system

Abstract

Provide a system. 【Solution means】 Data collection means for collecting data from external data sources and internal databases, Data analysis means for performing natural language processing on the collected data and extracting the thinking patterns of administrators and planners, Predictive analysis means for integrating past business data and market trends to build a prediction model, Simulation means for simulating the generated business scenarios and evaluating the probability of success and risks, Question answering means for generating real-time answers to questions entered by users during meetings, Agenda setting means for proposing important issues based on past decision history and industry trends, Learning means for analyzing feedback and improving the model, Urban strategy providing means for analyzing urban data and proposing business plans in real time, A system including the above.

Description

Technical Field

[0001] The technology of the present disclosure relates to a system.

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In a company, the rapid and accurate formulation of a business strategy is essential for success in a highly competitive market. However, manually analyzing a large amount of data and devising countermeasures is very time-consuming and has limitations in accuracy. Also, for decision-making in meetings, it is required to refer to appropriate data in real time, but usually this process is inefficient. Amidst such problems, a mechanism that anyone can easily utilize is demanded.

Means for Solving the Problems

[0005] This invention provides a system comprising means for collecting data from external data sources and internal databases, means for data analysis using natural language processing, and means for predictive analysis that integrates business data and market trends. This system includes simulation means for simulating and evaluating generated business scenarios, and question answering means for generating real-time responses to user questions during meetings. Furthermore, by including agenda setting means for analyzing past decision history and industry trends and proposing important topics, and learning means for improving models based on feedback, the system solves the challenges of business strategy planning faced by companies.

[0006] "Data collection means" refers to a function or device designed to collect necessary information from external data sources and internal databases.

[0007] "Data analysis means" refers to a function or device that analyzes collected data using technologies such as natural language processing to extract the thinking patterns of managers and strategists.

[0008] "Predictive analytics means" refers to a function or device designed to predict future business scenarios using past business data and market trends.

[0009] A "simulation tool" is a function or device that executes various hypotheses to evaluate the feasibility and risks of a generated business scenario.

[0010] A "question answering means" is a function or device that generates appropriate answers in real time to questions from users.

[0011] A "topic setting tool" is a function or device that analyzes past decision history and industry trends to propose important topics to be discussed at a meeting.

[0012] A "learning tool" is a function or device used to analyze feedback data and continuously improve the system's model and functionality. [Brief explanation of the drawing]

[0013] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0014] 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.

[0015] First, the terms used in the following description will be explained.

[0016] 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.

[0017] 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.

[0018] In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0019] 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).

[0020] 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."

[0021] [First Embodiment]

[0022] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0023] 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.

[0024] 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).

[0025] 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.

[0026] 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.

[0027] 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.

[0028] 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.

[0029] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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".

[0034] This invention will be specifically implemented as an AI system to support a company's business strategy. Each function is based on the coordinated operation of three parties: the server, the terminal, and the user.

[0035] First, the server collects necessary information from the company's internal databases and external data sources. The collected data encompasses various types of business strategies and is analyzed in detail using natural language processing techniques to contribute to corporate decision-making. For example, it can collect news articles about competitors and data on market trends, and extract useful information from their content.

[0036] Next, the server performs predictive analytics based on the collected data to generate future business scenarios. This allows companies to simulate future developments and assess the probability of success and potential risks. For example, multiple scenarios for entering a new market are evaluated, and the most promising approach is selected.

[0037] The terminal is used in board meetings and management meetings, providing an interface for users to access AI. Through this interface, users can input questions in real time during meetings and receive immediate strategic suggestions from the AI. For example, if a question is asked about pricing for a new product, the AI ​​will suggest an appropriate price range based on historical market data and current trends.

[0038] Furthermore, the server leverages past discussion history and industry trends to suggest important topics. This feature helps users recognize key issues that they might otherwise overlook. Finally, the system is continuously improved based on feedback, enhancing the accuracy of the model for future strategic planning.

[0039] In this way, AI systems are being used as a powerful tool to quickly and accurately support the complex decision-making processes that companies face, and to maintain a competitive advantage.

[0040] The following describes the processing flow.

[0041] Step 1:

[0042] The server collects relevant data from internal corporate databases and external data sources. This includes market trend reports, competitor news articles, and social media posts. Automated crawlers and API integrations are used for data collection.

[0043] Step 2:

[0044] The server applies natural language processing (NLP) to the collected data and performs text analysis. This extracts the thinking patterns and insights of executives and prominent strategists from the data, and the analysis results are then templated. These templates serve as important guidelines for subsequent strategic planning.

[0045] Step 3:

[0046] The server builds a predictive analytics model based on the analyzed data. This model incorporates past business performance and market trends to generate future business scenarios. Machine learning algorithms are used in this process to refine the scenarios.

[0047] Step 4:

[0048] The server performs simulations for the generated scenarios. It runs simulations under various assumptions and evaluates the likelihood of success and the risks associated with each scenario. The evaluation results are recorded in a database and used for subsequent decision-making.

[0049] Step 5:

[0050] The device provides an interface that allows users to input questions to the AI ​​in real time. This enables quick questioning during meetings to facilitate business decision-making. The UI is designed with real-time functionality in mind, making it user-friendly.

[0051] Step 6:

[0052] The server instantly generates answers to user questions. Based on the question, it extracts the most relevant data and uses a predictive model to generate the answer. The answer is presented as a concrete strategic proposal or actionable plan.

[0053] Step 7:

[0054] Users proceed with discussions in board meetings and management meetings based on strategies proposed by the AI. This includes considering proposed scenarios, success probabilities, and risks. If necessary, the AI ​​also assists in setting the agenda for the meetings.

[0055] Step 8:

[0056] The server aggregates user feedback and uses it to learn from and improve the system. The collected feedback is used to improve the accuracy of the model and enhance the quality of future strategic proposals. Through this process, the system continuously evolves, more effectively supporting the formulation of corporate strategies.

[0057] (Example 1)

[0058] 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."

[0059] In corporate business strategy, it is necessary to effectively collect and analyze large amounts of data and predict future developments. However, the diversity of information and the rapid pace of trends complicate the decision-making process, making it difficult to quickly formulate appropriate strategies. This invention aims to solve these problems and improve the competitiveness of companies.

[0060] 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.

[0061] In this invention, the server includes information gathering means for collecting information from external information sources and internal information repositories, information analysis means for performing natural language processing on the collected information and extracting the thinking patterns of decision-makers and formulaters, and predictive analysis means for integrating past business information and market trends to construct a predictive model. This enables rapid and accurate decision-making within companies.

[0062] "Information gathering means" refers to the function of effectively and efficiently collecting necessary information from external information sources and internal information repositories.

[0063] "Information analysis tools" are functions that apply natural language processing to collected information to extract the thought patterns of decision-makers and formulaters.

[0064] "Predictive analysis tools" refer to functions that integrate past business information and market trends to build models for predicting future business developments.

[0065] A "simulation tool" is a function that uses generated business scenarios to evaluate the likelihood of success and the associated risks.

[0066] The "inquiry response system" is a function that generates appropriate answers immediately to inquiries entered by users during a meeting.

[0067] The "agenda setting mechanism" is a function that proposes important topics to be discussed based on past decision history and industry trends.

[0068] "Learning tools" refer to a function that continuously improves information gathering and analysis models based on user feedback, aiming to enhance the accuracy of future proposals.

[0069] "Generative AI models" refer to artificial intelligence technology used to generate new business scenarios based on diverse information.

[0070] In an embodiment of this invention, the server first acquires necessary information from external information sources and internal information libraries using information gathering means. APIs and web crawling technologies are used for this information gathering, and market data and competitor trends necessary for strengthening the company's competitiveness are collected.

[0071] Next, the server activates its information analysis tools and uses natural language processing technology to analyze the collected information in detail. This analysis uses an NLP engine to classify the information and performs entity recognition and sentiment analysis to extract information useful from the decision-maker's perspective.

[0072] The analysis results are processed using predictive analytics tools, and by integrating past business information and market trends, a model is constructed to predict future business developments. Generative AI models are utilized in this process to propose realistic business scenarios.

[0073] The terminal provides an interface for users to access the system. Through this interface, users can receive analysis results and strategic suggestions from the server in real time. For example, by entering a prompt such as, "Please propose a strategy to gain a competitive advantage in the sustainable energy market," users can receive specific suggestions from the system.

[0074] Furthermore, the server utilizes an agenda-setting mechanism to propose new topics based on past decision history and industry trends. This feature helps in identifying important issues that are often overlooked during meetings and strategic planning.

[0075] The server analyzes user feedback through learning mechanisms and continuously improves the system. This improves the accuracy of the generated AI model, further enhancing the quality of future suggestions.

[0076] In this way, the invention functions as a comprehensive system to support a company's strategic decision-making.

[0077] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0078] Step 1:

[0079] The server collects information from external sources and internal databases. This process utilizes APIs and web crawling technologies to obtain market data and competitor information. Inputs include parameters for data collection based on the company's requirements, and output is a dataset of the acquired raw data. Specifically, the server periodically updates the information using specified URLs and database connections.

[0080] Step 2:

[0081] The server processes the collected data using information analysis tools. This process extracts important keywords and topics from the data using natural language processing techniques. The raw data collected in step 1 is used as input, and structured information is generated as output. Specifically, the server activates an NLP engine and applies entity recognition and sentiment analysis algorithms.

[0082] Step 3:

[0083] The server builds a predictive model based on the analysis results using predictive analytics tools. A generative AI model is used in this process to generate future business scenarios. The structured information obtained in step 2 is provided as input, and multiple predicted business scenarios are generated as output. Specifically, the server trains the model using statistical methods and machine learning algorithms.

[0084] Step 4:

[0085] The terminal provides an interface for the user to interact with the system. Here, the user can input prompts and receive strategic suggestions in real time. As input, the user provides prompts to the terminal, and as output, the AI's suggestions are presented to the user. Specifically, the terminal displays the results in a dashboard format and provides immediate responses to the user's queries.

[0086] Step 5:

[0087] The server receives feedback from users and improves the system through learning mechanisms. This improves the accuracy of the generated AI model. User feedback is sent to the server as input, and the improved model is used as output for the next strategy proposal. Specific operations include feedback analysis and model retraining.

[0088] (Application Example 1)

[0089] 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."

[0090] The problem that this invention aims to solve is to make quick and accurate decisions for optimizing urban management and resident services in smart cities. Conventional systems have had difficulty effectively analyzing diverse data and supporting real-time strategic planning. Therefore, it is necessary to strengthen data-driven decision-making processes in urban planning and urban management.

[0091] 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.

[0092] In this invention, the server includes data collection means for collecting data from external data sources and internal databases, data analysis means for performing natural language processing on the collected data and extracting thought patterns of administrators and planners, and predictive analysis means for integrating past business data and market trends to construct a predictive model. This enables the real-time generation of effective policy proposals for optimizing urban management and resident services in smart cities.

[0093] "Data collection means" refers to the function of systematically and efficiently acquiring necessary information from external data sources and internal databases.

[0094] "Data analysis methods" refer to techniques that apply natural language processing and other methods to collected data to extract the thought patterns of managers and planners.

[0095] "Predictive analytics" refers to the process of analyzing past business data and market trends to build models for predicting future scenarios.

[0096] A "simulation tool" is a technology that evaluates the likelihood of success and the risks based on generated business scenarios, and supports decision-making.

[0097] A "question answering system" is a function that instantly generates appropriate answers to real-time questions entered by users during a meeting.

[0098] The "agenda setting mechanism" is a function that proposes important agenda items based on past decision history and industry trends.

[0099] "Learning methods" refer to the process of improving the accuracy of an analytical model based on feedback information.

[0100] The "Urban Strategy Provisioning Tool" is a function that proposes operational plans useful for improving urban management and resident services in real time, based on collected urban data.

[0101] The system for realizing this application consists of three main components: a server, a terminal, and a user. The server collects data from external data sources and internal databases and performs data analysis using natural language processing technology. Specifically, it extracts necessary information from the company's internal database, incorporates external data sources such as market trend data and industry news articles, and integrates diverse data to extract the thought patterns of managers and planners.

[0102] Furthermore, the server possesses predictive analytics capabilities, leveraging historical operational data and market trends to predict and generate future operational scenarios. This process involves data integration and model construction using machine learning algorithms. As a result, it becomes possible to propose effective strategies that contribute to the optimization of urban management and resident services.

[0103] The terminal is used particularly during meetings and provides an interface that allows users to input questions into the system in real time. Based on user questions, the server immediately uses a generated AI model to suggest optimal measures and solutions. Important agenda items that are often overlooked during discussions can also be suggested by the server based on past decision history and industry trends. This function supports critical decision-making in cities and promotes the rapid and effective implementation of plans and measures.

[0104] The hardware and software used include a programming environment using Python, data analysis servers running on Google Cloud Platform or Amazon Web Services, and libraries specialized for natural language processing (e.g., spaCy or NLTK). As a concrete example, in discussions about introducing a new public transportation system, a prompt such as "What is the optimal way to introduce a new bus route?" could be generated based on the discovered transportation data and predictive analytics. In this way, the system supports urban management operations and contributes to the provision of more efficient and effective services to residents.

[0105] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0106] Step 1:

[0107] The server collects data from external data sources and internal databases. It systematically acquires various types of data related to urban management (e.g., traffic data, demographic data, environmental data) using internet APIs and database queries. The input is a data acquisition request, and the output is the collected raw data.

[0108] Step 2:

[0109] The server applies natural language processing to the collected data and performs analysis. Specifically, it uses a Python natural language processing library (e.g., spaCy) to extract the thought patterns of managers and planners from the data. The input is the raw data collected in step 1, and the output is the extracted thought patterns and related topics.

[0110] Step 3:

[0111] The server performs predictive analysis based on historical business data and market trends to generate future business scenarios. In this process, it builds models using machine learning algorithms. The input is the analyzed data, and the output is the predicted business scenario.

[0112] Step 4:

[0113] The terminal receives questions entered by the user during the meeting and sends those questions to the server. Users ask questions about specific issues and measures related to urban management. The input is the user's question, and the output is the query sent to the server.

[0114] Step 5:

[0115] The server uses a generative AI model to suggest optimal measures and solutions based on the received questions. The generative AI model provides real-time answers while referencing past performance and trends. The input is the user's question query, and the output is the suggested measures.

[0116] Step 6:

[0117] The server proposes key agenda items based on past decision history and industry trends. This process involves historical data and trend analysis to complement often overlooked issues in urban planning. The input is existing decision history and trend data, and the output is the proposed agenda items.

[0118] Step 7:

[0119] The server receives feedback and learns to improve the system's accuracy. This feedback is used to improve the accuracy of the analysis model and inform future decision-making. The input is feedback on individual proposals, and the output is the improved analysis model.

[0120] Step 8:

[0121] Based on the generated strategic proposals and agendas, users implement measures to optimize urban management and resident services. Ultimately, users utilize the outputted information to reflect it in actual policies and plans. The input consists of actions proposed by the system, and the output consists of the implemented measures.

[0122] 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.

[0123] This invention aims to provide more effective strategic proposals by incorporating an emotion engine into an AI system that supports corporate decision-making. The system operates primarily through the interaction of three parties: a server, a terminal, and a user.

[0124] First, the server collects data from external data sources and internal databases and performs analysis using natural language processing. The results of this data analysis are used for predictive analytics, building a predictive model that integrates historical business data and market trends. Business scenarios generated based on the predictive model are evaluated for risk and probability of success through simulation.

[0125] The terminal provides an interface to users during meetings, enabling them to access the AI ​​system. Users can input questions in real time through the terminal and instantly receive responses and strategic suggestions from the AI ​​as a result.

[0126] This is where the emotion engine comes in. The server uses the emotion engine to recognize emotions from the user's facial expressions, tone of voice, and other factors. This recognized emotion information is used for question answering and personalized strategic suggestions. Specifically, if the user is feeling stressed, the suggestions can be made simpler or focused on positive outcomes.

[0127] Furthermore, the server has the ability to analyze past decision history and industry trends and suggest important agenda items to be discussed in meetings. Priorities and interests suggested by user sentiment are also taken into consideration to help ensure effective discussions.

[0128] Finally, the system analyzes the feedback and uses it to improve the next model. This allows the system to continuously improve its functionality, providing strong support for companies' business strategy planning. The emotion engine enables more personalized support and flexible suggestions tailored to user needs.

[0129] The following describes the processing flow.

[0130] Step 1:

[0131] The server automatically collects necessary information from the company's internal databases and external data sources. This includes transaction data, competitive analysis reports, and market trend information, and collection is performed via crawlers and APIs.

[0132] Step 2:

[0133] The server applies natural language processing (NLP) to the collected data and performs analysis. From the analysis results, it extracts the thinking patterns of managers and strategists and converts them into information that can be used as templates for strategic planning.

[0134] Step 3:

[0135] The server builds a predictive analytics model based on the analysis results. Here, it considers past success stories and current market trends to generate multiple future business scenarios. Machine learning algorithms are used to improve the accuracy of these scenarios.

[0136] Step 4:

[0137] The server simulates the generated business scenarios and evaluates their likelihood of success and the associated risks. The evaluation results are recorded in a database to aid in decision-making.

[0138] Step 5:

[0139] The terminal provides an interface for users to input questions in real time during a meeting. Users can input specific management questions and expect immediate responses.

[0140] Step 6:

[0141] The server searches relevant data based on the entered question and generates answers and strategic suggestions by referring to predictive models. This is where the emotion engine comes in, tailoring the suggestions to the user's emotional state.

[0142] Step 7:

[0143] The server uses an emotion engine to recognize the user's emotions in real time from their facial expressions and tone of voice. For example, if the user is feeling anxious, it will select a suggestion style that provides reassurance.

[0144] Step 8:

[0145] Users facilitate discussions in board meetings and management meetings based on the answers and suggestions received from the AI. They discuss the validity and feasibility of proposed strategies and provide feedback as needed.

[0146] Step 9:

[0147] The server analyzes user feedback and uses it to improve the model. This allows the system to continuously evolve, improving the accuracy of the strategies it proposes next.

[0148] (Example 2)

[0149] 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".

[0150] In modern business management, rapid and appropriate decision-making is essential, but effectively utilizing vast amounts of external information and internal company data while providing real-time strategic proposals is challenging. Furthermore, providing personalized recommendations that consider the user's emotions and stress levels during decision-making is a major challenge. To address these challenges, a system integrating efficient data analysis and emotion recognition is necessary.

[0151] 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.

[0152] In this invention, the server includes information gathering means, information analysis means, and a prediction function. This enables the extraction of useful knowledge patterns from vast amounts of external and internal data, allowing for real-time strategic proposals and personalized decision support. Furthermore, by using an emotion-responsive function, it is possible to realize flexible proposals that take into account the user's psychological state, thereby improving the accuracy and efficiency of decision-making.

[0153] "Information gathering means" refers to mechanisms and methods for efficiently collecting necessary information from external information sources and internal information databases.

[0154] "Information analysis means" refers to mechanisms and methods for analyzing collected raw data using natural language processing techniques to extract useful knowledge patterns.

[0155] A "predictive function" is a mechanism or method for predicting future trends based on past business data and market conditions, and for generating specific predictive models.

[0156] A "simulation tool" is a mechanism or method for conducting simulations to evaluate the feasibility and associated risks of a generated scenario.

[0157] A "question and answer function" is a mechanism or method for generating quick and accurate answers to questions entered by users during meetings or other similar situations.

[0158] The "agenda setting function" refers to a mechanism or method for proposing important discussion topics based on past decision-making results and industry trends.

[0159] "Emotional response function" refers to a mechanism or method that analyzes the user's psychological state and enables individualized responses in providing suggestions and supporting decision-making.

[0160] A "learning function" refers to a mechanism or method for improving the overall accuracy and efficiency of a system by collecting and analyzing user feedback.

[0161] The system in this invention implements a decision support process through the collaboration of a server, a terminal, and a user.

[0162] First, the server uses information gathering tools to collect necessary information from external sources and internal information databases. This process extracts data from publicly available information on the internet and from the company's internal data management system. Specifically, it utilizes Python libraries such as pandas and APIs. The collected data is then analyzed using information analysis tools and natural language processing (NLP) techniques. Here, NLP libraries such as spaCy and NLTK are used to extract topics and sentiment from text data, and to extract knowledge patterns.

[0163] Next, the server uses the data collected by the prediction function to generate a predictive model using a machine learning algorithm. This algorithm utilizes libraries such as scikit-learn and TENSORFLOW® to achieve more accurate future predictions. Based on these predictions, the server simulates the generated business scenarios using simulation tools, evaluates the likelihood of success and the associated risks, and proposes the optimal strategy. In this process, the use of Monte Carlo's method and linear programming in the simulation is recommended.

[0164] The terminal assists users in accessing server analysis results and suggestions during meetings through its user interface. The terminal instantly sends entered questions to the AI ​​system and presents the user with responses based on its question-and-answer function.

[0165] A unique feature of the system is its server-based emotion-responsiveness. It analyzes the user's voice tone and facial expressions using speech recognition and image processing technologies, and then provides strategic suggestions tailored to the user's emotional state. Specific technologies used include speech recognition via Google Cloud Speech-to-Text and facial recognition via OpenCV. By flexibly adjusting responses and suggestions based on this emotional information, the system can support more accurate decision-making.

[0166] Furthermore, the server collects feedback from users through terminals and improves the system's accuracy through its learning function. Here, the collected feedback is analyzed and used to readjust the model. An example of a specific prompt message is, "Please forecast sales of the new product for the next three months and provide additional information to improve reliability." Through this process, the system is constantly updated and can respond to user needs in the most optimal way.

[0167] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0168] Step 1:

[0169] The server retrieves information from external sources and internal databases. Specifically, it uses news sites and market data from the internet as external sources, and customer information and sales history from the company as internal databases. This information is automatically retrieved through APIs and database connections. The input is in various data formats, and the output is a structured data list. The Python pandas library is used to format the data and output it in a unified format.

[0170] Step 2:

[0171] The server performs natural language processing on the collected information and then analyzes it. The software used includes spaCy and NLTK, which extract meaningful topics and sentiments from text data. Raw text data is provided as input, and the output generates feature lists and numerical data based on the analysis results. This allows for the extraction of key topics in business operations and market sentiment trends.

[0172] Step 3:

[0173] The server builds a machine learning model based on the analysis results. Specifically, it uses libraries such as scikit-learn and TensorFlow to model trends from historical data. The input is a list of features from the analysis results, and the output is a predictive model. This can be used to predict sales and market trends. Hyperparameter optimization is performed as needed during model construction.

[0174] Step 4:

[0175] The server uses the generated predictive model to simulate multiple business scenarios. It employs methods such as Monte Carlo and linear programming to evaluate the probability of success and the risks associated with each scenario. The inputs are the predictive model and scenario data, while the outputs are the success probability and risk assessment for each scenario. This allows the server to identify the most promising strategic options.

[0176] Step 5:

[0177] The terminal provides an interface for users to input inquiries and instructions. Users use the terminal to enter questions about specific strategies, which are processed in real time by the server. The user's question is given as input, and the server's response is displayed as output. This allows users to make quick decisions even during meetings.

[0178] Step 6:

[0179] The server analyzes the user's psychological state using emotion-responsiveness features. It utilizes speech recognition and facial recognition technologies to analyze whether the user is experiencing stress or excitement. Input is the user's voice and video data, and output is the result of the emotional state analysis. Based on these results, the server personalizes responses and strategic suggestions, providing appropriate care for specific emotional states.

[0180] Step 7:

[0181] The server collects user feedback and uses it to improve the system. The feedback information is stored in a database, and the model's accuracy is improved through learning. The input is user feedback data, and the output is the improved model. This allows for continuous improvement in the accuracy of the system's analysis and recommendation functions.

[0182] (Application Example 2)

[0183] 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".

[0184] In mobility services provided by autonomous vehicles, there is a need to appropriately understand passengers' emotional states and provide a comfortable and satisfying travel experience. However, current technology is unable to analyze passengers' emotions in real time and respond flexibly based on that analysis. As a result, it is difficult to fully meet passenger needs and improve the quality of service.

[0185] 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.

[0186] In this invention, the server includes information gathering means for collecting information from external information sources and internal information repositories, information analysis means for performing natural language processing on the collected information and extracting the decision-maker's thinking tendencies, and emotion analysis means for analyzing the user's emotional state and optimizing the operation of the transportation means. This makes it possible to adjust the operation of the transportation means according to the passenger's emotions, enabling a comfortable and personalized travel experience.

[0187] "Information gathering means" refers to methods and systems for collecting relevant information from external sources and internal information repositories.

[0188] "Information analysis methods" refer to methods and techniques that perform natural language processing on collected information to extract and analyze the thinking tendencies and characteristics of decision-makers.

[0189] "Predictive analysis tools" refer to methods and devices that integrate past business information and market trends to build models for predicting future developments.

[0190] "Simulation methods" refer to technologies and techniques for simulating and implementing generated business operations to evaluate their likelihood of success and associated risks.

[0191] A "question answering system" refers to a method or system for instantly generating and providing answers to questions entered by users in meetings or other settings.

[0192] "Agenda setting methods" refer to processes and techniques for proposing important agenda items based on past decision history and industry trends.

[0193] "Learning methods" refer to methods or systems that analyze feedback within a system and continuously improve the model based on that information.

[0194] "Emotional analysis means" refers to technologies and methods for analyzing a user's emotional state in real time and optimizing the operation and services of transportation based on that analysis.

[0195] This invention is a method for realizing a system that analyzes passenger emotions in autonomous vehicles and provides a comfortable travel experience.

[0196] The server collects information from external and internal data sources and applies natural language processing to recognize passengers' emotional states. This utilizes the camera and microphone on smartphones and employs the Google Cloud Vision API for facial expression analysis. Audio data is analyzed for tone using Amazon Polly. The analysis results are stored in a Microsoft® Azure® database, and each time data is collected, data processing is performed to quantify the passengers' emotional states.

[0197] The terminal provides passengers with real-time suggestions based on analysis results. For example, if a passenger shows signs of fatigue, the system will select and play appropriate music and suggest a scenic route. These features improve comfort within the vehicle and provide passengers with a more satisfying travel experience.

[0198] Users can provide feedback to the system through their devices. This feedback is analyzed by learning mechanisms, and the system continuously improves its model.

[0199] For example, if a passenger appears tired after work, the system will suggest and automatically play relaxing music. It will also flexibly change the route, recommending a route that offers more refreshing scenery for the passenger to the autonomous vehicle.

[0200] An example of a prompt might be: "The passenger's expression indicates fatigue. Based on this information, suggest relaxing music and a refreshing route."

[0201] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0202] Step 1:

[0203] The server captures passengers' facial expressions and voice tones through the smartphone's camera and microphone. Real-time video and audio data from the smartphone are used as input. The data is analyzed using the Google Cloud Vision API and Amazon Polly to quantify the passengers' emotional state. At this stage, facial analysis assesses passenger happiness and fatigue levels, while voice analysis evaluates stress levels. The output generates a set of passenger emotional state data.

[0204] Step 2:

[0205] The server stores the analyzed data in a Microsoft Azure database and re-evaluates passengers' emotional patterns by comparing them with historical data. At this point, it compares the data with previous passenger feedback to improve the accuracy of emotion-based action recommendations. The input consists of newly acquired emotional state data and historical records, and the output is an updated emotion analysis model.

[0206] Step 3:

[0207] The terminal uses emotional data received from a server to provide passengers with real-time feedback. If a passenger shows signs of fatigue, it selects relaxing music and automatically plays a music playlist. Furthermore, it works in conjunction with the car's navigation system to select scenic routes. The inputs utilize emotional data from the server and the vehicle's geographical information, and the output determines the music playlist to be played and alternative routes.

[0208] Step 4:

[0209] Users experience music selection and route changes from the system as passengers and provide feedback on the quality of the services provided through their terminals. Input is feedback information based on the user's actual experience, and output is feedback data sent to a server for use in future model improvements.

[0210] Step 5:

[0211] The server analyzes user feedback using learning mechanisms and performs updates to improve the accuracy of its sentiment analysis model and recommended content. The input is feedback data sent from the device, and the output is an enhanced sentiment analysis model and improved user experience.

[0212] 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.

[0213] Data generation model 58 is a type of 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.

[0214] 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.

[0215] [Second Embodiment]

[0216] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0217] 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.

[0218] 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).

[0219] 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.

[0220] 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.

[0221] 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).

[0222] 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.

[0223] 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.

[0224] 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.

[0225] 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.

[0226] 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.

[0227] 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".

[0228] This invention will be specifically implemented as an AI system to support a company's business strategy. Each function is based on the coordinated operation of three parties: the server, the terminal, and the user.

[0229] First, the server collects necessary information from the company's internal databases and external data sources. The collected data encompasses various types of business strategies and is analyzed in detail using natural language processing techniques to contribute to corporate decision-making. For example, it can collect news articles about competitors and data on market trends, and extract useful information from their content.

[0230] Next, the server performs predictive analytics based on the collected data to generate future business scenarios. This allows companies to simulate future developments and assess the probability of success and potential risks. For example, multiple scenarios for entering a new market are evaluated, and the most promising approach is selected.

[0231] The terminal is used in board meetings and management meetings, providing an interface for users to access AI. Through this interface, users can input questions in real time during meetings and receive immediate strategic suggestions from the AI. For example, if a question is asked about pricing for a new product, the AI ​​will suggest an appropriate price range based on historical market data and current trends.

[0232] Furthermore, the server leverages past discussion history and industry trends to suggest important topics. This feature helps users recognize key issues that they might otherwise overlook. Finally, the system is continuously improved based on feedback, enhancing the accuracy of the model for future strategic planning.

[0233] In this way, AI systems are being used as a powerful tool to quickly and accurately support the complex decision-making processes that companies face, and to maintain a competitive advantage.

[0234] The following describes the processing flow.

[0235] Step 1:

[0236] The server collects relevant data from internal corporate databases and external data sources. This includes market trend reports, competitor news articles, and social media posts. Automated crawlers and API integrations are used for data collection.

[0237] Step 2:

[0238] The server applies natural language processing (NLP) to the collected data and performs text analysis. This extracts the thinking patterns and insights of executives and prominent strategists from the data, and the analysis results are then templated. These templates serve as important guidelines for subsequent strategic planning.

[0239] Step 3:

[0240] The server builds a predictive analytics model based on the analyzed data. This model incorporates past business performance and market trends to generate future business scenarios. Machine learning algorithms are used in this process to refine the scenarios.

[0241] Step 4:

[0242] The server performs simulations for the generated scenarios. It runs simulations under various assumptions and evaluates the likelihood of success and the risks associated with each scenario. The evaluation results are recorded in a database and used for subsequent decision-making.

[0243] Step 5:

[0244] The device provides an interface that allows users to input questions to the AI ​​in real time. This enables quick questioning during meetings to facilitate business decision-making. The UI is designed with real-time functionality in mind, making it user-friendly.

[0245] Step 6:

[0246] The server instantly generates answers to user questions. Based on the question, it extracts the most relevant data and uses a predictive model to generate the answer. The answer is presented as a concrete strategic proposal or actionable plan.

[0247] Step 7:

[0248] Users proceed with discussions in board meetings and management meetings based on strategies proposed by the AI. This includes considering proposed scenarios, success probabilities, and risks. If necessary, the AI ​​also assists in setting the agenda for the meetings.

[0249] Step 8:

[0250] The server aggregates user feedback and uses it to learn from and improve the system. The collected feedback is used to improve the accuracy of the model and enhance the quality of future strategic proposals. Through this process, the system continuously evolves, more effectively supporting the formulation of corporate strategies.

[0251] (Example 1)

[0252] 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."

[0253] In corporate business strategy, it is necessary to effectively collect and analyze large amounts of data and predict future developments. However, the diversity of information and the rapid pace of trends complicate the decision-making process, making it difficult to quickly formulate appropriate strategies. This invention aims to solve these problems and improve the competitiveness of companies.

[0254] 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.

[0255] In this invention, the server includes information gathering means for collecting information from external information sources and internal information repositories, information analysis means for performing natural language processing on the collected information and extracting the thinking patterns of decision-makers and formulaters, and predictive analysis means for integrating past business information and market trends to construct a predictive model. This enables rapid and accurate decision-making within companies.

[0256] "Information gathering means" refers to the function of effectively and efficiently collecting necessary information from external information sources and internal information repositories.

[0257] "Information analysis tools" are functions that apply natural language processing to collected information to extract the thought patterns of decision-makers and formulaters.

[0258] "Predictive analysis tools" refer to functions that integrate past business information and market trends to build models for predicting future business developments.

[0259] A "simulation tool" is a function that uses generated business scenarios to evaluate the likelihood of success and the associated risks.

[0260] The "inquiry response system" is a function that generates appropriate answers immediately to inquiries entered by users during a meeting.

[0261] The "agenda setting mechanism" is a function that proposes important topics to be discussed based on past decision history and industry trends.

[0262] "Learning tools" refer to a function that continuously improves information gathering and analysis models based on user feedback, aiming to enhance the accuracy of future proposals.

[0263] "Generative AI models" refer to artificial intelligence technology used to generate new business scenarios based on diverse information.

[0264] In an embodiment of this invention, the server first acquires necessary information from external information sources and internal information libraries using information gathering means. APIs and web crawling technologies are used for this information gathering, and market data and competitor trends necessary for strengthening the company's competitiveness are collected.

[0265] Next, the server activates its information analysis tools and uses natural language processing technology to analyze the collected information in detail. This analysis uses an NLP engine to classify the information and performs entity recognition and sentiment analysis to extract information useful from the decision-maker's perspective.

[0266] The analysis results are processed using predictive analytics tools, and by integrating past business information and market trends, a model is constructed to predict future business developments. Generative AI models are utilized in this process to propose realistic business scenarios.

[0267] The terminal provides an interface for users to access the system. Through this interface, users can receive analysis results and strategic suggestions from the server in real time. For example, by entering a prompt such as, "Please propose a strategy to gain a competitive advantage in the sustainable energy market," users can receive specific suggestions from the system.

[0268] Furthermore, the server utilizes an agenda-setting mechanism to propose new topics based on past decision history and industry trends. This feature helps in identifying important issues that are often overlooked during meetings and strategic planning.

[0269] The server analyzes user feedback through learning mechanisms and continuously improves the system. This improves the accuracy of the generated AI model, further enhancing the quality of future suggestions.

[0270] In this way, the invention functions as a comprehensive system to support a company's strategic decision-making.

[0271] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0272] Step 1:

[0273] The server collects information from external sources and internal databases. This process utilizes APIs and web crawling technologies to obtain market data and competitor information. Inputs include parameters for data collection based on the company's requirements, and output is a dataset of the acquired raw data. Specifically, the server periodically updates the information using specified URLs and database connections.

[0274] Step 2:

[0275] The server processes the collected data using information analysis tools. This process extracts important keywords and topics from the data using natural language processing techniques. The raw data collected in step 1 is used as input, and structured information is generated as output. Specifically, the server activates an NLP engine and applies entity recognition and sentiment analysis algorithms.

[0276] Step 3:

[0277] The server builds a predictive model based on the analysis results using predictive analytics tools. A generative AI model is used in this process to generate future business scenarios. The structured information obtained in step 2 is provided as input, and multiple predicted business scenarios are generated as output. Specifically, the server trains the model using statistical methods and machine learning algorithms.

[0278] Step 4:

[0279] The terminal provides an interface for the user to interact with the system. Here, the user can input prompts and receive strategic suggestions in real time. As input, the user provides prompts to the terminal, and as output, the AI's suggestions are presented to the user. Specifically, the terminal displays the results in a dashboard format and provides immediate responses to the user's queries.

[0280] Step 5:

[0281] The server receives feedback from the user and improves the system through learning means. This improves the accuracy of the generative AI model. As input, the user's feedback is sent to the server, and as output, the improved model is used for the next strategic proposal. Specific operations include feedback analysis and model retraining.

[0282] (Application Example 1)

[0283] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0284] The problem to be solved by the present invention is to make quick and accurate decisions for urban management and optimization of resident services in smart cities. In conventional systems, it was difficult to effectively analyze various types of data and support real-time strategy formulation. Therefore, it is necessary to strengthen the data-driven decision-making process in urban planning and management.

[0285] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0286] In this invention, the server includes data collection means for collecting data from external data sources and internal databases, data analysis means for performing natural language processing on the collected data and extracting the thinking patterns of administrators and planners, and predictive analysis means for integrating past business data and market trends to build a predictive model. This enables the real-time generation of effective policy proposals for urban management and optimization of resident services in smart cities.

[0287] The "data collection means" is a function for systematically and efficiently acquiring necessary information from external data sources and internal databases.

[0288] "Data analysis methods" refer to techniques that apply natural language processing and other methods to collected data to extract the thought patterns of managers and planners.

[0289] "Predictive analytics" refers to the process of analyzing past business data and market trends to build models for predicting future scenarios.

[0290] A "simulation tool" is a technology that evaluates the likelihood of success and the risks based on generated business scenarios, and supports decision-making.

[0291] A "question answering system" is a function that instantly generates appropriate answers to real-time questions entered by users during a meeting.

[0292] The "agenda setting mechanism" is a function that proposes important agenda items based on past decision history and industry trends.

[0293] "Learning methods" refer to the process of improving the accuracy of an analytical model based on feedback information.

[0294] The "Urban Strategy Provisioning Tool" is a function that proposes operational plans useful for improving urban management and resident services in real time, based on collected urban data.

[0295] The system for realizing this application consists of three main components: a server, a terminal, and a user. The server collects data from external data sources and internal databases and performs data analysis using natural language processing technology. Specifically, it extracts necessary information from the company's internal database, incorporates external data sources such as market trend data and industry news articles, and integrates diverse data to extract the thought patterns of managers and planners.

[0296] Furthermore, the server possesses predictive analytics capabilities, leveraging historical operational data and market trends to predict and generate future operational scenarios. This process involves data integration and model construction using machine learning algorithms. As a result, it becomes possible to propose effective strategies that contribute to the optimization of urban management and resident services.

[0297] The terminal is used particularly during meetings and provides an interface that allows users to input questions into the system in real time. Based on user questions, the server immediately uses a generated AI model to suggest optimal measures and solutions. Important agenda items that are often overlooked during discussions can also be suggested by the server based on past decision history and industry trends. This function supports critical decision-making in cities and promotes the rapid and effective implementation of plans and measures.

[0298] The hardware and software used include a programming environment using Python, data analysis servers running on Google Cloud Platform or Amazon Web Services, and libraries specialized for natural language processing (e.g., spaCy or NLTK). As a concrete example, in discussions about introducing a new public transportation system, a prompt such as "What is the optimal way to introduce a new bus route?" could be generated based on the discovered transportation data and predictive analytics. In this way, the system supports urban management operations and contributes to the provision of more efficient and effective services to residents.

[0299] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0300] Step 1:

[0301] The server collects data from external data sources and internal databases. It systematically acquires various types of data related to urban management (e.g., traffic data, demographic data, environmental data) using internet APIs and database queries. The input is a data acquisition request, and the output is the collected raw data.

[0302] Step 2:

[0303] The server applies natural language processing to the collected data for analysis. Specifically, it uses a natural language processing library in Python (e.g., spaCy) to extract the thinking patterns of administrators and planners from the data. The input is the raw data collected in Step 1, and the output is the extracted thinking patterns and related topics.

[0304] Step 3:

[0305] The server performs predictive analysis based on past business data and market trends to generate future business scenarios. In this process, it constructs models using machine learning algorithms. The input is the analyzed data, and the output is the predicted business scenarios.

[0306] Step 4:

[0307] The terminal receives the questions entered by the user during the meeting and sends the questions to the server. The user asks questions about specific issues and measures related to urban management. The input is the question from the user, and the output is the question query to the server.

[0308] Step 5:

[0309] Based on the received questions, the server proposes optimal measures and solutions using the generated AI model. The generated AI model provides answers in real time while referring to past performance and trends. The input is the user's question query, and the output is the proposed measures.

[0310] Step 6:

[0311] The server proposes important issues based on past decision histories and industry trends. In this process, it conducts historical data and trend analysis to complement the arguments that are often overlooked in urban planning. The input is the existing decision history and trend data, and the output is the proposed issues.

[0312] Step 7:

[0313] The server receives feedback and learns to improve the system's accuracy. This feedback is used to improve the accuracy of the analysis model and inform future decision-making. The input is feedback on individual proposals, and the output is the improved analysis model.

[0314] Step 8:

[0315] Based on the generated strategic proposals and agendas, users implement measures to optimize urban management and resident services. Ultimately, users utilize the outputted information to reflect it in actual policies and plans. The input consists of actions proposed by the system, and the output consists of the implemented measures.

[0316] 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.

[0317] This invention aims to provide more effective strategic proposals by incorporating an emotion engine into an AI system that supports corporate decision-making. The system operates primarily through the interaction of three parties: a server, a terminal, and a user.

[0318] First, the server collects data from external data sources and internal databases and performs analysis using natural language processing. The results of this data analysis are used for predictive analytics, building a predictive model that integrates historical business data and market trends. Business scenarios generated based on the predictive model are evaluated for risk and probability of success through simulation.

[0319] The terminal provides an interface to users during meetings, enabling them to access the AI ​​system. Users can input questions in real time through the terminal and instantly receive responses and strategic suggestions from the AI ​​as a result.

[0320] This is where the emotion engine comes in. The server uses the emotion engine to recognize emotions from the user's facial expressions, tone of voice, and other factors. This recognized emotion information is used for question answering and personalized strategic suggestions. Specifically, if the user is feeling stressed, the suggestions can be made simpler or focused on positive outcomes.

[0321] Furthermore, the server has the ability to analyze past decision history and industry trends and suggest important agenda items to be discussed in meetings. Priorities and interests suggested by user sentiment are also taken into consideration to help ensure effective discussions.

[0322] Finally, the system analyzes the feedback and uses it to improve the next model. This allows the system to continuously improve its functionality, providing strong support for companies' business strategy planning. The emotion engine enables more personalized support and flexible suggestions tailored to user needs.

[0323] The following describes the processing flow.

[0324] Step 1:

[0325] The server automatically collects necessary information from the company's internal databases and external data sources. This includes transaction data, competitive analysis reports, and market trend information, and collection is performed via crawlers and APIs.

[0326] Step 2:

[0327] The server applies natural language processing (NLP) to the collected data and performs analysis. From the analysis results, it extracts the thinking patterns of managers and strategists and converts them into information that can be used as templates for strategic planning.

[0328] Step 3:

[0329] The server builds a predictive analytics model based on the analysis results. Here, it considers past success stories and current market trends to generate multiple future business scenarios. Machine learning algorithms are used to improve the accuracy of these scenarios.

[0330] Step 4:

[0331] The server simulates the generated business scenarios and evaluates their likelihood of success and the associated risks. The evaluation results are recorded in a database to aid in decision-making.

[0332] Step 5:

[0333] The terminal provides an interface for users to input questions in real time during a meeting. Users can input specific management questions and expect immediate responses.

[0334] Step 6:

[0335] The server searches relevant data based on the entered question and generates answers and strategic suggestions by referring to predictive models. This is where the emotion engine comes in, tailoring the suggestions to the user's emotional state.

[0336] Step 7:

[0337] The server uses an emotion engine to recognize the user's emotions in real time from their facial expressions and tone of voice. For example, if the user is feeling anxious, it will select a suggestion style that provides reassurance.

[0338] Step 8:

[0339] Users facilitate discussions in board meetings and management meetings based on the answers and suggestions received from the AI. They discuss the validity and feasibility of proposed strategies and provide feedback as needed.

[0340] Step 9:

[0341] The server analyzes user feedback and uses it to improve the model. This allows the system to continuously evolve, improving the accuracy of the strategies it proposes next.

[0342] (Example 2)

[0343] 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".

[0344] In modern business management, rapid and appropriate decision-making is essential, but effectively utilizing vast amounts of external information and internal company data while providing real-time strategic proposals is challenging. Furthermore, providing personalized recommendations that consider the user's emotions and stress levels during decision-making is a major challenge. To address these challenges, a system integrating efficient data analysis and emotion recognition is necessary.

[0345] 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.

[0346] In this invention, the server includes information gathering means, information analysis means, and a prediction function. This enables the extraction of useful knowledge patterns from vast amounts of external and internal data, allowing for real-time strategic proposals and personalized decision support. Furthermore, by using an emotion-responsive function, it is possible to realize flexible proposals that take into account the user's psychological state, thereby improving the accuracy and efficiency of decision-making.

[0347] "Information gathering means" refers to mechanisms and methods for efficiently collecting necessary information from external information sources and internal information databases.

[0348] "Information analysis means" refers to mechanisms and methods for analyzing collected raw data using natural language processing techniques to extract useful knowledge patterns.

[0349] A "predictive function" is a mechanism or method for predicting future trends based on past business data and market conditions, and for generating specific predictive models.

[0350] A "simulation tool" is a mechanism or method for conducting simulations to evaluate the feasibility and associated risks of a generated scenario.

[0351] A "question and answer function" is a mechanism or method for generating quick and accurate answers to questions entered by users during meetings or other similar situations.

[0352] The "agenda setting function" refers to a mechanism or method for proposing important discussion topics based on past decision-making results and industry trends.

[0353] "Emotional response function" refers to a mechanism or method that analyzes the user's psychological state and enables individualized responses in providing suggestions and supporting decision-making.

[0354] A "learning function" refers to a mechanism or method for improving the overall accuracy and efficiency of a system by collecting and analyzing user feedback.

[0355] The system in this invention implements a decision support process through the collaboration of a server, a terminal, and a user.

[0356] First, the server uses information gathering tools to collect necessary information from external sources and internal information databases. This process extracts data from publicly available information on the internet and from the company's internal data management system. Specifically, it utilizes Python libraries such as pandas and APIs. The collected data is then analyzed using information analysis tools and natural language processing (NLP) techniques. Here, NLP libraries such as spaCy and NLTK are used to extract topics and sentiment from text data, and to extract knowledge patterns.

[0357] Next, the server uses the data collected by the prediction function to generate a predictive model using a machine learning algorithm. This algorithm utilizes libraries such as scikit-learn and TensorFlow to achieve more accurate future predictions. Based on these predictions, the server simulates the generated business scenarios using simulation tools, evaluates the likelihood of success and the associated risks, and proposes the optimal strategy. In this process, the use of Monte Carlo's method or linear programming in the simulation is recommended.

[0358] The terminal assists users in accessing server analysis results and suggestions during meetings through its user interface. The terminal instantly sends entered questions to the AI ​​system and presents the user with responses based on its question-and-answer function.

[0359] A unique feature of the system is its server-based emotion-responsiveness. It analyzes the user's voice tone and facial expressions using speech recognition and image processing technologies, and then provides strategic suggestions tailored to the user's emotional state. Specific technologies used include speech recognition via Google Cloud Speech-to-Text and facial recognition via OpenCV. By flexibly adjusting responses and suggestions based on this emotional information, the system can support more accurate decision-making.

[0360] Furthermore, the server collects feedback from users through terminals and improves the system's accuracy through its learning function. Here, the collected feedback is analyzed and used to readjust the model. An example of a specific prompt message is, "Please forecast sales of the new product for the next three months and provide additional information to improve reliability." Through this process, the system is constantly updated and can respond to user needs in the most optimal way.

[0361] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0362] Step 1:

[0363] The server retrieves information from external sources and internal databases. Specifically, it uses news sites and market data from the internet as external sources, and customer information and sales history from the company as internal databases. This information is automatically retrieved through APIs and database connections. The input is in various data formats, and the output is a structured data list. The Python pandas library is used to format the data and output it in a unified format.

[0364] Step 2:

[0365] The server performs natural language processing on the collected information and then analyzes it. The software used includes spaCy and NLTK, which extract meaningful topics and sentiments from text data. Raw text data is provided as input, and the output generates feature lists and numerical data based on the analysis results. This allows for the extraction of key topics in business operations and market sentiment trends.

[0366] Step 3:

[0367] The server builds a machine learning model based on the analysis results. Specifically, it uses libraries such as scikit-learn and TensorFlow to model trends from historical data. The input is a list of features from the analysis results, and the output is a predictive model. This can be used to predict sales and market trends. Hyperparameter optimization is performed as needed during model construction.

[0368] Step 4:

[0369] The server uses the generated predictive model to simulate multiple business scenarios. It employs methods such as Monte Carlo and linear programming to evaluate the probability of success and the risks associated with each scenario. The inputs are the predictive model and scenario data, while the outputs are the success probability and risk assessment for each scenario. This allows the server to identify the most promising strategic options.

[0370] Step 5:

[0371] The terminal provides an interface for users to input inquiries and instructions. Users use the terminal to enter questions about specific strategies, which are processed in real time by the server. The user's question is given as input, and the server's response is displayed as output. This allows users to make quick decisions even during meetings.

[0372] Step 6:

[0373] The server analyzes the user's psychological state using emotion-responsiveness features. It utilizes speech recognition and facial recognition technologies to analyze whether the user is experiencing stress or excitement. Input is the user's voice and video data, and output is the result of the emotional state analysis. Based on these results, the server personalizes responses and strategic suggestions, providing appropriate care for specific emotional states.

[0374] Step 7:

[0375] The server collects user feedback and uses it to improve the system. The feedback information is stored in a database, and the model's accuracy is improved through learning. The input is user feedback data, and the output is the improved model. This allows for continuous improvement in the accuracy of the system's analysis and recommendation functions.

[0376] (Application Example 2)

[0377] 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."

[0378] In mobility services provided by autonomous vehicles, there is a need to appropriately understand passengers' emotional states and provide a comfortable and satisfying travel experience. However, current technology is unable to analyze passengers' emotions in real time and respond flexibly based on that analysis. As a result, it is difficult to fully meet passenger needs and improve the quality of service.

[0379] 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.

[0380] In this invention, the server includes information gathering means for collecting information from external information sources and internal information repositories, information analysis means for performing natural language processing on the collected information and extracting the decision-maker's thinking tendencies, and emotion analysis means for analyzing the user's emotional state and optimizing the operation of the transportation means. This makes it possible to adjust the operation of the transportation means according to the passenger's emotions, enabling a comfortable and personalized travel experience.

[0381] "Information gathering means" refers to methods and systems for collecting relevant information from external sources and internal information repositories.

[0382] "Information analysis methods" refer to methods and techniques that perform natural language processing on collected information to extract and analyze the thinking tendencies and characteristics of decision-makers.

[0383] "Predictive analysis tools" refer to methods and devices that integrate past business information and market trends to build models for predicting future developments.

[0384] "Simulation methods" refer to technologies and techniques for simulating and implementing generated business operations to evaluate their likelihood of success and associated risks.

[0385] A "question answering system" refers to a method or system for instantly generating and providing answers to questions entered by users in meetings or other settings.

[0386] "Agenda setting methods" refer to processes and techniques for proposing important agenda items based on past decision history and industry trends.

[0387] "Learning methods" refer to methods or systems that analyze feedback within a system and continuously improve the model based on that information.

[0388] "Emotional analysis means" refers to technologies and methods for analyzing a user's emotional state in real time and optimizing the operation and services of transportation based on that analysis.

[0389] This invention is a method for realizing a system that analyzes passenger emotions in autonomous vehicles and provides a comfortable travel experience.

[0390] The server collects information from external and internal data sources and applies natural language processing to recognize passengers' emotional states. This utilizes the camera and microphone on smartphones and employs the Google Cloud Vision API for facial expression analysis. Audio data is analyzed for tone using Amazon Polly. The analysis results are stored in a Microsoft Azure database, and each time data is collected, data processing is performed to quantify the passengers' emotional states.

[0391] The terminal provides passengers with real-time suggestions based on analysis results. For example, if a passenger shows signs of fatigue, the system will select and play appropriate music and suggest a scenic route. These features improve comfort within the vehicle and provide passengers with a more satisfying travel experience.

[0392] Users can provide feedback to the system through their devices. This feedback is analyzed by learning mechanisms, and the system continuously improves its model.

[0393] For example, if a passenger appears tired after work, the system will suggest and automatically play relaxing music. It will also flexibly change the route, recommending a route that offers more refreshing scenery for the passenger to the autonomous vehicle.

[0394] An example of a prompt might be: "The passenger's expression indicates fatigue. Based on this information, suggest relaxing music and a refreshing route."

[0395] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0396] Step 1:

[0397] The server captures passengers' facial expressions and voice tones through the smartphone's camera and microphone. Real-time video and audio data from the smartphone are used as input. The data is analyzed using the Google Cloud Vision API and Amazon Polly to quantify the passengers' emotional state. At this stage, facial analysis assesses passenger happiness and fatigue levels, while voice analysis evaluates stress levels. The output generates a set of passenger emotional state data.

[0398] Step 2:

[0399] The server stores the analyzed data in a Microsoft Azure database and re-evaluates passengers' emotional patterns by comparing them with historical data. At this point, it compares the data with previous passenger feedback to improve the accuracy of emotion-based action recommendations. The input consists of newly acquired emotional state data and historical records, and the output is an updated emotion analysis model.

[0400] Step 3:

[0401] The terminal uses emotional data received from a server to provide passengers with real-time feedback. If a passenger shows signs of fatigue, it selects relaxing music and automatically plays a music playlist. Furthermore, it works in conjunction with the car's navigation system to select scenic routes. The inputs utilize emotional data from the server and the vehicle's geographical information, and the output determines the music playlist to be played and alternative routes.

[0402] Step 4:

[0403] Users experience music selection and route changes from the system as passengers and provide feedback on the quality of the services provided through their terminals. Input is feedback information based on the user's actual experience, and output is feedback data sent to a server for use in future model improvements.

[0404] Step 5:

[0405] The server analyzes user feedback using learning mechanisms and performs updates to improve the accuracy of its sentiment analysis model and recommended content. The input is feedback data sent from the device, and the output is an enhanced sentiment analysis model and improved user experience.

[0406] 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.

[0407] 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.

[0408] 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.

[0409] [Third Embodiment]

[0410] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0411] 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.

[0412] 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).

[0413] 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.

[0414] 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.

[0415] 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).

[0416] 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.

[0417] 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.

[0418] 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.

[0419] 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.

[0420] 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.

[0421] 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".

[0422] This invention will be specifically implemented as an AI system to support a company's business strategy. Each function is based on the coordinated operation of three parties: the server, the terminal, and the user.

[0423] First, the server collects necessary information from the company's internal databases and external data sources. The collected data encompasses various types of business strategies and is analyzed in detail using natural language processing techniques to contribute to corporate decision-making. For example, it can collect news articles about competitors and data on market trends, and extract useful information from their content.

[0424] Next, the server performs predictive analytics based on the collected data to generate future business scenarios. This allows companies to simulate future developments and assess the probability of success and potential risks. For example, multiple scenarios for entering a new market are evaluated, and the most promising approach is selected.

[0425] The terminal is used in board meetings and management meetings, providing an interface for users to access AI. Through this interface, users can input questions in real time during meetings and receive immediate strategic suggestions from the AI. For example, if a question is asked about pricing for a new product, the AI ​​will suggest an appropriate price range based on historical market data and current trends.

[0426] Furthermore, the server leverages past discussion history and industry trends to suggest important topics. This feature helps users recognize key issues that they might otherwise overlook. Finally, the system is continuously improved based on feedback, enhancing the accuracy of the model for future strategic planning.

[0427] In this way, AI systems are being used as a powerful tool to quickly and accurately support the complex decision-making processes that companies face, and to maintain a competitive advantage.

[0428] The following describes the processing flow.

[0429] Step 1:

[0430] The server collects relevant data from internal corporate databases and external data sources. This includes market trend reports, competitor news articles, and social media posts. Automated crawlers and API integrations are used for data collection.

[0431] Step 2:

[0432] The server applies natural language processing (NLP) to the collected data and performs text analysis. This extracts the thinking patterns and insights of executives and prominent strategists from the data, and the analysis results are then templated. These templates serve as important guidelines for subsequent strategic planning.

[0433] Step 3:

[0434] The server builds a predictive analytics model based on the analyzed data. This model incorporates past business performance and market trends to generate future business scenarios. Machine learning algorithms are used in this process to refine the scenarios.

[0435] Step 4:

[0436] The server performs simulations for the generated scenarios. It runs simulations under various assumptions and evaluates the likelihood of success and the risks associated with each scenario. The evaluation results are recorded in a database and used for subsequent decision-making.

[0437] Step 5:

[0438] The device provides an interface that allows users to input questions to the AI ​​in real time. This enables quick questioning during meetings to facilitate business decision-making. The UI is designed with real-time functionality in mind, making it user-friendly.

[0439] Step 6:

[0440] The server instantly generates answers to user questions. Based on the question, it extracts the most relevant data and uses a predictive model to generate the answer. The answer is presented as a concrete strategic proposal or actionable plan.

[0441] Step 7:

[0442] Users proceed with discussions in board meetings and management meetings based on strategies proposed by the AI. This includes considering proposed scenarios, success probabilities, and risks. If necessary, the AI ​​also assists in setting the agenda for the meetings.

[0443] Step 8:

[0444] The server aggregates user feedback and uses it to learn from and improve the system. The collected feedback is used to improve the accuracy of the model and enhance the quality of future strategic proposals. Through this process, the system continuously evolves, more effectively supporting the formulation of corporate strategies.

[0445] (Example 1)

[0446] 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."

[0447] In corporate business strategy, it is necessary to effectively collect and analyze large amounts of data and predict future developments. However, the diversity of information and the rapid pace of trends complicate the decision-making process, making it difficult to quickly formulate appropriate strategies. This invention aims to solve these problems and improve the competitiveness of companies.

[0448] 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.

[0449] In this invention, the server includes information gathering means for collecting information from external information sources and internal information repositories, information analysis means for performing natural language processing on the collected information and extracting the thinking patterns of decision-makers and formulaters, and predictive analysis means for integrating past business information and market trends to construct a predictive model. This enables rapid and accurate decision-making within companies.

[0450] "Information gathering means" refers to the function of effectively and efficiently collecting necessary information from external information sources and internal information repositories.

[0451] "Information analysis tools" are functions that apply natural language processing to collected information to extract the thought patterns of decision-makers and formulaters.

[0452] "Predictive analysis tools" refer to functions that integrate past business information and market trends to build models for predicting future business developments.

[0453] A "simulation tool" is a function that uses generated business scenarios to evaluate the likelihood of success and the associated risks.

[0454] The "inquiry response system" is a function that generates appropriate answers immediately to inquiries entered by users during a meeting.

[0455] The "agenda setting mechanism" is a function that proposes important topics to be discussed based on past decision history and industry trends.

[0456] "Learning tools" refer to a function that continuously improves information gathering and analysis models based on user feedback, aiming to enhance the accuracy of future proposals.

[0457] "Generative AI models" refer to artificial intelligence technology used to generate new business scenarios based on diverse information.

[0458] In an embodiment of this invention, the server first acquires necessary information from external information sources and internal information libraries using information gathering means. APIs and web crawling technologies are used for this information gathering, and market data and competitor trends necessary for strengthening the company's competitiveness are collected.

[0459] Next, the server activates its information analysis tools and uses natural language processing technology to analyze the collected information in detail. This analysis uses an NLP engine to classify the information and performs entity recognition and sentiment analysis to extract information useful from the decision-maker's perspective.

[0460] The analysis results are processed using predictive analytics tools, and by integrating past business information and market trends, a model is constructed to predict future business developments. Generative AI models are utilized in this process to propose realistic business scenarios.

[0461] The terminal provides an interface for users to access the system. Through this interface, users can receive analysis results and strategic suggestions from the server in real time. For example, by entering a prompt such as, "Please propose a strategy to gain a competitive advantage in the sustainable energy market," users can receive specific suggestions from the system.

[0462] Furthermore, the server utilizes an agenda-setting mechanism to propose new topics based on past decision history and industry trends. This feature helps in identifying important issues that are often overlooked during meetings and strategic planning.

[0463] The server analyzes user feedback through learning mechanisms and continuously improves the system. This improves the accuracy of the generated AI model, further enhancing the quality of future suggestions.

[0464] In this way, the invention functions as a comprehensive system to support a company's strategic decision-making.

[0465] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0466] Step 1:

[0467] The server collects information from external sources and internal databases. This process utilizes APIs and web crawling technologies to obtain market data and competitor information. Inputs include parameters for data collection based on the company's requirements, and output is a dataset of the acquired raw data. Specifically, the server periodically updates the information using specified URLs and database connections.

[0468] Step 2:

[0469] The server processes the collected data using information analysis tools. This process extracts important keywords and topics from the data using natural language processing techniques. The raw data collected in step 1 is used as input, and structured information is generated as output. Specifically, the server activates an NLP engine and applies entity recognition and sentiment analysis algorithms.

[0470] Step 3:

[0471] The server builds a predictive model based on the analysis results using predictive analytics tools. A generative AI model is used in this process to generate future business scenarios. The structured information obtained in step 2 is provided as input, and multiple predicted business scenarios are generated as output. Specifically, the server trains the model using statistical methods and machine learning algorithms.

[0472] Step 4:

[0473] The terminal provides an interface for the user to interact with the system. Here, the user can input prompts and receive strategic suggestions in real time. As input, the user provides prompts to the terminal, and as output, the AI's suggestions are presented to the user. Specifically, the terminal displays the results in a dashboard format and provides immediate responses to the user's queries.

[0474] Step 5:

[0475] The server receives feedback from users and improves the system through learning mechanisms. This improves the accuracy of the generated AI model. User feedback is sent to the server as input, and the improved model is used as output for the next strategy proposal. Specific operations include feedback analysis and model retraining.

[0476] (Application Example 1)

[0477] 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."

[0478] The problem that this invention aims to solve is to make quick and accurate decisions for optimizing urban management and resident services in smart cities. Conventional systems have had difficulty effectively analyzing diverse data and supporting real-time strategic planning. Therefore, it is necessary to strengthen data-driven decision-making processes in urban planning and urban management.

[0479] 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.

[0480] In this invention, the server includes data collection means for collecting data from external data sources and internal databases, data analysis means for performing natural language processing on the collected data and extracting thought patterns of administrators and planners, and predictive analysis means for integrating past business data and market trends to construct a predictive model. This enables the real-time generation of effective policy proposals for optimizing urban management and resident services in smart cities.

[0481] "Data collection means" refers to the function of systematically and efficiently acquiring necessary information from external data sources and internal databases.

[0482] "Data analysis methods" refer to techniques that apply natural language processing and other methods to collected data to extract the thought patterns of managers and planners.

[0483] "Predictive analytics" refers to the process of analyzing past business data and market trends to build models for predicting future scenarios.

[0484] A "simulation tool" is a technology that evaluates the likelihood of success and the risks based on generated business scenarios, and supports decision-making.

[0485] A "question answering system" is a function that instantly generates appropriate answers to real-time questions entered by users during a meeting.

[0486] The "agenda setting mechanism" is a function that proposes important agenda items based on past decision history and industry trends.

[0487] "Learning methods" refer to the process of improving the accuracy of an analytical model based on feedback information.

[0488] The "Urban Strategy Provisioning Tool" is a function that proposes operational plans useful for improving urban management and resident services in real time, based on collected urban data.

[0489] The system for realizing this application consists of three main components: a server, a terminal, and a user. The server collects data from external data sources and internal databases and performs data analysis using natural language processing technology. Specifically, it extracts necessary information from the company's internal database, incorporates external data sources such as market trend data and industry news articles, and integrates diverse data to extract the thought patterns of managers and planners.

[0490] Furthermore, the server possesses predictive analytics capabilities, leveraging historical operational data and market trends to predict and generate future operational scenarios. This process involves data integration and model construction using machine learning algorithms. As a result, it becomes possible to propose effective strategies that contribute to the optimization of urban management and resident services.

[0491] The terminal is used particularly during meetings and provides an interface that allows users to input questions into the system in real time. Based on user questions, the server immediately uses a generated AI model to suggest optimal measures and solutions. Important agenda items that are often overlooked during discussions can also be suggested by the server based on past decision history and industry trends. This function supports critical decision-making in cities and promotes the rapid and effective implementation of plans and measures.

[0492] The hardware and software used include a programming environment using Python, data analysis servers running on Google Cloud Platform or Amazon Web Services, and libraries specialized for natural language processing (e.g., spaCy or NLTK). As a concrete example, in discussions about introducing a new public transportation system, a prompt such as "What is the optimal way to introduce a new bus route?" could be generated based on the discovered transportation data and predictive analytics. In this way, the system supports urban management operations and contributes to the provision of more efficient and effective services to residents.

[0493] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0494] Step 1:

[0495] The server collects data from external data sources and internal databases. It systematically acquires various types of data related to urban management (e.g., traffic data, demographic data, environmental data) using internet APIs and database queries. The input is a data acquisition request, and the output is the collected raw data.

[0496] Step 2:

[0497] The server applies natural language processing to the collected data and performs analysis. Specifically, it uses a Python natural language processing library (e.g., spaCy) to extract the thought patterns of managers and planners from the data. The input is the raw data collected in step 1, and the output is the extracted thought patterns and related topics.

[0498] Step 3:

[0499] The server performs predictive analysis based on historical business data and market trends to generate future business scenarios. In this process, it builds models using machine learning algorithms. The input is the analyzed data, and the output is the predicted business scenario.

[0500] Step 4:

[0501] The terminal receives questions entered by the user during the meeting and sends those questions to the server. Users ask questions about specific issues and measures related to urban management. The input is the user's question, and the output is the query sent to the server.

[0502] Step 5:

[0503] The server uses a generative AI model to suggest optimal measures and solutions based on the received questions. The generative AI model provides real-time answers while referencing past performance and trends. The input is the user's question query, and the output is the suggested measures.

[0504] Step 6:

[0505] The server proposes key agenda items based on past decision history and industry trends. This process involves historical data and trend analysis to complement often overlooked issues in urban planning. The input is existing decision history and trend data, and the output is the proposed agenda items.

[0506] Step 7:

[0507] The server receives feedback and learns to improve the system's accuracy. This feedback is used to improve the accuracy of the analysis model and inform future decision-making. The input is feedback on individual proposals, and the output is the improved analysis model.

[0508] Step 8:

[0509] Based on the generated strategic proposals and agendas, users implement measures to optimize urban management and resident services. Ultimately, users utilize the outputted information to reflect it in actual policies and plans. The input consists of actions proposed by the system, and the output consists of the implemented measures.

[0510] 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.

[0511] This invention aims to provide more effective strategic proposals by incorporating an emotion engine into an AI system that supports corporate decision-making. The system operates primarily through the interaction of three parties: a server, a terminal, and a user.

[0512] First, the server collects data from external data sources and internal databases and performs analysis using natural language processing. The results of this data analysis are used for predictive analytics, building a predictive model that integrates historical business data and market trends. Business scenarios generated based on the predictive model are evaluated for risk and probability of success through simulation.

[0513] The terminal provides an interface to users during meetings, enabling them to access the AI ​​system. Users can input questions in real time through the terminal and instantly receive responses and strategic suggestions from the AI ​​as a result.

[0514] This is where the emotion engine comes in. The server uses the emotion engine to recognize emotions from the user's facial expressions, tone of voice, and other factors. This recognized emotion information is used for question answering and personalized strategic suggestions. Specifically, if the user is feeling stressed, the suggestions can be made simpler or focused on positive outcomes.

[0515] Furthermore, the server has the ability to analyze past decision history and industry trends and suggest important agenda items to be discussed in meetings. Priorities and interests suggested by user sentiment are also taken into consideration to help ensure effective discussions.

[0516] Finally, the system analyzes the feedback and uses it to improve the next model. This allows the system to continuously improve its functionality, providing strong support for companies' business strategy planning. The emotion engine enables more personalized support and flexible suggestions tailored to user needs.

[0517] The following describes the processing flow.

[0518] Step 1:

[0519] The server automatically collects necessary information from the company's internal databases and external data sources. This includes transaction data, competitive analysis reports, and market trend information, and collection is performed via crawlers and APIs.

[0520] Step 2:

[0521] The server applies natural language processing (NLP) to the collected data and performs analysis. From the analysis results, it extracts the thinking patterns of managers and strategists and converts them into information that can be used as templates for strategic planning.

[0522] Step 3:

[0523] The server builds a predictive analytics model based on the analysis results. Here, it considers past success stories and current market trends to generate multiple future business scenarios. Machine learning algorithms are used to improve the accuracy of these scenarios.

[0524] Step 4:

[0525] The server simulates the generated business scenarios and evaluates their likelihood of success and the associated risks. The evaluation results are recorded in a database to aid in decision-making.

[0526] Step 5:

[0527] The terminal provides an interface for users to input questions in real time during a meeting. Users can input specific management questions and expect immediate responses.

[0528] Step 6:

[0529] The server searches relevant data based on the entered question and generates answers and strategic suggestions by referring to predictive models. This is where the emotion engine comes in, tailoring the suggestions to the user's emotional state.

[0530] Step 7:

[0531] The server uses an emotion engine to recognize the user's emotions in real time from their facial expressions and tone of voice. For example, if the user is feeling anxious, it will select a suggestion style that provides reassurance.

[0532] Step 8:

[0533] Users facilitate discussions in board meetings and management meetings based on the answers and suggestions received from the AI. They discuss the validity and feasibility of proposed strategies and provide feedback as needed.

[0534] Step 9:

[0535] The server analyzes user feedback and uses it to improve the model. This allows the system to continuously evolve, improving the accuracy of the strategies it proposes next.

[0536] (Example 2)

[0537] 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."

[0538] In modern business management, rapid and appropriate decision-making is essential, but effectively utilizing vast amounts of external information and internal company data while providing real-time strategic proposals is challenging. Furthermore, providing personalized recommendations that consider the user's emotions and stress levels during decision-making is a major challenge. To address these challenges, a system integrating efficient data analysis and emotion recognition is necessary.

[0539] 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.

[0540] In this invention, the server includes information gathering means, information analysis means, and a prediction function. This enables the extraction of useful knowledge patterns from vast amounts of external and internal data, allowing for real-time strategic proposals and personalized decision support. Furthermore, by using an emotion-responsive function, it is possible to realize flexible proposals that take into account the user's psychological state, thereby improving the accuracy and efficiency of decision-making.

[0541] "Information gathering means" refers to mechanisms and methods for efficiently collecting necessary information from external information sources and internal information databases.

[0542] "Information analysis means" refers to mechanisms and methods for analyzing collected raw data using natural language processing techniques to extract useful knowledge patterns.

[0543] A "predictive function" is a mechanism or method for predicting future trends based on past business data and market conditions, and for generating specific predictive models.

[0544] A "simulation tool" is a mechanism or method for conducting simulations to evaluate the feasibility and associated risks of a generated scenario.

[0545] A "question and answer function" is a mechanism or method for generating quick and accurate answers to questions entered by users during meetings or other similar situations.

[0546] The "agenda setting function" refers to a mechanism or method for proposing important discussion topics based on past decision-making results and industry trends.

[0547] "Emotional response function" refers to a mechanism or method that analyzes the user's psychological state and enables individualized responses in providing suggestions and supporting decision-making.

[0548] A "learning function" refers to a mechanism or method for improving the overall accuracy and efficiency of a system by collecting and analyzing user feedback.

[0549] The system in this invention implements a decision support process through the collaboration of a server, a terminal, and a user.

[0550] First, the server uses information gathering tools to collect necessary information from external sources and internal information databases. This process extracts data from publicly available information on the internet and from the company's internal data management system. Specifically, it utilizes Python libraries such as pandas and APIs. The collected data is then analyzed using information analysis tools and natural language processing (NLP) techniques. Here, NLP libraries such as spaCy and NLTK are used to extract topics and sentiment from text data, and to extract knowledge patterns.

[0551] Next, the server uses the data collected by the prediction function to generate a predictive model using a machine learning algorithm. This algorithm utilizes libraries such as scikit-learn and TensorFlow to achieve more accurate future predictions. Based on these predictions, the server simulates the generated business scenarios using simulation tools, evaluates the likelihood of success and the associated risks, and proposes the optimal strategy. In this process, the use of Monte Carlo's method or linear programming in the simulation is recommended.

[0552] The terminal assists users in accessing server analysis results and suggestions during meetings through its user interface. The terminal instantly sends entered questions to the AI ​​system and presents the user with responses based on its question-and-answer function.

[0553] A unique feature of the system is its server-based emotion-responsiveness. It analyzes the user's voice tone and facial expressions using speech recognition and image processing technologies, and then provides strategic suggestions tailored to the user's emotional state. Specific technologies used include speech recognition via Google Cloud Speech-to-Text and facial recognition via OpenCV. By flexibly adjusting responses and suggestions based on this emotional information, the system can support more accurate decision-making.

[0554] Furthermore, the server collects feedback from users through terminals and improves the system's accuracy through its learning function. Here, the collected feedback is analyzed and used to readjust the model. An example of a specific prompt message is, "Please forecast sales of the new product for the next three months and provide additional information to improve reliability." Through this process, the system is constantly updated and can respond to user needs in the most optimal way.

[0555] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0556] Step 1:

[0557] The server retrieves information from external sources and internal databases. Specifically, it uses news sites and market data from the internet as external sources, and customer information and sales history from the company as internal databases. This information is automatically retrieved through APIs and database connections. The input is in various data formats, and the output is a structured data list. The Python pandas library is used to format the data and output it in a unified format.

[0558] Step 2:

[0559] The server performs natural language processing on the collected information and then analyzes it. The software used includes spaCy and NLTK, which extract meaningful topics and sentiments from text data. Raw text data is provided as input, and the output generates feature lists and numerical data based on the analysis results. This allows for the extraction of key topics in business operations and market sentiment trends.

[0560] Step 3:

[0561] The server builds a machine learning model based on the analysis results. Specifically, it uses libraries such as scikit-learn and TensorFlow to model trends from historical data. The input is a list of features from the analysis results, and the output is a predictive model. This can be used to predict sales and market trends. Hyperparameter optimization is performed as needed during model construction.

[0562] Step 4:

[0563] The server uses the generated predictive model to simulate multiple business scenarios. It employs methods such as Monte Carlo and linear programming to evaluate the probability of success and the risks associated with each scenario. The inputs are the predictive model and scenario data, while the outputs are the success probability and risk assessment for each scenario. This allows the server to identify the most promising strategic options.

[0564] Step 5:

[0565] The terminal provides an interface for users to input inquiries and instructions. Users use the terminal to enter questions about specific strategies, which are processed in real time by the server. The user's question is given as input, and the server's response is displayed as output. This allows users to make quick decisions even during meetings.

[0566] Step 6:

[0567] The server analyzes the user's psychological state using emotion-responsiveness features. It utilizes speech recognition and facial recognition technologies to analyze whether the user is experiencing stress or excitement. Input is the user's voice and video data, and output is the result of the emotional state analysis. Based on these results, the server personalizes responses and strategic suggestions, providing appropriate care for specific emotional states.

[0568] Step 7:

[0569] The server collects user feedback and uses it to improve the system. The feedback information is stored in a database, and the model's accuracy is improved through learning. The input is user feedback data, and the output is the improved model. This allows for continuous improvement in the accuracy of the system's analysis and recommendation functions.

[0570] (Application Example 2)

[0571] 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."

[0572] In mobility services provided by autonomous vehicles, there is a need to appropriately understand passengers' emotional states and provide a comfortable and satisfying travel experience. However, current technology is unable to analyze passengers' emotions in real time and respond flexibly based on that analysis. As a result, it is difficult to fully meet passenger needs and improve the quality of service.

[0573] 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.

[0574] In this invention, the server includes information gathering means for collecting information from external information sources and internal information repositories, information analysis means for performing natural language processing on the collected information and extracting the decision-maker's thinking tendencies, and emotion analysis means for analyzing the user's emotional state and optimizing the operation of the transportation means. This makes it possible to adjust the operation of the transportation means according to the passenger's emotions, enabling a comfortable and personalized travel experience.

[0575] "Information gathering means" refers to methods and systems for collecting relevant information from external sources and internal information repositories.

[0576] "Information analysis methods" refer to methods and techniques that perform natural language processing on collected information to extract and analyze the thinking tendencies and characteristics of decision-makers.

[0577] "Predictive analysis tools" refer to methods and devices that integrate past business information and market trends to build models for predicting future developments.

[0578] "Simulation methods" refer to technologies and techniques for simulating and implementing generated business operations to evaluate their likelihood of success and associated risks.

[0579] A "question answering system" refers to a method or system for instantly generating and providing answers to questions entered by users in meetings or other settings.

[0580] "Agenda setting methods" refer to processes and techniques for proposing important agenda items based on past decision history and industry trends.

[0581] "Learning methods" refer to methods or systems that analyze feedback within a system and continuously improve the model based on that information.

[0582] "Emotional analysis means" refers to technologies and methods for analyzing a user's emotional state in real time and optimizing the operation and services of transportation based on that analysis.

[0583] This invention is a method for realizing a system that analyzes passenger emotions in autonomous vehicles and provides a comfortable travel experience.

[0584] The server collects information from external and internal data sources and applies natural language processing to recognize passengers' emotional states. This utilizes the camera and microphone on smartphones and employs the Google Cloud Vision API for facial expression analysis. Audio data is analyzed for tone using Amazon Polly. The analysis results are stored in a Microsoft Azure database, and each time data is collected, data processing is performed to quantify the passengers' emotional states.

[0585] The terminal provides passengers with real-time suggestions based on analysis results. For example, if a passenger shows signs of fatigue, the system will select and play appropriate music and suggest a scenic route. These features improve comfort within the vehicle and provide passengers with a more satisfying travel experience.

[0586] Users can provide feedback to the system through their devices. This feedback is analyzed by learning mechanisms, and the system continuously improves its model.

[0587] For example, if a passenger appears tired after work, the system will suggest and automatically play relaxing music. It will also flexibly change the route, recommending a route that offers more refreshing scenery for the passenger to the autonomous vehicle.

[0588] An example of a prompt might be: "The passenger's expression indicates fatigue. Based on this information, suggest relaxing music and a refreshing route."

[0589] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0590] Step 1:

[0591] The server captures passengers' facial expressions and voice tones through the smartphone's camera and microphone. Real-time video and audio data from the smartphone are used as input. The data is analyzed using the Google Cloud Vision API and Amazon Polly to quantify the passengers' emotional state. At this stage, facial analysis assesses passenger happiness and fatigue levels, while voice analysis evaluates stress levels. The output generates a set of passenger emotional state data.

[0592] Step 2:

[0593] The server stores the analyzed data in a Microsoft Azure database and re-evaluates passengers' emotional patterns by comparing them with historical data. At this point, it compares the data with previous passenger feedback to improve the accuracy of emotion-based action recommendations. The input consists of newly acquired emotional state data and historical records, and the output is an updated emotion analysis model.

[0594] Step 3:

[0595] The terminal uses emotional data received from a server to provide passengers with real-time feedback. If a passenger shows signs of fatigue, it selects relaxing music and automatically plays a music playlist. Furthermore, it works in conjunction with the car's navigation system to select scenic routes. The inputs utilize emotional data from the server and the vehicle's geographical information, and the output determines the music playlist to be played and alternative routes.

[0596] Step 4:

[0597] Users experience music selection and route changes from the system as passengers and provide feedback on the quality of the services provided through their terminals. Input is feedback information based on the user's actual experience, and output is feedback data sent to a server for use in future model improvements.

[0598] Step 5:

[0599] The server analyzes user feedback using learning mechanisms and performs updates to improve the accuracy of its sentiment analysis model and recommended content. The input is feedback data sent from the device, and the output is an enhanced sentiment analysis model and improved user experience.

[0600] 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.

[0601] 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.

[0602] 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.

[0603] [Fourth Embodiment]

[0604] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0605] 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.

[0606] 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).

[0607] 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.

[0608] 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.

[0609] 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).

[0610] 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.

[0611] 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.

[0612] 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.

[0613] 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.

[0614] 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.

[0615] 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.

[0616] 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".

[0617] This invention will be specifically implemented as an AI system to support a company's business strategy. Each function is based on the coordinated operation of three parties: the server, the terminal, and the user.

[0618] First, the server collects necessary information from the company's internal databases and external data sources. The collected data encompasses various types of business strategies and is analyzed in detail using natural language processing techniques to contribute to corporate decision-making. For example, it can collect news articles about competitors and data on market trends, and extract useful information from their content.

[0619] Next, the server performs predictive analytics based on the collected data to generate future business scenarios. This allows companies to simulate future developments and assess the probability of success and potential risks. For example, multiple scenarios for entering a new market are evaluated, and the most promising approach is selected.

[0620] The terminal is used in board meetings and management meetings, providing an interface for users to access AI. Through this interface, users can input questions in real time during meetings and receive immediate strategic suggestions from the AI. For example, if a question is asked about pricing for a new product, the AI ​​will suggest an appropriate price range based on historical market data and current trends.

[0621] Furthermore, the server leverages past discussion history and industry trends to suggest important topics. This feature helps users recognize key issues that they might otherwise overlook. Finally, the system is continuously improved based on feedback, enhancing the accuracy of the model for future strategic planning.

[0622] In this way, AI systems are being used as a powerful tool to quickly and accurately support the complex decision-making processes that companies face, and to maintain a competitive advantage.

[0623] The following describes the processing flow.

[0624] Step 1:

[0625] The server collects relevant data from internal corporate databases and external data sources. This includes market trend reports, competitor news articles, and social media posts. Automated crawlers and API integrations are used for data collection.

[0626] Step 2:

[0627] The server applies natural language processing (NLP) to the collected data and performs text analysis. This extracts the thinking patterns and insights of executives and prominent strategists from the data, and the analysis results are then templated. These templates serve as important guidelines for subsequent strategic planning.

[0628] Step 3:

[0629] The server builds a predictive analytics model based on the analyzed data. This model incorporates past business performance and market trends to generate future business scenarios. Machine learning algorithms are used in this process to refine the scenarios.

[0630] Step 4:

[0631] The server performs simulations for the generated scenarios. It runs simulations under various assumptions and evaluates the likelihood of success and the risks associated with each scenario. The evaluation results are recorded in a database and used for subsequent decision-making.

[0632] Step 5:

[0633] The device provides an interface that allows users to input questions to the AI ​​in real time. This enables quick questioning during meetings to facilitate business decision-making. The UI is designed with real-time functionality in mind, making it user-friendly.

[0634] Step 6:

[0635] The server instantly generates answers to user questions. Based on the question, it extracts the most relevant data and uses a predictive model to generate the answer. The answer is presented as a concrete strategic proposal or actionable plan.

[0636] Step 7:

[0637] Users proceed with discussions in board meetings and management meetings based on strategies proposed by the AI. This includes considering proposed scenarios, success probabilities, and risks. If necessary, the AI ​​also assists in setting the agenda for the meetings.

[0638] Step 8:

[0639] The server aggregates user feedback and uses it to learn from and improve the system. The collected feedback is used to improve the accuracy of the model and enhance the quality of future strategic proposals. Through this process, the system continuously evolves, more effectively supporting the formulation of corporate strategies.

[0640] (Example 1)

[0641] 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".

[0642] In corporate business strategy, it is necessary to effectively collect and analyze large amounts of data and predict future developments. However, the diversity of information and the rapid pace of trends complicate the decision-making process, making it difficult to quickly formulate appropriate strategies. This invention aims to solve these problems and improve the competitiveness of companies.

[0643] 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.

[0644] In this invention, the server includes information gathering means for collecting information from external information sources and internal information repositories, information analysis means for performing natural language processing on the collected information and extracting the thinking patterns of decision-makers and formulaters, and predictive analysis means for integrating past business information and market trends to construct a predictive model. This enables rapid and accurate decision-making within companies.

[0645] "Information gathering means" refers to the function of effectively and efficiently collecting necessary information from external information sources and internal information repositories.

[0646] "Information analysis tools" are functions that apply natural language processing to collected information to extract the thought patterns of decision-makers and formulaters.

[0647] "Predictive analysis tools" refer to functions that integrate past business information and market trends to build models for predicting future business developments.

[0648] A "simulation tool" is a function that uses generated business scenarios to evaluate the likelihood of success and the associated risks.

[0649] The "inquiry response system" is a function that generates appropriate answers immediately to inquiries entered by users during a meeting.

[0650] The "agenda setting mechanism" is a function that proposes important topics to be discussed based on past decision history and industry trends.

[0651] "Learning tools" refer to a function that continuously improves information gathering and analysis models based on user feedback, aiming to enhance the accuracy of future proposals.

[0652] "Generative AI models" refer to artificial intelligence technology used to generate new business scenarios based on diverse information.

[0653] In an embodiment of this invention, the server first acquires necessary information from external information sources and internal information libraries using information gathering means. APIs and web crawling technologies are used for this information gathering, and market data and competitor trends necessary for strengthening the company's competitiveness are collected.

[0654] Next, the server activates its information analysis tools and uses natural language processing technology to analyze the collected information in detail. This analysis uses an NLP engine to classify the information and performs entity recognition and sentiment analysis to extract information useful from the decision-maker's perspective.

[0655] The analysis results are processed using predictive analytics tools, and by integrating past business information and market trends, a model is constructed to predict future business developments. Generative AI models are utilized in this process to propose realistic business scenarios.

[0656] The terminal provides an interface for users to access the system. Through this interface, users can receive analysis results and strategic suggestions from the server in real time. For example, by entering a prompt such as, "Please propose a strategy to gain a competitive advantage in the sustainable energy market," users can receive specific suggestions from the system.

[0657] Furthermore, the server utilizes an agenda-setting mechanism to propose new topics based on past decision history and industry trends. This feature helps in identifying important issues that are often overlooked during meetings and strategic planning.

[0658] The server analyzes user feedback through learning mechanisms and continuously improves the system. This improves the accuracy of the generated AI model, further enhancing the quality of future suggestions.

[0659] In this way, the invention functions as a comprehensive system to support a company's strategic decision-making.

[0660] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0661] Step 1:

[0662] The server collects information from external sources and internal databases. This process utilizes APIs and web crawling technologies to obtain market data and competitor information. Inputs include parameters for data collection based on the company's requirements, and output is a dataset of the acquired raw data. Specifically, the server periodically updates the information using specified URLs and database connections.

[0663] Step 2:

[0664] The server processes the collected data using information analysis tools. This process extracts important keywords and topics from the data using natural language processing techniques. The raw data collected in step 1 is used as input, and structured information is generated as output. Specifically, the server activates an NLP engine and applies entity recognition and sentiment analysis algorithms.

[0665] Step 3:

[0666] The server builds a predictive model based on the analysis results using predictive analytics tools. A generative AI model is used in this process to generate future business scenarios. The structured information obtained in step 2 is provided as input, and multiple predicted business scenarios are generated as output. Specifically, the server trains the model using statistical methods and machine learning algorithms.

[0667] Step 4:

[0668] The terminal provides an interface for the user to interact with the system. Here, the user can input prompts and receive strategic suggestions in real time. As input, the user provides prompts to the terminal, and as output, the AI's suggestions are presented to the user. Specifically, the terminal displays the results in a dashboard format and provides immediate responses to the user's queries.

[0669] Step 5:

[0670] The server receives feedback from users and improves the system through learning mechanisms. This improves the accuracy of the generated AI model. User feedback is sent to the server as input, and the improved model is used as output for the next strategy proposal. Specific operations include feedback analysis and model retraining.

[0671] (Application Example 1)

[0672] 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".

[0673] The problem that this invention aims to solve is to make quick and accurate decisions for optimizing urban management and resident services in smart cities. Conventional systems have had difficulty effectively analyzing diverse data and supporting real-time strategic planning. Therefore, it is necessary to strengthen data-driven decision-making processes in urban planning and urban management.

[0674] 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.

[0675] In this invention, the server includes data collection means for collecting data from external data sources and internal databases, data analysis means for performing natural language processing on the collected data and extracting thought patterns of administrators and planners, and predictive analysis means for integrating past business data and market trends to construct a predictive model. This enables the real-time generation of effective policy proposals for optimizing urban management and resident services in smart cities.

[0676] "Data collection means" refers to the function of systematically and efficiently acquiring necessary information from external data sources and internal databases.

[0677] "Data analysis methods" refer to techniques that apply natural language processing and other methods to collected data to extract the thought patterns of managers and planners.

[0678] "Predictive analytics" refers to the process of analyzing past business data and market trends to build models for predicting future scenarios.

[0679] A "simulation tool" is a technology that evaluates the likelihood of success and the risks based on generated business scenarios, and supports decision-making.

[0680] A "question answering system" is a function that instantly generates appropriate answers to real-time questions entered by users during a meeting.

[0681] The "agenda setting mechanism" is a function that proposes important agenda items based on past decision history and industry trends.

[0682] "Learning methods" refer to the process of improving the accuracy of an analytical model based on feedback information.

[0683] The "Urban Strategy Provisioning Tool" is a function that proposes operational plans useful for improving urban management and resident services in real time, based on collected urban data.

[0684] The system for realizing this application consists of three main components: a server, a terminal, and a user. The server collects data from external data sources and internal databases and performs data analysis using natural language processing technology. Specifically, it extracts necessary information from the company's internal database, incorporates external data sources such as market trend data and industry news articles, and integrates diverse data to extract the thought patterns of managers and planners.

[0685] Furthermore, the server possesses predictive analytics capabilities, leveraging historical operational data and market trends to predict and generate future operational scenarios. This process involves data integration and model construction using machine learning algorithms. As a result, it becomes possible to propose effective strategies that contribute to the optimization of urban management and resident services.

[0686] The terminal is used particularly during meetings and provides an interface that allows users to input questions into the system in real time. Based on user questions, the server immediately uses a generated AI model to suggest optimal measures and solutions. Important agenda items that are often overlooked during discussions can also be suggested by the server based on past decision history and industry trends. This function supports critical decision-making in cities and promotes the rapid and effective implementation of plans and measures.

[0687] The hardware and software used include a programming environment using Python, data analysis servers running on Google Cloud Platform or Amazon Web Services, and libraries specialized for natural language processing (e.g., spaCy or NLTK). As a concrete example, in discussions about introducing a new public transportation system, a prompt such as "What is the optimal way to introduce a new bus route?" could be generated based on the discovered transportation data and predictive analytics. In this way, the system supports urban management operations and contributes to the provision of more efficient and effective services to residents.

[0688] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0689] Step 1:

[0690] The server collects data from external data sources and internal databases. It systematically acquires various types of data related to urban management (e.g., traffic data, demographic data, environmental data) using internet APIs and database queries. The input is a data acquisition request, and the output is the collected raw data.

[0691] Step 2:

[0692] The server applies natural language processing to the collected data and performs analysis. Specifically, it uses a Python natural language processing library (e.g., spaCy) to extract the thought patterns of managers and planners from the data. The input is the raw data collected in step 1, and the output is the extracted thought patterns and related topics.

[0693] Step 3:

[0694] The server performs predictive analysis based on historical business data and market trends to generate future business scenarios. In this process, it builds models using machine learning algorithms. The input is the analyzed data, and the output is the predicted business scenario.

[0695] Step 4:

[0696] The terminal receives questions entered by the user during the meeting and sends those questions to the server. Users ask questions about specific issues and measures related to urban management. The input is the user's question, and the output is the query sent to the server.

[0697] Step 5:

[0698] The server uses a generative AI model to suggest optimal measures and solutions based on the received questions. The generative AI model provides real-time answers while referencing past performance and trends. The input is the user's question query, and the output is the suggested measures.

[0699] Step 6:

[0700] The server proposes key agenda items based on past decision history and industry trends. This process involves historical data and trend analysis to complement often overlooked issues in urban planning. The input is existing decision history and trend data, and the output is the proposed agenda items.

[0701] Step 7:

[0702] The server receives feedback and learns to improve the system's accuracy. This feedback is used to improve the accuracy of the analysis model and inform future decision-making. The input is feedback on individual proposals, and the output is the improved analysis model.

[0703] Step 8:

[0704] Based on the generated strategic proposals and agendas, users implement measures to optimize urban management and resident services. Ultimately, users utilize the outputted information to reflect it in actual policies and plans. The input consists of actions proposed by the system, and the output consists of the implemented measures.

[0705] 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.

[0706] This invention aims to provide more effective strategic proposals by incorporating an emotion engine into an AI system that supports corporate decision-making. The system operates primarily through the interaction of three parties: a server, a terminal, and a user.

[0707] First, the server collects data from external data sources and internal databases and performs analysis using natural language processing. The results of this data analysis are used for predictive analytics, building a predictive model that integrates historical business data and market trends. Business scenarios generated based on the predictive model are evaluated for risk and probability of success through simulation.

[0708] The terminal provides an interface to users during meetings, enabling them to access the AI ​​system. Users can input questions in real time through the terminal and instantly receive responses and strategic suggestions from the AI ​​as a result.

[0709] This is where the emotion engine comes in. The server uses the emotion engine to recognize emotions from the user's facial expressions, tone of voice, and other factors. This recognized emotion information is used for question answering and personalized strategic suggestions. Specifically, if the user is feeling stressed, the suggestions can be made simpler or focused on positive outcomes.

[0710] Furthermore, the server has the ability to analyze past decision history and industry trends and suggest important agenda items to be discussed in meetings. Priorities and interests suggested by user sentiment are also taken into consideration to help ensure effective discussions.

[0711] Finally, the system analyzes the feedback and uses it to improve the next model. This allows the system to continuously improve its functionality, providing strong support for companies' business strategy planning. The emotion engine enables more personalized support and flexible suggestions tailored to user needs.

[0712] The following describes the processing flow.

[0713] Step 1:

[0714] The server automatically collects necessary information from the company's internal databases and external data sources. This includes transaction data, competitive analysis reports, and market trend information, and collection is performed via crawlers and APIs.

[0715] Step 2:

[0716] The server applies natural language processing (NLP) to the collected data and performs analysis. From the analysis results, it extracts the thinking patterns of managers and strategists and converts them into information that can be used as templates for strategic planning.

[0717] Step 3:

[0718] The server builds a predictive analytics model based on the analysis results. Here, it considers past success stories and current market trends to generate multiple future business scenarios. Machine learning algorithms are used to improve the accuracy of these scenarios.

[0719] Step 4:

[0720] The server simulates the generated business scenarios and evaluates their likelihood of success and the associated risks. The evaluation results are recorded in a database to aid in decision-making.

[0721] Step 5:

[0722] The terminal provides an interface for users to input questions in real time during a meeting. Users can input specific management questions and expect immediate responses.

[0723] Step 6:

[0724] The server searches relevant data based on the entered question and generates answers and strategic suggestions by referring to predictive models. This is where the emotion engine comes in, tailoring the suggestions to the user's emotional state.

[0725] Step 7:

[0726] The server uses an emotion engine to recognize the user's emotions in real time from their facial expressions and tone of voice. For example, if the user is feeling anxious, it will select a suggestion style that provides reassurance.

[0727] Step 8:

[0728] Users facilitate discussions in board meetings and management meetings based on the answers and suggestions received from the AI. They discuss the validity and feasibility of proposed strategies and provide feedback as needed.

[0729] Step 9:

[0730] The server analyzes user feedback and uses it to improve the model. This allows the system to continuously evolve, improving the accuracy of the strategies it proposes next.

[0731] (Example 2)

[0732] 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".

[0733] In modern business management, rapid and appropriate decision-making is essential, but effectively utilizing vast amounts of external information and internal company data while providing real-time strategic proposals is challenging. Furthermore, providing personalized recommendations that consider the user's emotions and stress levels during decision-making is a major challenge. To address these challenges, a system integrating efficient data analysis and emotion recognition is necessary.

[0734] 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.

[0735] In this invention, the server includes information gathering means, information analysis means, and a prediction function. This enables the extraction of useful knowledge patterns from vast amounts of external and internal data, allowing for real-time strategic proposals and personalized decision support. Furthermore, by using an emotion-responsive function, it is possible to realize flexible proposals that take into account the user's psychological state, thereby improving the accuracy and efficiency of decision-making.

[0736] "Information gathering means" refers to mechanisms and methods for efficiently collecting necessary information from external information sources and internal information databases.

[0737] "Information analysis means" refers to mechanisms and methods for analyzing collected raw data using natural language processing techniques to extract useful knowledge patterns.

[0738] A "predictive function" is a mechanism or method for predicting future trends based on past business data and market conditions, and for generating specific predictive models.

[0739] A "simulation tool" is a mechanism or method for conducting simulations to evaluate the feasibility and associated risks of a generated scenario.

[0740] A "question and answer function" is a mechanism or method for generating quick and accurate answers to questions entered by users during meetings or other similar situations.

[0741] The "agenda setting function" refers to a mechanism or method for proposing important discussion topics based on past decision-making results and industry trends.

[0742] "Emotional response function" refers to a mechanism or method that analyzes the user's psychological state and enables individualized responses in providing suggestions and supporting decision-making.

[0743] A "learning function" refers to a mechanism or method for improving the overall accuracy and efficiency of a system by collecting and analyzing user feedback.

[0744] The system in this invention implements a decision support process through the collaboration of a server, a terminal, and a user.

[0745] First, the server uses information gathering tools to collect necessary information from external sources and internal information databases. This process extracts data from publicly available information on the internet and from the company's internal data management system. Specifically, it utilizes Python libraries such as pandas and APIs. The collected data is then analyzed using information analysis tools and natural language processing (NLP) techniques. Here, NLP libraries such as spaCy and NLTK are used to extract topics and sentiment from text data, and to extract knowledge patterns.

[0746] Next, the server uses the data collected by the prediction function to generate a predictive model using a machine learning algorithm. This algorithm utilizes libraries such as scikit-learn and TensorFlow to achieve more accurate future predictions. Based on these predictions, the server simulates the generated business scenarios using simulation tools, evaluates the likelihood of success and the associated risks, and proposes the optimal strategy. In this process, the use of Monte Carlo's method or linear programming in the simulation is recommended.

[0747] The terminal assists users in accessing server analysis results and suggestions during meetings through its user interface. The terminal instantly sends entered questions to the AI ​​system and presents the user with responses based on its question-and-answer function.

[0748] A unique feature of the system is its server-based emotion-responsiveness. It analyzes the user's voice tone and facial expressions using speech recognition and image processing technologies, and then provides strategic suggestions tailored to the user's emotional state. Specific technologies used include speech recognition via Google Cloud Speech-to-Text and facial recognition via OpenCV. By flexibly adjusting responses and suggestions based on this emotional information, the system can support more accurate decision-making.

[0749] Furthermore, the server collects feedback from users through terminals and improves the system's accuracy through its learning function. Here, the collected feedback is analyzed and used to readjust the model. An example of a specific prompt message is, "Please forecast sales of the new product for the next three months and provide additional information to improve reliability." Through this process, the system is constantly updated and can respond to user needs in the most optimal way.

[0750] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0751] Step 1:

[0752] The server retrieves information from external sources and internal databases. Specifically, it uses news sites and market data from the internet as external sources, and customer information and sales history from the company as internal databases. This information is automatically retrieved through APIs and database connections. The input is in various data formats, and the output is a structured data list. The Python pandas library is used to format the data and output it in a unified format.

[0753] Step 2:

[0754] The server performs natural language processing on the collected information and then analyzes it. The software used includes spaCy and NLTK, which extract meaningful topics and sentiments from text data. Raw text data is provided as input, and the output generates feature lists and numerical data based on the analysis results. This allows for the extraction of key topics in business operations and market sentiment trends.

[0755] Step 3:

[0756] The server builds a machine learning model based on the analysis results. Specifically, it uses libraries such as scikit-learn and TensorFlow to model trends from historical data. The input is a list of features from the analysis results, and the output is a predictive model. This can be used to predict sales and market trends. Hyperparameter optimization is performed as needed during model construction.

[0757] Step 4:

[0758] The server uses the generated predictive model to simulate multiple business scenarios. It employs methods such as Monte Carlo and linear programming to evaluate the probability of success and the risks associated with each scenario. The inputs are the predictive model and scenario data, while the outputs are the success probability and risk assessment for each scenario. This allows the server to identify the most promising strategic options.

[0759] Step 5:

[0760] The terminal provides an interface for users to input inquiries and instructions. Users use the terminal to enter questions about specific strategies, which are processed in real time by the server. The user's question is given as input, and the server's response is displayed as output. This allows users to make quick decisions even during meetings.

[0761] Step 6:

[0762] The server analyzes the user's psychological state using emotion-responsiveness features. It utilizes speech recognition and facial recognition technologies to analyze whether the user is experiencing stress or excitement. Input is the user's voice and video data, and output is the result of the emotional state analysis. Based on these results, the server personalizes responses and strategic suggestions, providing appropriate care for specific emotional states.

[0763] Step 7:

[0764] The server collects user feedback and uses it to improve the system. The feedback information is stored in a database, and the model's accuracy is improved through learning. The input is user feedback data, and the output is the improved model. This allows for continuous improvement in the accuracy of the system's analysis and recommendation functions.

[0765] (Application Example 2)

[0766] 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".

[0767] In mobility services provided by autonomous vehicles, there is a need to appropriately understand passengers' emotional states and provide a comfortable and satisfying travel experience. However, current technology is unable to analyze passengers' emotions in real time and respond flexibly based on that analysis. As a result, it is difficult to fully meet passenger needs and improve the quality of service.

[0768] 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.

[0769] In this invention, the server includes information gathering means for collecting information from external information sources and internal information repositories, information analysis means for performing natural language processing on the collected information and extracting the decision-maker's thinking tendencies, and emotion analysis means for analyzing the user's emotional state and optimizing the operation of the transportation means. This makes it possible to adjust the operation of the transportation means according to the passenger's emotions, enabling a comfortable and personalized travel experience.

[0770] "Information gathering means" refers to methods and systems for collecting relevant information from external sources and internal information repositories.

[0771] "Information analysis methods" refer to methods and techniques that perform natural language processing on collected information to extract and analyze the thinking tendencies and characteristics of decision-makers.

[0772] "Predictive analysis tools" refer to methods and devices that integrate past business information and market trends to build models for predicting future developments.

[0773] "Simulation methods" refer to technologies and techniques for simulating and implementing generated business operations to evaluate their likelihood of success and associated risks.

[0774] A "question answering system" refers to a method or system for instantly generating and providing answers to questions entered by users in meetings or other settings.

[0775] "Agenda setting methods" refer to processes and techniques for proposing important agenda items based on past decision history and industry trends.

[0776] "Learning methods" refer to methods or systems that analyze feedback within a system and continuously improve the model based on that information.

[0777] "Emotional analysis means" refers to technologies and methods for analyzing a user's emotional state in real time and optimizing the operation and services of transportation based on that analysis.

[0778] This invention is a method for realizing a system that analyzes passenger emotions in autonomous vehicles and provides a comfortable travel experience.

[0779] The server collects information from external and internal data sources and applies natural language processing to recognize passengers' emotional states. This utilizes the camera and microphone on smartphones and employs the Google Cloud Vision API for facial expression analysis. Audio data is analyzed for tone using Amazon Polly. The analysis results are stored in a Microsoft Azure database, and each time data is collected, data processing is performed to quantify the passengers' emotional states.

[0780] The terminal provides passengers with real-time suggestions based on analysis results. For example, if a passenger shows signs of fatigue, the system will select and play appropriate music and suggest a scenic route. These features improve comfort within the vehicle and provide passengers with a more satisfying travel experience.

[0781] Users can provide feedback to the system through their devices. This feedback is analyzed by learning mechanisms, and the system continuously improves its model.

[0782] For example, if a passenger appears tired after work, the system will suggest and automatically play relaxing music. It will also flexibly change the route, recommending a route that offers more refreshing scenery for the passenger to the autonomous vehicle.

[0783] An example of a prompt might be: "The passenger's expression indicates fatigue. Based on this information, suggest relaxing music and a refreshing route."

[0784] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0785] Step 1:

[0786] The server captures passengers' facial expressions and voice tones through the smartphone's camera and microphone. Real-time video and audio data from the smartphone are used as input. The data is analyzed using the Google Cloud Vision API and Amazon Polly to quantify the passengers' emotional state. At this stage, facial analysis assesses passenger happiness and fatigue levels, while voice analysis evaluates stress levels. The output generates a set of passenger emotional state data.

[0787] Step 2:

[0788] The server stores the analyzed data in a Microsoft Azure database and re-evaluates passengers' emotional patterns by comparing them with historical data. At this point, it compares the data with previous passenger feedback to improve the accuracy of emotion-based action recommendations. The input consists of newly acquired emotional state data and historical records, and the output is an updated emotion analysis model.

[0789] Step 3:

[0790] The terminal uses emotional data received from a server to provide passengers with real-time feedback. If a passenger shows signs of fatigue, it selects relaxing music and automatically plays a music playlist. Furthermore, it works in conjunction with the car's navigation system to select scenic routes. The inputs utilize emotional data from the server and the vehicle's geographical information, and the output determines the music playlist to be played and alternative routes.

[0791] Step 4:

[0792] Users experience music selection and route changes from the system as passengers and provide feedback on the quality of the services provided through their terminals. Input is feedback information based on the user's actual experience, and output is feedback data sent to a server for use in future model improvements.

[0793] Step 5:

[0794] The server analyzes user feedback using learning mechanisms and performs updates to improve the accuracy of its sentiment analysis model and recommended content. The input is feedback data sent from the device, and the output is an enhanced sentiment analysis model and improved user experience.

[0795] 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.

[0796] 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.

[0797] 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 robot 414.

[0798] 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.

[0799] 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.

[0800] 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.

[0801] 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.

[0802] 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.

[0803] 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."

[0804] 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.

[0805] 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.

[0806] 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.

[0807] 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.

[0808] 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.

[0809] 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.

[0810] 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.

[0811] 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.

[0812] 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.

[0813] 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.

[0814] 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.

[0815] 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.

[0816] The following is further disclosed regarding the embodiments described above.

[0817] (Claim 1)

[0818] A data collection means for collecting data from external data sources and internal databases,

[0819] A data analysis method that performs natural language processing on collected data to extract the thinking patterns of managers and strategists,

[0820] A predictive analysis tool that integrates past business data and market trends to construct a predictive model,

[0821] A simulation means for simulating generated business scenarios and evaluating the likelihood of success and risk,

[0822] A question-answering system that generates real-time answers to questions entered by users during a meeting,

[0823] A means of setting agenda items that proposes important topics based on past decision history and industry trends,

[0824] Learning methods for analyzing feedback and improving the model,

[0825] A system that includes this.

[0826] (Claim 2)

[0827] The system according to claim 1, further comprising means for converting business scenarios into personalized strategic proposals based on real-time data analysis results.

[0828] (Claim 3)

[0829] The system according to claim 1, wherein the simulation means identifies the optimal strategy by comparing the likelihood of success and risks in multiple business scenarios.

[0830] "Example 1"

[0831] (Claim 1)

[0832] Information gathering means for collecting information from external information sources and internal information repositories,

[0833] An information analysis tool that performs natural language processing on collected information to extract the thinking patterns of decision-makers and formulaters,

[0834] A predictive analysis tool that constructs a predictive model by integrating past business information and market trends,

[0835] A simulation means for simulating generated business scenarios and evaluating the likelihood of success and risk,

[0836] An inquiry response system that generates immediate answers to inquiries entered by users during a meeting,

[0837] A means of setting agenda items that proposes important issues based on past decision history and industry trends,

[0838] Learning methods for analyzing feedback and improving the model,

[0839] A means of transforming information into personalized strategic proposals,

[0840] A system that includes this.

[0841] (Claim 2)

[0842] The system according to claim 1, wherein the simulation means identifies the optimal policy by comparing the likelihood of success and the risks in multiple business scenarios.

[0843] (Claim 3)

[0844] The system according to claim 1, which utilizes a generative AI model and uses business scenarios generated based on information to predict trends in business development.

[0845] "Application Example 1"

[0846] (Claim 1)

[0847] A data collection means for collecting data from external data sources and internal databases,

[0848] A data analysis method that performs natural language processing on collected data to extract the thought patterns of managers and planners,

[0849] A predictive analysis tool that integrates past business data and market trends to construct a predictive model,

[0850] A simulation means for simulating generated business scenarios and evaluating the likelihood of success and the risks,

[0851] A question-answering system that generates real-time answers to questions entered by users during a meeting,

[0852] A means of setting agenda items that propose important issues based on past decision history and industry trends,

[0853] Learning methods for analyzing feedback and improving the model,

[0854] A means of providing urban strategies that analyzes urban data and proposes business plans in real time,

[0855] A system that includes this.

[0856] (Claim 2)

[0857] The system according to claim 1, further comprising means for converting business scenarios into personalized policy proposals based on real-time data analysis results.

[0858] (Claim 3)

[0859] The system according to claim 1, wherein the simulation means identifies the optimal measure by comparing the probability of success and the risks in multiple business scenarios.

[0860] "Example 2 of combining an emotion engine"

[0861] (Claim 1)

[0862] Information gathering means for obtaining information from external data sources and internal databases,

[0863] An information analysis means that performs natural language processing on acquired information and extracts knowledge patterns,

[0864] A forecasting function that generates a forecasting model by integrating past business data and market conditions,

[0865] A simulation tool that simulates the generated scenario and evaluates the likelihood and risks of success,

[0866] A question-and-answer function that generates immediate responses to questions entered by users during a meeting,

[0867] A topic setting function that proposes important topics based on past decision-making history and industry trends,

[0868] An emotion response function that analyzes the user's emotional state using emotion analysis and adjusts the suggested content accordingly,

[0869] A learning function to analyze user feedback and improve the model,

[0870] A system that includes this.

[0871] (Claim 2)

[0872] The system according to claim 1, further comprising a function to convert scenarios into individualized strategic proposals based on real-time information analysis results.

[0873] (Claim 3)

[0874] The system according to claim 1, wherein the simulation measures identify the optimal strategy by comparing the likelihood and risk of success in multiple scenarios.

[0875] "Application example 2 when combining with an emotional engine"

[0876] (Claim 1)

[0877] Information gathering means for collecting information from external information sources and internal information repositories,

[0878] An information analysis method that performs natural language processing on collected information to extract the thinking tendencies of decision-makers,

[0879] A predictive analysis tool that integrates past business information and market trends to construct a predictive model,

[0880] A simulation method for simulating the generated business development and evaluating the likelihood of success and the risks,

[0881] A question-answering system that instantly generates answers to questions entered by users during a meeting,

[0882] A means of setting agenda items that proposes important issues based on past decision history and industry trends,

[0883] Learning methods for analyzing reactions and improving models,

[0884] An emotion analysis means that analyzes the emotional state of the user and optimizes the operation of the means of transport,

[0885] A system that includes this.

[0886] (Claim 2)

[0887] The system according to claim 1, further comprising means for converting business operations into individualized strategic proposals based on real-time information analysis results.

[0888] (Claim 3)

[0889] The system according to claim 1, wherein a simulation means identifies the optimal strategy by comparing the likelihood of success and risks in multiple business operations, and an emotion analysis means proposes the optimal behavior of the means of transport based on the user's emotions. [Explanation of Symbols]

[0890] 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

1. A data collection means for collecting data from external data sources and internal databases, A data analysis method that performs natural language processing on collected data to extract the thought patterns of managers and planners, A predictive analysis tool that integrates past business data and market trends to construct a predictive model, A simulation means for simulating generated business scenarios and evaluating the likelihood of success and the risks, A question-answering system that generates real-time answers to questions entered by users during a meeting, A means of setting agenda items that propose important issues based on past decision history and industry trends, Learning methods for analyzing feedback and improving the model, A means of providing urban strategies that analyzes urban data and proposes business plans in real time, A system that includes this.

2. The system according to claim 1, further comprising means for converting business scenarios into individualized policy proposals based on real-time data analysis results.

3. The system according to claim 1, wherein the simulation means identifies the optimal measure by comparing the probability of success and the risks in multiple business scenarios.

Images