System

Abstract

A system is provided.SOLUTION: A system comprising: means for collecting work data and stress data of an employee; means for analyzing the collected data and evaluating fatigue and stress of the employee; means for proposing an optimum break time and refresh method to the employee based on the evaluation result; and means for notifying a terminal of the employee of the proposal.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the 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 Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] In today's workplace, many employees accumulate stress and fatigue due to long working hours and sudden changes in their working environment. This situation can lead to a decline in employee performance and health problems, ultimately negatively impacting the company's overall productivity. Furthermore, traditional uniform break and refreshment methods make it difficult to appropriately respond to the individual needs of each employee. For this reason, there is a need to provide optimal break times and refreshment methods tailored to each employee's situation, enabling them to maintain their physical and mental health while always performing at their best. [Means for solving the problem]

[0005] This invention provides a system that collects employee work data and stress data, analyzes them, and evaluates employee fatigue and stress. Specifically, the system collects and analyzes data on employees' PC operating time, work content, work location, and stress questionnaire results to assess each employee's fatigue and stress levels in real time. Based on the evaluation results, the system then generates optimal break times and refreshment methods and notifies the employees' devices. Suggested refreshment methods include eye exercises, specific foods and drinks, and short walks. This allows employees to understand their own health status and refresh themselves at appropriate times, enabling them to work in the best possible physical and mental condition.

[0006] "Business data" refers to information such as employees' daily work activities, PC operating hours, and work location.

[0007] "Stress data" refers to survey results and other psychological assessment data used to assess the level of stress experienced by employees.

[0008] "Data collection means" refers to the functions of devices and software used to collect employee work data and stress data.

[0009] "Data analysis means" refers to the algorithms and software functions used to analyze collected work data and stress data and assess employees' levels of fatigue and stress.

[0010] "Evaluation results" refers to numerical values ​​and indicators that indicate the employee's fatigue and stress levels obtained through data analysis methods.

[0011] "Break time suggestion means" refers to a function for suggesting optimal break times to employees based on evaluation results.

[0012] "Means for suggesting refreshment methods" refers to a function for suggesting the most suitable refreshment methods to employees based on the evaluation results.

[0013] "Notification means" refers to a function for displaying break times and suggestions for ways to refresh on employees' devices. [Brief explanation of the drawings]

[0014] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14]FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0015] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0016] First, the terms used in the following description will be explained.

[0017] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0018] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0019] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0020] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0021] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0022] [First embodiment]

[0023] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0024] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0025] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0026] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0027] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0028] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0029] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0030] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] 2, in the data processing device 12, a specific process 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" according to the technology of the present 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 process 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.

[0032] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0033] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0034] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0035] The present invention is a system that detects fatigue and stress in employees and suggests optimal break times and methods for refreshing. Specific embodiments of the system and their operation will be described below.

[0036] System configuration

[0037] The system consists of the following main components:

[0038] server

[0039] Device (PC, smartphone, etc.)

[0040] Database

[0041] Installation and Operation Overview

[0042] 1. Data Collection

[0043] Users (employees) perform their daily work on their PCs or smartphones, and the associated work data is automatically recorded. They also periodically answer a stress questionnaire.

[0044] The terminal collects work data (PC operating time, work content, work location, etc.) and stress data (survey results) and sends them to the server.

[0045] 2. Data analysis

[0046] The server stores the received business data and stress data in an analysis database and performs data preprocessing, which includes removing invalid data and outliers.

[0047] The server analyzes the collected data and assesses the employee's level of fatigue and stress using a machine learning model that combines the employee's past data history with real-time data.

[0048] 3. Creating Actions

[0049] Based on the analysis, the server generates optimal break times and methods of relaxation for each employee, which could include, for example, eye exercises, eating specific foods and drinks, or taking short walks.

[0050] 4. Notifications and Alerts

[0051] The server notifies the employee of the action details generated via email or real-time pop-up messages.

[0052] The terminal displays the received notification on the screen and prompts the user (employee) to take an appropriate break or refresh themselves.

[0053] 5. Administrator Alerts

[0054] The server consolidates data from across departments and identifies employees and departments with particularly high levels of stress and fatigue.

[0055] An alert is generated for the administrator, such as "Many employees in department X are experiencing high levels of stress," and sent to the administrator's device. The administrator can then take company-wide measures based on this information.

[0056] Specific examples

[0057] Example 1: Email notification

[0058] Consider the case where employee A uses a PC for long periods of time and the results of a stress questionnaire indicate a high level of stress.

[0059] The server analyzes employee A's data and determines whether he is under excessive stress.

[0060] Generate an action that recommends 10 minutes of eye exercises and creates an email with detailed instructions on how to do the exercises.

[0061] An email is automatically sent to the device (employee A's email client) and a notification is displayed.

[0062] The user (Employee A) checks his email and performs eye exercises.

[0063] Example 2: Real-time notifications

[0064] Consider the case where it is detected that employee B has been working long hours in a row.

[0065] The server analyzes employee B's data and detects that he has been working long hours.

[0066] Generates actions that recommend a 15-minute break and a short walk.

[0067] A real-time notification is displayed on the device (Employee B's PC) encouraging the employee to "take a short walk."

[0068] The user (Employee B) follows the instructions and takes a short walk.

[0069] Example 3: Alerting the administrator

[0070] Suppose data reveals that a large percentage of employees in department X are in a state of high stress.

[0071] The server consolidates the data from Department X and determines that many employees are experiencing high levels of stress.

[0072] Generate an alert message for administrators: "Many employees in department X are experiencing high stress. Please recommend they take a break."

[0073] Display a notification on the terminal (administrator's PC).

[0074] The user (administrator) checks the alert, schedules a meeting to take appropriate measures, and sends an email to the entire department recommending a break.

[0075] In this way, this system supports efficient work performance while maintaining employee health by proposing and notifying optimal break and refreshment methods based on each employee's working style and condition.

[0076] The processing flow will be explained below.

[0077] Step 1:

[0078] Users (employees) use PCs and smartphones to carry out their work and periodically answer stress questionnaires while working.

[0079] Step 2:

[0080] The devices (employee PCs and smartphones) collect work data (PC operating time, work content, work location) and stress data (survey results). Collection is done automatically.

[0081] Step 3:

[0082] The device periodically sends the collected data to the server in the background, without affecting the user's work.

[0083] Step 4:

[0084] The server stores the received data in an analysis database, where data preprocessing (removal of invalid data and outliers, etc.) is performed as necessary.

[0085] Step 5:

[0086] The server uses machine learning algorithms to analyze the data, assessing each employee's fatigue and stress levels, and combines past data history with real-time data for analysis.

[0087] Step 6:

[0088] Based on the evaluation results, the server generates optimal break times and methods of relaxation for each employee, including actions such as eye exercises, eating specific foods and drinks, or taking a short walk.

[0089] Step 7:

[0090] The server then sends the generated action details to the employee's device, and notifications are sent via real-time pop-up messages or emails.

[0091] Step 8:

[0092] The device will display the received notification on the screen, for example, a message such as "Do 10 minutes of eye exercises."

[0093] Step 9:

[0094] The user (employee) follows the notification and performs the suggested refreshment method, such as doing eye exercises or taking a short walk.

[0095] Step 10:

[0096] The server analyzes the overall data and identifies employees or departments with particularly high stress levels. Based on the results of this analysis, it generates alerts for administrators.

[0097] Step 11:

[0098] The server then sends an alert to the administrator's device, such as a message saying, "Many employees in department X are experiencing high stress. Please encourage them to take a break."

[0099] Step 12:

[0100] An alert will be displayed on the device (administrator's PC or smartphone).

[0101] Step 13:

[0102] The user (administrator) checks the alert and schedules a meeting to take appropriate measures or sends an email to all employees recommending they take a break.

[0103] Example 1

[0104] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0105] With conventional systems, it was difficult to properly assess employee fatigue and stress and suggest effective break times and ways to refresh. Furthermore, there was a lack of a mechanism to grasp the stress levels of not only individual employees but the entire department, and to provide appropriate alerts to managers. This could lead to inadequate health management for employees, leading to a decline in performance.

[0106] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0107] In this invention, the server includes means for collecting employee work data and stress data, means for preprocessing the collected data to remove invalid data and outliers, means for analyzing the preprocessed data and executing a machine learning model for assessing employee fatigue and stress, means for proposing optimal break times and relaxation methods to employees based on the assessment results, means for notifying the employees of the suggestions to their terminals, and means for integrating data from the entire department, identifying employees or departments with particularly high levels of fatigue or stress, and notifying a manager of an alert. This makes it possible to accurately monitor the health status of individual employees and propose effective relaxation methods, and by notifying a manager of the stress level of the entire department, it is possible to take prompt and appropriate measures.

[0108] "Business data" refers to all information related to an employee's work, such as the employee's PC operating time, work content, and work location.

[0109] "Stress data" refers to the results of stress questionnaires answered by employees and information regarding the psychological and physiological state of employees.

[0110] "Data preprocessing" refers to the process of removing invalid data and outliers from collected data.

[0111] A "machine learning model" refers to a collection of algorithms and mathematical methods used to assess an employee's level of fatigue or stress based on past data.

[0112] "Refreshment methods" are specific methods suggested to reduce employees' fatigue and stress, such as eye exercises or short walks.

[0113] "Notification" refers to the act of transmitting generated action details and alert information to an employee or administrator's device.

[0114] "Alert to managers" refers to the act of integrating data from across departments to identify employees or departments with high levels of fatigue or stress and issuing a warning to managers.

[0115] This invention relates to a system that detects employee fatigue and stress and suggests optimal break times and ways to refresh. This system is mainly composed of a server, terminals, and a database.

[0116] Hardware and software used

[0117] Server: A server with high-performance data processing capabilities (e.g., Apache HTTP Server, Nginx)

[0118] Device: General PC or smartphone (e.g. Windows PC, Mac, iPhone (registered trademark), ANDROID (registered trademark) device)

[0119] Database: A database that stores and manages large amounts of data (e.g., MySQL (registered trademark), PostgreSQL)

[0120] Machine learning model: The machine learning algorithm used to assess employee fatigue and stress (e.g., TENSORFLOW®, scikit-learn)

[0121] Specific Embodiments of the System

[0122] 1. Data Collection

[0123] Users carry out their daily work on their PC or smartphone, and their work data is automatically recorded. They also periodically answer a stress questionnaire.

[0124] The terminal collects business data such as the user's PC operating time, work content, and work location, as well as the user's stress data (survey results), and sends this to the server.

[0125] 2. Data Preprocessing

[0126] The server stores the received business data and stress data in an analysis database.

[0127] The server performs preprocessing on the stored data, such as removing invalid data and outliers. For example, consecutive identical data and obviously unrealistic values ​​are filtered out.

[0128] 3. Data analysis

[0129] The server uses the pre-processed data to run machine learning models to assess employees' levels of fatigue and stress.

[0130] The server inputs past data history and real-time data to calculate each employee's fatigue and stress levels.

[0131] 4. Creating Actions

[0132] Based on the evaluation results, the server will suggest optimal break times and ways to refresh employees.

[0133] Suggestions may include eye exercises, eating specific foods and drinks, or taking a short walk.

[0134] 5. Notifications and Alerts

[0135] The server notifies the specified device (PC or smartphone) of the generated action content.

[0136] The terminal displays the received notification on the screen in real time and prompts the user to perform the refresh method.

[0137] 6. Alert the administrator

[0138] The server aggregates data from across the department and detects high stress levels among specific employees or departments.

[0139] The server sends an alert to the administrator's device, such as "Many employees in department X are feeling high levels of stress."

[0140] Specific examples

[0141] 1. Example 1: Email notification

[0142] If employee A uses a PC for a long time and the results of a stress questionnaire indicate a high level of stress, the server will analyze the data and determine whether the stress is excessive.

[0143] The server generates an action that recommends 10 minutes of eye exercises and creates an email with detailed instructions on how to do it.

[0144] An email is automatically sent to the device (employee A's email client) and a notification is displayed.

[0145] The user (Employee A) checks his email and performs eye exercises.

[0146] 2. Example 2: Real-time notifications

[0147] If employee B works long hours consecutively, the server analyzes employee B's data and detects that long working hours have continued.

[0148] The server generates an action that recommends a 15-minute break and a short walk.

[0149] A real-time notification is displayed on the device (Employee B's PC) encouraging the employee to "take a short walk."

[0150] The user (Employee B) follows the instructions and takes a short walk.

[0151] 3. Example 3: Alerting the administrator

[0152] If most of the employees in department X are in a high stress state, the server consolidates the data for department X and determines that a large number of employees are experiencing high stress.

[0153] The server displays an alert on the administrator's device saying, "Many employees in department X are feeling high stress. Please recommend they take a break."

[0154] The user (administrator) checks the alert, schedules a meeting to take appropriate measures, and sends an email to the entire department recommending a break.

[0155] As described above, this system supports efficient work performance while maintaining employee health by proposing and notifying employees of optimal break and refreshment methods based on their individual work style and condition.

[0156] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0157] Step 1:

[0158] Data collection

[0159] Users carry out their daily work on their PC or smartphone, and their work data is automatically recorded. In addition, they are required to answer a stress questionnaire periodically.

[0160] Input: Work data such as user PC operating time, work content, and work location, as well as stress questionnaire results

[0161] The device collects this work data and stress data and sends it to the server using an HTTP request.

[0162] Output: Raw work and stress data sent to the server

[0163] Specific behavior:

[0164] The terminal records the PC operation time from when the user starts work at 9:00 AM until 6:00 PM. The terminal also collects the results of a stress questionnaire conducted at 1:00 PM (e.g., stress level 7 / 10) and sends them to the server.

[0165] Step 2:

[0166] Data Preprocessing

[0167] The server stores the received business data and stress data in an analysis database.

[0168] Input: Raw data received by the server

[0169] Perform data preprocessing to remove invalid data and outliers, for example, filtering out repeated identical data or unrealistic values.

[0170] Output: Preprocessed and clean data

[0171] Specific behavior:

[0172] The server stores the received data in a database and removes records with PC operating time of more than 24 hours as outliers.

[0173] Step 3:

[0174] Data analysis

[0175] The server uses the pre-processed data to run machine learning models to assess employees' levels of fatigue and stress.

[0176] Input: Preprocessed operational and stress data

[0177] Use machine learning models to assess employee stress levels based on historical and real-time data.

[0178] Output: Fatigue and stress levels for each employee

[0179] Specific behavior:

[0180] The server analyzes Alice's work data and stress questionnaire results from the past month and determines that her current stress level is 8 / 10.

[0181] Step 4:

[0182] Creating Actions

[0183] Based on the evaluation results, the server will suggest optimal break times and ways to refresh employees.

[0184] Input: Fatigue and stress levels for each employee

[0185] Generate optimal refreshment methods (e.g., eye exercises, eating certain foods and drinks, taking short walks).

[0186] Output: Refresh method suggestions

[0187] Specific behavior:

[0188] The server generates an action that recommends 10 minutes of eye exercises and creates data containing detailed instructions on how to do it.

[0189] Step 5:

[0190] Notifications and Alerts

[0191] The server notifies the employee's terminal of the generated action content.

[0192] Input: Refresh method proposal

[0193] The terminal displays the received notification on the screen and prompts the user to take action.

[0194] Output: Real-time notification messages

[0195] Specific behavior:

[0196] The server sends a pop-up message to Alice's PC saying, "Do eye exercises for 10 minutes," and the device immediately displays the message.

[0197] Step 6:

[0198] Administrator Alert

[0199] The server aggregates data from across the department and detects high fatigue or stress levels in specific employees or departments.

[0200] Input: Department-wide data

[0201] Alerts administrators to high stress situations.

[0202] Output: Alert message to administrator

[0203] Specific behavior:

[0204] The server detects that many employees in Department X have stress levels of 8 / 10 or higher and displays an alert on the administrator's PC saying, "Many employees in Department X are experiencing high levels of stress. Please recommend that they take a break."

[0205] (Application example 1)

[0206] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0207] The problem with employees and drivers is that fatigue caused by long working hours and stress leads to reduced productivity and health problems. The present invention aims to solve these problems and realize a healthy and efficient working environment.

[0208] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0209] In this invention, the server includes means for collecting employee work data and stress data, means for analyzing the collected data and evaluating the employee's fatigue and stress, means for proposing optimal rest periods and refreshment methods for the employee based on the evaluation results, and means for notifying the employee's terminal of the suggestions, means for collecting driver driving data and stress data, means for analyzing the collected data and evaluating the driver's fatigue and stress, means for proposing optimal rest periods and refreshment methods for the driver based on the evaluation results, and means for notifying the driver's terminal of the suggestions. This makes it possible to monitor the health status of employees and drivers in real time and suggest appropriate rest periods and refreshment methods, thereby improving work efficiency and maintaining health.

[0210] "Employee" refers to a person who belongs to a company or organization and performs work for that company or organization.

[0211] "Driver" means a person who drives a vehicle.

[0212] "Business data" refers to data generated or acquired by employees during work hours, and specifically includes PC operating time, work content, work location, etc.

[0213] "Stress data" refers to data that measures the stress levels of employees and drivers, and specifically includes the results of stress questionnaires and heart rates.

[0214] "Means of collecting data" refers to devices and software systems used to acquire and store various data on employees and drivers.

[0215] "Means for analyzing data" refers to software or algorithms used to analyze collected data and assess fatigue and stress levels among employees and drivers.

[0216] "Means for suggesting rest times and refreshment methods" refers to a system for recommending optimal rest and refreshment activities based on the results of data analysis.

[0217] "Means of notification" refers to devices or software that transmit suggested break times and refreshment methods to employees' or drivers' devices.

[0218] "Terminal" refers to a device used by employees or drivers to receive information, and specifically includes smartphones and in-vehicle displays.

[0219] This invention is a system that collects work data and stress data of employees and drivers, analyzes and evaluates the data, and proposes optimal rest times and methods for refreshing. Specific embodiments of the system and their operation are described below.

[0220] System Components

[0221] The system consists of the following main components:

[0222] server

[0223] Terminals (smartphones, in-car displays)

[0224] Database

[0225] Data collection

[0226] The server collects work data and stress data from smartphones and in-car displays. Work data includes driving speed, frequency of brake and accelerator operation, and driving time. Stress data includes the results of a simple stress questionnaire and heart rate. The collected data is stored in Firebase Firestore in real time.

[0227] Data analysis

[0228] The server stores the collected work data and stress data in an analysis database and performs data preprocessing, which involves removing invalid data and outliers. TensorFlow.js is used for analysis, and a machine learning model that combines past data history and real-time data is used. This allows the system to evaluate the fatigue and stress levels of employees and drivers.

[0229] Creating Actions

[0230] Based on the analysis results, the server generates optimal break times and methods of relaxation for each employee and driver. For example, it may suggest eye exercises, specific foods and drinks, a short walk, or a short meditation session. These suggestions are selected based on the most appropriate one for each situation.

[0231] Notifications and Alerts

[0232] The server then sends the generated action details to the employee or driver's device, which then displays the notification as a real-time pop-up message on the employee's smartphone or in-car display. Additionally, if a particularly high-stress state is detected, an alert will be sent.

[0233] Specific examples

[0234] Example 1: Real-time notifications for drivers

[0235] Consider a case where a driver has been working for long periods of time. The server analyzes the driver's driving data and stress data and detects that the driver has been working for long periods of time. The server generates an action recommending a 15-minute break and a short walk, and displays a notification such as "Please take a short walk" on the in-vehicle display.

[0236] Example 2: Break notification on smartphone

[0237] Consider a case where an employee uses a PC for long periods of time and the results of a stress questionnaire indicate high stress. The server analyzes the employee's work data and stress data to determine whether the employee is under excessive stress. It then generates an action recommending 10 minutes of eye exercises and sends a notification to the employee's smartphone.

[0238] Prompt Sentence Examples

[0239] "Please tell me the best time to take a break and refresh yourself while driving today. We will use the following data: acceleration data, heart rate, and driving time."

[0240] This system monitors the health status of employees and drivers in real time and suggests appropriate breaks and refreshments, thereby improving work efficiency and maintaining health.

[0241] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0242] Step 1: Data collection

[0243] The device (smartphone or in-car display) collects the driver's or employee's work data (driving speed, frequency of brake and accelerator operation, driving time, PC operating time, work content, work location, etc.) and stress data (heart rate, results of stress questionnaire) in real time.

[0244] Input: Sensor data, survey results

[0245] Output: Collected work data and stress data

[0246] Specific operation: Data is collected using smartphone sensors (e.g., acceleration sensor, heart rate sensor) and a simple stress questionnaire provided within the app. The in-car display collects vehicle driving information.

[0247] Step 2: Send data

[0248] The terminal transmits the collected data to the server in real time.

[0249] Input: Collected work data and stress data

[0250] Output: Data sent to the server

[0251] Specific operation: The application on the device has the function of periodically sending collected data to Firebase Firestore.

[0252] Step 3: Data Preprocessing

[0253] The server stores the received data in an analysis database and performs data preprocessing.

[0254] Input: Received work data and stress data

[0255] Output: Preprocessed data

[0256] Specific operation: Removes invalid data and outliers from the data stored in the database, and performs imputation and normalization as necessary.

[0257] Step 4: Data analysis

[0258] The server uses the preprocessed data to analyze employee and driver fatigue and stress using machine learning models.

[0259] Input: Preprocessed data

[0260] Output: Fatigue and stress assessment results

[0261] Specific operation: Using TensorFlow.js, a machine learning model is applied to the collected data to assess fatigue and stress in real time.

[0262] Step 5: Action Creation

[0263] The server generates optimal break times and refreshment methods based on the evaluation results.

[0264] Input: Fatigue and stress assessment results

[0265] Output: Suggestions for optimal break times and ways to refresh

[0266] Specific actions: Action generation algorithms create specific suggestions such as eye exercises, eating specific foods or drinks, taking a short walk, or meditating.

[0267] Step 6: Notifications and Alerts

[0268] The server notifies the generated action details to the employee or driver's device.

[0269] Input: Suggestions for optimal break times and ways to refresh

[0270] Output: Notifications and alerts

[0271] What it does: It uses Firebase Cloud Messaging to send real-time popup messages to smartphones and in-car displays, alerting drivers when particularly stressful situations are detected.

[0272] Step 7: Rest and Refresh

[0273] Users (employees or drivers) follow the suggestions displayed on the terminal to take breaks and refresh themselves.

[0274] Input: Notifications and Alerts

[0275] Output: Maintaining health and improving work efficiency

[0276] Specific actions: Do eye exercises, drink something, take a short walk or meditate.

[0277] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0278] The present invention is a system that detects employee fatigue and stress and proposes more accurate break times and methods for refreshing by combining it with an emotion engine that recognizes the user's emotions. Specific embodiments of the system and their operation are described below.

[0279] System configuration

[0280] The system consists of the following main components:

[0281] server

[0282] Device (PC, smartphone, etc.)

[0283] Database

[0284] Emotion Engine

[0285] Installation and Operation Overview

[0286] 1. Data Collection

[0287] Users (employees) use PCs and smartphones to carry out their work and periodically answer stress questionnaires while working.

[0288] The terminal collects work data (PC operating time, work content, work location) and stress data (survey results).

[0289] The emotion engine analyzes the user's facial expressions and voice through the device's camera and microphone, collecting emotional data in real time.

[0290] 2. Data Transmission

[0291] The terminal transmits the collected work data, stress data, and emotion data to the server at regular intervals.

[0292] 3. Data analysis

[0293] The server stores the received data in an analytical database and performs preprocessing on the data, which includes removing invalid data and outliers.

[0294] The server uses machine learning algorithms to assess each employee's fatigue level, stress level, and emotional state, combining historical data with real-time data for analysis.

[0295] 4. Creating Actions

[0296] Based on the analysis results, the server generates optimal break times and methods of relaxation for each employee, such as eye exercises, eating specific foods and drinks, or taking a short walk.

[0297] 5. Notifications and Alerts

[0298] The server then notifies the employee of the action details generated via a real-time pop-up message or email.

[0299] The terminal displays the received notification on the screen and prompts the user (employee) to take an appropriate break or refresh themselves.

[0300] 6. Administrator Alerts

[0301] The server analyzes the overall data and identifies employees or departments with particularly high stress or poor performance, and generates alerts for administrators based on the results of this analysis.

[0302] The server sends the generated alert to the administrator's terminal.

[0303] The device displays an alert on the administrator's PC or smartphone.

[0304] The user (administrator) checks the alert, schedules a meeting to take appropriate measures, and sends a company-wide email recommending a break.

[0305] Specific examples

[0306] Example 1: Email notification

[0307] Let's consider a case where Employee A uses a PC for long periods of time, and the results of a stress questionnaire indicate a high level of stress. Also, the emotion engine detects facial expressions that indicate anxiety or fatigue on Employee A.

[0308] The server analyzes employee A's data and determines whether he is experiencing excessive stress or fatigue.

[0309] Generate an action that recommends 10 minutes of eye exercises and creates an email with detailed instructions on how to do the exercises.

[0310] The device (employee A's email client) will automatically send an email and display a notification.

[0311] The user (Employee A) checks his email and performs eye exercises.

[0312] Example 2: Real-time notifications

[0313] Consider a case where the emotion engine detects that employee B has been working long hours in a row, and further detects fatigue and stress from employee B's facial expressions.

[0314] The server analyzes employee B's data and detects long working hours and high stress levels.

[0315] Generates actions that recommend a 15-minute break and a short walk.

[0316] The device (Employee B's PC) displays a real-time notification, encouraging the employee to "take a short walk."

[0317] The user (Employee B) follows the instructions and takes a short walk.

[0318] Example 3: Alerting the administrator

[0319] Consider a case where most employees in department X are in a state of high stress and the emotion engine detects facial expressions of anxiety and fatigue from multiple employees.

[0320] The server consolidates the data from Department X and determines that many employees are experiencing high levels of stress.

[0321] Generate an alert message for administrators: "Many employees in department X are experiencing high stress. Please recommend they take a break."

[0322] The device (administrator's PC or smartphone) will display a notification.

[0323] The user (administrator) checks the alert, schedules a meeting to take appropriate measures, and sends an email to the entire department recommending a break.

[0324] In this way, by combining this emotion engine, the system provides more precise break and refreshment methods that take into account the emotional state of each employee, helping to balance employee health with work efficiency.

[0325] The processing flow will be explained below.

[0326] Step 1:

[0327] Users (employees) use PCs and smartphones to carry out their work and periodically answer stress questionnaires while working.

[0328] Step 2:

[0329] The devices (employee PCs and smartphones) collect work data (PC operating time, work content, work location) and stress data (survey results). Collection is done automatically.

[0330] Step 3:

[0331] The emotion engine analyzes the user's facial expressions and voice through the device's camera and microphone to collect emotion data in real time, for example, tracking changes in the user's facial expressions through the camera and analyzing voice tone through the microphone.

[0332] Step 4:

[0333] The device periodically transmits collected work data, stress data, and emotion data to a server. The transmission is performed in the background and does not affect the user's work.

[0334] Step 5:

[0335] The server stores the received data in an analysis database, where data preprocessing (such as removing invalid data and outliers) is performed as necessary.

[0336] Step 6:

[0337] The server uses machine learning algorithms to assess each employee's fatigue level, stress level, and emotional state, combining historical data with real-time data for analysis.

[0338] Step 7:

[0339] Based on the evaluation results, the server generates optimal break times and methods of relaxation for each employee, including actions such as eye exercises, eating specific foods and drinks, or taking a short walk.

[0340] Step 8:

[0341] The server then sends the generated action details to the employee's device, and notifications are sent via real-time pop-up messages or emails.

[0342] Step 9:

[0343] The device will display the received notification on the screen, for example, a message such as "Do 10 minutes of eye exercises."

[0344] Step 10:

[0345] The user (employee) follows the notification and performs the suggested refreshment method, such as doing eye exercises or taking a short walk.

[0346] Step 11:

[0347] The server analyzes the overall data and identifies employees or departments that are particularly stressed or underperforming.

[0348] Step 12:

[0349] The server generates an alert message for the administrator, for example, "Many employees in department X are experiencing high stress. Please recommend they take a break."

[0350] Step 13:

[0351] The server sends an alert to the administrator's terminal, either via email or a pop-up message.

[0352] Step 14:

[0353] An alert will be displayed on the device (administrator's PC or smartphone).

[0354] Step 15:

[0355] The user (administrator) checks the alert and schedules a meeting to take appropriate measures or sends an email to all employees recommending they take a break.

[0356] Example 2

[0357] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0358] In today's work environment, employee fatigue and stress are increasing, resulting in a decline in labor productivity and work efficiency. Conventional systems primarily collect and analyze employee work data and stress data, but lack the ability to grasp employees' emotional states in real time or provide appropriate notifications to managers. As a result, they are unable to adequately suggest optimal break times and refreshment methods based on employees' conditions, limiting the effectiveness of improving labor productivity. A system that can solve these problems and improve employee health and work efficiency is needed.

[0359] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting employee work data, stress data, and emotional data; means for analyzing the collected data and evaluating the employee's fatigue, stress, and emotional state; means for proposing optimal break times and refreshment methods to the employee based on the evaluation results; means for notifying the employee of the suggestions to their terminal; and means for notifying the manager of employees and departments with high stress or low performance. This enables highly accurate fatigue and stress management that takes the employee's emotional state into consideration. Furthermore, real-time notifications and alerts to the manager enable prompt and appropriate responses, thereby maintaining employee health and improving work productivity.

[0360] "Business data" refers to data generated by employees during their work hours, including PC operating time, work content, and work location.

[0361] "Stress data" refers to data that indicates the level of stress felt by employees, and includes the results of stress questionnaires, etc.

[0362] "Emotional data" refers to data that indicates the emotional state of employees as analyzed from their facial expressions and voice, and is obtained through real-time facial and voice analysis.

[0363] An "emotion engine" is software or an algorithm that analyzes employees' emotional states from data obtained through devices such as cameras and microphones.

[0364] The "server" is a central processing unit that stores and analyzes collected data and provides optimal suggestions and notifications to employees and managers.

[0365] "Terminal" means a computing device used by an employee or administrator, including a PC or smartphone.

[0366] "Notifications" are information sent from the server to the terminal, and include suggestions for employees to take breaks or refresh themselves, and alerts to managers about high stress levels.

[0367] "Rest period" means a period of time designated for an employee to rest from work.

[0368] "Refreshment methods" are actions employees take to reduce stress and fatigue, including eye exercises, eating and drinking, and taking short walks.

[0369] A "database" is a digital storage system for systematically storing and managing business data, stress data, and emotional data collected by a server.

[0370] A "machine learning algorithm" is a mathematical model or calculation method used to analyze and evaluate employees' fatigue and stress levels based on collected data.

[0371] This system collects and analyzes employee work data, stress data, and emotional data, assesses employee fatigue and stress levels, and suggests optimal break times and ways to refresh. The system is comprised of the following main components:

[0372] server

[0373] Device (PC, smartphone, etc.)

[0374] Database

[0375] Emotion Engine

[0376] Data collection

[0377] Users (employees) use PCs or smartphones during work hours and periodically answer stress questionnaires. For example, employees answer a questionnaire every two hours during their eight-hour workday, rating their stress level on a five-point scale.

[0378] The device automatically collects work data (PC operating time, work content, work location) and stress data (survey results). For example, PC operating time and activity logs are periodically saved as log files. In addition, the device's camera and microphone are used to collect facial and voice data through an emotion engine. The emotion engine uses facial recognition software (e.g., OpenFace) and voice analysis tools to collect emotion data in real time.

[0379] Data transmission

[0380] The device sends the collected work data, stress data, and emotion data to the server at regular intervals (for example, every hour). Data is sent using a secure communication protocol such as HTTPS.

[0381] Data analysis

[0382] The server stores the received data in a database for analysis. For example, the data is stored systematically using an SQL database. The server then pre-processes the data, using principal component analysis (PCA) and data cleaning techniques to remove incorrect data and outliers.

[0383] The server uses machine learning algorithms (e.g., random forest, SVM) to assess each employee's fatigue level, stress level, and emotional state. It builds a predictive model based on past data history and real-time data to assess the employee's condition in real time.

[0384] Creating Actions

[0385] Based on the evaluation results, the server will generate optimal break times and methods for refreshing each employee, suggesting specific actions such as eye exercises, eating certain foods and drinks, or taking a short walk.

[0386] Notifications and Alerts

[0387] The server notifies the employee of the action details generated via a pop-up message or email.

[0388] The device will display the received notification on the screen and notify the user with an audio alert or vibration notification.

[0389] The user (employee) checks the notification and takes the suggested break or refreshment method.

[0390] Administrator Alerts

[0391] The server analyzes the overall data and identifies employees or departments with particularly high stress or poor performance. Based on the detected issues, it generates alert messages for administrators and sends them to their terminals.

[0392] The device displays an alert using an administrator application or email client.

[0393] The user (administrator) checks the alert, quickly schedules a meeting, and sends a company-wide email recommending a break.

[0394] Specific examples

[0395] Example 1: Email notification

[0396] Employee A uses a PC for long periods of time and indicates high stress in a stress questionnaire.

[0397] The server analyzes employee A's data and determines whether he is experiencing excessive stress or fatigue.

[0398] The server generates an action recommending 10 minutes of eye exercises and creates an email with detailed instructions.

[0399] The device (employee A's email client) will automatically send an email and display a notification.

[0400] The user (Employee A) checks his email and performs eye exercises.

[0401] Example 2: Real-time notifications

[0402] Employee B has been working long hours in a row and the emotion engine detects fatigue and high stress.

[0403] The server analyzes employee B's data and determines whether he is working long hours or experiencing high stress.

[0404] The server generates an action that recommends a 15-minute break and a short walk.

[0405] The device (Employee B's PC) displays a real-time notification, encouraging the employee to "take a short walk."

[0406] The user (Employee B) follows the instructions and takes a short walk.

[0407] Example 3: Alerting the administrator

[0408] A large proportion of employees in department X are under high stress, and the emotion engine detects expressions of anxiety and fatigue on multiple employees' faces.

[0409] The server consolidates the data from Department X and determines that many employees are experiencing high levels of stress.

[0410] The server generates an alert message for the administrator: "Many employees in department X are experiencing high stress. Please recommend they take a break."

[0411] The device (administrator's PC or smartphone) will display a notification.

[0412] The user (administrator) checks the alert, quickly schedules a meeting, and sends an email to the entire department recommending a break.

[0413] Prompt Sentence Examples

[0414] An example of a prompt to be input to the generative AI model is as follows:

[0415] "Describe a system that detects employee fatigue and stress and uses an emotion engine to suggest appropriate breaks and ways to refresh. Illustrate examples of email notifications for employees who have worked long hours, real-time notifications in natural language, and department-wide alerts for managers."

[0416] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0417] Step 1: Data collection

[0418] Users (employees) perform their work using PCs and smartphones.

[0419] The device automatically collects business data (PC operating time, work content, work location), for example, via the device's log file.

[0420] Users fill out a stress questionnaire periodically, for example, every two hours, by filling out a questionnaire form that appears on the screen.

[0421] The device uses a camera and microphone to collect the user's facial and voice data through the emotion engine. Specifically, the emotion engine acquires emotion data in real time using facial recognition software (e.g., OpenFace) and voice analysis tools.

[0422] Input: User's work data (PC operating time, work content, work location), stress questionnaire results, facial expression data, voice data.

[0423] Output: Collected work data, stress data, and emotion data.

[0424] Step 2: Send data

[0425] The terminal transmits the collected data to the server at regular intervals, for example, a schedule for transmitting data every hour is set.

[0426] Data is transmitted using secure communication protocols such as HTTPS.

[0427] Input: Collected work data, stress data, and emotion data.

[0428] Output: Work data, stress data, and emotion data sent to the server.

[0429] Step 3: Data analysis

[0430] The server stores the received data in a database for analysis, for example, by systematically storing the data using an SQL database.

[0431] The server pre-processes the data, using principal component analysis (PCA) and data cleaning techniques to remove incorrect data and outliers.

[0432] The server uses machine learning algorithms (e.g., random forest, SVM) to assess each employee's fatigue level, stress level, and emotional state. It builds and analyzes a predictive model based on past data history and real-time data.

[0433] Input: Work data, stress data, and emotion data sent to the server.

[0434] Output: Fatigue, stress, and emotional state assessment results.

[0435] Step 4: Creating Actions

[0436] The server generates optimal break times and refreshment methods for each employee based on the evaluation results.

[0437] Specifically, it generates actions such as eye exercises, eating specific foods and drinks, taking a short walk, etc. For example, if the user is highly fatigued, it will suggest "10 minutes of eye exercises recommended."

[0438] Input: Fatigue, stress, and emotional state assessment results.

[0439] Output: Generated break times and refresh methods.

[0440] Step 5: Notifications and Alerts

[0441] The server notifies the employee of the action details generated via a pop-up message or email.

[0442] The device will display the received notification on the screen and notify the user with an audio alert or vibration notification.

[0443] The user checks the notification content and takes the suggested break or refreshment method.

[0444] Input: Generated break times and refreshment methods.

[0445] Output: Notifications that appear on employee devices.

[0446] Step 6: Administrator alerts

[0447] The server analyzes the overall data and identifies employees or departments that are particularly stressed or underperforming.

[0448] An alert message for the administrator is generated based on the data and sent to the administrator's terminal.

[0449] The device displays an alert using an administrator application or email client.

[0450] The user (administrator) checks the alert, quickly schedules a meeting, and sends a company-wide email recommending a break.

[0451] Input: Overall data analysis results.

[0452] Output: An alert message for the administrator.

[0453] (Application example 2)

[0454] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0455] In today's work environment, it is common for employees to work long hours, which can easily lead to the accumulation of fatigue and stress. Therefore, managing employee health and maintaining and improving work efficiency are important issues. However, traditional methods make it difficult to effectively monitor individual employees' fatigue and stress levels in real time and suggest personalized break times and ways to refresh. This can lead to excessive employee stress, which can ultimately lead to health problems and reduced work efficiency.

[0456] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0457] In this invention, the server includes means for collecting employee work data and stress data, means for analyzing the collected data and evaluating the employee's fatigue and stress, means for collecting and analyzing emotional data in real time, means for evaluating the employee's emotional state based on the emotional data and using the evaluation results to generate personalized break times and relaxation methods, and means for notifying the employee's terminal of the suggestions. This makes it possible to provide highly accurate break time suggestions and relaxation methods tailored to the individual circumstances of each employee.

[0458] "Business data" refers to data generated when employees perform their work, and specifically includes information such as PC operating time, work content, and work location.

[0459] "Stress data" refers to data that indicates the stress state of employees, and specifically includes survey results and physiological indicators.

[0460] "Evaluation measures" are means for analyzing collected data and evaluating employee fatigue and stress.

[0461] The "suggestion means" is a means for generating optimal break times and methods of relaxation for employees based on the evaluation results and proposing these to employees.

[0462] "Terminal" refers to an information processing device used by an employee, and specifically includes PCs, smartphones, tablets, etc.

[0463] "Emotion data" is data that indicates the emotional state of an employee, and specifically includes the analysis results of facial expressions, voice, movements, etc.

[0464] "Emotional state" refers to an employee's current emotional state, such as happiness, anxiety, fatigue, etc.

[0465] "Personalization" means that it is individually tailored to each employee's characteristics and circumstances.

[0466] The "notification means" refers to a means for informing employees of the generated break times and refreshment methods, and specifically includes real-time pop-up messages, emails, etc.

[0467] "Real-time analysis" means analyzing data immediately, close to the moment it is generated.

[0468] This invention is a system that detects employee fatigue and stress, and uses emotion data to evaluate the employee's emotional state in real time, thereby providing more accurate break times and methods for refreshing. This invention is composed of the following main components: a server, a terminal, a database, and an emotion engine.

[0469] System Configuration

[0470] 1. Server

[0471] The server is responsible for the main calculations, collecting and analyzing work data, stress data, and emotion data, and also notifying each employee of the generated break times and how to refresh themselves.

[0472] 2. Terminal

[0473] The devices are information processing devices used by employees, such as PCs, smartphones, tablets, etc. The devices collect work data and stress data, and also use an emotion engine to collect emotion data in real time from cameras and microphones.

[0474] 3. Database

[0475] The database stores the collected work data, stress data, and emotion data, and the server uses this database for analysis.

[0476] 4. Emotion Engine

[0477] The emotion engine uses the device's camera and microphone to analyze employees' facial expressions and voices and assess their emotional state in real time.

[0478] Processing flow

[0479] 1. Data Collection

[0480] Employees use devices to carry out their work and periodically answer stress questionnaires. The emotion engine analyzes employees' facial expressions and voices via cameras and microphones to collect emotional data in real time.

[0481] 2. Data Transmission

[0482] The collected work data, stress data, and emotion data are transmitted to a server at regular intervals.

[0483] 3. Data analysis

[0484] The server stores the received data in a database and performs preprocessing. It uses machine learning algorithms to evaluate each employee's fatigue level, stress level, and emotional state. It then combines past data history with real-time data for analysis.

[0485] 4. Creating Actions

[0486] Based on the analysis results, the server generates optimal break times and methods for refreshing each employee, such as eye exercises, eating certain foods and drinks, or taking a short walk.

[0487] 5. Notification

[0488] The generated action details are sent to the employee's device via a real-time pop-up message or email.

[0489] Specific examples

[0490] Example 1: Email notification

[0491] Let's assume that employee A works long hours and the results of a stress questionnaire and emotional data indicate a high level of stress.

[0492] The server analyzes employee A's data, generates an action recommending 10 minutes of eye exercises, and sends the specific instructions via email.

[0493] The message reads, "Do eye exercises for 10 minutes."

[0494] Example 2: Real-time notifications

[0495] Consider a case where the server detects that employee B has been working long hours in a row, and furthermore, emotion data confirms that he or she is tired.

[0496] The server generates actions recommending a 15-minute break and a short walk, and displays real-time notifications on the device.

[0497] The message reads, "Take a short walk."

[0498] Example 3: Alerting the administrator

[0499] Imagine that the server detects that many employees in department X are in a state of high stress.

[0500] The server consolidates data from department X and alerts the administrator when stress levels are high.

[0501] The message read, "Employees in department X are under high stress. Please recommend a company-wide break."

[0502] As shown in these specific examples, by combining an emotion engine, the present invention provides more precise break and refreshment methods that take into account the emotional state of each employee, thereby helping employees achieve both health and work efficiency.

[0503] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0504] Step 1:

[0505] Data collection

[0506] The device collects work data (e.g., PC operating time, work content, and work location) generated by employees using their PCs or smartphones while performing their work. Employees also periodically answer stress questionnaires, and the results are collected as stress data. Furthermore, the emotion engine analyzes facial expressions and voices through the device's camera and microphone to collect emotion data in real time. The input data are work data, stress data, and emotion data. The output is a set of collected data.

[0507] Step 2:

[0508] Data transmission

[0509] The device periodically sends the work data, stress data, and emotion data collected in step 1 to the server. The input is the collected dataset. The data is packaged in JSON format and sent to the cloud server using an HTTP API. The output is a confirmation message indicating that the data was successfully sent to the server.

[0510] Step 3:

[0511] Data storage and preprocessing

[0512] The server stores the received data in a database. For example, MySQL or PostgreSQL is used as the database system. The received data is first preprocessed to remove invalid data and outliers. The input is the dataset sent to the server. Before storing it in the database, processing such as filling in missing data and standardizing the data format is performed. The output is a preprocessed, clean dataset.

[0513] Step 4:

[0514] Data analysis

[0515] The server runs machine learning algorithms to analyze the preprocessed data. For example, a generative AI model is used to assess emotional states. Analysis combines historical data with real-time data. The input is the preprocessed dataset. The machine learning algorithm assesses each employee's fatigue, stress, and emotional state. The output is the assessment of each employee's fatigue, stress, and emotional state.

[0516] Step 5:

[0517] Action Generation

[0518] Based on the evaluation results obtained in step 4, the server generates optimal break times and refreshment methods for each employee. Specifically, it suggests eye exercises, specific foods and drinks, short walks, etc. The input is the employee's evaluation results. The generative AI model generates options for breaks and refreshment methods and creates the necessary instructions. The output is personalized break and refreshment suggestions.

[0519] Step 6:

[0520] notification

[0521] The server notifies the employee's terminal of the generated action content. Notification formats include real-time pop-up messages and emails. The terminal receives the notification content and prompts the employee to take an appropriate break or refresh themselves. The input is the action proposal. The output is a notification to the employee's terminal.

[0522] Step 7:

[0523] Administrator Alerts

[0524] The server analyzes data from across departments and identifies employees and departments with high stress or low performance. Based on the results of this analysis, it generates an alert for the administrator. The alert is sent to the administrator's device, and the administrator takes appropriate measures based on the alert. The input is the evaluation results of employee data and department data. The output is the alert to the administrator and its contents.

[0525] The above are the specific processing steps of the program for the system that realizes the application example.

[0526] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the 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.

[0527] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0528] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0529] [Second embodiment]

[0530] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0531] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0532] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0533] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0534] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0535] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0536] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0537] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0538] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[0539] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0540] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0541] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[0542] The present invention is a system that detects fatigue and stress in employees and suggests optimal break times and methods for refreshing. Specific embodiments of the system and their operation will be described below.

[0543] System configuration

[0544] The system consists of the following main components:

[0545] server

[0546] Device (PC, smartphone, etc.)

[0547] Database

[0548] Installation and Operation Overview

[0549] 1. Data Collection

[0550] Users (employees) perform their daily work on their PCs or smartphones, and the associated work data is automatically recorded. They also periodically answer a stress questionnaire.

[0551] The terminal collects work data (PC operating time, work content, work location, etc.) and stress data (survey results) and sends them to the server.

[0552] 2. Data analysis

[0553] The server stores the received business data and stress data in an analysis database and performs data preprocessing, which includes removing invalid data and outliers.

[0554] The server analyzes the collected data and assesses the employee's level of fatigue and stress using a machine learning model that combines the employee's past data history with real-time data.

[0555] 3. Creating Actions

[0556] Based on the analysis, the server generates optimal break times and methods of relaxation for each employee, which could include, for example, eye exercises, eating specific foods and drinks, or taking short walks.

[0557] 4. Notifications and Alerts

[0558] The server notifies the employee of the action details generated via email or real-time pop-up messages.

[0559] The terminal displays the received notification on the screen and prompts the user (employee) to take an appropriate break or refresh themselves.

[0560] 5. Administrator Alerts

[0561] The server consolidates data from across departments and identifies employees and departments with particularly high levels of stress and fatigue.

[0562] An alert is generated for the administrator, such as "Many employees in department X are experiencing high levels of stress," and sent to the administrator's device. The administrator can then take company-wide measures based on this information.

[0563] Specific examples

[0564] Example 1: Email notification

[0565] Consider the case where employee A uses a PC for long periods of time and the results of a stress questionnaire indicate a high level of stress.

[0566] The server analyzes employee A's data and determines whether he is under excessive stress.

[0567] Generate an action that recommends 10 minutes of eye exercises and creates an email with detailed instructions on how to do the exercises.

[0568] An email is automatically sent to the device (employee A's email client) and a notification is displayed.

[0569] The user (Employee A) checks his email and performs eye exercises.

[0570] Example 2: Real-time notifications

[0571] Consider the case where it is detected that employee B has been working long hours in a row.

[0572] The server analyzes employee B's data and detects that he has been working long hours.

[0573] Generates actions that recommend a 15-minute break and a short walk.

[0574] A real-time notification is displayed on the device (Employee B's PC) encouraging the employee to "take a short walk."

[0575] The user (Employee B) follows the instructions and takes a short walk.

[0576] Example 3: Alerting the administrator

[0577] Suppose data reveals that a large percentage of employees in department X are in a state of high stress.

[0578] The server consolidates the data from Department X and determines that many employees are experiencing high levels of stress.

[0579] Generate an alert message for administrators: "Many employees in department X are experiencing high stress. Please recommend they take a break."

[0580] Display a notification on the terminal (administrator's PC).

[0581] The user (administrator) checks the alert, schedules a meeting to take appropriate measures, and sends an email to the entire department recommending a break.

[0582] In this way, this system supports efficient work performance while maintaining employee health by proposing and notifying optimal break and refreshment methods based on each employee's working style and condition.

[0583] The processing flow will be explained below.

[0584] Step 1:

[0585] Users (employees) use PCs and smartphones to carry out their work and periodically answer stress questionnaires while working.

[0586] Step 2:

[0587] The devices (employee PCs and smartphones) collect work data (PC operating time, work content, work location) and stress data (survey results). Collection is done automatically.

[0588] Step 3:

[0589] The device periodically sends the collected data to the server in the background, without affecting the user's work.

[0590] Step 4:

[0591] The server stores the received data in an analysis database, where data preprocessing (removal of invalid data and outliers, etc.) is performed as necessary.

[0592] Step 5:

[0593] The server uses machine learning algorithms to analyze the data, assessing each employee's fatigue and stress levels, and combines past data history with real-time data for analysis.

[0594] Step 6:

[0595] Based on the evaluation results, the server generates optimal break times and methods of relaxation for each employee, including actions such as eye exercises, eating specific foods and drinks, or taking a short walk.

[0596] Step 7:

[0597] The server then sends the generated action details to the employee's device, and notifications are sent via real-time pop-up messages or emails.

[0598] Step 8:

[0599] The device will display the received notification on the screen, for example, a message such as "Do 10 minutes of eye exercises."

[0600] Step 9:

[0601] The user (employee) follows the notification and performs the suggested refreshment method, such as doing eye exercises or taking a short walk.

[0602] Step 10:

[0603] The server analyzes the overall data and identifies employees or departments with particularly high stress levels. Based on the results of this analysis, it generates alerts for administrators.

[0604] Step 11:

[0605] The server then sends an alert to the administrator's device, such as a message saying, "Many employees in department X are experiencing high stress. Please encourage them to take a break."

[0606] Step 12:

[0607] An alert will be displayed on the device (administrator's PC or smartphone).

[0608] Step 13:

[0609] The user (administrator) checks the alert and schedules a meeting to take appropriate measures or sends an email to all employees recommending they take a break.

[0610] Example 1

[0611] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0612] With conventional systems, it was difficult to properly assess employee fatigue and stress and suggest effective break times and ways to refresh. Furthermore, there was a lack of a mechanism to grasp the stress levels of not only individual employees but the entire department, and to provide appropriate alerts to managers. This could lead to inadequate health management for employees, leading to a decline in performance.

[0613] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0614] In this invention, the server includes means for collecting employee work data and stress data, means for preprocessing the collected data to remove invalid data and outliers, means for analyzing the preprocessed data and executing a machine learning model for assessing employee fatigue and stress, means for proposing optimal break times and relaxation methods to employees based on the assessment results, means for notifying the employees of the suggestions to their terminals, and means for integrating data from the entire department, identifying employees or departments with particularly high levels of fatigue or stress, and notifying a manager of an alert. This makes it possible to accurately monitor the health status of individual employees and propose effective relaxation methods, and by notifying a manager of the stress level of the entire department, it is possible to take prompt and appropriate measures.

[0615] "Business data" refers to all information related to an employee's work, such as the employee's PC operating time, work content, and work location.

[0616] "Stress data" refers to the results of stress questionnaires answered by employees and information regarding the psychological and physiological state of employees.

[0617] "Data preprocessing" refers to the process of removing invalid data and outliers from collected data.

[0618] A "machine learning model" refers to a collection of algorithms and mathematical methods used to assess an employee's level of fatigue or stress based on past data.

[0619] "Refreshment methods" are specific methods suggested to reduce employees' fatigue and stress, such as eye exercises or short walks.

[0620] "Notification" refers to the act of transmitting generated action details and alert information to an employee or administrator's device.

[0621] "Alert to managers" refers to the act of integrating data from across departments to identify employees or departments with high levels of fatigue or stress and issuing a warning to managers.

[0622] This invention relates to a system that detects employee fatigue and stress and suggests optimal break times and ways to refresh. This system is mainly composed of a server, terminals, and a database.

[0623] Hardware and software used

[0624] Server: A server with high-performance data processing capabilities (e.g., Apache HTTP Server, Nginx)

[0625] Device: General PC or smartphone (e.g. Windows PC, Mac, iPhone, Android device)

[0626] Database: A database that stores and manages large amounts of data (e.g., MySQL, PostgreSQL)

[0627] Machine learning models: The machine learning algorithms used to assess employee fatigue and stress (e.g., TensorFlow, scikit-learn)

[0628] Specific Embodiments of the System

[0629] 1. Data Collection

[0630] Users carry out their daily work on their PC or smartphone, and their work data is automatically recorded. They also periodically answer a stress questionnaire.

[0631] The terminal collects business data such as the user's PC operating time, work content, and work location, as well as the user's stress data (survey results), and sends this to the server.

[0632] 2. Data Preprocessing

[0633] The server stores the received business data and stress data in an analysis database.

[0634] The server performs preprocessing on the stored data, such as removing invalid data and outliers. For example, consecutive identical data and obviously unrealistic values ​​are filtered out.

[0635] 3. Data analysis

[0636] The server uses the pre-processed data to run machine learning models to assess employees' levels of fatigue and stress.

[0637] The server inputs past data history and real-time data to calculate each employee's fatigue and stress levels.

[0638] 4. Creating Actions

[0639] Based on the evaluation results, the server will suggest optimal break times and ways to refresh employees.

[0640] Suggestions may include eye exercises, eating specific foods and drinks, or taking a short walk.

[0641] 5. Notifications and Alerts

[0642] The server notifies the specified device (PC or smartphone) of the generated action content.

[0643] The terminal displays the received notification on the screen in real time and prompts the user to perform the refresh method.

[0644] 6. Alert the administrator

[0645] The server aggregates data from across the department and detects high stress levels among specific employees or departments.

[0646] The server sends an alert to the administrator's device, such as "Many employees in department X are feeling high levels of stress."

[0647] Specific examples

[0648] 1. Example 1: Email notification

[0649] If employee A uses a PC for a long time and the results of a stress questionnaire indicate a high level of stress, the server will analyze the data and determine whether the stress is excessive.

[0650] The server generates an action that recommends 10 minutes of eye exercises and creates an email with detailed instructions on how to do it.

[0651] An email is automatically sent to the device (employee A's email client) and a notification is displayed.

[0652] The user (Employee A) checks his email and performs eye exercises.

[0653] 2. Example 2: Real-time notifications

[0654] If employee B works long hours consecutively, the server analyzes employee B's data and detects that long working hours have continued.

[0655] The server generates an action that recommends a 15-minute break and a short walk.

[0656] A real-time notification is displayed on the device (Employee B's PC) encouraging the employee to "take a short walk."

[0657] The user (Employee B) follows the instructions and takes a short walk.

[0658] 3. Example 3: Alerting the administrator

[0659] If most of the employees in department X are in a high stress state, the server consolidates the data for department X and determines that a large number of employees are experiencing high stress.

[0660] The server displays an alert on the administrator's device saying, "Many employees in department X are feeling high stress. Please recommend they take a break."

[0661] The user (administrator) checks the alert, schedules a meeting to take appropriate measures, and sends an email to the entire department recommending a break.

[0662] As described above, this system supports efficient work performance while maintaining employee health by proposing and notifying employees of optimal break and refreshment methods based on their individual work style and condition.

[0663] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0664] Step 1:

[0665] Data collection

[0666] Users carry out their daily work on their PC or smartphone, and their work data is automatically recorded. In addition, they are required to answer a stress questionnaire periodically.

[0667] Input: Work data such as user PC operating time, work content, and work location, as well as stress questionnaire results

[0668] The device collects this work data and stress data and sends it to the server using an HTTP request.

[0669] Output: Raw work and stress data sent to the server

[0670] Specific behavior:

[0671] The terminal records the PC operation time from when the user starts work at 9:00 AM until 6:00 PM. The terminal also collects the results of a stress questionnaire conducted at 1:00 PM (e.g., stress level 7 / 10) and sends them to the server.

[0672] Step 2:

[0673] Data Preprocessing

[0674] The server stores the received business data and stress data in an analysis database.

[0675] Input: Raw data received by the server

[0676] Perform data preprocessing to remove invalid data and outliers, for example, filtering out repeated identical data or unrealistic values.

[0677] Output: Preprocessed and clean data

[0678] Specific behavior:

[0679] The server stores the received data in a database and removes records with PC operating time of more than 24 hours as outliers.

[0680] Step 3:

[0681] Data analysis

[0682] The server uses the pre-processed data to run machine learning models to assess employees' levels of fatigue and stress.

[0683] Input: Preprocessed operational and stress data

[0684] Use machine learning models to assess employee stress levels based on historical and real-time data.

[0685] Output: Fatigue and stress levels for each employee

[0686] Specific behavior:

[0687] The server analyzes Alice's work data and stress questionnaire results from the past month and determines that her current stress level is 8 / 10.

[0688] Step 4:

[0689] Creating Actions

[0690] Based on the evaluation results, the server will suggest optimal break times and ways to refresh employees.

[0691] Input: Fatigue and stress levels for each employee

[0692] Generate optimal refreshment methods (e.g., eye exercises, eating certain foods and drinks, taking short walks).

[0693] Output: Refresh method suggestions

[0694] Specific behavior:

[0695] The server generates an action that recommends 10 minutes of eye exercises and creates data containing detailed instructions on how to do it.

[0696] Step 5:

[0697] Notifications and Alerts

[0698] The server notifies the employee's terminal of the generated action content.

[0699] Input: Refresh method proposal

[0700] The terminal displays the received notification on the screen and prompts the user to take action.

[0701] Output: Real-time notification messages

[0702] Specific behavior:

[0703] The server sends a pop-up message to Alice's PC saying, "Do eye exercises for 10 minutes," and the device immediately displays the message.

[0704] Step 6:

[0705] Administrator Alert

[0706] The server aggregates data from across the department and detects high fatigue or stress levels in specific employees or departments.

[0707] Input: Department-wide data

[0708] Alerts administrators to high stress situations.

[0709] Output: Alert message to administrator

[0710] Specific behavior:

[0711] The server detects that many employees in Department X have stress levels of 8 / 10 or higher and displays an alert on the administrator's PC saying, "Many employees in Department X are experiencing high levels of stress. Please recommend that they take a break."

[0712] (Application example 1)

[0713] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0714] The problem with employees and drivers is that fatigue caused by long working hours and stress leads to reduced productivity and health problems. The present invention aims to solve these problems and realize a healthy and efficient working environment.

[0715] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0716] In this invention, the server includes means for collecting employee work data and stress data, means for analyzing the collected data and evaluating the employee's fatigue and stress, means for proposing optimal rest periods and refreshment methods for the employee based on the evaluation results, and means for notifying the employee's terminal of the suggestions, means for collecting driver driving data and stress data, means for analyzing the collected data and evaluating the driver's fatigue and stress, means for proposing optimal rest periods and refreshment methods for the driver based on the evaluation results, and means for notifying the driver's terminal of the suggestions. This makes it possible to monitor the health status of employees and drivers in real time and suggest appropriate rest periods and refreshment methods, thereby improving work efficiency and maintaining health.

[0717] "Employee" refers to a person who belongs to a company or organization and performs work for that company or organization.

[0718] "Driver" means a person who drives a vehicle.

[0719] "Business data" refers to data generated or acquired by employees during work hours, and specifically includes PC operating time, work content, work location, etc.

[0720] "Stress data" refers to data that measures the stress levels of employees and drivers, and specifically includes the results of stress questionnaires and heart rates.

[0721] "Means of collecting data" refers to devices and software systems used to acquire and store various data on employees and drivers.

[0722] "Means for analyzing data" refers to software or algorithms used to analyze collected data and assess fatigue and stress levels among employees and drivers.

[0723] "Means for suggesting rest times and refreshment methods" refers to a system for recommending optimal rest and refreshment activities based on the results of data analysis.

[0724] "Means of notification" refers to devices or software that transmit suggested break times and refreshment methods to employees' or drivers' devices.

[0725] "Terminal" refers to a device used by employees or drivers to receive information, and specifically includes smartphones and in-vehicle displays.

[0726] This invention is a system that collects work data and stress data of employees and drivers, analyzes and evaluates the data, and proposes optimal rest times and methods for refreshing. Specific embodiments of the system and their operation are described below.

[0727] System Components

[0728] The system consists of the following main components:

[0729] server

[0730] Terminals (smartphones, in-car displays)

[0731] Database

[0732] Data collection

[0733] The server collects work data and stress data from smartphones and in-car displays. Work data includes driving speed, frequency of brake and accelerator operation, and driving time. Stress data includes the results of a simple stress questionnaire and heart rate. The collected data is stored in Firebase Firestore in real time.

[0734] Data analysis

[0735] The server stores the collected work data and stress data in an analysis database and performs data preprocessing, which involves removing invalid data and outliers. TensorFlow.js is used for analysis, and a machine learning model that combines past data history and real-time data is used. This allows the system to evaluate the fatigue and stress levels of employees and drivers.

[0736] Creating Actions

[0737] Based on the analysis results, the server generates optimal break times and methods of relaxation for each employee and driver. For example, it may suggest eye exercises, specific foods and drinks, a short walk, or a short meditation session. These suggestions are selected based on the most appropriate one for each situation.

[0738] Notifications and Alerts

[0739] The server then sends the generated action details to the employee or driver's device, which then displays the notification as a real-time pop-up message on the employee's smartphone or in-car display. Additionally, if a particularly high-stress state is detected, an alert will be sent.

[0740] Specific examples

[0741] Example 1: Real-time notifications for drivers

[0742] Consider a case where a driver has been working for long periods of time. The server analyzes the driver's driving data and stress data and detects that the driver has been working for long periods of time. The server generates an action recommending a 15-minute break and a short walk, and displays a notification such as "Please take a short walk" on the in-vehicle display.

[0743] Example 2: Break notification on smartphone

[0744] Consider a case where an employee uses a PC for long periods of time and the results of a stress questionnaire indicate high stress. The server analyzes the employee's work data and stress data to determine whether the employee is under excessive stress. It then generates an action recommending 10 minutes of eye exercises and sends a notification to the employee's smartphone.

[0745] Prompt Sentence Examples

[0746] "Please tell me the best time to take a break and refresh yourself while driving today. We will use the following data: acceleration data, heart rate, and driving time."

[0747] This system monitors the health status of employees and drivers in real time and suggests appropriate breaks and refreshments, thereby improving work efficiency and maintaining health.

[0748] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0749] Step 1: Data collection

[0750] The device (smartphone or in-car display) collects the driver's or employee's work data (driving speed, frequency of brake and accelerator operation, driving time, PC operating time, work content, work location, etc.) and stress data (heart rate, results of stress questionnaire) in real time.

[0751] Input: Sensor data, survey results

[0752] Output: Collected work data and stress data

[0753] Specific operation: Data is collected using smartphone sensors (e.g., acceleration sensor, heart rate sensor) and a simple stress questionnaire provided within the app. The in-car display collects vehicle driving information.

[0754] Step 2: Send data

[0755] The terminal transmits the collected data to the server in real time.

[0756] Input: Collected work data and stress data

[0757] Output: Data sent to the server

[0758] Specific operation: The application on the device has the function of periodically sending collected data to Firebase Firestore.

[0759] Step 3: Data Preprocessing

[0760] The server stores the received data in an analysis database and performs data preprocessing.

[0761] Input: Received work data and stress data

[0762] Output: Preprocessed data

[0763] Specific operation: Removes invalid data and outliers from the data stored in the database, and performs imputation and normalization as necessary.

[0764] Step 4: Data analysis

[0765] The server uses the preprocessed data to analyze employee and driver fatigue and stress using machine learning models.

[0766] Input: Preprocessed data

[0767] Output: Fatigue and stress assessment results

[0768] Specific operation: Using TensorFlow.js, a machine learning model is applied to the collected data to assess fatigue and stress in real time.

[0769] Step 5: Action Creation

[0770] The server generates optimal break times and refreshment methods based on the evaluation results.

[0771] Input: Fatigue and stress assessment results

[0772] Output: Suggestions for optimal break times and ways to refresh

[0773] Specific actions: Action generation algorithms create specific suggestions such as eye exercises, eating specific foods or drinks, taking a short walk, or meditating.

[0774] Step 6: Notifications and Alerts

[0775] The server notifies the generated action details to the employee or driver's device.

[0776] Input: Suggestions for optimal break times and ways to refresh

[0777] Output: Notifications and alerts

[0778] What it does: It uses Firebase Cloud Messaging to send real-time popup messages to smartphones and in-car displays, alerting drivers when particularly stressful situations are detected.

[0779] Step 7: Rest and Refresh

[0780] Users (employees or drivers) follow the suggestions displayed on the terminal to take breaks and refresh themselves.

[0781] Input: Notifications and Alerts

[0782] Output: Maintaining health and improving work efficiency

[0783] Specific actions: Do eye exercises, drink something, take a short walk or meditate.

[0784] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0785] The present invention is a system that detects employee fatigue and stress and proposes more accurate break times and methods for refreshing by combining it with an emotion engine that recognizes the user's emotions. Specific embodiments of the system and their operation are described below.

[0786] System configuration

[0787] The system consists of the following main components:

[0788] server

[0789] Device (PC, smartphone, etc.)

[0790] Database

[0791] Emotion Engine

[0792] Installation and Operation Overview

[0793] 1. Data Collection

[0794] Users (employees) use PCs and smartphones to carry out their work and periodically answer stress questionnaires while working.

[0795] The terminal collects work data (PC operating time, work content, work location) and stress data (survey results).

[0796] The emotion engine analyzes the user's facial expressions and voice through the device's camera and microphone, collecting emotional data in real time.

[0797] 2. Data Transmission

[0798] The terminal transmits the collected work data, stress data, and emotion data to the server at regular intervals.

[0799] 3. Data analysis

[0800] The server stores the received data in an analytical database and performs preprocessing on the data, which includes removing invalid data and outliers.

[0801] The server uses machine learning algorithms to assess each employee's fatigue level, stress level, and emotional state, combining historical data with real-time data for analysis.

[0802] 4. Creating Actions

[0803] Based on the analysis results, the server generates optimal break times and methods of relaxation for each employee, such as eye exercises, eating specific foods and drinks, or taking a short walk.

[0804] 5. Notifications and Alerts

[0805] The server then notifies the employee of the action details generated via a real-time pop-up message or email.

[0806] The terminal displays the received notification on the screen and prompts the user (employee) to take an appropriate break or refresh themselves.

[0807] 6. Administrator Alerts

[0808] The server analyzes the overall data and identifies employees or departments with particularly high stress or poor performance, and generates alerts for administrators based on the results of this analysis.

[0809] The server sends the generated alert to the administrator's terminal.

[0810] The device displays an alert on the administrator's PC or smartphone.

[0811] The user (administrator) checks the alert, schedules a meeting to take appropriate measures, and sends a company-wide email recommending a break.

[0812] Specific examples

[0813] Example 1: Email notification

[0814] Let's consider a case where Employee A uses a PC for long periods of time, and the results of a stress questionnaire indicate a high level of stress. Also, the emotion engine detects facial expressions that indicate anxiety or fatigue on Employee A.

[0815] The server analyzes employee A's data and determines whether he is experiencing excessive stress or fatigue.

[0816] Generate an action that recommends 10 minutes of eye exercises and creates an email with detailed instructions on how to do the exercises.

[0817] The device (employee A's email client) will automatically send an email and display a notification.

[0818] The user (Employee A) checks his email and performs eye exercises.

[0819] Example 2: Real-time notifications

[0820] Consider a case where the emotion engine detects that employee B has been working long hours in a row, and further detects fatigue and stress from employee B's facial expressions.

[0821] The server analyzes employee B's data and detects long working hours and high stress levels.

[0822] Generates actions that recommend a 15-minute break and a short walk.

[0823] The device (Employee B's PC) displays a real-time notification, encouraging the employee to "take a short walk."

[0824] The user (Employee B) follows the instructions and takes a short walk.

[0825] Example 3: Alerting the administrator

[0826] Consider a case where most employees in department X are in a state of high stress and the emotion engine detects facial expressions of anxiety and fatigue from multiple employees.

[0827] The server consolidates the data from Department X and determines that many employees are experiencing high levels of stress.

[0828] Generate an alert message for administrators: "Many employees in department X are experiencing high stress. Please recommend they take a break."

[0829] The device (administrator's PC or smartphone) will display a notification.

[0830] The user (administrator) checks the alert, schedules a meeting to take appropriate measures, and sends an email to the entire department recommending a break.

[0831] In this way, by combining this emotion engine, the system provides more precise break and refreshment methods that take into account the emotional state of each employee, helping to balance employee health with work efficiency.

[0832] The processing flow will be explained below.

[0833] Step 1:

[0834] Users (employees) use PCs and smartphones to carry out their work and periodically answer stress questionnaires while working.

[0835] Step 2:

[0836] The devices (employee PCs and smartphones) collect work data (PC operating time, work content, work location) and stress data (survey results). Collection is done automatically.

[0837] Step 3:

[0838] The emotion engine analyzes the user's facial expressions and voice through the device's camera and microphone to collect emotion data in real time, for example, tracking changes in the user's facial expressions through the camera and analyzing voice tone through the microphone.

[0839] Step 4:

[0840] The device periodically transmits collected work data, stress data, and emotion data to a server. The transmission is performed in the background and does not affect the user's work.

[0841] Step 5:

[0842] The server stores the received data in an analysis database, where data preprocessing (such as removing invalid data and outliers) is performed as necessary.

[0843] Step 6:

[0844] The server uses machine learning algorithms to assess each employee's fatigue level, stress level, and emotional state, combining historical data with real-time data for analysis.

[0845] Step 7:

[0846] Based on the evaluation results, the server generates optimal break times and methods of relaxation for each employee, including actions such as eye exercises, eating specific foods and drinks, or taking a short walk.

[0847] Step 8:

[0848] The server then sends the generated action details to the employee's device, and notifications are sent via real-time pop-up messages or emails.

[0849] Step 9:

[0850] The device will display the received notification on the screen, for example, a message such as "Do 10 minutes of eye exercises."

[0851] Step 10:

[0852] The user (employee) follows the notification and performs the suggested refreshment method, such as doing eye exercises or taking a short walk.

[0853] Step 11:

[0854] The server analyzes the overall data and identifies employees or departments that are particularly stressed or underperforming.

[0855] Step 12:

[0856] The server generates an alert message for the administrator, for example, "Many employees in department X are experiencing high stress. Please recommend they take a break."

[0857] Step 13:

[0858] The server sends an alert to the administrator's terminal, either via email or a pop-up message.

[0859] Step 14:

[0860] An alert will be displayed on the device (administrator's PC or smartphone).

[0861] Step 15:

[0862] The user (administrator) checks the alert and schedules a meeting to take appropriate measures or sends an email to all employees recommending they take a break.

[0863] Example 2

[0864] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0865] In today's work environment, employee fatigue and stress are increasing, resulting in a decline in labor productivity and work efficiency. Conventional systems primarily collect and analyze employee work data and stress data, but lack the ability to grasp employees' emotional states in real time or provide appropriate notifications to managers. As a result, they are unable to adequately suggest optimal break times and refreshment methods based on employees' conditions, limiting the effectiveness of improving labor productivity. A system that can solve these problems and improve employee health and work efficiency is needed.

[0866] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting employee work data, stress data, and emotional data; means for analyzing the collected data and evaluating the employee's fatigue, stress, and emotional state; means for proposing optimal break times and refreshment methods to the employee based on the evaluation results; means for notifying the employee of the suggestions to their terminal; and means for notifying the manager of employees and departments with high stress or low performance. This enables highly accurate fatigue and stress management that takes the employee's emotional state into consideration. Furthermore, real-time notifications and alerts to the manager enable prompt and appropriate responses, thereby maintaining employee health and improving work productivity.

[0867] "Business data" refers to data generated by employees during their work hours, including PC operating time, work content, and work location.

[0868] "Stress data" refers to data that indicates the level of stress felt by employees, and includes the results of stress questionnaires, etc.

[0869] "Emotional data" refers to data that indicates the emotional state of employees as analyzed from their facial expressions and voice, and is obtained through real-time facial and voice analysis.

[0870] An "emotion engine" is software or an algorithm that analyzes employees' emotional states from data obtained through devices such as cameras and microphones.

[0871] The "server" is a central processing unit that stores and analyzes collected data and provides optimal suggestions and notifications to employees and managers.

[0872] "Terminal" means a computing device used by an employee or administrator, including a PC or smartphone.

[0873] "Notifications" are information sent from the server to the terminal, and include suggestions for employees to take breaks or refresh themselves, and alerts to managers about high stress levels.

[0874] "Rest period" means a period of time designated for an employee to rest from work.

[0875] "Refreshment methods" are actions employees take to reduce stress and fatigue, including eye exercises, eating and drinking, and taking short walks.

[0876] A "database" is a digital storage system for systematically storing and managing business data, stress data, and emotional data collected by a server.

[0877] A "machine learning algorithm" is a mathematical model or calculation method used to analyze and evaluate employees' fatigue and stress levels based on collected data.

[0878] This system collects and analyzes employee work data, stress data, and emotional data, assesses employee fatigue and stress levels, and suggests optimal break times and ways to refresh. The system is comprised of the following main components:

[0879] server

[0880] Device (PC, smartphone, etc.)

[0881] Database

[0882] Emotion Engine

[0883] Data collection

[0884] Users (employees) use PCs or smartphones during work hours and periodically answer stress questionnaires. For example, employees answer a questionnaire every two hours during their eight-hour workday, rating their stress level on a five-point scale.

[0885] The device automatically collects work data (PC operating time, work content, work location) and stress data (survey results). For example, PC operating time and activity logs are periodically saved as log files. In addition, the device's camera and microphone are used to collect facial and voice data through an emotion engine. The emotion engine uses facial recognition software (e.g., OpenFace) and voice analysis tools to collect emotion data in real time.

[0886] Data transmission

[0887] The device sends the collected work data, stress data, and emotion data to the server at regular intervals (for example, every hour). Data is sent using a secure communication protocol such as HTTPS.

[0888] Data analysis

[0889] The server stores the received data in a database for analysis. For example, the data is stored systematically using an SQL database. The server then pre-processes the data, using principal component analysis (PCA) and data cleaning techniques to remove incorrect data and outliers.

[0890] The server uses machine learning algorithms (e.g., random forest, SVM) to assess each employee's fatigue level, stress level, and emotional state. It builds a predictive model based on past data history and real-time data to assess the employee's condition in real time.

[0891] Creating Actions

[0892] Based on the evaluation results, the server will generate optimal break times and methods for refreshing each employee, suggesting specific actions such as eye exercises, eating certain foods and drinks, or taking a short walk.

[0893] Notifications and Alerts

[0894] The server notifies the employee of the action details generated via a pop-up message or email.

[0895] The device will display the received notification on the screen and notify the user with an audio alert or vibration notification.

[0896] The user (employee) checks the notification and takes the suggested break or refreshment method.

[0897] Administrator Alerts

[0898] The server analyzes the overall data and identifies employees or departments with particularly high stress or poor performance. Based on the detected issues, it generates alert messages for administrators and sends them to their terminals.

[0899] The device displays an alert using an administrator application or email client.

[0900] The user (administrator) checks the alert, quickly schedules a meeting, and sends a company-wide email recommending a break.

[0901] Specific examples

[0902] Example 1: Email notification

[0903] Employee A uses a PC for long periods of time and indicates high stress in a stress questionnaire.

[0904] The server analyzes employee A's data and determines whether he is experiencing excessive stress or fatigue.

[0905] The server generates an action recommending 10 minutes of eye exercises and creates an email with detailed instructions.

[0906] The device (employee A's email client) will automatically send an email and display a notification.

[0907] The user (Employee A) checks his email and performs eye exercises.

[0908] Example 2: Real-time notifications

[0909] Employee B has been working long hours in a row and the emotion engine detects fatigue and high stress.

[0910] The server analyzes employee B's data and determines whether he is working long hours or experiencing high stress.

[0911] The server generates an action that recommends a 15-minute break and a short walk.

[0912] The device (Employee B's PC) displays a real-time notification, encouraging the employee to "take a short walk."

[0913] The user (Employee B) follows the instructions and takes a short walk.

[0914] Example 3: Alerting the administrator

[0915] A large proportion of employees in department X are under high stress, and the emotion engine detects expressions of anxiety and fatigue on multiple employees' faces.

[0916] The server consolidates the data from Department X and determines that many employees are experiencing high levels of stress.

[0917] The server generates an alert message for the administrator: "Many employees in department X are experiencing high stress. Please recommend they take a break."

[0918] The device (administrator's PC or smartphone) will display a notification.

[0919] The user (administrator) checks the alert, quickly schedules a meeting, and sends an email to the entire department recommending a break.

[0920] Prompt Sentence Examples

[0921] An example of a prompt to be input to the generative AI model is as follows:

[0922] "Describe a system that detects employee fatigue and stress and uses an emotion engine to suggest appropriate breaks and ways to refresh. Illustrate examples of email notifications for employees who have worked long hours, real-time notifications in natural language, and department-wide alerts for managers."

[0923] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0924] Step 1: Data collection

[0925] Users (employees) perform their work using PCs and smartphones.

[0926] The device automatically collects business data (PC operating time, work content, work location), for example, via the device's log file.

[0927] Users fill out a stress questionnaire periodically, for example, every two hours, by filling out a questionnaire form that appears on the screen.

[0928] The device uses a camera and microphone to collect the user's facial and voice data through the emotion engine. Specifically, the emotion engine acquires emotion data in real time using facial recognition software (e.g., OpenFace) and voice analysis tools.

[0929] Input: User's work data (PC operating time, work content, work location), stress questionnaire results, facial expression data, voice data.

[0930] Output: Collected work data, stress data, and emotion data.

[0931] Step 2: Send data

[0932] The terminal transmits the collected data to the server at regular intervals, for example, a schedule for transmitting data every hour is set.

[0933] Data is transmitted using secure communication protocols such as HTTPS.

[0934] Input: Collected work data, stress data, and emotion data.

[0935] Output: Work data, stress data, and emotion data sent to the server.

[0936] Step 3: Data analysis

[0937] The server stores the received data in a database for analysis, for example, by systematically storing the data using an SQL database.

[0938] The server pre-processes the data, using principal component analysis (PCA) and data cleaning techniques to remove incorrect data and outliers.

[0939] The server uses machine learning algorithms (e.g., random forest, SVM) to assess each employee's fatigue level, stress level, and emotional state. It builds and analyzes a predictive model based on past data history and real-time data.

[0940] Input: Work data, stress data, and emotion data sent to the server.

[0941] Output: Fatigue, stress, and emotional state assessment results.

[0942] Step 4: Creating Actions

[0943] The server generates optimal break times and refreshment methods for each employee based on the evaluation results.

[0944] Specifically, it generates actions such as eye exercises, eating specific foods and drinks, taking a short walk, etc. For example, if the user is highly fatigued, it will suggest "10 minutes of eye exercises recommended."

[0945] Input: Fatigue, stress, and emotional state assessment results.

[0946] Output: Generated break times and refresh methods.

[0947] Step 5: Notifications and Alerts

[0948] The server notifies the employee of the action details generated via a pop-up message or email.

[0949] The device will display the received notification on the screen and notify the user with an audio alert or vibration notification.

[0950] The user checks the notification content and takes the suggested break or refreshment method.

[0951] Input: Generated break times and refreshment methods.

[0952] Output: Notifications that appear on employee devices.

[0953] Step 6: Administrator alerts

[0954] The server analyzes the overall data and identifies employees or departments that are particularly stressed or underperforming.

[0955] An alert message for the administrator is generated based on the data and sent to the administrator's terminal.

[0956] The device displays an alert using an administrator application or email client.

[0957] The user (administrator) checks the alert, quickly schedules a meeting, and sends a company-wide email recommending a break.

[0958] Input: Overall data analysis results.

[0959] Output: An alert message for the administrator.

[0960] (Application example 2)

[0961] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0962] In today's work environment, it is common for employees to work long hours, which can easily lead to the accumulation of fatigue and stress. Therefore, managing employee health and maintaining and improving work efficiency are important issues. However, traditional methods make it difficult to effectively monitor individual employees' fatigue and stress levels in real time and suggest personalized break times and ways to refresh. This can lead to excessive employee stress, which can ultimately lead to health problems and reduced work efficiency.

[0963] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0964] In this invention, the server includes means for collecting employee work data and stress data, means for analyzing the collected data and evaluating the employee's fatigue and stress, means for collecting and analyzing emotional data in real time, means for evaluating the employee's emotional state based on the emotional data and using the evaluation results to generate personalized break times and relaxation methods, and means for notifying the employee's terminal of the suggestions. This makes it possible to provide highly accurate break time suggestions and relaxation methods tailored to the individual circumstances of each employee.

[0965] "Business data" refers to data generated when employees perform their work, and specifically includes information such as PC operating time, work content, and work location.

[0966] "Stress data" refers to data that indicates the stress state of employees, and specifically includes survey results and physiological indicators.

[0967] "Evaluation measures" are means for analyzing collected data and evaluating employee fatigue and stress.

[0968] The "suggestion means" is a means for generating optimal break times and methods of relaxation for employees based on the evaluation results and proposing these to employees.

[0969] "Terminal" refers to an information processing device used by an employee, and specifically includes PCs, smartphones, tablets, etc.

[0970] "Emotion data" is data that indicates the emotional state of an employee, and specifically includes the analysis results of facial expressions, voice, movements, etc.

[0971] "Emotional state" refers to an employee's current emotional state, such as happiness, anxiety, fatigue, etc.

[0972] "Personalization" means that it is individually tailored to each employee's characteristics and circumstances.

[0973] The "notification means" refers to a means for informing employees of the generated break times and refreshment methods, and specifically includes real-time pop-up messages, emails, etc.

[0974] "Real-time analysis" means analyzing data immediately, close to the moment it is generated.

[0975] This invention is a system that detects employee fatigue and stress and evaluates their emotional state in real time using emotional data, thereby providing more accurate break times and methods for refreshing. This invention is composed of the following main components: a server, a terminal, a database, and an emotion engine.

[0976] System Configuration

[0977] 1. Server

[0978] The server is responsible for the main calculations, collecting and analyzing work data, stress data, and emotion data, and also notifying each employee of the generated break times and how to refresh themselves.

[0979] 2. Terminal

[0980] The devices are information processing devices used by employees, such as PCs, smartphones, tablets, etc. The devices collect work data and stress data, and also use an emotion engine to collect emotion data in real time from cameras and microphones.

[0981] 3. Database

[0982] The database stores the collected work data, stress data, and emotion data, and the server uses this database for analysis.

[0983] 4. Emotion Engine

[0984] The emotion engine uses the device's camera and microphone to analyze employees' facial expressions and voices and assess their emotional state in real time.

[0985] Processing flow

[0986] 1. Data Collection

[0987] Employees use devices to carry out their work and periodically answer stress questionnaires. The emotion engine analyzes employees' facial expressions and voices via cameras and microphones to collect emotional data in real time.

[0988] 2. Data Transmission

[0989] The collected work data, stress data, and emotion data are transmitted to a server at regular intervals.

[0990] 3. Data analysis

[0991] The server stores the received data in a database and performs preprocessing. It uses machine learning algorithms to evaluate each employee's fatigue level, stress level, and emotional state. It then combines past data history with real-time data for analysis.

[0992] 4. Creating Actions

[0993] Based on the analysis results, the server generates optimal break times and methods for refreshing each employee, such as eye exercises, eating certain foods and drinks, or taking a short walk.

[0994] 5. Notification

[0995] The generated action details are sent to the employee's device via a real-time pop-up message or email.

[0996] Specific examples

[0997] Example 1: Email notification

[0998] Let's assume that employee A works long hours and the results of a stress questionnaire and emotional data indicate a high level of stress.

[0999] The server analyzes employee A's data, generates an action recommending 10 minutes of eye exercises, and sends the specific instructions via email.

[1000] The message reads, "Do eye exercises for 10 minutes."

[1001] Example 2: Real-time notifications

[1002] Consider a case where the server detects that employee B has been working long hours in a row, and furthermore, emotion data confirms that he or she is tired.

[1003] The server generates actions recommending a 15-minute break and a short walk, and displays real-time notifications on the device.

[1004] The message reads, "Take a short walk."

[1005] Example 3: Alerting the administrator

[1006] Imagine that the server detects that many employees in department X are in a state of high stress.

[1007] The server consolidates data from department X and alerts the administrator when stress levels are high.

[1008] The message read, "Employees in department X are under high stress. Please recommend a company-wide break."

[1009] As shown in these specific examples, by combining an emotion engine, the present invention provides more precise break and refreshment methods that take into account the emotional state of each employee, thereby helping employees achieve both health and work efficiency.

[1010] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1011] Step 1:

[1012] Data collection

[1013] The device collects work data (e.g., PC operating time, work content, and work location) generated by employees using their PCs or smartphones while performing their work. Employees also periodically answer stress questionnaires, and the results are collected as stress data. Furthermore, the emotion engine analyzes facial expressions and voices through the device's camera and microphone to collect emotion data in real time. The input data are work data, stress data, and emotion data. The output is a set of collected data.

[1014] Step 2:

[1015] Data transmission

[1016] The device periodically sends the work data, stress data, and emotion data collected in step 1 to the server. The input is the collected dataset. The data is packaged in JSON format and sent to the cloud server using an HTTP API. The output is a confirmation message indicating that the data was successfully sent to the server.

[1017] Step 3:

[1018] Data storage and preprocessing

[1019] The server stores the received data in a database. For example, MySQL or PostgreSQL is used as the database system. The received data is first preprocessed to remove invalid data and outliers. The input is the dataset sent to the server. Before storing it in the database, processing such as filling in missing data and standardizing the data format is performed. The output is a preprocessed, clean dataset.

[1020] Step 4:

[1021] Data analysis

[1022] The server runs machine learning algorithms to analyze the preprocessed data. For example, a generative AI model is used to assess emotional states. Analysis combines historical data with real-time data. The input is the preprocessed dataset. The machine learning algorithm assesses each employee's fatigue, stress, and emotional state. The output is the assessment of each employee's fatigue, stress, and emotional state.

[1023] Step 5:

[1024] Action Generation

[1025] Based on the evaluation results obtained in step 4, the server generates optimal break times and refreshment methods for each employee. Specifically, it suggests eye exercises, specific foods and drinks, short walks, etc. The input is the employee's evaluation results. The generative AI model generates options for breaks and refreshment methods and creates the necessary instructions. The output is personalized break and refreshment suggestions.

[1026] Step 6:

[1027] notification

[1028] The server notifies the employee's terminal of the generated action content. Notification formats include real-time pop-up messages and emails. The terminal receives the notification content and prompts the employee to take an appropriate break or refresh themselves. The input is the action proposal. The output is a notification to the employee's terminal.

[1029] Step 7:

[1030] Administrator Alerts

[1031] The server analyzes data from across departments and identifies employees and departments with high stress or low performance. Based on the results of this analysis, it generates an alert for the administrator. The alert is sent to the administrator's device, and the administrator takes appropriate measures based on the alert. The input is the evaluation results of employee data and department data. The output is the alert to the administrator and its contents.

[1032] The above are the specific processing steps of the program for the system that realizes the application example.

[1033] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1034] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1035] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[1036] [Third embodiment]

[1037] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1038] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[1039] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1040] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[1041] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1042] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1043] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1044] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1045] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[1046] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1047] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1048] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[1049] The present invention is a system that detects fatigue and stress in employees and suggests optimal break times and methods for refreshing. Specific embodiments of the system and their operation will be described below.

[1050] System configuration

[1051] The system consists of the following main components:

[1052] server

[1053] Device (PC, smartphone, etc.)

[1054] Database

[1055] Installation and Operation Overview

[1056] 1. Data Collection

[1057] Users (employees) perform their daily work on their PCs or smartphones, and the associated work data is automatically recorded. They also periodically answer a stress questionnaire.

[1058] The terminal collects work data (PC operating time, work content, work location, etc.) and stress data (survey results) and sends them to the server.

[1059] 2. Data analysis

[1060] The server stores the received business data and stress data in an analysis database and performs data preprocessing, which includes removing invalid data and outliers.

[1061] The server analyzes the collected data and assesses the employee's level of fatigue and stress using a machine learning model that combines the employee's past data history with real-time data.

[1062] 3. Creating Actions

[1063] Based on the analysis, the server generates optimal break times and methods of relaxation for each employee, which could include, for example, eye exercises, eating specific foods and drinks, or taking short walks.

[1064] 4. Notifications and Alerts

[1065] The server notifies the employee of the action details generated via email or real-time pop-up messages.

[1066] The terminal displays the received notification on the screen and prompts the user (employee) to take an appropriate break or refresh themselves.

[1067] 5. Administrator Alerts

[1068] The server consolidates data from across departments and identifies employees and departments with particularly high levels of stress and fatigue.

[1069] An alert is generated for the administrator, such as "Many employees in department X are experiencing high levels of stress," and sent to the administrator's device. The administrator can then take company-wide measures based on this information.

[1070] Specific examples

[1071] Example 1: Email notification

[1072] Consider the case where employee A uses a PC for long periods of time and the results of a stress questionnaire indicate a high level of stress.

[1073] The server analyzes employee A's data and determines whether he is under excessive stress.

[1074] Generate an action that recommends 10 minutes of eye exercises and creates an email with detailed instructions on how to do the exercises.

[1075] An email is automatically sent to the device (employee A's email client) and a notification is displayed.

[1076] The user (Employee A) checks his email and performs eye exercises.

[1077] Example 2: Real-time notifications

[1078] Consider the case where it is detected that employee B has been working long hours in a row.

[1079] The server analyzes employee B's data and detects that he has been working long hours.

[1080] Generates actions that recommend a 15-minute break and a short walk.

[1081] A real-time notification is displayed on the device (Employee B's PC) encouraging the employee to "take a short walk."

[1082] The user (Employee B) follows the instructions and takes a short walk.

[1083] Example 3: Alerting the administrator

[1084] Suppose data reveals that a large percentage of employees in department X are in a state of high stress.

[1085] The server consolidates the data from Department X and determines that many employees are experiencing high levels of stress.

[1086] Generate an alert message for administrators: "Many employees in department X are experiencing high stress. Please recommend they take a break."

[1087] Display a notification on the terminal (administrator's PC).

[1088] The user (administrator) checks the alert, schedules a meeting to take appropriate measures, and sends an email to the entire department recommending a break.

[1089] In this way, this system supports efficient work performance while maintaining employee health by proposing and notifying optimal break and refreshment methods based on each employee's working style and condition.

[1090] The processing flow will be explained below.

[1091] Step 1:

[1092] Users (employees) use PCs and smartphones to carry out their work and periodically answer stress questionnaires while working.

[1093] Step 2:

[1094] The devices (employee PCs and smartphones) collect work data (PC operating time, work content, work location) and stress data (survey results). Collection is done automatically.

[1095] Step 3:

[1096] The device periodically sends the collected data to the server in the background, without affecting the user's work.

[1097] Step 4:

[1098] The server stores the received data in an analysis database, where data preprocessing (removal of invalid data and outliers, etc.) is performed as necessary.

[1099] Step 5:

[1100] The server uses machine learning algorithms to analyze the data, assessing each employee's fatigue and stress levels, and combines past data history with real-time data for analysis.

[1101] Step 6:

[1102] Based on the evaluation results, the server generates optimal break times and methods of relaxation for each employee, including actions such as eye exercises, eating specific foods and drinks, or taking a short walk.

[1103] Step 7:

[1104] The server then sends the generated action details to the employee's device, and notifications are sent via real-time pop-up messages or emails.

[1105] Step 8:

[1106] The device will display the received notification on the screen, for example, a message such as "Do 10 minutes of eye exercises."

[1107] Step 9:

[1108] The user (employee) follows the notification and performs the suggested refreshment method, such as doing eye exercises or taking a short walk.

[1109] Step 10:

[1110] The server analyzes the overall data and identifies employees or departments with particularly high stress levels. Based on the results of this analysis, it generates alerts for administrators.

[1111] Step 11:

[1112] The server then sends an alert to the administrator's device, such as a message saying, "Many employees in department X are experiencing high stress. Please encourage them to take a break."

[1113] Step 12:

[1114] An alert will be displayed on the device (administrator's PC or smartphone).

[1115] Step 13:

[1116] The user (administrator) checks the alert and schedules a meeting to take appropriate measures or sends an email to all employees recommending they take a break.

[1117] Example 1

[1118] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1119] With conventional systems, it was difficult to properly assess employee fatigue and stress and suggest effective break times and ways to refresh. Furthermore, there was a lack of a mechanism to grasp the stress levels of not only individual employees but the entire department, and to provide appropriate alerts to managers. This could lead to inadequate health management for employees, leading to a decline in performance.

[1120] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1121] In this invention, the server includes means for collecting employee work data and stress data, means for preprocessing the collected data to remove invalid data and outliers, means for analyzing the preprocessed data and executing a machine learning model for assessing employee fatigue and stress, means for proposing optimal break times and relaxation methods to employees based on the assessment results, means for notifying the employees of the suggestions to their terminals, and means for integrating data from the entire department, identifying employees or departments with particularly high levels of fatigue or stress, and notifying a manager of an alert. This makes it possible to accurately monitor the health status of individual employees and propose effective relaxation methods, and by notifying a manager of the stress level of the entire department, it is possible to take prompt and appropriate measures.

[1122] "Business data" refers to all information related to an employee's work, such as the employee's PC operating time, work content, and work location.

[1123] "Stress data" refers to the results of stress questionnaires answered by employees and information regarding the psychological and physiological state of employees.

[1124] "Data preprocessing" refers to the process of removing invalid data and outliers from collected data.

[1125] A "machine learning model" refers to a collection of algorithms and mathematical methods used to assess an employee's level of fatigue or stress based on past data.

[1126] "Refreshment methods" are specific methods suggested to reduce employees' fatigue and stress, such as eye exercises or short walks.

[1127] "Notification" refers to the act of transmitting generated action details and alert information to an employee or administrator's device.

[1128] "Alert to managers" refers to the act of integrating data from across departments to identify employees or departments with high levels of fatigue or stress and issuing a warning to managers.

[1129] This invention relates to a system that detects employee fatigue and stress and suggests optimal break times and ways to refresh. This system is mainly composed of a server, terminals, and a database.

[1130] Hardware and software used

[1131] Server: A server with high-performance data processing capabilities (e.g., Apache HTTP Server, Nginx)

[1132] Device: General PC or smartphone (e.g. Windows PC, Mac, iPhone, Android device)

[1133] Database: A database that stores and manages large amounts of data (e.g., MySQL, PostgreSQL)

[1134] Machine learning models: The machine learning algorithms used to assess employee fatigue and stress (e.g., TensorFlow, scikit-learn)

[1135] Specific Embodiments of the System

[1136] 1. Data Collection

[1137] Users carry out their daily work on their PC or smartphone, and their work data is automatically recorded. They also periodically answer a stress questionnaire.

[1138] The terminal collects business data such as the user's PC operating time, work content, and work location, as well as the user's stress data (survey results), and sends this to the server.

[1139] 2. Data Preprocessing

[1140] The server stores the received business data and stress data in an analysis database.

[1141] The server performs preprocessing on the stored data, such as removing invalid data and outliers. For example, consecutive identical data and obviously unrealistic values ​​are filtered out.

[1142] 3. Data analysis

[1143] The server uses the pre-processed data to run machine learning models to assess employees' levels of fatigue and stress.

[1144] The server inputs past data history and real-time data to calculate each employee's fatigue and stress levels.

[1145] 4. Creating Actions

[1146] Based on the evaluation results, the server will suggest optimal break times and ways to refresh employees.

[1147] Suggestions may include eye exercises, eating specific foods and drinks, or taking a short walk.

[1148] 5. Notifications and Alerts

[1149] The server notifies the specified device (PC or smartphone) of the generated action content.

[1150] The terminal displays the received notification on the screen in real time and prompts the user to perform the refresh method.

[1151] 6. Alert the administrator

[1152] The server aggregates data from across the department and detects high stress levels among specific employees or departments.

[1153] The server sends an alert to the administrator's device, such as "Many employees in department X are feeling high levels of stress."

[1154] Specific examples

[1155] 1. Example 1: Email notification

[1156] If employee A uses a PC for a long time and the results of a stress questionnaire indicate a high level of stress, the server will analyze the data and determine whether the stress is excessive.

[1157] The server generates an action that recommends 10 minutes of eye exercises and creates an email with detailed instructions on how to do it.

[1158] An email is automatically sent to the device (employee A's email client) and a notification is displayed.

[1159] The user (Employee A) checks his email and performs eye exercises.

[1160] 2. Example 2: Real-time notifications

[1161] If employee B works long hours consecutively, the server analyzes employee B's data and detects that long working hours have continued.

[1162] The server generates an action that recommends a 15-minute break and a short walk.

[1163] A real-time notification is displayed on the device (Employee B's PC) encouraging the employee to "take a short walk."

[1164] The user (Employee B) follows the instructions and takes a short walk.

[1165] 3. Example 3: Alerting the administrator

[1166] If most of the employees in department X are in a high stress state, the server consolidates the data for department X and determines that a large number of employees are experiencing high stress.

[1167] The server displays an alert on the administrator's device saying, "Many employees in department X are feeling high stress. Please recommend they take a break."

[1168] The user (administrator) checks the alert, schedules a meeting to take appropriate measures, and sends an email to the entire department recommending a break.

[1169] As described above, this system supports efficient work performance while maintaining employee health by proposing and notifying employees of optimal break and refreshment methods based on their individual work style and condition.

[1170] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1171] Step 1:

[1172] Data collection

[1173] Users carry out their daily work on their PC or smartphone, and their work data is automatically recorded. In addition, they are required to answer a stress questionnaire periodically.

[1174] Input: Work data such as user PC operating time, work content, and work location, as well as stress questionnaire results

[1175] The device collects this work data and stress data and sends it to the server using an HTTP request.

[1176] Output: Raw work and stress data sent to the server

[1177] Specific behavior:

[1178] The terminal records the PC operation time from when the user starts work at 9:00 AM until 6:00 PM. The terminal also collects the results of a stress questionnaire conducted at 1:00 PM (e.g., stress level 7 / 10) and sends them to the server.

[1179] Step 2:

[1180] Data Preprocessing

[1181] The server stores the received business data and stress data in an analysis database.

[1182] Input: Raw data received by the server

[1183] Perform data preprocessing to remove invalid data and outliers, for example, filtering out repeated identical data or unrealistic values.

[1184] Output: Preprocessed and clean data

[1185] Specific behavior:

[1186] The server stores the received data in a database and removes records with PC operating time of more than 24 hours as outliers.

[1187] Step 3:

[1188] Data analysis

[1189] The server uses the pre-processed data to run machine learning models to assess employees' levels of fatigue and stress.

[1190] Input: Preprocessed operational and stress data

[1191] Use machine learning models to assess employee stress levels based on historical and real-time data.

[1192] Output: Fatigue and stress levels for each employee

[1193] Specific behavior:

[1194] The server analyzes Alice's work data and stress questionnaire results from the past month and determines that her current stress level is 8 / 10.

[1195] Step 4:

[1196] Creating Actions

[1197] Based on the evaluation results, the server will suggest optimal break times and ways to refresh employees.

[1198] Input: Fatigue and stress levels for each employee

[1199] Generate optimal refreshment methods (e.g., eye exercises, eating certain foods and drinks, taking short walks).

[1200] Output: Refresh method suggestions

[1201] Specific behavior:

[1202] The server generates an action that recommends 10 minutes of eye exercises and creates data containing detailed instructions on how to do it.

[1203] Step 5:

[1204] Notifications and Alerts

[1205] The server notifies the employee's terminal of the generated action content.

[1206] Input: Refresh method proposal

[1207] The terminal displays the received notification on the screen and prompts the user to take action.

[1208] Output: Real-time notification messages

[1209] Specific behavior:

[1210] The server sends a pop-up message to Alice's PC saying, "Do eye exercises for 10 minutes," and the device immediately displays the message.

[1211] Step 6:

[1212] Administrator Alert

[1213] The server aggregates data from across the department and detects high fatigue or stress levels in specific employees or departments.

[1214] Input: Department-wide data

[1215] Alerts administrators to high stress situations.

[1216] Output: Alert message to administrator

[1217] Specific behavior:

[1218] The server detects that many employees in Department X have stress levels of 8 / 10 or higher and displays an alert on the administrator's PC saying, "Many employees in Department X are experiencing high levels of stress. Please recommend that they take a break."

[1219] (Application example 1)

[1220] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1221] The problem with employees and drivers is that fatigue caused by long working hours and stress leads to reduced productivity and health problems. The present invention aims to solve these problems and realize a healthy and efficient working environment.

[1222] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1223] In this invention, the server includes means for collecting employee work data and stress data, means for analyzing the collected data and evaluating the employee's fatigue and stress, means for proposing optimal rest periods and refreshment methods for the employee based on the evaluation results, and means for notifying the employee's terminal of the suggestions, means for collecting driver driving data and stress data, means for analyzing the collected data and evaluating the driver's fatigue and stress, means for proposing optimal rest periods and refreshment methods for the driver based on the evaluation results, and means for notifying the driver's terminal of the suggestions. This makes it possible to monitor the health status of employees and drivers in real time and suggest appropriate rest periods and refreshment methods, thereby improving work efficiency and maintaining health.

[1224] "Employee" refers to a person who belongs to a company or organization and performs work for that company or organization.

[1225] "Driver" means a person who drives a vehicle.

[1226] "Business data" refers to data generated or acquired by employees during work hours, and specifically includes PC operating time, work content, work location, etc.

[1227] "Stress data" refers to data that measures the stress levels of employees and drivers, and specifically includes the results of stress questionnaires and heart rates.

[1228] "Means of collecting data" refers to devices and software systems used to acquire and store various data on employees and drivers.

[1229] "Means for analyzing data" refers to software or algorithms used to analyze collected data and assess fatigue and stress levels among employees and drivers.

[1230] "Means for suggesting rest times and refreshment methods" refers to a system for recommending optimal rest and refreshment activities based on the results of data analysis.

[1231] "Means of notification" refers to devices or software that transmit suggested break times and refreshment methods to employees' or drivers' devices.

[1232] "Terminal" refers to a device used by employees or drivers to receive information, and specifically includes smartphones and in-vehicle displays.

[1233] This invention is a system that collects work data and stress data of employees and drivers, analyzes and evaluates the data, and proposes optimal rest times and methods for refreshing. Specific embodiments of the system and their operation are described below.

[1234] System Components

[1235] The system consists of the following main components:

[1236] server

[1237] Terminals (smartphones, in-car displays)

[1238] Database

[1239] Data collection

[1240] The server collects work data and stress data from smartphones and in-car displays. Work data includes driving speed, frequency of brake and accelerator operation, and driving time. Stress data includes the results of a simple stress questionnaire and heart rate. The collected data is stored in Firebase Firestore in real time.

[1241] Data analysis

[1242] The server stores the collected work data and stress data in an analysis database and performs data preprocessing, which involves removing invalid data and outliers. TensorFlow.js is used for analysis, and a machine learning model that combines past data history and real-time data is used. This allows the system to evaluate the fatigue and stress levels of employees and drivers.

[1243] Creating Actions

[1244] Based on the analysis results, the server generates optimal break times and methods of relaxation for each employee and driver. For example, it may suggest eye exercises, specific foods and drinks, a short walk, or a short meditation session. These suggestions are selected based on the most appropriate one for each situation.

[1245] Notifications and Alerts

[1246] The server then sends the generated action details to the employee or driver's device, which then displays the notification as a real-time pop-up message on the employee's smartphone or in-car display. Additionally, if a particularly high-stress state is detected, an alert will be sent.

[1247] Specific examples

[1248] Example 1: Real-time notifications for drivers

[1249] Consider a case where a driver has been working for long periods of time. The server analyzes the driver's driving data and stress data and detects that the driver has been working for long periods of time. The server generates an action recommending a 15-minute break and a short walk, and displays a notification such as "Please take a short walk" on the in-vehicle display.

[1250] Example 2: Break notification on smartphone

[1251] Consider a case where an employee uses a PC for long periods of time and the results of a stress questionnaire indicate high stress. The server analyzes the employee's work data and stress data to determine whether the employee is under excessive stress. It then generates an action recommending 10 minutes of eye exercises and sends a notification to the employee's smartphone.

[1252] Prompt Sentence Examples

[1253] "Please tell me the best time to take a break and refresh yourself while driving today. We will use the following data: acceleration data, heart rate, and driving time."

[1254] This system monitors the health status of employees and drivers in real time and suggests appropriate breaks and refreshments, thereby improving work efficiency and maintaining health.

[1255] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1256] Step 1: Data collection

[1257] The device (smartphone or in-car display) collects the driver's or employee's work data (driving speed, frequency of brake and accelerator operation, driving time, PC operating time, work content, work location, etc.) and stress data (heart rate, results of stress questionnaire) in real time.

[1258] Input: Sensor data, survey results

[1259] Output: Collected work data and stress data

[1260] Specific operation: Data is collected using smartphone sensors (e.g., acceleration sensor, heart rate sensor) and a simple stress questionnaire provided within the app. The in-car display collects vehicle driving information.

[1261] Step 2: Send data

[1262] The terminal transmits the collected data to the server in real time.

[1263] Input: Collected work data and stress data

[1264] Output: Data sent to the server

[1265] Specific operation: The application on the device has the function of periodically sending collected data to Firebase Firestore.

[1266] Step 3: Data Preprocessing

[1267] The server stores the received data in an analysis database and performs data preprocessing.

[1268] Input: Received work data and stress data

[1269] Output: Preprocessed data

[1270] Specific operation: Removes invalid data and outliers from the data stored in the database, and performs imputation and normalization as necessary.

[1271] Step 4: Data analysis

[1272] The server uses the preprocessed data to analyze employee and driver fatigue and stress using machine learning models.

[1273] Input: Preprocessed data

[1274] Output: Fatigue and stress assessment results

[1275] Specific operation: Using TensorFlow.js, a machine learning model is applied to the collected data to assess fatigue and stress in real time.

[1276] Step 5: Action Creation

[1277] The server generates optimal break times and refreshment methods based on the evaluation results.

[1278] Input: Fatigue and stress assessment results

[1279] Output: Suggestions for optimal break times and ways to refresh

[1280] Specific actions: Action generation algorithms create specific suggestions such as eye exercises, eating specific foods or drinks, taking a short walk, or meditating.

[1281] Step 6: Notifications and Alerts

[1282] The server notifies the generated action details to the employee or driver's device.

[1283] Input: Suggestions for optimal break times and ways to refresh

[1284] Output: Notifications and alerts

[1285] What it does: It uses Firebase Cloud Messaging to send real-time popup messages to smartphones and in-car displays, alerting drivers when particularly stressful situations are detected.

[1286] Step 7: Rest and Refresh

[1287] Users (employees or drivers) follow the suggestions displayed on the terminal to take breaks and refresh themselves.

[1288] Input: Notifications and Alerts

[1289] Output: Maintaining health and improving work efficiency

[1290] Specific actions: Do eye exercises, drink something, take a short walk or meditate.

[1291] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1292] The present invention is a system that detects employee fatigue and stress and proposes more accurate break times and methods for refreshing by combining it with an emotion engine that recognizes the user's emotions. Specific embodiments of the system and their operation are described below.

[1293] System configuration

[1294] The system consists of the following main components:

[1295] server

[1296] Device (PC, smartphone, etc.)

[1297] Database

[1298] Emotion Engine

[1299] Installation and Operation Overview

[1300] 1. Data Collection

[1301] Users (employees) use PCs and smartphones to carry out their work and periodically answer stress questionnaires while working.

[1302] The terminal collects work data (PC operating time, work content, work location) and stress data (survey results).

[1303] The emotion engine analyzes the user's facial expressions and voice through the device's camera and microphone, collecting emotional data in real time.

[1304] 2. Data Transmission

[1305] The terminal transmits the collected work data, stress data, and emotion data to the server at regular intervals.

[1306] 3. Data analysis

[1307] The server stores the received data in an analytical database and performs preprocessing on the data, which includes removing invalid data and outliers.

[1308] The server uses machine learning algorithms to assess each employee's fatigue level, stress level, and emotional state, combining historical data with real-time data for analysis.

[1309] 4. Creating Actions

[1310] Based on the analysis results, the server generates optimal break times and methods of relaxation for each employee, such as eye exercises, eating specific foods and drinks, or taking a short walk.

[1311] 5. Notifications and Alerts

[1312] The server then notifies the employee of the action details generated via a real-time pop-up message or email.

[1313] The terminal displays the received notification on the screen and prompts the user (employee) to take an appropriate break or refresh themselves.

[1314] 6. Administrator Alerts

[1315] The server analyzes the overall data and identifies employees or departments with particularly high stress or poor performance, and generates alerts for administrators based on the results of this analysis.

[1316] The server sends the generated alert to the administrator's terminal.

[1317] The device displays an alert on the administrator's PC or smartphone.

[1318] The user (administrator) checks the alert, schedules a meeting to take appropriate measures, and sends a company-wide email recommending a break.

[1319] Specific examples

[1320] Example 1: Email notification

[1321] Let's consider a case where Employee A uses a PC for long periods of time, and the results of a stress questionnaire indicate a high level of stress. Also, the emotion engine detects facial expressions that indicate anxiety or fatigue on Employee A.

[1322] The server analyzes employee A's data and determines whether he is experiencing excessive stress or fatigue.

[1323] Generate an action that recommends 10 minutes of eye exercises and creates an email with detailed instructions on how to do the exercises.

[1324] The device (employee A's email client) will automatically send an email and display a notification.

[1325] The user (Employee A) checks his email and performs eye exercises.

[1326] Example 2: Real-time notifications

[1327] Consider a case where the emotion engine detects that employee B has been working long hours in a row, and further detects fatigue and stress from employee B's facial expressions.

[1328] The server analyzes employee B's data and detects long working hours and high stress levels.

[1329] Generates actions that recommend a 15-minute break and a short walk.

[1330] The device (Employee B's PC) displays a real-time notification, encouraging the employee to "take a short walk."

[1331] The user (Employee B) follows the instructions and takes a short walk.

[1332] Example 3: Alerting the administrator

[1333] Consider a case where most employees in department X are in a state of high stress and the emotion engine detects facial expressions of anxiety and fatigue from multiple employees.

[1334] The server consolidates the data from Department X and determines that many employees are experiencing high levels of stress.

[1335] Generate an alert message for administrators: "Many employees in department X are experiencing high stress. Please recommend they take a break."

[1336] The device (administrator's PC or smartphone) will display a notification.

[1337] The user (administrator) checks the alert, schedules a meeting to take appropriate measures, and sends an email to the entire department recommending a break.

[1338] In this way, by combining this emotion engine, the system provides more precise break and refreshment methods that take into account the emotional state of each employee, helping to balance employee health with work efficiency.

[1339] The processing flow will be explained below.

[1340] Step 1:

[1341] Users (employees) use PCs and smartphones to carry out their work and periodically answer stress questionnaires while working.

[1342] Step 2:

[1343] The devices (employee PCs and smartphones) collect work data (PC operating time, work content, work location) and stress data (survey results). Collection is done automatically.

[1344] Step 3:

[1345] The emotion engine analyzes the user's facial expressions and voice through the device's camera and microphone to collect emotion data in real time, for example, tracking changes in the user's facial expressions through the camera and analyzing voice tone through the microphone.

[1346] Step 4:

[1347] The device periodically transmits collected work data, stress data, and emotion data to a server. The transmission is performed in the background and does not affect the user's work.

[1348] Step 5:

[1349] The server stores the received data in an analysis database, where data preprocessing (such as removing invalid data and outliers) is performed as necessary.

[1350] Step 6:

[1351] The server uses machine learning algorithms to assess each employee's fatigue level, stress level, and emotional state, combining historical data with real-time data for analysis.

[1352] Step 7:

[1353] Based on the evaluation results, the server generates optimal break times and methods of relaxation for each employee, including actions such as eye exercises, eating specific foods and drinks, or taking a short walk.

[1354] Step 8:

[1355] The server then sends the generated action details to the employee's device, and notifications are sent via real-time pop-up messages or emails.

[1356] Step 9:

[1357] The device will display the received notification on the screen, for example, a message such as "Do 10 minutes of eye exercises."

[1358] Step 10:

[1359] The user (employee) follows the notification and performs the suggested refreshment method, such as doing eye exercises or taking a short walk.

[1360] Step 11:

[1361] The server analyzes the overall data and identifies employees or departments that are particularly stressed or underperforming.

[1362] Step 12:

[1363] The server generates an alert message for the administrator, for example, "Many employees in department X are experiencing high stress. Please recommend they take a break."

[1364] Step 13:

[1365] The server sends an alert to the administrator's terminal, either via email or a pop-up message.

[1366] Step 14:

[1367] An alert will be displayed on the device (administrator's PC or smartphone).

[1368] Step 15:

[1369] The user (administrator) checks the alert and schedules a meeting to take appropriate measures or sends an email to all employees recommending they take a break.

[1370] Example 2

[1371] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1372] In today's work environment, employee fatigue and stress are increasing, resulting in a decline in labor productivity and work efficiency. Conventional systems primarily collect and analyze employee work data and stress data, but lack the ability to grasp employees' emotional states in real time or provide appropriate notifications to managers. As a result, they are unable to adequately suggest optimal break times and refreshment methods based on employees' conditions, limiting the effectiveness of improving labor productivity. A system that can solve these problems and improve employee health and work efficiency is needed.

[1373] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting employee work data, stress data, and emotional data; means for analyzing the collected data and evaluating the employee's fatigue, stress, and emotional state; means for proposing optimal break times and refreshment methods to the employee based on the evaluation results; means for notifying the employee of the suggestions to their terminal; and means for notifying the manager of employees and departments with high stress or low performance. This enables highly accurate fatigue and stress management that takes the employee's emotional state into consideration. Furthermore, real-time notifications and alerts to the manager enable prompt and appropriate responses, thereby maintaining employee health and improving work productivity.

[1374] "Business data" refers to data generated by employees during their work hours, including PC operating time, work content, and work location.

[1375] "Stress data" refers to data that indicates the level of stress felt by employees, and includes the results of stress questionnaires, etc.

[1376] "Emotional data" refers to data that indicates the emotional state of employees as analyzed from their facial expressions and voice, and is obtained through real-time facial and voice analysis.

[1377] An "emotion engine" is software or an algorithm that analyzes employees' emotional states from data obtained through devices such as cameras and microphones.

[1378] The "server" is a central processing unit that stores and analyzes collected data and provides optimal suggestions and notifications to employees and managers.

[1379] "Terminal" means a computing device used by an employee or administrator, including a PC or smartphone.

[1380] "Notifications" are information sent from the server to the terminal, and include suggestions for employees to take breaks or refresh themselves, and alerts to managers about high stress levels.

[1381] "Rest period" means a period of time designated for an employee to rest from work.

[1382] "Refreshment methods" are actions employees take to reduce stress and fatigue, including eye exercises, eating and drinking, and taking short walks.

[1383] A "database" is a digital storage system for systematically storing and managing business data, stress data, and emotional data collected by a server.

[1384] A "machine learning algorithm" is a mathematical model or calculation method used to analyze and evaluate employees' fatigue and stress levels based on collected data.

[1385] This system collects and analyzes employee work data, stress data, and emotional data, assesses employee fatigue and stress levels, and suggests optimal break times and ways to refresh. The system is comprised of the following main components:

[1386] server

[1387] Device (PC, smartphone, etc.)

[1388] Database

[1389] Emotion Engine

[1390] Data collection

[1391] Users (employees) use PCs or smartphones during work hours and periodically answer stress questionnaires. For example, employees answer a questionnaire every two hours during their eight-hour workday, rating their stress level on a five-point scale.

[1392] The device automatically collects work data (PC operating time, work content, work location) and stress data (survey results). For example, PC operating time and activity logs are periodically saved as log files. In addition, the device's camera and microphone are used to collect facial and voice data through an emotion engine. The emotion engine uses facial recognition software (e.g., OpenFace) and voice analysis tools to collect emotion data in real time.

[1393] Data transmission

[1394] The device sends the collected work data, stress data, and emotion data to the server at regular intervals (for example, every hour). Data is sent using a secure communication protocol such as HTTPS.

[1395] Data analysis

[1396] The server stores the received data in a database for analysis. For example, the data is stored systematically using an SQL database. The server then pre-processes the data, using principal component analysis (PCA) and data cleaning techniques to remove incorrect data and outliers.

[1397] The server uses machine learning algorithms (e.g., random forest, SVM) to assess each employee's fatigue level, stress level, and emotional state. It builds a predictive model based on past data history and real-time data to assess the employee's condition in real time.

[1398] Creating Actions

[1399] Based on the evaluation results, the server will generate optimal break times and methods for refreshing each employee, suggesting specific actions such as eye exercises, eating certain foods and drinks, or taking a short walk.

[1400] Notifications and Alerts

[1401] The server notifies the employee of the action details generated via a pop-up message or email.

[1402] The device will display the received notification on the screen and notify the user with an audio alert or vibration notification.

[1403] The user (employee) checks the notification and takes the suggested break or refreshment method.

[1404] Administrator Alerts

[1405] The server analyzes the overall data and identifies employees or departments with particularly high stress or poor performance. Based on the detected issues, it generates alert messages for administrators and sends them to their terminals.

[1406] The device displays an alert using an administrator application or email client.

[1407] The user (administrator) checks the alert, quickly schedules a meeting, and sends a company-wide email recommending a break.

[1408] Specific examples

[1409] Example 1: Email notification

[1410] Employee A uses a PC for long periods of time and indicates high stress in a stress questionnaire.

[1411] The server analyzes employee A's data and determines whether he is experiencing excessive stress or fatigue.

[1412] The server generates an action recommending 10 minutes of eye exercises and creates an email with detailed instructions.

[1413] The device (employee A's email client) will automatically send an email and display a notification.

[1414] The user (Employee A) checks his email and performs eye exercises.

[1415] Example 2: Real-time notifications

[1416] Employee B has been working long hours in a row and the emotion engine detects fatigue and high stress.

[1417] The server analyzes employee B's data and determines whether he is working long hours or experiencing high stress.

[1418] The server generates an action that recommends a 15-minute break and a short walk.

[1419] The device (Employee B's PC) displays a real-time notification, encouraging the employee to "take a short walk."

[1420] The user (Employee B) follows the instructions and takes a short walk.

[1421] Example 3: Alerting the administrator

[1422] A large proportion of employees in department X are under high stress, and the emotion engine detects expressions of anxiety and fatigue on multiple employees' faces.

[1423] The server consolidates the data from Department X and determines that many employees are experiencing high levels of stress.

[1424] The server generates an alert message for the administrator: "Many employees in department X are experiencing high stress. Please recommend they take a break."

[1425] The device (administrator's PC or smartphone) will display a notification.

[1426] The user (administrator) checks the alert, quickly schedules a meeting, and sends an email to the entire department recommending a break.

[1427] Prompt Sentence Examples

[1428] An example of a prompt to be input to the generative AI model is as follows:

[1429] "Describe a system that detects employee fatigue and stress and uses an emotion engine to suggest appropriate breaks and ways to refresh. Illustrate examples of email notifications for employees who have worked long hours, real-time notifications in natural language, and department-wide alerts for managers."

[1430] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1431] Step 1: Data collection

[1432] Users (employees) perform their work using PCs and smartphones.

[1433] The device automatically collects business data (PC operating time, work content, work location), for example, via the device's log file.

[1434] Users fill out a stress questionnaire periodically, for example, every two hours, by filling out a questionnaire form that appears on the screen.

[1435] The device uses a camera and microphone to collect the user's facial and voice data through the emotion engine. Specifically, the emotion engine acquires emotion data in real time using facial recognition software (e.g., OpenFace) and voice analysis tools.

[1436] Input: User's work data (PC operating time, work content, work location), stress questionnaire results, facial expression data, voice data.

[1437] Output: Collected work data, stress data, and emotion data.

[1438] Step 2: Send data

[1439] The terminal transmits the collected data to the server at regular intervals, for example, a schedule for transmitting data every hour is set.

[1440] Data is transmitted using secure communication protocols such as HTTPS.

[1441] Input: Collected work data, stress data, and emotion data.

[1442] Output: Work data, stress data, and emotion data sent to the server.

[1443] Step 3: Data analysis

[1444] The server stores the received data in a database for analysis, for example, by systematically storing the data using an SQL database.

[1445] The server pre-processes the data, using principal component analysis (PCA) and data cleaning techniques to remove incorrect data and outliers.

[1446] The server uses machine learning algorithms (e.g., random forest, SVM) to assess each employee's fatigue level, stress level, and emotional state. It builds and analyzes a predictive model based on past data history and real-time data.

[1447] Input: Work data, stress data, and emotion data sent to the server.

[1448] Output: Fatigue, stress, and emotional state assessment results.

[1449] Step 4: Creating Actions

[1450] The server generates optimal break times and refreshment methods for each employee based on the evaluation results.

[1451] Specifically, it generates actions such as eye exercises, eating specific foods and drinks, taking a short walk, etc. For example, if the user is highly fatigued, it will suggest "10 minutes of eye exercises recommended."

[1452] Input: Fatigue, stress, and emotional state assessment results.

[1453] Output: Generated break times and refresh methods.

[1454] Step 5: Notifications and Alerts

[1455] The server notifies the employee of the action details generated via a pop-up message or email.

[1456] The device will display the received notification on the screen and notify the user with an audio alert or vibration notification.

[1457] The user checks the notification content and takes the suggested break or refreshment method.

[1458] Input: Generated break times and refreshment methods.

[1459] Output: Notifications that appear on employee devices.

[1460] Step 6: Administrator alerts

[1461] The server analyzes the overall data and identifies employees or departments that are particularly stressed or underperforming.

[1462] An alert message for the administrator is generated based on the data and sent to the administrator's terminal.

[1463] The device displays an alert using an administrator application or email client.

[1464] The user (administrator) checks the alert, quickly schedules a meeting, and sends a company-wide email recommending a break.

[1465] Input: Overall data analysis results.

[1466] Output: An alert message for the administrator.

[1467] (Application example 2)

[1468] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1469] In today's work environment, it is common for employees to work long hours, which can easily lead to the accumulation of fatigue and stress. Therefore, managing employee health and maintaining and improving work efficiency are important issues. However, traditional methods make it difficult to effectively monitor individual employees' fatigue and stress levels in real time and suggest personalized break times and ways to refresh. This can lead to excessive employee stress, which can ultimately lead to health problems and reduced work efficiency.

[1470] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1471] In this invention, the server includes means for collecting employee work data and stress data, means for analyzing the collected data and evaluating the employee's fatigue and stress, means for collecting and analyzing emotional data in real time, means for evaluating the employee's emotional state based on the emotional data and using the evaluation results to generate personalized break times and relaxation methods, and means for notifying the employee's terminal of the suggestions. This makes it possible to provide highly accurate break time suggestions and relaxation methods tailored to the individual circumstances of each employee.

[1472] "Business data" refers to data generated when employees perform their work, and specifically includes information such as PC operating time, work content, and work location.

[1473] "Stress data" refers to data that indicates the stress state of employees, and specifically includes survey results and physiological indicators.

[1474] "Evaluation measures" are means for analyzing collected data and evaluating employee fatigue and stress.

[1475] The "suggestion means" is a means for generating optimal break times and methods of relaxation for employees based on the evaluation results and proposing these to employees.

[1476] "Terminal" refers to an information processing device used by an employee, and specifically includes PCs, smartphones, tablets, etc.

[1477] "Emotion data" is data that indicates the emotional state of an employee, and specifically includes the analysis results of facial expressions, voice, movements, etc.

[1478] "Emotional state" refers to an employee's current emotional state, such as happiness, anxiety, fatigue, etc.

[1479] "Personalization" means that it is individually tailored to each employee's characteristics and circumstances.

[1480] The "notification means" refers to a means for informing employees of the generated break times and refreshment methods, and specifically includes real-time pop-up messages, emails, etc.

[1481] "Real-time analysis" means analyzing data immediately, close to the moment it is generated.

[1482] This invention is a system that detects employee fatigue and stress, and uses emotion data to evaluate the employee's emotional state in real time, thereby providing more accurate break times and methods for refreshing. This invention is composed of the following main components: a server, a terminal, a database, and an emotion engine.

[1483] System Configuration

[1484] 1. Server

[1485] The server is responsible for the main calculations, collecting and analyzing work data, stress data, and emotion data, and also notifying each employee of the generated break times and how to refresh themselves.

[1486] 2. Terminal

[1487] The devices are information processing devices used by employees, such as PCs, smartphones, tablets, etc. The devices collect work data and stress data, and also use an emotion engine to collect emotion data in real time from cameras and microphones.

[1488] 3. Database

[1489] The database stores the collected work data, stress data, and emotion data, and the server uses this database for analysis.

[1490] 4. Emotion Engine

[1491] The emotion engine uses the device's camera and microphone to analyze employees' facial expressions and voices and assess their emotional state in real time.

[1492] Processing flow

[1493] 1. Data Collection

[1494] Employees use devices to carry out their work and periodically answer stress questionnaires. The emotion engine analyzes employees' facial expressions and voices via cameras and microphones to collect emotional data in real time.

[1495] 2. Data Transmission

[1496] The collected work data, stress data, and emotion data are transmitted to a server at regular intervals.

[1497] 3. Data analysis

[1498] The server stores the received data in a database and performs preprocessing. It uses machine learning algorithms to evaluate each employee's fatigue level, stress level, and emotional state. It then combines past data history with real-time data for analysis.

[1499] 4. Creating Actions

[1500] Based on the analysis results, the server generates optimal break times and methods for refreshing each employee, such as eye exercises, eating certain foods and drinks, or taking a short walk.

[1501] 5. Notification

[1502] The generated action details are sent to the employee's device via a real-time pop-up message or email.

[1503] Specific examples

[1504] Example 1: Email notification

[1505] Let's assume that employee A works long hours and the results of a stress questionnaire and emotional data indicate a high level of stress.

[1506] The server analyzes employee A's data, generates an action recommending 10 minutes of eye exercises, and sends the specific instructions via email.

[1507] The message reads, "Do eye exercises for 10 minutes."

[1508] Example 2: Real-time notifications

[1509] Consider a case where the server detects that employee B has been working long hours in a row, and furthermore, emotion data confirms that he or she is tired.

[1510] The server generates actions recommending a 15-minute break and a short walk, and displays real-time notifications on the device.

[1511] The message reads, "Take a short walk."

[1512] Example 3: Alerting the administrator

[1513] Imagine that the server detects that many employees in department X are in a state of high stress.

[1514] The server consolidates data from department X and alerts the administrator when stress levels are high.

[1515] The message read, "Employees in department X are under high stress. Please recommend a company-wide break."

[1516] As shown in these specific examples, by combining an emotion engine, the present invention provides more precise break and refreshment methods that take into account the emotional state of each employee, thereby helping employees achieve both health and work efficiency.

[1517] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1518] Step 1:

[1519] Data collection

[1520] The device collects work data (e.g., PC operating time, work content, and work location) generated by employees using their PCs or smartphones while performing their work. Employees also periodically answer stress questionnaires, and the results are collected as stress data. Furthermore, the emotion engine analyzes facial expressions and voices through the device's camera and microphone to collect emotion data in real time. The input data are work data, stress data, and emotion data. The output is a set of collected data.

[1521] Step 2:

[1522] Data transmission

[1523] The device periodically sends the work data, stress data, and emotion data collected in step 1 to the server. The input is the collected dataset. The data is packaged in JSON format and sent to the cloud server using an HTTP API. The output is a confirmation message indicating that the data was successfully sent to the server.

[1524] Step 3:

[1525] Data storage and preprocessing

[1526] The server stores the received data in a database. For example, MySQL or PostgreSQL is used as the database system. The received data is first preprocessed to remove invalid data and outliers. The input is the dataset sent to the server. Before storing it in the database, processing such as filling in missing data and standardizing the data format is performed. The output is a preprocessed, clean dataset.

[1527] Step 4:

[1528] Data analysis

[1529] The server runs machine learning algorithms to analyze the preprocessed data. For example, a generative AI model is used to assess emotional states. Analysis combines historical data with real-time data. The input is the preprocessed dataset. The machine learning algorithm assesses each employee's fatigue, stress, and emotional state. The output is the assessment of each employee's fatigue, stress, and emotional state.

[1530] Step 5:

[1531] Action Generation

[1532] Based on the evaluation results obtained in step 4, the server generates optimal break times and refreshment methods for each employee. Specifically, it suggests eye exercises, specific foods and drinks, short walks, etc. The input is the employee's evaluation results. The generative AI model generates options for breaks and refreshment methods and creates the necessary instructions. The output is personalized break and refreshment suggestions.

[1533] Step 6:

[1534] notification

[1535] The server notifies the employee's terminal of the generated action content. Notification formats include real-time pop-up messages and emails. The terminal receives the notification content and prompts the employee to take an appropriate break or refresh themselves. The input is the action proposal. The output is a notification to the employee's terminal.

[1536] Step 7:

[1537] Administrator Alerts

[1538] The server analyzes data from across departments and identifies employees and departments with high stress or low performance. Based on the results of this analysis, it generates an alert for the administrator. The alert is sent to the administrator's device, and the administrator takes appropriate measures based on the alert. The input is the evaluation results of employee data and department data. The output is the alert to the administrator and its contents.

[1539] The above are the specific processing steps of the program for the system that realizes the application example.

[1540] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1541] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1542] 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 the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1543] [Fourth embodiment]

[1544] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1545] 7, a 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.

[1546] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1547] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1548] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1549] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1550] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1551] The control object 443 includes a display device, LEDs in the eyes, and motors for driving 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 emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1552] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1553] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[1554] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1555] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1556] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1557] The present invention is a system that detects fatigue and stress in employees and suggests optimal break times and methods for refreshing. Specific embodiments of the system and their operation will be described below.

[1558] System configuration

[1559] The system consists of the following main components:

[1560] server

[1561] Device (PC, smartphone, etc.)

[1562] Database

[1563] Installation and Operation Overview

[1564] 1. Data Collection

[1565] Users (employees) perform their daily work on their PCs or smartphones, and the associated work data is automatically recorded. They also periodically answer a stress questionnaire.

[1566] The terminal collects work data (PC operating time, work content, work location, etc.) and stress data (survey results) and sends them to the server.

[1567] 2. Data analysis

[1568] The server stores the received business data and stress data in an analysis database and performs data preprocessing, which includes removing invalid data and outliers.

[1569] The server analyzes the collected data and assesses the employee's level of fatigue and stress using a machine learning model that combines the employee's past data history with real-time data.

[1570] 3. Creating Actions

[1571] Based on the analysis, the server generates optimal break times and methods of relaxation for each employee, which could include, for example, eye exercises, eating specific foods and drinks, or taking short walks.

[1572] 4. Notifications and Alerts

[1573] The server notifies the employee of the action details generated via email or real-time pop-up messages.

[1574] The terminal displays the received notification on the screen and prompts the user (employee) to take an appropriate break or refresh themselves.

[1575] 5. Administrator Alerts

[1576] The server consolidates data from across departments and identifies employees and departments with particularly high levels of stress and fatigue.

[1577] An alert is generated for the administrator, such as "Many employees in department X are experiencing high levels of stress," and sent to the administrator's device. The administrator can then take company-wide measures based on this information.

[1578] Specific examples

[1579] Example 1: Email notification

[1580] Consider the case where employee A uses a PC for long periods of time and the results of a stress questionnaire indicate a high level of stress.

[1581] The server analyzes employee A's data and determines whether he is under excessive stress.

[1582] Generate an action that recommends 10 minutes of eye exercises and creates an email with detailed instructions on how to do the exercises.

[1583] An email is automatically sent to the device (employee A's email client) and a notification is displayed.

[1584] The user (Employee A) checks his email and performs eye exercises.

[1585] Example 2: Real-time notifications

[1586] Consider the case where it is detected that employee B has been working long hours in a row.

[1587] The server analyzes employee B's data and detects that he has been working long hours.

[1588] Generates actions that recommend a 15-minute break and a short walk.

[1589] A real-time notification is displayed on the device (Employee B's PC) encouraging the employee to "take a short walk."

[1590] The user (Employee B) follows the instructions and takes a short walk.

[1591] Example 3: Alerting the administrator

[1592] Suppose data reveals that a large percentage of employees in department X are in a state of high stress.

[1593] The server consolidates the data from Department X and determines that many employees are experiencing high levels of stress.

[1594] Generate an alert message for administrators: "Many employees in department X are experiencing high stress. Please recommend they take a break."

[1595] Display a notification on the terminal (administrator's PC).

[1596] The user (administrator) checks the alert, schedules a meeting to take appropriate measures, and sends an email to the entire department recommending a break.

[1597] In this way, this system supports efficient work performance while maintaining employee health by proposing and notifying optimal break and refreshment methods based on each employee's working style and condition.

[1598] The processing flow will be explained below.

[1599] Step 1:

[1600] Users (employees) use PCs and smartphones to carry out their work and periodically answer stress questionnaires while working.

[1601] Step 2:

[1602] The devices (employee PCs and smartphones) collect work data (PC operating time, work content, work location) and stress data (survey results). Collection is done automatically.

[1603] Step 3:

[1604] The device periodically sends the collected data to the server in the background, without affecting the user's work.

[1605] Step 4:

[1606] The server stores the received data in an analysis database, where data preprocessing (removal of invalid data and outliers, etc.) is performed as necessary.

[1607] Step 5:

[1608] The server uses machine learning algorithms to analyze the data, assessing each employee's fatigue and stress levels, and combines past data history with real-time data for analysis.

[1609] Step 6:

[1610] Based on the evaluation results, the server generates optimal break times and methods of relaxation for each employee, including actions such as eye exercises, eating specific foods and drinks, or taking a short walk.

[1611] Step 7:

[1612] The server then sends the generated action details to the employee's device, and notifications are sent via real-time pop-up messages or emails.

[1613] Step 8:

[1614] The device will display the received notification on the screen, for example, a message such as "Do 10 minutes of eye exercises."

[1615] Step 9:

[1616] The user (employee) follows the notification and performs the suggested refreshment method, such as doing eye exercises or taking a short walk.

[1617] Step 10:

[1618] The server analyzes the overall data and identifies employees or departments with particularly high stress levels. Based on the results of this analysis, it generates alerts for administrators.

[1619] Step 11:

[1620] The server then sends an alert to the administrator's device, such as a message saying, "Many employees in department X are experiencing high stress. Please encourage them to take a break."

[1621] Step 12:

[1622] An alert will be displayed on the device (administrator's PC or smartphone).

[1623] Step 13:

[1624] The user (administrator) checks the alert and schedules a meeting to take appropriate measures or sends an email to all employees recommending they take a break.

[1625] Example 1

[1626] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1627] With conventional systems, it was difficult to properly assess employee fatigue and stress and suggest effective break times and ways to refresh. Furthermore, there was a lack of a mechanism to grasp the stress levels of not only individual employees but the entire department, and to provide appropriate alerts to managers. This could lead to inadequate health management for employees, leading to a decline in performance.

[1628] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1629] In this invention, the server includes means for collecting employee work data and stress data, means for preprocessing the collected data to remove invalid data and outliers, means for analyzing the preprocessed data and executing a machine learning model for assessing employee fatigue and stress, means for proposing optimal break times and relaxation methods to employees based on the assessment results, means for notifying the employees of the suggestions to their terminals, and means for integrating data from the entire department, identifying employees or departments with particularly high levels of fatigue or stress, and notifying a manager of an alert. This makes it possible to accurately monitor the health status of individual employees and propose effective relaxation methods, and by notifying a manager of the stress level of the entire department, it is possible to take prompt and appropriate measures.

[1630] "Business data" refers to all information related to an employee's work, such as the employee's PC operating time, work content, and work location.

[1631] "Stress data" refers to the results of stress questionnaires answered by employees and information regarding the psychological and physiological state of employees.

[1632] "Data preprocessing" refers to the process of removing invalid data and outliers from collected data.

[1633] A "machine learning model" refers to a collection of algorithms and mathematical methods used to assess an employee's level of fatigue or stress based on past data.

[1634] "Refreshment methods" are specific methods suggested to reduce employees' fatigue and stress, such as eye exercises or short walks.

[1635] "Notification" refers to the act of transmitting generated action details and alert information to an employee or administrator's device.

[1636] "Alert to managers" refers to the act of integrating data from across departments to identify employees or departments with high levels of fatigue or stress and issuing a warning to managers.

[1637] This invention relates to a system that detects employee fatigue and stress and suggests optimal break times and ways to refresh. This system is mainly composed of a server, terminals, and a database.

[1638] Hardware and software used

[1639] Server: A server with high-performance data processing capabilities (e.g., Apache HTTP Server, Nginx)

[1640] Device: General PC or smartphone (e.g. Windows PC, Mac, iPhone, Android device)

[1641] Database: A database that stores and manages large amounts of data (e.g., MySQL, PostgreSQL)

[1642] Machine learning models: The machine learning algorithms used to assess employee fatigue and stress (e.g., TensorFlow, scikit-learn)

[1643] Specific Embodiments of the System

[1644] 1. Data Collection

[1645] Users carry out their daily work on their PC or smartphone, and their work data is automatically recorded. They also periodically answer a stress questionnaire.

[1646] The terminal collects business data such as the user's PC operating time, work content, and work location, as well as the user's stress data (survey results), and sends this to the server.

[1647] 2. Data Preprocessing

[1648] The server stores the received business data and stress data in an analysis database.

[1649] The server performs preprocessing on the stored data, such as removing invalid data and outliers. For example, consecutive identical data and obviously unrealistic values ​​are filtered out.

[1650] 3. Data analysis

[1651] The server uses the pre-processed data to run machine learning models to assess employees' levels of fatigue and stress.

[1652] The server inputs past data history and real-time data to calculate each employee's fatigue and stress levels.

[1653] 4. Creating Actions

[1654] Based on the evaluation results, the server will suggest optimal break times and ways to refresh employees.

[1655] Suggestions may include eye exercises, eating specific foods and drinks, or taking a short walk.

[1656] 5. Notifications and Alerts

[1657] The server notifies the specified device (PC or smartphone) of the generated action content.

[1658] The terminal displays the received notification on the screen in real time and prompts the user to perform the refresh method.

[1659] 6. Alert the administrator

[1660] The server aggregates data from across the department and detects high stress levels among specific employees or departments.

[1661] The server sends an alert to the administrator's device, such as "Many employees in department X are feeling high levels of stress."

[1662] Specific examples

[1663] 1. Example 1: Email notification

[1664] If employee A uses a PC for a long time and the results of a stress questionnaire indicate a high level of stress, the server will analyze the data and determine whether the stress is excessive.

[1665] The server generates an action that recommends 10 minutes of eye exercises and creates an email with detailed instructions on how to do it.

[1666] An email is automatically sent to the device (employee A's email client) and a notification is displayed.

[1667] The user (Employee A) checks his email and performs eye exercises.

[1668] 2. Example 2: Real-time notifications

[1669] If employee B works long hours consecutively, the server analyzes employee B's data and detects that long working hours have continued.

[1670] The server generates an action that recommends a 15-minute break and a short walk.

[1671] A real-time notification is displayed on the device (Employee B's PC) encouraging the employee to "take a short walk."

[1672] The user (Employee B) follows the instructions and takes a short walk.

[1673] 3. Example 3: Alerting the administrator

[1674] If most of the employees in department X are in a high stress state, the server consolidates the data for department X and determines that a large number of employees are experiencing high stress.

[1675] The server displays an alert on the administrator's device saying, "Many employees in department X are feeling high stress. Please recommend they take a break."

[1676] The user (administrator) checks the alert, schedules a meeting to take appropriate measures, and sends an email to the entire department recommending a break.

[1677] As described above, this system supports efficient work performance while maintaining employee health by proposing and notifying employees of optimal break and refreshment methods based on their individual work style and condition.

[1678] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1679] Step 1:

[1680] Data collection

[1681] Users carry out their daily work on their PC or smartphone, and their work data is automatically recorded. In addition, they are required to answer a stress questionnaire periodically.

[1682] Input: Work data such as user PC operating time, work content, and work location, as well as stress questionnaire results

[1683] The device collects this work data and stress data and sends it to the server using an HTTP request.

[1684] Output: Raw work and stress data sent to the server

[1685] Specific behavior:

[1686] The terminal records the PC operation time from when the user starts work at 9:00 AM until 6:00 PM. The terminal also collects the results of a stress questionnaire conducted at 1:00 PM (e.g., stress level 7 / 10) and sends them to the server.

[1687] Step 2:

[1688] Data Preprocessing

[1689] The server stores the received business data and stress data in an analysis database.

[1690] Input: Raw data received by the server

[1691] Perform data preprocessing to remove invalid data and outliers, for example, filtering out repeated identical data or unrealistic values.

[1692] Output: Preprocessed and clean data

[1693] Specific behavior:

[1694] The server stores the received data in a database and removes records with PC operating time of more than 24 hours as outliers.

[1695] Step 3:

[1696] Data analysis

[1697] The server uses the pre-processed data to run machine learning models to assess employees' levels of fatigue and stress.

[1698] Input: Preprocessed operational and stress data

[1699] Use machine learning models to assess employee stress levels based on historical and real-time data.

[1700] Output: Fatigue and stress levels for each employee

[1701] Specific behavior:

[1702] The server analyzes Alice's work data and stress questionnaire results from the past month and determines that her current stress level is 8 / 10.

[1703] Step 4:

[1704] Creating Actions

[1705] Based on the evaluation results, the server will suggest optimal break times and ways to refresh employees.

[1706] Input: Fatigue and stress levels for each employee

[1707] Generate optimal refreshment methods (e.g., eye exercises, eating certain foods and drinks, taking short walks).

[1708] Output: Refresh method suggestions

[1709] Specific behavior:

[1710] The server generates an action that recommends 10 minutes of eye exercises and creates data containing detailed instructions on how to do it.

[1711] Step 5:

[1712] Notifications and Alerts

[1713] The server notifies the employee's terminal of the generated action content.

[1714] Input: Refresh method proposal

[1715] The terminal displays the received notification on the screen and prompts the user to take action.

[1716] Output: Real-time notification messages

[1717] Specific behavior:

[1718] The server sends a pop-up message to Alice's PC saying, "Do eye exercises for 10 minutes," and the device immediately displays the message.

[1719] Step 6:

[1720] Administrator Alert

[1721] The server aggregates data from across the department and detects high fatigue or stress levels in specific employees or departments.

[1722] Input: Department-wide data

[1723] Alerts administrators to high stress situations.

[1724] Output: Alert message to administrator

[1725] Specific behavior:

[1726] The server detects that many employees in Department X have stress levels of 8 / 10 or higher and displays an alert on the administrator's PC saying, "Many employees in Department X are experiencing high levels of stress. Please recommend that they take a break."

[1727] (Application example 1)

[1728] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1729] The problem with employees and drivers is that fatigue caused by long working hours and stress leads to reduced productivity and health problems. The present invention aims to solve these problems and realize a healthy and efficient working environment.

[1730] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1731] In this invention, the server includes means for collecting employee work data and stress data, means for analyzing the collected data and evaluating the employee's fatigue and stress, means for proposing optimal rest periods and refreshment methods for the employee based on the evaluation results, and means for notifying the employee's terminal of the suggestions, means for collecting driver driving data and stress data, means for analyzing the collected data and evaluating the driver's fatigue and stress, means for proposing optimal rest periods and refreshment methods for the driver based on the evaluation results, and means for notifying the driver's terminal of the suggestions. This makes it possible to monitor the health status of employees and drivers in real time and suggest appropriate rest periods and refreshment methods, thereby improving work efficiency and maintaining health.

[1732] "Employee" refers to a person who belongs to a company or organization and performs work for that company or organization.

[1733] "Driver" means a person who drives a vehicle.

[1734] "Business data" refers to data generated or acquired by employees during work hours, and specifically includes PC operating time, work content, work location, etc.

[1735] "Stress data" refers to data that measures the stress levels of employees and drivers, and specifically includes the results of stress questionnaires and heart rates.

[1736] "Means of collecting data" refers to devices and software systems used to acquire and store various data on employees and drivers.

[1737] "Means for analyzing data" refers to software or algorithms used to analyze collected data and assess fatigue and stress levels among employees and drivers.

[1738] "Means for suggesting rest times and refreshment methods" refers to a system for recommending optimal rest and refreshment activities based on the results of data analysis.

[1739] "Means of notification" refers to devices or software that transmit suggested break times and refreshment methods to employees' or drivers' devices.

[1740] "Terminal" refers to a device used by employees or drivers to receive information, and specifically includes smartphones and in-vehicle displays.

[1741] This invention is a system that collects work data and stress data of employees and drivers, analyzes and evaluates the data, and proposes optimal rest times and methods for refreshing. Specific embodiments of the system and their operation are described below.

[1742] System Components

[1743] The system consists of the following main components:

[1744] server

[1745] Terminals (smartphones, in-car displays)

[1746] Database

[1747] Data collection

[1748] The server collects work data and stress data from smartphones and in-car displays. Work data includes driving speed, frequency of brake and accelerator operation, and driving time. Stress data includes the results of a simple stress questionnaire and heart rate. The collected data is stored in Firebase Firestore in real time.

[1749] Data analysis

[1750] The server stores the collected work data and stress data in an analysis database and performs data preprocessing, which involves removing invalid data and outliers. TensorFlow.js is used for analysis, and a machine learning model that combines past data history and real-time data is used. This allows the system to evaluate the fatigue and stress levels of employees and drivers.

[1751] Creating Actions

[1752] Based on the analysis results, the server generates optimal break times and methods of relaxation for each employee and driver. For example, it may suggest eye exercises, specific foods and drinks, a short walk, or a short meditation session. These suggestions are selected based on the most appropriate one for each situation.

[1753] Notifications and Alerts

[1754] The server then sends the generated action details to the employee or driver's device, which then displays the notification as a real-time pop-up message on the employee's smartphone or in-car display. Additionally, if a particularly high-stress state is detected, an alert will be sent.

[1755] Specific examples

[1756] Example 1: Real-time notifications for drivers

[1757] Consider a case where a driver has been working for long periods of time. The server analyzes the driver's driving data and stress data and detects that the driver has been working for long periods of time. The server generates an action recommending a 15-minute break and a short walk, and displays a notification such as "Please take a short walk" on the in-vehicle display.

[1758] Example 2: Break notification on smartphone

[1759] Consider a case where an employee uses a PC for long periods of time and the results of a stress questionnaire indicate high stress. The server analyzes the employee's work data and stress data to determine whether the employee is under excessive stress. It then generates an action recommending 10 minutes of eye exercises and sends a notification to the employee's smartphone.

[1760] Prompt Sentence Examples

[1761] "Please tell me the best time to take a break and refresh yourself while driving today. We will use the following data: acceleration data, heart rate, and driving time."

[1762] This system monitors the health status of employees and drivers in real time and suggests appropriate breaks and refreshments, thereby improving work efficiency and maintaining health.

[1763] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1764] Step 1: Data collection

[1765] The device (smartphone or in-car display) collects the driver's or employee's work data (driving speed, frequency of brake and accelerator operation, driving time, PC operating time, work content, work location, etc.) and stress data (heart rate, results of stress questionnaire) in real time.

[1766] Input: Sensor data, survey results

[1767] Output: Collected work data and stress data

[1768] Specific operation: Data is collected using smartphone sensors (e.g., acceleration sensor, heart rate sensor) and a simple stress questionnaire provided within the app. The in-car display collects vehicle driving information.

[1769] Step 2: Send data

[1770] The terminal transmits the collected data to the server in real time.

[1771] Input: Collected work data and stress data

[1772] Output: Data sent to the server

[1773] Specific operation: The application on the device has the function of periodically sending collected data to Firebase Firestore.

[1774] Step 3: Data Preprocessing

[1775] The server stores the received data in an analysis database and performs data preprocessing.

[1776] Input: Received work data and stress data

[1777] Output: Preprocessed data

[1778] Specific operation: Removes invalid data and outliers from the data stored in the database, and performs imputation and normalization as necessary.

[1779] Step 4: Data analysis

[1780] The server uses the preprocessed data to analyze employee and driver fatigue and stress using machine learning models.

[1781] Input: Preprocessed data

[1782] Output: Fatigue and stress assessment results

[1783] Specific operation: Using TensorFlow.js, a machine learning model is applied to the collected data to assess fatigue and stress in real time.

[1784] Step 5: Action Creation

[1785] The server generates optimal break times and refreshment methods based on the evaluation results.

[1786] Input: Fatigue and stress assessment results

[1787] Output: Suggestions for optimal break times and ways to refresh

[1788] Specific actions: Action generation algorithms create specific suggestions such as eye exercises, eating specific foods or drinks, taking a short walk, or meditating.

[1789] Step 6: Notifications and Alerts

[1790] The server notifies the generated action details to the employee or driver's device.

[1791] Input: Suggestions for optimal break times and ways to refresh

[1792] Output: Notifications and alerts

[1793] What it does: It uses Firebase Cloud Messaging to send real-time popup messages to smartphones and in-car displays, alerting drivers when particularly stressful situations are detected.

[1794] Step 7: Rest and Refresh

[1795] Users (employees or drivers) follow the suggestions displayed on the terminal to take breaks and refresh themselves.

[1796] Input: Notifications and Alerts

[1797] Output: Maintaining health and improving work efficiency

[1798] Specific actions: Do eye exercises, drink something, take a short walk or meditate.

[1799] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1800] The present invention is a system that detects employee fatigue and stress and proposes more accurate break times and methods for refreshing by combining it with an emotion engine that recognizes the user's emotions. Specific embodiments of the system and their operation are described below.

[1801] System configuration

[1802] The system consists of the following main components:

[1803] server

[1804] Device (PC, smartphone, etc.)

[1805] Database

[1806] Emotion Engine

[1807] Installation and Operation Overview

[1808] 1. Data Collection

[1809] Users (employees) use PCs and smartphones to carry out their work and periodically answer stress questionnaires while working.

[1810] The terminal collects work data (PC operating time, work content, work location) and stress data (survey results).

[1811] The emotion engine analyzes the user's facial expressions and voice through the device's camera and microphone, collecting emotional data in real time.

[1812] 2. Data Transmission

[1813] The terminal transmits the collected work data, stress data, and emotion data to the server at regular intervals.

[1814] 3. Data analysis

[1815] The server stores the received data in an analytical database and performs preprocessing on the data, which includes removing invalid data and outliers.

[1816] The server uses machine learning algorithms to assess each employee's fatigue level, stress level, and emotional state, combining historical data with real-time data for analysis.

[1817] 4. Creating Actions

[1818] Based on the analysis results, the server generates optimal break times and methods of relaxation for each employee, such as eye exercises, eating specific foods and drinks, or taking a short walk.

[1819] 5. Notifications and Alerts

[1820] The server then notifies the employee of the action details generated via a real-time pop-up message or email.

[1821] The terminal displays the received notification on the screen and prompts the user (employee) to take an appropriate break or refresh themselves.

[1822] 6. Administrator Alerts

[1823] The server analyzes the overall data and identifies employees or departments with particularly high stress or poor performance, and generates alerts for administrators based on the results of this analysis.

[1824] The server sends the generated alert to the administrator's terminal.

[1825] The device displays an alert on the administrator's PC or smartphone.

[1826] The user (administrator) checks the alert, schedules a meeting to take appropriate measures, and sends a company-wide email recommending a break.

[1827] Specific examples

[1828] Example 1: Email notification

[1829] Let's consider a case where Employee A uses a PC for long periods of time, and the results of a stress questionnaire indicate a high level of stress. Also, the emotion engine detects facial expressions that indicate anxiety or fatigue on Employee A.

[1830] The server analyzes employee A's data and determines whether he is experiencing excessive stress or fatigue.

[1831] Generate an action that recommends 10 minutes of eye exercises and creates an email with detailed instructions on how to do the exercises.

[1832] The device (employee A's email client) will automatically send an email and display a notification.

[1833] The user (Employee A) checks his email and performs eye exercises.

[1834] Example 2: Real-time notifications

[1835] Consider a case where the emotion engine detects that employee B has been working long hours in a row, and further detects fatigue and stress from employee B's facial expressions.

[1836] The server analyzes employee B's data and detects long working hours and high stress levels.

[1837] Generates actions that recommend a 15-minute break and a short walk.

[1838] The device (Employee B's PC) displays a real-time notification, encouraging the employee to "take a short walk."

[1839] The user (Employee B) follows the instructions and takes a short walk.

[1840] Example 3: Alerting the administrator

[1841] Consider a case where most employees in department X are in a state of high stress and the emotion engine detects facial expressions of anxiety and fatigue from multiple employees.

[1842] The server consolidates the data from Department X and determines that many employees are experiencing high levels of stress.

[1843] Generate an alert message for administrators: "Many employees in department X are experiencing high stress. Please recommend they take a break."

[1844] The device (administrator's PC or smartphone) will display a notification.

[1845] The user (administrator) checks the alert, schedules a meeting to take appropriate measures, and sends an email to the entire department recommending a break.

[1846] In this way, by combining this emotion engine, the system provides more precise break and refreshment methods that take into account the emotional state of each employee, helping to balance employee health with work efficiency.

[1847] The processing flow will be explained below.

[1848] Step 1:

[1849] Users (employees) use PCs and smartphones to carry out their work and periodically answer stress questionnaires while working.

[1850] Step 2:

[1851] The devices (employee PCs and smartphones) collect work data (PC operating time, work content, work location) and stress data (survey results). Collection is done automatically.

[1852] Step 3:

[1853] The emotion engine analyzes the user's facial expressions and voice through the device's camera and microphone to collect emotion data in real time, for example, tracking changes in the user's facial expressions through the camera and analyzing voice tone through the microphone.

[1854] Step 4:

[1855] The device periodically transmits collected work data, stress data, and emotion data to a server. The transmission is performed in the background and does not affect the user's work.

[1856] Step 5:

[1857] The server stores the received data in an analysis database, where data preprocessing (such as removing invalid data and outliers) is performed as necessary.

[1858] Step 6:

[1859] The server uses machine learning algorithms to assess each employee's fatigue level, stress level, and emotional state, combining historical data with real-time data for analysis.

[1860] Step 7:

[1861] Based on the evaluation results, the server generates optimal break times and methods of relaxation for each employee, including actions such as eye exercises, eating specific foods and drinks, or taking a short walk.

[1862] Step 8:

[1863] The server then sends the generated action details to the employee's device, and notifications are sent via real-time pop-up messages or emails.

[1864] Step 9:

[1865] The device will display the received notification on the screen, for example, a message such as "Do 10 minutes of eye exercises."

[1866] Step 10:

[1867] The user (employee) follows the notification and performs the suggested refreshment method, such as doing eye exercises or taking a short walk.

[1868] Step 11:

[1869] The server analyzes the overall data and identifies employees or departments that are particularly stressed or underperforming.

[1870] Step 12:

[1871] The server generates an alert message for the administrator, for example, "Many employees in department X are experiencing high stress. Please recommend they take a break."

[1872] Step 13:

[1873] The server sends an alert to the administrator's terminal, either via email or a pop-up message.

[1874] Step 14:

[1875] An alert will be displayed on the device (administrator's PC or smartphone).

[1876] Step 15:

[1877] The user (administrator) checks the alert and schedules a meeting to take appropriate measures or sends an email to all employees recommending they take a break.

[1878] Example 2

[1879] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1880] In today's work environment, employee fatigue and stress are increasing, resulting in a decline in labor productivity and work efficiency. Conventional systems primarily collect and analyze employee work data and stress data, but lack the ability to grasp employees' emotional states in real time or provide appropriate notifications to managers. As a result, they are unable to adequately suggest optimal break times and refreshment methods based on employees' conditions, limiting the effectiveness of improving labor productivity. A system that can solve these problems and improve employee health and work efficiency is needed.

[1881] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting employee work data, stress data, and emotional data; means for analyzing the collected data and evaluating the employee's fatigue, stress, and emotional state; means for proposing optimal break times and refreshment methods to the employee based on the evaluation results; means for notifying the employee of the suggestions to their terminal; and means for notifying the manager of employees and departments with high stress or low performance. This enables highly accurate fatigue and stress management that takes the employee's emotional state into consideration. Furthermore, real-time notifications and alerts to the manager enable prompt and appropriate responses, thereby maintaining employee health and improving work productivity.

[1882] "Business data" refers to data generated by employees during their work hours, including PC operating time, work content, and work location.

[1883] "Stress data" refers to data that indicates the level of stress felt by employees, and includes the results of stress questionnaires, etc.

[1884] "Emotional data" refers to data that indicates the emotional state of employees as analyzed from their facial expressions and voice, and is obtained through real-time facial and voice analysis.

[1885] An "emotion engine" is software or an algorithm that analyzes employees' emotional states from data obtained through devices such as cameras and microphones.

[1886] The "server" is a central processing unit that stores and analyzes collected data and provides optimal suggestions and notifications to employees and managers.

[1887] "Terminal" means a computing device used by an employee or administrator, including a PC or smartphone.

[1888] "Notifications" are information sent from the server to the terminal, and include suggestions for employees to take breaks or refresh themselves, and alerts to managers about high stress levels.

[1889] "Rest period" means a period of time designated for an employee to rest from work.

[1890] "Refreshment methods" are actions employees take to reduce stress and fatigue, including eye exercises, eating and drinking, and taking short walks.

[1891] A "database" is a digital storage system for systematically storing and managing business data, stress data, and emotional data collected by a server.

[1892] A "machine learning algorithm" is a mathematical model or calculation method used to analyze and evaluate employees' fatigue and stress levels based on collected data.

[1893] This system collects and analyzes employee work data, stress data, and emotional data, assesses employee fatigue and stress levels, and suggests optimal break times and ways to refresh. The system is comprised of the following main components:

[1894] server

[1895] Device (PC, smartphone, etc.)

[1896] Database

[1897] Emotion Engine

[1898] Data collection

[1899] Users (employees) use PCs or smartphones during work hours and periodically answer stress questionnaires. For example, employees answer a questionnaire every two hours during their eight-hour workday, rating their stress level on a five-point scale.

[1900] The device automatically collects work data (PC operating time, work content, work location) and stress data (survey results). For example, PC operating time and activity logs are periodically saved as log files. In addition, the device's camera and microphone are used to collect facial and voice data through an emotion engine. The emotion engine uses facial recognition software (e.g., OpenFace) and voice analysis tools to collect emotion data in real time.

[1901] Data transmission

[1902] The device sends the collected work data, stress data, and emotion data to the server at regular intervals (for example, every hour). Data is sent using a secure communication protocol such as HTTPS.

[1903] Data analysis

[1904] The server stores the received data in a database for analysis. For example, the data is stored systematically using an SQL database. The server then pre-processes the data, using principal component analysis (PCA) and data cleaning techniques to remove incorrect data and outliers.

[1905] The server uses machine learning algorithms (e.g., random forest, SVM) to assess each employee's fatigue level, stress level, and emotional state. It builds a predictive model based on past data history and real-time data to assess the employee's condition in real time.

[1906] Creating Actions

[1907] Based on the evaluation results, the server will generate optimal break times and methods for refreshing each employee, suggesting specific actions such as eye exercises, eating certain foods and drinks, or taking a short walk.

[1908] Notifications and Alerts

[1909] The server notifies the employee of the action details generated via a pop-up message or email.

[1910] The device will display the received notification on the screen and notify the user with an audio alert or vibration notification.

[1911] The user (employee) checks the notification and takes the suggested break or refreshment method.

[1912] Administrator Alerts

[1913] The server analyzes the overall data and identifies employees or departments with particularly high stress or poor performance. Based on the detected issues, it generates alert messages for administrators and sends them to their terminals.

[1914] The device displays an alert using an administrator application or email client.

[1915] The user (administrator) checks the alert, quickly schedules a meeting, and sends a company-wide email recommending a break.

[1916] Specific examples

[1917] Example 1: Email notification

[1918] Employee A uses a PC for long periods of time and indicates high stress in a stress questionnaire.

[1919] The server analyzes employee A's data and determines whether he is experiencing excessive stress or fatigue.

[1920] The server generates an action recommending 10 minutes of eye exercises and creates an email with detailed instructions.

[1921] The device (employee A's email client) will automatically send an email and display a notification.

[1922] The user (Employee A) checks his email and performs eye exercises.

[1923] Example 2: Real-time notifications

[1924] Employee B has been working long hours in a row and the emotion engine detects fatigue and high stress.

[1925] The server analyzes employee B's data and determines whether he is working long hours or experiencing high stress.

[1926] The server generates an action that recommends a 15-minute break and a short walk.

[1927] The device (Employee B's PC) displays a real-time notification, encouraging the employee to "take a short walk."

[1928] The user (Employee B) follows the instructions and takes a short walk.

[1929] Example 3: Alerting the administrator

[1930] A large proportion of employees in department X are under high stress, and the emotion engine detects expressions of anxiety and fatigue on multiple employees' faces.

[1931] The server consolidates the data from Department X and determines that many employees are experiencing high levels of stress.

[1932] The server generates an alert message for the administrator: "Many employees in department X are experiencing high stress. Please recommend they take a break."

[1933] The device (administrator's PC or smartphone) will display a notification.

[1934] The user (administrator) checks the alert, quickly schedules a meeting, and sends an email to the entire department recommending a break.

[1935] Prompt Sentence Examples

[1936] An example of a prompt to be input to the generative AI model is as follows:

[1937] "Describe a system that detects employee fatigue and stress and uses an emotion engine to suggest appropriate breaks and ways to refresh. Illustrate examples of email notifications for employees who have worked long hours, real-time notifications in natural language, and department-wide alerts for managers."

[1938] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1939] Step 1: Data collection

[1940] Users (employees) perform their work using PCs and smartphones.

[1941] The device automatically collects business data (PC operating time, work content, work location), for example, via the device's log file.

[1942] Users fill out a stress questionnaire periodically, for example, every two hours, by filling out a questionnaire form that appears on the screen.

[1943] The device uses a camera and microphone to collect the user's facial and voice data through the emotion engine. Specifically, the emotion engine acquires emotion data in real time using facial recognition software (e.g., OpenFace) and voice analysis tools.

[1944] Input: User's work data (PC operating time, work content, work location), stress questionnaire results, facial expression data, voice data.

[1945] Output: Collected work data, stress data, and emotion data.

[1946] Step 2: Send data

[1947] The terminal transmits the collected data to the server at regular intervals, for example, a schedule for transmitting data every hour is set.

[1948] Data is transmitted using secure communication protocols such as HTTPS.

[1949] Input: Collected work data, stress data, and emotion data.

[1950] Output: Work data, stress data, and emotion data sent to the server.

[1951] Step 3: Data analysis

[1952] The server stores the received data in a database for analysis, for example, by systematically storing the data using an SQL database.

[1953] The server pre-processes the data, using principal component analysis (PCA) and data cleaning techniques to remove incorrect data and outliers.

[1954] The server uses machine learning algorithms (e.g., random forest, SVM) to assess each employee's fatigue level, stress level, and emotional state. It builds and analyzes a predictive model based on past data history and real-time data.

[1955] Input: Work data, stress data, and emotion data sent to the server.

[1956] Output: Fatigue, stress, and emotional state assessment results.

[1957] Step 4: Creating Actions

[1958] The server generates optimal break times and refreshment methods for each employee based on the evaluation results.

[1959] Specifically, it generates actions such as eye exercises, eating specific foods and drinks, taking a short walk, etc. For example, if the user is highly fatigued, it will suggest "10 minutes of eye exercises recommended."

[1960] Input: Fatigue, stress, and emotional state assessment results.

[1961] Output: Generated break times and refresh methods.

[1962] Step 5: Notifications and Alerts

[1963] The server notifies the employee of the action details generated via a pop-up message or email.

[1964] The device will display the received notification on the screen and notify the user with an audio alert or vibration notification.

[1965] The user checks the notification content and takes the suggested break or refreshment method.

[1966] Input: Generated break times and refreshment methods.

[1967] Output: Notifications that appear on employee devices.

[1968] Step 6: Administrator alerts

[1969] The server analyzes the overall data and identifies employees or departments that are particularly stressed or underperforming.

[1970] An alert message for the administrator is generated based on the data and sent to the administrator's terminal.

[1971] The device displays an alert using an administrator application or email client.

[1972] The user (administrator) checks the alert, quickly schedules a meeting, and sends a company-wide email recommending a break.

[1973] Input: Overall data analysis results.

[1974] Output: An alert message for the administrator.

[1975] (Application example 2)

[1976] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1977] In today's work environment, it is common for employees to work long hours, which can easily lead to the accumulation of fatigue and stress. Therefore, managing employee health and maintaining and improving work efficiency are important issues. However, traditional methods make it difficult to effectively monitor individual employees' fatigue and stress levels in real time and suggest personalized break times and ways to refresh. This can lead to excessive employee stress, which can ultimately lead to health problems and reduced work efficiency.

[1978] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1979] In this invention, the server includes means for collecting employee work data and stress data, means for analyzing the collected data and evaluating the employee's fatigue and stress, means for collecting and analyzing emotional data in real time, means for evaluating the employee's emotional state based on the emotional data and using the evaluation results to generate personalized break times and relaxation methods, and means for notifying the employee's terminal of the suggestions. This makes it possible to provide highly accurate break time suggestions and relaxation methods tailored to the individual circumstances of each employee.

[1980] "Business data" refers to data generated when employees perform their work, and specifically includes information such as PC operating time, work content, and work location.

[1981] "Stress data" refers to data that indicates the stress state of employees, and specifically includes survey results and physiological indicators.

[1982] "Evaluation measures" are means for analyzing collected data and evaluating employee fatigue and stress.

[1983] The "suggestion means" is a means for generating optimal break times and methods of relaxation for employees based on the evaluation results and proposing these to employees.

[1984] "Terminal" refers to an information processing device used by an employee, and specifically includes PCs, smartphones, tablets, etc.

[1985] "Emotion data" is data that indicates the emotional state of an employee, and specifically includes the analysis results of facial expressions, voice, movements, etc.

[1986] "Emotional state" refers to an employee's current emotional state, such as happiness, anxiety, fatigue, etc.

[1987] "Personalization" means that it is individually tailored to each employee's characteristics and circumstances.

[1988] The "notification means" refers to a means for informing employees of the generated break times and refreshment methods, and specifically includes real-time pop-up messages, emails, etc.

[1989] "Real-time analysis" means analyzing data immediately, close to the moment it is generated.

[1990] This invention is a system that detects employee fatigue and stress, and uses emotion data to evaluate the employee's emotional state in real time, thereby providing more accurate break times and methods for refreshing. This invention is composed of the following main components: a server, a terminal, a database, and an emotion engine.

[1991] System Configuration

[1992] 1. Server

[1993] The server is responsible for the main calculations, collecting and analyzing work data, stress data, and emotion data, and also notifying each employee of the generated break times and how to refresh themselves.

[1994] 2. Terminal

[1995] The devices are information processing devices used by employees, such as PCs, smartphones, tablets, etc. The devices collect work data and stress data, and also use an emotion engine to collect emotion data in real time from cameras and microphones.

[1996] 3. Database

[1997] The database stores the collected work data, stress data, and emotion data, and the server uses this database for analysis.

[1998] 4. Emotion Engine

[1999] The emotion engine uses the device's camera and microphone to analyze employees' facial expressions and voices and assess their emotional state in real time.

[2000] Processing flow

[2001] 1. Data Collection

[2002] Employees use devices to carry out their work and periodically answer stress questionnaires. The emotion engine analyzes employees' facial expressions and voices via cameras and microphones to collect emotional data in real time.

[2003] 2. Data Transmission

[2004] The collected work data, stress data, and emotion data are transmitted to a server at regular intervals.

[2005] 3. Data analysis

[2006] The server stores the received data in a database and performs preprocessing. It uses machine learning algorithms to evaluate each employee's fatigue level, stress level, and emotional state. It then combines past data history with real-time data for analysis.

[2007] 4. Creating Actions

[2008] Based on the analysis results, the server generates optimal break times and methods for refreshing each employee, such as eye exercises, eating certain foods and drinks, or taking a short walk.

[2009] 5. Notification

[2010] The generated action details are sent to the employee's device via a real-time pop-up message or email.

[2011] Specific examples

[2012] Example 1: Email notification

[2013] Let's assume that employee A works long hours and the results of a stress questionnaire and emotional data indicate a high level of stress.

[2014] The server analyzes employee A's data, generates an action recommending 10 minutes of eye exercises, and sends the specific instructions via email.

[2015] The message reads, "Do eye exercises for 10 minutes."

[2016] Example 2: Real-time notifications

[2017] Consider a case where the server detects that employee B has been working long hours in a row, and furthermore, emotion data confirms that he or she is tired.

[2018] The server generates actions recommending a 15-minute break and a short walk, and displays real-time notifications on the device.

[2019] The message reads, "Take a short walk."

[2020] Example 3: Alerting the administrator

[2021] Imagine that the server detects that many employees in department X are in a state of high stress.

[2022] The server consolidates data from department X and alerts the administrator when stress levels are high.

[2023] The message read, "Employees in department X are under high stress. Please recommend a company-wide break."

[2024] As shown in these specific examples, by combining an emotion engine, the present invention provides more precise break and refreshment methods that take into account the emotional state of each employee, thereby helping employees achieve both health and work efficiency.

[2025] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[2026] Step 1:

[2027] Data collection

[2028] The device collects work data (e.g., PC operating time, work content, and work location) generated by employees using their PCs or smartphones while performing their work. Employees also periodically answer stress questionnaires, and the results are collected as stress data. Furthermore, the emotion engine analyzes facial expressions and voices through the device's camera and microphone to collect emotion data in real time. The input data are work data, stress data, and emotion data. The output is a set of collected data.

[2029] Step 2:

[2030] Data transmission

[2031] The device periodically sends the work data, stress data, and emotion data collected in step 1 to the server. The input is the collected dataset. The data is packaged in JSON format and sent to the cloud server using an HTTP API. The output is a confirmation message indicating that the data was successfully sent to the server.

[2032] Step 3:

[2033] Data storage and preprocessing

[2034] The server stores the received data in a database. For example, MySQL or PostgreSQL is used as the database system. The received data is first preprocessed to remove invalid data and outliers. The input is the dataset sent to the server. Before storing it in the database, processing such as filling in missing data and standardizing the data format is performed. The output is a preprocessed, clean dataset.

[2035] Step 4:

[2036] Data analysis

[2037] The server runs machine learning algorithms to analyze the preprocessed data. For example, a generative AI model is used to assess emotional states. Analysis combines historical data with real-time data. The input is the preprocessed dataset. The machine learning algorithm assesses each employee's fatigue, stress, and emotional state. The output is the assessment of each employee's fatigue, stress, and emotional state.

[2038] Step 5:

[2039] Action Generation

[2040] Based on the evaluation results obtained in step 4, the server generates optimal break times and refreshment methods for each employee. Specifically, it suggests eye exercises, specific foods and drinks, short walks, etc. The input is the employee's evaluation results. The generative AI model generates options for breaks and refreshment methods and creates the necessary instructions. The output is personalized break and refreshment suggestions.

[2041] Step 6:

[2042] notification

[2043] The server notifies the employee's terminal of the generated action content. Notification formats include real-time pop-up messages and emails. The terminal receives the notification content and prompts the employee to take an appropriate break or refresh themselves. The input is the action proposal. The output is a notification to the employee's terminal.

[2044] Step 7:

[2045] Administrator Alerts

[2046] The server analyzes data from across departments and identifies employees and departments with high stress or low performance. Based on the results of this analysis, it generates an alert for the administrator. The alert is sent to the administrator's device, and the administrator takes appropriate measures based on the alert. The input is the evaluation results of employee data and department data. The output is the alert to the administrator and its contents.

[2047] The above are the specific processing steps of the program for the system that realizes the application example.

[2048] 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 control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[2049] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[2050] 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 the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[2051] The emotion identification model 59 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 an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[2052] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[2053] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[2054] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[2055] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[2056] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs 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 a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[2057] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[2058] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[2059] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[2060] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[2061] 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.

[2062] It is not necessary to store all 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 all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[2063] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[2064] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with 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). Also, the hardware resource that executes the specific processing may be a single processor.

[2065] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[2066] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[2067] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[2068] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[2069] The following is further disclosed regarding the above embodiment.

[2070] (Claim 1)

[2071] A means of collecting employee work data and stress data;

[2072] A means for analyzing the collected data and assessing employee fatigue and stress;

[2073] A means for proposing optimal break times and refreshment methods to employees based on the evaluation results;

[2074] means for notifying said proposal to an employee's terminal;

[2075] A system including:

[2076] (Claim 2)

[2077] 2. The system according to claim 1, wherein said evaluation means comprises means for analyzing data on employees' PC operating time, work content, workplace, and stress questionnaire results.

[2078] (Claim 3)

[2079] 10. The system of claim 1, wherein the suggestion means includes suggestions for eye exercises, recommendations for eating certain foods and drinks, and suggestions for taking short walks.

[2080] "Example 1"

[2081] (Claim 1)

[2082] A means of collecting employee work data and stress data;

[2083] means for pre-processing the collected data to remove incorrect data and outliers;

[2084] means for analyzing the pre-processed data and running a machine learning model to assess employee fatigue and stress;

[2085] A means for proposing optimal break times and refreshment methods to employees based on the evaluation results;

[2086] means for notifying said proposal to an employee's terminal;

[2087] A system that integrates data from across departments, identifies employees or departments with particularly high levels of fatigue or stress, and includes a means of sending alerts to managers.

[2088] (Claim 2)

[2089] 2. The system according to claim 1, wherein said evaluation means comprises means for analyzing data on employees' PC operating time, work content, workplace, and stress questionnaire results.

[2090] (Claim 3)

[2091] 10. The system of claim 1, wherein the suggestion means includes suggestions for eye exercises, recommendations for eating certain foods and drinks, and suggestions for taking short walks.

[2092] "Application Example 1"

[2093] (Claim 1)

[2094] A means of collecting employee work data and stress data;

[2095] A means for analyzing the collected data and assessing employee fatigue and stress;

[2096] A means for proposing optimal break times and refreshment methods to employees based on the evaluation results;

[2097] means for notifying said proposal to an employee's terminal;

[2098] A means for collecting driving data and stress data of a driver;

[2099] means for analyzing the collected data and assessing driver fatigue and stress;

[2100] A means for proposing optimal rest times and refreshment methods to the driver based on the evaluation results;

[2101] means for notifying the driver's terminal of the proposal;

[2102] A system including:

[2103] (Claim 2)

[2104] 2. The system according to claim 1, wherein said evaluation means comprises means for analyzing data on employees' PC operating time, work content, workplace, and stress questionnaire results.

[2105] (Claim 3)

[2106] 10. The system of claim 1, wherein the suggestion means includes suggestions for eye exercises, recommendations for eating certain foods and drinks, and suggestions for taking short walks.

[2107] "Example 2: Combining Emotion Engines"

[2108] (Claim 1)

[2109] A means for collecting employee work data, stress data and emotion data;

[2110] a means for analyzing the collected data to assess employee fatigue, stress, and emotional state;

[2111] A means for proposing optimal break times and refreshment methods to employees based on the evaluation results;

[2112] means for notifying said proposal to an employee's terminal;

[2113] A means to notify managers of high-stress and low-performing employees and departments;

[2114] A system including:

[2115] (Claim 2)

[2116] 2. The system according to claim 1, wherein the evaluation means comprises means for analyzing data on the employee's computer operating time, work content, work location, and stress questionnaire results, as well as facial expressions and voice analysis using an emotion engine.

[2117] (Claim 3)

[2118] 10. The system of claim 1, wherein the suggestion means includes suggestions for eye exercises, recommendations for eating certain foods and drinks, suggestions for short walks, and real-time pop-up messages and email notifications.

[2119] "Application example 2 when combining emotion engines"

[2120] (Claim 1)

[2121] A means of collecting employee work data and stress data;

[2122] A means for analyzing the collected data and assessing employee fatigue and stress;

[2123] A means for proposing optimal break times and refreshment methods to employees based on the evaluation results;

[2124] means for notifying said proposal to an employee's terminal;

[2125] means for collecting emotion data using a camera or microphone of the device and analyzing it in real time;

[2126] a means for evaluating the employee's emotional state based on the emotional data and using the evaluation results to generate personalized break times and refreshment methods;

[2127] A system including:

[2128] (Claim 2)

[2129] The system according to claim 1, characterized in that the evaluation means has a means for analyzing data on employees' PC operating time, work content, work location, and stress questionnaire results, and further combines and analyzes the emotional data.

[2130] (Claim 3)

[2131] The system described in claim 1, characterized in that the suggestion means, in addition to suggesting break times and ways to refresh, also suggests taking a short break, taking a walk, or consuming specific foods and drinks, providing employees with specific measures to reduce stress. [Explanation of symbols]

[2132] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of collecting employee work data and stress data; A means for analyzing the collected data and assessing employee fatigue and stress; A means for proposing optimal break times and refreshment methods to employees based on the evaluation results; means for notifying said proposal to an employee's terminal; A system including:

2. 2. The system according to claim 1, wherein said evaluation means comprises means for analyzing data on employees' PC operating time, work content, workplace, and stress questionnaire results.

3. The system of claim 1 , wherein the suggestion means includes suggestions for eye exercises, recommendations for eating certain foods and drinks, and suggestions for taking short walks.

Images