system

Abstract

We provide the system. [Solution] Means of obtaining schedule information, A means of analyzing scheduled information to predict tasks, A means of automatically generating content based on predicted tasks, A means of monitoring business automation processes and detecting, analyzing, and correcting errors, Means for providing notifications regarding generated content and modifications, A means of recording user selections and feedback to improve system performance, 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, including 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 modern information society, a huge number of tasks occur daily, and especially workers are required to process these tasks efficiently. However, manually managing and executing these tasks not only consumes a large amount of time and labor but also causes errors and omissions. The purpose of the present invention is to solve these problems, reduce the workload of users, and realize the efficiency improvement of operations. 【Means for Solving the Problems】 【0005】 This invention provides a system that automatically acquires user schedule information, analyzes that information to predict the next task to be performed, and automatically generates the necessary content. Furthermore, this system has the function to monitor the business automation process, detect and analyze the occurrence of errors, and correct them as needed. The generated content and corrections are notified to the user in a timely manner, and the user can review the suggested options and choose the best one. In addition, it has a means of improving accuracy in the long term by recording user feedback and using it to improve the system's performance. 【0006】 "Schedule information" refers to information that includes details of various activities and events based on a schedule, and includes the title of the schedule, date and time, and a detailed description. 【0007】 A "task" refers to a specific task or action that needs to be performed in one's work or daily life. 【0008】 "Content" refers to a collection of information and materials necessary to perform a task, including documents, tables, and presentation materials. 【0009】 "Automatic generation" refers to the process by which a system creates content and other materials based on a program, without human intervention. 【0010】 "Business process automation" refers to the automated execution of repetitive tasks and operations, often using methods such as RPA (Robotic Process Automation). 【0011】 An "error" refers to an abnormal condition that indicates a system or process is not functioning correctly. 【0012】 "Analysis" refers to the process of breaking down data and information to reveal their structure and relationships. 【0013】 "Correction" refers to the act of fixing errors or malfunctions and restoring a system or process to a normal state. 【0014】 "Notification" refers to a message or alert sent from a system to convey specific information to a user. 【0015】 "Feedback" refers to opinions and evaluation information provided by users to help improve the performance of the system. [Brief explanation of the drawing] 【0016】 [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of the data processing device and 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]It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Embodiment 2 when combined with an emotion engine. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when combined with an emotion engine. 【Mode for Carrying Out the Invention】 【0017】 Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings. 【0018】 First, the terms used in the following description will be explained. 【0019】 In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like. 【0020】 In the following embodiments, the numbered RAM (Random Access Memory) is a memory where information is temporarily stored and is used as a work memory by the processor. 【0021】 In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes. 【0022】 In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark). 【0023】 In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or." 【0024】 [First Embodiment] 【0025】 Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment. 【0026】 As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server. 【0027】 The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network). 【0028】 The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52. 【0029】 The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input. 【0030】 The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor. 【0031】 Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54. 【0032】 Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14. 【0033】 As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30. 【0034】 The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. 【0035】 In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48. 【0036】 Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal". 【0037】 This invention is a system that efficiently automates tasks and supports business operations by exchanging information between servers, terminals, and users. This system mainly consists of the following components: 【0038】 Data acquisition and analysis 【0039】 The server uses the Google Calendar API and other services via a scheduling information network to retrieve user schedule information. The retrieved schedule information includes title, date and time, and details. The server analyzes this information using natural language processing technology to predict the type and urgency of the task. 【0040】 Automatic content generation 【0041】 The server generates the necessary content based on the analyzed task information. This process can automatically create relevant documents such as meeting materials, presentations, and reports using AI. For example, if a meeting is scheduled, it can generate new meeting materials from past agendas and participant lists. 【0042】 Error monitoring and correction 【0043】 The server continuously monitors the automated business process, detecting errors and analyzing logs. If an error occurs, the server uses machine learning algorithms to identify the cause and generate corrective solutions. The corrected code is automatically reapplied, minimizing disruption to the business process. 【0044】 User notifications and interface 【0045】 The device displays notifications from the server to the user, including links to generated content and error reports. The user can review the content provided through the device and make any necessary edits or approvals. 【0046】 Feedback loop 【0047】 User feedback is crucial, and the server collects this information to improve the accuracy of future task predictions and content generation. This allows the system to continuously improve and evolve to better meet user needs. 【0048】 Specific example 【0049】 For example, suppose a user enters a "project review meeting" into their device's calendar. The server uses this information to reference the participants' attendance history and past meeting records, and automatically generates new meeting materials. The generated materials include the project's progress and the goals for the next meeting, and the user can review the content on their device. This cycle is continuous, creating an environment where the user can focus on more important decision-making. 【0050】 The following describes the processing flow. 【0051】 Step 1: 【0052】 The server accesses the Google Calendar API via a scheduling information network at regular intervals to retrieve all of the user's appointments. This includes collecting appointment data such as title, date and time, and detailed description. 【0053】 Step 2: 【0054】 The server analyzes the acquired schedule information using natural language processing (NLP). This analysis identifies the type of task, its importance, the urgency of its deadline, and other factors, and then determines its priority. 【0055】 Step 3: 【0056】 The server automatically generates relevant content based on the analysis results. For example, for a meeting schedule, it creates meeting materials, agendas, and topic lists, and generates other documents as needed using AI. 【0057】 Step 4: 【0058】 The server monitors business automation processes and detects errors in real time that occur during the execution of RPA and other processes. It analyzes log data and applies algorithms to identify the cause of the errors. 【0059】 Step 5: 【0060】 The server automatically generates a suggested fix based on the identified error cause and applies it to the code. It then reruns the corrected process and verifies that it is working correctly. 【0061】 Step 6: 【0062】 The device displays notifications to the user regarding generated content and modified tasks received from the server. These notifications include links and related information. 【0063】 Step 7: 【0064】 Users view notifications on their devices and select or edit the appropriate content provided. After approval, they can enter additional instructions or feedback as needed. 【0065】 Step 8: 【0066】 The server records user feedback and stores it in a database. This information is used for learning to improve the accuracy of future task predictions and content generation. 【0067】 (Example 1) 【0068】 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." 【0069】 In today's information society, schedule management and business process automation are crucial challenges. However, conventional systems have limitations in efficiently predicting individual tasks and automatically generating appropriate information resources. Furthermore, the rapid detection and correction of errors in business automation processes are insufficient, leading to a decrease in the overall efficiency of the system. 【0070】 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. 【0071】 In this invention, the server includes means for acquiring schedule information via an external information system, means for analyzing the acquired schedule information using language information processing technology to predict the type of activity and its priority, and means for automatically generating related information resources using a generative information processing model based on the predicted activities. This makes it possible to streamline schedule management and automate business processes with high accuracy. 【0072】 "Schedule information" refers to data about a user's planned activities, obtained through an external information system. 【0073】 "Language information processing technology" is a technique that analyzes natural language and processes information empirically, and is mainly used for task classification and priority prediction. 【0074】 A "generative information processing model" refers to an algorithm or system that automatically generates related information resources based on given information. 【0075】 "Activity type" refers to the category of a specific action or task, classified based on the analysis of planned information. 【0076】 "Priority" is an indicator that shows the degree of importance or urgency of a schedule or task. 【0077】 "Information resources" refers to digital content related to work and activities, such as automatically generated documents, materials, and reports. 【0078】 "Error detection methods" refer to technologies and methods for identifying errors in business automation processes and analyzing their causes. 【0079】 A "proposal for correction" refers to a proposed improvement or restructuring method to address the cause of an error identified by an error detection method. 【0080】 This invention is an advanced business automation system that acquires schedule information and generates related information resources through analysis. The server uses a general information communication interface to acquire user schedule information from external information systems. For example, it is possible to acquire schedule information using a calendar API. 【0081】 The server applies natural language processing techniques to the acquired schedule information. This technique utilizes natural language processing libraries (such as Python's NLTK or spaCy) to analyze the information, determining the type of activity and its priority. This allows for the determination of the urgency and importance of tasks. 【0082】 Based on the analysis results, the server utilizes a generative information processing model to automatically generate relevant information resources. This process can use a generative AI model (for example, a currently available natural language generation model) to generate necessary meeting materials and reports. For example, if you want to create materials for a "project review meeting," the server sends the following prompt to the generative AI model: "Please create materials for the project review meeting. Refer to past data and include the latest progress and goals for the next meeting." 【0083】 The terminal notifies the user of information resources generated from the server. This includes links to created documents and error reports. The user can use the terminal to review this information and edit or approve it as needed. 【0084】 Furthermore, the server monitors the entire business automation process, and if an error is detected, it analyzes the cause and generates a corrective solution. This process utilizes machine learning algorithms, and the server automatically incorporates the results into the activity process. 【0085】 Finally, users provide data to the server for further improvement through post-use feedback. This feedback is used to improve the system's accuracy and adapt to user needs, leading to continuous system improvement. 【0086】 The flow of the specific processing in Example 1 will be explained using Figure 11. 【0087】 Step 1: 【0088】 The server retrieves user schedule information from an external information system. Specifically, it uses an API for schedule management to obtain data such as the title, date and time, and details of appointments entered by the user in JSON format. This input data enables analysis in the next step. 【0089】 Step 2: 【0090】 The server analyzes the acquired schedule information. Using natural language processing technology and a natural language processing library (for example, spaCy in Python), it classifies the schedule information into activity types and priorities. Through this process, it determines the type and urgency of tasks from the acquired schedule information and outputs structured data. 【0091】 Step 3: 【0092】 The server automatically generates relevant information resources based on the analyzed data. A prompt is input to the information generation processing model (e.g., an AI-based natural language generation model), for example, to request the creation of meeting materials. This prompt might include instructions such as, "Please create materials for the project review meeting. Refer to past data and include the latest progress and goals for the next meeting." The generated materials are then output. 【0093】 Step 4: 【0094】 The server sends the generated information resources to the terminal. The terminal receives this and notifies the user. This includes a download link for the generated materials and any related error reports. The user can review the contents of the materials on the terminal and edit or approve them as needed. 【0095】 Step 5: 【0096】 The server monitors the automated business process and detects errors. It analyzes log data and uses statistical algorithms to identify the root cause of errors. For detected errors, it generates corrective solutions and automates the response process. This process results in a business process with fewer errors. 【0097】 Step 6: 【0098】 Users send feedback on the services provided to the server. This data is used to improve the system's accuracy. Specifically, by retraining the machine learning model based on the feedback data, the accuracy of subsequent generation can be improved. 【0099】 (Application Example 1) 【0100】 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." 【0101】 In modern urban life, residents must efficiently manage a vast amount of schedules and tasks, and coordinating community events with personal schedules is particularly difficult. A system is needed to address this situation, reduce the burden on residents, and efficiently manage and update information. 【0102】 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. 【0103】 In this invention, the server includes means for acquiring schedule information, means for analyzing the schedule information to predict tasks, and means for organizing and managing community event information. This enables residents to seamlessly manage their personal schedules and community events and process information efficiently. 【0104】 "Schedule information acquisition means" refers to a technology for collecting user schedule data, and is a system configuration that acquires information based on time. 【0105】 A "task prediction method" is a process that analyzes collected schedule information and predicts the tasks that should be performed. 【0106】 "Automatic information generation means" refers to technology for automatically creating necessary relevant information based on predicted tasks. 【0107】 "Information automation process monitoring means" refers to technology that constantly monitors the progress of automated information processing and identifies the occurrence of errors. 【0108】 An "error correction method" is a method for identifying the cause of a detected error and formulating and applying corrective measures. 【0109】 "Notification provision means" refers to communication technology used to inform users of generated information and modifications. 【0110】 A "means for organizing and managing information on community events" refers to a mechanism for systematically organizing and managing data related to social events in a specific region. 【0111】 "Feedback recording and performance improvement methods" refer to technologies that collect user feedback and opinions and use them to improve the system. 【0112】 To implement this invention, a server, terminal, and user are used as the basic system configuration. The server utilizes a common calendar API as a scheduling information communication technology to obtain the user's schedule information. The server, which runs on Google Cloud Platform, analyzes the collected schedule information using natural language processing technology and predicts tasks related to each user. 【0113】 Based on the analysis results, the server automatically generates information using a generative AI model. The generated information includes materials related to local community events and information necessary for specific tasks. The generative AI model has the ability to design the necessary content based on universal prompt statements. 【0114】 The terminal functions as an interface that receives notifications from the server and provides the user with generated information and error corrections. Users can view and edit information through the terminal, managing their own schedules and community events. 【0115】 The server also monitors the automated information process and, if an error is detected, analyzes the log data to identify the cause of the error. For detected errors, it automatically applies corrective measures using remediation tools and quickly updates the information. This process utilizes machine learning frameworks such as TENSORFLOW®. 【0116】 As a concrete example, when a user enters "community cleanup activity" into their calendar, the server uses an AI model to automatically generate activity information, past activity data, and a list of necessary preparations based on that information. This information is then notified to the user's device, allowing them to check the details. 【0117】 As an example of a prompt for the generative AI model, we will use the following format: "Please prepare documentation for the following task: Community cleanup activity. Include a summary of the previous activity and areas for improvement." 【0118】 The flow of a specific process in Application Example 1 will be explained using Figure 12. 【0119】 Step 1: 【0120】 The server retrieves calendar information from the user's terminal via the internet. The input is the appointment information registered by the user on their terminal, and the output is a dataset containing that information. This data includes the appointment title, date, time, etc. 【0121】 Step 2: 【0122】 The server analyzes the acquired schedule information using natural language processing techniques. The input is the dataset obtained in step 1, and the output is the type and urgency of the analyzed tasks. This reveals the task priorities. The server performs this analysis to identify important events and decide on actions based on them. 【0123】 Step 3: 【0124】 The server inputs prompt messages into the generation AI model, which automatically generates the necessary information. The input consists of analyzed task information and prompt messages, while the output is the generated documents and information. For example, based on a prompt requesting detailed information about a local event, the server generates event-related documents. This prepares the system for handling the request. 【0125】 Step 4: 【0126】 The server sends the generated information to the terminal in a usable format and notifies the user. The input is the generated information, and the output is the notification to the user's terminal. The server composes and sends the notification, and the user can access, review, and edit the information via their terminal. 【0127】 Step 5: 【0128】 The server monitors the automated information process and analyzes logs to identify the cause of any errors. The input is the log data from the automated process, and the output is the identified error and its cause. Based on this analysis, the server uses a machine learning framework to generate corrective actions. 【0129】 Step 6: 【0130】 The server applies the fix and updates the information. The input is the fix and existing information, and the output is the corrected information. The server automatically implements the fix, minimizing the impact on users. 【0131】 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. 【0132】 This invention relates to a task automation system that takes into account the user's emotional state. The system consists of a server, a terminal, and a user interface, and incorporates an emotion engine. This emotion engine recognizes the user's emotions in real time and dynamically adjusts task priorities, content, and format accordingly. An embodiment thereof is shown below. 【0133】 Collection of emotional data 【0134】 The server monitors user input and everyday interactions through an emotion engine, collecting emotional data. This data is acquired in various formats, including text, voice, and facial expressions. 【0135】 Emotional analysis 【0136】 The server analyzes the collected emotional data to identify emotional states such as positive, negative, and neutral. This analysis utilizes machine learning algorithms to continuously improve the accuracy of emotion recognition. 【0137】 Adjusting task priorities 【0138】 The server dynamically adjusts task priorities based on the user's emotional state. For example, if the user is stressed, the system will prioritize easier tasks. 【0139】 Automatic content generation and adjustment 【0140】 The server adjusts the content and presentation based on the results of sentiment analysis. For example, if a user is experiencing positive emotions, it will focus on providing content related to challenging tasks. 【0141】 Notifications and Interface 【0142】 The device notifies the user of tailored tasks and content. The user selects from the provided options and completes the tasks through the device. They can also provide feedback on their experience. 【0143】 Feedback and Learning 【0144】 The server incorporates user feedback into its emotion recognition engine, using it as training data to further improve its accuracy. This enables personalized support over time. 【0145】 Specific example 【0146】 Suppose a user inputs a message via their device stating that "the project deadline is approaching." The emotion engine detects the user's stress level based on their input style and related history. The server determines the urgency of the tasks, prioritizes and lists the essential tasks, and notifies the user via their device. Once the user has calmed down, it notifies them of more important tasks and adjusts the overall process to ensure efficient progress. This process allows the user to work smoothly while reducing their burden. 【0147】 The following describes the processing flow. 【0148】 Step 1: 【0149】 The server collects input data from the user's terminal in real time. During this process, it transfers various data formats, such as text messages, voice commands, and input speed, to the emotion engine. 【0150】 Step 2: 【0151】 The server analyzes the collected data using an emotion engine to identify the user's emotional state. For example, the emotion engine determines whether the user is stressed or relaxed based on their textual expressions and voice tone. 【0152】 Step 3: 【0153】 The server re-evaluates the user's current task priorities based on their emotional state. If the user is stressed, it prioritizes less burdensome tasks; if they are in a positive state, it recommends more important tasks. 【0154】 Step 4: 【0155】 The server automatically generates content tailored to the user's emotional state. For example, it provides positive users with materials that encourage proactive behavior, and stressed users with content that promotes relaxation. 【0156】 Step 5: 【0157】 The server notifies the user's device of the generated task list and content. The device then displays these to the user and prompts them to select the tasks to perform and the content to use. 【0158】 Step 6: 【0159】 Users view a list of tasks provided through their device and select tasks that are suitable for them. They then perform the tasks, referring to the provided content as needed. 【0160】 Step 7: 【0161】 Users provide feedback after completing a task or during the process. The device forwards this feedback to a server, which is then used to improve the accuracy of sentiment recognition in the future. 【0162】 Step 8: 【0163】 The server updates its emotion recognition model based on the collected feedback, focusing on improving the accuracy of future analyses and personalization capabilities. This learning process is continuous. 【0164】 (Example 2) 【0165】 Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal". 【0166】 Traditional task management systems present tasks without considering the user's emotional state, leading to problems such as stress and decreased efficiency. Furthermore, they lack dynamic task adjustment features that respond to user emotions, resulting in insufficient personalized support. 【0167】 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. 【0168】 In this invention, the server includes means for collecting user emotional information, means for analyzing the collected emotional information to identify the emotional state, and means for dynamically adjusting task priorities based on the identified emotional state. This enables task management according to the user's emotional state, allowing for optimal task progress for each individual user. 【0169】 "User emotional information" refers to data that indicates the user's emotional state, extracted from the user's text input, voice, and facial expressions. 【0170】 "Emotional state" refers to the classification of emotions, such as positive, negative, and neutral, obtained from analyzing the user's emotional information. 【0171】 "Dynamically adjusting task priorities" is a process that changes the order in which tasks are executed in real time based on the user's emotional state. 【0172】 "Automatically generating and adjusting content" refers to automatically creating and optimizing the content and format of the information provided based on the emotional state. 【0173】 "Means of notification" refers to methods or devices for communicating coordinated tasks or content to a user, often via electronic devices. 【0174】 "Improving emotion recognition accuracy based on feedback" is a process that uses user responses to improve the emotional state recognition algorithm, enabling more accurate analysis. 【0175】 This invention relates to a system that automates tasks while taking into account the user's emotional state. The system consists of a server, a terminal, and a user interface. A key component is the emotion engine, which is used to process the user's emotional information in real time. 【0176】 Hardware and software configuration 【0177】 The server functions as the primary component, powering the emotion engine. The emotion engine includes software modules that execute machine learning algorithms, enabling the analysis of collected emotion information. Required hardware includes high-speed processing units and large-capacity storage. For analysis, for example, speech recognition software and text analysis libraries are used. The terminal functions as a communication interface, managing user interaction. 【0178】 Data processing and calculation 【0179】 The server monitors everyday user interactions and collects sentiment information based on them. Text, voice, and facial expression data are treated as primary sources of sentiment information. The sentiment engine receives this information as input and identifies emotional states through machine learning algorithms. Based on these results, tasks are prioritized and optimal content is automatically generated. 【0180】 Specific example 【0181】 For example, if a user inputs "The project deadline is approaching" on their terminal, the emotion engine analyzes the input content and related information such as input speed. The server uses this analysis to identify emotional states indicating stress. It then selects high-priority tasks and effectively notifies the user. An example of a prompt used in this process is, "Evaluate the user's emotional state based on the new data and generate a list of optimal tasks." 【0182】 This allows users to receive optimal task management tailored to their individual emotional state, enabling them to perform their work efficiently while reducing stress. 【0183】 The flow of the specific processing in Example 2 will be explained using Figure 13. 【0184】 Step 1: 【0185】 The server collects user emotion information. Input consists of text, voice, and facial expression data provided by the user through their device. This data is acquired and sent to the emotion engine. A specific example of this operation is recording and collecting information about the speed at which the user types characters on the keyboard. 【0186】 Step 2: 【0187】 The server analyzes emotional information using an emotion engine. In this step, the collected data is used as input, and a machine learning algorithm is used to identify the emotional state. As part of the data processing, pitch and tone are extracted from the audio, and keywords for emotion analysis are extracted from the text. Specifically, the operation involves identifying indicators of negative emotions from the user's voice data. 【0188】 Step 3: 【0189】 The server dynamically adjusts task priorities based on the analysis results. It determines which tasks should be prioritized based on the output of emotional states and updates the task list. The input is identified emotional states, which are used to change the order of tasks. Specifically, if an emotion indicating stress is detected, the display order in the task management system is changed. 【0190】 Step 4: 【0191】 The server automatically generates and adjusts content based on the adjusted tasks. The input for this step is specific emotional states and adjusted task information, while the output is user-specific content. A concrete example of this operation is generating information about a new project to take on when a positive emotional state is detected. 【0192】 Step 5: 【0193】 The terminal notifies the user of the adjusted tasks and content sent from the server. It receives information from the server as input and presents it to the user as output. Specifically, it may display a task list on the screen along with a notification sound. 【0194】 Step 6: 【0195】 Users select tasks and provide feedback through their terminals. This feedback is collected to improve the system's emotion recognition accuracy and sent to the server as input. Specifically, the system may evaluate whether the user was satisfied with the order of the presented tasks and send a short message stating the result. 【0196】 (Application Example 2) 【0197】 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". 【0198】 In modern retail settings, there is a demand for services that cater to the diverse emotional states of customers, but there is a lack of means to quickly provide appropriate customer service. This results in uniform service that disregards customer emotions, hindering improvements in customer satisfaction. Furthermore, it increases the burden on employees and presents challenges in providing efficient customer service. 【0199】 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. 【0200】 In this invention, the server includes means for acquiring schedule information, means for recognizing the user's emotional state, and means for dynamically adjusting the priority of activities based on emotional data. This enables personalized customer service and product recommendations that respond to the customer's emotions. 【0201】 "Schedule information" refers to data related to the user's planned activities and schedule, including information about events and appointments that have been registered in advance. 【0202】 An "activity" refers to the tasks or work that a user should perform, encompassing everyday tasks and errands. 【0203】 "Emotional state" refers to information about the user's current feelings and mood, and includes emotional classifications such as positive, negative, and neutral. 【0204】 "Product and service recommendations" refer to recommendations for specific products or services provided to users based on their emotional state, and involve presenting the optimal choice that aligns with the user's feelings. 【0205】 "Business process automation procedures" refer to methods and flows of automating various processes through programs in order to efficiently carry out user activities. 【0206】 "Historical data" refers to records of past activities and processes, which are used for system learning and analysis. 【0207】 This invention is a system for providing personalized services that take into account the emotional state of the user, and is particularly intended to suggest products and services that are appropriate to the customer's emotions in real time, especially in a retail setting. This system consists of a server, terminals, and devices worn by employees. 【0208】 The server acquires scheduled information and activity-related data, and uses an emotion recognition engine to recognize the user's emotional state. This emotion recognition utilizes machine learning models such as TensorFlow and PyTorch. For example, it analyzes audio data and facial expression data acquired by devices such as smart glasses to determine the user's emotions. This allows for dynamic adjustment of activity priorities based on the emotional data. 【0209】 The terminal provides store employees with specific product suggestions and services based on information sent from the server. This includes suggestions optimized for the customer's emotional state. For example, if a customer is feeling stressed, recommending products with relaxing effects can improve customer satisfaction. 【0210】 Users, i.e., store employees, receive real-time information through smart glasses they wear and immediately suggest appropriate products and services to customers. This process is monitored and corrected in a timely manner by error detection mechanisms to ensure that accurate information and services are provided. 【0211】 A concrete example of implementing this invention is a system in which an employee reads a customer's mood and sends a prompt to a generating AI model, for example, "What products or services can be offered to a customer who wants to relax?", to obtain suggestions. The suggestions generated using this prompt are displayed on a terminal, and appropriate services are provided on the spot. 【0212】 The flow of a specific process in Application Example 2 will be explained using Figure 14. 【0213】 Step 1: 【0214】 The server obtains basic appointment information and activity-related data from customers via the terminal. This input data includes customer reservation information and past purchase history. Based on this data, the server generates a basic profile of the customer. This profile forms the basis for providing personalized services. 【0215】 Step 2: 【0216】 The device or smart glasses capture the voice and facial expressions of customers in real time and send them to the server. The input data mainly consists of camera footage and audio data from the microphone. The server analyzes this data using a machine learning model to determine the customer's emotional state. The output is categorized as positive, negative, or neutral. 【0217】 Step 3: 【0218】 The server dynamically readjusts the priorities of existing tasks based on the analyzed emotional state. The input data consists of the profile obtained in Step 1 and the emotional categories from Step 2. As part of the data processing, a priority list is generated based on the urgency of the tasks and the customer's state, and an optimized task list is created as the output. 【0219】 Step 4: 【0220】 The server generates product and service suggestions based on the customer's emotional state and priority task list. This process uses a generation AI model to suggest products and services best suited to the customer's current situation. Based on the input data, a list of suggested products is output and provided to employees via their terminals. 【0221】 Step 5: 【0222】 Users (employees) review product suggestions provided by the server via the terminal's display or smart glasses, and then provide specific customer service. The input data is suggestion information from the server, and the resulting output is the actual service provided to the customer. This service provision contributes to improving customer satisfaction. 【0223】 Step 6: 【0224】 The terminal sends user feedback and service results to the server, recording them as data to improve system performance. The input data is post-service feedback information; the server uses this information as training data to improve the accuracy of future suggestions. The output is the improved service algorithm. 【0225】 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. 【0226】 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. 【0227】 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. 【0228】 [Second Embodiment] 【0229】 Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment. 【0230】 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. 【0231】 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). 【0232】 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. 【0233】 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. 【0234】 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). 【0235】 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. 【0236】 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. 【0237】 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. 【0238】 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. 【0239】 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. 【0240】 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". 【0241】 This invention is a system that efficiently automates tasks and supports business operations by exchanging information between servers, terminals, and users. This system mainly consists of the following components: 【0242】 Data acquisition and analysis 【0243】 The server uses the Google Calendar API and other services via a scheduling information network to retrieve user schedule information. The retrieved schedule information includes title, date and time, and details. The server analyzes this information using natural language processing technology to predict the type and urgency of the task. 【0244】 Automatic content generation 【0245】 The server generates the necessary content based on the analyzed task information. This process can automatically create relevant documents such as meeting materials, presentations, and reports using AI. For example, if a meeting is scheduled, it can generate new meeting materials from past agendas and participant lists. 【0246】 Error monitoring and correction 【0247】 The server continuously monitors the automated business process, detecting errors and analyzing logs. If an error occurs, the server uses machine learning algorithms to identify the cause and generate corrective solutions. The corrected code is automatically reapplied, minimizing disruption to the business process. 【0248】 User notifications and interface 【0249】 The device displays notifications from the server to the user, including links to generated content and error reports. The user can review the content provided through the device and make any necessary edits or approvals. 【0250】 Feedback loop 【0251】 User feedback is crucial, and the server collects this information to improve the accuracy of future task predictions and content generation. This allows the system to continuously improve and evolve to better meet user needs. 【0252】 Specific example 【0253】 For example, suppose a user enters a "project review meeting" into their device's calendar. The server uses this information to reference the participants' attendance history and past meeting records, and automatically generates new meeting materials. The generated materials include the project's progress and the goals for the next meeting, and the user can review the content on their device. This cycle is continuous, creating an environment where the user can focus on more important decision-making. 【0254】 The following describes the processing flow. 【0255】 Step 1: 【0256】 The server accesses the Google Calendar API via a scheduling information network at regular intervals to retrieve all of the user's appointments. This includes collecting appointment data such as title, date and time, and detailed description. 【0257】 Step 2: 【0258】 The server analyzes the acquired schedule information using natural language processing (NLP). This analysis identifies the type of task, its importance, the urgency of its deadline, and other factors, and then determines its priority. 【0259】 Step 3: 【0260】 The server automatically generates relevant content based on the analysis results. For example, for a meeting schedule, it creates meeting materials, agendas, and topic lists, and generates other documents as needed using AI. 【0261】 Step 4: 【0262】 The server monitors business automation processes and detects errors in real time that occur during the execution of RPA and other processes. It analyzes log data and applies algorithms to identify the cause of the errors. 【0263】 Step 5: 【0264】 The server automatically generates a suggested fix based on the identified error cause and applies it to the code. It then reruns the corrected process and verifies that it is working correctly. 【0265】 Step 6: 【0266】 The device displays notifications to the user regarding generated content and modified tasks received from the server. These notifications include links and related information. 【0267】 Step 7: 【0268】 Users view notifications on their devices and select or edit the appropriate content provided. After approval, they can enter additional instructions or feedback as needed. 【0269】 Step 8: 【0270】 The server records user feedback and stores it in a database. This information is used for learning to improve the accuracy of future task predictions and content generation. 【0271】 (Example 1) 【0272】 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." 【0273】 In today's information society, schedule management and business process automation are crucial challenges. However, conventional systems have limitations in efficiently predicting individual tasks and automatically generating appropriate information resources. Furthermore, the rapid detection and correction of errors in business automation processes are insufficient, leading to a decrease in the overall efficiency of the system. 【0274】 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. 【0275】 In this invention, the server includes means for acquiring schedule information via an external information system, means for analyzing the acquired schedule information using language information processing technology to predict the type of activity and its priority, and means for automatically generating related information resources using a generative information processing model based on the predicted activities. This makes it possible to streamline schedule management and automate business processes with high accuracy. 【0276】 "Schedule information" refers to data about the user's planned activities, obtained through external information systems. 【0277】 "Language information processing technology" is a technique that analyzes natural language and processes information empirically, and is mainly used for task classification and priority prediction. 【0278】 A "generative information processing model" refers to an algorithm or system that automatically generates related information resources based on given information. 【0279】 "Activity type" refers to the category of a specific action or task, classified based on the analysis of planned information. 【0280】 "Priority" is an indicator that shows the degree of importance or urgency of a schedule or task. 【0281】 "Information resources" refers to digital content related to work and activities, such as automatically generated documents, materials, and reports. 【0282】 "Error detection methods" refer to technologies and methods for identifying errors in business automation processes and analyzing their causes. 【0283】 A "proposal for correction" refers to a proposed improvement or restructuring method to address the cause of an error identified by an error detection method. 【0284】 This invention is an advanced business automation system that acquires scheduling information and generates relevant information resources through analysis. The server uses a general information communication interface to obtain the user's scheduling information from an external information system. For example, it is possible to obtain scheduling information using a calendar API. 【0285】 The server applies language information processing technology to the acquired scheduling information. In this technology, natural language processing libraries (such as NLTK or spaCy in Python) are used to analyze the type of activity and its priority from the information. As a result, it is possible to determine the urgency and importance of tasks. 【0286】 Based on the analysis results, the server utilizes a generated information processing model to automatically generate relevant information resources. In this process, a generative AI model (such as currently available natural language generation models) can be used to generate the necessary meeting materials and reports. As a specific example, when wanting to create materials for a "project review meeting", the server sends the following prompt sentence to the generative AI model. "Please create materials for the project review meeting. Refer to past data and include the latest progress and next goals." 【0287】 The terminal notifies the user of the generated information resources from the server. This includes links to the created materials, error reports, etc. The user can use the terminal to check this information and make edits or approvals as needed. 【0288】 Furthermore, the server monitors the entire business automation process. When an error is detected, it analyzes the cause and generates a correction. A machine learning algorithm is used in this process, and the server automatically reflects the results in the activity process. 【0289】 Finally, users provide data to the server for further improvement through post-use feedback. This feedback is used to improve the system's accuracy and adapt to user needs, leading to continuous system improvement. 【0290】 The flow of the specific processing in Example 1 will be explained using Figure 11. 【0291】 Step 1: 【0292】 The server retrieves user schedule information from an external information system. Specifically, it uses an API for schedule management to obtain data such as the title, date and time, and details of appointments entered by the user in JSON format. This input data enables analysis in the next step. 【0293】 Step 2: 【0294】 The server analyzes the acquired schedule information. Using natural language processing technology and a natural language processing library (for example, spaCy in Python), it classifies the schedule information into activity types and priorities. Through this process, it determines the type and urgency of tasks from the acquired schedule information and outputs structured data. 【0295】 Step 3: 【0296】 The server automatically generates relevant information resources based on the analyzed data. A prompt is input to the information generation processing model (e.g., an AI-based natural language generation model), for example, to request the creation of meeting materials. This prompt might include instructions such as, "Please create materials for the project review meeting. Refer to past data and include the latest progress and goals for the next meeting." The generated materials are then output. 【0297】 Step 4: 【0298】 The server sends the generated information resources to the terminal. The terminal receives them and notifies the user. This includes a download link for the generated materials and any related error reports. The user can review the contents of the materials on the terminal and edit or approve them as needed. 【0299】 Step 5: 【0300】 The server monitors the automated business process and detects errors. It analyzes log data and uses statistical algorithms to identify the root cause of errors. For detected errors, it generates corrective solutions and automates the response process. This process results in a business process with fewer errors. 【0301】 Step 6: 【0302】 Users send feedback on the services provided to the server. This data is used to improve the system's accuracy. Specifically, by retraining the machine learning model based on the feedback data, the accuracy of subsequent generation can be improved. 【0303】 (Application Example 1) 【0304】 Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal." 【0305】 In modern urban life, residents must efficiently manage a vast amount of schedules and tasks, and coordinating community events with personal schedules is particularly difficult. A system is needed to address this situation, reduce the burden on residents, and efficiently manage and update information. 【0306】 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. 【0307】 In this invention, the server includes means for acquiring schedule information, means for analyzing the schedule information to predict tasks, and means for organizing and managing the information on the local community's events. As a result, it becomes possible for residents to seamlessly manage their personal schedules and local events and efficiently process information. 【0308】 The "schedule information acquisition means" is a technology for collecting the user's schedule data and is a system configuration for acquiring information based on time. 【0309】 The "task prediction means" is a process of analyzing the collected schedule information and inferring the tasks to be executed. 【0310】 The "information automatic generation means" is a technology for automatically creating necessary related information based on the predicted tasks. 【0311】 The "information automation process monitoring means" is a technology for constantly monitoring the progress of automated information processing and confirming the occurrence of errors. 【0312】 The "error correction means" is a method for identifying the cause of the detected error and formulating and applying corrective measures. 【0313】 The "notification providing means" is a communication technology for notifying the user of the generated information and the corrected content. 【0314】 The "means for organizing and managing the information on the local community's events" is a mechanism for systematically organizing and managing data on social events in a specific region. 【0315】 The "feedback recording and performance improvement means" is a technology for collecting the user's reactions and opinions and using them for system improvement. 【0316】 To implement this invention, a server, terminal, and user are used as the basic system configuration. The server utilizes a common calendar API as a scheduling information communication technology to obtain the user's schedule information. The server, which runs on Google Cloud Platform, analyzes the collected schedule information using natural language processing technology and predicts tasks related to each user. 【0317】 Based on the analysis results, the server automatically generates information using a generative AI model. The generated information includes materials related to local community events and information necessary for specific tasks. The generative AI model has the ability to design the necessary content based on universal prompt statements. 【0318】 The terminal functions as an interface that receives notifications from the server and provides the user with generated information and error corrections. Users can view and edit information through the terminal, managing their own schedules and community events. 【0319】 The server also monitors the automated information process and, if an error is detected, analyzes the log data to identify the cause of the error. For detected errors, it automatically applies corrective measures using available tools and quickly updates the information. This process utilizes machine learning frameworks such as TensorFlow. 【0320】 As a concrete example, when a user enters "community cleanup activity" into their calendar, the server uses an AI model to automatically generate activity information, past activity data, and a list of necessary preparations based on that information. This information is then notified to the user's device, allowing them to check the details. 【0321】 As an example of a prompt for the generative AI model, we will use the following format: "Please prepare documentation for the following task: Community cleanup activity. Include a summary of the previous activity and areas for improvement." 【0322】 The flow of a specific process in Application Example 1 will be explained using Figure 12. 【0323】 Step 1: 【0324】 The server retrieves calendar information from the user's terminal via the internet. The input is the appointment information registered by the user on their terminal, and the output is a dataset containing that information. This data includes the appointment title, date, time, etc. 【0325】 Step 2: 【0326】 The server analyzes the acquired schedule information using natural language processing techniques. The input is the dataset obtained in step 1, and the output is the type and urgency of the analyzed tasks. This reveals the task priorities. The server performs this analysis to identify important events and decide on actions based on them. 【0327】 Step 3: 【0328】 The server inputs prompt messages into the generation AI model, which automatically generates the necessary information. The input consists of analyzed task information and prompt messages, while the output is the generated documents and information. For example, based on a prompt requesting detailed information about a local event, the server generates event-related documents. This prepares the system for handling the request. 【0329】 Step 4: 【0330】 The server sends the generated information to the terminal in a usable format and notifies the user. The input is the generated information, and the output is the notification to the user's terminal. The server composes and sends the notification, and the user can access, review, and edit the information via their terminal. 【0331】 Step 5: 【0332】 The server monitors the automated information process and analyzes logs to identify the cause of any errors. The input is the log data from the automated process, and the output is the identified error and its cause. Based on this analysis, the server uses a machine learning framework to generate corrective actions. 【0333】 Step 6: 【0334】 The server applies the fix and updates the information. The input is the fix and existing information, and the output is the corrected information. The server automatically implements the fix, minimizing the impact on users. 【0335】 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. 【0336】 This invention relates to a task automation system that takes into account the user's emotional state. The system consists of a server, a terminal, and a user interface, and incorporates an emotion engine. This emotion engine recognizes the user's emotions in real time and dynamically adjusts task priorities, content, and format accordingly. An embodiment thereof is shown below. 【0337】 Collection of emotional data 【0338】 The server monitors user input and everyday interactions through an emotion engine, collecting emotional data. This data is acquired in various formats, including text, voice, and facial expressions. 【0339】 Emotional analysis 【0340】 The server analyzes the collected emotional data to identify emotional states such as positive, negative, and neutral. This analysis utilizes machine learning algorithms to continuously improve the accuracy of emotion recognition. 【0341】 Adjusting task priorities 【0342】 The server dynamically adjusts task priorities based on the user's emotional state. For example, if the user is stressed, the system will prioritize easier tasks. 【0343】 Automatic content generation and adjustment 【0344】 The server adjusts the content and presentation based on the results of sentiment analysis. For example, if a user is experiencing positive emotions, it will focus on providing content related to challenging tasks. 【0345】 Notifications and Interface 【0346】 The device notifies the user of tailored tasks and content. The user selects from the provided options and completes the tasks through the device. They can also provide feedback on their experience. 【0347】 Feedback and Learning 【0348】 The server incorporates user feedback into its emotion recognition engine, using it as training data to further improve its accuracy. This enables personalized support over time. 【0349】 Specific example 【0350】 Suppose a user inputs a message via their device stating that "the project deadline is approaching." The emotion engine detects the user's stress level based on their input style and related history. The server determines the urgency of the tasks, prioritizes and lists the essential tasks, and notifies the user via their device. Once the user has calmed down, it notifies them of more important tasks and adjusts the overall process to ensure efficient progress. This process allows the user to work smoothly while reducing their burden. 【0351】 The following describes the processing flow. 【0352】 Step 1: 【0353】 The server collects input data from the user's terminal in real time. During this process, it transfers various data formats, such as text messages, voice commands, and input speed, to the emotion engine. 【0354】 Step 2: 【0355】 The server analyzes the collected data using an emotion engine to identify the user's emotional state. For example, the emotion engine determines whether the user is stressed or relaxed based on their textual expressions and voice tone. 【0356】 Step 3: 【0357】 The server re-evaluates the user's current task priorities based on their emotional state. If the user is stressed, it prioritizes less burdensome tasks; if they are in a positive state, it recommends more important tasks. 【0358】 Step 4: 【0359】 The server automatically generates content tailored to the user's emotional state. For example, it provides positive users with materials that encourage proactive behavior, and stressed users with content that promotes relaxation. 【0360】 Step 5: 【0361】 The server notifies the user's device of the generated task list and content. The device then displays these to the user and prompts them to select the tasks to perform and the content to use. 【0362】 Step 6: 【0363】 Users review the task list provided through their device and select tasks that suit them. They then perform the tasks, referring to the provided content as needed. 【0364】 Step 7: 【0365】 Users provide feedback after completing a task or during the process. The device then forwards this feedback to a server, which is used to improve the accuracy of sentiment recognition in the future. 【0366】 Step 8: 【0367】 The server updates its emotion recognition model based on the collected feedback, focusing on improving the accuracy of future analyses and personalization capabilities. This learning process is continuous. 【0368】 (Example 2) 【0369】 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". 【0370】 Traditional task management systems present tasks without considering the user's emotional state, leading to problems such as stress and decreased efficiency. Furthermore, they lack dynamic task adjustment features that respond to user emotions, resulting in insufficient personalized support. 【0371】 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. 【0372】 In this invention, the server includes means for collecting user emotional information, means for analyzing the collected emotional information to identify the emotional state, and means for dynamically adjusting task priorities based on the identified emotional state. This enables task management according to the user's emotional state, allowing for optimal task progress for each individual user. 【0373】 "User emotional information" refers to data that indicates the user's emotional state, extracted from the user's text input, voice, and facial expressions. 【0374】 "Emotional state" refers to the classification of emotions, such as positive, negative, and neutral, obtained from analyzing the user's emotional information. 【0375】 "Dynamically adjusting task priorities" is a process that changes the order in which tasks are executed in real time based on the user's emotional state. 【0376】 "Automatically generating and adjusting content" refers to automatically creating and optimizing the content and format of the information provided based on the emotional state. 【0377】 "Means of notification" refers to methods or devices for communicating coordinated tasks or content to a user, often via electronic devices. 【0378】 "Improving emotion recognition accuracy based on feedback" is a process that uses user responses to improve the emotional state recognition algorithm, enabling more accurate analysis. 【0379】 This invention relates to a system that automates tasks while taking into account the user's emotional state. The system consists of a server, a terminal, and a user interface. A key component is the emotion engine, which is used to process the user's emotional information in real time. 【0380】 Hardware and software configuration 【0381】 The server functions as the primary component, powering the emotion engine. The emotion engine includes software modules that execute machine learning algorithms, enabling the analysis of collected emotion information. Required hardware includes high-speed processing units and large-capacity storage. For analysis, for example, speech recognition software and text analysis libraries are used. The terminal functions as a communication interface, managing user interaction. 【0382】 Data processing and calculations 【0383】 The server monitors everyday user interactions and collects sentiment information based on them. Text, voice, and facial expression data are treated as primary sources of sentiment information. The sentiment engine receives this information as input and identifies emotional states through machine learning algorithms. Based on these results, tasks are prioritized and optimal content is automatically generated. 【0384】 Specific example 【0385】 For example, if a user inputs "The project deadline is approaching" on their terminal, the emotion engine analyzes the input content and related information such as input speed. The server uses this analysis to identify emotional states indicating stress. It then selects high-priority tasks and effectively notifies the user. An example of a prompt used in this process is, "Evaluate the user's emotional state based on the new data and generate a list of optimal tasks." 【0386】 This allows users to receive optimal task management tailored to their individual emotional state, enabling them to perform their work efficiently while reducing stress. 【0387】 The flow of the specific processing in Example 2 will be explained using Figure 13. 【0388】 Step 1: 【0389】 The server collects user emotion information. Input consists of text, voice, and facial expression data provided by the user through their device. This data is acquired and sent to the emotion engine. A specific example of this operation is recording and collecting information about the speed at which the user types characters on the keyboard. 【0390】 Step 2: 【0391】 The server analyzes emotional information using an emotion engine. In this step, the collected data is used as input, and a machine learning algorithm is used to identify the emotional state. As part of the data processing, pitch and tone are extracted from the audio, and keywords for emotion analysis are extracted from the text. Specifically, the operation involves identifying indicators of negative emotions from the user's voice data. 【0392】 Step 3: 【0393】 The server dynamically adjusts task priorities based on the analysis results. It determines which tasks should be prioritized based on the output of emotional states and updates the task list. The input is identified emotional states, which are used to change the order of tasks. Specifically, if an emotion indicating stress is detected, the display order in the task management system is changed. 【0394】 Step 4: 【0395】 The server automatically generates and adjusts content based on the adjusted tasks. The input for this step is specific emotional states and adjusted task information, while the output is user-specific content. A concrete example of this operation is generating information about a new project to take on when a positive emotional state is detected. 【0396】 Step 5: 【0397】 The terminal notifies the user of the adjusted tasks and content sent from the server. It receives information from the server as input and presents it to the user as output. Specifically, it may display a task list on the screen along with a notification sound. 【0398】 Step 6: 【0399】 Users select tasks and provide feedback through their terminals. This feedback is collected to improve the system's emotion recognition accuracy and sent to the server as input. Specifically, the system may evaluate whether the user was satisfied with the order of the presented tasks and send a short message stating the result. 【0400】 (Application Example 2) 【0401】 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 as the "terminal". 【0402】 In modern retail settings, there is a demand for services that cater to the diverse emotional states of customers, but there is a lack of means to quickly provide appropriate customer service. This results in uniform service that disregards customer emotions, hindering improvements in customer satisfaction. Furthermore, it increases the burden on employees and presents challenges in providing efficient customer service. 【0403】 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. 【0404】 In this invention, the server includes means for acquiring schedule information, means for recognizing the user's emotional state, and means for dynamically adjusting the priority of activities based on emotional data. This enables personalized customer service and product recommendations that respond to the customer's emotions. 【0405】 "Schedule information" refers to data related to the user's planned activities and schedule, including information about events and appointments that have been registered in advance. 【0406】 An "activity" refers to the tasks or work that a user should perform, encompassing everyday tasks and errands. 【0407】 "Emotional state" refers to information about the user's current feelings and mood, and includes emotional classifications such as positive, negative, and neutral. 【0408】 "Product and service recommendations" refer to recommendations for specific products or services provided to users based on their emotional state, and involve presenting the optimal choice that aligns with the user's feelings. 【0409】 "Business process automation procedures" refer to methods and flows of automating various processes through programs in order to efficiently carry out user activities. 【0410】 "Historical data" refers to records of past activities and processes, which are used for system learning and analysis. 【0411】 This invention is a system for providing personalized services that take into account the emotional state of the user, and is particularly intended to suggest products and services that are appropriate to the customer's emotions in real time, especially in a retail setting. This system consists of a server, terminals, and devices worn by employees. 【0412】 The server acquires scheduled information and activity-related data, and uses an emotion recognition engine to recognize the user's emotional state. This emotion recognition utilizes machine learning models such as TensorFlow and PyTorch. For example, it analyzes audio data and facial expression data acquired by devices such as smart glasses to determine the user's emotions. This allows for dynamic adjustment of activity priorities based on the emotional data. 【0413】 The terminal provides store employees with specific product suggestions and services based on information sent from the server. This includes suggestions optimized for the customer's emotional state. For example, if a customer is feeling stressed, recommending products with relaxing effects can improve customer satisfaction. 【0414】 Users, i.e., store employees, receive real-time information through smart glasses they wear and immediately suggest appropriate products and services to customers. This process is monitored and corrected in a timely manner by error detection mechanisms to ensure that accurate information and services are provided. 【0415】 A concrete example of implementing this invention is a system in which an employee reads a customer's mood and sends a prompt to a generating AI model, for example, "What products or services can be offered to a customer who wants to relax?", to obtain suggestions. The suggestions generated using this prompt are displayed on a terminal, and appropriate services are provided on the spot. 【0416】 The flow of a specific process in Application Example 2 will be explained using Figure 14. 【0417】 Step 1: 【0418】 The server obtains basic appointment information and activity-related data from customers via the terminal. This input data includes customer reservation information and past purchase history. Based on this data, the server generates a basic profile of the customer. This profile forms the basis for providing personalized services. 【0419】 Step 2: 【0420】 The device or smart glasses capture the voice and facial expressions of customers in real time and send them to the server. The input data mainly consists of camera footage and audio data from the microphone. The server analyzes this data using a machine learning model to determine the customer's emotional state. The output is categorized as positive, negative, or neutral. 【0421】 Step 3: 【0422】 The server dynamically readjusts the priorities of existing tasks based on the analyzed emotional state. The input data consists of the profile obtained in Step 1 and the emotional categories from Step 2. As part of the data processing, a priority list is generated based on the urgency of the tasks and the customer's state, and an optimized task list is created as the output. 【0423】 Step 4: 【0424】 The server generates product and service suggestions based on the customer's emotional state and priority task list. This process uses a generation AI model to suggest products and services best suited to the customer's current situation. Based on the input data, a list of suggested products is output and provided to employees via their terminals. 【0425】 Step 5: 【0426】 Users (employees) review product suggestions provided by the server via the terminal's display or smart glasses, and then provide specific customer service. The input data is suggestion information from the server, and the resulting output is the actual service provided to the customer. This service provision contributes to improving customer satisfaction. 【0427】 Step 6: 【0428】 The terminal sends user feedback and service results to the server, recording them as data to improve system performance. The input data is post-service feedback information; the server uses this information as training data to improve the accuracy of future suggestions. The output is the improved service algorithm. 【0429】 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. 【0430】 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. 【0431】 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. 【0432】 [Third Embodiment] 【0433】 Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment. 【0434】 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. 【0435】 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). 【0436】 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. 【0437】 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. 【0438】 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). 【0439】 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. 【0440】 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. 【0441】 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. 【0442】 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. 【0443】 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. 【0444】 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". 【0445】 This invention is a system that efficiently automates tasks and supports business operations by exchanging information between servers, terminals, and users. This system mainly consists of the following components: 【0446】 Data acquisition and analysis 【0447】 The server uses the Google Calendar API and other services via a scheduling information network to retrieve user schedule information. The retrieved schedule information includes title, date and time, and details. The server analyzes this information using natural language processing technology to predict the type and urgency of the task. 【0448】 Automatic content generation 【0449】 The server generates the necessary content based on the analyzed task information. This process can automatically create relevant documents such as meeting materials, presentations, and reports using AI. For example, if a meeting is scheduled, it can generate new meeting materials from past agendas and participant lists. 【0450】 Error monitoring and correction 【0451】 The server continuously monitors the automated business process, detecting errors and analyzing logs. If an error occurs, the server uses machine learning algorithms to identify the cause and generate corrective solutions. The corrected code is automatically reapplied, minimizing disruption to the business process. 【0452】 User notifications and interface 【0453】 The device displays notifications from the server to the user, including links to generated content and error reports. The user can review the content provided through the device and make any necessary edits or approvals. 【0454】 Feedback loop 【0455】 User feedback is crucial, and the server collects this information to improve the accuracy of future task predictions and content generation. This allows the system to continuously improve and evolve to better meet user needs. 【0456】 Specific example 【0457】 For example, suppose a user enters a "project review meeting" into their device's calendar. The server uses this information to reference the participants' attendance history and past meeting records, and automatically generates new meeting materials. The generated materials include the project's progress and the goals for the next meeting, and the user can review the content on their device. This cycle is continuous, creating an environment where the user can focus on more important decision-making. 【0458】 The following describes the processing flow. 【0459】 Step 1: 【0460】 The server accesses the Google Calendar API via a scheduling information network at regular intervals to retrieve all of the user's appointments. This includes collecting appointment data such as title, date and time, and detailed description. 【0461】 Step 2: 【0462】 The server analyzes the acquired schedule information using natural language processing (NLP). This analysis identifies the type of task, its importance, the urgency of its deadline, and other factors, and then determines its priority. 【0463】 Step 3: 【0464】 The server automatically generates relevant content based on the analysis results. For example, for a meeting schedule, it creates meeting materials, agendas, and topic lists, and generates other documents as needed using AI. 【0465】 Step 4: 【0466】 The server monitors business automation processes and detects errors in real time that occur during the execution of RPA and other processes. It analyzes log data and applies algorithms to identify the cause of the errors. 【0467】 Step 5: 【0468】 The server automatically generates a suggested fix based on the identified error cause and applies it to the code. It then reruns the corrected process and verifies that it is working correctly. 【0469】 Step 6: 【0470】 The device displays notifications to the user regarding generated content and modified tasks received from the server. These notifications include links and related information. 【0471】 Step 7: 【0472】 Users view notifications on their devices and select or edit the appropriate content provided. After approval, they can enter additional instructions or feedback as needed. 【0473】 Step 8: 【0474】 The server records user feedback and stores it in a database. This information is used for learning to improve the accuracy of future task predictions and content generation. 【0475】 (Example 1) 【0476】 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." 【0477】 In today's information society, schedule management and business process automation are crucial challenges. However, conventional systems have limitations in efficiently predicting individual tasks and automatically generating appropriate information resources. Furthermore, the rapid detection and correction of errors in business automation processes are insufficient, leading to a decrease in the overall efficiency of the system. 【0478】 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. 【0479】 In this invention, the server includes means for acquiring schedule information via an external information system, means for analyzing the acquired schedule information using language information processing technology to predict the type of activity and its priority, and means for automatically generating related information resources using a generative information processing model based on the predicted activities. This makes it possible to streamline schedule management and automate business processes with high accuracy. 【0480】 "Schedule information" refers to data about the user's planned activities, obtained through external information systems. 【0481】 "Language information processing technology" is a technique that analyzes natural language and processes information empirically, and is mainly used for task classification and priority prediction. 【0482】 A "generative information processing model" refers to an algorithm or system that automatically generates related information resources based on given information. 【0483】 "Activity type" refers to the category of a specific action or task, classified based on the analysis of planned information. 【0484】 "Priority" is an indicator that shows the degree of importance or urgency of a schedule or task. 【0485】 "Information resources" refers to digital content related to work and activities, such as automatically generated documents, materials, and reports. 【0486】 "Error detection methods" refer to technologies and methods for identifying errors in business automation processes and analyzing their causes. 【0487】 A "proposal for correction" refers to a proposed improvement or restructuring method to address the cause of an error identified by an error detection method. 【0488】 This invention is an advanced business automation system that acquires schedule information and generates related information resources through analysis. The server uses a general information communication interface to acquire user schedule information from external information systems. For example, it is possible to acquire schedule information using a calendar API. 【0489】 The server applies natural language processing techniques to the acquired schedule information. This technique utilizes natural language processing libraries (such as Python's NLTK or spaCy) to analyze the information, determining the type of activity and its priority. This allows for the determination of the urgency and importance of tasks. 【0490】 Based on the analysis results, the server utilizes a generative information processing model to automatically generate relevant information resources. This process can use a generative AI model (for example, a currently available natural language generation model) to generate necessary meeting materials and reports. For example, if you want to create materials for a "project review meeting," the server sends the following prompt to the generative AI model: "Please create materials for the project review meeting. Refer to past data and include the latest progress and goals for the next meeting." 【0491】 The terminal notifies the user of information resources generated from the server. This includes links to created documents and error reports. The user can use the terminal to review this information and edit or approve it as needed. 【0492】 Furthermore, the server monitors the entire business automation process, and if an error is detected, it analyzes the cause and generates a corrective solution. This process utilizes machine learning algorithms, and the server automatically incorporates the results into the activity process. 【0493】 Finally, users provide data to the server for further improvement through post-use feedback. This feedback is used to improve the system's accuracy and adapt to user needs, leading to continuous system improvement. 【0494】 The flow of the specific processing in Example 1 will be explained using Figure 11. 【0495】 Step 1: 【0496】 The server retrieves user schedule information from an external information system. Specifically, it uses an API for schedule management to obtain data such as the title, date and time, and details of appointments entered by the user in JSON format. This input data enables analysis in the next step. 【0497】 Step 2: 【0498】 The server analyzes the acquired schedule information. Using natural language processing technology and a natural language processing library (for example, spaCy in Python), it classifies the schedule information into activity types and priorities. Through this process, it determines the type and urgency of tasks from the acquired schedule information and outputs structured data. 【0499】 Step 3: 【0500】 The server automatically generates relevant information resources based on the analyzed data. A prompt is input to the information generation processing model (e.g., an AI-based natural language generation model), for example, to request the creation of meeting materials. This prompt might include instructions such as, "Please create materials for the project review meeting. Refer to past data and include the latest progress and goals for the next meeting." The generated materials are then output. 【0501】 Step 4: 【0502】 The server sends the generated information resources to the terminal. The terminal receives them and notifies the user. This includes a download link for the generated materials and any related error reports. The user can review the contents of the materials on the terminal and edit or approve them as needed. 【0503】 Step 5: 【0504】 The server monitors the automated business process and detects errors. It analyzes log data and uses statistical algorithms to identify the root cause of errors. For detected errors, it generates corrective solutions and automates the response process. This process results in a business process with fewer errors. 【0505】 Step 6: 【0506】 Users send feedback on the services provided to the server. This data is used to improve the system's accuracy. Specifically, by retraining the machine learning model based on the feedback data, the accuracy of subsequent generation can be improved. 【0507】 (Application Example 1) 【0508】 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." 【0509】 In modern urban life, residents must efficiently manage a vast amount of schedules and tasks, and coordinating community events with personal schedules is particularly difficult. A system is needed to address this situation, reduce the burden on residents, and efficiently manage and update information. 【0510】 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. 【0511】 In this invention, the server includes means for acquiring schedule information, means for analyzing the schedule information to predict tasks, and means for organizing and managing community event information. This enables residents to seamlessly manage their personal schedules and community events and process information efficiently. 【0512】 "Schedule information acquisition means" refers to a technology for collecting user schedule data, and is a system configuration that acquires information based on time. 【0513】 A "task prediction method" is a process that analyzes collected schedule information and predicts the tasks that should be performed. 【0514】 "Automatic information generation means" refers to technology for automatically creating necessary relevant information based on predicted tasks. 【0515】 "Information automation process monitoring means" refers to technology that constantly monitors the progress of automated information processing and identifies the occurrence of errors. 【0516】 An "error correction method" is a method for identifying the cause of a detected error and formulating and applying corrective measures. 【0517】 "Notification provision means" refers to communication technology used to inform users of generated information and modifications. 【0518】 A "means for organizing and managing information on community events" refers to a mechanism for systematically organizing and managing data related to social events in a specific region. 【0519】 "Feedback recording and performance improvement methods" refer to technologies that collect user feedback and opinions and use them to improve the system. 【0520】 To implement this invention, a server, terminal, and user are used as the basic system configuration. The server utilizes a common calendar API as a scheduling information communication technology to obtain the user's schedule information. The server, which runs on Google Cloud Platform, analyzes the collected schedule information using natural language processing technology and predicts tasks related to each user. 【0521】 Based on the analysis results, the server automatically generates information using a generative AI model. The generated information includes materials related to local community events and information necessary for specific tasks. The generative AI model has the ability to design the necessary content based on universal prompt statements. 【0522】 The terminal functions as an interface that receives notifications from the server and provides the user with generated information and error corrections. Users can view and edit information through the terminal, managing their own schedules and community events. 【0523】 The server also monitors the automated information process and, if an error is detected, analyzes the log data to identify the cause of the error. For detected errors, it automatically applies corrective measures using available tools and quickly updates the information. This process utilizes machine learning frameworks such as TensorFlow. 【0524】 As a concrete example, when a user enters "community cleanup activity" into their calendar, the server uses an AI model to automatically generate activity information, past activity data, and a list of necessary preparations based on that information. This information is then notified to the user's device, allowing them to check the details. 【0525】 As an example of a prompt for the generative AI model, we will use the following format: "Please prepare documentation for the following task: Community cleanup activity. Include a summary of the previous activity and areas for improvement." 【0526】 The flow of a specific process in Application Example 1 will be explained using Figure 12. 【0527】 Step 1: 【0528】 The server retrieves calendar information from the user's terminal via the internet. The input is the appointment information registered by the user on their terminal, and the output is a dataset containing that information. This data includes the appointment title, date, time, etc. 【0529】 Step 2: 【0530】 The server analyzes the acquired schedule information using natural language processing techniques. The input is the dataset obtained in step 1, and the output is the type and urgency of the analyzed tasks. This reveals the task priorities. The server performs this analysis to identify important events and decide on actions based on them. 【0531】 Step 3: 【0532】 The server inputs prompt messages into the generation AI model, which automatically generates the necessary information. The input consists of analyzed task information and prompt messages, while the output is the generated documents and information. For example, based on a prompt requesting detailed information about a local event, the server generates event-related documents. This prepares the system for handling the request. 【0533】 Step 4: 【0534】 The server sends the generated information to the terminal in a usable format and notifies the user. The input is the generated information, and the output is the notification to the user's terminal. The server composes and sends the notification, and the user can access, review, and edit the information via their terminal. 【0535】 Step 5: 【0536】 The server monitors the automated information process and analyzes logs to identify the cause of any errors. The input is the log data from the automated process, and the output is the identified error and its cause. Based on this analysis, the server uses a machine learning framework to generate corrective actions. 【0537】 Step 6: 【0538】 The server applies the fix and updates the information. The input is the fix and existing information, and the output is the corrected information. The server automatically implements the fix, minimizing the impact on users. 【0539】 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. 【0540】 This invention relates to a task automation system that takes into account the user's emotional state. The system consists of a server, a terminal, and a user interface, and incorporates an emotion engine. This emotion engine recognizes the user's emotions in real time and dynamically adjusts task priorities, content, and format accordingly. An embodiment thereof is shown below. 【0541】 Collection of emotional data 【0542】 The server monitors user input and everyday interactions through an emotion engine, collecting emotional data. This data is acquired in various formats, including text, voice, and facial expressions. 【0543】 Emotional analysis 【0544】 The server analyzes the collected emotional data to identify emotional states such as positive, negative, and neutral. This analysis utilizes machine learning algorithms to continuously improve the accuracy of emotion recognition. 【0545】 Adjusting task priorities 【0546】 The server dynamically adjusts task priorities based on the user's emotional state. For example, if the user is stressed, the system will prioritize easier tasks. 【0547】 Automatic content generation and adjustment 【0548】 The server adjusts the content and presentation based on the results of sentiment analysis. For example, if a user is experiencing positive emotions, it will focus on providing content related to challenging tasks. 【0549】 Notifications and Interface 【0550】 The device notifies the user of tailored tasks and content. The user selects from the provided options and completes the tasks through the device. They can also provide feedback on their experience. 【0551】 Feedback and Learning 【0552】 The server incorporates user feedback into its emotion recognition engine, using it as training data to further improve its accuracy. This enables personalized support over time. 【0553】 Specific example 【0554】 Suppose a user inputs a message via their device stating that "the project deadline is approaching." The emotion engine detects the user's stress level based on their input style and related history. The server determines the urgency of the tasks, prioritizes and lists the essential tasks, and notifies the user via their device. Once the user has calmed down, it notifies them of more important tasks and adjusts the overall process to ensure efficient progress. This process allows the user to work smoothly while reducing their burden. 【0555】 The following describes the processing flow. 【0556】 Step 1: 【0557】 The server collects input data from the user's terminal in real time. During this process, it transfers various data formats, such as text messages, voice commands, and input speed, to the emotion engine. 【0558】 Step 2: 【0559】 The server analyzes the collected data using an emotion engine to identify the user's emotional state. For example, the emotion engine determines whether the user is stressed or relaxed based on their textual expressions and voice tone. 【0560】 Step 3: 【0561】 The server re-evaluates the user's current task priorities based on their emotional state. If the user is stressed, it prioritizes less burdensome tasks; if they are in a positive state, it recommends more important tasks. 【0562】 Step 4: 【0563】 The server automatically generates content tailored to the user's emotional state. For example, it provides positive users with materials that encourage proactive behavior, and stressed users with content that promotes relaxation. 【0564】 Step 5: 【0565】 The server notifies the user's device of the generated task list and content. The device then displays these to the user and prompts them to select the tasks to perform and the content to use. 【0566】 Step 6: 【0567】 Users review the task list provided through their device and select tasks that suit them. They then perform the tasks, referring to the provided content as needed. 【0568】 Step 7: 【0569】 Users provide feedback after completing a task or during the process. The device then forwards this feedback to a server, which is used to improve the accuracy of sentiment recognition in the future. 【0570】 Step 8: 【0571】 The server updates its emotion recognition model based on the collected feedback, focusing on improving the accuracy of future analyses and personalization capabilities. This learning process is continuous. 【0572】 (Example 2) 【0573】 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." 【0574】 Traditional task management systems present tasks without considering the user's emotional state, leading to problems such as stress and decreased efficiency. Furthermore, they lack dynamic task adjustment features that respond to user emotions, resulting in insufficient personalized support. 【0575】 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. 【0576】 In this invention, the server includes means for collecting user emotional information, means for analyzing the collected emotional information to identify the emotional state, and means for dynamically adjusting task priorities based on the identified emotional state. This enables task management according to the user's emotional state, allowing for optimal task progress for each individual user. 【0577】 "User emotional information" refers to data that indicates the user's emotional state, extracted from the user's text input, voice, and facial expressions. 【0578】 "Emotional state" refers to the classification of emotions, such as positive, negative, and neutral, obtained from analyzing the user's emotional information. 【0579】 "Dynamically adjusting task priorities" is a process that changes the order in which tasks are executed in real time based on the user's emotional state. 【0580】 "Automatically generating and adjusting content" refers to automatically creating and optimizing the content and format of the information provided based on the emotional state. 【0581】 "Means of notification" refers to methods or devices for communicating coordinated tasks or content to a user, often via electronic devices. 【0582】 "Improving emotion recognition accuracy based on feedback" is a process that uses user responses to improve the emotional state recognition algorithm, enabling more accurate analysis. 【0583】 This invention relates to a system that automates tasks while taking into account the user's emotional state. The system consists of a server, a terminal, and a user interface. A key component is the emotion engine, which is used to process the user's emotional information in real time. 【0584】 Hardware and software configuration 【0585】 The server functions as the primary component, powering the emotion engine. The emotion engine includes software modules that execute machine learning algorithms, enabling the analysis of collected emotion information. Required hardware includes high-speed processing units and large-capacity storage. For analysis, for example, speech recognition software and text analysis libraries are used. The terminal functions as a communication interface, managing user interaction. 【0586】 Data processing and calculations 【0587】 The server monitors everyday user interactions and collects sentiment information based on them. Text, voice, and facial expression data are treated as primary sources of sentiment information. The sentiment engine receives this information as input and identifies emotional states through machine learning algorithms. Based on these results, tasks are prioritized and optimal content is automatically generated. 【0588】 Specific example 【0589】 For example, if a user inputs "The project deadline is approaching" on their terminal, the emotion engine analyzes the input content and related information such as input speed. The server uses this analysis to identify emotional states indicating stress. It then selects high-priority tasks and effectively notifies the user. An example of a prompt used in this process is, "Evaluate the user's emotional state based on the new data and generate a list of optimal tasks." 【0590】 This allows users to receive optimal task management tailored to their individual emotional state, enabling them to perform their work efficiently while reducing stress. 【0591】 The flow of the specific processing in Example 2 will be explained using Figure 13. 【0592】 Step 1: 【0593】 The server collects user emotion information. Input consists of text, voice, and facial expression data provided by the user through their device. This data is acquired and sent to the emotion engine. A specific example of this operation is recording and collecting information about the speed at which the user types characters on the keyboard. 【0594】 Step 2: 【0595】 The server analyzes emotional information using an emotion engine. In this step, the collected data is used as input, and a machine learning algorithm is used to identify the emotional state. As part of the data processing, pitch and tone are extracted from the audio, and keywords for emotion analysis are extracted from the text. Specifically, the operation involves identifying indicators of negative emotions from the user's voice data. 【0596】 Step 3: 【0597】 The server dynamically adjusts task priorities based on the analysis results. It determines which tasks should be prioritized based on the output of emotional states and updates the task list. The input is identified emotional states, which are used to change the order of tasks. Specifically, if an emotion indicating stress is detected, the display order in the task management system is changed. 【0598】 Step 4: 【0599】 The server automatically generates and adjusts content based on the adjusted tasks. The input for this step is specific emotional states and adjusted task information, while the output is user-specific content. A concrete example of this operation is generating information about a new project to take on when a positive emotional state is detected. 【0600】 Step 5: 【0601】 The terminal notifies the user of the adjusted tasks and content sent from the server. It receives information from the server as input and presents it to the user as output. Specifically, it may display a task list on the screen along with a notification sound. 【0602】 Step 6: 【0603】 Users select tasks and provide feedback through their terminals. This feedback is collected to improve the system's emotion recognition accuracy and sent to the server as input. Specifically, the system may evaluate whether the user was satisfied with the order of the presented tasks and send a short message stating the result. 【0604】 (Application Example 2) 【0605】 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." 【0606】 In modern retail settings, there is a demand for services that cater to the diverse emotional states of customers, but there is a lack of means to quickly provide appropriate customer service. This results in uniform service that disregards customer emotions, hindering improvements in customer satisfaction. Furthermore, it increases the burden on employees and presents challenges in providing efficient customer service. 【0607】 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. 【0608】 In this invention, the server includes means for acquiring schedule information, means for recognizing the user's emotional state, and means for dynamically adjusting the priority of activities based on emotional data. This enables personalized customer service and product recommendations that respond to the customer's emotions. 【0609】 "Schedule information" refers to data related to the user's planned activities and schedule, including information about events and appointments that have been registered in advance. 【0610】 An "activity" refers to the tasks or work that a user should perform, encompassing everyday tasks and errands. 【0611】 "Emotional state" refers to information about the user's current feelings and mood, and includes emotional classifications such as positive, negative, and neutral. 【0612】 "Product and service recommendations" refer to recommendations for specific products or services provided to users based on their emotional state, and involve presenting the optimal choice that aligns with the user's feelings. 【0613】 "Business process automation procedures" refer to methods and flows of automating various processes through programs in order to efficiently carry out user activities. 【0614】 "Historical data" refers to records of past activities and processes, which are used for system learning and analysis. 【0615】 This invention is a system for providing personalized services that take into account the emotional state of the user, and is particularly intended to suggest products and services that are appropriate to the customer's emotions in real time, especially in a retail setting. This system consists of a server, terminals, and devices worn by employees. 【0616】 The server acquires scheduled information and activity-related data, and uses an emotion recognition engine to recognize the user's emotional state. This emotion recognition utilizes machine learning models such as TensorFlow and PyTorch. For example, it analyzes audio data and facial expression data acquired by devices such as smart glasses to determine the user's emotions. This allows for dynamic adjustment of activity priorities based on the emotional data. 【0617】 The terminal provides store employees with specific product suggestions and services based on information sent from the server. This includes suggestions optimized for the customer's emotional state. For example, if a customer is feeling stressed, recommending products with relaxing effects can improve customer satisfaction. 【0618】 Users, i.e., store employees, receive real-time information through smart glasses they wear and immediately suggest appropriate products and services to customers. This process is monitored and corrected in a timely manner by error detection mechanisms to ensure that accurate information and services are provided. 【0619】 A concrete example of implementing this invention is a system in which an employee reads a customer's mood and sends a prompt to a generating AI model, for example, "What products or services can be offered to a customer who wants to relax?", to obtain suggestions. The suggestions generated using this prompt are displayed on a terminal, and appropriate services are provided on the spot. 【0620】 The flow of a specific process in Application Example 2 will be explained using Figure 14. 【0621】 Step 1: 【0622】 The server obtains basic appointment information and activity-related data from customers via the terminal. This input data includes customer reservation information and past purchase history. Based on this data, the server generates a basic profile of the customer. This profile forms the basis for providing personalized services. 【0623】 Step 2: 【0624】 The device or smart glasses capture the voice and facial expressions of customers in real time and send them to the server. The input data mainly consists of camera footage and audio data from the microphone. The server analyzes this data using a machine learning model to determine the customer's emotional state. The output is categorized as positive, negative, or neutral. 【0625】 Step 3: 【0626】 The server dynamically readjusts the priorities of existing tasks based on the analyzed emotional state. The input data consists of the profile obtained in Step 1 and the emotional categories from Step 2. As part of the data processing, a priority list is generated based on the urgency of the tasks and the customer's state, and an optimized task list is created as the output. 【0627】 Step 4: 【0628】 The server generates product and service suggestions based on the customer's emotional state and priority task list. This process uses a generation AI model to suggest products and services best suited to the customer's current situation. Based on the input data, a list of suggested products is output and provided to employees via their terminals. 【0629】 Step 5: 【0630】 Users (employees) review product suggestions provided by the server via the terminal's display or smart glasses, and then provide specific customer service. The input data is suggestion information from the server, and the resulting output is the actual service provided to the customer. This service provision contributes to improving customer satisfaction. 【0631】 Step 6: 【0632】 The terminal sends user feedback and service results to the server, recording them as data to improve system performance. The input data is post-service feedback information; the server uses this information as training data to improve the accuracy of future suggestions. The output is the improved service algorithm. 【0633】 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. 【0634】 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. 【0635】 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. 【0636】 [Fourth Embodiment] 【0637】 Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment. 【0638】 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. 【0639】 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). 【0640】 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. 【0641】 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. 【0642】 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). 【0643】 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. 【0644】 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. 【0645】 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. 【0646】 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. 【0647】 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. 【0648】 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. 【0649】 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". 【0650】 This invention is a system that efficiently automates tasks and supports business operations by exchanging information between servers, terminals, and users. This system mainly consists of the following components: 【0651】 Data acquisition and analysis 【0652】 The server uses the Google Calendar API and other services via a scheduling information network to retrieve user schedule information. The retrieved schedule information includes title, date and time, and details. The server analyzes this information using natural language processing technology to predict the type and urgency of the task. 【0653】 Automatic content generation 【0654】 The server generates the necessary content based on the analyzed task information. This process can automatically create relevant documents such as meeting materials, presentations, and reports using AI. For example, if a meeting is scheduled, it can generate new meeting materials from past agendas and participant lists. 【0655】 Error monitoring and correction 【0656】 The server continuously monitors the automated business process, detecting errors and analyzing logs. If an error occurs, the server uses machine learning algorithms to identify the cause and generate corrective solutions. The corrected code is automatically reapplied, minimizing disruption to the business process. 【0657】 User notifications and interface 【0658】 The device displays notifications from the server to the user, including links to generated content and error reports. The user can review the content provided through the device and make any necessary edits or approvals. 【0659】 Feedback loop 【0660】 User feedback is crucial, and the server collects this information to improve the accuracy of future task predictions and content generation. This allows the system to continuously improve and evolve to better meet user needs. 【0661】 Specific example 【0662】 For example, suppose a user enters a "project review meeting" into their device's calendar. The server uses this information to reference the participants' attendance history and past meeting records, and automatically generates new meeting materials. The generated materials include the project's progress and the goals for the next meeting, and the user can review the content on their device. This cycle is continuous, creating an environment where the user can focus on more important decision-making. 【0663】 The following describes the processing flow. 【0664】 Step 1: 【0665】 The server accesses the Google Calendar API via a scheduling information network at regular intervals to retrieve all of the user's appointments. This includes collecting appointment data such as title, date and time, and detailed description. 【0666】 Step 2: 【0667】 The server analyzes the acquired schedule information using natural language processing (NLP). This analysis identifies the type of task, its importance, the urgency of its deadline, and other factors, and then determines its priority. 【0668】 Step 3: 【0669】 The server automatically generates relevant content based on the analysis results. For example, for a meeting schedule, it creates meeting materials, agendas, and topic lists, and generates other documents as needed using AI. 【0670】 Step 4: 【0671】 The server monitors business automation processes and detects errors in real time that occur during the execution of RPA and other processes. It analyzes log data and applies algorithms to identify the cause of the errors. 【0672】 Step 5: 【0673】 The server automatically generates a suggested fix based on the identified error cause and applies it to the code. It then reruns the corrected process and verifies that it is working correctly. 【0674】 Step 6: 【0675】 The device displays notifications to the user regarding generated content and modified tasks received from the server. These notifications include links and related information. 【0676】 Step 7: 【0677】 Users view notifications on their devices and select or edit the appropriate content provided. After approval, they can enter additional instructions or feedback as needed. 【0678】 Step 8: 【0679】 The server records user feedback and stores it in a database. This information is used for learning to improve the accuracy of future task predictions and content generation. 【0680】 (Example 1) 【0681】 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". 【0682】 In today's information society, schedule management and business process automation are crucial challenges. However, conventional systems have limitations in efficiently predicting individual tasks and automatically generating appropriate information resources. Furthermore, the rapid detection and correction of errors in business automation processes are insufficient, leading to a decrease in the overall efficiency of the system. 【0683】 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. 【0684】 In this invention, the server includes means for acquiring schedule information via an external information system, means for analyzing the acquired schedule information using language information processing technology to predict the type of activity and its priority, and means for automatically generating related information resources using a generative information processing model based on the predicted activities. This makes it possible to streamline schedule management and automate business processes with high accuracy. 【0685】 "Schedule information" refers to data about the user's planned activities, obtained through external information systems. 【0686】 "Language information processing technology" is a technique that analyzes natural language and processes information empirically, and is mainly used for task classification and priority prediction. 【0687】 A "generative information processing model" refers to an algorithm or system that automatically generates related information resources based on given information. 【0688】 "Activity type" refers to the category of a specific action or task, classified based on the analysis of planned information. 【0689】 "Priority" is an indicator that shows the degree of importance or urgency of a schedule or task. 【0690】 "Information resources" refers to digital content related to work and activities, such as automatically generated documents, materials, and reports. 【0691】 "Error detection methods" refer to technologies and methods for identifying errors in business automation processes and analyzing their causes. 【0692】 A "proposal for correction" refers to a proposed improvement or restructuring method to address the cause of an error identified by an error detection method. 【0693】 This invention is an advanced business automation system that acquires schedule information and generates related information resources through analysis. The server uses a general information communication interface to acquire user schedule information from external information systems. For example, it is possible to acquire schedule information using a calendar API. 【0694】 The server applies natural language processing techniques to the acquired schedule information. This technique utilizes natural language processing libraries (such as Python's NLTK or spaCy) to analyze the information, determining the type of activity and its priority. This allows for the determination of the urgency and importance of tasks. 【0695】 Based on the analysis results, the server utilizes a generative information processing model to automatically generate relevant information resources. This process can use a generative AI model (for example, a currently available natural language generation model) to generate necessary meeting materials and reports. For example, if you want to create materials for a "project review meeting," the server sends the following prompt to the generative AI model: "Please create materials for the project review meeting. Refer to past data and include the latest progress and goals for the next meeting." 【0696】 The terminal notifies the user of information resources generated from the server. This includes links to created documents and error reports. The user can use the terminal to review this information and edit or approve it as needed. 【0697】 Furthermore, the server monitors the entire business automation process, and if an error is detected, it analyzes the cause and generates a corrective solution. This process utilizes machine learning algorithms, and the server automatically incorporates the results into the activity process. 【0698】 Finally, users provide data to the server for further improvement through post-use feedback. This feedback is used to improve the system's accuracy and adapt to user needs, leading to continuous system improvement. 【0699】 The flow of the specific processing in Example 1 will be explained using Figure 11. 【0700】 Step 1: 【0701】 The server retrieves user schedule information from an external information system. Specifically, it uses an API for schedule management to obtain data such as the title, date and time, and details of appointments entered by the user in JSON format. This input data enables analysis in the next step. 【0702】 Step 2: 【0703】 The server analyzes the acquired schedule information. Using natural language processing technology and a natural language processing library (for example, spaCy in Python), it classifies the schedule information into activity types and priorities. Through this process, it determines the type and urgency of tasks from the acquired schedule information and outputs structured data. 【0704】 Step 3: 【0705】 The server automatically generates relevant information resources based on the analyzed data. A prompt is input to the information generation processing model (e.g., an AI-based natural language generation model), for example, to request the creation of meeting materials. This prompt might include instructions such as, "Please create materials for the project review meeting. Refer to past data and include the latest progress and goals for the next meeting." The generated materials are then output. 【0706】 Step 4: 【0707】 The server sends the generated information resources to the terminal. The terminal receives them and notifies the user. This includes a download link for the generated materials and any related error reports. The user can review the contents of the materials on the terminal and edit or approve them as needed. 【0708】 Step 5: 【0709】 The server monitors the automated business process and detects errors. It analyzes log data and uses statistical algorithms to identify the root cause of errors. For detected errors, it generates corrective solutions and automates the response process. This process results in a business process with fewer errors. 【0710】 Step 6: 【0711】 Users send feedback on the services provided to the server. This data is used to improve the system's accuracy. Specifically, by retraining the machine learning model based on the feedback data, the accuracy of subsequent generation can be improved. 【0712】 (Application Example 1) 【0713】 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". 【0714】 In modern urban life, residents must efficiently manage a vast amount of schedules and tasks, and coordinating community events with personal schedules is particularly difficult. A system is needed to address this situation, reduce the burden on residents, and efficiently manage and update information. 【0715】 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. 【0716】 In this invention, the server includes means for acquiring schedule information, means for analyzing the schedule information to predict tasks, and means for organizing and managing community event information. This enables residents to seamlessly manage their personal schedules and community events and process information efficiently. 【0717】 "Schedule information acquisition means" refers to a technology for collecting user schedule data, and is a system configuration that acquires information based on time. 【0718】 A "task prediction method" is a process that analyzes collected schedule information and predicts the tasks that should be performed. 【0719】 "Automatic information generation means" refers to technology for automatically creating necessary relevant information based on predicted tasks. 【0720】 "Information automation process monitoring means" refers to technology that constantly monitors the progress of automated information processing and identifies the occurrence of errors. 【0721】 An "error correction method" is a method for identifying the cause of a detected error and formulating and applying corrective measures. 【0722】 "Notification provision means" refers to communication technology used to inform users of generated information and modifications. 【0723】 A "means for organizing and managing information on community events" refers to a mechanism for systematically organizing and managing data related to social events in a specific region. 【0724】 "Feedback recording and performance improvement methods" refer to technologies that collect user feedback and opinions and use them to improve the system. 【0725】 To implement this invention, a server, terminal, and user are used as the basic system configuration. The server utilizes a common calendar API as a scheduling information communication technology to obtain the user's schedule information. The server, which runs on Google Cloud Platform, analyzes the collected schedule information using natural language processing technology and predicts tasks related to each user. 【0726】 Based on the analysis results, the server automatically generates information using a generative AI model. The generated information includes materials related to local community events and information necessary for specific tasks. The generative AI model has the ability to design the necessary content based on universal prompt statements. 【0727】 The terminal functions as an interface that receives notifications from the server and provides the user with generated information and error corrections. Users can view and edit information through the terminal, managing their own schedules and community events. 【0728】 The server also monitors the automated information process and, if an error is detected, analyzes the log data to identify the cause of the error. For detected errors, it automatically applies corrective measures using available tools and quickly updates the information. This process utilizes machine learning frameworks such as TensorFlow. 【0729】 As a concrete example, when a user enters "community cleanup activity" into their calendar, the server uses an AI model to automatically generate activity information, past activity data, and a list of necessary preparations based on that information. This information is then notified to the user's device, allowing them to check the details. 【0730】 As an example of a prompt for the generative AI model, we will use the following format: "Please prepare documentation for the following task: Community cleanup activity. Include a summary of the previous activity and areas for improvement." 【0731】 The flow of a specific process in Application Example 1 will be explained using Figure 12. 【0732】 Step 1: 【0733】 The server retrieves calendar information from the user's terminal via the internet. The input is the appointment information registered by the user on their terminal, and the output is a dataset containing that information. This data includes the appointment title, date, time, etc. 【0734】 Step 2: 【0735】 The server analyzes the acquired schedule information using natural language processing techniques. The input is the dataset obtained in step 1, and the output is the type and urgency of the analyzed tasks. This reveals the task priorities. The server performs this analysis to identify important events and decide on actions based on them. 【0736】 Step 3: 【0737】 The server inputs prompt messages into the generation AI model, which automatically generates the necessary information. The input consists of analyzed task information and prompt messages, while the output is the generated documents and information. For example, based on a prompt requesting detailed information about a local event, the server generates event-related documents. This prepares the system for handling the request. 【0738】 Step 4: 【0739】 The server sends the generated information to the terminal in a usable format and notifies the user. The input is the generated information, and the output is the notification to the user's terminal. The server composes and sends the notification, and the user can access, review, and edit the information via their terminal. 【0740】 Step 5: 【0741】 The server monitors the automated information process and analyzes logs to identify the cause of any errors. The input is the log data from the automated process, and the output is the identified error and its cause. Based on this analysis, the server uses a machine learning framework to generate corrective actions. 【0742】 Step 6: 【0743】 The server applies the fix and updates the information. The input is the fix and existing information, and the output is the corrected information. The server automatically implements the fix, minimizing the impact on users. 【0744】 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. 【0745】 This invention relates to a task automation system that takes into account the user's emotional state. The system consists of a server, a terminal, and a user interface, and incorporates an emotion engine. This emotion engine recognizes the user's emotions in real time and dynamically adjusts task priorities, content, and format accordingly. An embodiment thereof is shown below. 【0746】 Collection of emotional data 【0747】 The server monitors user input and everyday interactions through an emotion engine, collecting emotional data. This data is acquired in various formats, including text, voice, and facial expressions. 【0748】 Emotional analysis 【0749】 The server analyzes the collected emotional data to identify emotional states such as positive, negative, and neutral. This analysis utilizes machine learning algorithms to continuously improve the accuracy of emotion recognition. 【0750】 Adjusting task priorities 【0751】 The server dynamically adjusts task priorities based on the user's emotional state. For example, if the user is stressed, the system will prioritize easier tasks. 【0752】 Automatic content generation and adjustment 【0753】 The server adjusts the content and presentation based on the results of sentiment analysis. For example, if a user is experiencing positive emotions, it will focus on providing content related to challenging tasks. 【0754】 Notifications and Interface 【0755】 The device notifies the user of tailored tasks and content. The user selects from the provided options and completes the tasks through the device. They can also provide feedback on their experience. 【0756】 Feedback and Learning 【0757】 The server incorporates user feedback into its emotion recognition engine, using it as training data to further improve its accuracy. This enables personalized support over time. 【0758】 Specific example 【0759】 Suppose a user inputs a message via their device stating that "the project deadline is approaching." The emotion engine detects the user's stress level based on their input style and related history. The server determines the urgency of the tasks, prioritizes and lists the essential tasks, and notifies the user via their device. Once the user has calmed down, it notifies them of more important tasks and adjusts the overall process to ensure efficient progress. This process allows the user to work smoothly while reducing their burden. 【0760】 The following describes the processing flow. 【0761】 Step 1: 【0762】 The server collects input data from the user's terminal in real time. During this process, it transfers various data formats, such as text messages, voice commands, and input speed, to the emotion engine. 【0763】 Step 2: 【0764】 The server analyzes the collected data using an emotion engine to identify the user's emotional state. For example, the emotion engine determines whether the user is stressed or relaxed based on their textual expressions and voice tone. 【0765】 Step 3: 【0766】 The server re-evaluates the user's current task priorities based on their emotional state. If the user is stressed, it prioritizes less burdensome tasks; if they are in a positive state, it recommends more important tasks. 【0767】 Step 4: 【0768】 The server automatically generates content tailored to the user's emotional state. For example, it provides positive users with materials that encourage proactive behavior, and stressed users with content that promotes relaxation. 【0769】 Step 5: 【0770】 The server notifies the user's device of the generated task list and content. The device then displays these to the user and prompts them to select the tasks to perform and the content to use. 【0771】 Step 6: 【0772】 Users review the task list provided through their device and select tasks that suit them. They then perform the tasks, referring to the provided content as needed. 【0773】 Step 7: 【0774】 Users provide feedback after completing a task or during the process. The device then forwards this feedback to a server, which is used to improve the accuracy of sentiment recognition in the future. 【0775】 Step 8: 【0776】 The server updates its emotion recognition model based on the collected feedback, focusing on improving the accuracy of future analyses and personalization capabilities. This learning process is continuous. 【0777】 (Example 2) 【0778】 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". 【0779】 Traditional task management systems present tasks without considering the user's emotional state, leading to problems such as stress and decreased efficiency. Furthermore, they lack dynamic task adjustment features that respond to user emotions, resulting in insufficient personalized support. 【0780】 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. 【0781】 In this invention, the server includes means for collecting user emotional information, means for analyzing the collected emotional information to identify the emotional state, and means for dynamically adjusting task priorities based on the identified emotional state. This enables task management according to the user's emotional state, allowing for optimal task progress for each individual user. 【0782】 "User emotional information" refers to data that indicates the user's emotional state, extracted from the user's text input, voice, and facial expressions. 【0783】 "Emotional state" refers to the classification of emotions, such as positive, negative, and neutral, obtained from analyzing the user's emotional information. 【0784】 "Dynamically adjusting task priorities" is a process that changes the order in which tasks are executed in real time based on the user's emotional state. 【0785】 "Automatically generating and adjusting content" refers to automatically creating and optimizing the content and format of the information provided based on the emotional state. 【0786】 "Means of notification" refers to methods or devices for communicating coordinated tasks or content to a user, often via electronic devices. 【0787】 "Improving emotion recognition accuracy based on feedback" is a process that uses user responses to improve the emotional state recognition algorithm, enabling more accurate analysis. 【0788】 This invention relates to a system that automates tasks while taking into account the user's emotional state. The system consists of a server, a terminal, and a user interface. A key component is the emotion engine, which is used to process the user's emotional information in real time. 【0789】 Hardware and software configuration 【0790】 The server functions as the primary component, powering the emotion engine. The emotion engine includes software modules that execute machine learning algorithms, enabling the analysis of collected emotion information. Required hardware includes high-speed processing units and large-capacity storage. For analysis, for example, speech recognition software and text analysis libraries are used. The terminal functions as a communication interface, managing user interaction. 【0791】 Data processing and calculations 【0792】 The server monitors everyday user interactions and collects sentiment information based on them. Text, voice, and facial expression data are treated as primary sources of sentiment information. The sentiment engine receives this information as input and identifies emotional states through machine learning algorithms. Based on these results, tasks are prioritized and optimal content is automatically generated. 【0793】 Specific example 【0794】 For example, if a user inputs "The project deadline is approaching" on their terminal, the emotion engine analyzes the input content and related information such as input speed. The server uses this analysis to identify emotional states indicating stress. It then selects high-priority tasks and effectively notifies the user. An example of a prompt used in this process is, "Evaluate the user's emotional state based on the new data and generate a list of optimal tasks." 【0795】 This allows users to receive optimal task management tailored to their individual emotional state, enabling them to perform their work efficiently while reducing stress. 【0796】 The flow of the specific processing in Example 2 will be explained using Figure 13. 【0797】 Step 1: 【0798】 The server collects user emotion information. Input consists of text, voice, and facial expression data provided by the user through their device. This data is acquired and sent to the emotion engine. A specific example of this operation is recording and collecting information about the speed at which the user types characters on the keyboard. 【0799】 Step 2: 【0800】 The server analyzes emotional information using an emotion engine. In this step, the collected data is used as input, and a machine learning algorithm is used to identify the emotional state. As part of the data processing, pitch and tone are extracted from the audio, and keywords for emotion analysis are extracted from the text. Specifically, the operation involves identifying indicators of negative emotions from the user's voice data. 【0801】 Step 3: 【0802】 The server dynamically adjusts task priorities based on the analysis results. It determines which tasks should be prioritized based on the output of emotional states and updates the task list. The input is identified emotional states, which are used to change the order of tasks. Specifically, if an emotion indicating stress is detected, the display order in the task management system is changed. 【0803】 Step 4: 【0804】 The server automatically generates and adjusts content based on the adjusted tasks. The input for this step is specific emotional states and adjusted task information, while the output is user-specific content. A concrete example of this operation is generating information about a new project to take on when a positive emotional state is detected. 【0805】 Step 5: 【0806】 The terminal notifies the user of the adjusted tasks and content sent from the server. It receives information from the server as input and presents it to the user as output. Specifically, it may display a task list on the screen along with a notification sound. 【0807】 Step 6: 【0808】 Users select tasks and provide feedback through their terminals. This feedback is collected to improve the system's emotion recognition accuracy and sent to the server as input. Specifically, the system may evaluate whether the user was satisfied with the order of the presented tasks and send a short message stating the result. 【0809】 (Application Example 2) 【0810】 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". 【0811】 In modern retail settings, there is a demand for services that cater to the diverse emotional states of customers, but there is a lack of means to quickly provide appropriate customer service. This results in uniform service that disregards customer emotions, hindering improvements in customer satisfaction. Furthermore, it increases the burden on employees and presents challenges in providing efficient customer service. 【0812】 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. 【0813】 In this invention, the server includes means for acquiring schedule information, means for recognizing the user's emotional state, and means for dynamically adjusting the priority of activities based on emotional data. This enables personalized customer service and product recommendations that respond to the customer's emotions. 【0814】 "Schedule information" refers to data related to the user's planned activities and schedule, including information about events and appointments that have been registered in advance. 【0815】 An "activity" refers to the tasks or work that a user should perform, encompassing everyday tasks and errands. 【0816】 "Emotional state" refers to information about the user's current feelings and mood, and includes emotional classifications such as positive, negative, and neutral. 【0817】 "Product and service recommendations" refer to recommendations for specific products or services provided to users based on their emotional state, and involve presenting the optimal choice that aligns with the user's feelings. 【0818】 "Business process automation procedures" refer to methods and flows of automating various processes through programs in order to efficiently carry out user activities. 【0819】 "Historical data" refers to records of past activities and processes, which are used for system learning and analysis. 【0820】 This invention is a system for providing personalized services that take into account the emotional state of the user, and is particularly intended to suggest products and services that are appropriate to the customer's emotions in real time, especially in a retail setting. This system consists of a server, terminals, and devices worn by employees. 【0821】 The server acquires scheduled information and activity-related data, and uses an emotion recognition engine to recognize the user's emotional state. This emotion recognition utilizes machine learning models such as TensorFlow and PyTorch. For example, it analyzes audio data and facial expression data acquired by devices such as smart glasses to determine the user's emotions. This allows for dynamic adjustment of activity priorities based on the emotional data. 【0822】 The terminal provides store employees with specific product suggestions and services based on information sent from the server. This includes suggestions optimized for the customer's emotional state. For example, if a customer is feeling stressed, recommending products with relaxing effects can improve customer satisfaction. 【0823】 Users, i.e., store employees, receive real-time information through smart glasses they wear and immediately suggest appropriate products and services to customers. This process is monitored and corrected in a timely manner by error detection mechanisms to ensure that accurate information and services are provided. 【0824】 A concrete example of implementing this invention is a system in which an employee reads a customer's mood and sends a prompt to a generating AI model, for example, "What products or services can be offered to a customer who wants to relax?", to obtain suggestions. The suggestions generated using this prompt are displayed on a terminal, and appropriate services are provided on the spot. 【0825】 The flow of a specific process in Application Example 2 will be explained using Figure 14. 【0826】 Step 1: 【0827】 The server obtains basic appointment information and activity-related data from customers via the terminal. This input data includes customer reservation information and past purchase history. Based on this data, the server generates a basic profile of the customer. This profile forms the basis for providing personalized services. 【0828】 Step 2: 【0829】 The device or smart glasses capture the voice and facial expressions of customers in real time and send them to the server. The input data mainly consists of camera footage and audio data from the microphone. The server analyzes this data using a machine learning model to determine the customer's emotional state. The output is categorized as positive, negative, or neutral. 【0830】 Step 3: 【0831】 The server dynamically readjusts the priorities of existing tasks based on the analyzed emotional state. The input data consists of the profile obtained in Step 1 and the emotional categories from Step 2. As part of the data processing, a priority list is generated based on the urgency of the tasks and the customer's state, and an optimized task list is created as the output. 【0832】 Step 4: 【0833】 The server generates product and service suggestions based on the customer's emotional state and priority task list. This process uses a generation AI model to suggest products and services best suited to the customer's current situation. Based on the input data, a list of suggested products is output and provided to employees via their terminals. 【0834】 Step 5: 【0835】 Users (employees) review product suggestions provided by the server via the terminal's display or smart glasses, and then provide specific customer service. The input data is suggestion information from the server, and the resulting output is the actual service provided to the customer. This service provision contributes to improving customer satisfaction. 【0836】 Step 6: 【0837】 The terminal sends user feedback and service results to the server, recording them as data to improve system performance. The input data is post-service feedback information; the server uses this information as training data to improve the accuracy of future suggestions. The output is the improved service algorithm. 【0838】 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. 【0839】 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. 【0840】 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. 【0841】 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. 【0842】 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. 【0843】 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. 【0844】 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. 【0845】 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. 【0846】 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." 【0847】 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. 【0848】 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. 【0849】 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. 【0850】 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. 【0851】 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. 【0852】 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. 【0853】 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. 【0854】 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. 【0855】 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. 【0856】 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. 【0857】 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. 【0858】 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. 【0859】 The following is further disclosed regarding the embodiments described above. 【0860】 (Claim 1) 【0861】 Means of obtaining schedule information, 【0862】 A means of analyzing scheduled information to predict tasks, 【0863】 A means of automatically generating content based on predicted tasks, 【0864】 A means of monitoring business automation processes and detecting, analyzing, and correcting errors, 【0865】 Means for providing notifications regarding generated content and modifications, 【0866】 A means of recording user selections and feedback to improve system performance, 【0867】 A system that includes this. 【0868】 (Claim 2) 【0869】 The system according to claim 1, characterized in that the means for obtaining user schedule information is to obtain the information based on time via a schedule information communication network. 【0870】 (Claim 3) 【0871】 The system according to claim 1, characterized in that the error detection means analyzes log data of business automation to identify the cause of the error, generates a proposed correction, and automatically applies it. 【0872】 "Example 1" 【0873】 (Claim 1) 【0874】 A means of obtaining schedule information via an external information system, 【0875】 A means for analyzing acquired schedule information using language information processing technology to predict the type of activity and its priority, 【0876】 A means for automatically generating relevant information resources using a generative information processing model based on predicted activities, 【0877】 A means to monitor the process of automating business procedures, detect errors, analyze information records to generate corrective suggestions, and automatically apply the results, 【0878】 A means of providing users with notifications regarding the generated information resources and modifications, 【0879】 A means of collecting user operations and feedback to improve the system's functionality, 【0880】 A system that includes this. 【0881】 (Claim 2) 【0882】 The system according to claim 1, characterized in that it obtains the user's schedule information based on time information via an external schedule information communication network. 【0883】 (Claim 3) 【0884】 The system according to claim 1, characterized in that the error detection means analyzes information records for automating business procedures to identify the cause of the error, generates a proposed correction, and automatically applies it. 【0885】 "Application Example 1" 【0886】 (Claim 1) 【0887】 Means of obtaining schedule information, 【0888】 A means of analyzing scheduled information to predict tasks, 【0889】 A means of automatically generating information based on predicted tasks, 【0890】 A means of monitoring information automation processes and detecting, analyzing, and correcting errors, 【0891】 Means for providing notifications regarding generated information and modifications, 【0892】 A means of organizing and managing community event information via an information processing device, 【0893】 A means of recording user selections and feedback to improve system performance, 【0894】 A system that includes this. 【0895】 (Claim 2) 【0896】 The system according to claim 1, characterized in that the means for obtaining user schedule information is to obtain the information based on time via schedule information communication technology. 【0897】 (Claim 3) 【0898】 The system according to claim 1, characterized in that the error detection means analyzes recorded data of information automation to identify the cause of the error, generates a proposed correction, and automatically implements it. 【0899】 "Example 2 of combining an emotion engine" 【0900】 (Claim 1) 【0901】 Means for collecting user sentiment information, 【0902】 A means of identifying emotional states by analyzing collected emotional information, 【0903】 A means of dynamically adjusting task priorities based on identified emotional states, 【0904】 A means for automatically generating and adjusting content according to emotional state, 【0905】 Means for notifying adjusted tasks and content, 【0906】 A means to improve the accuracy of emotion recognition based on user selections and feedback, 【0907】 A system that includes this. 【0908】 (Claim 2) 【0909】 The system according to claim 1, characterized in that it acquires the user's schedule information via schedule information communication and adjusts tasks by integrating it with emotional information. 【0910】 (Claim 3) 【0911】 The system according to claim 1, characterized by improving accuracy by analyzing feedback and retraining a machine learning model for emotion recognition. 【0912】 "Application example 2 when combining with an emotional engine" 【0913】 (Claim 1) 【0914】 Means of obtaining schedule information, 【0915】 A means of analyzing scheduled information to predict activity, 【0916】 A means of recognizing the user's emotional state, 【0917】 A means of dynamically adjusting the priority of activities based on emotional data, 【0918】 A means of automatically generating content based on predicted activity, 【0919】 A means of providing real-time suggestions for products and services tailored to emotional states, 【0920】 A means of monitoring business automation procedures and detecting, analyzing, and correcting errors, 【0921】 Means for providing notifications regarding generated content and modifications, 【0922】 A means of recording user selections and feedback to improve system performance, 【0923】 A system that includes this. 【0924】 (Claim 2) 【0925】 The system according to claim 1, characterized in that the means for obtaining user schedule information is to obtain the information based on time via a schedule information communication network. 【0926】 (Claim 3) 【0927】 The system according to claim 1, characterized in that the error detection means analyzes the history data of business automation to identify the cause of the error, generates a proposed correction, and automatically implements it. [Explanation of Symbols] 【0928】 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] Means of obtaining schedule information, A means of analyzing scheduled information to predict tasks, A means of automatically generating content based on predicted tasks, A means of monitoring business automation processes and detecting, analyzing, and correcting errors, Means for providing notifications regarding generated content and modifications, A means of recording user selections and feedback to improve system performance, A system that includes this. [Claim 2] The system according to claim 1, characterized in that the means for obtaining user schedule information is to obtain the information based on time via a schedule information communication network. [Claim 3] The system according to claim 1, characterized in that the error detection means analyzes log data of business automation to identify the cause of the error, generates a proposed correction, and automatically applies it.

Images