system

Abstract

We provide the system. [Solution] A means of collecting data related to a group of administrators and learning the behavior of administrators based on that data, A means for generating appropriate management advice in response to an input question using a pre-trained model, A means of displaying the generated advice on the device in a style corresponding to the character selected by the user, A means of collecting user feedback and retraining the model's accuracy based on that feedback, A system that includes this.

Description

【Technical Field】 【0001】 The technology of the present disclosure relates to a system. 【Background Art】 【0002】 Patent Document 1 discloses a 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】 Japanese Patent Application Laid-Open No. 2022-180282 【Summary of the Invention】 【Problems to be Solved by the Invention】 【0004】 In a modern workplace environment, managers face various problems and are required to seek quick and appropriate solutions to individual problems. However, due to the lack of support means that can immediately provide effective management, managers will bear the risks of stress and reduced efficiency. In particular, for newly appointed managers or managers with little experience, the opportunities to receive appropriate guidance and advice are limited, and innovative means to solve this problem are required. 【Means for Solving the Problems】 【0005】 This invention solves this problem by aggregating data on managerial behavior and learning that behavior using an AI model. The trained model analyzes management-related questions entered by the user and generates optimal advice. This advice is presented in a friendly and easy-to-understand format, as it is expressed in the tone of a character chosen by the user. Furthermore, the system provides a way to continuously improve the accuracy of the advice by incorporating user feedback into the model's retraining. 【0006】 A "management group" refers to individuals or groups of people who assume managerial roles and are responsible for decision-making and exercise leadership within the organization. 【0007】 "Data collection" refers to the activity of systematically gathering necessary information from various sources, forming a foundation for analysis and learning. 【0008】 A "trained model" refers to a state where an AI has understood and grasped specific patterns and knowledge using data, and is a model built in a way that can be used for problem solving. 【0009】 "Management advice" refers to guidance and advice provided to managers regarding specific challenges and situations they face. 【0010】 A "terminal" refers to a digital device used by users to input information or check output results. 【0011】 "Character" refers to the depiction and speech patterns of the anthropomorphic AI agents selected by the user within the system, and serves as an element that users can relate to. 【0012】 "Retraining" refers to the process of updating and improving the knowledge and accuracy of an existing learning model by incorporating new data and feedback. 【0013】 "Feedback" refers to the reactions and opinions received from users, and is information used to improve systems and processes. [Brief explanation of the drawing] 【0014】 [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14]It is a sequence diagram showing the processing flow of a data processing system in Application Example 2 when a sentiment engine is combined. 【Embodiments for Carrying Out the Invention】 【0015】 Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings. 【0016】 First, the terms used in the following description will be explained. 【0017】 In the following embodiments, a processor with a reference number (hereinafter simply referred to as "processor") may be one arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be one type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like. 【0018】 In the following embodiments, a RAM (Random Access Memory) with a reference number is a memory in which information is temporarily stored and is used as a work memory by the processor. 【0019】 In the following embodiments, a storage with a reference number is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc. 【0020】 In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark). 【0021】 In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or." 【0022】 [First Embodiment] 【0023】 Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment. 【0024】 As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server. 【0025】 The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network). 【0026】 The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52. 【0027】 The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input. 【0028】 The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor. 【0029】 Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54. 【0030】 Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14. 【0031】 As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30. 【0032】 The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. 【0033】 In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48. 【0034】 Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal". 【0035】 This invention relates to a system for providing effective advice to administrators regarding various challenges they face in their daily work. This system consists of three entities: a server, a terminal, and a user, each playing a specific role. 【0036】 The server first collects a large amount of data about administrators and uses AI technology to learn from it. Specifically, it trains a model using a dataset that includes successful management examples, leadership principles, and problem-solving strategies. This model is then equipped with predictive analytical capabilities for the diverse situations and problems that administrators face. 【0037】 The terminal functions as an interface for receiving user input. Users can input specific problems or questions in natural language, and the terminal processes that information to quickly communicate it to the server. Users can also select a character according to their preferences, and the terminal customizes its display content to provide advice based on the tone of the selected character. 【0038】 When a user enters their management concerns into the device, the device sends this information to a server, which uses a pre-trained model to generate appropriate advice. The generated advice is then returned to the device and presented in the style of a character selected by the user. This allows the user to receive information in a way that is easy for them to understand and accept. 【0039】 For example, if a user enters "I want to know how to motivate my subordinates," the device sends the question to the server. The server's AI model analyzes the question and generates specific advice, such as "It would be good to boost your subordinates' morale by holding regular review meetings and sharing success stories." This advice is then presented to the user through the device. 【0040】 Furthermore, this system can continuously improve accuracy by collecting user feedback and using it to retrain the AI ​​model. There is a mechanism for users to rate their satisfaction with the advice, and this feedback enhances the overall system performance, enabling even more effective management support. 【0041】 The following describes the processing flow. 【0042】 Step 1: 【0043】 The server collects data on administrator actions and success stories. By gathering data from multiple sources and storing it in a database, it forms training material for AI models. 【0044】 Step 2: 【0045】 The server uses AI algorithms to train the collected data. This builds a trained model that can generate analyses and solutions to various challenges that administrators may face. 【0046】 Step 3: 【0047】 The user logs into the device and selects a character. The device records the selection and configures it to reflect that selection in subsequent interactions. 【0048】 Step 4: 【0049】 Users input their management-related concerns and questions in natural language on their devices. 【0050】 Step 5: 【0051】 The terminal analyzes the user's input and sends it to the server as a query in the appropriate format. 【0052】 Step 6: 【0053】 The server inputs queries received from the terminal into a trained model and generates advice to address specific management challenges. 【0054】 Step 7: 【0055】 The server sends the generated advice back to the terminal. The advice includes specific steps for resolving the problem. 【0056】 Step 8: 【0057】 The device formats the received advice to match the tone and style of the character chosen by the user and presents it to the user. 【0058】 Step 9: 【0059】 Users review the advice provided and utilize it as needed. Furthermore, they provide feedback on the usefulness of the advice. 【0060】 Step 10: 【0061】 The device collects user feedback and sends it to the server. The server uses this feedback to retrain the AI ​​model and improve the accuracy of future advice. 【0062】 (Example 1) 【0063】 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." 【0064】 Administrators face a variety of problems in their daily work, making it difficult to receive timely and accurate advice. Furthermore, existing systems fail to adequately provide information in a format that is easily understandable and acceptable to users. Therefore, the challenge lies in providing responsive and effective support for the complex situations administrators face. 【0065】 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. 【0066】 In this invention, the server includes means for collecting a wide range of data related to the administrator group, means for analyzing questions entered by the user in natural language and generating appropriate management advice, and means for displaying the generated advice on a terminal based on a character style selected by the user. This allows the user to receive flexible and accurate advice tailored to their preferences. 【0067】 A "management group" refers to individuals or a group of people within an organization or company who are responsible for guiding and making decisions regarding operations. 【0068】 A "generative AI model" refers to an artificial intelligence model that has the ability to learn patterns from data and generate output in response to new inputs. 【0069】 "Natural language" refers to the forms of language that humans use on a daily basis, and specifically to communication using human language, in contrast to programming languages. 【0070】 "Character style" refers to a style of expression used in presenting information that is based on the personality and behavior of a particular character. 【0071】 "Feedback" refers to opinions and evaluations, such as satisfaction levels and areas for improvement, that users provide after using advice or a service. 【0072】 "Retraining" refers to the process of improving a previously trained model by incorporating new data and feedback to make the model even more accurate. 【0073】 An "interface" refers to the input and output points that allow a user to operate a system, and is an environment that enables communication between humans and machines. 【0074】 This invention is a system for providing effective advice on various problems that administrators face in their daily work. The system consists of three components: a server, a terminal, and a user, which work together to achieve the objectives of the invention. 【0075】 Server Role 【0076】 The server collects a wide range of data related to the management group and learns from it using a generative AI model. Specifically, it trains the AI ​​model based on data such as successful management examples, leadership principles, and problem-solving strategies. This training uses machine learning libraries such as Python and Tensorflow®. The server receives natural language questions from users, analyzes those questions, and generates appropriate management advice. For example, if a user enters the prompt "I want to know how to motivate my subordinates," the server will generate specific advice such as "Hold regular review meetings and share success stories." 【0077】 Terminal role 【0078】 The device provides an interface for users to input questions in natural language. Users can intuitively interact with the device and input questions about management. The device customizes the displayed content based on the character selected by the user. This customization allows users to receive advice in a style that suits them. 【0079】 User roles 【0080】 Users begin using this system by entering their administrative concerns or questions into a terminal. Users select a character according to their preferences and receive information in that style, resulting in more understandable and acceptable advice. Furthermore, user feedback is used by the server to retrain the AI ​​model, continuously improving its accuracy. 【0081】 The system thus formed provides flexible and accurate advice to managers regarding the challenges they face, contributing to an improvement in the quality of management. 【0082】 The flow of the specific processing in Example 1 will be explained using Figure 11. 【0083】 Step 1: 【0084】 The server collects data related to the group of administrators. The input is a dataset containing success stories, leadership principles, and problem-solving strategies, which is used to train a generative AI model. The data is trained using Python or TensorFlow, and the output is a trained model capable of analyzing various management situations. Specifically, it periodically retrieves the latest information from the database and feeds it to the AI ​​model to update it. 【0085】 Step 2: 【0086】 The user inputs management-related questions in natural language through the terminal's interface. The input consists of prompts containing the user's specific questions or concerns. The terminal sends this input to the server and generates data analyzing the user's intent as output. For example, if the user inputs "How can I increase employee motivation?", the terminal converts this information into a digital format and sends it to the server, then waits for a response from the server. 【0087】 Step 3: 【0088】 The server generates appropriate advice using a pre-trained generative AI model based on the analysis request received from the terminal. The input is an analyzed prompt sentence, which is used to search for relevant information in the database and perform advanced data calculations for analysis. The output is specific and practical management advice. Specifically, the server quickly runs the AI ​​model and generates advice in text form, combining relevant success stories. 【0089】 Step 4: 【0090】 The generated advice is sent back to the terminal and displayed in a customized form based on the user's selected character style. The input is the content of the advice sent from the server, which the terminal converts into a format according to the user's settings. The output is an advice display that is easy for the user to understand and accept. Specifically, the terminal displays the message in the tone of a character selected from multiple templates. 【0091】 Step 5: 【0092】 Users provide feedback on the advice given on their device, and this feedback is sent to the server. The input is the user's evaluation, and the output is the feedback data stored on the server. Specifically, the user submits their satisfaction level and improvement requests through an evaluation button, and the server stores this in a database for reference when retraining the AI ​​model. 【0093】 (Application Example 1) 【0094】 Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal." 【0095】 In today's busy lifestyle, maintaining harmony within the family while efficiently managing household affairs is a challenging task. Managing family schedules, coordinating household tasks, and maintaining motivation, in particular, require significant time and effort. Against this backdrop, there is a need for voice-input-enabled advice systems to help administrators or family members improve harmony and efficiency within the home. 【0096】 The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means. 【0097】 In this invention, the server includes means for collecting data related to a group of administrators and learning the administrators' behavior based on said data; means for generating appropriate management advice in response to voice-input questions using a trained model; and means for displaying the generated advice on an information processing device in a speaking style corresponding to a character selected by the user. This makes it possible for families and individuals to instantly receive specific advice to achieve efficient and harmonious activities within the home. 【0098】 A "management group" is a group of people who are responsible for managing and making decisions within a particular organization or household. 【0099】 "Data collection" is the process of systematically gathering various types of information related to a group of administrators. 【0100】 "Behavioral learning" is the process of understanding the behavioral patterns and decision-making of managers based on collected data, and reflecting this in algorithmic models. 【0101】 "Voice input" is an interface that allows users to give instructions or ask questions to a device using their voice. 【0102】 An "information processing device" is a device or system that processes input data and provides useful information to the user. 【0103】 "Character-appropriate communication" refers to a method where advice is provided based on a specific style or personality chosen by the user. 【0104】 "Feedback collection" is the process of systematically gathering and incorporating reactions and evaluations from users. 【0105】 "Model retraining" is the process of training a model again to improve the accuracy of its predictions and recommendations based on the feedback it has collected. 【0106】 "Support for household activities" refers to the process of effectively assisting in the management and execution of various tasks and events that take place within the home. 【0107】 "Supporting harmony" means creating an environment that facilitates smooth relationships among family members and encourages cooperation towards common goals. 【0108】 To implement this system, the server first collects data related to the group of administrators and uses this data to learn the administrators' behavior and decision patterns. High-performance server equipment is used for the hardware, and machine learning frameworks such as TensorFlow are employed for the software. The server leverages a trained generative AI model to generate appropriate management advice in response to questions entered by the user via voice. 【0109】 The terminal is responsible for converting the user's voice input into text data and sending it to the server. The hardware used includes a home information processing device equipped with a microphone and speaker. Libraries such as spaCy are utilized for natural language processing. The terminal then presents the generated advice in voice, customizing the speaking style based on the user's chosen character. 【0110】 Users utilize the system to help solve problems within the home. For example, if a user voice-inputs, "Please suggest some fun family activities for this weekend," the system will suggest picnics or cycling trips to nearby parks. User feedback is collected and used for continuous learning. 【0111】 As an example of a prompt, a user could input into the system in the form of, "Robot assistant, please give me some ideas for making family time more enjoyable." The responses to this type of question are based on various datasets that the AI ​​model has learned from, and are designed to help support harmony and efficiency within the home. 【0112】 The flow of a specific process in Application Example 1 will be explained using Figure 12. 【0113】 Step 1: 【0114】 The user inputs a problem or question they want to solve at home into the device using voice. The device's microphone converts the voice data into text. Speech recognition technology is used in this process, and the voice signal is output as text data. 【0115】 Step 2: 【0116】 The terminal analyzes text data using natural language processing to understand the intent of the question. Here, a library like spaCy is used to syntactically analyze the text and extract the user's intent as understood data. 【0117】 Step 3: 【0118】 The terminal sends the analyzed question data to the server and requests analysis based on a generative AI model. The server receives this data as input and generates appropriate advice using a machine learning model. A model using TensorFlow outputs predictions and management advice based on this analyzed data. 【0119】 Step 4: 【0120】 Advice generated from the server is returned to the terminal. The terminal outputs the advice in audio format, using a speaking style and manner appropriate to the character selected by the user. Here, the terminal's speaker is used, and the text data is converted back into audio, which is then provided to the user in a user-friendly format. 【0121】 Step 5: 【0122】 Users provide feedback on the content and practicality of the advice. The device digitizes this feedback and formats it as input data for the retraining process, sending it to the server. This feedback is analyzed and contributes to the continuous improvement of the AI ​​model's accuracy. 【0123】 Step 6: 【0124】 The server retrains the model based on feedback to improve prediction accuracy and the quality of suggestions. Model tuning involves analyzing user feedback data and adjusting the algorithm to generate more optimal advice. As a result of retraining, new parameters are applied to the model, leading to improved advice delivery in the future. 【0125】 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. 【0126】 This invention relates to a system that provides personalized and optimal advice, taking into account the emotional state of users, with the aim of supporting administrators in their management. This system is designed to improve the user experience through the integrated operation of a server, terminal, and emotion engine. 【0127】 The server first collects a wide range of data related to administrators and uses AI technology to learn solutions to the various challenges and problems that administrators face. As a result, it generates a trained model with the knowledge necessary for managers and stores it on the server. This makes it possible to generate quick and effective advice for any management-related question. 【0128】 The terminal functions as an interface with the user. Users can log in to the terminal and input their concerns and questions regarding their own management in natural language. The information entered by the user is analyzed by an emotion engine, which can identify the user's emotional state from the text and voice. 【0129】 The emotion engine is responsible for recognizing emotions based on user input. For example, if a user is feeling frustrated, the emotion engine analyzes this and assigns an appropriate emotion tag. This emotion information is used to optimize advice generated on the server side. Specifically, it allows for more empathetic responses by adjusting the tone of the advice and providing emotionally sensitive recommendations. 【0130】 For example, if a user inputs "My team won't listen to me, and I don't know what to do," the device sends this information to the server, and simultaneously the emotion engine recognizes the user's emotional state as "anxiety" or "frustration." The server can then consider this emotional information and generate more supportive and reassuring advice. One example of such advice is one that encourages an approach like, "Show empathy and try to find the root cause of the problem together." 【0131】 Ultimately, users have the opportunity to evaluate the advice provided, and this feedback is used to further improve the system. This feedback helps in the model's retraining process, including improving the accuracy of the emotion engine, with the aim of making future advice more personalized. 【0132】 The following describes the processing flow. 【0133】 Step 1: 【0134】 The server collects administrator-related data and learns administrator behavior patterns and problem-solving strategies. This data includes success stories and problem-solving skills. The learned results are stored as an AI model. 【0135】 Step 2: 【0136】 Users log in to their device and input their concerns and questions regarding management in natural language. 【0137】 Step 3: 【0138】 The device passes user input to the emotion engine, which analyzes the user's emotional state. The emotion engine identifies the emotional state from text and voice and generates corresponding emotion data tags. 【0139】 Step 4: 【0140】 The device sends the user's questions and sentiment data to the server. This allows the server to generate advice that takes the user's current sentiment state into account. 【0141】 Step 5: 【0142】 The server uses an AI model based on the received questions and sentiment data to generate appropriate and emotionally sensitive management advice. This advice includes specific action suggestions. 【0143】 Step 6: 【0144】 The server sends the generated advice back to the terminal. The advice includes adjustments based on emotions. 【0145】 Step 7: 【0146】 The device formats and displays advice to the user according to the style of the character selected by the user. 【0147】 Step 8: 【0148】 The user reviews and implements the suggested advice. If necessary, they provide feedback on the usefulness of the advice. 【0149】 Step 9: 【0150】 The device sends user feedback to the server. The server uses this feedback to retrain the AI ​​model and improve the accuracy of its advice. 【0151】 (Example 2) 【0152】 Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal." 【0153】 Modern managers need support to effectively manage tasks and navigate complex interpersonal relationships. Traditional systems can provide general management advice, but they struggle to offer personalized support tailored to the individual emotional states and specific concerns of each user. This has resulted in a lack of timely and accurate solutions to the challenges managers face. 【0154】 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. 【0155】 In this invention, the server includes means for collecting information related to a group of administrators and learning the administrators' activities based on that information; means for generating appropriate advice for input problems using a learned algorithm; and means for analyzing the user's emotional state and optimizing the content of the advice generated based on that emotion. This makes it possible to provide individually optimized advice that takes the user's emotional state into consideration. 【0156】 A "management group" refers to a group of people who hold positions within a company or organization and are responsible for business operations and personnel management. 【0157】 "Means of collecting information" refers to the processes and technologies used to acquire data related to administrators and transmit it to devices such as servers for analysis. 【0158】 "Means of learning from activities" refers to a function that uses AI and machine learning technologies to understand the patterns of administrator behavior and decision-making based on collected data. 【0159】 A "trained algorithm" refers to a program that has been trained to generate appropriate outputs for new inputs based on rules and patterns obtained through learning from a given dataset. 【0160】 "Means for generating appropriate advice for a problem" refers to the processes and technologies used to provide situation-appropriate solutions and advice based on questions and concerns submitted by users. 【0161】 "Means of analyzing emotional states" refers to technologies and processes that identify a user's emotions from text or audio and provide information based on those emotions. 【0162】 "Methods for optimizing the content of advice" refer to technologies that adjust the content of generated advice according to the user's emotional state and situation, making it the most effective and acceptable form. 【0163】 This invention relates to a system that provides personalized and optimal advice based on the user's emotional state to support efficient management by administrators. This system operates using a server, terminals, and an emotion analysis device. 【0164】 The server first collects information related to the group of administrators. This information includes past management cases and administrator documentation. The server analyzes this data using machine learning algorithms to learn patterns for solving various problems and challenges faced by administrators. This creates and stores trained models for solving problems in management operations. 【0165】 The terminal functions as a user interface, allowing users to input their concerns and questions about management in natural language. The input is compatible with both voice and keyboard input. Before sending the input received from the user to the server, the terminal processes it using an emotion analyzer to identify the user's emotional state. 【0166】 The emotion analysis device incorporates technology to analyze a user's emotions from input text or audio. This device tags the user's emotions as "anxiety," "frustration," "joy," etc., and provides this information to a server. 【0167】 The server uses a generative AI model to generate optimal advice based on emotional information obtained from the emotion analysis device. In this process, the content and tone of the advice are adjusted according to the emotion. For example, if a user inputs "My team won't listen to me, and I don't know what to do," the server can generate advice such as "Show empathy and work together to find the root cause of the problem." 【0168】 Finally, the device presents the generated advice to the user. The user is given the opportunity to review and evaluate it. This feedback is sent to the server to further improve the system and helps to improve the accuracy of the sentiment analyzer and trained models. 【0169】 A concrete example of a prompt is, "What are the best practices for team management?" This prompt is used to ask a generative AI model for specific advice. 【0170】 The flow of the specific processing in Example 2 will be explained using Figure 13. 【0171】 Step 1: 【0172】 The server collects information related to the group of administrators. It uses business-related documents and historical management case data as input. The server stores this data in a database and applies machine learning algorithms for analysis. As output, it generates and saves a trained model that extracts patterns and rules useful for solving management challenges. 【0173】 Step 2: 【0174】 Users log in to the terminal and input their concerns and questions regarding management in natural language. They can use a keyboard or voice input device for input. The terminal temporarily stores the user's input data and prepares it for sentiment analysis. It converts the input data to text data to prepare for the next processing step. 【0175】 Step 3: 【0176】 The terminal transmits natural language data entered by the user to an emotion analyzer. This input is user question data in text format. The emotion analyzer analyzes this data and uses natural language processing techniques to identify the user's emotional state. As output, it generates information tagged with the user's emotions, such as "anxiety" or "frustration," and transmits this information to a server via the terminal. 【0177】 Step 4: 【0178】 The server utilizes emotional information obtained from an emotion analysis device and generates optimal advice using a generative AI model. It uses emotion tags and the user's natural language input as input. The server considers the emotional information and adjusts the tone and content of the advice to generate more empathetic and appropriate guidance. For example, if the input is "My team isn't listening, and I don't know what to do," the server will generate specific advice such as "Show empathy and work together to find the root cause of the problem." 【0179】 Step 5: 【0180】 The terminal presents the user with advice received from the server. The input is optimized advice data sent from the server. The terminal displays the advice in a user-friendly format and provides an interface for the user to evaluate the advice. The user reviews the advice and inputs their evaluation as feedback into the terminal. 【0181】 Step 6: 【0182】 User feedback is sent from the terminal to the server. The server uses this feedback to improve the algorithm. User feedback data is the input. The server analyzes the feedback data and uses it to retrain the trained model, thereby improving the accuracy of future advice and continuously improving the system to enable personalized and optimal advice. 【0183】 (Application Example 2) 【0184】 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". 【0185】 Conventional management support systems and user guidance systems often fail to consider users' emotional states and provide uniform responses, making it difficult to offer optimal advice and information to users. Furthermore, they lack sufficient functionality to improve system accuracy through user feedback. Therefore, there is a need for the development of technologies that consider users' emotional states, provide individually optimized advice, and utilize feedback to further improve accuracy. 【0186】 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. 【0187】 In this invention, the server includes means for collecting data related to the managed group and learning role behaviors based on said data; means for generating appropriate advice in response to input questions using a trained model; and means for analyzing the user's emotional state and adapting the tone of the advice considering said emotional information. This enables the generation of optimal advice tailored to the user's unique emotional state, allowing for more effective information provision. Furthermore, the system's accuracy continuously improves based on feedback. 【0188】 A "target group" refers to an individual or group that exhibits specific behaviors or roles, and is the subject of data collection. 【0189】 "Role" is a concept that refers to the function or behavior that an individual or group should perform in a particular situation. 【0190】 A "trained model" refers to an algorithm that has been trained in advance using a machine learning algorithm based on data, and possesses the knowledge necessary to perform a specific task. 【0191】 "Emotional state" refers to the psychological or emotional state that an individual is experiencing at a particular time, and is the object that a system identifies and analyzes. 【0192】 "Tone of advice" refers to the style and tone of expression in the advice and suggestions that are generated, and is an element that is adapted based on the user's emotional state. 【0193】 "Feedback" refers to evaluation information provided by users regarding the performance and results of the system, and is data used to improve the system. 【0194】 "Optimal advice" refers to the most appropriate and beneficial instructions or suggestions provided, taking into account the individual circumstances and emotional state of the user. 【0195】 This invention is a system for providing advice optimized for the user's emotional state. Its central components are a server, a terminal, and an emotion engine. The server collects extensive data related to the managed population and uses machine learning algorithms to learn role behaviors based on this data. The trained model can then generate appropriate advice in response to input questions. 【0196】 The terminal functions as an interface with the user, receiving questions and feedback in natural language. The emotion engine analyzes the user's input information from the terminal, identifying emotional states from voice and text data. This emotional information is sent to the server's advice generation process and used to adapt the tone and content of the generated advice. This enables more empathetic and personalized advice. 【0197】 For example, if a user asks via their device, "I'm stuck in traffic while traveling; how can I maintain a good mood?", the device sends this input to the server, and the emotion engine identifies whether the user is experiencing anxiety or stress. The server then considers this emotional information and generates emotionally sensitive advice, such as suggesting relaxing music. 【0198】 An example of a prompt message would be, "Generate suggestions on how to help a user relax when they are feeling stressed in the car." 【0199】 The flow of a specific process in Application Example 2 will be explained using Figure 14. 【0200】 Step 1: 【0201】 The user inputs a question or concern into the terminal in natural language. The terminal receives this input and prepares to send it to the server as voice or text data. It checks the format of the input data and performs text conversion as needed. The input in this step is the user's natural language query, and the output is text data. 【0202】 Step 2: 【0203】 The terminal sends user input to the emotion engine. The emotion engine identifies the user's emotional state from the input text data and generates an emotion tag. Natural language processing techniques are used for identification, and an emotion analysis algorithm is executed as data processing. The input is the user's text data, and the output is the emotion tag. 【0204】 Step 3: 【0205】 The server receives text data sent from the terminal and generates optimal advice using a pre-trained model. In this process, it creates a variety of answer candidates using a generative AI model. It adjusts the tone of the advice, taking sentiment tags into consideration, to create the final advice. The input is the user's question and sentiment tags, and the output is the most optimized advice. 【0206】 Step 4: 【0207】 The terminal receives advice generated from the server and displays it to the user. The information is delivered according to a pre-configured display format. Based on the user's selection, the advice is displayed on the screen as text. The input is advice data from the server, and the output is advice information formatted for user readability. 【0208】 Step 5: 【0209】 Users send feedback on the displayed advice via their device. The device receives the feedback and sends the information to the server. This feedback is then processed and analyzed again as data on the server. Input is data such as user ratings and opinions, and output is sent to the server as feedback data. 【0210】 Step 6: 【0211】 The server uses the accumulated feedback data to retrain the machine learning model. This improves the accuracy of the generated AI model and optimizes the advice generation process for subsequent sessions. The input is the feedback data, and the output is the updated, trained model. 【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 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 relates to a system for providing effective advice to administrators regarding various challenges they face in their daily work. This system consists of three entities: a server, a terminal, and a user, each playing a specific role. 【0229】 The server first collects a large amount of data about administrators and uses AI technology to learn from it. Specifically, it trains a model using a dataset that includes successful management examples, leadership principles, and problem-solving strategies. This model is then equipped with predictive analytical capabilities for the diverse situations and problems that administrators face. 【0230】 The terminal functions as an interface for receiving user input. Users can input specific problems or questions in natural language, and the terminal processes that information to quickly communicate it to the server. Users can also select a character according to their preferences, and the terminal customizes its display content to provide advice based on the tone of the selected character. 【0231】 When a user enters their management concerns into the device, the device sends this information to a server, which uses a pre-trained model to generate appropriate advice. The generated advice is then returned to the device and presented in the style of a character selected by the user. This allows the user to receive information in a way that is easy for them to understand and accept. 【0232】 For example, if a user enters "I want to know how to motivate my subordinates," the device sends the question to the server. The server's AI model analyzes the question and generates specific advice, such as "It would be good to boost your subordinates' morale by holding regular review meetings and sharing success stories." This advice is then presented to the user through the device. 【0233】 Furthermore, this system can continuously improve accuracy by collecting user feedback and using it to retrain the AI ​​model. There is a mechanism for users to rate their satisfaction with the advice, and this feedback enhances the overall system performance, enabling even more effective management support. 【0234】 The following describes the processing flow. 【0235】 Step 1: 【0236】 The server collects data on administrator actions and success stories. By gathering data from multiple sources and storing it in a database, it forms training material for AI models. 【0237】 Step 2: 【0238】 The server uses AI algorithms to train the collected data. This builds a trained model that can generate analyses and solutions to various challenges that administrators may face. 【0239】 Step 3: 【0240】 The user logs into the device and selects a character. The device records the selection and configures it to reflect that selection in subsequent interactions. 【0241】 Step 4: 【0242】 Users input their management-related concerns and questions in natural language on their devices. 【0243】 Step 5: 【0244】 The terminal analyzes the user's input and sends it to the server as a query in the appropriate format. 【0245】 Step 6: 【0246】 The server inputs queries received from the terminal into a trained model and generates advice to address specific management challenges. 【0247】 Step 7: 【0248】 The server sends the generated advice back to the terminal. The advice includes specific steps for resolving the problem. 【0249】 Step 8: 【0250】 The device formats the received advice to match the tone and style of the character chosen by the user and presents it to the user. 【0251】 Step 9: 【0252】 Users review the advice provided and utilize it as needed. Furthermore, they provide feedback on the usefulness of the advice. 【0253】 Step 10: 【0254】 The device collects user feedback and sends it to the server. The server uses this feedback to retrain the AI ​​model and improve the accuracy of future advice. 【0255】 (Example 1) 【0256】 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." 【0257】 Administrators face a variety of problems in their daily work, making it difficult to receive timely and accurate advice. Furthermore, existing systems fail to adequately provide information in a format that is easily understandable and acceptable to users. Therefore, the challenge lies in providing responsive and effective support for the complex situations administrators face. 【0258】 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. 【0259】 In this invention, the server includes means for collecting a wide range of data related to the administrator group, means for analyzing questions entered by the user in natural language and generating appropriate management advice, and means for displaying the generated advice on a terminal based on a character style selected by the user. This allows the user to receive flexible and accurate advice tailored to their preferences. 【0260】 A "management group" refers to individuals or a group of people within an organization or company who are responsible for guiding and making decisions regarding operations. 【0261】 A "generative AI model" refers to an artificial intelligence model that has the ability to learn patterns from data and generate output in response to new inputs. 【0262】 "Natural language" refers to the forms of language that humans use on a daily basis, and specifically to communication using human language, in contrast to programming languages. 【0263】 "Character style" refers to a style of expression used in presenting information that is based on the personality and behavior of a particular character. 【0264】 "Feedback" refers to opinions and evaluations, such as satisfaction levels and areas for improvement, that users provide after using advice or a service. 【0265】 "Retraining" refers to the process of improving a previously trained model by incorporating new data and feedback to make the model even more accurate. 【0266】 An "interface" refers to the input and output points that allow a user to operate a system, and is an environment that enables communication between humans and machines. 【0267】 This invention is a system for providing effective advice on various problems that administrators face in their daily work. The system consists of three components: a server, a terminal, and a user, which work together to achieve the objectives of the invention. 【0268】 Server Role 【0269】 The server collects a wide range of data related to the management group and trains a generative AI model on it. Specifically, it trains the AI ​​model based on data such as successful management examples, leadership principles, and problem-solving strategies. Machine learning libraries such as Python and TensorFlow are used for this training. The server receives questions from users in natural language, analyzes those questions, and generates appropriate management advice. For example, if a user enters the prompt "I want to know how to motivate my subordinates," the server will generate specific advice such as "Hold regular review meetings and share success stories." 【0270】 Terminal role 【0271】 The device provides an interface for users to input questions in natural language. Users can intuitively interact with the device and input questions about management. The device customizes the displayed content based on the character selected by the user. This customization allows users to receive advice in a style that suits them. 【0272】 User roles 【0273】 Users begin using this system by entering their administrative concerns or questions into a terminal. Users select a character according to their preferences and receive information in that style, resulting in more understandable and acceptable advice. Furthermore, user feedback is used by the server to retrain the AI ​​model, continuously improving its accuracy. 【0274】 The system thus formed provides flexible and accurate advice to managers regarding the challenges they face, contributing to an improvement in the quality of management. 【0275】 The flow of the specific processing in Example 1 will be explained using Figure 11. 【0276】 Step 1: 【0277】 The server collects data related to the group of administrators. The input is a dataset containing success stories, leadership principles, and problem-solving strategies, which is used to train a generative AI model. The data is trained using Python or TensorFlow, and the output is a trained model capable of analyzing various management situations. Specifically, it periodically retrieves the latest information from the database and feeds it to the AI ​​model to update it. 【0278】 Step 2: 【0279】 The user inputs management-related questions in natural language through the terminal's interface. The input consists of prompts containing the user's specific questions or concerns. The terminal sends this input to the server and generates data analyzing the user's intent as output. For example, if the user inputs "How can I increase employee motivation?", the terminal converts this information into a digital format and sends it to the server, then waits for a response from the server. 【0280】 Step 3: 【0281】 The server generates appropriate advice using a pre-trained generative AI model based on the analysis request received from the terminal. The input is an analyzed prompt sentence, which is used to search for relevant information in the database and perform advanced data calculations for analysis. The output is specific and practical management advice. Specifically, the server quickly runs the AI ​​model and generates advice in text form, combining relevant success stories. 【0282】 Step 4: 【0283】 The generated advice is sent back to the terminal and displayed in a customized form based on the style of the character selected by the user. The input is the content of the advice sent by the server, and the terminal converts it into a format according to the user settings. As output, the advice is displayed in a form that is easy for the user to understand and accept. As a specific operation, the terminal displays the message in the tone of a character selected from a plurality of templates. 【0284】 Step 5: 【0285】 The user provides feedback on the advice on the terminal, and the feedback is sent to the server. The input is the user's evaluation, and as output, the feedback data is accumulated in the server. As a specific operation, the satisfaction and improvement requests provided by the user are sent through the evaluation button, and the server stores this in the database for reference during the re-learning of the AI model. 【0286】 (Application Example 1) 【0287】 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". 【0288】 In modern busy lives, it is a difficult task to efficiently manage a household while maintaining harmony at home. Especially, managing the schedules of family members, coordinating household tasks, or maintaining motivation requires a lot of time and effort. Against this background, there is a demand for the provision of an advice system that supports voice input in order for administrators or family members to improve harmony and efficiency within the household. 【0289】 The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following respective means. 【0290】 In this invention, the server includes means for collecting data related to a group of administrators and learning the administrators' behavior based on said data; means for generating appropriate management advice in response to voice-input questions using a trained model; and means for displaying the generated advice on an information processing device in a speaking style corresponding to a character selected by the user. This makes it possible for families and individuals to instantly receive specific advice to achieve efficient and harmonious activities within the home. 【0291】 A "management group" is a group of people who are responsible for managing and making decisions within a particular organization or household. 【0292】 "Data collection" is the process of systematically gathering various types of information related to a group of administrators. 【0293】 "Behavioral learning" is the process of understanding the behavioral patterns and decision-making of managers based on collected data, and reflecting this in algorithmic models. 【0294】 "Voice input" is an interface that allows users to give instructions or ask questions to a device using their voice. 【0295】 An "information processing device" is a device or system that processes input data and provides useful information to the user. 【0296】 "Character-appropriate communication" refers to a method where advice is provided based on a specific style or personality chosen by the user. 【0297】 "Feedback collection" is the process of systematically gathering and incorporating reactions and evaluations from users. 【0298】 "Model retraining" is the process of training a model again to improve the accuracy of its predictions and recommendations based on the feedback it has collected. 【0299】 "Support for household activities" refers to the process of effectively assisting in the management and execution of various tasks and events that take place within the home. 【0300】 "Supporting harmony" means creating an environment that facilitates smooth relationships among family members and encourages cooperation towards common goals. 【0301】 To implement this system, the server first collects data related to the group of administrators and uses this data to learn the administrators' behavior and decision patterns. High-performance server equipment is used for the hardware, and machine learning frameworks such as TensorFlow are employed for the software. The server leverages a trained generative AI model to generate appropriate management advice in response to questions entered by the user via voice. 【0302】 The terminal is responsible for converting the user's voice input into text data and sending it to the server. The hardware used includes a home information processing device equipped with a microphone and speaker. Libraries such as spaCy are utilized for natural language processing. The terminal then presents the generated advice in voice, customizing the speaking style based on the user's chosen character. 【0303】 Users utilize the system to help solve problems within the home. For example, if a user voice-inputs, "Please suggest some fun family activities for this weekend," the system will suggest picnics or cycling trips to nearby parks. User feedback is collected and used for continuous learning. 【0304】 As an example of a prompt, a user could input into the system in the form of, "Robot assistant, please give me some ideas for making family time more enjoyable." The responses to this type of question are based on various datasets that the AI ​​model has learned from, and are designed to help support harmony and efficiency within the home. 【0305】 The flow of the specific process in Application Example 1 will be described using FIG. 12. 【0306】 Step 1: 【0307】 The user inputs the problems or questions to be solved at home into the terminal by voice. The microphone of the terminal converts the voice data into text. In this process, voice recognition technology is used, and the voice signal is output as text data. 【0308】 Step 2: 【0309】 The terminal analyzes the text data by natural language processing to understand the intention of the question. Here, a library such as spaCy is used, the text is parsed syntactically, and the user's intention is extracted as understanding data. 【0310】 Step 3: 【0311】 The terminal sends the analyzed question data to the server and requests an analysis based on the generative AI model. The server receives this data as input and uses a machine learning model to generate appropriate advice. A model using TensorFlow outputs predictions and management advice based on this analysis data. 【0312】 Step 4: 【0313】 The advice generated by the server is returned to the terminal. The terminal outputs the advice in voice format in a speaking style and style according to the character selected by the user. Here, the speaker of the terminal is used, and the character data is reconverted into voice and provided to the user in an easy-to-understand format. 【0314】 Step 5: 【0315】 Users provide feedback on the content and practicality of the advice. The device digitizes this feedback and formats it as input data for the retraining process, sending it to the server. This feedback is analyzed and contributes to the continuous improvement of the AI ​​model's accuracy. 【0316】 Step 6: 【0317】 The server retrains the model based on feedback to improve prediction accuracy and the quality of suggestions. Model tuning involves analyzing user feedback data and adjusting the algorithm to generate more optimal advice. As a result of retraining, new parameters are applied to the model, leading to improved advice delivery in the future. 【0318】 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. 【0319】 This invention relates to a system that provides personalized and optimal advice, taking into account the emotional state of users, with the aim of supporting administrators in their management. This system is designed to improve the user experience through the integrated operation of a server, terminal, and emotion engine. 【0320】 The server first collects a wide range of data related to administrators and uses AI technology to learn solutions to the various challenges and problems that administrators face. As a result, it generates a trained model with the knowledge necessary for managers and stores it on the server. This makes it possible to generate quick and effective advice for any management-related question. 【0321】 The terminal functions as an interface with the user. Users can log in to the terminal and input their concerns and questions regarding their own management in natural language. The information entered by the user is analyzed by an emotion engine, which can identify the user's emotional state from the text and voice. 【0322】 The emotion engine is responsible for recognizing emotions based on user input. For example, if a user is feeling frustrated, the emotion engine analyzes this and assigns an appropriate emotion tag. This emotion information is used to optimize advice generated on the server side. Specifically, it allows for more empathetic responses by adjusting the tone of the advice and providing emotionally sensitive recommendations. 【0323】 For example, if a user inputs "My team won't listen to me, and I don't know what to do," the device sends this information to the server, and simultaneously the emotion engine recognizes the user's emotional state as "anxiety" or "frustration." The server can then consider this emotional information and generate more supportive and reassuring advice. One example of such advice is one that encourages an approach like, "Show empathy and try to find the root cause of the problem together." 【0324】 Ultimately, users have the opportunity to evaluate the advice provided, and this feedback is used to further improve the system. This feedback helps in the model's retraining process, including improving the accuracy of the emotion engine, with the aim of making future advice more personalized. 【0325】 The following describes the processing flow. 【0326】 Step 1: 【0327】 The server collects administrator-related data and learns administrator behavior patterns and problem-solving strategies. This data includes success stories and problem-solving skills. The learned results are stored as an AI model. 【0328】 Step 2: 【0329】 Users log in to their device and input their concerns and questions regarding management in natural language. 【0330】 Step 3: 【0331】 The device passes user input to the emotion engine, which analyzes the user's emotional state. The emotion engine identifies the emotional state from text and voice and generates corresponding emotion data tags. 【0332】 Step 4: 【0333】 The device sends the user's questions and sentiment data to the server. This allows the server to generate advice that takes the user's current sentiment state into account. 【0334】 Step 5: 【0335】 The server uses an AI model based on the received questions and sentiment data to generate appropriate and emotionally sensitive management advice. This advice includes specific action suggestions. 【0336】 Step 6: 【0337】 The server sends the generated advice back to the terminal. The advice includes adjustments based on emotions. 【0338】 Step 7: 【0339】 The device formats and displays advice to the user according to the style of the character selected by the user. 【0340】 Step 8: 【0341】 The user reviews and implements the suggested advice. If necessary, they provide feedback on the usefulness of the advice. 【0342】 Step 9: 【0343】 The device sends user feedback to the server. The server uses this feedback to retrain the AI ​​model and improve the accuracy of its advice. 【0344】 (Example 2) 【0345】 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". 【0346】 Modern managers need support to effectively manage tasks and navigate complex interpersonal relationships. Traditional systems can provide general management advice, but they struggle to offer personalized support tailored to the individual emotional states and specific concerns of each user. This has resulted in a lack of timely and accurate solutions to the challenges managers face. 【0347】 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. 【0348】 In this invention, the server includes means for collecting information related to a group of administrators and learning the administrators' activities based on that information; means for generating appropriate advice for input problems using a learned algorithm; and means for analyzing the user's emotional state and optimizing the content of the advice generated based on that emotion. This makes it possible to provide individually optimized advice that takes the user's emotional state into consideration. 【0349】 A "management group" refers to a group of people who hold positions within a company or organization and are responsible for business operations and personnel management. 【0350】 "Means of collecting information" refers to the processes and technologies used to acquire data related to administrators and transmit it to devices such as servers for analysis. 【0351】 "Means of learning from activities" refers to a function that uses AI and machine learning technologies to understand the patterns of administrator behavior and decision-making based on collected data. 【0352】 A "trained algorithm" refers to a program that has been trained to generate appropriate outputs for new inputs based on rules and patterns obtained through learning from a given dataset. 【0353】 "Means for generating appropriate advice for a problem" refers to the processes and technologies used to provide situation-appropriate solutions and advice based on questions and concerns submitted by users. 【0354】 "Means of analyzing emotional states" refers to technologies and processes that identify a user's emotions from text or audio and provide information based on those emotions. 【0355】 "Methods for optimizing the content of advice" refer to technologies that adjust the content of generated advice according to the user's emotional state and situation, making it the most effective and acceptable form. 【0356】 This invention relates to a system that provides personalized and optimal advice based on the user's emotional state to support efficient management by administrators. This system operates using a server, terminals, and an emotion analysis device. 【0357】 The server first collects information related to the group of administrators. This information includes past management cases and administrator documentation. The server analyzes this data using machine learning algorithms to learn patterns for solving various problems and challenges faced by administrators. This creates and stores trained models for solving problems in management operations. 【0358】 The terminal functions as a user interface, allowing users to input their concerns and questions about management in natural language. The input is compatible with both voice and keyboard input. Before sending the input received from the user to the server, the terminal processes it using an emotion analyzer to identify the user's emotional state. 【0359】 The emotion analysis device incorporates technology to analyze a user's emotions from input text or audio. This device tags the user's emotions as "anxiety," "frustration," "joy," etc., and provides this information to a server. 【0360】 The server uses a generative AI model to generate optimal advice based on emotional information obtained from the emotion analysis device. In this process, the content and tone of the advice are adjusted according to the emotion. For example, if a user inputs "My team won't listen to me, and I don't know what to do," the server can generate advice such as "Show empathy and work together to find the root cause of the problem." 【0361】 Finally, the device presents the generated advice to the user. The user is given the opportunity to review and evaluate it. This feedback is sent to the server to further improve the system and helps to improve the accuracy of the sentiment analyzer and trained models. 【0362】 A concrete example of a prompt is, "What are the best practices for team management?" This prompt is used to ask a generative AI model for specific advice. 【0363】 The flow of the specific processing in Example 2 will be explained using Figure 13. 【0364】 Step 1: 【0365】 The server collects information related to the group of administrators. It uses business-related documents and historical management case data as input. The server stores this data in a database and applies machine learning algorithms for analysis. As output, it generates and saves a trained model that extracts patterns and rules useful for solving management challenges. 【0366】 Step 2: 【0367】 Users log in to the terminal and input their concerns and questions regarding management in natural language. They can use a keyboard or voice input device for input. The terminal temporarily stores the user's input data and prepares it for sentiment analysis. It converts the input data to text data to prepare for the next processing step. 【0368】 Step 3: 【0369】 The terminal transmits natural language data entered by the user to an emotion analyzer. This input is user question data in text format. The emotion analyzer analyzes this data and uses natural language processing techniques to identify the user's emotional state. As output, it generates information tagged with the user's emotions, such as "anxiety" or "frustration," and transmits this information to a server via the terminal. 【0370】 Step 4: 【0371】 The server utilizes emotional information obtained from an emotion analysis device and generates optimal advice using a generative AI model. It uses emotion tags and the user's natural language input as input. The server considers the emotional information and adjusts the tone and content of the advice to generate more empathetic and appropriate guidance. For example, if the input is "My team isn't listening, and I don't know what to do," the server will generate specific advice such as "Show empathy and work together to find the root cause of the problem." 【0372】 Step 5: 【0373】 The terminal presents the user with advice received from the server. The input is optimized advice data sent from the server. The terminal displays the advice in a user-friendly format and provides an interface for the user to evaluate the advice. The user reviews the advice and inputs their evaluation as feedback into the terminal. 【0374】 Step 6: 【0375】 User feedback is sent from the terminal to the server. The server uses this feedback to improve the algorithm. User feedback data is the input. The server analyzes the feedback data and uses it to retrain the trained model, thereby improving the accuracy of future advice and continuously improving the system to enable personalized and optimal advice. 【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】 Conventional management support systems and user guidance systems often fail to consider users' emotional states and provide uniform responses, making it difficult to offer optimal advice and information to users. Furthermore, they lack sufficient functionality to improve system accuracy through user feedback. Therefore, there is a need for the development of technologies that consider users' emotional states, provide individually optimized advice, and utilize feedback to further improve accuracy. 【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 means for collecting data related to the managed group and learning role behaviors based on said data; means for generating appropriate advice in response to input questions using a trained model; and means for analyzing the user's emotional state and adapting the tone of the advice considering said emotional information. This enables the generation of optimal advice tailored to the user's unique emotional state, allowing for more effective information provision. Furthermore, the system's accuracy continuously improves based on feedback. 【0381】 A "target group" refers to an individual or group that exhibits specific behaviors or roles, and is the subject of data collection. 【0382】 "Role" is a concept that refers to the function or behavior that an individual or group should perform in a particular situation. 【0383】 A "trained model" refers to an algorithm that has been trained in advance using a machine learning algorithm based on data, and possesses the knowledge necessary to perform a specific task. 【0384】 "Emotional state" refers to the psychological or emotional state that an individual is experiencing at a particular time, and is the object that a system identifies and analyzes. 【0385】 "Tone of advice" refers to the style and tone of expression in the advice and suggestions that are generated, and is an element that is adapted based on the user's emotional state. 【0386】 "Feedback" refers to evaluation information provided by users regarding the performance and results of the system, and is data used to improve the system. 【0387】 "Optimal advice" refers to the most appropriate and beneficial instructions or suggestions provided, taking into account the individual circumstances and emotional state of the user. 【0388】 This invention is a system for providing advice optimized for the user's emotional state. Its central components are a server, a terminal, and an emotion engine. The server collects extensive data related to the managed population and uses machine learning algorithms to learn role behaviors based on this data. The trained model can then generate appropriate advice in response to input questions. 【0389】 The terminal functions as an interface with the user, receiving questions and feedback in natural language. The emotion engine analyzes the user's input information from the terminal, identifying emotional states from voice and text data. This emotional information is sent to the server's advice generation process and used to adapt the tone and content of the generated advice. This enables more empathetic and personalized advice. 【0390】 For example, if a user asks via their device, "I'm stuck in traffic while traveling; how can I maintain a good mood?", the device sends this input to the server, and the emotion engine identifies whether the user is experiencing anxiety or stress. The server then considers this emotional information and generates emotionally sensitive advice, such as suggesting relaxing music. 【0391】 An example of a prompt message would be, "Generate suggestions on how to help a user relax when they are feeling stressed in the car." 【0392】 The flow of a specific process in Application Example 2 will be explained using Figure 14. 【0393】 Step 1: 【0394】 The user inputs a question or concern into the terminal in natural language. The terminal receives this input and prepares to send it to the server as voice or text data. It checks the format of the input data and performs text conversion as needed. The input in this step is the user's natural language query, and the output is text data. 【0395】 Step 2: 【0396】 The terminal sends user input to the emotion engine. The emotion engine identifies the user's emotional state from the input text data and generates an emotion tag. Natural language processing techniques are used for identification, and an emotion analysis algorithm is executed as data processing. The input is the user's text data, and the output is the emotion tag. 【0397】 Step 3: 【0398】 The server receives text data sent from the terminal and generates optimal advice using a pre-trained model. In this process, it creates a variety of answer candidates using a generative AI model. It adjusts the tone of the advice, taking sentiment tags into consideration, to create the final advice. The input is the user's question and sentiment tags, and the output is the most optimized advice. 【0399】 Step 4: 【0400】 The terminal receives advice generated from the server and displays it to the user. The information is delivered according to a pre-configured display format. Based on the user's selection, the advice is displayed on the screen as text. The input is advice data from the server, and the output is advice information formatted for user readability. 【0401】 Step 5: 【0402】 Users send feedback on the displayed advice via their device. The device receives the feedback and sends the information to the server. This feedback is then processed and analyzed again as data on the server. Input is data such as user ratings and opinions, and output is sent to the server as feedback data. 【0403】 Step 6: 【0404】 The server uses the accumulated feedback data to retrain the machine learning model. This improves the accuracy of the generated AI model and optimizes the advice generation process for subsequent sessions. The input is the feedback data, and the output is the updated, trained model. 【0405】 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. 【0406】 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. 【0407】 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. 【0408】 [Third Embodiment] 【0409】 Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment. 【0410】 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. 【0411】 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). 【0412】 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. 【0413】 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. 【0414】 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). 【0415】 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. 【0416】 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. 【0417】 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. 【0418】 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. 【0419】 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. 【0420】 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". 【0421】 This invention relates to a system for providing effective advice to administrators regarding various challenges they face in their daily work. This system consists of three entities: a server, a terminal, and a user, each playing a specific role. 【0422】 The server first collects a large amount of data about administrators and uses AI technology to learn from it. Specifically, it trains a model using a dataset that includes successful management examples, leadership principles, and problem-solving strategies. This model is then equipped with predictive analytical capabilities for the diverse situations and problems that administrators face. 【0423】 The terminal functions as an interface for receiving user input. Users can input specific problems or questions in natural language, and the terminal processes that information to quickly communicate it to the server. Users can also select a character according to their preferences, and the terminal customizes its display content to provide advice based on the tone of the selected character. 【0424】 When a user enters their management concerns into the device, the device sends this information to a server, which uses a pre-trained model to generate appropriate advice. The generated advice is then returned to the device and presented in the style of a character selected by the user. This allows the user to receive information in a way that is easy for them to understand and accept. 【0425】 For example, if a user enters "I want to know how to motivate my subordinates," the device sends the question to the server. The server's AI model analyzes the question and generates specific advice, such as "It would be good to boost your subordinates' morale by holding regular review meetings and sharing success stories." This advice is then presented to the user through the device. 【0426】 Furthermore, this system can continuously improve accuracy by collecting user feedback and using it to retrain the AI ​​model. There is a mechanism for users to rate their satisfaction with the advice, and this feedback enhances the overall system performance, enabling even more effective management support. 【0427】 The following describes the processing flow. 【0428】 Step 1: 【0429】 The server collects data on administrator actions and success stories. By gathering data from multiple sources and storing it in a database, it forms training material for AI models. 【0430】 Step 2: 【0431】 The server uses AI algorithms to train the collected data. This builds a trained model that can generate analyses and solutions to various challenges that administrators may face. 【0432】 Step 3: 【0433】 The user logs into the device and selects a character. The device records the selection and configures it to reflect that selection in subsequent interactions. 【0434】 Step 4: 【0435】 Users input their management-related concerns and questions in natural language on their devices. 【0436】 Step 5: 【0437】 The terminal analyzes the user's input and sends it to the server as a query in the appropriate format. 【0438】 Step 6: 【0439】 The server inputs queries received from the terminal into a trained model and generates advice to address specific management challenges. 【0440】 Step 7: 【0441】 The server sends the generated advice back to the terminal. The advice includes specific steps for resolving the problem. 【0442】 Step 8: 【0443】 The device formats the received advice to match the tone and style of the character chosen by the user and presents it to the user. 【0444】 Step 9: 【0445】 Users review the advice provided and utilize it as needed. Furthermore, they provide feedback on the usefulness of the advice. 【0446】 Step 10: 【0447】 The device collects user feedback and sends it to the server. The server uses this feedback to retrain the AI ​​model and improve the accuracy of future advice. 【0448】 (Example 1) 【0449】 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." 【0450】 Administrators face a variety of problems in their daily work, making it difficult to receive timely and accurate advice. Furthermore, existing systems fail to adequately provide information in a format that is easily understandable and acceptable to users. Therefore, the challenge lies in providing responsive and effective support for the complex situations administrators face. 【0451】 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. 【0452】 In this invention, the server includes means for collecting a wide range of data related to the administrator group, means for analyzing questions entered by the user in natural language and generating appropriate management advice, and means for displaying the generated advice on a terminal based on a character style selected by the user. This allows the user to receive flexible and accurate advice tailored to their preferences. 【0453】 A "management group" refers to individuals or a group of people within an organization or company who are responsible for guiding and making decisions regarding operations. 【0454】 A "generative AI model" refers to an artificial intelligence model that has the ability to learn patterns from data and generate output in response to new inputs. 【0455】 "Natural language" refers to the forms of language that humans use on a daily basis, and specifically to communication using human language, in contrast to programming languages. 【0456】 "Character style" refers to a style of expression used in presenting information that is based on the personality and behavior of a particular character. 【0457】 "Feedback" refers to opinions and evaluations, such as satisfaction levels and areas for improvement, that users provide after using advice or a service. 【0458】 "Retraining" refers to the process of improving a previously trained model by incorporating new data and feedback to make the model even more accurate. 【0459】 An "interface" refers to the input and output points that allow a user to operate a system, and is an environment that enables communication between humans and machines. 【0460】 This invention is a system for providing effective advice on various problems that administrators face in their daily work. The system consists of three components: a server, a terminal, and a user, which work together to achieve the objectives of the invention. 【0461】 Server Role 【0462】 The server collects a wide range of data related to the management group and trains a generative AI model on it. Specifically, it trains the AI ​​model based on data such as successful management examples, leadership principles, and problem-solving strategies. Machine learning libraries such as Python and TensorFlow are used for this training. The server receives questions from users in natural language, analyzes those questions, and generates appropriate management advice. For example, if a user enters the prompt "I want to know how to motivate my subordinates," the server will generate specific advice such as "Hold regular review meetings and share success stories." 【0463】 Terminal role 【0464】 The device provides an interface for users to input questions in natural language. Users can intuitively interact with the device and input questions about management. The device customizes the displayed content based on the character selected by the user. This customization allows users to receive advice in a style that suits them. 【0465】 User roles 【0466】 Users begin using this system by entering their administrative concerns or questions into a terminal. Users select a character according to their preferences and receive information in that style, resulting in more understandable and acceptable advice. Furthermore, user feedback is used by the server to retrain the AI ​​model, continuously improving its accuracy. 【0467】 The system thus formed provides flexible and accurate advice to managers regarding the challenges they face, contributing to an improvement in the quality of management. 【0468】 The flow of the specific processing in Example 1 will be explained using Figure 11. 【0469】 Step 1: 【0470】 The server collects data related to the group of administrators. The input is a dataset containing success stories, leadership principles, and problem-solving strategies, which is used to train a generative AI model. The data is trained using Python or TensorFlow, and the output is a trained model capable of analyzing various management situations. Specifically, it periodically retrieves the latest information from the database and feeds it to the AI ​​model to update it. 【0471】 Step 2: 【0472】 The user inputs management-related questions in natural language through the terminal's interface. The input consists of prompts containing the user's specific questions or concerns. The terminal sends this input to the server and generates data analyzing the user's intent as output. For example, if the user inputs "How can I increase employee motivation?", the terminal converts this information into a digital format and sends it to the server, then waits for a response from the server. 【0473】 Step 3: 【0474】 The server generates appropriate advice using a pre-trained generative AI model based on the analysis request received from the terminal. The input is an analyzed prompt sentence, which is used to search for relevant information in the database and perform advanced data calculations for analysis. The output is specific and practical management advice. Specifically, the server quickly runs the AI ​​model and generates advice in text form, combining relevant success stories. 【0475】 Step 4: 【0476】 The generated advice is sent back to the terminal and displayed in a customized form based on the user's selected character style. The input is the content of the advice sent from the server, which the terminal converts into a format according to the user's settings. The output is an advice display that is easy for the user to understand and accept. Specifically, the terminal displays the message in the tone of a character selected from multiple templates. 【0477】 Step 5: 【0478】 Users provide feedback on the advice given on their device, and this feedback is sent to the server. The input is the user's evaluation, and the output is the feedback data stored on the server. Specifically, the user submits their satisfaction level and improvement requests through an evaluation button, and the server stores this in a database for reference when retraining the AI ​​model. 【0479】 (Application Example 1) 【0480】 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." 【0481】 In today's busy lifestyle, maintaining harmony within the family while efficiently managing household affairs is a challenging task. Managing family schedules, coordinating household tasks, and maintaining motivation, in particular, require significant time and effort. Against this backdrop, there is a need for voice-input-enabled advice systems to help administrators or family members improve harmony and efficiency within the home. 【0482】 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. 【0483】 In this invention, the server includes means for collecting data related to a group of administrators and learning the administrators' behavior based on said data; means for generating appropriate management advice in response to voice-input questions using a trained model; and means for displaying the generated advice on an information processing device in a speaking style corresponding to a character selected by the user. This makes it possible for families and individuals to instantly receive specific advice to achieve efficient and harmonious activities within the home. 【0484】 A "management group" is a group of people who are responsible for managing and making decisions within a particular organization or household. 【0485】 "Data collection" is the process of systematically gathering various types of information related to a group of administrators. 【0486】 "Behavioral learning" is the process of understanding the behavioral patterns and decision-making of managers based on collected data, and reflecting this in algorithmic models. 【0487】 "Voice input" is an interface that allows users to give instructions or ask questions to a device using their voice. 【0488】 An "information processing device" is a device or system that processes input data and provides useful information to the user. 【0489】 "Character-appropriate communication" refers to a method where advice is provided based on a specific style or personality chosen by the user. 【0490】 "Feedback collection" is the process of systematically gathering and incorporating reactions and evaluations from users. 【0491】 "Model retraining" is the process of training a model again to improve the accuracy of its predictions and recommendations based on the feedback it has collected. 【0492】 "Support for household activities" refers to the process of effectively assisting in the management and execution of various tasks and events that take place within the home. 【0493】 "Supporting harmony" means creating an environment that facilitates smooth relationships among family members and encourages cooperation towards common goals. 【0494】 To implement this system, the server first collects data related to the group of administrators and uses this data to learn the administrators' behavior and decision patterns. High-performance server equipment is used for the hardware, and machine learning frameworks such as TensorFlow are employed for the software. The server leverages a trained generative AI model to generate appropriate management advice in response to questions entered by the user via voice. 【0495】 The terminal is responsible for converting the user's voice input into text data and sending it to the server. The hardware used includes a home information processing device equipped with a microphone and speaker. Libraries such as spaCy are utilized for natural language processing. The terminal then presents the generated advice in voice, customizing the speaking style based on the user's chosen character. 【0496】 Users utilize the system to help solve problems within the home. For example, if a user voice-inputs, "Please suggest some fun family activities for this weekend," the system will suggest picnics or cycling trips to nearby parks. User feedback is collected and used for continuous learning. 【0497】 As an example of a prompt, a user could input into the system in the form of, "Robot assistant, please give me some ideas for making family time more enjoyable." The responses to this type of question are based on various datasets that the AI ​​model has learned from, and are designed to help support harmony and efficiency within the home. 【0498】 The flow of a specific process in Application Example 1 will be explained using Figure 12. 【0499】 Step 1: 【0500】 The user inputs a problem or question they want to solve at home into the device using voice. The device's microphone converts the voice data into text. Speech recognition technology is used in this process, and the voice signal is output as text data. 【0501】 Step 2: 【0502】 The terminal analyzes text data using natural language processing to understand the intent of the question. Here, a library like spaCy is used to syntactically analyze the text and extract the user's intent as understood data. 【0503】 Step 3: 【0504】 The terminal sends the analyzed question data to the server and requests analysis based on a generative AI model. The server receives this data as input and generates appropriate advice using a machine learning model. A model using TensorFlow outputs predictions and management advice based on this analyzed data. 【0505】 Step 4: 【0506】 Advice generated from the server is returned to the terminal. The terminal outputs the advice in audio format, using a speaking style and manner appropriate to the character selected by the user. Here, the terminal's speaker is used, and the text data is converted back into audio, which is then provided to the user in a user-friendly format. 【0507】 Step 5: 【0508】 Users provide feedback on the content and practicality of the advice. The device digitizes this feedback and formats it as input data for the retraining process, sending it to the server. This feedback is analyzed and contributes to the continuous improvement of the AI ​​model's accuracy. 【0509】 Step 6: 【0510】 The server retrains the model based on feedback to improve prediction accuracy and the quality of suggestions. Model tuning involves analyzing user feedback data and adjusting the algorithm to generate more optimal advice. As a result of retraining, new parameters are applied to the model, leading to improved advice delivery in the future. 【0511】 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. 【0512】 This invention relates to a system that provides personalized and optimal advice, taking into account the emotional state of users, with the aim of supporting administrators in their management. This system is designed to improve the user experience through the integrated operation of a server, terminal, and emotion engine. 【0513】 The server first collects a wide range of data related to administrators and uses AI technology to learn solutions to the various challenges and problems that administrators face. As a result, it generates a trained model with the knowledge necessary for managers and stores it on the server. This makes it possible to generate quick and effective advice for any management-related question. 【0514】 The terminal functions as an interface with the user. Users can log in to the terminal and input their concerns and questions regarding their own management in natural language. The information entered by the user is analyzed by an emotion engine, which can identify the user's emotional state from the text and voice. 【0515】 The emotion engine is responsible for recognizing emotions based on user input. For example, if a user is feeling frustrated, the emotion engine analyzes this and assigns an appropriate emotion tag. This emotion information is used to optimize advice generated on the server side. Specifically, it allows for more empathetic responses by adjusting the tone of the advice and providing emotionally sensitive recommendations. 【0516】 For example, if a user inputs "My team won't listen to me, and I don't know what to do," the device sends this information to the server, and simultaneously the emotion engine recognizes the user's emotional state as "anxiety" or "frustration." The server can then consider this emotional information and generate more supportive and reassuring advice. One example of such advice is one that encourages an approach like, "Show empathy and try to find the root cause of the problem together." 【0517】 Ultimately, users have the opportunity to evaluate the advice provided, and this feedback is used to further improve the system. This feedback helps in the model's retraining process, including improving the accuracy of the emotion engine, with the aim of making future advice more personalized. 【0518】 The following describes the processing flow. 【0519】 Step 1: 【0520】 The server collects administrator-related data and learns administrator behavior patterns and problem-solving strategies. This data includes success stories and problem-solving skills. The learned results are stored as an AI model. 【0521】 Step 2: 【0522】 Users log in to their device and input their concerns and questions regarding management in natural language. 【0523】 Step 3: 【0524】 The device passes user input to the emotion engine, which analyzes the user's emotional state. The emotion engine identifies the emotional state from text and voice and generates corresponding emotion data tags. 【0525】 Step 4: 【0526】 The device sends the user's questions and sentiment data to the server. This allows the server to generate advice that takes the user's current sentiment state into account. 【0527】 Step 5: 【0528】 The server uses an AI model based on the received questions and sentiment data to generate appropriate and emotionally sensitive management advice. This advice includes specific action suggestions. 【0529】 Step 6: 【0530】 The server sends the generated advice back to the terminal. The advice includes adjustments based on emotions. 【0531】 Step 7: 【0532】 The device formats and displays advice to the user according to the style of the character selected by the user. 【0533】 Step 8: 【0534】 The user reviews and implements the suggested advice. If necessary, they provide feedback on the usefulness of the advice. 【0535】 Step 9: 【0536】 The device sends user feedback to the server. The server uses this feedback to retrain the AI ​​model and improve the accuracy of its advice. 【0537】 (Example 2) 【0538】 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." 【0539】 Modern managers need support to effectively manage tasks and navigate complex interpersonal relationships. Traditional systems can provide general management advice, but they struggle to offer personalized support tailored to the individual emotional states and specific concerns of each user. This has resulted in a lack of timely and accurate solutions to the challenges managers face. 【0540】 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. 【0541】 In this invention, the server includes means for collecting information related to a group of administrators and learning the administrators' activities based on that information; means for generating appropriate advice for input problems using a learned algorithm; and means for analyzing the user's emotional state and optimizing the content of the advice generated based on that emotion. This makes it possible to provide individually optimized advice that takes the user's emotional state into consideration. 【0542】 A "management group" refers to a group of people who hold positions within a company or organization and are responsible for business operations and personnel management. 【0543】 "Means of collecting information" refers to the processes and technologies used to acquire data related to administrators and transmit it to devices such as servers for analysis. 【0544】 "Means of learning from activities" refers to a function that uses AI and machine learning technologies to understand the patterns of administrator behavior and decision-making based on collected data. 【0545】 A "trained algorithm" refers to a program that has been trained to generate appropriate outputs for new inputs based on rules and patterns obtained through learning from a given dataset. 【0546】 "Means for generating appropriate advice for a problem" refers to the processes and technologies used to provide situation-appropriate solutions and advice based on questions and concerns submitted by users. 【0547】 "Means of analyzing emotional states" refers to technologies and processes that identify a user's emotions from text or audio and provide information based on those emotions. 【0548】 "Methods for optimizing the content of advice" refer to technologies that adjust the content of generated advice according to the user's emotional state and situation, making it the most effective and acceptable form. 【0549】 This invention relates to a system that provides personalized and optimal advice based on the user's emotional state to support efficient management by administrators. This system operates using a server, terminals, and an emotion analysis device. 【0550】 The server first collects information related to the group of administrators. This information includes past management cases and administrator documentation. The server analyzes this data using machine learning algorithms to learn patterns for solving various problems and challenges faced by administrators. This creates and stores trained models for solving problems in management operations. 【0551】 The terminal functions as a user interface, allowing users to input their concerns and questions about management in natural language. The input is compatible with both voice and keyboard input. Before sending the input received from the user to the server, the terminal processes it using an emotion analyzer to identify the user's emotional state. 【0552】 The emotion analysis device incorporates technology to analyze a user's emotions from input text or audio. This device tags the user's emotions as "anxiety," "frustration," "joy," etc., and provides this information to a server. 【0553】 The server uses a generative AI model to generate optimal advice based on emotional information obtained from the emotion analysis device. In this process, the content and tone of the advice are adjusted according to the emotion. For example, if a user inputs "My team won't listen to me, and I don't know what to do," the server can generate advice such as "Show empathy and work together to find the root cause of the problem." 【0554】 Finally, the device presents the generated advice to the user. The user is given the opportunity to review and evaluate it. This feedback is sent to the server to further improve the system and helps to improve the accuracy of the sentiment analyzer and trained models. 【0555】 A concrete example of a prompt is, "What are the best practices for team management?" This prompt is used to ask a generative AI model for specific advice. 【0556】 The flow of the specific processing in Example 2 will be explained using Figure 13. 【0557】 Step 1: 【0558】 The server collects information related to the group of administrators. It uses business-related documents and historical management case data as input. The server stores this data in a database and applies machine learning algorithms for analysis. As output, it generates and saves a trained model that extracts patterns and rules useful for solving management challenges. 【0559】 Step 2: 【0560】 Users log in to the terminal and input their concerns and questions regarding management in natural language. They can use a keyboard or voice input device for input. The terminal temporarily stores the user's input data and prepares it for sentiment analysis. It converts the input data to text data to prepare for the next processing step. 【0561】 Step 3: 【0562】 The terminal transmits natural language data entered by the user to an emotion analyzer. This input is user question data in text format. The emotion analyzer analyzes this data and uses natural language processing techniques to identify the user's emotional state. As output, it generates information tagged with the user's emotions, such as "anxiety" or "frustration," and transmits this information to a server via the terminal. 【0563】 Step 4: 【0564】 The server utilizes emotional information obtained from an emotion analysis device and generates optimal advice using a generative AI model. It uses emotion tags and the user's natural language input as input. The server considers the emotional information and adjusts the tone and content of the advice to generate more empathetic and appropriate guidance. For example, if the input is "My team isn't listening, and I don't know what to do," the server will generate specific advice such as "Show empathy and work together to find the root cause of the problem." 【0565】 Step 5: 【0566】 The terminal presents the user with advice received from the server. The input is optimized advice data sent from the server. The terminal displays the advice in a user-friendly format and provides an interface for the user to evaluate the advice. The user reviews the advice and inputs their evaluation as feedback into the terminal. 【0567】 Step 6: 【0568】 User feedback is sent from the terminal to the server. The server uses this feedback to improve the algorithm. User feedback data is the input. The server analyzes the feedback data and uses it to retrain the trained model, thereby improving the accuracy of future advice and continuously improving the system to enable personalized and optimal advice. 【0569】 (Application Example 2) 【0570】 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." 【0571】 Conventional management support systems and user guidance systems often fail to consider users' emotional states and provide uniform responses, making it difficult to offer optimal advice and information to users. Furthermore, they lack sufficient functionality to improve system accuracy through user feedback. Therefore, there is a need for the development of technologies that consider users' emotional states, provide individually optimized advice, and utilize feedback to further improve accuracy. 【0572】 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. 【0573】 In this invention, the server includes means for collecting data related to the managed group and learning role behaviors based on said data; means for generating appropriate advice in response to input questions using a trained model; and means for analyzing the user's emotional state and adapting the tone of the advice considering said emotional information. This enables the generation of optimal advice tailored to the user's unique emotional state, allowing for more effective information provision. Furthermore, the system's accuracy continuously improves based on feedback. 【0574】 A "target group" refers to an individual or group that exhibits specific behaviors or roles, and is the subject of data collection. 【0575】 "Role" is a concept that refers to the function or behavior that an individual or group should perform in a particular situation. 【0576】 A "trained model" refers to an algorithm that has been trained in advance using a machine learning algorithm based on data, and possesses the knowledge necessary to perform a specific task. 【0577】 "Emotional state" refers to the psychological or emotional state that an individual is experiencing at a particular time, and is the object that a system identifies and analyzes. 【0578】 "Tone of advice" refers to the style and tone of expression in the advice and suggestions that are generated, and is an element that is adapted based on the user's emotional state. 【0579】 "Feedback" refers to evaluation information provided by users regarding the performance and results of the system, and is data used to improve the system. 【0580】 "Optimal advice" refers to the most appropriate and beneficial instructions or suggestions provided, taking into account the individual circumstances and emotional state of the user. 【0581】 This invention is a system for providing advice optimized for the user's emotional state. Its central components are a server, a terminal, and an emotion engine. The server collects extensive data related to the managed population and uses machine learning algorithms to learn role behaviors based on this data. The trained model can then generate appropriate advice in response to input questions. 【0582】 The terminal functions as an interface with the user, receiving questions and feedback in natural language. The emotion engine analyzes the user's input information from the terminal, identifying emotional states from voice and text data. This emotional information is sent to the server's advice generation process and used to adapt the tone and content of the generated advice. This enables more empathetic and personalized advice. 【0583】 For example, if a user asks via their device, "I'm stuck in traffic while traveling; how can I maintain a good mood?", the device sends this input to the server, and the emotion engine identifies whether the user is experiencing anxiety or stress. The server then considers this emotional information and generates emotionally sensitive advice, such as suggesting relaxing music. 【0584】 An example of a prompt message would be, "Generate suggestions on how to help a user relax when they are feeling stressed in the car." 【0585】 The flow of a specific process in Application Example 2 will be explained using Figure 14. 【0586】 Step 1: 【0587】 The user inputs a question or concern into the terminal in natural language. The terminal receives this input and prepares to send it to the server as voice or text data. It checks the format of the input data and performs text conversion as needed. The input in this step is the user's natural language query, and the output is text data. 【0588】 Step 2: 【0589】 The terminal sends user input to the emotion engine. The emotion engine identifies the user's emotional state from the input text data and generates an emotion tag. Natural language processing techniques are used for identification, and an emotion analysis algorithm is executed as data processing. The input is the user's text data, and the output is the emotion tag. 【0590】 Step 3: 【0591】 The server receives text data sent from the terminal and generates optimal advice using a pre-trained model. In this process, it creates a variety of answer candidates using a generative AI model. It adjusts the tone of the advice, taking sentiment tags into consideration, to create the final advice. The input is the user's question and sentiment tags, and the output is the most optimized advice. 【0592】 Step 4: 【0593】 The terminal receives advice generated from the server and displays it to the user. The information is delivered according to a pre-configured display format. Based on the user's selection, the advice is displayed on the screen as text. The input is advice data from the server, and the output is advice information formatted for user readability. 【0594】 Step 5: 【0595】 Users send feedback on the displayed advice via their device. The device receives the feedback and sends the information to the server. This feedback is then processed and analyzed again as data on the server. Input is data such as user ratings and opinions, and output is sent to the server as feedback data. 【0596】 Step 6: 【0597】 The server uses the accumulated feedback data to retrain the machine learning model. This improves the accuracy of the generated AI model and optimizes the advice generation process for subsequent sessions. The input is the feedback data, and the output is the updated, trained model. 【0598】 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. 【0599】 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. 【0600】 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. 【0601】 [Fourth Embodiment] 【0602】 Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment. 【0603】 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. 【0604】 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). 【0605】 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. 【0606】 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. 【0607】 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). 【0608】 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. 【0609】 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. 【0610】 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. 【0611】 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. 【0612】 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. 【0613】 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. 【0614】 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". 【0615】 This invention relates to a system for providing effective advice to administrators regarding various challenges they face in their daily work. This system consists of three entities: a server, a terminal, and a user, each playing a specific role. 【0616】 The server first collects a large amount of data about administrators and uses AI technology to learn from it. Specifically, it trains a model using a dataset that includes successful management examples, leadership principles, and problem-solving strategies. This model is then equipped with predictive analytical capabilities for the diverse situations and problems that administrators face. 【0617】 The terminal functions as an interface for receiving user input. Users can input specific problems or questions in natural language, and the terminal processes that information to quickly communicate it to the server. Users can also select a character according to their preferences, and the terminal customizes its display content to provide advice based on the tone of the selected character. 【0618】 When a user enters their management concerns into the device, the device sends this information to a server, which uses a pre-trained model to generate appropriate advice. The generated advice is then returned to the device and presented in the style of a character selected by the user. This allows the user to receive information in a way that is easy for them to understand and accept. 【0619】 For example, if a user enters "I want to know how to motivate my subordinates," the device sends the question to the server. The server's AI model analyzes the question and generates specific advice, such as "It would be good to boost your subordinates' morale by holding regular review meetings and sharing success stories." This advice is then presented to the user through the device. 【0620】 Furthermore, this system can continuously improve accuracy by collecting user feedback and using it to retrain the AI ​​model. There is a mechanism for users to rate their satisfaction with the advice, and this feedback enhances the overall system performance, enabling even more effective management support. 【0621】 The following describes the processing flow. 【0622】 Step 1: 【0623】 The server collects data on administrator actions and success stories. By gathering data from multiple sources and storing it in a database, it forms training material for AI models. 【0624】 Step 2: 【0625】 The server uses AI algorithms to train the collected data. This builds a trained model that can generate analyses and solutions to various challenges that administrators may face. 【0626】 Step 3: 【0627】 The user logs into the device and selects a character. The device records the selection and configures it to reflect that selection in subsequent interactions. 【0628】 Step 4: 【0629】 Users input their management-related concerns and questions in natural language on their devices. 【0630】 Step 5: 【0631】 The terminal analyzes the user's input and sends it to the server as a query in the appropriate format. 【0632】 Step 6: 【0633】 The server inputs queries received from the terminal into a trained model and generates advice to address specific management challenges. 【0634】 Step 7: 【0635】 The server sends the generated advice back to the terminal. The advice includes specific steps for resolving the problem. 【0636】 Step 8: 【0637】 The device formats the received advice to match the tone and style of the character chosen by the user and presents it to the user. 【0638】 Step 9: 【0639】 Users review the advice provided and utilize it as needed. Furthermore, they provide feedback on the usefulness of the advice. 【0640】 Step 10: 【0641】 The device collects user feedback and sends it to the server. The server uses this feedback to retrain the AI ​​model and improve the accuracy of future advice. 【0642】 (Example 1) 【0643】 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". 【0644】 Administrators face a variety of problems in their daily work, making it difficult to receive timely and accurate advice. Furthermore, existing systems fail to adequately provide information in a format that is easily understandable and acceptable to users. Therefore, the challenge lies in providing responsive and effective support for the complex situations administrators face. 【0645】 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. 【0646】 In this invention, the server includes means for collecting a wide range of data related to the administrator group, means for analyzing questions entered by the user in natural language and generating appropriate management advice, and means for displaying the generated advice on a terminal based on a character style selected by the user. This allows the user to receive flexible and accurate advice tailored to their preferences. 【0647】 A "management group" refers to individuals or a group of people within an organization or company who are responsible for guiding and making decisions regarding operations. 【0648】 A "generative AI model" refers to an artificial intelligence model that has the ability to learn patterns from data and generate output in response to new inputs. 【0649】 "Natural language" refers to the forms of language that humans use on a daily basis, and specifically to communication using human language, in contrast to programming languages. 【0650】 "Character style" refers to a style of expression used in presenting information that is based on the personality and behavior of a particular character. 【0651】 "Feedback" refers to opinions and evaluations, such as satisfaction levels and areas for improvement, that users provide after using advice or a service. 【0652】 "Retraining" refers to the process of improving a previously trained model by incorporating new data and feedback to make the model even more accurate. 【0653】 An "interface" refers to the input and output points that allow a user to operate a system, and is an environment that enables communication between humans and machines. 【0654】 This invention is a system for providing effective advice on various problems that administrators face in their daily work. The system consists of three components: a server, a terminal, and a user, which work together to achieve the objectives of the invention. 【0655】 Server Role 【0656】 The server collects a wide range of data related to the management group and trains a generative AI model on it. Specifically, it trains the AI ​​model based on data such as successful management examples, leadership principles, and problem-solving strategies. Machine learning libraries such as Python and TensorFlow are used for this training. The server receives questions from users in natural language, analyzes those questions, and generates appropriate management advice. For example, if a user enters the prompt "I want to know how to motivate my subordinates," the server will generate specific advice such as "Hold regular review meetings and share success stories." 【0657】 Terminal role 【0658】 The device provides an interface for users to input questions in natural language. Users can intuitively interact with the device and input questions about management. The device customizes the displayed content based on the character selected by the user. This customization allows users to receive advice in a style that suits them. 【0659】 User roles 【0660】 Users begin using this system by entering their administrative concerns or questions into a terminal. Users select a character according to their preferences and receive information in that style, resulting in more understandable and acceptable advice. Furthermore, user feedback is used by the server to retrain the AI ​​model, continuously improving its accuracy. 【0661】 The system thus formed provides flexible and accurate advice to managers regarding the challenges they face, contributing to an improvement in the quality of management. 【0662】 The flow of the specific processing in Example 1 will be explained using Figure 11. 【0663】 Step 1: 【0664】 The server collects data related to the group of administrators. The input is a dataset containing success stories, leadership principles, and problem-solving strategies, which is used to train a generative AI model. The data is trained using Python or TensorFlow, and the output is a trained model capable of analyzing various management situations. Specifically, it periodically retrieves the latest information from the database and feeds it to the AI ​​model to update it. 【0665】 Step 2: 【0666】 The user inputs management-related questions in natural language through the terminal's interface. The input consists of prompts containing the user's specific questions or concerns. The terminal sends this input to the server and generates data analyzing the user's intent as output. For example, if the user inputs "How can I increase employee motivation?", the terminal converts this information into a digital format and sends it to the server, then waits for a response from the server. 【0667】 Step 3: 【0668】 The server generates appropriate advice using a pre-trained generative AI model based on the analysis request received from the terminal. The input is an analyzed prompt sentence, which is used to search for relevant information in the database and perform advanced data calculations for analysis. The output is specific and practical management advice. Specifically, the server quickly runs the AI ​​model and generates advice in text form, combining relevant success stories. 【0669】 Step 4: 【0670】 The generated advice is sent back to the terminal and displayed in a customized form based on the user's selected character style. The input is the content of the advice sent from the server, which the terminal converts into a format according to the user's settings. The output is an advice display that is easy for the user to understand and accept. Specifically, the terminal displays the message in the tone of a character selected from multiple templates. 【0671】 Step 5: 【0672】 Users provide feedback on the advice given on their device, and this feedback is sent to the server. The input is the user's evaluation, and the output is the feedback data stored on the server. Specifically, the user submits their satisfaction level and improvement requests through an evaluation button, and the server stores this in a database for reference when retraining the AI ​​model. 【0673】 (Application Example 1) 【0674】 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". 【0675】 In today's busy lifestyle, maintaining harmony within the family while efficiently managing household affairs is a challenging task. Managing family schedules, coordinating household tasks, and maintaining motivation, in particular, require significant time and effort. Against this backdrop, there is a need for voice-input-enabled advice systems to help administrators or family members improve harmony and efficiency within the home. 【0676】 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. 【0677】 In this invention, the server includes means for collecting data related to a group of administrators and learning the administrators' behavior based on said data; means for generating appropriate management advice in response to voice-input questions using a trained model; and means for displaying the generated advice on an information processing device in a speaking style corresponding to a character selected by the user. This makes it possible for families and individuals to instantly receive specific advice to achieve efficient and harmonious activities within the home. 【0678】 A "management group" is a group of people who are responsible for managing and making decisions within a particular organization or household. 【0679】 "Data collection" is the process of systematically gathering various types of information related to a group of administrators. 【0680】 "Behavioral learning" is the process of understanding the behavioral patterns and decision-making of managers based on collected data, and reflecting this in algorithmic models. 【0681】 "Voice input" is an interface that allows users to give instructions or ask questions to a device using their voice. 【0682】 An "information processing device" is a device or system that processes input data and provides useful information to the user. 【0683】 "Character-appropriate communication" refers to a method where advice is provided based on a specific style or personality chosen by the user. 【0684】 "Feedback collection" is the process of systematically gathering and incorporating reactions and evaluations from users. 【0685】 "Model retraining" is the process of training a model again to improve the accuracy of its predictions and recommendations based on the feedback it has collected. 【0686】 "Support for household activities" refers to the process of effectively assisting in the management and execution of various tasks and events that take place within the home. 【0687】 "Supporting harmony" means creating an environment that facilitates smooth relationships among family members and encourages cooperation towards common goals. 【0688】 To implement this system, the server first collects data related to the group of administrators and uses this data to learn the administrators' behavior and decision patterns. High-performance server equipment is used for the hardware, and machine learning frameworks such as TensorFlow are employed for the software. The server leverages a trained generative AI model to generate appropriate management advice in response to questions entered by the user via voice. 【0689】 The terminal is responsible for converting the user's voice input into text data and sending it to the server. The hardware used includes a home information processing device equipped with a microphone and speaker. Libraries such as spaCy are utilized for natural language processing. The terminal then presents the generated advice in voice, customizing the speaking style based on the user's chosen character. 【0690】 Users utilize the system to help solve problems within the home. For example, if a user voice-inputs, "Please suggest some fun family activities for this weekend," the system will suggest picnics or cycling trips to nearby parks. User feedback is collected and used for continuous learning. 【0691】 As an example of a prompt, a user could input into the system in the form of, "Robot assistant, please give me some ideas for making family time more enjoyable." The responses to this type of question are based on various datasets that the AI ​​model has learned from, and are designed to help support harmony and efficiency within the home. 【0692】 The flow of a specific process in Application Example 1 will be explained using Figure 12. 【0693】 Step 1: 【0694】 The user inputs a problem or question they want to solve at home into the device using voice. The device's microphone converts the voice data into text. Speech recognition technology is used in this process, and the voice signal is output as text data. 【0695】 Step 2: 【0696】 The terminal analyzes text data using natural language processing to understand the intent of the question. Here, a library like spaCy is used to syntactically analyze the text and extract the user's intent as understood data. 【0697】 Step 3: 【0698】 The terminal sends the analyzed question data to the server and requests analysis based on a generative AI model. The server receives this data as input and generates appropriate advice using a machine learning model. A model using TensorFlow outputs predictions and management advice based on this analyzed data. 【0699】 Step 4: 【0700】 Advice generated from the server is returned to the terminal. The terminal outputs the advice in audio format, using a speaking style and manner appropriate to the character selected by the user. Here, the terminal's speaker is used, and the text data is converted back into audio, which is then provided to the user in a user-friendly format. 【0701】 Step 5: 【0702】 Users provide feedback on the content and practicality of the advice. The device digitizes this feedback and formats it as input data for the retraining process, sending it to the server. This feedback is analyzed and contributes to the continuous improvement of the AI ​​model's accuracy. 【0703】 Step 6: 【0704】 The server retrains the model based on feedback to improve prediction accuracy and the quality of suggestions. Model tuning involves analyzing user feedback data and adjusting the algorithm to generate more optimal advice. As a result of retraining, new parameters are applied to the model, leading to improved advice delivery in the future. 【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 relates to a system that provides personalized and optimal advice, taking into account the emotional state of users, with the aim of supporting administrators in their management. This system is designed to improve the user experience through the integrated operation of a server, terminal, and emotion engine. 【0707】 The server first collects a wide range of data related to administrators and uses AI technology to learn solutions to the various challenges and problems that administrators face. As a result, it generates a trained model with the knowledge necessary for managers and stores it on the server. This makes it possible to generate quick and effective advice for any management-related question. 【0708】 The terminal functions as an interface with the user. Users can log in to the terminal and input their concerns and questions regarding their own management in natural language. The information entered by the user is analyzed by an emotion engine, which can identify the user's emotional state from the text and voice. 【0709】 The emotion engine is responsible for recognizing emotions based on user input. For example, if a user is feeling frustrated, the emotion engine analyzes this and assigns an appropriate emotion tag. This emotion information is used to optimize advice generated on the server side. Specifically, it allows for more empathetic responses by adjusting the tone of the advice and providing emotionally sensitive recommendations. 【0710】 For example, if a user inputs "My team won't listen to me, and I don't know what to do," the device sends this information to the server, and simultaneously the emotion engine recognizes the user's emotional state as "anxiety" or "frustration." The server can then consider this emotional information and generate more supportive and reassuring advice. One example of such advice is one that encourages an approach like, "Show empathy and try to find the root cause of the problem together." 【0711】 Ultimately, users have the opportunity to evaluate the advice provided, and this feedback is used to further improve the system. This feedback helps in the model's retraining process, including improving the accuracy of the emotion engine, with the aim of making future advice more personalized. 【0712】 The following describes the processing flow. 【0713】 Step 1: 【0714】 The server collects administrator-related data and learns administrator behavior patterns and problem-solving strategies. This data includes success stories and problem-solving skills. The learned results are stored as an AI model. 【0715】 Step 2: 【0716】 Users log in to their device and input their concerns and questions regarding management in natural language. 【0717】 Step 3: 【0718】 The device passes user input to the emotion engine, which analyzes the user's emotional state. The emotion engine identifies the emotional state from text and voice and generates corresponding emotion data tags. 【0719】 Step 4: 【0720】 The device sends the user's questions and sentiment data to the server. This allows the server to generate advice that takes the user's current sentiment state into account. 【0721】 Step 5: 【0722】 The server uses an AI model based on the received questions and sentiment data to generate appropriate and emotionally sensitive management advice. This advice includes specific action suggestions. 【0723】 Step 6: 【0724】 The server sends the generated advice back to the terminal. The advice includes adjustments based on emotions. 【0725】 Step 7: 【0726】 The device formats and displays advice to the user according to the style of the character selected by the user. 【0727】 Step 8: 【0728】 The user reviews and implements the suggested advice. If necessary, they provide feedback on the usefulness of the advice. 【0729】 Step 9: 【0730】 The device sends user feedback to the server. The server uses this feedback to retrain the AI ​​model and improve the accuracy of its advice. 【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】 Modern managers need support to effectively manage tasks and navigate complex interpersonal relationships. Traditional systems can provide general management advice, but they struggle to offer personalized support tailored to the individual emotional states and specific concerns of each user. This has resulted in a lack of timely and accurate solutions to the challenges managers face. 【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 means for collecting information related to a group of administrators and learning the administrators' activities based on that information; means for generating appropriate advice for input problems using a learned algorithm; and means for analyzing the user's emotional state and optimizing the content of the advice generated based on that emotion. This makes it possible to provide individually optimized advice that takes the user's emotional state into consideration. 【0736】 A "management group" refers to a group of people who hold positions within a company or organization and are responsible for business operations and personnel management. 【0737】 "Means of collecting information" refers to the processes and technologies used to acquire data related to administrators and transmit it to devices such as servers for analysis. 【0738】 "Means of learning from activities" refers to a function that uses AI and machine learning technologies to understand the patterns of administrator behavior and decision-making based on collected data. 【0739】 A "trained algorithm" refers to a program that has been trained to generate appropriate outputs for new inputs based on rules and patterns obtained through learning from a given dataset. 【0740】 "Means for generating appropriate advice for a problem" refers to the processes and technologies used to provide situation-appropriate solutions and advice based on questions and concerns submitted by users. 【0741】 "Means of analyzing emotional states" refers to technologies and processes that identify a user's emotions from text or audio and provide information based on those emotions. 【0742】 "Methods for optimizing the content of advice" refer to technologies that adjust the content of generated advice according to the user's emotional state and situation, making it the most effective and acceptable form. 【0743】 This invention relates to a system that provides personalized and optimal advice based on the user's emotional state to support efficient management by administrators. This system operates using a server, terminals, and an emotion analysis device. 【0744】 The server first collects information related to the group of administrators. This information includes past management cases and administrator documentation. The server analyzes this data using machine learning algorithms to learn patterns for solving various problems and challenges faced by administrators. This creates and stores trained models for solving problems in management operations. 【0745】 The terminal functions as a user interface, allowing users to input their concerns and questions about management in natural language. The input is compatible with both voice and keyboard input. Before sending the input received from the user to the server, the terminal processes it using an emotion analyzer to identify the user's emotional state. 【0746】 The emotion analysis device incorporates technology to analyze a user's emotions from input text or audio. This device tags the user's emotions as "anxiety," "frustration," "joy," etc., and provides this information to a server. 【0747】 The server uses a generative AI model to generate optimal advice based on emotional information obtained from the emotion analysis device. In this process, the content and tone of the advice are adjusted according to the emotion. For example, if a user inputs "My team won't listen to me, and I don't know what to do," the server can generate advice such as "Show empathy and work together to find the root cause of the problem." 【0748】 Finally, the device presents the generated advice to the user. The user is given the opportunity to review and evaluate it. This feedback is sent to the server to further improve the system and helps to improve the accuracy of the sentiment analyzer and trained models. 【0749】 A concrete example of a prompt is, "What are the best practices for team management?" This prompt is used to ask a generative AI model for specific advice. 【0750】 The flow of the specific processing in Example 2 will be explained using Figure 13. 【0751】 Step 1: 【0752】 The server collects information related to the group of administrators. It uses business-related documents and historical management case data as input. The server stores this data in a database and applies machine learning algorithms for analysis. As output, it generates and saves a trained model that extracts patterns and rules useful for solving management challenges. 【0753】 Step 2: 【0754】 Users log in to the terminal and input their concerns and questions regarding management in natural language. They can use a keyboard or voice input device for input. The terminal temporarily stores the user's input data and prepares it for sentiment analysis. It converts the input data to text data to prepare for the next processing step. 【0755】 Step 3: 【0756】 The terminal transmits natural language data entered by the user to an emotion analyzer. This input is user question data in text format. The emotion analyzer analyzes this data and uses natural language processing techniques to identify the user's emotional state. As output, it generates information tagged with the user's emotions, such as "anxiety" or "frustration," and transmits this information to a server via the terminal. 【0757】 Step 4: 【0758】 The server utilizes emotional information obtained from an emotion analysis device and generates optimal advice using a generative AI model. It uses emotion tags and the user's natural language input as input. The server considers the emotional information and adjusts the tone and content of the advice to generate more empathetic and appropriate guidance. For example, if the input is "My team isn't listening, and I don't know what to do," the server will generate specific advice such as "Show empathy and work together to find the root cause of the problem." 【0759】 Step 5: 【0760】 The terminal presents the user with advice received from the server. The input is optimized advice data sent from the server. The terminal displays the advice in a user-friendly format and provides an interface for the user to evaluate the advice. The user reviews the advice and inputs their evaluation as feedback into the terminal. 【0761】 Step 6: 【0762】 User feedback is sent from the terminal to the server. The server uses this feedback to improve the algorithm. User feedback data is the input. The server analyzes the feedback data and uses it to retrain the trained model, thereby improving the accuracy of future advice and continuously improving the system to enable personalized and optimal advice. 【0763】 (Application Example 2) 【0764】 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". 【0765】 Conventional management support systems and user guidance systems often fail to consider users' emotional states and provide uniform responses, making it difficult to offer optimal advice and information to users. Furthermore, they lack sufficient functionality to improve system accuracy through user feedback. Therefore, there is a need for the development of technologies that consider users' emotional states, provide individually optimized advice, and utilize feedback to further improve accuracy. 【0766】 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. 【0767】 In this invention, the server includes means for collecting data related to the managed group and learning role behaviors based on said data; means for generating appropriate advice in response to input questions using a trained model; and means for analyzing the user's emotional state and adapting the tone of the advice considering said emotional information. This enables the generation of optimal advice tailored to the user's unique emotional state, allowing for more effective information provision. Furthermore, the system's accuracy continuously improves based on feedback. 【0768】 A "target group" refers to an individual or group that exhibits specific behaviors or roles, and is the subject of data collection. 【0769】 "Role" is a concept that refers to the function or behavior that an individual or group should perform in a particular situation. 【0770】 A "trained model" refers to an algorithm that has been trained in advance using a machine learning algorithm based on data, and possesses the knowledge necessary to perform a specific task. 【0771】 "Emotional state" refers to the psychological or emotional state that an individual is experiencing at a particular time, and is the object that a system identifies and analyzes. 【0772】 "Tone of advice" refers to the style and tone of expression in the advice and suggestions that are generated, and is an element that is adapted based on the user's emotional state. 【0773】 "Feedback" refers to evaluation information provided by users regarding the performance and results of the system, and is data used to improve the system. 【0774】 "Optimal advice" refers to the most appropriate and beneficial instructions or suggestions provided, taking into account the individual circumstances and emotional state of the user. 【0775】 This invention is a system for providing advice optimized for the user's emotional state. Its central components are a server, a terminal, and an emotion engine. The server collects extensive data related to the managed population and uses machine learning algorithms to learn role behaviors based on this data. The trained model can then generate appropriate advice in response to input questions. 【0776】 The terminal functions as an interface with the user, receiving questions and feedback in natural language. The emotion engine analyzes the user's input information from the terminal, identifying emotional states from voice and text data. This emotional information is sent to the server's advice generation process and used to adapt the tone and content of the generated advice. This enables more empathetic and personalized advice. 【0777】 For example, if a user asks via their device, "I'm stuck in traffic while traveling; how can I maintain a good mood?", the device sends this input to the server, and the emotion engine identifies whether the user is experiencing anxiety or stress. The server then considers this emotional information and generates emotionally sensitive advice, such as suggesting relaxing music. 【0778】 An example of a prompt message would be, "Generate suggestions on how to help a user relax when they are feeling stressed in the car." 【0779】 The flow of a specific process in Application Example 2 will be explained using Figure 14. 【0780】 Step 1: 【0781】 The user inputs a question or concern into the terminal in natural language. The terminal receives this input and prepares to send it to the server as voice or text data. It checks the format of the input data and performs text conversion as needed. The input in this step is the user's natural language query, and the output is text data. 【0782】 Step 2: 【0783】 The terminal sends user input to the emotion engine. The emotion engine identifies the user's emotional state from the input text data and generates an emotion tag. Natural language processing techniques are used for identification, and an emotion analysis algorithm is executed as data processing. The input is the user's text data, and the output is the emotion tag. 【0784】 Step 3: 【0785】 The server receives text data sent from the terminal and generates optimal advice using a pre-trained model. In this process, it creates a variety of answer candidates using a generative AI model. It adjusts the tone of the advice, taking sentiment tags into consideration, to create the final advice. The input is the user's question and sentiment tags, and the output is the most optimized advice. 【0786】 Step 4: 【0787】 The terminal receives advice generated from the server and displays it to the user. The information is delivered according to a pre-configured display format. Based on the user's selection, the advice is displayed on the screen as text. The input is advice data from the server, and the output is advice information formatted for user readability. 【0788】 Step 5: 【0789】 Users send feedback on the displayed advice via their device. The device receives the feedback and sends the information to the server. This feedback is then processed and analyzed again as data on the server. Input is data such as user ratings and opinions, and output is sent to the server as feedback data. 【0790】 Step 6: 【0791】 The server uses the accumulated feedback data to retrain the machine learning model. This improves the accuracy of the generated AI model and optimizes the advice generation process for subsequent sessions. The input is the feedback data, and the output is the updated, trained model. 【0792】 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. 【0793】 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. 【0794】 In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414. 【0795】 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. 【0796】 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. 【0797】 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. 【0798】 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. 【0799】 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. 【0800】 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." 【0801】 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. 【0802】 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. 【0803】 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. 【0804】 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. 【0805】 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. 【0806】 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. 【0807】 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. 【0808】 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. 【0809】 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. 【0810】 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. 【0811】 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. 【0812】 All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference. 【0813】 The following is further disclosed regarding the embodiments described above. 【0814】 (Claim 1) 【0815】 A means of collecting data related to a group of administrators and learning the behavior of administrators based on that data, 【0816】 A means for generating appropriate management advice in response to an input question using a pre-trained model, 【0817】 A means of displaying the generated advice on the device in a style corresponding to the character selected by the user, 【0818】 A means of collecting user feedback and retraining the model's accuracy based on that feedback, 【0819】 A system that includes this. 【0820】 (Claim 2) 【0821】 The system according to claim 1, characterized in that the user inputs their concerns as an administrator in natural language, the input is analyzed, and the system sends it to the server as a query. 【0822】 (Claim 3) 【0823】 The system according to claim 1, characterized in that the generated advice receives feedback based on user evaluation and uses that feedback for relearning. 【0824】 "Example 1" 【0825】 (Claim 1) 【0826】 A means of collecting a wide range of data related to the group of administrators and analyzing the information using a pre-trained model generated based on that data, 【0827】 A means for analyzing questions entered by users in natural language and generating appropriate management advice through a pre-trained model in response to those questions, 【0828】 A means of displaying the generated advice on the device based on the character style selected by the user, 【0829】 A means of collecting user feedback on the generated advice and using that feedback to retrain the model to improve its accuracy, 【0830】 A means for the user to select a character and customize the interface according to that selection, 【0831】 A system that includes this. 【0832】 (Claim 2) 【0833】 The system according to claim 1, characterized in that the user inputs their management concerns in natural language and communicates to quickly send the input data to a server. 【0834】 (Claim 3) 【0835】 The system according to claim 1, characterized in that the advice generated on the terminal receives feedback from the user's evaluation, and the feedback is used to retrain the model to continuously improve performance. 【0836】 "Application Example 1" 【0837】 (Claim 1) 【0838】 A means of collecting data related to a group of administrators and learning the behavior of administrators based on that data, 【0839】 A means for generating appropriate management advice in response to voice-input questions using a pre-trained model, 【0840】 A means for displaying the generated advice on an information processing device in a speaking style appropriate to the character selected by the user, 【0841】 A means of collecting user feedback and retraining the model's accuracy based on that feedback, 【0842】 It is implemented in an information processing device for supporting people's domestic activities, and provides a means of offering advice to support household management and harmony. 【0843】 A system that includes this. 【0844】 (Claim 2) 【0845】 The system according to claim 1, characterized in that the user voice-inputs their concerns as an administrator in natural language, the input is analyzed, and the system sends the input to the server as a query. 【0846】 (Claim 3) 【0847】 The system according to claim 1, characterized in that the generated advice receives feedback based on user evaluation, uses that feedback for retraining, and is reflected in the optimization and adjustment of activities within the home. 【0848】 "Example 2 of combining an emotion engine" 【0849】 (Claim 1) 【0850】 A means of collecting information related to the group of administrators and learning about the administrators' activities based on that information, 【0851】 A means for generating appropriate advice for an input problem using a pre-trained algorithm, 【0852】 A means for analyzing the user's emotional state and optimizing the content of advice generated based on that emotion, 【0853】 A means of presenting optimized advice on the device in a format selected by the user, 【0854】 A means of collecting user feedback and retraining the algorithm's accuracy based on that feedback, 【0855】 A system that includes this. 【0856】 (Claim 2) 【0857】 The system according to claim 1, characterized in that a user inputs an administrator's task in natural language, the input is processed, and the system sends it to the server as a query. 【0858】 (Claim 3) 【0859】 The system according to claim 1, characterized in that the generated advice receives feedback based on user evaluations and uses that feedback for retraining. 【0860】 "Application example 2 when combining with an emotional engine" 【0861】 (Claim 1) 【0862】 A means of collecting data related to the managed group and learning role behaviors based on that data, 【0863】 A means for generating appropriate advice in response to an input question using a pre-trained model, 【0864】 A means for displaying the generated advice on the device in a display style selected by the user, 【0865】 A means for analyzing the user's emotional state and adapting the tone of advice to take that emotional information into consideration, 【0866】 A means of collecting feedback from users and retraining the model's accuracy based on that feedback, 【0867】 A system that includes this. 【0868】 (Claim 2) 【0869】 The system according to claim 1, characterized in that the user inputs their role-related worries in natural language, the input is analyzed, and the system sends it to the server as a query, taking into account the emotional state. 【0870】 (Claim 3) 【0871】 The system according to claim 1, characterized in that the generated advice receives feedback based on the user's evaluation, and that this feedback and emotional information are used for relearning. [Explanation of symbols] 【0872】 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

[Claim 1] A means of collecting data related to a group of administrators and learning the behavior of administrators based on that data, A means for generating appropriate management advice in response to an input question using a pre-trained model, A means of displaying the generated advice on the device in a style corresponding to the character selected by the user, A means of collecting user feedback and retraining the model's accuracy based on that feedback, A system that includes this. [Claim 2] The system according to claim 1, characterized in that the user inputs their concerns as an administrator in natural language, the input is analyzed, and the system sends it to the server as a query. [Claim 3] The system according to claim 1, characterized in that the generated advice receives feedback based on user evaluation and uses that feedback for relearning.

Images