system

Abstract

We provide the system. [Solution] Means for collecting and analyzing data, A means of automatically generating tasks based on analysis results, Means for executing the generated tasks, A means of monitoring execution results, detecting anomalies, and generating alerts, A means of notifying users of alert information, A system that includes this.

Description

【Technical Field】 【0001】 The technology of this disclosure relates to a system. 【Background Art】 【0002】 Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. 【Prior Art Documents】 【Patent Documents】 【0003】 【Patent Document 1】 Japanese Patent Application Laid-Open No. 2022-180282 【Summary of the Invention】 【Problems to be Solved by the Invention】 【0004】 In enterprises, the processes of case management and progress management conventionally require a lot of manual work and it is difficult to improve work efficiency. Also, system operations and email responses are often carried out individually, and overall optimization hardly progresses. For this reason, there is a problem that the work burden becomes large and it is difficult to optimize resources. Furthermore, in monitoring the progress status and detecting abnormalities, there are many cases where manual intervention is involved, and real-time response may be delayed. 【Means for Solving the Problems】 【0005】 To solve this problem, we provide a system that includes means for collecting and analyzing data, means for automatically generating tasks based on the analysis results, means for executing the generated tasks, means for monitoring the execution results, detecting anomalies and generating alerts, and means for notifying the user of the alert information. By including means for receiving user feedback and improving the accuracy of automatic task generation, this system automates real-time progress management and anomaly detection, and further optimizes overall operational efficiency by using reinforcement learning to predict progress based on past data and determine the next action. 【0006】 "Means of collecting and analyzing data" refers to elements that have the function of aggregating information acquired from terminals on a network, analyzing that information, and extracting specific insights or states. 【0007】 A "means for automatically generating tasks" refers to an element that has the function of mechanically creating the necessary actions and work procedures based on the results of data analysis. 【0008】 "Means for executing generated tasks" are elements that have the functionality to physically or logically carry out actions or work instructions that the system has generated. 【0009】 "Means for monitoring execution results, detecting anomalies, and generating alerts" refers to elements that allow a system to check the status of task execution in real time and issue warnings when problems or anomalies are detected. 【0010】 "Means of notifying users of alert information" refers to elements that have the function of communicating warnings and important information that have occurred in the system to users in an appropriate manner. 【0011】 "Means of receiving user feedback to improve the accuracy of automated task generation" refers to elements in the system that utilize user input and responses to adjust the task generation algorithm and parameters, thereby improving accuracy. 【0012】 "A means of predicting progress and determining the next action based on past data using reinforcement learning" refers to an element that incorporates reinforcement learning techniques to predict future situations using data accumulated in the past and select the optimal next step. [Brief explanation of the drawing] 【0013】 [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of 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] This 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 a data processing system in Embodiment 2 when combined with an emotion engine. [Figure 14] It is a sequence diagram showing the processing flow of a data processing system in Application Example 2 when combined with an emotion engine. 【Mode for Carrying Out the Invention】 【0014】 Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings. 【0015】 First, the terms used in the following description will be explained. 【0016】 In the following embodiments, a processor with a reference numeral (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like. 【0017】 In the following embodiments, a RAM (Random Access Memory) with a reference numeral is a memory in which information is temporarily stored and is used as a work memory by the processor. 【0018】 In the following embodiments, a storage with a reference numeral is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc. 【0019】 In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark). 【0020】 In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or." 【0021】 [First Embodiment] 【0022】 Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment. 【0023】 As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server. 【0024】 The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network). 【0025】 The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52. 【0026】 The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input. 【0027】 The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor. 【0028】 Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54. 【0029】 Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14. 【0030】 As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30. 【0031】 The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. 【0032】 In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48. 【0033】 Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal". 【0034】 The system implementing this invention integrates the functions of data collection, analysis, automatic task generation, execution, monitoring, alert generation, notification, feedback reception, and prediction using reinforcement learning. The main components of the system, the server, terminals, and users, each play their respective roles. 【0035】 The server receives project information from terminals via the network, analyzes this information, and understands the current progress. Based on the analyzed progress data, the server automatically generates tasks under specific conditions. This task generation incorporates past performance data and user feedback to formulate highly accurate action plans. 【0036】 The terminal receives tasks delivered from the server and executes them. Depending on the task, physical and digital actions are taken, such as system operations or sending emails. The progress and results of the executed tasks are reported from the terminal to the server in real time. 【0037】 The server monitors the execution results based on these reports and immediately generates an alert if an anomaly is detected. This alert is promptly notified to the user, allowing them to resolve the issue directly if necessary. 【0038】 Furthermore, the server uses reinforcement learning to leverage past case data and feedback to more effectively determine the next action. This allows it to flexibly respond to the ever-changing business environment and improve productivity. 【0039】 For example, if a project is found to be at risk of not being completed on time, the server automatically generates the optimal countermeasures task. The terminal executes this task and reports its progress to the server. Based on the alerts sent from the server, the user determines whether human intervention is necessary and takes action if required. In this way, the system supports the efficient operation of projects and distributes the workload. 【0040】 The following describes the processing flow. 【0041】 Step 1: 【0042】 The server periodically collects case data from terminals via the network. Here, APIs and database queries are used to effectively retrieve the necessary information. 【0043】 Step 2: 【0044】 The server analyzes the collected data and evaluates the progress of projects in real time. Statistical algorithms and machine learning models are used in the analysis to detect anomalies and delay risks. 【0045】 Step 3: 【0046】 The server determines the necessary actions based on the analysis results. Specifically, it automatically generates tasks if the conditions are met and adds them to the execution queue. 【0047】 Step 4: 【0048】 The terminal receives tasks from the server and performs specific actions. Examples include automating system operations and sending emails. The terminal reports the results of the tasks it has performed back to the server. 【0049】 Step 5: 【0050】 The server receives result reports from the terminals and analyzes the execution results. If an anomaly is detected or if certain indicators fall below a certain level, an alert is immediately generated. 【0051】 Step 6: 【0052】 The server notifies users of any alerts that occur. These notifications are sent via email or a dashboard, allowing users to check the status. 【0053】 Step 7: 【0054】 Users receive alert notifications from the server and take additional actions manually as needed, such as issuing instructions to the project team or scheduling meetings. 【0055】 Step 8: 【0056】 The server uses reinforcement learning to improve its task generation algorithm by leveraging past data and feedback. This learning process improves the accuracy of subsequent operations. 【0057】 (Example 1) 【0058】 Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal." 【0059】 In today's business environment, it is essential to track project progress in real time and manage risks efficiently. However, manual data collection and analysis alone can lead to delays and reduce project efficiency. In addition, the inability to respond quickly to generated alerts can lead to further delays and risks. Therefore, to solve these problems, automated data analysis and task generation, along with flexible responses utilizing feedback, are necessary. 【0060】 The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means. 【0061】 In this invention, the server includes means for collecting data, receiving and storing information, performing data analysis, identifying progress and risk factors, and executing generated tasks by physical or electronic means. This enables automatic and real-time management of project progress and efficient risk response. 【0062】 "Data collection" refers to the process of gathering information, specifically receiving and storing case information from terminals via a communication network. 【0063】 "Data analysis" refers to the process of processing collected information and performing calculations and analyses to identify progress and risk factors. 【0064】 "Automatic task generation" refers to the process of constructing a work plan and generating an action plan based on the results of analysis and specific conditions. 【0065】 "To execute" means to perform a specified task or operation through physical or electronic means. 【0066】 "Progress and results reporting" refers to continuously communicating the progress and results of completed tasks to the information system. 【0067】 "Monitoring" refers to activities that continuously track the progress and results of work and detect abnormal situations. 【0068】 "Alert generation" refers to creating a warning and notification when an anomaly is detected, prompting a quick response. 【0069】 "User notification" refers to providing a means of informing human users of the generated warning information. 【0070】 "Feedback collection" refers to activities that involve gathering reactions and evaluations from users to help improve the system's performance. 【0071】 A "machine learning algorithm" is a computational method that learns from past data to make predictions and decisions, and it supports the automation and optimization of systems. 【0072】 Modes for carrying out the invention 【0073】 This invention is an integrated system that includes data collection, analysis, automated task generation and execution, monitoring, alert generation, notification, feedback reception, and prediction using reinforcement learning. The main components are a server, terminals, and users, each playing a specific role. 【0074】 The server performs data collection and analysis. Specifically, it receives data from multiple terminals via HTTP requests, structures the information using database management software, and stores it. By using an analysis platform such as Apache Spark, it enables real-time data analysis to identify project progress and potential risks. The analysis results are combined with historical data and feedback to be used for automated task generation. 【0075】 Terminals receive tasks delivered from the server and perform the actual operations and processing. Tasks can be executed electronically using physical devices or automated scripts using a "scripting language." For example, in an "email sending task," information is communicated to relevant parties through email client software. Each terminal reports the progress and results of the tasks it has performed to the server in real time, supporting more detailed monitoring and feedback accumulation. 【0076】 Users receive information and alerts from servers and terminals and intervene as needed. Generated alerts are notified to users in a way that prompts real-time decision-making. Users utilize the "communication platform" to quickly consider countermeasures within the team and reallocate project resources as necessary. 【0077】 The system utilizes reinforcement learning algorithms, using past case data and feedback as learning material to determine the next optimal action. This process employs a "machine learning framework," enabling it to continuously adapt flexibly to changes in business operations. 【0078】 For example, if a project delay risk is identified, the server automatically generates the optimal countermeasure. The terminal implements this countermeasure and reports the results. By receiving alerts, users can take necessary interventions and properly manage the project's progress. Effective operation of this system makes project progress management more efficient and allows for the distribution of workload. 【0079】 An example of a prompt would be, "If a project is at risk of missing its deadline, how does the server automatically generate mitigation tasks? And how can the user intervene?" This prompt helps understand how the system works by leveraging the generative AI model. 【0080】 The flow of the specific processing in Example 1 will be explained using Figure 11. 【0081】 Step 1: 【0082】 The server receives case information from terminals via HTTP requests. This input data is in JSON format, and the server parses it before storing it in a database management system. Storing the data allows for quick access during subsequent analysis. 【0083】 Step 2: 【0084】 The server uses an "analysis platform" to perform data analysis based on the stored data. In this step, historical data is compared with current data to identify progress and risk factors. Finally, the analysis results are output and used in the task generation process. 【0085】 Step 3: 【0086】 The server automatically generates tasks based on analysis results, provided certain conditions are met. This process uses an "optimization algorithm" to maximize the efficiency of each task. Inputs include analysis output data and past feedback, which are then used to generate output as task information. 【0087】 Step 4: 【0088】 The terminal receives task information sent from the server and performs the task according to the specific instructions. This step utilizes physical or electronic means, for example, to automate sending emails using a "scripting language." The output is the result of the task execution. 【0089】 Step 5: 【0090】 The terminal reports the progress and results of the executed task to the server via an HTTP POST request. The input includes the task's progress and results, and the output is received by the server as report data. 【0091】 Step 6: 【0092】 The server monitors the received report data and immediately generates an alert if an anomaly is detected in the system. The input in this step is progress report data, and the output generates and stores alert information. 【0093】 Step 7: 【0094】 Users receive alert notifications from the server and intervene as needed. They receive alert information displayed on the screen as input, make decisions and adjustments, and produce outputs such as reallocating resources through project management software. 【0095】 Step 8: 【0096】 The server collects user feedback and learns from this information using a reinforcement learning algorithm. At this stage, it takes feedback data as input and updates parameters based on the learning results. This further optimizes the generation of subsequent tasks. 【0097】 (Application Example 1) 【0098】 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." 【0099】 There is a need to improve the operational efficiency of robots in production systems, quickly detect operational anomalies, and take appropriate action. Furthermore, a challenge is to improve productivity and reduce workload by automating the optimization of future operations based on past data. 【0100】 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. 【0101】 In this invention, the server includes a device for acquiring and analyzing data, a device for automatically generating tasks based on the analysis results, a device for performing the generated tasks, a device for monitoring the execution results, detecting anomalies and generating alarms, a device for notifying users of alarm information, and a device for managing the operation of equipment involved in task execution and using reinforcement learning to generate new tasks. This makes it possible to optimize the operation of robots in the production system and respond quickly to abnormal conditions. Furthermore, it is possible to efficiently perform repetitive tasks using reinforcement learning. 【0102】 "Data" refers to information and records related to the execution of business operations, and serves as the basis for analysis and business generation. 【0103】 "Analysis" is the process of analyzing business conditions based on acquired data and extracting information necessary for carrying out business operations. 【0104】 "Work" refers to a set of tasks that are planned and carried out to achieve a specific objective. 【0105】 "Execution" refers to carrying out planned tasks and achieving specified goals. 【0106】 "Monitoring" refers to the act of constantly checking the progress of work and keeping an eye out for any abnormalities. 【0107】 "An anomaly" refers to an unexpected situation or problem that occurs during the performance of duties. 【0108】 An "alarm" is a warning message issued when an abnormality is detected, intended to prompt a quick response. 【0109】 "Users" refers to individuals or organizations that operate the system and monitor its operation. 【0110】 "Reinforcement learning" is a machine learning technique that learns the optimal actions based on past records and applies them to future work performance. 【0111】 "Device" refers to a component of a machine or system that performs a specific function. 【0112】 The system for implementing this invention integrates the functions of detailed data collection, analysis, automated task generation, execution, monitoring, alarm generation, notification, feedback reception, and optimization through reinforcement learning. This system includes three main components: a server, terminals, and users. 【0113】 The server is built on a cloud infrastructure (e.g., Amazon Web Services) and acquires production-related data from terminals via the network. This acquired data is analyzed using Python data analysis libraries (such as pandas and scikit-learn). Based on the analysis results, past production records and feedback information are integrated to automatically generate business processes. 【0114】 The generated tasks are sent to factory robot terminals equipped with NVIDIA Jetson. These terminals use multiple sensors and control devices to execute the received tasks. The terminals send real-time data acquired during execution back to the server, which monitors the execution status based on this data and immediately generates an alarm if an anomaly is detected. 【0115】 Alarm information is sent to the user's smartphone and displayed through an application developed using React Native. Based on the alarm, the user can take necessary action and directly impact the system. 【0116】 Furthermore, the server performs reinforcement learning through a generative AI model, using past data to improve operations and optimize future operations. Through this reinforcement learning, the system improves the efficiency of its operations over time. 【0117】 As a concrete example, consider a scenario where a bottleneck occurs on a production line. The server can analyze the cause, automatically generate new tasks to adjust specific processes, and send them as tasks to robot terminals. This process smooths the production flow and improves efficiency. Using the prompt, "Please tell me the best way to generate and execute specific tasks to resolve the bottleneck on the production line," the AI ​​model assists in generating the optimal tasks. 【0118】 The flow of a specific process in Application Example 1 will be explained using Figure 12. 【0119】 Step 1: 【0120】 The server acquires production-related data from factory terminals via the network. The terminals transmit raw data, including robot movements and information from sensors. Based on this input data, the server stores it in a database and prepares it for analysis. 【0121】 Step 2: 【0122】 The server preprocesses the acquired raw data using the Python pandas library. This removes noise, normalizes the data, and converts it into a format suitable for analysis. The output includes organized production data. 【0123】 Step 3: 【0124】 The server uses the scikit-learn library to analyze the preprocessed data. This analysis uses machine learning algorithms to identify bottlenecks and anomaly patterns in the production line. The output includes the identified problems and their locations. 【0125】 Step 4: 【0126】 The server automatically generates new tasks based on the analysis results. Here, it uses a generation AI model to reference historical data and design the optimal task plan. The prompt "Generate specific tasks to resolve bottlenecks in the production line and tell me the best way to execute them" is used to support the model. The output is the newly generated task. 【0127】 Step 5: 【0128】 The terminal receives business tasks sent from the server and uses the NVIDIA Jetson platform to issue execution instructions to the robot. Based on these tasks, the terminal controls the robot's movements, performing optimized actions at each stage of the process. The output is the improvement in production efficiency resulting from the executed business tasks. 【0129】 Step 6: 【0130】 The server monitors execution data from terminals in real time and immediately generates an alarm if an anomaly is detected. This alarm is sent to the user through the alert system. The output is an alarm message that the user can quickly review. 【0131】 Step 7: 【0132】 Users receive alerts via a smartphone app and analyze their content. They then send feedback to the system as needed to adjust their work processes. The output consists of adjusted work instructions and improvement measures. 【0133】 Step 8: 【0134】 The server executes a reinforcement learning algorithm, continuously learning from the feedback it receives and past records. This learning is then used in subsequent task generation and optimization processes. The output is insights and strategies for future business improvement. 【0135】 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. 【0136】 The system of this invention, in addition to conventional progress management and automation systems, has the function of recognizing user emotions and performing actions accordingly. The system mainly consists of a server, terminals, an emotion engine, and users. 【0137】 The server collects necessary data from terminals via the network and analyzes it. Based on the analyzed information, the server evaluates the progress and automatically generates the necessary tasks. These tasks are sent to terminals, where appropriate system operations or email sending are performed. 【0138】 The emotion engine evaluates the user's emotional state in real time through interaction with the user. This evaluation uses voice tone analysis and facial recognition technology to determine the user's stress level and satisfaction level. If the server determines that the user is feeling anxious or stressed, it generates an alert and sets up emotion-sensitive feedback methods in addition to conventional notification methods. 【0139】 For example, if the emotion engine determines that a user is expressing negative emotions about project progress, the server generates an alert and promptly notifies the support team. Based on the alert, the terminal can then perform additional tasks to assist the user. In this way, the system responds flexibly to the user's emotional state, aiming to improve project success and user satisfaction. Furthermore, user feedback is also analyzed through the emotion engine, and the results are used to improve the accuracy of automated task generation. This enables the system to achieve more personalized task management and support efficient business operations. 【0140】 The following describes the processing flow. 【0141】 Step 1: 【0142】 The server collects project-related data from terminals. This data includes progress information and task completion status. 【0143】 Step 2: 【0144】 The server analyzes the collected data, evaluates the progress of each project, and identifies anomalies and risks. This analysis uses historical data and established baseline values. 【0145】 Step 3: 【0146】 The emotion engine evaluates the user's emotional state through interaction with the user. It uses speech recognition and facial recognition systems to analyze the user's stress level and satisfaction level. 【0147】 Step 4: 【0148】 The server receives the evaluation results from the emotion engine and generates an alert if it determines that the user is experiencing stress. This alert contains important information that requires consideration for the user. 【0149】 Step 5: 【0150】 The device receives alerts from the server and notifies the user as needed. The notification method is selected considering the user's emotional state. 【0151】 Step 6: 【0152】 The device automatically performs support tasks based on the generated alerts, including suggesting additional assistance and contacting support personnel. 【0153】 Step 7: 【0154】 The user reviews the alert notification and decides on any further actions that may be necessary. Based on the user's judgment, further actions are taken to resolve the problem. 【0155】 Step 8: 【0156】 The server receives user feedback, analyzes it using an emotion engine, and uses that feedback to improve the accuracy of automated task generation. This feedback processing enables the system to provide more precise and personalized responses. 【0157】 (Example 2) 【0158】 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". 【0159】 Traditional progress management systems fail to consider users' emotional states, resulting in an inability to properly manage user satisfaction and stress levels, ultimately leading to decreased project management efficiency. Furthermore, the inaccuracy of automated task generation hindered efficient work execution. 【0160】 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. 【0161】 In this invention, the server includes means for collecting and analyzing data, means for evaluating the user's emotional state in real time, and means for notifying the user of alert information based on the emotional evaluation. This enables project management that takes the user's emotional state into consideration, leading to improved user satisfaction and effective task management. 【0162】 "Means of collecting and analyzing data" refers to processes and devices for gathering necessary information from users and the environment, and for processing that information to obtain meaningful insights. 【0163】 "Means for automatically generating tasks" refer to processes or devices that mechanically generate tasks to be performed based on collected and analyzed data. 【0164】 "Means for evaluating a user's emotional state in real time" refers to processes or devices that analyze a user's voice, image data, etc., to instantly determine the user's emotions. 【0165】 "Means for executing generated tasks" refers to the processes or devices that actually carry out the generated tasks according to pre-set instructions. 【0166】 "Means for monitoring execution results, detecting anomalies, and generating alerts" refers to processes or devices that verify the results of tasks during and after execution and issue warnings when problems occur. 【0167】 "Means for notifying users of alert information based on sentiment evaluation" refers to processes or devices that provide users with relevant notifications and warning information while taking into account the user's sentiment evaluation. 【0168】 "Means of receiving user feedback to improve the accuracy of automated task generation" refers to processes or devices that reflect user opinions and feelings to improve the accuracy of task generation. 【0169】 "A means of predicting progress and determining the next action based on past data using reinforcement learning" refers to a process or device that applies historical data analysis and machine learning techniques to predict future events and set necessary actions. 【0170】 Embodiments of the present invention relate to a system that highly integrates user progress management and sentiment analysis to achieve efficient project management. This system includes a server, terminals, and a sentiment engine. 【0171】 The server collects data from terminals via the network and analyzes that data. Specifically, it uses an Application Programming Interface (API) to retrieve task management data and compares it with historical data managed in a database. Machine learning models are used for data processing, which evaluates the progress of tasks. 【0172】 The emotion engine utilizes voice analysis libraries and facial recognition AI to analyze the user's voice tone and facial expressions in real time. For example, it uses open-source voice analysis tools to determine how stressed a user is during a meeting. The results are sent to the server, and alerts are generated as needed. 【0173】 The device performs tasks based on instructions from the server and sends email and application notifications to the user. The appropriate timing of notifications is determined by considering the user's schedule and emotional state. 【0174】 For example, if a user expresses negative feelings about the project's progress, the server generates a prompt message stating, "A user has expressed concern about the progress of an important project. Action is required," and notifies the administrator. The terminal then quickly takes action based on this message to assist the user. 【0175】 This system allows us to collect user feedback and improve the accuracy of task generation through reinforcement learning. As a result, more personalized task management that takes into account the user's emotional state becomes possible. 【0176】 The flow of the specific processing in Example 2 will be explained using Figure 13. 【0177】 Step 1: 【0178】 The server collects user task management data from the terminal. The input is task data entered by the user into the application, and the output is task information stored in a database on the server. Specifically, the server collects data via an API and processes it to obtain task deadlines and priority information. 【0179】 Step 2: 【0180】 The server analyzes the collected task data and performs progress evaluation. The input is the collected task information, and the output is the evaluated progress data. Here, a machine learning model is used to calculate the degree of task completion and perform specific processing to evaluate progress against the schedule. 【0181】 Step 3: 【0182】 The emotion engine analyzes the user's voice tone and facial expression data to evaluate the user's emotional state. Input is the user's voice and image data, and output is the emotion evaluation result. Using voice analysis libraries and facial recognition technology, it specifically determines the user's stress level and satisfaction level. 【0183】 Step 4: 【0184】 The server automatically generates necessary tasks and issues alerts based on progress and sentiment assessment results. Inputs are progress assessment data and sentiment assessment results, while outputs are the generated tasks and alerts. Based on this, the server generates prompt messages and performs specific actions to notify administrators and relevant parties. 【0185】 Step 5: 【0186】 The device presents task information received from the server to the user and executes email and app notifications according to the user's instructions. Input consists of tasks and alert information from the server, while output is the notification results sent to the user. The device takes the user's emotions into consideration while providing timely notifications and performing specific actions to track progress. 【0187】 (Application Example 2) 【0188】 Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal". 【0189】 In modern industrial settings, workers' emotional states significantly impact work efficiency and safety. However, conventional systems struggle to provide real-time feedback based on workers' emotions, resulting in stress and anxiety. To address this, there is a need for technology that can efficiently provide emotionally sensitive support. 【0190】 The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. 【0191】 In this invention, the server includes means for collecting and analyzing data, means for automatically generating tasks based on the analysis results, and means for analyzing the user's emotional state and providing emotionally sensitive feedback based on the analysis results. This enables appropriate feedback tailored to the user's emotional state. 【0192】 "Means of collecting and analyzing data" refers to a system that takes in information acquired through sensors and input devices, analyzes its content using algorithms, and converts it into a usable format. 【0193】 "Means for automatically generating tasks based on analysis results" refers to a mechanism that automatically creates appropriate processes and tasks based on the results of data analysis, enabling the user to proceed to the next step. 【0194】 "Means for executing generated tasks" refers to functions within a system that carry out tasks generated as concrete actions or operations. 【0195】 "A means of monitoring execution results, detecting anomalies, and generating alerts" refers to a system that monitors the execution status of tasks and issues warnings if anomalies or problems occur. 【0196】 "Means of notifying users of alert information" refers to means of communicating warnings and important information generated by the system to users. 【0197】 "A means of analyzing a user's emotional state and providing emotionally sensitive feedback based on the analysis results" refers to a technology that performs analysis to determine a user's emotions and provides responses or messages accordingly. 【0198】 The program to implement this system possesses the technology to collect and analyze data through a server, terminal, and emotion engine, and to provide feedback that takes the user's emotions into consideration. The server plays the role of data collection, analyzing data using analysis algorithms based on information obtained from sensors and various input devices. Specifically, it can evaluate the user's emotional state by using voice tone and facial expression recognition technologies. Based on these analysis results, the server automatically generates appropriate tasks and sends them to the terminal as needed. 【0199】 The terminal is a device for receiving and executing generated tasks, monitoring anomalies and problems in real time, and generating alerts as needed. The alert information is analyzed through an emotion engine, and feedback is provided to the user. This feedback is presented to the user in written or interactive formats and is used for work improvement and emotional support. 【0200】 As a concrete example, if a worker experiences stress on the factory floor, the system immediately analyzes their emotions and notifies the manager, while simultaneously displaying a message on the worker's terminal encouraging them to take a break. This function aims to enhance user support and improve productivity. 【0201】 By utilizing generative AI models and prompt messages, more accurate feedback and task management are achieved. For example, prompt messages such as, "How can we analyze visual and audio data of workers during their work and suggest appropriate manager notifications and feedback to workers when stress or anxiety is detected?" can be used. 【0202】 The flow of a specific process in Application Example 2 will be explained using Figure 14. 【0203】 Step 1: 【0204】 The server collects data from sensors and input devices. Specifically, it captures voice tone and facial expression data. This data is saved as initial input and prepared for analysis. 【0205】 Step 2: 【0206】 The server passes the collected data to the analysis engine. The analysis engine processes the data using speech recognition and image processing technologies to determine the user's emotional state. As a result of the analysis, the emotional state (e.g., stress level and anxiety index) is output as numerical data. 【0207】 Step 3: 【0208】 The server automatically generates the next task based on the analysis results. Specifically, if the user's emotional state indicates stress, it prepares a suggestion to take a break and a message of encouragement. This task is sent to the terminal and prepared for execution. 【0209】 Step 4: 【0210】 The terminal receives tasks from the server and displays specific instructions. It also notifies the user of break suggestion messages and reminders, and monitors the task's progress. 【0211】 Step 5: 【0212】 The system monitors whether the user has responded to feedback via the device and returns the result to the server. The device collects user operation and response data as input and sends it to the server. 【0213】 Step 6: 【0214】 Based on the feedback data it receives, the server updates its reinforcement learning model to improve the accuracy of its task generation algorithm. This process makes it possible to further improve the accuracy of task generation in subsequent attempts. 【0215】 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. 【0216】 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. 【0217】 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. 【0218】 [Second Embodiment] 【0219】 Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment. 【0220】 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. 【0221】 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). 【0222】 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. 【0223】 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. 【0224】 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). 【0225】 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. 【0226】 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. 【0227】 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. 【0228】 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. 【0229】 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. 【0230】 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". 【0231】 The system implementing this invention integrates the functions of data collection, analysis, automatic task generation, execution, monitoring, alert generation, notification, feedback reception, and prediction using reinforcement learning. The main components of the system, the server, terminals, and users, each play their respective roles. 【0232】 The server receives project information from terminals via the network, analyzes this information, and understands the current progress. Based on the analyzed progress data, the server automatically generates tasks under specific conditions. This task generation incorporates past performance data and user feedback to formulate highly accurate action plans. 【0233】 The terminal receives tasks delivered from the server and executes them. Depending on the task, physical and digital actions are taken, such as system operations or sending emails. The progress and results of the executed tasks are reported from the terminal to the server in real time. 【0234】 The server monitors the execution results based on these reports and immediately generates an alert if an anomaly is detected. This alert is promptly notified to the user, allowing them to resolve the issue directly if necessary. 【0235】 Furthermore, the server uses reinforcement learning to leverage past case data and feedback to more effectively determine the next action. This allows it to flexibly respond to the ever-changing business environment and improve productivity. 【0236】 For example, if a project is found to be at risk of not being completed on time, the server automatically generates the optimal countermeasures task. The terminal executes this task and reports its progress to the server. Based on the alerts sent from the server, the user determines whether human intervention is necessary and takes action if required. In this way, the system supports the efficient operation of projects and distributes the workload. 【0237】 The following describes the processing flow. 【0238】 Step 1: 【0239】 The server periodically collects case data from terminals via the network. Here, APIs and database queries are used to effectively retrieve the necessary information. 【0240】 Step 2: 【0241】 The server analyzes the collected data and evaluates the progress of projects in real time. Statistical algorithms and machine learning models are used in the analysis to detect anomalies and delay risks. 【0242】 Step 3: 【0243】 The server determines the necessary actions based on the analysis results. Specifically, it automatically generates tasks if the conditions are met and adds them to the execution queue. 【0244】 Step 4: 【0245】 The terminal receives tasks from the server and performs specific actions. Examples include automating system operations and sending emails. The terminal reports the results of the tasks it has performed back to the server. 【0246】 Step 5: 【0247】 The server receives result reports from the terminals and analyzes the execution results. If an anomaly is detected or if certain indicators fall below a certain level, an alert is immediately generated. 【0248】 Step 6: 【0249】 The server notifies users of any alerts that occur. These notifications are sent via email or a dashboard, allowing users to check the status. 【0250】 Step 7: 【0251】 Users receive alert notifications from the server and take additional actions manually as needed, such as issuing instructions to the project team or scheduling meetings. 【0252】 Step 8: 【0253】 The server uses reinforcement learning to improve its task generation algorithm by leveraging past data and feedback. This learning process improves the accuracy of subsequent operations. 【0254】 (Example 1) 【0255】 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." 【0256】 In today's business environment, it is essential to track project progress in real time and manage risks efficiently. However, manual data collection and analysis alone can lead to delays and reduce project efficiency. In addition, the inability to respond quickly to generated alerts can lead to further delays and risks. Therefore, to solve these problems, automated data analysis and task generation, along with flexible responses utilizing feedback, are necessary. 【0257】 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. 【0258】 In this invention, the server includes means for collecting data, receiving and storing information, performing data analysis, identifying progress and risk factors, and executing generated tasks by physical or electronic means. This enables automatic and real-time management of project progress and efficient risk response. 【0259】 "Data collection" refers to the process of gathering information, specifically receiving and storing case information from terminals via a communication network. 【0260】 "Data analysis" refers to the process of processing collected information and performing calculations and analyses to identify progress and risk factors. 【0261】 "Automatic task generation" refers to the process of constructing a work plan and generating an action plan based on the results of analysis and specific conditions. 【0262】 "To execute" means to perform a specified task or operation through physical or electronic means. 【0263】 "Progress and results reporting" refers to continuously communicating the progress and results of completed tasks to the information system. 【0264】 "Monitoring" refers to activities that continuously track the progress and results of work and detect abnormal situations. 【0265】 "Alert generation" refers to creating a warning and notification when an anomaly is detected, prompting a quick response. 【0266】 "User notification" refers to providing a means of informing human users of the generated warning information. 【0267】 "Feedback collection" refers to activities that involve gathering reactions and evaluations from users to help improve the system's performance. 【0268】 A "machine learning algorithm" is a computational method that learns from past data to make predictions and decisions, and it supports the automation and optimization of systems. 【0269】 Modes for carrying out the invention 【0270】 This invention is an integrated system that includes data collection, analysis, automated task generation and execution, monitoring, alert generation, notification, feedback reception, and prediction using reinforcement learning. The main components are a server, terminals, and users, each playing a specific role. 【0271】 The server performs data collection and analysis. Specifically, it receives data from multiple terminals via HTTP requests, structures the information using database management software, and stores it. By using an analysis platform such as Apache Spark, it enables real-time data analysis to identify project progress and potential risks. The analysis results are combined with historical data and feedback to be used for automated task generation. 【0272】 Terminals receive tasks delivered from the server and perform the actual operations and processing. Tasks can be executed electronically using physical devices or automated scripts using a "scripting language." For example, in an "email sending task," information is communicated to relevant parties through email client software. Each terminal reports the progress and results of the tasks it has performed to the server in real time, supporting more detailed monitoring and feedback accumulation. 【0273】 Users receive information and alerts from servers and terminals and intervene as needed. Generated alerts are notified to users in a way that prompts real-time decision-making. Users utilize the "communication platform" to quickly consider countermeasures within the team and reallocate project resources as necessary. 【0274】 The system utilizes reinforcement learning algorithms, using past case data and feedback as learning material to determine the next optimal action. This process employs a "machine learning framework," enabling it to continuously adapt flexibly to changes in business operations. 【0275】 For example, if a project delay risk is identified, the server automatically generates the optimal countermeasure. The terminal implements this countermeasure and reports the results. By receiving alerts, users can take necessary interventions and properly manage the project's progress. Effective operation of this system makes project progress management more efficient and allows for the distribution of workload. 【0276】 Examples of prompt sentences include "When a project is at risk of deadline delay, how does the server automatically generate countermeasure tasks? Also, how can the user intervene?" This prompt sentence helps to understand how the system functions by utilizing the generative AI model. 【0277】 The flow of the specific process in Example 1 will be described using FIG. 11. 【0278】 Step 1: 【0279】 The server receives project information from the terminal via an "HTTP request". This input data is in "JSON format", and the server analyzes it and stores it in a "database management system". Storing the data enables quick access during subsequent analysis stages. 【0280】 Step 2: 【0281】 The server performs data analysis using an "analysis platform" based on the stored data. In this step, past data is compared with current data to identify progress status and risk factors. Finally, the analysis results are output and utilized in the task generation process. 【0282】 Step 3: 【0283】 The server automatically generates tasks when specific conditions are met based on the analysis results. In this process, an "optimization algorithm" is used to maximize the efficiency of each task. The inputs are the output data of the analysis and past feedback, and an output as task information is generated. 【0284】 Step 4: 【0285】 The terminal receives the task information sent from the server and executes the work according to specific instructions. In this step, physical or electronic means are utilized, for example, using a "script language" to automate the sending of emails. The output is the task execution result. 【0286】 Step 5: 【0287】 The terminal reports the progress and result of the executed task to the server via an "HTTP POST request". The inputs are the task progress status and achievements, and the output is incorporated into the server side as the reported data. 【0288】 Step 6: 【0289】 The server monitors the received reported data and generates an alert immediately if an anomaly is detected in the system. The input at this step is the progress report data, and the output is to generate and save the alert information. 【0290】 Step 7: 【0291】 The user receives the alert notification from the server and intervenes if necessary. The user receives the alert information presented on the display as input, makes judgments and adjustments, and produces outputs such as redistributing resources through project management software. 【0292】 <0000�23>Step 8: 【0293】 The server collects the feedback from the user and learns the information using a reinforcement learning algorithm. At this stage, the feedback data is taken as input, and parameter updates as the learning result are performed. Thereby, the next task generation is further optimized. 【0294】 (Application Example 1) 【0295】 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." 【0296】 There is a need to improve the operational efficiency of robots in production systems, quickly detect operational anomalies, and take appropriate action. Furthermore, a challenge is to improve productivity and reduce workload by automating the optimization of future operations based on past data. 【0297】 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. 【0298】 In this invention, the server includes a device for acquiring and analyzing data, a device for automatically generating tasks based on the analysis results, a device for performing the generated tasks, a device for monitoring the execution results, detecting anomalies and generating alarms, a device for notifying users of alarm information, and a device for managing the operation of equipment involved in task execution and using reinforcement learning to generate new tasks. This makes it possible to optimize the operation of robots in the production system and respond quickly to abnormal conditions. Furthermore, it is possible to efficiently perform repetitive tasks using reinforcement learning. 【0299】 "Data" refers to information and records related to the execution of business operations, and serves as the basis for analysis and business generation. 【0300】 "Analysis" is the process of analyzing business conditions based on acquired data and extracting information necessary for carrying out business operations. 【0301】 "Work" refers to a set of tasks that are planned and carried out to achieve a specific objective. 【0302】 "Execution" refers to carrying out planned tasks and achieving specified goals. 【0303】 "Monitoring" refers to the act of constantly checking the progress of work and keeping an eye out for any abnormalities. 【0304】 "Abnormality" refers to unforeseen situations or problems that occur during business operations. 【0305】 "Alarm" is warning information sent when an abnormality is detected, and is used to prompt immediate response. 【0306】 "User" refers to a person or organization that operates the system and monitors business operations. 【0307】 "Reinforcement learning" is a machine learning technique that learns optimal actions based on past records and reflects them in future business operations. 【0308】 "Device" refers to a machine or a component of a system that performs a specific function. 【0309】 The system for implementing this invention integrates functions of detailed data collection, analysis, business automatic generation, execution, monitoring, alarm generation, notification, feedback reception, and optimization by reinforcement learning. This system includes three main components: a server, a terminal, and a user. 【0310】 The server is built on a cloud platform (such as Amazon Web Services) and acquires production-related data from the terminal via a network. The acquired data is analyzed using Python data analysis libraries (such as pandas and scikit-learn). Based on the analysis results, past production records and feedback information are integrated to automatically generate business operations. 【0311】 The generated business operations are sent to the robot terminal in the factory equipped with NVIDIA Jetson. This terminal uses multiple sensors and control devices to perform tasks in order to execute the received business operations. The terminal returns the real-time data acquired during the execution to the server, and the server monitors the execution status based on this, and immediately generates an alarm when an abnormality is detected. 【0312】 Alarm information is sent to the user's smartphone and displayed through an application developed using React Native. Based on the alarm, the user can take necessary action and directly impact the system. 【0313】 Furthermore, the server performs reinforcement learning through a generative AI model, using past data to improve operations and optimize future operations. Through this reinforcement learning, the system improves the efficiency of its operations over time. 【0314】 As a concrete example, consider a scenario where a bottleneck occurs on a production line. The server can analyze the cause, automatically generate new tasks to adjust specific processes, and send them as tasks to robot terminals. This process smooths the production flow and improves efficiency. Using the prompt, "Please tell me the best way to generate and execute specific tasks to resolve the bottleneck on the production line," the AI ​​model assists in generating the optimal tasks. 【0315】 The flow of a specific process in Application Example 1 will be explained using Figure 12. 【0316】 Step 1: 【0317】 The server acquires production-related data from factory terminals via the network. The terminals transmit raw data, including robot movements and information from sensors. Based on this input data, the server stores it in a database and prepares it for analysis. 【0318】 Step 2: 【0319】 The server preprocesses the acquired raw data using the Python pandas library. This removes noise, normalizes the data, and converts it into a format suitable for analysis. The output includes organized production data. 【0320】 Step 3: 【0321】 The server uses the scikit-learn library to analyze the preprocessed data. This analysis uses machine learning algorithms to identify bottlenecks and anomaly patterns in the production line. The output includes the identified problems and their locations. 【0322】 Step 4: 【0323】 The server automatically generates new tasks based on the analysis results. Here, it uses a generation AI model to reference historical data and design the optimal task plan. The prompt "Generate specific tasks to resolve bottlenecks in the production line and tell me the best way to execute them" is used to support the model. The output is the newly generated task. 【0324】 Step 5: 【0325】 The terminal receives business tasks sent from the server and uses the NVIDIA Jetson platform to issue execution instructions to the robot. Based on these tasks, the terminal controls the robot's movements, performing optimized actions at each stage of the process. The output is the improvement in production efficiency resulting from the executed business tasks. 【0326】 Step 6: 【0327】 The server monitors execution data from terminals in real time and immediately generates an alarm if an anomaly is detected. This alarm is sent to the user through the alert system. The output is an alarm message that the user can quickly review. 【0328】 Step 7: 【0329】 Users receive alerts via a smartphone app and analyze their content. They then send feedback to the system as needed to adjust their work processes. The output consists of adjusted work instructions and improvement measures. 【0330】 Step 8: 【0331】 The server executes a reinforcement learning algorithm, continuously learning from the feedback it receives and past records. This learning is then used in subsequent task generation and optimization processes. The output is insights and strategies for future business improvement. 【0332】 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. 【0333】 The system of this invention, in addition to conventional progress management and automation systems, has the function of recognizing user emotions and performing actions accordingly. The system mainly consists of a server, terminals, an emotion engine, and users. 【0334】 The server collects necessary data from terminals via the network and analyzes it. Based on the analyzed information, the server evaluates the progress and automatically generates the necessary tasks. These tasks are sent to terminals, where appropriate system operations or email sending are performed. 【0335】 The emotion engine evaluates the user's emotional state in real time through interaction with the user. This evaluation uses voice tone analysis and facial recognition technology to determine the user's stress level and satisfaction level. If the server determines that the user is feeling anxious or stressed, it generates an alert and sets up emotion-sensitive feedback methods in addition to conventional notification methods. 【0336】 For example, if the emotion engine determines that a user is expressing negative emotions about project progress, the server generates an alert and promptly notifies the support team. Based on the alert, the terminal can then perform additional tasks to assist the user. In this way, the system responds flexibly to the user's emotional state, aiming to improve project success and user satisfaction. Furthermore, user feedback is also analyzed through the emotion engine, and the results are used to improve the accuracy of automated task generation. This enables the system to achieve more personalized task management and support efficient business operations. 【0337】 The following describes the processing flow. 【0338】 Step 1: 【0339】 The server collects project-related data from terminals. This data includes progress information and task completion status. 【0340】 Step 2: 【0341】 The server analyzes the collected data, evaluates the progress of each project, and identifies anomalies and risks. This analysis uses historical data and established baseline values. 【0342】 Step 3: 【0343】 The emotion engine evaluates the user's emotional state through interaction with the user. It uses speech recognition and facial recognition systems to analyze the user's stress level and satisfaction level. 【0344】 Step 4: 【0345】 The server receives the evaluation results from the emotion engine and generates an alert if it determines that the user is experiencing stress. This alert contains important information that requires consideration for the user. 【0346】 Step 5: 【0347】 The device receives alerts from the server and notifies the user as needed. The notification method is selected considering the user's emotional state. 【0348】 Step 6: 【0349】 The device automatically performs support tasks based on the generated alerts, including suggesting additional assistance and contacting support personnel. 【0350】 Step 7: 【0351】 The user reviews the alert notification and decides on any further actions they deem necessary. Based on the user's judgment, further actions are taken to resolve the problem. 【0352】 Step 8: 【0353】 The server receives user feedback, analyzes it using an emotion engine, and uses that feedback to improve the accuracy of automated task generation. This feedback processing enables the system to provide more precise and personalized responses. 【0354】 (Example 2) 【0355】 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". 【0356】 Traditional progress management systems fail to consider users' emotional states, resulting in an inability to properly manage user satisfaction and stress levels, ultimately leading to decreased project management efficiency. Furthermore, the inaccuracy of automated task generation hindered efficient work execution. 【0357】 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. 【0358】 In this invention, the server includes means for collecting and analyzing data, means for evaluating the user's emotional state in real time, and means for notifying the user of alert information based on the emotional evaluation. This enables project management that takes the user's emotional state into consideration, leading to improved user satisfaction and effective task management. 【0359】 "Means of collecting and analyzing data" refers to processes and devices for gathering necessary information from users and the environment, and for processing that information to obtain meaningful insights. 【0360】 "Means for automatically generating tasks" refer to processes or devices that mechanically generate tasks to be performed based on collected and analyzed data. 【0361】 "Means for evaluating a user's emotional state in real time" refers to processes or devices that analyze a user's voice, image data, etc., to instantly determine the user's emotions. 【0362】 "Means for executing generated tasks" refers to the processes or devices that actually carry out the generated tasks according to pre-set instructions. 【0363】 "Means for monitoring execution results, detecting anomalies, and generating alerts" refers to processes or devices that verify the results of tasks during and after execution and issue warnings when problems occur. 【0364】 "Means for notifying users of alert information based on sentiment evaluation" refers to processes or devices that provide users with relevant notifications and warning information while taking into account the user's sentiment evaluation. 【0365】 "Means of receiving user feedback to improve the accuracy of automated task generation" refers to processes or devices that reflect user opinions and feelings to improve the accuracy of task generation. 【0366】 "A means of predicting progress and determining the next action based on past data using reinforcement learning" refers to a process or device that applies historical data analysis and machine learning techniques to predict future events and set necessary actions. 【0367】 Embodiments of the present invention relate to a system that highly integrates user progress management and sentiment analysis to achieve efficient project management. This system includes a server, terminals, and a sentiment engine. 【0368】 The server collects data from terminals via the network and analyzes that data. Specifically, it uses an Application Programming Interface (API) to retrieve task management data and compares it with historical data managed in a database. Machine learning models are used for data processing, which evaluates the progress of tasks. 【0369】 The emotion engine utilizes voice analysis libraries and facial recognition AI to analyze the user's voice tone and facial expressions in real time. For example, it uses open-source voice analysis tools to determine how stressed a user is during a meeting. The results are sent to the server, and alerts are generated as needed. 【0370】 The device performs tasks based on instructions from the server and sends email and application notifications to the user. The appropriate timing of notifications is determined by considering the user's schedule and emotional state. 【0371】 For example, if a user expresses negative feelings about the project's progress, the server generates a prompt message stating, "A user has expressed concern about the progress of an important project. Action is required," and notifies the administrator. The terminal then quickly takes action based on this message to assist the user. 【0372】 This system allows us to collect user feedback and improve the accuracy of task generation through reinforcement learning. As a result, more personalized task management that takes into account the user's emotional state becomes possible. 【0373】 The flow of the specific processing in Example 2 will be explained using Figure 13. 【0374】 Step 1: 【0375】 The server collects user task management data from the terminal. The input is task data entered by the user into the application, and the output is task information stored in a database on the server. Specifically, the server collects data via an API and processes it to obtain task deadlines and priority information. 【0376】 Step 2: 【0377】 The server analyzes the collected task data and performs progress evaluation. The input is the collected task information, and the output is the evaluated progress data. Here, a machine learning model is used to calculate the degree of task completion and perform specific processing to evaluate progress against the schedule. 【0378】 Step 3: 【0379】 The emotion engine analyzes the user's voice tone and facial expression data to evaluate the user's emotional state. Input is the user's voice and image data, and output is the emotion evaluation result. Using voice analysis libraries and facial recognition technology, it specifically determines the user's stress level and satisfaction level. 【0380】 Step 4: 【0381】 The server automatically generates necessary tasks and issues alerts based on progress and sentiment assessment results. Inputs are progress assessment data and sentiment assessment results, while outputs are the generated tasks and alerts. Based on this, the server generates prompt messages and performs specific actions to notify administrators and relevant parties. 【0382】 Step 5: 【0383】 The device presents task information received from the server to the user and executes email and app notifications according to the user's instructions. Input consists of tasks and alert information from the server, while output is the notification results sent to the user. The device takes the user's emotions into consideration while providing timely notifications and performing specific actions to track progress. 【0384】 (Application Example 2) 【0385】 Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal." 【0386】 In modern industrial settings, workers' emotional states significantly impact work efficiency and safety. However, conventional systems struggle to provide real-time feedback based on workers' emotions, resulting in stress and anxiety. To address this, there is a need for technology that can efficiently provide emotionally sensitive support. 【0387】 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. 【0388】 In this invention, the server includes means for collecting and analyzing data, means for automatically generating tasks based on the analysis results, and means for analyzing the user's emotional state and providing emotionally sensitive feedback based on the analysis results. This enables appropriate feedback tailored to the user's emotional state. 【0389】 "Means of collecting and analyzing data" refers to a system that takes in information acquired through sensors and input devices, analyzes its content using algorithms, and converts it into a usable format. 【0390】 "Means for automatically generating tasks based on analysis results" refers to a mechanism that automatically creates appropriate processes and tasks based on the results of data analysis, enabling the user to proceed to the next step. 【0391】 "Means for executing generated tasks" refers to functions within a system that carry out tasks generated as concrete actions or operations. 【0392】 "A means of monitoring execution results, detecting anomalies, and generating alerts" refers to a system that monitors the execution status of tasks and issues warnings if anomalies or problems occur. 【0393】 "Means of notifying users of alert information" refers to means of communicating warnings and important information generated by the system to users. 【0394】 "A means of analyzing a user's emotional state and providing emotionally sensitive feedback based on the analysis results" refers to a technology that performs analysis to determine a user's emotions and provides responses or messages accordingly. 【0395】 The program to implement this system possesses the technology to collect and analyze data through a server, terminal, and emotion engine, and to provide feedback that takes the user's emotions into consideration. The server plays the role of data collection, analyzing data using analysis algorithms based on information obtained from sensors and various input devices. Specifically, it can evaluate the user's emotional state by using voice tone and facial expression recognition technologies. Based on these analysis results, the server automatically generates appropriate tasks and sends them to the terminal as needed. 【0396】 The terminal is a device for receiving and executing generated tasks, monitoring anomalies and problems in real time, and generating alerts as needed. The alert information is analyzed through an emotion engine, and feedback is provided to the user. This feedback is presented to the user in written or interactive formats and is used for work improvement and emotional support. 【0397】 As a concrete example, if a worker experiences stress on the factory floor, the system immediately analyzes their emotions and notifies the manager, while simultaneously displaying a message on the worker's terminal encouraging them to take a break. This function aims to enhance user support and improve productivity. 【0398】 By utilizing generative AI models and prompt messages, more accurate feedback and task management are achieved. For example, prompt messages such as, "How can we analyze visual and audio data of workers during their work and suggest appropriate manager notifications and feedback to workers when stress or anxiety is detected?" can be used. 【0399】 The flow of a specific process in Application Example 2 will be explained using Figure 14. 【0400】 Step 1: 【0401】 The server collects data from sensors and input devices. Specifically, it captures voice tone and facial expression data. This data is saved as initial input and prepared for analysis. 【0402】 Step 2: 【0403】 The server passes the collected data to the analysis engine. The analysis engine processes the data using speech recognition and image processing technologies to determine the user's emotional state. As a result of the analysis, the emotional state (e.g., stress level and anxiety index) is output as numerical data. 【0404】 Step 3: 【0405】 The server automatically generates the next task based on the analysis results. Specifically, if the user's emotional state indicates stress, it prepares a suggestion to take a break and a message of encouragement. This task is sent to the terminal and prepared for execution. 【0406】 Step 4: 【0407】 The terminal receives tasks from the server and displays specific instructions. It also notifies the user of break suggestion messages and reminders, and monitors the task's progress. 【0408】 Step 5: 【0409】 The system monitors whether the user has responded to feedback via the device and returns the result to the server. The device collects user operation and response data as input and sends it to the server. 【0410】 Step 6: 【0411】 Based on the feedback data it receives, the server updates its reinforcement learning model to improve the accuracy of its task generation algorithm. This process makes it possible to further improve the accuracy of task generation in subsequent attempts. 【0412】 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. 【0413】 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. 【0414】 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. 【0415】 [Third Embodiment] 【0416】 Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment. 【0417】 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. 【0418】 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). 【0419】 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. 【0420】 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. 【0421】 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). 【0422】 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. 【0423】 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. 【0424】 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. 【0425】 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. 【0426】 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. 【0427】 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". 【0428】 The system implementing this invention integrates the functions of data collection, analysis, automatic task generation, execution, monitoring, alert generation, notification, feedback reception, and prediction using reinforcement learning. The main components of the system, the server, terminals, and users, each play their respective roles. 【0429】 The server receives project information from terminals via the network, analyzes this information, and understands the current progress. Based on the analyzed progress data, the server automatically generates tasks under specific conditions. This task generation incorporates past performance data and user feedback to formulate highly accurate action plans. 【0430】 The terminal receives tasks delivered from the server and executes them. Depending on the task, physical and digital actions are taken, such as system operations or sending emails. The progress and results of the executed tasks are reported from the terminal to the server in real time. 【0431】 The server monitors the execution results based on these reports and immediately generates an alert if an anomaly is detected. This alert is promptly notified to the user, allowing them to resolve the issue directly if necessary. 【0432】 Furthermore, the server uses reinforcement learning to leverage past case data and feedback to more effectively determine the next action. This allows it to flexibly respond to the ever-changing business environment and improve productivity. 【0433】 For example, if a project is found to be at risk of not being completed on time, the server automatically generates the optimal countermeasures task. The terminal executes this task and reports its progress to the server. Based on the alerts sent from the server, the user determines whether human intervention is necessary and takes action if required. In this way, the system supports the efficient operation of projects and distributes the workload. 【0434】 The following describes the processing flow. 【0435】 Step 1: 【0436】 The server periodically collects case data from terminals via the network. Here, APIs and database queries are used to effectively retrieve the necessary information. 【0437】 Step 2: 【0438】 The server analyzes the collected data and evaluates the progress of projects in real time. Statistical algorithms and machine learning models are used in the analysis to detect anomalies and delay risks. 【0439】 Step 3: 【0440】 The server determines the necessary actions based on the analysis results. Specifically, it automatically generates tasks if the conditions are met and adds them to the execution queue. 【0441】 Step 4: 【0442】 The terminal receives tasks from the server and performs specific actions. Examples include automating system operations and sending emails. The terminal reports the results of the tasks it has performed back to the server. 【0443】 Step 5: 【0444】 The server receives result reports from the terminals and analyzes the execution results. If an anomaly is detected or if certain indicators fall below a certain level, an alert is immediately generated. 【0445】 Step 6: 【0446】 The server notifies users of any alerts that occur. These notifications are sent via email or a dashboard, allowing users to check the status. 【0447】 Step 7: 【0448】 Users receive alert notifications from the server and take additional actions manually as needed, such as issuing instructions to the project team or scheduling meetings. 【0449】 Step 8: 【0450】 The server uses reinforcement learning to improve its task generation algorithm by leveraging past data and feedback. This learning process improves the accuracy of subsequent operations. 【0451】 (Example 1) 【0452】 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." 【0453】 In today's business environment, it is essential to track project progress in real time and manage risks efficiently. However, manual data collection and analysis alone can lead to delays and reduce project efficiency. In addition, the inability to respond quickly to generated alerts can lead to further delays and risks. Therefore, to solve these problems, automated data analysis and task generation, along with flexible responses utilizing feedback, are necessary. 【0454】 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. 【0455】 In this invention, the server includes means for collecting data, receiving and storing information, performing data analysis, identifying progress and risk factors, and executing generated tasks by physical or electronic means. This enables automatic and real-time management of project progress and efficient risk response. 【0456】 "Data collection" refers to the process of gathering information, specifically receiving and storing case information from terminals via a communication network. 【0457】 "Data analysis" refers to the process of processing collected information and performing calculations and analyses to identify progress and risk factors. 【0458】 "Automatic task generation" refers to the process of constructing a work plan and generating an action plan based on the results of analysis and specific conditions. 【0459】 "To execute" means to perform a specified task or operation through physical or electronic means. 【0460】 "Progress and results reporting" refers to continuously communicating the progress and results of completed tasks to the information system. 【0461】 "Monitoring" refers to activities that continuously track the progress and results of work and detect abnormal situations. 【0462】 "Alert generation" refers to creating a warning and notification when an anomaly is detected, prompting a quick response. 【0463】 "User notification" refers to providing a means of informing human users of the generated warning information. 【0464】 "Feedback collection" refers to activities that involve gathering reactions and evaluations from users to help improve the system's performance. 【0465】 A "machine learning algorithm" is a computational method that learns from past data to make predictions and decisions, and it supports the automation and optimization of systems. 【0466】 Modes for carrying out the invention 【0467】 This invention is an integrated system that includes data collection, analysis, automated task generation and execution, monitoring, alert generation, notification, feedback reception, and prediction using reinforcement learning. The main components are a server, terminals, and users, each playing a specific role. 【0468】 The server performs data collection and analysis. Specifically, it receives data from multiple terminals via HTTP requests, structures the information using database management software, and stores it. By using an analysis platform such as Apache Spark, it enables real-time data analysis to identify project progress and potential risks. The analysis results are combined with historical data and feedback to be used for automated task generation. 【0469】 Terminals receive tasks delivered from the server and perform the actual operations and processing. Tasks can be executed electronically using physical devices or automated scripts using a "scripting language." For example, in an "email sending task," information is communicated to relevant parties through email client software. Each terminal reports the progress and results of the tasks it has performed to the server in real time, supporting more detailed monitoring and feedback accumulation. 【0470】 Users receive information and alerts from servers and terminals and intervene as needed. Generated alerts are notified to users in a way that prompts real-time decision-making. Users utilize the "communication platform" to quickly consider countermeasures within the team and reallocate project resources as necessary. 【0471】 The system utilizes reinforcement learning algorithms, using past case data and feedback as learning material to determine the next optimal action. This process employs a "machine learning framework," enabling it to continuously adapt flexibly to changes in business operations. 【0472】 For example, if a project delay risk is identified, the server automatically generates the optimal countermeasure. The terminal implements this countermeasure and reports the results. By receiving alerts, users can take necessary interventions and properly manage the project's progress. Effective operation of this system makes project progress management more efficient and allows for the distribution of workload. 【0473】 An example of a prompt would be, "If a project is at risk of missing its deadline, how does the server automatically generate mitigation tasks? And how can the user intervene?" This prompt helps understand how the system works by leveraging the generative AI model. 【0474】 The flow of the specific processing in Example 1 will be explained using Figure 11. 【0475】 Step 1: 【0476】 The server receives case information from terminals via HTTP requests. This input data is in JSON format, and the server parses it before storing it in a database management system. Storing the data allows for quick access during subsequent analysis. 【0477】 Step 2: 【0478】 The server uses an "analysis platform" to perform data analysis based on the stored data. In this step, historical data is compared with current data to identify progress and risk factors. Finally, the analysis results are output and used in the task generation process. 【0479】 Step 3: 【0480】 The server automatically generates tasks based on analysis results, provided certain conditions are met. This process uses an "optimization algorithm" to maximize the efficiency of each task. Inputs include analysis output data and past feedback, which are then used to generate output as task information. 【0481】 Step 4: 【0482】 The terminal receives task information sent from the server and performs the task according to the specific instructions. This step utilizes physical or electronic means, for example, to automate sending emails using a "scripting language." The output is the result of the task execution. 【0483】 Step 5: 【0484】 The terminal reports the progress and results of the executed task to the server via an HTTP POST request. The input includes the task's progress and results, and the output is received by the server as report data. 【0485】 Step 6: 【0486】 The server monitors the received report data and immediately generates an alert if an anomaly is detected in the system. The input in this step is progress report data, and the output generates and stores alert information. 【0487】 Step 7: 【0488】 Users receive alert notifications from the server and intervene as needed. They receive alert information displayed on the screen as input, make decisions and adjustments, and produce outputs such as reallocating resources through project management software. 【0489】 Step 8: 【0490】 The server collects user feedback and learns from this information using a reinforcement learning algorithm. At this stage, it takes feedback data as input and updates parameters based on the learning results. This further optimizes the generation of subsequent tasks. 【0491】 (Application Example 1) 【0492】 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." 【0493】 There is a need to improve the operational efficiency of robots in production systems, quickly detect operational anomalies, and take appropriate action. Furthermore, a challenge is to improve productivity and reduce workload by automating the optimization of future operations based on past data. 【0494】 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. 【0495】 In this invention, the server includes a device for acquiring and analyzing data, a device for automatically generating tasks based on the analysis results, a device for performing the generated tasks, a device for monitoring the execution results, detecting anomalies and generating alarms, a device for notifying users of alarm information, and a device for managing the operation of equipment involved in task execution and using reinforcement learning to generate new tasks. This makes it possible to optimize the operation of robots in the production system and respond quickly to abnormal conditions. Furthermore, it is possible to efficiently perform repetitive tasks using reinforcement learning. 【0496】 "Data" refers to information and records related to the execution of business operations, and serves as the basis for analysis and business generation. 【0497】 "Analysis" is the process of analyzing business conditions based on acquired data and extracting information necessary for carrying out business operations. 【0498】 "Work" refers to a set of tasks that are planned and carried out to achieve a specific objective. 【0499】 "Execution" refers to carrying out planned tasks and achieving specified goals. 【0500】 "Monitoring" refers to the act of constantly checking the progress of work and keeping an eye out for any abnormalities. 【0501】 "An anomaly" refers to an unexpected situation or problem that occurs during the performance of duties. 【0502】 An "alarm" is a warning message issued when an abnormality is detected, intended to prompt a quick response. 【0503】 "Users" refers to individuals or organizations that operate the system and monitor its operation. 【0504】 "Reinforcement learning" is a machine learning technique that learns the optimal actions based on past records and applies them to future work performance. 【0505】 "Device" refers to a component of a machine or system that performs a specific function. 【0506】 The system for implementing this invention integrates the functions of detailed data collection, analysis, automated task generation, execution, monitoring, alarm generation, notification, feedback reception, and optimization through reinforcement learning. This system includes three main components: a server, terminals, and users. 【0507】 The server is built on a cloud infrastructure (e.g., Amazon Web Services) and acquires production-related data from terminals via the network. This acquired data is analyzed using Python data analysis libraries (such as pandas and scikit-learn). Based on the analysis results, past production records and feedback information are integrated to automatically generate business processes. 【0508】 The generated tasks are sent to factory robot terminals equipped with NVIDIA Jetson. These terminals use multiple sensors and control devices to execute the received tasks. The terminals send real-time data acquired during execution back to the server, which monitors the execution status based on this data and immediately generates an alarm if an anomaly is detected. 【0509】 Alarm information is sent to the user's smartphone and displayed through an application developed using React Native. Based on the alarm, the user can take necessary action and directly impact the system. 【0510】 Furthermore, the server performs reinforcement learning through a generative AI model, using past data to improve operations and optimize future operations. Through this reinforcement learning, the system improves the efficiency of its operations over time. 【0511】 As a concrete example, consider a scenario where a bottleneck occurs on a production line. The server can analyze the cause, automatically generate new tasks to adjust specific processes, and send them as tasks to robot terminals. This process smooths the production flow and improves efficiency. Using the prompt, "Please tell me the best way to generate and execute specific tasks to resolve the bottleneck on the production line," the AI ​​model assists in generating the optimal tasks. 【0512】 The flow of a specific process in Application Example 1 will be explained using Figure 12. 【0513】 Step 1: 【0514】 The server acquires production-related data from factory terminals via the network. The terminals transmit raw data, including robot movements and information from sensors. Based on this input data, the server stores it in a database and prepares it for analysis. 【0515】 Step 2: 【0516】 The server preprocesses the acquired raw data using the Python pandas library. This removes noise, normalizes the data, and converts it into a format suitable for analysis. The output includes organized production data. 【0517】 Step 3: 【0518】 The server uses the scikit-learn library to analyze the preprocessed data. This analysis uses machine learning algorithms to identify bottlenecks and anomaly patterns in the production line. The output includes the identified problems and their locations. 【0519】 Step 4: 【0520】 The server automatically generates new tasks based on the analysis results. Here, it uses a generation AI model to reference historical data and design the optimal task plan. The prompt "Generate specific tasks to resolve bottlenecks in the production line and tell me the best way to execute them" is used to support the model. The output is the newly generated task. 【0521】 Step 5: 【0522】 The terminal receives business tasks sent from the server and uses the NVIDIA Jetson platform to issue execution instructions to the robot. Based on these tasks, the terminal controls the robot's movements, performing optimized actions at each stage of the process. The output is the improvement in production efficiency resulting from the executed business tasks. 【0523】 Step 6: 【0524】 The server monitors execution data from terminals in real time and immediately generates an alarm if an anomaly is detected. This alarm is sent to the user through the alert system. The output is an alarm message that the user can quickly review. 【0525】 Step 7: 【0526】 Users receive alerts via a smartphone app and analyze their content. They then send feedback to the system as needed to adjust their work processes. The output consists of adjusted work instructions and improvement measures. 【0527】 Step 8: 【0528】 The server executes a reinforcement learning algorithm, continuously learning from the feedback it receives and past records. This learning is then used in subsequent task generation and optimization processes. The output is insights and strategies for future business improvement. 【0529】 Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions. 【0530】 The system of this invention, in addition to conventional progress management and automation systems, has the function of recognizing user emotions and performing actions accordingly. The system mainly consists of a server, terminals, an emotion engine, and users. 【0531】 The server collects necessary data from terminals via the network and analyzes it. Based on the analyzed information, the server evaluates the progress and automatically generates the necessary tasks. These tasks are sent to terminals, where appropriate system operations or email sending are performed. 【0532】 The emotion engine evaluates the user's emotional state in real time through interaction with the user. This evaluation uses voice tone analysis and facial recognition technology to determine the user's stress level and satisfaction level. If the server determines that the user is feeling anxious or stressed, it generates an alert and sets up emotion-sensitive feedback methods in addition to conventional notification methods. 【0533】 For example, if the emotion engine determines that a user is expressing negative emotions about project progress, the server generates an alert and promptly notifies the support team. Based on the alert, the terminal can then perform additional tasks to assist the user. In this way, the system responds flexibly to the user's emotional state, aiming to improve project success and user satisfaction. Furthermore, user feedback is also analyzed through the emotion engine, and the results are used to improve the accuracy of automated task generation. This enables the system to achieve more personalized task management and support efficient business operations. 【0534】 The following describes the processing flow. 【0535】 Step 1: 【0536】 The server collects project-related data from terminals. This data includes progress information and task completion status. 【0537】 Step 2: 【0538】 The server analyzes the collected data, evaluates the progress of each project, and identifies anomalies and risks. This analysis uses historical data and established baseline values. 【0539】 Step 3: 【0540】 The emotion engine evaluates the user's emotional state through interaction with the user. It uses speech recognition and facial recognition systems to analyze the user's stress level and satisfaction level. 【0541】 Step 4: 【0542】 The server receives the evaluation results from the emotion engine and generates an alert if it determines that the user is experiencing stress. This alert contains important information that requires consideration for the user. 【0543】 Step 5: 【0544】 The device receives alerts from the server and notifies the user as needed. The notification method is selected considering the user's emotional state. 【0545】 Step 6: 【0546】 The device automatically performs support tasks based on the generated alerts, including suggesting additional assistance and contacting support personnel. 【0547】 Step 7: 【0548】 The user reviews the alert notification and decides on any further actions they deem necessary. Based on the user's judgment, further actions are taken to resolve the problem. 【0549】 Step 8: 【0550】 The server receives user feedback, analyzes it using an emotion engine, and uses that feedback to improve the accuracy of automated task generation. This feedback processing enables the system to provide more precise and personalized responses. 【0551】 (Example 2) 【0552】 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." 【0553】 Traditional progress management systems fail to consider users' emotional states, resulting in an inability to properly manage user satisfaction and stress levels, ultimately leading to decreased project management efficiency. Furthermore, the inaccuracy of automated task generation hindered efficient work execution. 【0554】 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. 【0555】 In this invention, the server includes means for collecting and analyzing data, means for evaluating the user's emotional state in real time, and means for notifying the user of alert information based on the emotional evaluation. This enables project management that takes the user's emotional state into consideration, leading to improved user satisfaction and effective task management. 【0556】 "Means of collecting and analyzing data" refers to processes and devices for gathering necessary information from users and the environment, and for processing that information to obtain meaningful insights. 【0557】 "Means for automatically generating tasks" refer to processes or devices that mechanically generate tasks to be performed based on collected and analyzed data. 【0558】 "Means for evaluating a user's emotional state in real time" refers to processes or devices that analyze a user's voice, image data, etc., to instantly determine the user's emotions. 【0559】 "Means for executing generated tasks" refers to the processes or devices that actually carry out the generated tasks according to pre-set instructions. 【0560】 "Means for monitoring execution results, detecting anomalies, and generating alerts" refers to processes or devices that verify the results of tasks during and after execution and issue warnings when problems occur. 【0561】 "Means for notifying users of alert information based on sentiment evaluation" refers to processes or devices that provide users with relevant notifications and warning information while taking into account the user's sentiment evaluation. 【0562】 "Means of receiving user feedback to improve the accuracy of automated task generation" refers to processes or devices that reflect user opinions and feelings to improve the accuracy of task generation. 【0563】 "A means of predicting progress and determining the next action based on past data using reinforcement learning" refers to a process or device that applies historical data analysis and machine learning techniques to predict future events and set necessary actions. 【0564】 Embodiments of the present invention relate to a system that highly integrates user progress management and sentiment analysis to achieve efficient project management. This system includes a server, terminals, and a sentiment engine. 【0565】 The server collects data from terminals via the network and analyzes that data. Specifically, it uses an Application Programming Interface (API) to retrieve task management data and compares it with historical data managed in a database. Machine learning models are used for data processing, which evaluates the progress of tasks. 【0566】 The emotion engine utilizes voice analysis libraries and facial recognition AI to analyze the user's voice tone and facial expressions in real time. For example, it uses open-source voice analysis tools to determine how stressed a user is during a meeting. The results are sent to the server, and alerts are generated as needed. 【0567】 The device performs tasks based on instructions from the server and sends email and application notifications to the user. The appropriate timing of notifications is determined by considering the user's schedule and emotional state. 【0568】 For example, if a user expresses negative feelings about the project's progress, the server generates a prompt message stating, "A user has expressed concern about the progress of an important project. Action is required," and notifies the administrator. The terminal then quickly takes action based on this message to assist the user. 【0569】 This system allows us to collect user feedback and improve the accuracy of task generation through reinforcement learning. As a result, more personalized task management that takes into account the user's emotional state becomes possible. 【0570】 The flow of the specific processing in Example 2 will be explained using Figure 13. 【0571】 Step 1: 【0572】 The server collects user task management data from the terminal. The input is task data entered by the user into the application, and the output is task information stored in a database on the server. Specifically, the server collects data via an API and processes it to obtain task deadlines and priority information. 【0573】 Step 2: 【0574】 The server analyzes the collected task data and performs progress evaluation. The input is the collected task information, and the output is the evaluated progress data. Here, a machine learning model is used to calculate the degree of task completion and perform specific processing to evaluate progress against the schedule. 【0575】 Step 3: 【0576】 The emotion engine analyzes the user's voice tone and facial expression data to evaluate the user's emotional state. Input is the user's voice and image data, and output is the emotion evaluation result. Using voice analysis libraries and facial recognition technology, it specifically determines the user's stress level and satisfaction level. 【0577】 Step 4: 【0578】 The server automatically generates necessary tasks and issues alerts based on progress and sentiment assessment results. Inputs are progress assessment data and sentiment assessment results, while outputs are the generated tasks and alerts. Based on this, the server generates prompt messages and performs specific actions to notify administrators and relevant parties. 【0579】 Step 5: 【0580】 The device presents task information received from the server to the user and executes email and app notifications according to the user's instructions. Input consists of tasks and alert information from the server, while output is the notification results sent to the user. The device takes the user's emotions into consideration while providing timely notifications and performing specific actions to track progress. 【0581】 (Application Example 2) 【0582】 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." 【0583】 In modern industrial settings, workers' emotional states significantly impact work efficiency and safety. However, conventional systems struggle to provide real-time feedback based on workers' emotions, resulting in stress and anxiety. To address this, there is a need for technology that can efficiently provide emotionally sensitive support. 【0584】 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. 【0585】 In this invention, the server includes means for collecting and analyzing data, means for automatically generating tasks based on the analysis results, and means for analyzing the user's emotional state and providing emotionally sensitive feedback based on the analysis results. This enables appropriate feedback tailored to the user's emotional state. 【0586】 "Means of collecting and analyzing data" refers to a system that takes in information acquired through sensors and input devices, analyzes its content using algorithms, and converts it into a usable format. 【0587】 "Means for automatically generating tasks based on analysis results" refers to a mechanism that automatically creates appropriate processes and tasks based on the results of data analysis, enabling the user to proceed to the next step. 【0588】 "Means for executing generated tasks" refers to functions within a system that carry out tasks generated as concrete actions or operations. 【0589】 "A means of monitoring execution results, detecting anomalies, and generating alerts" refers to a system that monitors the execution status of tasks and issues warnings if anomalies or problems occur. 【0590】 "Means of notifying users of alert information" refers to means of communicating warnings and important information generated by the system to users. 【0591】 "A means of analyzing a user's emotional state and providing emotionally sensitive feedback based on the analysis results" refers to a technology that performs analysis to determine a user's emotions and provides responses or messages accordingly. 【0592】 The program to implement this system possesses the technology to collect and analyze data through a server, terminal, and emotion engine, and to provide feedback that takes the user's emotions into consideration. The server plays the role of data collection, analyzing data using analysis algorithms based on information obtained from sensors and various input devices. Specifically, it can evaluate the user's emotional state by using voice tone and facial expression recognition technologies. Based on these analysis results, the server automatically generates appropriate tasks and sends them to the terminal as needed. 【0593】 The terminal is a device for receiving and executing generated tasks, monitoring anomalies and problems in real time, and generating alerts as needed. The alert information is analyzed through an emotion engine, and feedback is provided to the user. This feedback is presented to the user in written or interactive formats and is used for work improvement and emotional support. 【0594】 As a concrete example, if a worker experiences stress on the factory floor, the system immediately analyzes their emotions and notifies the manager, while simultaneously displaying a message on the worker's terminal encouraging them to take a break. This function aims to enhance user support and improve productivity. 【0595】 By utilizing generative AI models and prompt messages, more accurate feedback and task management are achieved. For example, prompt messages such as, "How can we analyze visual and audio data of workers during their work and suggest appropriate manager notifications and feedback to workers when stress or anxiety is detected?" can be used. 【0596】 The flow of a specific process in Application Example 2 will be explained using Figure 14. 【0597】 Step 1: 【0598】 The server collects data from sensors and input devices. Specifically, it captures voice tone and facial expression data. This data is saved as initial input and prepared for analysis. 【0599】 Step 2: 【0600】 The server passes the collected data to the analysis engine. The analysis engine processes the data using speech recognition and image processing technologies to determine the user's emotional state. As a result of the analysis, the emotional state (e.g., stress level and anxiety index) is output as numerical data. 【0601】 Step 3: 【0602】 The server automatically generates the next task based on the analysis results. Specifically, if the user's emotional state indicates stress, it prepares a suggestion to take a break and a message of encouragement. This task is sent to the terminal and prepared for execution. 【0603】 Step 4: 【0604】 The terminal receives tasks from the server and displays specific instructions. It also notifies the user of break suggestion messages and reminders, and monitors the task's progress. 【0605】 Step 5: 【0606】 The system monitors whether the user has responded to feedback via the device and returns the result to the server. The device collects user operation and response data as input and sends it to the server. 【0607】 Step 6: 【0608】 Based on the feedback data it receives, the server updates its reinforcement learning model to improve the accuracy of its task generation algorithm. This process makes it possible to further improve the accuracy of task generation in subsequent attempts. 【0609】 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. 【0610】 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. 【0611】 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. 【0612】 [Fourth Embodiment] 【0613】 Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment. 【0614】 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. 【0615】 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). 【0616】 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. 【0617】 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. 【0618】 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). 【0619】 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. 【0620】 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. 【0621】 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. 【0622】 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. 【0623】 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. 【0624】 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. 【0625】 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". 【0626】 The system implementing this invention integrates the functions of data collection, analysis, automatic task generation, execution, monitoring, alert generation, notification, feedback reception, and prediction using reinforcement learning. The main components of the system, the server, terminals, and users, each play their respective roles. 【0627】 The server receives project information from terminals via the network, analyzes this information, and understands the current progress. Based on the analyzed progress data, the server automatically generates tasks under specific conditions. This task generation incorporates past performance data and user feedback to formulate highly accurate action plans. 【0628】 The terminal receives tasks delivered from the server and executes them. Depending on the task, physical and digital actions are taken, such as system operations or sending emails. The progress and results of the executed tasks are reported from the terminal to the server in real time. 【0629】 The server monitors the execution results based on these reports and immediately generates an alert if an anomaly is detected. This alert is promptly notified to the user, allowing them to resolve the issue directly if necessary. 【0630】 Furthermore, the server uses reinforcement learning to leverage past case data and feedback to more effectively determine the next action. This allows it to flexibly respond to the ever-changing business environment and improve productivity. 【0631】 For example, if a project is found to be at risk of not being completed on time, the server automatically generates the optimal countermeasures task. The terminal executes this task and reports its progress to the server. Based on the alerts sent from the server, the user determines whether human intervention is necessary and takes action if required. In this way, the system supports the efficient operation of projects and distributes the workload. 【0632】 The following describes the processing flow. 【0633】 Step 1: 【0634】 The server periodically collects case data from terminals via the network. Here, APIs and database queries are used to effectively retrieve the necessary information. 【0635】 Step 2: 【0636】 The server analyzes the collected data and evaluates the progress of projects in real time. Statistical algorithms and machine learning models are used in the analysis to detect anomalies and delay risks. 【0637】 Step 3: 【0638】 The server determines the necessary actions based on the analysis results. Specifically, it automatically generates tasks if the conditions are met and adds them to the execution queue. 【0639】 Step 4: 【0640】 The terminal receives tasks from the server and performs specific actions. Examples include automating system operations and sending emails. The terminal reports the results of the tasks it has performed back to the server. 【0641】 Step 5: 【0642】 The server receives result reports from the terminals and analyzes the execution results. If an anomaly is detected or if certain indicators fall below a certain level, an alert is immediately generated. 【0643】 Step 6: 【0644】 The server notifies users of any alerts that occur. These notifications are sent via email or a dashboard, allowing users to check the status. 【0645】 Step 7: 【0646】 Users receive alert notifications from the server and take additional actions manually as needed, such as issuing instructions to the project team or scheduling meetings. 【0647】 Step 8: 【0648】 The server uses reinforcement learning to improve its task generation algorithm by leveraging past data and feedback. This learning process improves the accuracy of subsequent operations. 【0649】 (Example 1) 【0650】 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". 【0651】 In today's business environment, it is essential to track project progress in real time and manage risks efficiently. However, manual data collection and analysis alone can lead to delays and reduce project efficiency. In addition, the inability to respond quickly to generated alerts can lead to further delays and risks. Therefore, to solve these problems, automated data analysis and task generation, along with flexible responses utilizing feedback, are necessary. 【0652】 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. 【0653】 In this invention, the server includes means for collecting data, receiving and storing information, performing data analysis, identifying progress and risk factors, and executing generated tasks by physical or electronic means. This enables automatic and real-time management of project progress and efficient risk response. 【0654】 "Data collection" refers to the process of gathering information, specifically receiving and storing case information from terminals via a communication network. 【0655】 "Data analysis" refers to the process of processing collected information and performing calculations and analyses to identify progress and risk factors. 【0656】 "Automatic task generation" refers to the process of constructing a work plan and generating an action plan based on the results of analysis and specific conditions. 【0657】 "To execute" means to perform a specified task or operation through physical or electronic means. 【0658】 "Progress and results reporting" refers to continuously communicating the progress and results of completed tasks to the information system. 【0659】 "Monitoring" refers to activities that continuously track the progress and results of work and detect abnormal situations. 【0660】 "Alert generation" refers to creating a warning and notification when an anomaly is detected, prompting a quick response. 【0661】 "User notification" refers to providing a means of informing human users of the generated warning information. 【0662】 "Feedback collection" refers to activities that involve gathering reactions and evaluations from users to help improve the system's performance. 【0663】 A "machine learning algorithm" is a computational method that learns from past data to make predictions and decisions, and it supports the automation and optimization of systems. 【0664】 Modes for carrying out the invention 【0665】 This invention is an integrated system that includes data collection, analysis, automated task generation and execution, monitoring, alert generation, notification, feedback reception, and prediction using reinforcement learning. The main components are a server, terminals, and users, each playing a specific role. 【0666】 The server performs data collection and analysis. Specifically, it receives data from multiple terminals via HTTP requests, structures the information using database management software, and stores it. By using an analysis platform such as Apache Spark, it enables real-time data analysis to identify project progress and potential risks. The analysis results are combined with historical data and feedback to be used for automated task generation. 【0667】 Terminals receive tasks delivered from the server and perform the actual operations and processing. Tasks can be executed electronically using physical devices or automated scripts using a "scripting language." For example, in an "email sending task," information is communicated to relevant parties through email client software. Each terminal reports the progress and results of the tasks it has performed to the server in real time, supporting more detailed monitoring and feedback accumulation. 【0668】 Users receive information and alerts from servers and terminals and intervene as needed. Generated alerts are notified to users in a way that prompts real-time decision-making. Users utilize the "communication platform" to quickly consider countermeasures within the team and reallocate project resources as necessary. 【0669】 The system utilizes reinforcement learning algorithms, using past case data and feedback as learning material to determine the next optimal action. This process employs a "machine learning framework," enabling it to continuously adapt flexibly to changes in business operations. 【0670】 For example, if a project delay risk is identified, the server automatically generates the optimal countermeasure. The terminal implements this countermeasure and reports the results. By receiving alerts, users can take necessary interventions and properly manage the project's progress. Effective operation of this system makes project progress management more efficient and allows for the distribution of workload. 【0671】 An example of a prompt would be, "If a project is at risk of missing its deadline, how does the server automatically generate mitigation tasks? And how can the user intervene?" This prompt helps understand how the system works by leveraging the generative AI model. 【0672】 The flow of the specific processing in Example 1 will be explained using Figure 11. 【0673】 Step 1: 【0674】 The server receives case information from terminals via HTTP requests. This input data is in JSON format, and the server parses it before storing it in a database management system. Storing the data allows for quick access during subsequent analysis. 【0675】 Step 2: 【0676】 The server uses an "analysis platform" to perform data analysis based on the stored data. In this step, historical data is compared with current data to identify progress and risk factors. Finally, the analysis results are output and used in the task generation process. 【0677】 Step 3: 【0678】 The server automatically generates tasks based on analysis results, provided certain conditions are met. This process uses an "optimization algorithm" to maximize the efficiency of each task. Inputs include analysis output data and past feedback, which are then used to generate output as task information. 【0679】 Step 4: 【0680】 The terminal receives task information sent from the server and performs the task according to the specific instructions. This step utilizes physical or electronic means, for example, to automate sending emails using a "scripting language." The output is the result of the task execution. 【0681】 Step 5: 【0682】 The terminal reports the progress and results of the executed task to the server via an HTTP POST request. The input includes the task's progress and results, and the output is received by the server as report data. 【0683】 Step 6: 【0684】 The server monitors the received report data and immediately generates an alert if an anomaly is detected in the system. The input in this step is progress report data, and the output generates and stores alert information. 【0685】 Step 7: 【0686】 Users receive alert notifications from the server and intervene as needed. They receive alert information displayed on the screen as input, make decisions and adjustments, and produce outputs such as reallocating resources through project management software. 【0687】 Step 8: 【0688】 The server collects user feedback and learns from this information using a reinforcement learning algorithm. At this stage, it takes feedback data as input and updates parameters based on the learning results. This further optimizes the generation of subsequent tasks. 【0689】 (Application Example 1) 【0690】 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". 【0691】 There is a need to improve the operational efficiency of robots in production systems, quickly detect operational anomalies, and take appropriate action. Furthermore, a challenge is to improve productivity and reduce workload by automating the optimization of future operations based on past data. 【0692】 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. 【0693】 In this invention, the server includes a device for acquiring and analyzing data, a device for automatically generating tasks based on the analysis results, a device for performing the generated tasks, a device for monitoring the execution results, detecting anomalies and generating alarms, a device for notifying users of alarm information, and a device for managing the operation of equipment involved in task execution and using reinforcement learning to generate new tasks. This makes it possible to optimize the operation of robots in the production system and respond quickly to abnormal conditions. Furthermore, it is possible to efficiently perform repetitive tasks using reinforcement learning. 【0694】 "Data" refers to information and records related to the execution of business operations, and serves as the basis for analysis and business generation. 【0695】 "Analysis" is the process of analyzing business conditions based on acquired data and extracting information necessary for carrying out business operations. 【0696】 "Work" refers to a set of tasks that are planned and carried out to achieve a specific objective. 【0697】 "Execution" refers to carrying out planned tasks and achieving specified goals. 【0698】 "Monitoring" refers to the act of constantly checking the progress of work and keeping an eye out for any abnormalities. 【0699】 "An anomaly" refers to an unexpected situation or problem that occurs during the performance of duties. 【0700】 An "alarm" is a warning message issued when an abnormality is detected, intended to prompt a quick response. 【0701】 "Users" refers to individuals or organizations that operate the system and monitor its operation. 【0702】 "Reinforcement learning" is a machine learning technique that learns the optimal actions based on past records and applies them to future work performance. 【0703】 "Device" refers to a component of a machine or system that performs a specific function. 【0704】 The system for implementing this invention integrates the functions of detailed data collection, analysis, automated task generation, execution, monitoring, alarm generation, notification, feedback reception, and optimization through reinforcement learning. This system includes three main components: a server, terminals, and users. 【0705】 The server is built on a cloud infrastructure (e.g., Amazon Web Services) and acquires production-related data from terminals via the network. This acquired data is analyzed using Python data analysis libraries (such as pandas and scikit-learn). Based on the analysis results, past production records and feedback information are integrated to automatically generate business processes. 【0706】 The generated tasks are sent to factory robot terminals equipped with NVIDIA Jetson. These terminals use multiple sensors and control devices to execute the received tasks. The terminals send real-time data acquired during execution back to the server, which monitors the execution status based on this data and immediately generates an alarm if an anomaly is detected. 【0707】 Alarm information is sent to the user's smartphone and displayed through an application developed using React Native. Based on the alarm, the user can take necessary action and directly impact the system. 【0708】 Furthermore, the server performs reinforcement learning through a generative AI model, using past data to improve operations and optimize future operations. Through this reinforcement learning, the system improves the efficiency of its operations over time. 【0709】 As a concrete example, consider a scenario where a bottleneck occurs on a production line. The server can analyze the cause, automatically generate new tasks to adjust specific processes, and send them as tasks to robot terminals. This process smooths the production flow and improves efficiency. Using the prompt, "Please tell me the best way to generate and execute specific tasks to resolve the bottleneck on the production line," the AI ​​model assists in generating the optimal tasks. 【0710】 The flow of a specific process in Application Example 1 will be explained using Figure 12. 【0711】 Step 1: 【0712】 The server acquires production-related data from factory terminals via the network. The terminals transmit raw data, including robot movements and information from sensors. Based on this input data, the server stores it in a database and prepares it for analysis. 【0713】 Step 2: 【0714】 The server preprocesses the acquired raw data using the Python pandas library. This removes noise, normalizes the data, and converts it into a format suitable for analysis. The output includes organized production data. 【0715】 Step 3: 【0716】 The server uses the scikit-learn library to analyze the preprocessed data. This analysis uses machine learning algorithms to identify bottlenecks and anomaly patterns in the production line. The output includes the identified problems and their locations. 【0717】 Step 4: 【0718】 The server automatically generates new tasks based on the analysis results. Here, it uses a generation AI model to reference historical data and design the optimal task plan. The prompt "Generate specific tasks to resolve bottlenecks in the production line and tell me the best way to execute them" is used to support the model. The output is the newly generated task. 【0719】 Step 5: 【0720】 The terminal receives business tasks sent from the server and uses the NVIDIA Jetson platform to issue execution instructions to the robot. Based on these tasks, the terminal controls the robot's movements, performing optimized actions at each stage of the process. The output is the improvement in production efficiency resulting from the executed business tasks. 【0721】 Step 6: 【0722】 The server monitors execution data from terminals in real time and immediately generates an alarm if an anomaly is detected. This alarm is sent to the user through the alert system. The output is an alarm message that the user can quickly review. 【0723】 Step 7: 【0724】 Users receive alerts via a smartphone app and analyze their content. They then send feedback to the system as needed to adjust their work processes. The output consists of adjusted work instructions and improvement measures. 【0725】 Step 8: 【0726】 The server executes a reinforcement learning algorithm, continuously learning from the feedback it receives and past records. This learning is then used in subsequent task generation and optimization processes. The output is insights and strategies for future business improvement. 【0727】 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. 【0728】 The system of this invention, in addition to conventional progress management and automation systems, has the function of recognizing user emotions and performing actions accordingly. The system mainly consists of a server, terminals, an emotion engine, and users. 【0729】 The server collects necessary data from terminals via the network and analyzes it. Based on the analyzed information, the server evaluates the progress and automatically generates the necessary tasks. These tasks are sent to terminals, where appropriate system operations or email sending are performed. 【0730】 The emotion engine evaluates the user's emotional state in real time through interaction with the user. This evaluation uses voice tone analysis and facial recognition technology to determine the user's stress level and satisfaction level. If the server determines that the user is feeling anxious or stressed, it generates an alert and sets up emotion-sensitive feedback methods in addition to conventional notification methods. 【0731】 For example, if the emotion engine determines that a user is expressing negative emotions about project progress, the server generates an alert and promptly notifies the support team. Based on the alert, the terminal can then perform additional tasks to assist the user. In this way, the system responds flexibly to the user's emotional state, aiming to improve project success and user satisfaction. Furthermore, user feedback is also analyzed through the emotion engine, and the results are used to improve the accuracy of automated task generation. This enables the system to achieve more personalized task management and support efficient business operations. 【0732】 The following describes the processing flow. 【0733】 Step 1: 【0734】 The server collects project-related data from terminals. This data includes progress information and task completion status. 【0735】 Step 2: 【0736】 The server analyzes the collected data, evaluates the progress of each project, and identifies anomalies and risks. This analysis uses historical data and established baseline values. 【0737】 Step 3: 【0738】 The emotion engine evaluates the user's emotional state through interaction with the user. It uses speech recognition and facial recognition systems to analyze the user's stress level and satisfaction level. 【0739】 Step 4: 【0740】 The server receives the evaluation results from the emotion engine and generates an alert if it determines that the user is experiencing stress. This alert contains important information that requires consideration for the user. 【0741】 Step 5: 【0742】 The device receives alerts from the server and notifies the user as needed. The notification method is selected considering the user's emotional state. 【0743】 Step 6: 【0744】 The device automatically performs support tasks based on the generated alerts, including suggesting additional assistance and contacting support personnel. 【0745】 Step 7: 【0746】 The user reviews the alert notification and decides on any further actions they deem necessary. Based on the user's judgment, further actions are taken to resolve the problem. 【0747】 Step 8: 【0748】 The server receives user feedback, analyzes it using an emotion engine, and uses that feedback to improve the accuracy of automated task generation. This feedback processing enables the system to provide more precise and personalized responses. 【0749】 (Example 2) 【0750】 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". 【0751】 Traditional progress management systems fail to consider users' emotional states, resulting in an inability to properly manage user satisfaction and stress levels, ultimately leading to decreased project management efficiency. Furthermore, the inaccuracy of automated task generation hindered efficient work execution. 【0752】 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. 【0753】 In this invention, the server includes means for collecting and analyzing data, means for evaluating the user's emotional state in real time, and means for notifying the user of alert information based on the emotional evaluation. This enables project management that takes the user's emotional state into consideration, leading to improved user satisfaction and effective task management. 【0754】 "Means of collecting and analyzing data" refers to processes and devices for gathering necessary information from users and the environment, and for processing that information to obtain meaningful insights. 【0755】 "Means for automatically generating tasks" refer to processes or devices that mechanically generate tasks to be performed based on collected and analyzed data. 【0756】 "Means for evaluating a user's emotional state in real time" refers to processes or devices that analyze a user's voice, image data, etc., to instantly determine the user's emotions. 【0757】 "Means for executing generated tasks" refers to the processes or devices that actually carry out the generated tasks according to pre-set instructions. 【0758】 "Means for monitoring execution results, detecting anomalies, and generating alerts" refers to processes or devices that verify the results of tasks during and after execution and issue warnings when problems occur. 【0759】 "Means for notifying users of alert information based on sentiment evaluation" refers to processes or devices that provide users with relevant notifications and warning information while taking into account the user's sentiment evaluation. 【0760】 "Means of receiving user feedback to improve the accuracy of automated task generation" refers to processes or devices that reflect user opinions and feelings to improve the accuracy of task generation. 【0761】 "A means of predicting progress and determining the next action based on past data using reinforcement learning" refers to a process or device that applies historical data analysis and machine learning techniques to predict future events and set necessary actions. 【0762】 Embodiments of the present invention relate to a system that highly integrates user progress management and sentiment analysis to achieve efficient project management. This system includes a server, terminals, and a sentiment engine. 【0763】 The server collects data from terminals via the network and analyzes that data. Specifically, it uses an Application Programming Interface (API) to retrieve task management data and compares it with historical data managed in a database. Machine learning models are used for data processing, which evaluates the progress of tasks. 【0764】 The emotion engine utilizes voice analysis libraries and facial recognition AI to analyze the user's voice tone and facial expressions in real time. For example, it uses open-source voice analysis tools to determine how stressed a user is during a meeting. The results are sent to the server, and alerts are generated as needed. 【0765】 The device performs tasks based on instructions from the server and sends email and application notifications to the user. The appropriate timing of notifications is determined by considering the user's schedule and emotional state. 【0766】 For example, if a user expresses negative feelings about the project's progress, the server generates a prompt message stating, "A user has expressed concern about the progress of an important project. Action is required," and notifies the administrator. The terminal then quickly takes action based on this message to assist the user. 【0767】 This system allows us to collect user feedback and improve the accuracy of task generation through reinforcement learning. As a result, more personalized task management that takes into account the user's emotional state becomes possible. 【0768】 The flow of the specific processing in Example 2 will be explained using Figure 13. 【0769】 Step 1: 【0770】 The server collects user task management data from the terminal. The input is task data entered by the user into the application, and the output is task information stored in a database on the server. Specifically, the server collects data via an API and processes it to obtain task deadlines and priority information. 【0771】 Step 2: 【0772】 The server analyzes the collected task data and performs progress evaluation. The input is the collected task information, and the output is the evaluated progress data. Here, a machine learning model is used to calculate the degree of task completion and perform specific processing to evaluate progress against the schedule. 【0773】 Step 3: 【0774】 The emotion engine analyzes the user's voice tone and facial expression data to evaluate the user's emotional state. Input is the user's voice and image data, and output is the emotion evaluation result. Using voice analysis libraries and facial recognition technology, it specifically determines the user's stress level and satisfaction level. 【0775】 Step 4: 【0776】 The server automatically generates necessary tasks and issues alerts based on progress and sentiment assessment results. Inputs are progress assessment data and sentiment assessment results, while outputs are the generated tasks and alerts. Based on this, the server generates prompt messages and performs specific actions to notify administrators and relevant parties. 【0777】 Step 5: 【0778】 The device presents task information received from the server to the user and executes email and app notifications according to the user's instructions. Input consists of tasks and alert information from the server, while output is the notification results sent to the user. The device takes the user's emotions into consideration while providing timely notifications and performing specific actions to track progress. 【0779】 (Application Example 2) 【0780】 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". 【0781】 In modern industrial settings, workers' emotional states significantly impact work efficiency and safety. However, conventional systems struggle to provide real-time feedback based on workers' emotions, resulting in stress and anxiety. To address this, there is a need for technology that can efficiently provide emotionally sensitive support. 【0782】 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. 【0783】 In this invention, the server includes means for collecting and analyzing data, means for automatically generating tasks based on the analysis results, and means for analyzing the user's emotional state and providing emotionally sensitive feedback based on the analysis results. This enables appropriate feedback tailored to the user's emotional state. 【0784】 "Means of collecting and analyzing data" refers to a system that takes in information acquired through sensors and input devices, analyzes its content using algorithms, and converts it into a usable format. 【0785】 "Means for automatically generating tasks based on analysis results" refers to a mechanism that automatically creates appropriate processes and tasks based on the results of data analysis, enabling the user to proceed to the next step. 【0786】 "Means for executing generated tasks" refers to functions within a system that carry out tasks generated as concrete actions or operations. 【0787】 "A means of monitoring execution results, detecting anomalies, and generating alerts" refers to a system that monitors the execution status of tasks and issues warnings if anomalies or problems occur. 【0788】 "Means of notifying users of alert information" refers to means of communicating warnings and important information generated by the system to users. 【0789】 "A means of analyzing a user's emotional state and providing emotionally sensitive feedback based on the analysis results" refers to a technology that performs analysis to determine a user's emotions and provides responses or messages accordingly. 【0790】 The program to implement this system possesses the technology to collect and analyze data through a server, terminal, and emotion engine, and to provide feedback that takes the user's emotions into consideration. The server plays the role of data collection, analyzing data using analysis algorithms based on information obtained from sensors and various input devices. Specifically, it can evaluate the user's emotional state by using voice tone and facial expression recognition technologies. Based on these analysis results, the server automatically generates appropriate tasks and sends them to the terminal as needed. 【0791】 The terminal is a device for receiving and executing generated tasks, monitoring anomalies and problems in real time, and generating alerts as needed. The alert information is analyzed through an emotion engine, and feedback is provided to the user. This feedback is presented to the user in written or interactive formats and is used for work improvement and emotional support. 【0792】 As a concrete example, if a worker experiences stress on the factory floor, the system immediately analyzes their emotions and notifies the manager, while simultaneously displaying a message on the worker's terminal encouraging them to take a break. This function aims to enhance user support and improve productivity. 【0793】 By utilizing generative AI models and prompt messages, more accurate feedback and task management are achieved. For example, prompt messages such as, "How can we analyze visual and audio data of workers during their work and suggest appropriate manager notifications and feedback to workers when stress or anxiety is detected?" can be used. 【0794】 The flow of a specific process in Application Example 2 will be explained using Figure 14. 【0795】 Step 1: 【0796】 The server collects data from sensors and input devices. Specifically, it captures voice tone and facial expression data. This data is saved as initial input and prepared for analysis. 【0797】 Step 2: 【0798】 The server passes the collected data to the analysis engine. The analysis engine processes the data using speech recognition and image processing technologies to determine the user's emotional state. As a result of the analysis, the emotional state (e.g., stress level and anxiety index) is output as numerical data. 【0799】 Step 3: 【0800】 The server automatically generates the next task based on the analysis results. Specifically, if the user's emotional state indicates stress, it prepares a suggestion to take a break and a message of encouragement. This task is sent to the terminal and prepared for execution. 【0801】 Step 4: 【0802】 The terminal receives tasks from the server and displays specific instructions. It also notifies the user of break suggestion messages and reminders, and monitors the task's progress. 【0803】 Step 5: 【0804】 The system monitors whether the user has responded to feedback via the device and returns the result to the server. The device collects user operation and response data as input and sends it to the server. 【0805】 Step 6: 【0806】 Based on the feedback data it receives, the server updates its reinforcement learning model to improve the accuracy of its task generation algorithm. This process makes it possible to further improve the accuracy of task generation in subsequent attempts. 【0807】 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. 【0808】 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. 【0809】 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. 【0810】 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. 【0811】 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. 【0812】 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. 【0813】 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. 【0814】 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. 【0815】 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." 【0816】 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. 【0817】 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. 【0818】 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. 【0819】 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. 【0820】 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. 【0821】 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. 【0822】 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. 【0823】 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. 【0824】 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. 【0825】 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. 【0826】 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. 【0827】 All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference. 【0828】 The following is further disclosed regarding the embodiments described above. 【0829】 (Claim 1) 【0830】 Means for collecting and analyzing data, 【0831】 A means of automatically generating tasks based on analysis results, 【0832】 Means for executing the generated tasks, 【0833】 A means of monitoring execution results, detecting anomalies, and generating alerts, 【0834】 A means of notifying users of alert information, 【0835】 A system that includes this. 【0836】 (Claim 2) 【0837】 The system according to claim 1, further comprising means for receiving user feedback to improve the accuracy of automatic task generation. 【0838】 (Claim 3) 【0839】 The system according to claim 1, further comprising means for predicting progress based on past data using reinforcement learning and determining the next action. 【0840】 "Example 1" 【0841】 (Claim 1) 【0842】 A means for collecting data, receiving and storing information, 【0843】 A means of conducting data analysis to identify progress and risk factors, 【0844】 A means for automatically generating and optimizing tasks based on analysis results, 【0845】 Means for executing the generated task by physical or electronic means, 【0846】 A means of reporting the progress and results of the tasks that have been performed, 【0847】 A means of monitoring execution results, detecting anomalies, and quickly generating alerts, 【0848】 A means of notifying users of alert information and prompting rapid intervention, 【0849】 A system that includes this. 【0850】 (Claim 2) 【0851】 The system according to claim 1, further comprising means for collecting user feedback and improving the accuracy of automated task generation. 【0852】 (Claim 3) 【0853】 The system according to claim 1, further comprising means for using a machine learning algorithm to predict progress based on past information and for determining the next action. 【0854】 "Application Example 1" 【0855】 (Claim 1) 【0856】 A device that acquires and analyzes data, 【0857】 A device that automatically generates tasks based on analysis results, 【0858】 A device that performs the generated tasks, 【0859】 A device that monitors the results of execution, detects anomalies, and generates an alarm, 【0860】 A device that notifies users of alarm information, 【0861】 A device that manages the operation of equipment involved in business operations and uses reinforcement learning to generate new tasks, 【0862】 A system that includes this. 【0863】 (Claim 2) 【0864】 The system according to claim 1, further comprising a device that receives feedback from users and improves the accuracy of automated task generation. 【0865】 (Claim 3) 【0866】 The system according to claim 1, further comprising a device that uses reinforcement learning to predict tasks based on past records and to determine the next task. 【0867】 "Example 2 of combining an emotion engine" 【0868】 (Claim 1) 【0869】 Means for collecting and analyzing data, 【0870】 A means of automatically generating tasks based on analysis results, 【0871】 A means of evaluating the user's emotional state in real time, 【0872】 Means for executing the generated tasks, 【0873】 A means of monitoring execution results, detecting anomalies, and generating alerts, 【0874】 A means of notifying users of alert information based on sentiment evaluation, 【0875】 A system that includes this. 【0876】 (Claim 2) 【0877】 The system according to claim 1, further comprising means for receiving user feedback to improve the accuracy of automatic task generation. 【0878】 (Claim 3) 【0879】 The system according to claim 1, further comprising means for predicting progress based on past data using reinforcement learning and determining the next action. 【0880】 "Application example 2 when combining with an emotional engine" 【0881】 (Claim 1) 【0882】 Means for collecting and analyzing data, 【0883】 A means of automatically generating tasks based on analysis results, 【0884】 Means for executing the generated tasks, 【0885】 A means of monitoring execution results, detecting anomalies, and generating alerts, 【0886】 A means of notifying users of alert information, 【0887】 A means of analyzing the emotional state of users and providing emotionally sensitive feedback based on the analysis results, 【0888】 A system that includes this. 【0889】 (Claim 2) 【0890】 The system according to claim 1, further comprising means for receiving feedback from users and improving the accuracy of automatic task generation. 【0891】 (Claim 3) 【0892】 The system according to claim 1, further comprising means for predicting progress based on past data using reinforcement learning and determining the next action. [Explanation of Symbols] 【0893】 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 for collecting and analyzing data, A means of automatically generating tasks based on analysis results, Means for executing the generated tasks, A means of monitoring execution results, detecting anomalies, and generating alerts, A means of notifying users of alert information, A system that includes this. [Claim 2] The system according to claim 1, further comprising means for receiving user feedback and improving the accuracy of automatic task generation. [Claim 3] The system according to claim 1, further comprising means for predicting progress based on past data using reinforcement learning and determining the next action.

Images