and make predictions to inform business strategies. 【0569】 The device will collect the user's voice, text, and facial expressions captured by the camera. Input data obtained from the microphone and camera will be sent to a server in real time. The server will use APIs from Google and other general AI platforms to perform emotion recognition and understand the user's emotional state in real time. 【0570】 A concrete example of this system is a scenario where a user enters a prompt such as, "Please tell me about the latest trends in the stock market and an analysis of the risks of entering the market. I'm feeling a bit anxious right now, but I'd like suggestions based on concrete data." Based on this prompt, the server performs a comprehensive data analysis and immediately presents strategic suggestions that take emotions into account. In this way, useful decision-making support is provided to the user. 【0571】 The flow of the specific processing in Example 2 will be explained using Figure 13. 【0572】 Step 1: 【0573】 The server collects diverse information from both internal and external sources within the company. It utilizes databases and APIs as input, including sales data, employee information, market trends, and economic indicators. Specifically, it retrieves information through periodic database queries and external data feeds. Based on this information, the data is stored in cloud storage. 【0574】 Step 2: 【0575】 The server cleanses the collected data and formats it for analysis. The raw data collected in step 1 is used as input. Here, the Python Pandas library is used to remove noisy data and extract the necessary information. The output is a clean and organized dataset. Specific operations include imputing missing values, normalization, and data format conversion. 【0576】 Step 3: 【0577】 The device collects user voice, text, and facial expressions and sends them to the server. This includes user actions via camera and microphone input. Inputs include audio files, text input, and video footage. As output, this data is sent to the server in real time. 【0578】 Step 4: 【0579】 The server processes the user's voice, text, and facial expression data in real time to recognize their emotional state. This process uses data from step 3 as input and utilizes Google Cloud and general APIs for emotion recognition. The output is the user's emotional status. Specific processing includes tone analysis, keyword emotion weighting, and facial expression analysis. 【0580】 Step 5: 【0581】 The server analyzes documents to extract data related to business decisions. The input is text data from copyrighted works and speeches. Using natural language processing techniques, it extracts important keywords and business strategies as output. Specific operations include text mining, keyword extraction, and document classification. 【0582】 Step 6: 【0583】 The server builds a machine learning model using historical data and the current user's emotional state to predict business scenarios. The input is the dataset formatted in step 2 and the emotional data from step 4. Using Python's Scikit-learn, the output is a prediction tailored to a specific business situation. The specific operation involves data modeling, training, and prediction processes. 【0584】 Step 7: 【0585】 The user interacts with the server by entering a question via a terminal. The input is in text format. Based on the content of the question, the server generates an answer that takes into account the user's emotional state. The output is emotionally balanced strategic advice. The specific operations include query analysis, sentiment adjustment, and answer generation processes. 【0586】 Through this series of steps, the system achieves effective data processing and strategic proposals that take user emotions into consideration. 【0587】 (Application Example 2) 【0588】 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." 【0589】 In modern business management, decision-making that considers diverse information and emotional aspects is crucial. However, existing systems have struggled to adequately integrate and utilize these factors, making it impossible to provide personalized strategic proposals that take emotions and individual circumstances into account. Furthermore, in citizen-participatory policymaking, the insufficient reflection of citizens' emotions and opinions has been a challenge. In addition, achieving high-quality, real-time interaction during decision-making has not been easy. 【0590】 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. 【0591】 In this invention, the server includes means for collecting and cleansing corporate information and external market information, means for analyzing copyrighted works and audio content to extract decision-makers' thought patterns, and means for building machine learning models to predict future business scenarios. This enables the integrated use of data and emotions in corporate management and real-time strategic support based on sentiment analysis in citizen participation policies. Furthermore, customized strategic proposals are delivered to users, improving the quality of decision-making. 【0592】 "Corporate information" refers to internal data about a company, and the information necessary for management decision-making. 【0593】 "External market information" refers to market data collected from sources outside the company, including industry trends and economic indicators. 【0594】 "Cleansing" refers to the process of preparing raw data into an analyzable format, correcting or deleting inaccurate or duplicate data. 【0595】 "Copyrighted works" refer to intellectual creations such as books and papers on management and business. 【0596】 "Audio content" refers to audio data uttered as part of communication, and includes information about the words and tones used within it. 【0597】 "Extracting thought patterns" refers to analyzing important concepts and trends from copyrighted works or audio content to identify a foundation for decision-making that is useful in achieving specific goals. 【0598】 A "machine learning model" refers to an algorithm or mathematical model that uses large amounts of data to discover patterns and predict future situations and outcomes. 【0599】 "Predicting business scenarios" means statistically estimating future possibilities and outcomes related to management and policy decisions. 【0600】 "Analyzing emotional state" means identifying the user's emotional state based on inputs such as facial expressions and voice. 【0601】 "Summarizing policy proposals" means condensing suggestions from citizens and decision-makers and clearly presenting the key elements. 【0602】 A "customized strategy proposal" involves presenting a strategy tailored to individual needs and conditions, based on the information received and the user's current situation. 【0603】 In this invention, a server collects corporate and external market information, cleanses it, and converts it into an analyzable format. For example, data including sales data, customer feedback, employee data, and external market trends and economic indicators are centrally managed on the cloud. The server also analyzes copyrighted works and audio content to extract the thought patterns of decision-makers. In this process, natural language processing technology is used to efficiently extract keywords and strategies from documents. 【0604】 The server further builds machine learning models based on collected data and emotional information to predict future business scenarios. This enables the integrated use of real-time data and emotions in corporate management. In particular, in citizen-participatory policy proposals, it analyzes emotional states to identify emotions from the user's facial expressions and voice, and then summarizes and provides policy proposals based on that. 【0605】 Users can interact in real time through their smartphones or smart glasses. When users submit suggestions or questions, the system quickly generates more personalized strategic suggestions based on sentiment analysis and provides feedback to the user. This feedback is customized to suit the individual user's needs and circumstances. 【0606】 For example, if a user suggests "I want more lighting in the park," the emotion engine analyzes the user's anxieties and expectations. Based on this analysis, policymakers are provided with a summary such as "There is an emotional background of wanting improved public safety." In this way, the system makes optimized suggestions while taking emotional data into consideration. 【0607】 An example of a prompt for a generative AI model might be: "Based on the sentiment analysis results of the user's suggestion, 'We want more lights in the park,' generate a summary that should be conveyed to policymakers. Please consider the emotional context and also suggest possible solutions." 【0608】 The flow of a specific process in Application Example 2 will be explained using Figure 14. 【0609】 Step 1: 【0610】 The server collects corporate and external market information. It receives data such as sales data, customer feedback, employee data, external market trends, and economic indicators as input. This data is then cleansed and converted into an analyzable format. Specifically, it corrects and removes inaccuracies and duplicates, and consolidates them into a unified format. 【0611】 Step 2: 【0612】 The server analyzes copyrighted material and audio content to extract the thought patterns of decision-makers. It accepts books and audio data related to business management as input. Using natural language processing techniques, it extracts important keywords and statements from the documents and generates a model of thought patterns. Specifically, it uses document analysis algorithms to perform vocabulary frequency analysis and contextual understanding. 【0613】 Step 3: 【0614】 Based on data and sentiment information collected by the server, a machine learning model is built to predict future business scenarios. Input includes cleansed data and sentiment states. The model analyzes the data using relevant statistical methods and algorithms to predict future changes. Specifically, it performs the training and evaluation processes of the predictive model. 【0615】 Step 4: 【0616】 Users submit policy proposals and questions through their devices. The devices take user text and voice data as input. The devices then transfer this information to a server in real time for analysis by an emotion engine. Specifically, they use APIs for speech recognition and emotion analysis as interfaces. 【0617】 Step 5: 【0618】 The server analyzes the user's emotional state and identifies emotional patterns. It processes voice and text data sent from the terminal as input and applies an emotion recognition algorithm. The identified emotional state is generated as output. Specific operations include voice tone analysis and text sentiment analysis. 【0619】 Step 6: 【0620】 The server summarizes policy proposals and generates strategic proposals based on the analysis results. It uses emotional states and data analysis results obtained in steps 1 through 3 as input. The output consists of user-optimized policy proposals and strategic proposals, which are sent to the user and policymakers. Specifically, it utilizes a generative AI model to automatically generate expert prompts. 【0621】 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. 【0622】 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. 【0623】 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. 【0624】 [Fourth Embodiment] 【0625】 Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment. 【0626】 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. 【0627】 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). 【0628】 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. 【0629】 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. 【0630】 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). 【0631】 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. 【0632】 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. 【0633】 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. 【0634】 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. 【0635】 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. 【0636】 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. 【0637】 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". 【0638】 This invention is a system for supporting strategic planning in corporate management, providing strategic advice to managers using internal and external corporate data. Embodiments of this invention primarily function through the interaction of servers, terminals, and users. 【0639】 First, the server automatically collects information such as sales data, customer feedback, and employee data from the company's internal systems. In parallel, it acquires market trends, competitor information, and economic indicators from external data sources. This creates a comprehensive dataset of the company's current situation and market environment. 【0640】 Next, the server performs data cleansing to prepare the collected data for analysis. This includes removing duplicate data, correcting outliers, and properly imputing missing values. This improves the accuracy and reliability of the data. 【0641】 Furthermore, the server analyzes copyrighted works and speeches to extract the thought patterns of prominent business leaders. This involves using natural language processing technology to identify and learn keywords and themes related to the strategic decisions of these leaders. This provides insights that can be used to formulate new strategies. 【0642】 The server builds a machine learning model based on historical data and learned thought patterns. This model predicts future business scenarios for a company and estimates increases or decreases in sales and changes in market trends. This allows managers to quantitatively evaluate future trends. 【0643】 During meetings and board meetings, the terminal receives questions from users and enables real-time responses. The server quickly searches for relevant data and similar past cases, generates appropriate strategic recommendations, and sends them back to the terminal. In this way, executives can receive immediate support in making important decisions. 【0644】 Furthermore, the server analyzes past decision history and industry trends to suggest topics for discussion in meetings. This allows users to focus on important issues and enables efficient meeting management. 【0645】 Finally, the server provides customized strategic recommendations based on the user's individual requirements and profile. This enables optimized decision-making support for each user. For example, for a company considering entering a new market, it provides a detailed report on the risks and opportunities of entry, based on past success stories, to support management decisions. 【0646】 Through these functions, the system of the present invention provides powerful support for companies to make data-driven strategic decisions. 【0647】 The following describes the processing flow. 【0648】 Step 1: 【0649】 The server collects data from the company's internal systems and external data sources. Internal data includes sales data and customer feedback, while external data includes market trends and economic indicators. This creates a comprehensive dataset of the company's current situation and external environment. 【0650】 Step 2: 【0651】 The server performs data cleansing on the collected data. Duplicate data is removed, outliers are corrected, and missing values ​​are appropriately imputed. This increases the accuracy and reliability of the data used for analysis. 【0652】 Step 3: 【0653】 The server analyzes copyrighted works and speeches using natural language processing technology. This allows it to identify keywords related to the thought patterns and strategic decisions of prominent business leaders, and then uses this information to learn from them. 【0654】 Step 4: 【0655】 The server builds a machine learning model based on historical data and learned thought patterns. Using this model, it predicts future business scenarios for companies and estimates increases or decreases in sales and changes in market trends. 【0656】 Step 5: 【0657】 When a user enters a question using a terminal during a meeting or board meeting, the server instantly searches for relevant data and similar past cases to generate an appropriate answer. This answer is then sent back to the terminal and displayed to the user. 【0658】 Step 6: 【0659】 The server analyzes past decision history and industry trends, and supports user decision-making by suggesting key agenda items to discuss in meetings. This process improves meeting efficiency. 【0660】 Step 7: 【0661】 The server provides customized strategic suggestions based on the user's individual profile. This enables decision-making support that is adapted to the different requirements and conditions of each user. 【0662】 (Example 1) 【0663】 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". 【0664】 In corporate management, it is essential to accurately grasp both internal information and the external environment to make swift and accurate decisions. However, the process of extracting and analyzing necessary information from vast amounts of data is cumbersome, making efficient strategy formulation difficult. Furthermore, while it is important to learn from past decision-making patterns and utilize them in future operations, few systems can effectively do this. To solve these problems, a system that supports integrated and real-time strategic decision-making is necessary. 【0665】 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. 【0666】 In this invention, the server includes means for collecting and preprocessing internal and external environmental information of a company; means for analyzing the information using natural language processing technology and identifying management decision patterns; and means for simulating future business scenarios using predictive algorithms. This enables companies to make rapid and strategic decisions based on comprehensive information. 【0667】 "Internal company information" refers to information related to the operation of a company, such as sales data, customer feedback, and employee data, which are generated within the organization. 【0668】 "External environmental information" refers to data obtained from external sources, such as information on competing companies, market trends, and economic indicators. 【0669】 "Preprocessing" is a process that improves the accuracy and reliability of collected data by removing duplicate data, correcting outliers, and imputing missing values. 【0670】 "Natural language processing technology" is a technology that enables computers to understand and analyze text data written in human language. 【0671】 "Management decision patterns" refer to the tendencies in decision-making and strategic judgment criteria of past managers. 【0672】 A "predictive algorithm" is a computational method used to predict future business and market trends based on past data. 【0673】 "Simulating business scenarios" is a process for virtually trying out future business developments based on hypotheses and analyzing the results. 【0674】 This invention is a system that supports strategic decision-making within a company. This system operates in a manner in which three entities—a server, a terminal, and a user—interact with each other. 【0675】 First, the server collects data from various sources. Specifically, it obtains internal information from a company's ERP system, customer relationship management system, and HR system, and also collects market trends and competitor data via external APIs. This information is preprocessed on the server, with duplicates and outliers removed and missing values ​​imputed. This processing improves the accuracy of the data. 【0676】 Next, the server uses natural language processing technology to analyze past management documents and speeches and extract patterns in the managers' decision-making. This technology utilizes existing natural language processing libraries. Specifically, Python libraries such as NLTK and spaCy are used for this purpose. 【0677】 Furthermore, the server builds models to predict future business scenarios through machine learning algorithms. For example, it uses scikit-learn and TensorFlow to perform regression models and time series analysis to predict future business trends. 【0678】 Users interact with the server via their devices. When a user enters a question from their device during a meeting, the server uses a generative AI model to generate the best possible answer to the question and responds to the device in real time. An example of a prompt sentence that a user might enter is, "I request a risk analysis and strategic proposal based on success stories related to entering a new market." 【0679】 Furthermore, the server analyzes past decision-making history to provide strategic proposals tailored to individual user requests and industry changes. For example, for companies considering entering new markets, it provides detailed reports based on past success stories and risk analyses to support their decision-making. 【0680】 This means the system functions as a powerful tool for companies to make strategic and efficient decisions based on data. 【0681】 The flow of the specific processing in Example 1 will be explained using Figure 11. 【0682】 Step 1: 【0683】 The server collects data from both inside and outside the company. Inputs include sales data from the company's ERP system, feedback from customer relationship management (CRM) systems, employee data from HR systems, and market trends and economic indicators via external APIs. The server retrieves and integrates this input data to output a comprehensive dataset. 【0684】 Step 2: 【0685】 The server preprocesses the collected data. To improve data accuracy, it performs data cleansing, such as removing duplicate data, correcting outliers, and imputing missing values. Specifically, it uses statistical methods and imputation algorithms based on historical data to reshape the data. This results in clean data that can be analyzed. 【0686】 Step 3: 【0687】 The server analyzes data using natural language processing techniques. The input is clean data, which is then analyzed to identify patterns in managers' decision-making. Specifically, it uses Python's natural language processing library to extract keywords and themes from text data. The output of this step is knowledge and insights related to business strategy. 【0688】 Step 4: 【0689】 The server builds machine learning models and predicts future business scenarios. Inputs include historical data and learned business patterns. The server uses scikit-learn and TensorFlow to execute predictive algorithms and simulate future market trends and sales forecasts. Outputs include quantitative estimates and scenarios for future trends. 【0690】 Step 5: 【0691】 The user enters a question into the server via their terminal. The input is received as a prompt, which includes questions related to business decision-making. A specific example is, "We request a risk analysis and strategic proposal based on successful case studies for entering a new market." Based on this input, the server uses a generative AI model to generate the optimal answer and sends it back to the terminal as output. 【0692】 Step 6: 【0693】 The server analyzes past decision-making history and industry changes to provide customized strategic recommendations to the user. Input includes user profiles and historical data. The server analyzes this data and generates specific recommendations. The output is a strategic report tailored to the user's specific requirements. 【0694】 (Application Example 1) 【0695】 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". 【0696】 In corporate management, formulating effective strategies is crucial, but this presents the challenge of comprehensively analyzing vast amounts of internal and external data. Furthermore, a system is needed to provide appropriate strategic proposals in real time to support rapid decision-making. In urban management, too, it is necessary to efficiently utilize vast amounts of infrastructure data to formulate strategies for realizing smart cities. 【0697】 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. 【0698】 In this invention, the server includes means for collecting and cleansing corporate data and external market data, means for analyzing copyrighted works and audio to extract thought patterns, and means for building machine learning models to predict future business scenarios. This enables efficient data analysis and real-time strategic proposals in companies and cities. 【0699】 "Corporate data" refers to information about sales, customers, and employees generated within a company. 【0700】 "External market data" refers to information obtained from outside the company, such as market trends, competitor information, and economic indicators. 【0701】 "Data cleansing" refers to the process of preparing data for analysis by correcting duplicates and outliers, and imputing missing values. 【0702】 "Analyzing copyrighted works and audio" refers to extracting useful information and patterns from documents and audio using natural language processing technology. 【0703】 "Extracting thought patterns" refers to identifying and learning characteristics related to the strategic judgments of authors or speakers from documents or audio recordings. 【0704】 A "machine learning model" refers to a statistical model used to predict future trends and scenarios based on large amounts of data. 【0705】 "Generating answers to questions in real time" means immediately providing answers based on relevant information in response to user inquiries. 【0706】 "Providing strategic proposals" means recommending specific action plans and policies based on collected data and analysis results. 【0707】 "Urban infrastructure data" refers to information related to urban functions such as transportation, energy, and public safety. 【0708】 "Data aggregation and analysis" refers to the process of gathering diverse data in one place and analyzing its trends and patterns using statistical methods. 【0709】 The system for realizing this invention includes a series of processes for effectively processing and analyzing large amounts of data to support strategic decision-making. In particular, it has the function of supporting the formulation of management strategies using internal corporate data and external market data. Furthermore, it also has the function of analyzing urban infrastructure data for smart city management and providing strategic advice to urban planners. 【0710】 The server first collects data such as sales, customers, employees, market trends, and competitor information from the company's internal systems and external sources. Next, it cleans the collected data by removing duplicates, correcting outliers, and imputing data. This is done using data processing libraries such as Python. 【0711】 The server uses natural language processing techniques to extract thought patterns from copyrighted works and audio recordings. This process utilizes machine learning frameworks such as TensorFlow and PyTorch. Next, these thought patterns and historical data are used to build a machine learning model that predicts future business scenarios. 【0712】 The terminal receives questions from users during meetings and conferences, searches for information to enable the server to respond quickly, and generates answers. For example, it can refer to similar past cases and trends to provide real-time strategic suggestions. In this way, users can receive quick and accurate support for important decision-making. 【0713】 A concrete example is the efficient management of urban functions in preparation for an approaching typhoon. Based on historical data and current weather forecasts, an appropriate allocation of energy resources is proposed. By using generative AI models in conjunction, the accuracy of the planning can be improved. 【0714】 An example of a prompt might be a specific question such as, "In preparation for the typhoon approaching this weekend, please propose a strategic operational plan for urban infrastructure to minimize typhoon damage." 【0715】 The flow of a specific process in Application Example 1 will be explained using Figure 12. 【0716】 Step 1: 【0717】 First, the server collects corporate and market data from the company's internal systems and external sources. Inputs include sales data, customer information, employee information, and external sources such as market trends and competitor information. The output is a set of raw data. This data forms the basis for subsequent processing. Specifically, necessary data is extracted using APIs and database connectors. 【0718】 Step 2: 【0719】 The server cleanses the collected data. The raw data collected in step 1 is used as input. Data processing includes removing duplicates, correcting outliers, and imputing missing values, resulting in a formatted dataset as output. This process utilizes data processing libraries such as Python's Pandas to improve data reliability. 【0720】 Step 3: 【0721】 The server uses natural language processing technology to analyze copyrighted works and audio to extract the thought patterns of business leaders. It uses text and audio data as input. The data processing involves identifying keywords and themes from the text and audio, and obtaining the extracted patterns as output. Specifically, it utilizes TensorFlow to execute a text classification model. 【0722】 Step 4: 【0723】 The server builds a machine learning model based on these thought patterns and historical data to predict future business scenarios. It uses cleansed data and extracted thought patterns as input. For data computation, it performs predictive analytics and generates predicted scenarios as output. This process utilizes machine learning frameworks such as TensorFlow or PyTorch. 【0724】 Step 5: 【0725】 The terminal receives questions from users during a meeting, the server searches for relevant information, and generates appropriate answers. It uses user questions and scenarios as input and provides real-time strategic suggestions as output. Specifically, it performs rapid responses using database queries and natural language generation technologies. 【0726】 Step 6: 【0727】 This system provides an interface for users to make strategic decisions based on suggestions. Input is suggestion data from the terminal, and output is the display of information necessary for decision-making. Specifically, it visually presents information using a GUI on the terminal. 【0728】 Step 7: 【0729】 The server collects urban infrastructure data and creates operational plans for smart cities. It uses urban data such as transportation, energy, and public safety as input and proposes operational plans for each area as output. Specifically, it uses a generative AI model to visualize future scenarios. An example of a prompt is: "In preparation for the typhoon approaching this weekend, please propose a strategic operational plan for urban infrastructure to minimize typhoon damage." 【0730】 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. 【0731】 This invention is a system that supports strategic planning in corporate management, and further incorporates an emotion engine that recognizes user emotions. This system, which understands user emotions and the background of decision-making in real time and supports strategic decision-making, consists of the following elements. 【0732】 First, the server collects comprehensive internal and external datasets from the company and manages them in the cloud. This includes sales data, customer feedback, employee data, and even external market trends and economic indicators. The server cleanses this data and prepares it for analysis. 【0733】 Next, the emotion engine recognizes emotions from the user's voice, text tone, facial expressions, and other data. Data received via the device's camera and microphone is sent to a server and processed in real time. It recognizes emotional patterns and understands the user's current emotional state. 【0734】 The server further analyzes the writings and speeches of prominent business leaders to learn thought patterns related to business decisions. This involves utilizing natural language processing techniques to extract key keywords and strategies from the documents. 【0735】 Next, the server builds a machine learning model based on the collected data and sentiment information to predict future business scenarios. This model takes into account the current emotional state and can tailor optimal strategic suggestions to the user. 【0736】 When users want to ask a question during a meeting or other setting, they can interact through their device and input their question instantly. The server processes this information and generates an answer that takes into account the user's emotional state. This ensures that the question is answered at the most appropriate time and with the most suitable approach. 【0737】 For example, if a user is considering entering the stock market, the server will create a comprehensive report that includes risk analysis and recommended actions, taking into account historical data, market information, and even the user's current anxieties and expectations—the emotional aspects of the situation. Furthermore, by providing individually tailored suggestions, it will support decision-making that is adapted to the user's situation, including their emotions. 【0738】 Thus, the system of the present invention strongly supports effective decision-making by integrating data analysis and sentiment recognition technologies to provide managers with more personalized strategic proposals. 【0739】 The following describes the processing flow. 【0740】 Step 1: 【0741】 The server automatically collects sales data, customer feedback, employee data, and even market trends and economic indicators from internal corporate systems and external data sources. This creates a comprehensive dataset of the company's current situation and its external environment. 【0742】 Step 2: 【0743】 The server cleanses the collected data. Specifically, it improves the accuracy and reliability of the data by removing duplicate data, correcting outliers, and imputing missing values. This process is an important preparatory step for data analysis. 【0744】 Step 3: 【0745】 The device acquires data through its camera and microphone to input user voice and facial expression data. This data is sent to a server in real time for further processing. 【0746】 Step 4: 【0747】 The server uses an emotion engine to analyze voice, text, and facial expression data acquired from the user to recognize emotions. By evaluating the emotional patterns, it understands the user's current emotional state. 【0748】 Step 5: 【0749】 The server analyzes collected executive writings and speeches using natural language processing technology to learn thought patterns related to business decisions. This allows it to extract information useful for executives' strategic decision-making. 【0750】 Step 6: 【0751】 The server builds a machine learning model based on historical data and sentiment recognition results. This model is used to predict future business scenarios for companies and enables the adjustment of strategic recommendations that take into account the user's emotional state. 【0752】 Step 7: 【0753】 When users wish to interact during a meeting or board meeting, they can enter questions on a terminal. Based on the entered questions, the server generates answers considering relevant data, similar past cases, and even sentiment information, and sends them back to the terminal. 【0754】 Step 8: 【0755】 The server provides customized strategic suggestions based on the user's individual profile and emotion recognition results. This enables decision-making support that is adapted to the specific situation and emotions the user is facing. 【0756】 In this way, this system, which combines an emotion engine, provides deeper insights and personalized advice in supporting corporate decision-making. 【0757】 (Example 2) 【0758】 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". 【0759】 In modern business management, managers need to analyze vast amounts of internal and external data to make effective decisions. However, the complexity of organizing and analyzing this data makes it difficult to make quick and appropriate decisions. Furthermore, managers' emotions often influence decision-making, and there is a lack of approaches that take this into account. In addition, learning from past decision-making history is insufficient, limiting the ability to effectively predict future scenarios. 【0760】 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. 【0761】 In this invention, the server includes means for collecting and organizing information, means for analyzing documents to extract thought processes related to management decisions, means for predicting future scenarios using a learning algorithm, and means for recognizing and considering emotional states. This enables the effective organization and analysis of vast amounts of data, and realizes decision-making support that takes emotions into account. Furthermore, it becomes possible to learn past decision-making patterns and propose optimal management strategies based on them. 【0762】 "Means for collecting and organizing information" refers to the technology of acquiring diverse data from both inside and outside a company, and then scrutinizing and transforming it into a format that can be analyzed. 【0763】 "Methods for analyzing documents and extracting thought processes related to management decisions" refers to techniques for identifying thought patterns that drive management decisions from texts such as books and speeches on management. 【0764】 "Methods for predicting future scenarios using learning algorithms" refer to techniques that analyze past data and current circumstances to build machine learning models for predicting future business environments. 【0765】 "Means for recognizing and considering emotional states" refers to technologies that recognize a user's emotions from voice, text, and facial expressions, and reflect that in decision-making support. 【0766】 This invention is a system designed to support decision-making in corporate management. Its embodiments are described below. 【0767】 The server collects and organizes a wide variety of information from both internal and external sources within the company. Internal information includes sales data and employee information, while external information includes market trends and economic indicators. This information is stored on a cloud storage service and organized by a database management system. The server utilizes the Python Pandas library for data formatting and analysis. 【0768】 Furthermore, the server extracts thought processes related to management decisions through document analysis. This utilizes natural language processing technology, employing open-source libraries (e.g., NLTK and SpaCy) to extract important keywords and strategies from management-related books and speeches. 【0769】 Furthermore, the server uses machine learning algorithms to predict future business scenarios. In this process, frameworks such as Scikit-learn and TensorFlow are used to build models based on historical data and make predictions to inform business strategies. 【0770】 The device will collect the user's voice, text, and facial expressions captured by the camera. Input data obtained from the microphone and camera will be sent to a server in real time. The server will use APIs from Google and other general AI platforms to perform emotion recognition and understand the user's emotional state in real time. 【0771】 A concrete example of this system is a scenario where a user enters a prompt such as, "Please tell me about the latest trends in the stock market and an analysis of the risks of entering the market. I'm feeling a bit anxious right now, but I'd like suggestions based on concrete data." Based on this prompt, the server performs a comprehensive data analysis and immediately presents strategic suggestions that take emotions into account. In this way, useful decision-making support is provided to the user. 【0772】 The flow of the specific processing in Example 2 will be explained using Figure 13. 【0773】 Step 1: 【0774】 The server collects diverse information from both internal and external sources within the company. It utilizes databases and APIs as input, including sales data, employee information, market trends, and economic indicators. Specifically, it retrieves information through periodic database queries and external data feeds. Based on this information, the data is stored in cloud storage. 【0775】 Step 2: 【0776】 The server cleanses the collected data and formats it for analysis. The raw data collected in step 1 is used as input. Here, the Python Pandas library is used to remove noisy data and extract the necessary information. The output is a clean and organized dataset. Specific operations include imputing missing values, normalization, and data format conversion. 【0777】 Step 3: 【0778】 The device collects user voice, text, and facial expressions and sends them to the server. This includes user actions via camera and microphone input. Inputs include audio files, text input, and video footage. As output, this data is sent to the server in real time. 【0779】 Step 4: 【0780】 The server processes the user's voice, text, and facial expression data in real time to recognize their emotional state. This process uses data from step 3 as input and utilizes Google Cloud and general APIs for emotion recognition. The output is the user's emotional status. Specific processing includes tone analysis, keyword emotion weighting, and facial expression analysis. 【0781】 Step 5: 【0782】 The server analyzes documents to extract data related to business decisions. The input is text data from copyrighted works and speeches. Using natural language processing techniques, it extracts important keywords and business strategies as output. Specific operations include text mining, keyword extraction, and document classification. 【0783】 Step 6: 【0784】 The server builds a machine learning model using historical data and the current user's emotional state to predict business scenarios. The input is the dataset formatted in step 2 and the emotional data from step 4. Using Python's Scikit-learn, the output is a prediction tailored to a specific business situation. The specific operation involves data modeling, training, and prediction processes. 【0785】 Step 7: 【0786】 The user interacts with the server by entering a question via a terminal. The input is in text format. Based on the content of the question, the server generates an answer that takes into account the user's emotional state. The output is emotionally balanced strategic advice. The specific operations include query analysis, sentiment adjustment, and answer generation processes. 【0787】 Through this series of steps, the system achieves effective data processing and strategic proposals that take user emotions into consideration. 【0788】 (Application Example 2) 【0789】 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". 【0790】 In modern business management, decision-making that considers diverse information and emotional aspects is crucial. However, existing systems have struggled to adequately integrate and utilize these factors, making it impossible to provide personalized strategic proposals that take emotions and individual circumstances into account. Furthermore, in citizen-participatory policymaking, the insufficient reflection of citizens' emotions and opinions has been a challenge. In addition, achieving high-quality, real-time interaction during decision-making has not been easy. 【0791】 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. 【0792】 In this invention, the server includes means for collecting and cleansing corporate information and external market information, means for analyzing copyrighted works and audio content to extract decision-makers' thought patterns, and means for building machine learning models to predict future business scenarios. This enables the integrated use of data and emotions in corporate management and real-time strategic support based on sentiment analysis in citizen participation policies. Furthermore, customized strategic proposals are delivered to users, improving the quality of decision-making. 【0793】 "Corporate information" refers to internal data about a company, and the information necessary for management decision-making. 【0794】 "External market information" refers to market data collected from sources outside the company, including industry trends and economic indicators. 【0795】 "Cleansing" refers to the process of preparing raw data into an analyzable format, correcting or deleting inaccurate or duplicate data. 【0796】 "Copyrighted works" refer to intellectual creations such as books and papers on management and business. 【0797】 "Audio content" refers to audio data uttered as part of communication, and includes information about the words and tones used within it. 【0798】 "Extracting thought patterns" refers to analyzing important concepts and trends from copyrighted works or audio content to identify a foundation for decision-making that is useful in achieving specific goals. 【0799】 A "machine learning model" refers to an algorithm or mathematical model that uses large amounts of data to discover patterns and predict future situations and outcomes. 【0800】 "Predicting business scenarios" means statistically estimating future possibilities and outcomes related to management and policy decisions. 【0801】 "Analyzing emotional state" means identifying the user's emotional state based on inputs such as facial expressions and voice. 【0802】 "Summarizing policy proposals" means condensing suggestions from citizens and decision-makers and clearly presenting the key elements. 【0803】 A "customized strategy proposal" involves presenting a strategy tailored to individual needs and conditions, based on the information received and the user's current situation. 【0804】 In this invention, a server collects corporate and external market information, cleanses it, and converts it into an analyzable format. For example, data including sales data, customer feedback, employee data, and external market trends and economic indicators are centrally managed on the cloud. The server also analyzes copyrighted works and audio content to extract the thought patterns of decision-makers. In this process, natural language processing technology is used to efficiently extract keywords and strategies from documents. 【0805】 The server further builds machine learning models based on collected data and emotional information to predict future business scenarios. This enables the integrated use of real-time data and emotions in corporate management. In particular, in citizen-participatory policy proposals, it analyzes emotional states to identify emotions from the user's facial expressions and voice, and then summarizes and provides policy proposals based on that. 【0806】 Users can interact in real time through their smartphones or smart glasses. When users submit suggestions or questions, the system quickly generates more personalized strategic suggestions based on sentiment analysis and provides feedback to the user. This feedback is customized to suit the individual user's needs and circumstances. 【0807】 For example, if a user suggests "I want more lighting in the park," the emotion engine analyzes the user's anxieties and expectations. Based on this analysis, policymakers are provided with a summary such as "There is an emotional background of wanting improved public safety." In this way, the system makes optimized suggestions while taking emotional data into consideration. 【0808】 An example of a prompt for a generative AI model might be: "Based on the sentiment analysis results of the user's suggestion, 'We want more lights in the park,' generate a summary that should be conveyed to policymakers. Please consider the emotional context and also suggest possible solutions." 【0809】 The flow of a specific process in Application Example 2 will be explained using Figure 14. 【0810】 Step 1: 【0811】 The server collects corporate and external market information. It receives data such as sales data, customer feedback, employee data, external market trends, and economic indicators as input. This data is then cleansed and converted into an analyzable format. Specifically, it corrects and removes inaccuracies and duplicates, and consolidates them into a unified format. 【0812】 Step 2: 【0813】 The server analyzes copyrighted material and audio content to extract the thought patterns of decision-makers. It accepts books and audio data related to business management as input. Using natural language processing techniques, it extracts important keywords and statements from the documents and generates a model of thought patterns. Specifically, it uses document analysis algorithms to perform vocabulary frequency analysis and contextual understanding. 【0814】 Step 3: 【0815】 Based on data and sentiment information collected by the server, a machine learning model is built to predict future business scenarios. Input includes cleansed data and sentiment states. The model analyzes the data using relevant statistical methods and algorithms to predict future changes. Specifically, it performs the training and evaluation processes of the predictive model. 【0816】 Step 4: 【0817】 Users submit policy proposals and questions through their devices. The devices take user text and voice data as input. The devices then transfer this information to a server in real time for analysis by an emotion engine. Specifically, they use APIs for speech recognition and emotion analysis as interfaces. 【0818】 Step 5: 【0819】 The server analyzes the user's emotional state and identifies emotional patterns. It processes voice and text data sent from the terminal as input and applies an emotion recognition algorithm. The identified emotional state is generated as output. Specific operations include voice tone analysis and text sentiment analysis. 【0820】 Step 6: 【0821】 The server summarizes policy proposals and generates strategic proposals based on the analysis results. It uses emotional states and data analysis results obtained in steps 1 through 3 as input. The output consists of user-optimized policy proposals and strategic proposals, which are sent to the user and policymakers. Specifically, it utilizes a generative AI model to automatically generate expert prompts. 【0822】 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. 【0823】 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. 【0824】 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. 【0825】 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. 【0826】 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. 【0827】 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. 【0828】 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. 【0829】 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. 【0830】 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." 【0831】 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. 【0832】 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. 【0833】 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. 【0834】 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. 【0835】 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. 【0836】 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. 【0837】 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. 【0838】 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. 【0839】 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. 【0840】 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. 【0841】 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. 【0842】 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 to be incorporated by reference. 【0843】 The following is further disclosed regarding the embodiments described above. 【0844】 (Claim 1) 【0845】 Methods for collecting and cleansing corporate data and external market data, 【0846】 Methods for analyzing copyrighted works and speeches to extract the thought patterns of business leaders, 【0847】 A means of building machine learning models and predicting future business scenarios, 【0848】 A means of generating answers to questions from executives in real time, 【0849】 A means of proposing topics to be discussed based on past decision history and industry trends, 【0850】 Means of providing customized strategic proposals, 【0851】 A system that includes this. 【0852】 (Claim 2) 【0853】 The system according to claim 1, comprising means for analyzing internal and external corporate data in real time and providing information to support decision-making. 【0854】 (Claim 3) 【0855】 The system according to claim 1, further comprising means for analyzing past decision-making patterns of managers and proposing an optimal management strategy based on similar cases. 【0856】 "Example 1" 【0857】 (Claim 1) 【0858】 A means for collecting and preprocessing internal and external environmental information of a company, 【0859】 A method for analyzing information using natural language processing technology and identifying management decision patterns, 【0860】 A method for simulating future business scenarios using predictive algorithms, 【0861】 A means of responding to questions from management in real time and creating answers, 【0862】 A means of proposing meeting agendas based on past decision-making history and industry changes, 【0863】 Means for providing strategies tailored to specific requirements, 【0864】 A system that includes this. 【0865】 (Claim 2) 【0866】 The system according to claim 1, comprising means for instantly analyzing information from within and outside the organization and supplying information to support selection. 【0867】 (Claim 3) 【0868】 The system according to claim 1, further comprising means for evaluating past management selection patterns and presenting optimal business strategies based on similar cases. 【0869】 "Application Example 1" 【0870】 (Claim 1) 【0871】 Methods for collecting and cleansing corporate data and external market data, 【0872】 Methods for analyzing copyrighted works and audio recordings to extract the thought patterns of business leaders, 【0873】 A means of building machine learning models to predict future business scenarios, 【0874】 A means of generating answers to decision-makers' questions in real time, 【0875】 A means of proposing topics to be discussed based on past decision history and industry trends, 【0876】 Means of providing customized strategic proposals, 【0877】 A means of collecting and analyzing urban infrastructure data and providing strategic advice to urban planners, 【0878】 A system that includes this. 【0879】 (Claim 2) 【0880】 The system according to claim 1, comprising means for analyzing internal and external corporate data in real time and providing information to support decision-making. 【0881】 (Claim 3) 【0882】 The system according to claim 1, further comprising means for analyzing past decision-making patterns of managers and proposing an optimal strategy based on similar cases. 【0883】 "Example 2 of combining an emotion engine" 【0884】 (Claim 1) 【0885】 Means for collecting and organizing information, 【0886】 A means of analyzing documents to extract the thought process related to management decisions, 【0887】 A means of predicting future scenarios using a learning algorithm, 【0888】 A means of generating answers based on questions asked at any given time, 【0889】 A means of proposing agenda items based on past decision-making history and trends, 【0890】 Means for providing individually tailored strategic proposals, 【0891】 Means for recognizing and considering emotional states, 【0892】 A system that includes this. 【0893】 (Claim 2) 【0894】 The system according to claim 1, comprising means for analyzing internal and external information of an organization in real time and providing information to support decision-making. 【0895】 (Claim 3) 【0896】 The system according to claim 1, further comprising means for analyzing past decision-making processes and proposing the optimal strategy based on similar cases. 【0897】 "Application example 2 of combining emotional engines" 【0898】 (Claim 1) 【0899】 Methods for collecting and cleansing corporate information and external market information, 【0900】 A method for analyzing copyrighted works and audio content to extract the thought patterns of decision-makers, 【0901】 A means of building machine learning models to predict future business scenarios, 【0902】 A means of generating answers to decision-makers' questions in real time, 【0903】 A means of proposing topics to be discussed based on past decision records and industry trends, 【0904】 A means of analyzing the emotional state of users and summarizing policy proposals, 【0905】 Means of providing customized strategic proposals, 【0906】 A system that includes this. 【0907】 (Claim 2) 【0908】 The system according to claim 1, comprising means for analyzing internal and external corporate information in real time and providing information to support decision-making based on sentiment analysis results. 【0909】 (Claim 3) 【0910】 The system according to claim 1, further comprising means for analyzing the decision-making patterns of past decision-makers and summarizing optimal policy proposals based on similar cases with regard to sentiment analysis. [Explanation of Symbols] 【0911】 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 collecting and cleansing corporate data and external market data, Methods for analyzing copyrighted works and speeches to extract the thought patterns of business leaders, A means of building machine learning models and predicting future business scenarios, A means of generating answers to questions from executives in real time, A means of proposing topics to be discussed based on past decision history and industry trends, Means of providing customized strategic proposals, A system that includes this. [Claim 2] The system according to claim 1, comprising means for analyzing internal and external corporate data in real time and providing information to support decision-making. [Claim 3] The system according to claim 1, further comprising means for analyzing past decision-making patterns of managers and proposing an optimal management strategy based on similar cases.

Images