System

Abstract

A system is provided.SOLUTION: A system for monitoring a health condition of an employee, comprising: means for collecting weight data, diet data, and sleep data obtained from a data collection device; means for transmitting the data collected from the data collection device to a server; means for analyzing the data stored in the server by a generative model and calculating a fatigue degree score; and means for generating and notifying a proposal for vacation acquisition or work adjustment based on the fatigue degree score.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 work environment, employees are at increased risk of damaging their physical and mental health due to excessive workloads. In particular, in workplaces where long working hours and working on holidays are the norm, employee fatigue accumulates, making it more likely that problems such as poor health and burnout will occur. There is also concern that fatigue and stress that employees themselves are not aware of are often overlooked, delaying appropriate measures. Given this background, there is a need for a system that objectively assesses employees' fatigue levels and encourages them to take appropriate leave and adjust their work schedules. [Means for solving the problem]

[0005] The present invention provides a system for monitoring employee health, including: means for collecting weight data, dietary data, and sleep data from a data collection device; means for transmitting the data collected from the data collection device to a server; means for analyzing the data stored on the server using a generative model to calculate a fatigue score; and means for generating and notifying suggestions for taking vacation or adjusting work schedules based on the fatigue score. Furthermore, the data collection device includes a smartwatch, and also includes means for integrating calendar meeting data and reflecting it in the fatigue score. This system objectively evaluates the fatigue level of each employee and promotes appropriate measures, thereby maintaining the physical and mental health of employees.

[0006] "Data collection device" refers to a device that includes electronic devices and sensors for collecting weight data, dietary data, and sleep data.

[0007] A "generative model" refers to an algorithm or machine learning model that analyzes collected data and calculates a specific evaluation indicator (e.g., fatigue score).

[0008] "Fatigue score" refers to a numerical indicator that indicates the fatigue state of an individual employee, calculated based on weight data, dietary data, sleep data, and work-related information (e.g., time spent attending meetings).

[0009] "Notification" refers to the information and communication means for sending suggestions generated based on the analysis results to employees and managers.

[0010] "Server" refers to a computer system for storing, analyzing, and reporting data.

[0011] "Meeting data" refers to information about the duration and frequency of meetings within an employee's work schedule.

[0012] "Health status" refers to the physiological and psychological state of an employee, which is a comprehensive assessment of their weight, diet, sleep quality, and workload.

[0013] The "suggestion" for "taking vacation" refers to recommending that employees take vacation to reduce their workload based on their fatigue score. [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 system of the present invention is designed to monitor employee health status and promote appropriate leave taking and work adjustments. This system includes a data collection device, a server, a generative model, and a notification means. The following describes in detail how this system is implemented.

[0036] System Components and Operation

[0037] 1. Data Collection Equipment

[0038] User: Each employee wears a smartwatch, which collects weight, diet, and sleep data.

[0039] Device: The data collected by the smartwatch is automatically sent to employees' smartphones or tablets. Employees can also manually enter meal data using a dedicated app.

[0040] 2. Data transmission and storage

[0041] Device: At a set time each day, all collected data is sent to the server. The data is encrypted and transmitted to protect the privacy of the data.

[0042] Server: The server associates the received data with each employee's ID and stores it in a database, allowing all of each employee's weight, diet, and sleep data to be managed centrally.

[0043] 3. Data Analysis

[0044] Server: The server periodically extracts the stored data and analyzes it according to a generative model, which is designed using machine learning algorithms to calculate a fatigue score by taking into account weight fluctuations, dietary balance, sleep quality, and meeting participation time.

[0045] Generative model: Meeting data is taken from each employee's calendar information and added to the analysis. This meeting data is important for assessing how much time employees spend in meetings.

[0046] 4. Fatigue assessment and suggestions

[0047] Server: Evaluates the fatigue level of each employee based on the fatigue score calculated by the generative model. If the fatigue score exceeds a certain threshold, it generates suggestions for taking time off or adjusting work schedules.

[0048] Notification method: The server notifies the generated proposal to the employee and manager's devices. For example, a notification such as "We recommend you take a vacation this Friday" is sent to the employee's smartphone. Also, a report is sent to the manager saying, "Employee A is highly fatigued and we recommend that he take a weekend vacation."

[0049] Specific examples

[0050] Daily flow and data processing example

[0051] 7:00 AM - Weight data collection

[0052] User: After waking up, an employee steps on a scale linked to a smartwatch to measure their weight.

[0053] Device: Weight data is automatically recorded on your smartphone.

[0054] 13:00 noon - Collection of dietary data

[0055] User: After employees have lunch, they enter their meal details using a dedicated app.

[0056] Device: The entered meal data is saved on your smartphone.

[0057] 10:00 PM - Sleep data collection

[0058] User: Employees start sleep tracking on their smartwatch before going to bed.

[0059] Device: The smartwatch records your sleep data and syncs it to your smartphone the next morning.

[0060] 1:00 the next day - Data transmission and storage

[0061] Device: The smartphone sends the collected data to the server daily.

[0062] Server: The received data is linked to each employee's ID and stored in a database.

[0063] 3:00 the next day - Data analysis

[0064] Server: Extracts the stored data and calculates the fatigue score using a generative model.

[0065] 9:00 the next day - Suggestions and notifications

[0066] Server: Generates suggestions based on fatigue scores and sends notifications such as "Take time off recommended" to employees and managers.

[0067] In this way, a system can be created that supports the physical and mental health of employees by continuously and in detail monitoring their health status and recommending time off or work adjustments at the appropriate time.

[0068] The processing flow will be explained below.

[0069] Step 1: Data collection

[0070] User: Wears the smartwatch, weighs himself on a scale, manually enters his food intake into the app, and starts sleep tracking before going to bed.

[0071] Device: The smartwatch records weight, food, and sleep data, which is automatically synced to the user's smartphone.

[0072] Step 2: Send data

[0073] Device: At the end of each day, collected weight, food, and sleep data is sent to a server. The data is encrypted to protect privacy.

[0074] Step 3: Save data

[0075] Server: The received data is linked to each user's ID and stored in a database. The stored data includes date, weight, dietary details, and sleep information.

[0076] Step 4: Data Preprocessing

[0077] Server: Periodically extracts the stored data and converts it into the format required for analysis, for example by aggregating daily data into weekly data.

[0078] Step 5: Analysis with generative models

[0079] Server: Data extracted from the database is fed into a generative model to comprehensively analyze sleep quality, dietary balance, weight fluctuations, meeting attendance times, and more.

[0080] Step 6: Calculating your fatigue score

[0081] Server: The generative model uses the data to calculate a fatigue score for each user, which serves as an indicator of the user's health status.

[0082] Step 7: Proposal Generation

[0083] Server: Generates suggestions for taking time off or adjusting work load based on the calculated fatigue score. Specifically, it recommends taking time off if the fatigue score is high, and suggests redistributing tasks if the workload is high.

[0084] Step 8: Sending notifications

[0085] Server: Notifies the user and manager of the proposed schedule. For example, a notification such as "We recommend you take vacation next Friday" is sent to the user's smartphone. In addition, a report is sent to the manager stating, "User A is experiencing high levels of fatigue, so please adjust his or her work schedule."

[0086] Step 9: Gather feedback

[0087] User: Acts on the suggestions and provides feedback on the results in a dedicated app. For example, if a user takes a vacation, the app records the user's physical condition and mood for that day.

[0088] Terminal: Collects user feedback data and reflects it in the next analysis process.

[0089] Through these steps, a system can be created that can maintain the physical and mental health of employees by continuously monitoring their health status and recommending time off or work adjustments at the appropriate time.

[0090] Example 1

[0091] 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."

[0092] In modern companies, continuously monitoring employee health and encouraging appropriate leave and work adjustments is a challenging issue. This issue directly impacts employee productivity and well-being, so it must be resolved quickly. Furthermore, traditional health monitoring systems often have low data collection and analysis efficiency, and lack the ability to provide personalized recommendations based on individual employee conditions.

[0093] 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.

[0094] In this invention, the server includes means for collecting weight data, dietary data, and sleep data obtained from a data collection device, means for encrypting the data collected from the data collection device and transmitting it to the server, means for analyzing the data stored in the server using a generative model to calculate a fatigue score, means for generating and notifying suggestions for taking vacation or adjusting work schedules based on the fatigue score, means for the server to periodically extract and analyze data, and means for the terminal to receive and display suggestions from the server to the user. This enables detailed monitoring of employee health conditions and makes it possible to make appropriate suggestions for taking vacation or adjusting work schedules based on individual circumstances.

[0095] "Data collection device" refers to equipment used to collect weight data, dietary data, and sleep data.

[0096] "Weight data" refers to information about employees' weight, and is primarily numerical data measured using devices such as smartwatches and scales.

[0097] "Dietary data" refers to information about employees' daily dietary habits, including calories and nutrients, which is collected through a dedicated app.

[0098] "Sleep data" refers to information about employees' sleep patterns and quality, primarily tracked by devices such as smartwatches.

[0099] A "server" is a computer system for storing and analyzing collected data.

[0100] "Encryption" is the technique of converting data into a special format to protect its privacy and security.

[0101] A "generative model" is a program that uses machine learning algorithms to analyze data and generate predictions and suggestions.

[0102] The "fatigue score" is an indicator of an employee's level of fatigue, calculated by analyzing weight data, dietary data, sleep data, etc.

[0103] "Suggestions" refer to recommendations to employees to take time off or adjust their work schedules based on their fatigue scores.

[0104] "Notification" is the act of sending information such as suggestions or warnings to employees and managers.

[0105] "Meeting data" refers to information about meetings listed on employees' calendars, including participation time and frequency.

[0106] "Terminal" refers to a mobile information terminal such as a smartphone or tablet, which is a device that collects, transmits, and receives notifications about data.

[0107] This invention is a system that monitors the health status of employees and encourages them to take appropriate leave and adjust their work schedules. The invention is implemented using a data collection device, a server, a generative model, a terminal, and a notification means.

[0108] Data collection equipment

[0109] User: Each employee wears a smartwatch that collects weight, diet, and sleep data.

[0110] Device: Data collected by the smartwatch is automatically sent to employees' smartphones or tablets. Employees can also manually enter meal data using a dedicated app.

[0111] Hardware: Smartwatches used include Apple Watch, Fitbit, and Garmin.

[0112] Software: A dedicated app (such as MyFitnessPal) is used to input dietary data.

[0113] Data transmission and storage

[0114] Device: The smartphone sends all collected data to the server at a set time each day. The data is encrypted and transmitted to protect privacy. This encryption is done using AES-256.

[0115] Server: The server associates the received data with each employee's ID and stores it in a database using MySQL or PostgreSQL.

[0116] Data analysis

[0117] Server: The server periodically extracts the stored data and analyzes it according to the generative model, which is designed using a machine learning algorithm and implemented in TensorFlow or PyTorch.

[0118] Generative model: Meeting data is taken from each employee's calendar information and added to the analysis. Meeting data is important for assessing how much time an employee spends in meetings.

[0119] Fatigue assessment and suggestions

[0120] Server: Evaluates the fatigue level of each employee based on the fatigue score calculated by the generative model. If the fatigue score exceeds a certain threshold, it generates suggestions for taking time off or adjusting work schedules.

[0121] Notification method: The server notifies the generated proposal to the employee and manager's devices. For example, a notification saying "We recommend you take a vacation this Friday" is sent to the employee's smartphone. Also, a report saying "Employee A is highly fatigued and we recommend that he / she take a weekend vacation" is sent to the manager.

[0122] Specific examples

[0123] Daily flow and data processing example

[0124] 7:00 AM - Weight data collection

[0125] User: After waking up, an employee steps on a scale linked to a smartwatch to measure their weight.

[0126] Device: Weight data is automatically recorded on your smartphone.

[0127] 13:00 noon - Collection of dietary data

[0128] User: After employees have lunch, they enter their meal details using a dedicated app.

[0129] Device: The entered meal data is saved on your smartphone.

[0130] 10:00 PM - Sleep data collection

[0131] User: Employees start sleep tracking on their smartwatch before going to bed.

[0132] Device: The smartwatch records your sleep data and syncs it to your smartphone the next morning.

[0133] 1:00 the next day - Data transmission and storage

[0134] Device: The smartphone sends the collected data to the server daily.

[0135] Server: The received data is linked to each employee's ID and stored in a database.

[0136] 3:00 the next day - Data analysis

[0137] Server: Extracts the stored data and calculates the fatigue score using a generative model.

[0138] 9:00 the next day - Suggestions and notifications

[0139] Server: Generates suggestions based on fatigue scores and sends notifications such as "Take time off recommended" to employees and managers.

[0140] An example of a prompt sentence is, "After lunch, please enter your meal data in the dedicated app. Then, based on the fatigue score you submit, we will notify you of suggestions for taking time off."

[0141] This invention supports the physical and mental health of employees by continuously and in detail monitoring their health status and recommending time off or work adjustments at the appropriate time.

[0142] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0143] Step 1: Data collection

[0144] Subject: User

[0145] Specific operations: The user steps on a scale connected to a smartwatch to measure their weight. After lunch, they manually enter their meal details using a dedicated app. Before going to bed, they start sleep tracking on the smartwatch.

[0146] Input: Weight data measured by a scale, food data entered into a dedicated app, and sleep data tracked by a smartwatch.

[0147] Output: The respective data is recorded on the smartwatch and smartphone.

[0148] Step 2: Send data

[0149] Subject: Device

[0150] How it works: The smartwatch sends the collected data to a smartphone via Bluetooth or Wi-Fi, and the smartphone encrypts and sends the data to a server daily.

[0151] Input: Weight data, food data, and sleep data sent from the smartwatch.

[0152] Output: The encrypted data is sent from the smartphone to the server.

[0153] Step 3: Receiving and storing data

[0154] Subject: Server

[0155] Specific operation: The server receives the encrypted data sent from the smartphone, verifies that the data format is correct, and then associates it with each employee's ID and stores it in a database.

[0156] Input: Encrypted weight data, diet data, sleep data, and employee ID information.

[0157] Output: Data associated with each employee's ID is saved in the database.

[0158] Step 4: Data extraction and analysis

[0159] Subject: Server

[0160] Specific operation: The server periodically extracts weight, diet, and sleep data for each employee from the database. The extracted data is passed to the generative model for analysis.

[0161] Input: Weight data, dietary data, and sleep data stored in a database.

[0162] Output: Fatigue score as the analysis result.

[0163] Step 5: Integrating Meeting Data

[0164] Subject: Generative Model

[0165] What it does: The generative model retrieves meeting data from an employee's calendar information and adds it to the fatigue score analysis.

[0166] Input: Employee weight data, diet data, sleep data, and calendar meeting data.

[0167] Output: A calculated fatigue score based on the combined data.

[0168] Step 6: Fatigue assessment and recommendations

[0169] Subject: Server

[0170] Specific operation: Evaluate each employee's fatigue level based on the fatigue score calculated by the generative model. If the fatigue score exceeds a certain threshold, generate suggestions for taking time off or adjusting work schedules.

[0171] Input: Fatigue score calculated by the generative model.

[0172] Output: Suggestions for taking leave or adjusting work schedules.

[0173] Step 7: Proposal Notification

[0174] Subject: Server

[0175] Specific operation: The server notifies the employee and manager of the proposal, including details of taking leave and adjusting work schedules.

[0176] Input: Generated leave and work adjustment proposals.

[0177] Output: Proposals sent as push notifications and emails to employee and manager devices.

[0178] In this way, a system can be created that continuously and in detail monitors employees' health status and makes timely recommendations for leave and work adjustments.

[0179] (Application example 1)

[0180] 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."

[0181] Conventional health monitoring systems have difficulty accurately assessing employee fatigue levels due to insufficient management of employee physical condition. Furthermore, relying solely on fixed data collection devices has the drawback of being unable to collect real-time health data on-site or quickly propose appropriate work adjustments. Accumulating worker fatigue, particularly in factories, can lead to reduced productivity and potentially adversely affect safety.

[0182] 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.

[0183] In this invention, the server includes means for collecting weight data, dietary data, and sleep data obtained from a data collection device, means for transmitting the data collected from the data collection device to the server, means for analyzing the data stored in the server using a generative model to calculate a fatigue score, means for generating and notifying suggestions for taking time off or adjusting work schedules based on the fatigue score, and means for collecting and transmitting additional health data obtained from a patrolling mobile robot. This allows for more detailed and real-time monitoring of employee health conditions, enabling appropriate and prompt suggestions for taking time off or adjusting work schedules.

[0184] A "data collection device" is a device worn by an employee to collect weight data, dietary data, sleep data, and the like.

[0185] A "smartwatch" is a type of data collection device that is worn on an employee's wrist and collects various types of biometric data.

[0186] The "mobile robot" is a robot that patrols the factory and collects health data from workers' smartwatches.

[0187] The "server" is a device that collects and stores various data, and is a central processing unit that calculates fatigue scores and generates suggestions using generative models.

[0188] A "generative model" is a machine learning algorithm used to analyze collected data and calculate an employee's fatigue score.

[0189] The "fatigue score" is a value indicating an employee's level of fatigue calculated by the generative model based on weight data, dietary data, sleep data, meeting data, etc.

[0190] "Suggestions for taking vacation or adjusting work schedules" are notifications that recommend taking vacation or adjusting work schedules to maintain employees' health based on their fatigue score.

[0191] The present invention is a system that monitors the health status of employees and encourages them to take appropriate vacations and adjust their work schedules. This system includes a data collection device, a mobile robot, a server, a generative model, and a notification means. The program processing of this system is described in detail below.

[0192] System components and operation description

[0193] 1. Data Collection Equipment

[0194] User: Employees wear smartwatches that collect weight, diet, and sleep data.

[0195] Device: The data collected by the smartwatch is automatically sent to employees' smartphones or tablets. Employees can also manually enter meal data using a dedicated app.

[0196] 2. Data transmission and storage

[0197] Device: All collected data is sent to the server on a daily basis. The data is encrypted and transmitted to protect the privacy of the data.

[0198] Server: The server associates the received data with each employee's ID and stores it in a database, allowing all of each employee's weight, diet, and sleep data to be managed centrally.

[0199] 3. Data Analysis with Generative Models

[0200] Server: The server periodically extracts the stored data and analyzes it according to a generative model, which is designed using machine learning algorithms to calculate a fatigue score by taking into account weight fluctuations, dietary balance, sleep quality, and meeting participation time.

[0201] Generative model: Data analysis also includes meeting data obtained from calendar information to more precisely assess employee fatigue levels.

[0202] 4. Fatigue assessment and suggestions

[0203] Server: Evaluates the fatigue level of each employee based on the fatigue score calculated by the generative model. If the fatigue score exceeds a certain threshold, it generates suggestions for taking time off or adjusting work schedules.

[0204] Notification method: The server notifies the generated suggestions to the employees' and managers' devices. For example, a notification such as "We recommend you take a vacation this Friday" is sent to the employee's smartphone. Also, a report is sent to the manager saying, "Employee A's fatigue level is high, so we recommend that he or she take a weekend vacation."

[0205] 5. Additional data collection by mobile robots

[0206] Robot: The robot roams the factory floor, collecting real-time health data from workers' smartwatches and transmitting it to a server using its own Wi-Fi module.

[0207] Hardware and software used

[0208] Hardware

[0209] Smartwatches: Apple Watch, Fitbit, etc.

[0210] Mobile robots: such as Fetch Robotics' Fetch Mobile Manipulator.

[0211] Server: Linux-based dedicated server.

[0212] software

[0213] Generative model: Python machine learning library (TensorFlow or PyTorch)

[0214] Database: MySQL, PostgreSQL, etc.

[0215] Notification method: Voice synthesis technology such as Google Text-to-Speech.

[0216] Specific examples

[0217] Example prompts for generative AI models

[0218] Create a generative model that calculates fatigue levels based on workers' health data and suggests appropriate breaks and work adjustments.

[0219] Data points:

[0220] Weight data: 70 kg

[0221] Dietary data: Calories 2000 kcal

[0222] Sleep data: 6 hours

[0223] prompt:

[0224] 1. How to calculate worker fatigue?

[0225] 2. How do you assess your daily workload?

[0226] 3. How do we create specific proposals for breaks and work adjustments?

[0227] This system allows for detailed and real-time monitoring of employee health conditions, enabling appropriate and prompt leave proposals and work adjustments, contributing to improved productivity throughout the factory and ensuring employee safety.

[0228] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0229] Step 1:

[0230] The user wears a smartwatch to collect weight, diet, and sleep data. The smartwatch collects this data in real time and automatically transmits it to a smartphone. The input is biometric data, and the output is data stored on the smartphone.

[0231] Step 2:

[0232] The smartphone, which is the terminal, periodically sends the collected data to the server on a daily basis. The data is encrypted to protect privacy. The input is the data stored on the smartphone, and the output is the encrypted data sent to the server.

[0233] Step 3:

[0234] The server links the received data to each employee's ID and stores it in a database. This allows the server to centrally manage weight data, dietary data, and sleep data. The input is encrypted health data, and the output is organized data stored in the database.

[0235] Step 4:

[0236] The server periodically extracts data from the database and analyzes it using a generative model. The generative model, which uses a machine learning algorithm, analyzes weight fluctuations, dietary balance, sleep quality, and meeting participation time to calculate a fatigue score. The input is each employee's health data and meeting data, and the output is a fatigue score.

[0237] Step 5:

[0238] Based on the fatigue score calculated by the generative model, the server evaluates the employee's fatigue state. If the fatigue score exceeds a certain threshold, the server generates suggestions for taking time off or adjusting work schedules. The input is the fatigue score, and the output is the suggestion.

[0239] Step 6:

[0240] As a notification method, the server notifies the generated suggestions to the devices of employees and managers. For example, a notification such as "We recommend you take vacation this Friday" is sent to an employee's smartphone. The input is the suggestion content, and the output is the notification to employees and managers.

[0241] Step 7:

[0242] The mobile robot patrols the factory and collects additional health data from the smartwatch. The robot transmits this data to a server via its WiFi module. The input is the real-time health data of employees, and the output is the data transmitted to the server.

[0243] Step 8:

[0244] The server receives additional health data sent from the mobile robot and stores it in a database. It also updates the fatigue score in real time by reflecting the additional data in the generative model. The input is the health data from the mobile robot, and the output is the updated data stored in the database.

[0245] 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.

[0246] The system of the present invention is designed to monitor employee health status and promote appropriate leave taking and work adjustments. This system includes a data collection device, a server, a generative model, a notification means, and an emotion engine. The following describes in detail how this system is implemented.

[0247] System Components and Operation

[0248] 1. Data Collection Equipment

[0249] User: Each employee wears a smartwatch, which collects weight, diet, and sleep data.

[0250] Device: The data collected by the smartwatch is automatically sent to employees' smartphones or tablets. Employees can also manually enter meal data using a dedicated app.

[0251] 2. Data transmission and storage

[0252] Device: At a set time each day, all collected data is sent to the server. The data is encrypted and transmitted to protect the privacy of the data.

[0253] Server: The server associates the received data with each employee's ID and stores it in a database, allowing all of each employee's weight, diet, and sleep data to be managed centrally.

[0254] 3. Data Analysis

[0255] Server: The server periodically extracts the stored data and analyzes it according to the generative model. The generative model is designed using a machine learning algorithm and calculates a fatigue score by taking into account weight fluctuations, dietary balance, sleep quality, and meeting participation time. Emotion data from the emotion engine is also analyzed.

[0256] Generative model: Meeting data is taken from each employee's calendar information and added to the analysis. This meeting data is important for assessing how much time employees spend in meetings.

[0257] 4. Emotion Engine and Emotion Evaluation

[0258] User: Emotional data is collected periodically via smartphone or PC using facial recognition cameras and voice recognition.

[0259] Emotion engine: Recognizes the user's emotions using voice and facial expression analysis, converts them into numerical values, and stores them.

[0260] Server: Emotion data collected by the emotion engine is stored in a database and reflected in the calculation of fatigue scores.

[0261] 5. Fatigue assessment and suggestions

[0262] Server: Evaluates the fatigue level of each employee based on the fatigue score calculated by the generative model. If the fatigue score exceeds a certain threshold, it generates suggestions for taking time off or adjusting work schedules.

[0263] Notification method: The server notifies the generated proposal to the employee and manager's devices. For example, a notification such as "We recommend you take a vacation this Friday" is sent to the employee's smartphone. Also, a report is sent to the manager saying, "Employee A is highly fatigued and we recommend that he take a weekend vacation."

[0264] Specific examples

[0265] Daily flow and data processing example

[0266] 7:00 AM - Weight data collection

[0267] User: After waking up, an employee steps on a scale linked to a smartwatch to measure their weight.

[0268] Device: Weight data is automatically recorded on your smartphone.

[0269] 13:00 noon - Collection of dietary data

[0270] User: After employees have lunch, they enter their meal details using a dedicated app.

[0271] Device: The entered meal data is saved on your smartphone.

[0272] 15:00 noon - Emotion data collection

[0273] User: Employees use facial recognition cameras to collect emotional data.

[0274] Emotion engine: Analyzes emotional data, converts the user's emotional state into a numerical value, and sends it to the server.

[0275] 10:00 PM - Sleep data collection

[0276] User: Employees start sleep tracking on their smartwatch before going to bed.

[0277] Device: The smartwatch records your sleep data and syncs it to your smartphone the next morning.

[0278] 1:00 the next day - Data transmission and storage

[0279] Device: The smartphone sends the collected data to the server daily.

[0280] Server: The received data is linked to each employee's ID and stored in a database.

[0281] 3:00 the next day - Data analysis

[0282] Server: Extracts the stored data and calculates a fatigue score using a generative model. Emotional data is also included in the analysis to calculate a more accurate fatigue score.

[0283] 9:00 the next day - Suggestions and notifications

[0284] Server: Generates suggestions based on fatigue scores and sends notifications such as "Take time off recommended" to employees and managers.

[0285] In this way, by combining the emotion engine, a system can be created that can monitor employees' health in more detail and recommend time off or work adjustments at the appropriate time, thereby more effectively maintaining employees' physical and mental health.

[0286] The processing flow will be explained below.

[0287] Step 1: Data collection

[0288] User: Wears the smartwatch, weighs himself on a scale, manually enters his food intake into the app, and starts sleep tracking before going to bed.

[0289] Device: The smartwatch records weight, food, and sleep data, which is automatically synced to the user's smartphone.

[0290] Step 2: Collecting emotion data

[0291] User: Emotion data is collected periodically using a facial recognition camera or voice input. For example, the user records emotion data in front of the camera at 3:00 PM every day.

[0292] Emotion engine: Recognizes the user's emotions using voice and facial expression analysis, and generates numerical data.

[0293] Step 3: Send data

[0294] Device: At the end of each day, collected weight, food, sleep, and emotional data is sent to a server. The data is encrypted to protect privacy.

[0295] Step 4: Save Data

[0296] Server: The received data is linked to each user's ID and stored in a database. The stored data includes date, weight, dietary details, sleep information, and emotional data.

[0297] Step 5: Data Preprocessing

[0298] Server: Periodically extracts the stored data and converts it into the format required for analysis, for example by aggregating daily data into weekly data.

[0299] Step 6: Analysis with generative models

[0300] Server: Data extracted from the database is fed into a generative model to comprehensively analyze sleep quality, dietary balance, weight fluctuations, meeting attendance times, emotional data, and more.

[0301] Step 7: Calculating your fatigue score

[0302] Server: The generative model uses the data to calculate a fatigue score for each user, which serves as an indicator of the user's health status.

[0303] Step 8: Proposal Generation

[0304] Server: Generates suggestions for taking time off or adjusting work load based on the calculated fatigue score. Specifically, it recommends taking time off if the fatigue score is high, and suggests redistributing tasks if the workload is high.

[0305] Step 9: Sending notifications

[0306] Server: Notifies the user and manager of the proposed schedule. For example, a notification such as "We recommend you take vacation next Friday" is sent to the user's smartphone. In addition, a report is sent to the manager stating, "User A is experiencing high levels of fatigue, so please adjust his or her work schedule."

[0307] Step 10: Gather feedback

[0308] User: Acts on the suggestions and provides feedback on the results in a dedicated app. For example, if a user takes a vacation, the app records the user's physical condition and mood for that day.

[0309] Terminal: Collects user feedback data and reflects it in the next analysis process.

[0310] Through these steps, a system can be built that can maintain the physical and mental health of employees by continuously monitoring their health status and recommending time off or work adjustments at the appropriate time.The addition of an emotion engine will also enable more detailed health management by evaluating fluctuations in emotional stress and happiness.

[0311] Example 2

[0312] 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."

[0313] It is important to centrally monitor employees' health and make suggestions for appropriate leave and work adjustments. However, conventional systems only collect and analyze physical data such as weight, diet, and sleep, and do not take into account factors such as emotional data or meeting participation status, making it difficult to accurately and comprehensively assess fatigue levels.

[0314] The identification process by the identification 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 weight data, dietary data, and sleep data obtained from a data collection device, means for transmitting the data collected from the data collection device to the server, means for analyzing the data stored in the server using a generative model and calculating a fatigue score, means for generating and notifying suggestions for taking vacation or adjusting work schedules based on the fatigue score, and means for collecting emotion data using face recognition and voice recognition, analyzing the data using an emotion engine, and reflecting the results in the fatigue score. This enables a more accurate and comprehensive fatigue assessment by comprehensively taking into account not only physical data but also emotion data, meeting data, and the like.

[0315] A "data collection device" is a device used to collect employee weight data, dietary data, sleep data, emotional data, etc., and specifically refers to a smartwatch or dedicated application.

[0316] The "server" is a computer system that stores collected data, analyzes it using a generative model, and calculates a fatigue score.

[0317] A "generative model" is a program that uses machine learning algorithms to analyze collected data and calculate a fatigue score, taking into account factors such as weight fluctuations, dietary balance, sleep quality, and meeting attendance time.

[0318] The "fatigue score" is a numerical representation of an employee's health status, and is an index calculated using a generative model based on weight data, dietary data, sleep data, emotional data, and meeting data.

[0319] "Notification method" refers to the means used to notify employees and managers of generated vacation and work adjustment proposals, specifically notifications sent to smartphones, tablets, and PCs.

[0320] The "emotion engine" is a program that analyzes emotional data collected using facial and voice recognition technology, quantifies it, and reflects it in a fatigue score.

[0321] MODE FOR CARRYING OUT THE INVENTION

[0322] The present invention is a system designed to monitor the health status of employees and encourage them to take appropriate leave and adjust their work schedules. How the system is implemented will be explained below.

[0323] Hardware and software used

[0324] The system includes the following components:

[0325] Data collection device: smartwatch, dedicated application

[0326] Server: a computer system that stores and analyzes data

[0327] Generative model: a program that implements a machine learning algorithm

[0328] Emotion Engine: An emotion analysis program using facial and voice recognition technology

[0329] Notification method: smartphone, tablet, PC

[0330] Examples of data collection devices

[0331] The user wears a smartwatch and collects weight, diet, and sleep data in their daily lives.

[0332] For example, every morning a user steps on a scale linked to a smartwatch to measure their weight.

[0333] Users manually enter their meal data using a dedicated app.

[0334] Data transmission and storage

[0335] The device (smartphone or tablet) automatically sends the collected data to the server at a set time. The data is encrypted to protect privacy.

[0336] For example, every day at 1:00 AM, your smartphone sends all the data collected during the day to a server.

[0337] Data analysis

[0338] The server stores the received data and analyzes it using a generative model. A machine learning algorithm is used to calculate a fatigue score based on weight fluctuations, dietary balance, sleep quality, and meeting participation time.

[0339] The generative model retrieves meeting data from employees' calendar information and adds it to the analysis.

[0340] Emotion data collection and analysis

[0341] Users collect emotion data using a facial recognition camera and voice recognition.

[0342] For example, every day at 3 p.m., a facial recognition camera will photograph your face and collect emotional data.

[0343] The emotion engine analyzes the collected emotion data, quantifies it, and stores it on the server.

[0344] Fatigue assessment and suggestion generation

[0345] The server calculates a fatigue score based on the analysis results, and if this exceeds a certain threshold, it generates suggestions for taking time off or adjusting work schedules.

[0346] Notification means

[0347] A notification means notifies the proposal to the terminals of employees and managers.

[0348] For example, every morning at 9 a.m., employees will receive a notification on their smartphones saying, "We recommend that you take Friday off."

[0349] Prompt Sentence Examples

[0350] Give instructions to the generative AI model using prompt sentences like the following:

[0351] "Design a program that evaluates employee fatigue levels based on employee health data (weight, diet, sleep, meeting attendance time, and emotional data) and generates vacation recommendations and work adjustment suggestions."

[0352] This will enable the realization of a system that can effectively monitor employees' health by comprehensively taking into account not only physical data but also emotional data, meeting data, etc., and recommend vacation time and work adjustments at the appropriate time.

[0353] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0354] Step 1: Data collection

[0355] The user wears a smartwatch and collects weight, diet, and sleep data in their daily lives.

[0356] Input: Biometric data collected from the user's daily life.

[0357] Specific operation: Every morning, the user steps on the scale to measure their weight and manually enters their dietary data using a dedicated app.

[0358] Output: Collected weight data, dietary data, and sleep data are recorded on the smartwatch.

[0359] Step 2: Send and save data

[0360] The device automatically sends the collected data to the server at a set time. The data is encrypted.

[0361] Input: Data transferred from the smartwatch (weight data, diet data, sleep data).

[0362] Specific operation: The smartphone uploads data to the server at 1:00 AM every day.

[0363] Output: Data encrypted and stored on the server.

[0364] Step 3: Data analysis

[0365] The server stores the received data and analyzes it using a generative AI model.

[0366] Input: Weight data, dietary data, and sleep data stored on the server.

[0367] What it does: The server uses machine learning algorithms to analyze the data and calculate a fatigue score.

[0368] Output: Fatigue score based on weight fluctuations, dietary balance, and sleep quality.

[0369] Step 4: Collecting emotion data

[0370] Users collect emotional data using facial recognition cameras and voice recognition.

[0371] Input: Emotion data from the user's face recognition camera and voice recognition device.

[0372] Specific operation: The user takes a picture of their face with a facial recognition camera at 3:00 pm every day to collect emotional data.

[0373] Output: The collected emotion data is recorded on a smart device.

[0374] Step 5: Analyze the sentiment data

[0375] The emotion engine analyzes the collected emotion data, quantifies it, and stores it on the server.

[0376] Input: Emotion data transferred from smart devices.

[0377] Specific operation: The emotion engine analyzes facial expressions and voice to quantify the user's emotional state.

[0378] Output: The analysis results are sent to the server as numerical data and saved.

[0379] Step 6: Fatigue assessment and generation of recommendations

[0380] The server calculates a fatigue score based on the analysis results, and if this exceeds a certain threshold, generates a suggestion.

[0381] Input: Weight data, dietary data, sleep data, emotion data stored on the server, and analysis results from the generative model.

[0382] How it works: The server analyzes all data and uses a generative model to calculate a fatigue score. If the score exceeds a threshold, it generates suggestions for taking time off or adjusting work schedules.

[0383] Output: Data including fatigue score and suggested sentence.

[0384] Step 7: Notification methods

[0385] A notification means notifies the proposal to the terminals of employees and managers.

[0386] Input: Proposal and notification data from the server.

[0387] What it does: Employees will receive a notification on their smartphones saying, "We recommend you take time off on Friday." Managers will also receive a related report.

[0388] Output: Notifications displayed on employee and manager devices.

[0389] The above process allows for detailed and comprehensive monitoring of employee health status, allowing timely recommendations for leave and work adjustments to be made.

[0390] (Application example 2)

[0391] 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."

[0392] In factory environments, it is difficult to monitor workers' health in real time and schedule appropriate leave and work adjustments. This can lead to accumulated fatigue and stress, which can lead to increased accidents and reduced production efficiency. Conventional systems only collect single data such as body temperature and heart rate, making it difficult to accurately assess workers' overall health. Furthermore, because fatigue assessments do not take into account changes in emotional state, workers' mental health is often overlooked.

[0393] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting body temperature data, heart rate data, blood pressure data, voice data, and facial expression data obtained from a data collection device, means for transmitting the data collected from the data collection device to the server, means for analyzing the data stored in the server using a generative model and calculating a fatigue score, means for collecting emotion data from voice and facial expression using an emotion analysis engine and reflecting the emotion data in the fatigue score, and means for generating and notifying suggestions for taking vacation or adjusting work schedules in real time based on the fatigue score. This enables a comprehensive evaluation of workers' health conditions in real time, and enables improved production efficiency and reduced accidents through appropriate vacation and work schedule adjustments.

[0394] "Employee health status" refers to the physical and mental condition of workers, specifically body temperature, heart rate, blood pressure, quality of sleep, diet, emotional state, etc.

[0395] "Data collection devices" are equipment used to collect employee health data, specifically wearable devices such as smartwatches and smart helmets.

[0396] "Server" refers to a computer system that is capable of storing and analyzing collected data and is used to centrally manage and analyze collected data.

[0397] "Generative model" refers to a mathematical model that uses machine learning algorithms to analyze data and calculate a fatigue score.

[0398] The "fatigue score" is a numerical representation of an employee's level of fatigue, calculated by taking into account factors such as body temperature, heart rate, blood pressure, time spent in meetings, and emotional data.

[0399] An "emotion analysis engine" refers to software that analyzes voice data and facial expression data to quantify an employee's emotional state.

[0400] "Emotional data" refers to numerical or categorical data that express an employee's emotional state, and is obtained using voice analysis and facial recognition technology.

[0401] "Leave and work adjustment suggestions" refers to specific recommendations for appropriate leave and work schedule adjustments based on an employee's fatigue score.

[0402] The system of the present invention is designed to monitor the health status of factory workers in real time and promote appropriate leave taking and work adjustments. The system includes a data collection device, a server, a generative model, a notification means, and a sentiment analysis engine.

[0403] System Components and Operation

[0404] 1. Data Collection Equipment

[0405] The user wears a smart helmet equipped with temperature sensors, heart rate sensors, blood pressure sensors, a microphone, and a camera, which collects data on body temperature, heart rate, blood pressure, voice, and facial expression. This data is then sent to the user's smartphone via Bluetooth.

[0406] 2. Data transmission and storage

[0407] The collected data is sent to a server daily. The data is encrypted to protect the privacy of the data. The server associates the received data with each user's ID and stores it in a database.

[0408] 3. Data Analysis

[0409] The server periodically extracts the stored data and analyzes it based on a generative model. The generative model is designed using machine learning algorithms and comprehensively evaluates body temperature, heart rate, blood pressure, meeting participation time, emotional data, etc. to calculate a fatigue score. The server also evaluates how much time the user is spending in meetings.

[0410] 4. Sentiment Analysis Engine and Sentiment Evaluation

[0411] The user periodically collects emotional data using the microphone and camera in the smart helmet. The emotion analysis engine uses voice analysis and facial recognition technology to recognize the user's emotional state, converting it into a numerical value and storing it. The server stores the emotional data collected by the emotion analysis engine in a database and reflects it in the calculation of the fatigue score.

[0412] 5. Fatigue assessment and suggestions

[0413] The server evaluates the fatigue state of each user based on the fatigue score calculated by the generative model. If the fatigue score exceeds a certain threshold, it generates suggestions for taking vacation or adjusting work schedules and notifies the user via a notification method on their smartphone. For example, it may send a notification to the user saying, "We recommend taking vacation this Friday." It may also send a report to management saying, "Worker A's fatigue level is high, and weekend vacation is recommended."

[0414] Specific examples

[0415] Below is an example of a day's work and data processing.

[0416] 7:00 AM - Temperature data collection

[0417] After waking up, the user puts on the smart helmet and measures their body temperature.

[0418] Body temperature data is automatically recorded on a smartphone.

[0419] 13:00 noon - Heart rate data collection

[0420] After lunch, the user measures his / her heart rate.

[0421] Heart rate data is stored on your smartphone.

[0422] 15:00 noon - Emotion data collection

[0423] The user collects emotion data using the camera in the smart helmet.

[0424] The emotion analysis engine analyzes the emotion data, converts it into numbers, and sends it to the server.

[0425] 10:00 PM - Blood pressure data collection

[0426] The smart helmet measures the user's blood pressure before they go to sleep.

[0427] Blood pressure data is automatically synced to your smartphone.

[0428] 1:00 the next day - Data transmission and storage

[0429] The smartphone sends the collected data to the server daily.

[0430] The server associates the received data with each user's ID and stores it in a database.

[0431] 3:00 the next day - Data analysis

[0432] The server extracts the stored data and calculates a fatigue score using a generative model.

[0433] 9:00 the next day - Suggestions and notifications

[0434] The server generates suggestions based on the fatigue score and sends notifications such as "take vacation recommended" to the user and manager.

[0435] Prompt Sentence Examples

[0436] "Predict the user's fatigue level based on the following data: Body temperature: 36.5, Heart rate: 80, Blood pressure: 120 / 80, Emotion score: 7"

[0437] In this way, by combining it with an emotion analysis engine, it is possible to monitor the health status of factory workers in more detail and make timely recommendations for leave and work adjustments.

[0438] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0439] Step 1:

[0440] The user wears a smart helmet and collects data on body temperature, heart rate, blood pressure, voice, and facial expression. The various sensors in the smart helmet record this data in real time. The input is the signal from the various sensors, and the output is the raw health data recorded in the smart helmet.

[0441] Step 2:

[0442] The terminal (user's smartphone) receives health data collected from the smart helmet via Bluetooth and temporarily stores it. The input is raw data from the smart helmet, and the output is data stored on the smartphone.

[0443] Step 3:

[0444] The device sends all collected data to the server at a set time each day. The data is encrypted before being sent. The input is the data stored on the smartphone, and the output is the encrypted data stored on the server.

[0445] Step 4:

[0446] The server associates the received data with each user's ID and stores it in a database. The input is encrypted data, and the output is the data for each user stored in the database.

[0447] Step 5:

[0448] The server periodically extracts user data from the database and analyzes it using a generative model. The generative model is designed using a machine learning algorithm and comprehensively evaluates body temperature, heart rate, blood pressure, meeting participation time, emotional data, etc. to calculate a fatigue score. The input is the data extracted from the database, and the output is the calculated fatigue score.

[0449] Step 6:

[0450] The server uses an emotion analysis engine to collect emotion data from voice data and facial expression data and integrate it into a generative model. The emotion analysis engine quantifies the emotion data using voice recognition and facial recognition technology. The input is voice data and facial expression data, and the output is quantified emotion data.

[0451] Step 7:

[0452] The server incorporates the emotional data into the fatigue score calculation to generate a more accurate fatigue score. The input is the quantified emotional data and other health data, and the output is an updated fatigue score.

[0453] Step 8:

[0454] The server generates suggestions for taking time off or adjusting work schedules based on the fatigue score calculated by the generative model. The input is the fatigue score, and the output is suggestions for taking time off or adjusting work schedules.

[0455] Step 9:

[0456] The server notifies the generated proposals to the user's and manager's devices. Specific proposals for taking leave or adjusting work schedules are sent to the user's smartphone via the notification means. The input is the proposal content, and the output is a notification displayed on the user's and manager's device.

[0457] Through these steps, a system will be created that comprehensively assesses workers' health status in real time and suggests appropriate leave and work adjustments as needed.

[0458] 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.

[0459] 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.

[0460] 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.

[0461] [Second embodiment]

[0462] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0463] 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.

[0464] 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).

[0465] 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.

[0466] 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.

[0467] 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).

[0468] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for 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.

[0469] 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.

[0470] 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.

[0471] 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.

[0472] 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.

[0473] 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."

[0474] The system of the present invention is designed to monitor employee health status and promote appropriate leave taking and work adjustments. This system includes a data collection device, a server, a generative model, and a notification means. The following describes in detail how this system is implemented.

[0475] System Components and Operation

[0476] 1. Data Collection Equipment

[0477] User: Each employee wears a smartwatch, which collects weight, diet, and sleep data.

[0478] Device: The data collected by the smartwatch is automatically sent to employees' smartphones or tablets. Employees can also manually enter meal data using a dedicated app.

[0479] 2. Data transmission and storage

[0480] Device: At a set time each day, all collected data is sent to the server. The data is encrypted and transmitted to protect the privacy of the data.

[0481] Server: The server associates the received data with each employee's ID and stores it in a database, allowing all of each employee's weight, diet, and sleep data to be managed centrally.

[0482] 3. Data Analysis

[0483] Server: The server periodically extracts the stored data and analyzes it according to a generative model, which is designed using machine learning algorithms to calculate a fatigue score by taking into account weight fluctuations, dietary balance, sleep quality, and meeting participation time.

[0484] Generative model: Meeting data is taken from each employee's calendar information and added to the analysis. This meeting data is important for assessing how much time employees spend in meetings.

[0485] 4. Fatigue assessment and suggestions

[0486] Server: Evaluates the fatigue level of each employee based on the fatigue score calculated by the generative model. If the fatigue score exceeds a certain threshold, it generates suggestions for taking time off or adjusting work schedules.

[0487] Notification method: The server notifies the generated proposal to the employee and manager's devices. For example, a notification such as "We recommend you take a vacation this Friday" is sent to the employee's smartphone. Also, a report is sent to the manager saying, "Employee A is highly fatigued and we recommend that he take a weekend vacation."

[0488] Specific examples

[0489] Daily flow and data processing example

[0490] 7:00 AM - Weight data collection

[0491] User: After waking up, an employee steps on a scale linked to a smartwatch to measure their weight.

[0492] Device: Weight data is automatically recorded on your smartphone.

[0493] 13:00 noon - Collection of dietary data

[0494] User: After employees have lunch, they enter their meal details using a dedicated app.

[0495] Device: The entered meal data is saved on your smartphone.

[0496] 10:00 PM - Sleep data collection

[0497] User: Employees start sleep tracking on their smartwatch before going to bed.

[0498] Device: The smartwatch records your sleep data and syncs it to your smartphone the next morning.

[0499] 1:00 the next day - Data transmission and storage

[0500] Device: The smartphone sends the collected data to the server daily.

[0501] Server: The received data is linked to each employee's ID and stored in a database.

[0502] 3:00 the next day - Data analysis

[0503] Server: Extracts the stored data and calculates the fatigue score using a generative model.

[0504] 9:00 the next day - Suggestions and notifications

[0505] Server: Generates suggestions based on fatigue scores and sends notifications such as "Take time off recommended" to employees and managers.

[0506] In this way, a system can be created that supports the physical and mental health of employees by continuously and in detail monitoring their health status and recommending time off or work adjustments at the appropriate time.

[0507] The processing flow will be explained below.

[0508] Step 1: Data collection

[0509] User: Wears the smartwatch, weighs himself on a scale, manually enters his food intake into the app, and starts sleep tracking before going to bed.

[0510] Device: The smartwatch records weight, food, and sleep data, which is automatically synced to the user's smartphone.

[0511] Step 2: Send data

[0512] Device: At the end of each day, collected weight, food, and sleep data is sent to a server. The data is encrypted to protect privacy.

[0513] Step 3: Save data

[0514] Server: The received data is linked to each user's ID and stored in a database. The stored data includes date, weight, dietary details, and sleep information.

[0515] Step 4: Data Preprocessing

[0516] Server: Periodically extracts the stored data and converts it into the format required for analysis, for example by aggregating daily data into weekly data.

[0517] Step 5: Analysis with generative models

[0518] Server: Data extracted from the database is fed into a generative model to comprehensively analyze sleep quality, dietary balance, weight fluctuations, meeting attendance times, and more.

[0519] Step 6: Calculating your fatigue score

[0520] Server: The generative model uses the data to calculate a fatigue score for each user, which serves as an indicator of the user's health status.

[0521] Step 7: Proposal Generation

[0522] Server: Generates suggestions for taking time off or adjusting work load based on the calculated fatigue score. Specifically, it recommends taking time off if the fatigue score is high, and suggests redistributing tasks if the workload is high.

[0523] Step 8: Sending notifications

[0524] Server: Notifies the user and manager of the proposed schedule. For example, a notification such as "We recommend you take vacation next Friday" is sent to the user's smartphone. In addition, a report is sent to the manager stating, "User A is experiencing high levels of fatigue, so please adjust his or her work schedule."

[0525] Step 9: Gather feedback

[0526] User: Acts on the suggestions and provides feedback on the results in a dedicated app. For example, if a user takes a vacation, the app records the user's physical condition and mood for that day.

[0527] Terminal: Collects user feedback data and reflects it in the next analysis process.

[0528] Through these steps, a system can be created that can maintain the physical and mental health of employees by continuously monitoring their health status and recommending time off or work adjustments at the appropriate time.

[0529] Example 1

[0530] 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."

[0531] In modern companies, continuously monitoring employee health and encouraging appropriate leave and work adjustments is a challenging issue. This issue directly impacts employee productivity and well-being, so it must be resolved quickly. Furthermore, traditional health monitoring systems often have low data collection and analysis efficiency, and lack the ability to provide personalized recommendations based on individual employee conditions.

[0532] 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.

[0533] In this invention, the server includes means for collecting weight data, dietary data, and sleep data obtained from a data collection device, means for encrypting the data collected from the data collection device and transmitting it to the server, means for analyzing the data stored in the server using a generative model to calculate a fatigue score, means for generating and notifying suggestions for taking vacation or adjusting work schedules based on the fatigue score, means for the server to periodically extract and analyze data, and means for the terminal to receive and display suggestions from the server to the user. This enables detailed monitoring of employee health conditions and makes it possible to make appropriate suggestions for taking vacation or adjusting work schedules based on individual circumstances.

[0534] "Data collection device" refers to equipment used to collect weight data, dietary data, and sleep data.

[0535] "Weight data" refers to information about employees' weight, and is primarily numerical data measured using devices such as smartwatches and scales.

[0536] "Dietary data" refers to information about employees' daily dietary habits, including calories and nutrients, which is collected through a dedicated app.

[0537] "Sleep data" refers to information about employees' sleep patterns and quality, primarily tracked by devices such as smartwatches.

[0538] A "server" is a computer system for storing and analyzing collected data.

[0539] "Encryption" is the technique of converting data into a special format to protect its privacy and security.

[0540] A "generative model" is a program that uses machine learning algorithms to analyze data and generate predictions and suggestions.

[0541] The "fatigue score" is an indicator of an employee's level of fatigue, calculated by analyzing weight data, dietary data, sleep data, etc.

[0542] "Suggestions" refer to recommendations to employees to take time off or adjust their work schedules based on their fatigue scores.

[0543] "Notification" is the act of sending information such as suggestions or warnings to employees and managers.

[0544] "Meeting data" refers to information about meetings listed on employees' calendars, including participation time and frequency.

[0545] "Terminal" refers to a mobile information terminal such as a smartphone or tablet, which is a device that collects, transmits, and receives notifications about data.

[0546] This invention is a system that monitors the health status of employees and encourages them to take appropriate leave and adjust their work schedules. The invention is implemented using a data collection device, a server, a generative model, a terminal, and a notification means.

[0547] Data collection equipment

[0548] User: Each employee wears a smartwatch that collects weight, diet, and sleep data.

[0549] Device: Data collected by the smartwatch is automatically sent to employees' smartphones or tablets. Employees can also manually enter meal data using a dedicated app.

[0550] Hardware: Smartwatches used include Apple Watch, Fitbit, and Garmin.

[0551] Software: A dedicated app (such as MyFitnessPal) is used to input dietary data.

[0552] Data transmission and storage

[0553] Device: The smartphone sends all collected data to the server at a set time each day. The data is encrypted and transmitted to protect privacy. This encryption is done using AES-256.

[0554] Server: The server associates the received data with each employee's ID and stores it in a database using MySQL or PostgreSQL.

[0555] Data analysis

[0556] Server: The server periodically extracts the stored data and analyzes it according to the generative model, which is designed using a machine learning algorithm and implemented in TensorFlow or PyTorch.

[0557] Generative model: Meeting data is taken from each employee's calendar information and added to the analysis. Meeting data is important for assessing how much time an employee spends in meetings.

[0558] Fatigue assessment and suggestions

[0559] Server: Evaluates the fatigue level of each employee based on the fatigue score calculated by the generative model. If the fatigue score exceeds a certain threshold, it generates suggestions for taking time off or adjusting work schedules.

[0560] Notification method: The server notifies the generated proposal to the employee and manager's devices. For example, a notification saying "We recommend you take a vacation this Friday" is sent to the employee's smartphone. Also, a report saying "Employee A is highly fatigued and we recommend that he / she take a weekend vacation" is sent to the manager.

[0561] Specific examples

[0562] Daily flow and data processing example

[0563] 7:00 AM - Weight data collection

[0564] User: After waking up, an employee steps on a scale linked to a smartwatch to measure their weight.

[0565] Device: Weight data is automatically recorded on your smartphone.

[0566] 13:00 noon - Collection of dietary data

[0567] User: After employees have lunch, they enter their meal details using a dedicated app.

[0568] Device: The entered meal data is saved on your smartphone.

[0569] 10:00 PM - Sleep data collection

[0570] User: Employees start sleep tracking on their smartwatch before going to bed.

[0571] Device: The smartwatch records your sleep data and syncs it to your smartphone the next morning.

[0572] 1:00 the next day - Data transmission and storage

[0573] Device: The smartphone sends the collected data to the server daily.

[0574] Server: The received data is linked to each employee's ID and stored in a database.

[0575] 3:00 the next day - Data analysis

[0576] Server: Extracts the stored data and calculates the fatigue score using a generative model.

[0577] 9:00 the next day - Suggestions and notifications

[0578] Server: Generates suggestions based on fatigue scores and sends notifications such as "Take time off recommended" to employees and managers.

[0579] An example of a prompt sentence is, "After lunch, please enter your meal data in the dedicated app. Then, based on the fatigue score you submit, we will notify you of suggestions for taking time off."

[0580] This invention supports the physical and mental health of employees by continuously and in detail monitoring their health status and recommending time off or work adjustments at the appropriate time.

[0581] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0582] Step 1: Data collection

[0583] Subject: User

[0584] Specific operations: The user steps on a scale connected to a smartwatch to measure their weight. After lunch, they manually enter their meal details using a dedicated app. Before going to bed, they start sleep tracking on the smartwatch.

[0585] Input: Weight data measured by a scale, food data entered into a dedicated app, and sleep data tracked by a smartwatch.

[0586] Output: The respective data is recorded on the smartwatch and smartphone.

[0587] Step 2: Send data

[0588] Subject: Device

[0589] How it works: The smartwatch sends the collected data to a smartphone via Bluetooth or Wi-Fi, and the smartphone encrypts and sends the data to a server daily.

[0590] Input: Weight data, food data, and sleep data sent from the smartwatch.

[0591] Output: The encrypted data is sent from the smartphone to the server.

[0592] Step 3: Receiving and storing data

[0593] Subject: Server

[0594] Specific operation: The server receives the encrypted data sent from the smartphone, verifies that the data format is correct, and then associates it with each employee's ID and stores it in a database.

[0595] Input: Encrypted weight data, diet data, sleep data, and employee ID information.

[0596] Output: Data associated with each employee's ID is saved in the database.

[0597] Step 4: Data extraction and analysis

[0598] Subject: Server

[0599] Specific operation: The server periodically extracts weight, diet, and sleep data for each employee from the database. The extracted data is passed to the generative model for analysis.

[0600] Input: Weight data, dietary data, and sleep data stored in a database.

[0601] Output: Fatigue score as the analysis result.

[0602] Step 5: Integrating Meeting Data

[0603] Subject: Generative Model

[0604] What it does: The generative model retrieves meeting data from an employee's calendar information and adds it to the fatigue score analysis.

[0605] Input: Employee weight data, diet data, sleep data, and calendar meeting data.

[0606] Output: A calculated fatigue score based on the combined data.

[0607] Step 6: Fatigue assessment and recommendations

[0608] Subject: Server

[0609] Specific operation: Evaluate each employee's fatigue level based on the fatigue score calculated by the generative model. If the fatigue score exceeds a certain threshold, generate suggestions for taking time off or adjusting work schedules.

[0610] Input: Fatigue score calculated by the generative model.

[0611] Output: Suggestions for taking leave or adjusting work schedules.

[0612] Step 7: Proposal Notification

[0613] Subject: Server

[0614] Specific operation: The server notifies the employee and manager of the proposal, including details of taking leave and adjusting work schedules.

[0615] Input: Generated leave and work adjustment proposals.

[0616] Output: Proposals sent as push notifications and emails to employee and manager devices.

[0617] In this way, a system can be created that continuously and in detail monitors employees' health status and makes timely recommendations for leave and work adjustments.

[0618] (Application example 1)

[0619] 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."

[0620] Conventional health monitoring systems have difficulty accurately assessing employee fatigue levels due to insufficient management of employee physical condition. Furthermore, relying solely on fixed data collection devices has the drawback of being unable to collect real-time health data on-site or quickly propose appropriate work adjustments. Accumulating worker fatigue, particularly in factories, can lead to reduced productivity and potentially adversely affect safety.

[0621] 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.

[0622] In this invention, the server includes means for collecting weight data, dietary data, and sleep data obtained from a data collection device, means for transmitting the data collected from the data collection device to the server, means for analyzing the data stored in the server using a generative model to calculate a fatigue score, means for generating and notifying suggestions for taking time off or adjusting work schedules based on the fatigue score, and means for collecting and transmitting additional health data obtained from a patrolling mobile robot. This allows for more detailed and real-time monitoring of employee health conditions, enabling appropriate and prompt suggestions for taking time off or adjusting work schedules.

[0623] A "data collection device" is a device worn by an employee to collect weight data, dietary data, sleep data, and the like.

[0624] A "smartwatch" is a type of data collection device that is worn on an employee's wrist and collects various types of biometric data.

[0625] The "mobile robot" is a robot that patrols the factory and collects health data from workers' smartwatches.

[0626] The "server" is a device that collects and stores various data, and is a central processing unit that calculates fatigue scores and generates suggestions using generative models.

[0627] A "generative model" is a machine learning algorithm used to analyze collected data and calculate an employee's fatigue score.

[0628] The "fatigue score" is a value indicating an employee's level of fatigue calculated by the generative model based on weight data, dietary data, sleep data, meeting data, etc.

[0629] "Suggestions for taking vacation or adjusting work schedules" are notifications that recommend taking vacation or adjusting work schedules to maintain employees' health based on their fatigue score.

[0630] The present invention is a system that monitors the health status of employees and encourages them to take appropriate vacations and adjust their work schedules. This system includes a data collection device, a mobile robot, a server, a generative model, and a notification means. The program processing of this system is described in detail below.

[0631] System components and operation description

[0632] 1. Data Collection Equipment

[0633] User: Employees wear smartwatches that collect weight, diet, and sleep data.

[0634] Device: The data collected by the smartwatch is automatically sent to employees' smartphones or tablets. Employees can also manually enter meal data using a dedicated app.

[0635] 2. Data transmission and storage

[0636] Device: All collected data is sent to the server on a daily basis. The data is encrypted and transmitted to protect the privacy of the data.

[0637] Server: The server associates the received data with each employee's ID and stores it in a database, allowing all of each employee's weight, diet, and sleep data to be managed centrally.

[0638] 3. Data Analysis with Generative Models

[0639] Server: The server periodically extracts the stored data and analyzes it according to a generative model, which is designed using machine learning algorithms to calculate a fatigue score by taking into account weight fluctuations, dietary balance, sleep quality, and meeting participation time.

[0640] Generative model: Data analysis also includes meeting data obtained from calendar information to more precisely assess employee fatigue levels.

[0641] 4. Fatigue assessment and suggestions

[0642] Server: Evaluates the fatigue level of each employee based on the fatigue score calculated by the generative model. If the fatigue score exceeds a certain threshold, it generates suggestions for taking time off or adjusting work schedules.

[0643] Notification method: The server notifies the generated suggestions to the employees' and managers' devices. For example, a notification such as "We recommend you take a vacation this Friday" is sent to the employee's smartphone. Also, a report is sent to the manager saying, "Employee A's fatigue level is high, so we recommend that he or she take a weekend vacation."

[0644] 5. Additional data collection by mobile robots

[0645] Robot: The robot roams the factory floor, collecting real-time health data from workers' smartwatches and transmitting it to a server using its own Wi-Fi module.

[0646] Hardware and software used

[0647] Hardware

[0648] Smartwatches: Apple Watch, Fitbit, etc.

[0649] Mobile robots: such as Fetch Robotics' Fetch Mobile Manipulator.

[0650] Server: Linux-based dedicated server.

[0651] software

[0652] Generative model: Python machine learning library (TensorFlow or PyTorch)

[0653] Database: MySQL, PostgreSQL, etc.

[0654] Notification method: Voice synthesis technology such as Google Text-to-Speech.

[0655] Specific examples

[0656] Example prompts for generative AI models

[0657] Create a generative model that calculates fatigue levels based on workers' health data and suggests appropriate breaks and work adjustments.

[0658] Data points:

[0659] Weight data: 70 kg

[0660] Dietary data: Calories 2000 kcal

[0661] Sleep data: 6 hours

[0662] prompt:

[0663] 1. How to calculate worker fatigue?

[0664] 2. How do you assess your daily workload?

[0665] 3. How do we create specific proposals for breaks and work adjustments?

[0666] This system allows for detailed and real-time monitoring of employee health conditions, enabling appropriate and prompt leave proposals and work adjustments, contributing to improved productivity throughout the factory and ensuring employee safety.

[0667] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0668] Step 1:

[0669] The user wears a smartwatch to collect weight, diet, and sleep data. The smartwatch collects this data in real time and automatically transmits it to a smartphone. The input is biometric data, and the output is data stored on the smartphone.

[0670] Step 2:

[0671] The smartphone, which is the terminal, periodically sends the collected data to the server on a daily basis. The data is encrypted to protect privacy. The input is the data stored on the smartphone, and the output is the encrypted data sent to the server.

[0672] Step 3:

[0673] The server links the received data to each employee's ID and stores it in a database. This allows the server to centrally manage weight data, dietary data, and sleep data. The input is encrypted health data, and the output is organized data stored in the database.

[0674] Step 4:

[0675] The server periodically extracts data from the database and analyzes it using a generative model. The generative model, which uses a machine learning algorithm, analyzes weight fluctuations, dietary balance, sleep quality, and meeting participation time to calculate a fatigue score. The input is each employee's health data and meeting data, and the output is a fatigue score.

[0676] Step 5:

[0677] Based on the fatigue score calculated by the generative model, the server evaluates the employee's fatigue state. If the fatigue score exceeds a certain threshold, the server generates suggestions for taking time off or adjusting work schedules. The input is the fatigue score, and the output is the suggestion.

[0678] Step 6:

[0679] As a notification method, the server notifies the generated suggestions to the devices of employees and managers. For example, a notification such as "We recommend you take vacation this Friday" is sent to an employee's smartphone. The input is the suggestion content, and the output is the notification to employees and managers.

[0680] Step 7:

[0681] The mobile robot patrols the factory and collects additional health data from the smartwatch. The robot transmits this data to a server via its WiFi module. The input is the real-time health data of employees, and the output is the data transmitted to the server.

[0682] Step 8:

[0683] The server receives additional health data sent from the mobile robot and stores it in a database. It also updates the fatigue score in real time by reflecting the additional data in the generative model. The input is the health data from the mobile robot, and the output is the updated data stored in the database.

[0684] 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.

[0685] The system of the present invention is designed to monitor employee health status and promote appropriate leave taking and work adjustments. This system includes a data collection device, a server, a generative model, a notification means, and an emotion engine. The following describes in detail how this system is implemented.

[0686] System Components and Operation

[0687] 1. Data Collection Equipment

[0688] User: Each employee wears a smartwatch, which collects weight, diet, and sleep data.

[0689] Device: The data collected by the smartwatch is automatically sent to employees' smartphones or tablets. Employees can also manually enter meal data using a dedicated app.

[0690] 2. Data transmission and storage

[0691] Device: At a set time each day, all collected data is sent to the server. The data is encrypted and transmitted to protect the privacy of the data.

[0692] Server: The server associates the received data with each employee's ID and stores it in a database, allowing all of each employee's weight, diet, and sleep data to be managed centrally.

[0693] 3. Data Analysis

[0694] Server: The server periodically extracts the stored data and analyzes it according to the generative model. The generative model is designed using a machine learning algorithm and calculates a fatigue score by taking into account weight fluctuations, dietary balance, sleep quality, and meeting participation time. Emotion data from the emotion engine is also analyzed.

[0695] Generative model: Meeting data is taken from each employee's calendar information and added to the analysis. This meeting data is important for assessing how much time employees spend in meetings.

[0696] 4. Emotion Engine and Emotion Evaluation

[0697] User: Emotional data is collected periodically via smartphone or PC using facial recognition cameras and voice recognition.

[0698] Emotion engine: Recognizes the user's emotions using voice and facial expression analysis, converts them into numerical values, and stores them.

[0699] Server: Emotion data collected by the emotion engine is stored in a database and reflected in the calculation of fatigue scores.

[0700] 5. Fatigue assessment and suggestions

[0701] Server: Evaluates the fatigue level of each employee based on the fatigue score calculated by the generative model. If the fatigue score exceeds a certain threshold, it generates suggestions for taking time off or adjusting work schedules.

[0702] Notification method: The server notifies the generated proposal to the employee and manager's devices. For example, a notification such as "We recommend you take a vacation this Friday" is sent to the employee's smartphone. Also, a report is sent to the manager saying, "Employee A is highly fatigued and we recommend that he take a weekend vacation."

[0703] Specific examples

[0704] Daily flow and data processing example

[0705] 7:00 AM - Weight data collection

[0706] User: After waking up, an employee steps on a scale linked to a smartwatch to measure their weight.

[0707] Device: Weight data is automatically recorded on your smartphone.

[0708] 13:00 noon - Collection of dietary data

[0709] User: After employees have lunch, they enter their meal details using a dedicated app.

[0710] Device: The entered meal data is saved on your smartphone.

[0711] 15:00 noon - Emotion data collection

[0712] User: Employees use facial recognition cameras to collect emotional data.

[0713] Emotion engine: Analyzes emotional data, converts the user's emotional state into a numerical value, and sends it to the server.

[0714] 10:00 PM - Sleep data collection

[0715] User: Employees start sleep tracking on their smartwatch before going to bed.

[0716] Device: The smartwatch records your sleep data and syncs it to your smartphone the next morning.

[0717] 1:00 the next day - Data transmission and storage

[0718] Device: The smartphone sends the collected data to the server daily.

[0719] Server: The received data is linked to each employee's ID and stored in a database.

[0720] 3:00 the next day - Data analysis

[0721] Server: Extracts the stored data and calculates a fatigue score using a generative model. Emotional data is also included in the analysis to calculate a more accurate fatigue score.

[0722] 9:00 the next day - Suggestions and notifications

[0723] Server: Generates suggestions based on fatigue scores and sends notifications such as "Take time off recommended" to employees and managers.

[0724] In this way, by combining the emotion engine, a system can be created that can monitor employees' health in more detail and recommend time off or work adjustments at the appropriate time, thereby more effectively maintaining employees' physical and mental health.

[0725] The processing flow will be explained below.

[0726] Step 1: Data collection

[0727] User: Wears the smartwatch, weighs himself on a scale, manually enters his food intake into the app, and starts sleep tracking before going to bed.

[0728] Device: The smartwatch records weight, food, and sleep data, which is automatically synced to the user's smartphone.

[0729] Step 2: Collecting emotion data

[0730] User: Emotion data is collected periodically using a facial recognition camera or voice input. For example, the user records emotion data in front of the camera at 3:00 PM every day.

[0731] Emotion engine: Recognizes the user's emotions using voice and facial expression analysis, and generates numerical data.

[0732] Step 3: Send data

[0733] Device: At the end of each day, collected weight, food, sleep, and emotional data is sent to a server. The data is encrypted to protect privacy.

[0734] Step 4: Save Data

[0735] Server: The received data is linked to each user's ID and stored in a database. The stored data includes date, weight, dietary details, sleep information, and emotional data.

[0736] Step 5: Data Preprocessing

[0737] Server: Periodically extracts the stored data and converts it into the format required for analysis, for example by aggregating daily data into weekly data.

[0738] Step 6: Analysis with generative models

[0739] Server: Data extracted from the database is fed into a generative model to comprehensively analyze sleep quality, dietary balance, weight fluctuations, meeting attendance times, emotional data, and more.

[0740] Step 7: Calculating your fatigue score

[0741] Server: The generative model uses the data to calculate a fatigue score for each user, which serves as an indicator of the user's health status.

[0742] Step 8: Proposal Generation

[0743] Server: Generates suggestions for taking time off or adjusting work load based on the calculated fatigue score. Specifically, it recommends taking time off if the fatigue score is high, and suggests redistributing tasks if the workload is high.

[0744] Step 9: Sending notifications

[0745] Server: Notifies the user and manager of the proposed schedule. For example, a notification such as "We recommend you take vacation next Friday" is sent to the user's smartphone. In addition, a report is sent to the manager stating, "User A is experiencing high levels of fatigue, so please adjust his or her work schedule."

[0746] Step 10: Gather feedback

[0747] User: Acts on the suggestions and provides feedback on the results in a dedicated app. For example, if a user takes a vacation, the app records the user's physical condition and mood for that day.

[0748] Terminal: Collects user feedback data and reflects it in the next analysis process.

[0749] Through these steps, a system can be built that can maintain the physical and mental health of employees by continuously monitoring their health status and recommending time off or work adjustments at the appropriate time.The addition of an emotion engine will also enable more detailed health management by evaluating fluctuations in emotional stress and happiness.

[0750] Example 2

[0751] 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."

[0752] It is important to centrally monitor employees' health and make suggestions for appropriate leave and work adjustments. However, conventional systems only collect and analyze physical data such as weight, diet, and sleep, and do not take into account factors such as emotional data or meeting participation status, making it difficult to accurately and comprehensively assess fatigue levels.

[0753] The identification process by the identification 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 weight data, dietary data, and sleep data obtained from a data collection device, means for transmitting the data collected from the data collection device to the server, means for analyzing the data stored in the server using a generative model and calculating a fatigue score, means for generating and notifying suggestions for taking vacation or adjusting work schedules based on the fatigue score, and means for collecting emotion data using face recognition and voice recognition, analyzing the data using an emotion engine, and reflecting the results in the fatigue score. This enables a more accurate and comprehensive fatigue assessment by comprehensively taking into account not only physical data but also emotion data, meeting data, and the like.

[0754] A "data collection device" is a device used to collect employee weight data, dietary data, sleep data, emotional data, etc., and specifically refers to a smartwatch or dedicated application.

[0755] The "server" is a computer system that stores collected data, analyzes it using a generative model, and calculates a fatigue score.

[0756] A "generative model" is a program that uses machine learning algorithms to analyze collected data and calculate a fatigue score, taking into account factors such as weight fluctuations, dietary balance, sleep quality, and meeting attendance time.

[0757] The "fatigue score" is a numerical representation of an employee's health status, and is an index calculated using a generative model based on weight data, dietary data, sleep data, emotional data, and meeting data.

[0758] "Notification method" refers to the means used to notify employees and managers of generated vacation and work adjustment proposals, specifically notifications sent to smartphones, tablets, and PCs.

[0759] The "emotion engine" is a program that analyzes emotional data collected using facial and voice recognition technology, quantifies it, and reflects it in a fatigue score.

[0760] MODE FOR CARRYING OUT THE INVENTION

[0761] The present invention is a system designed to monitor the health status of employees and encourage them to take appropriate leave and adjust their work schedules. How the system is implemented will be explained below.

[0762] Hardware and software used

[0763] The system includes the following components:

[0764] Data collection device: smartwatch, dedicated application

[0765] Server: a computer system that stores and analyzes data

[0766] Generative model: a program that implements a machine learning algorithm

[0767] Emotion Engine: An emotion analysis program using facial and voice recognition technology

[0768] Notification method: smartphone, tablet, PC

[0769] Examples of data collection devices

[0770] The user wears a smartwatch and collects weight, diet, and sleep data in their daily lives.

[0771] For example, every morning a user steps on a scale linked to a smartwatch to measure their weight.

[0772] Users manually enter their meal data using a dedicated app.

[0773] Data transmission and storage

[0774] The device (smartphone or tablet) automatically sends the collected data to the server at a set time. The data is encrypted to protect privacy.

[0775] For example, every day at 1:00 AM, your smartphone sends all the data collected during the day to a server.

[0776] Data analysis

[0777] The server stores the received data and analyzes it using a generative model. A machine learning algorithm is used to calculate a fatigue score based on weight fluctuations, dietary balance, sleep quality, and meeting participation time.

[0778] The generative model retrieves meeting data from employees' calendar information and adds it to the analysis.

[0779] Emotion data collection and analysis

[0780] Users collect emotion data using a facial recognition camera and voice recognition.

[0781] For example, every day at 3 p.m., a facial recognition camera will photograph your face and collect emotional data.

[0782] The emotion engine analyzes the collected emotion data, quantifies it, and stores it on the server.

[0783] Fatigue assessment and suggestion generation

[0784] The server calculates a fatigue score based on the analysis results, and if this exceeds a certain threshold, it generates suggestions for taking time off or adjusting work schedules.

[0785] Notification means

[0786] A notification means notifies the proposal to the terminals of employees and managers.

[0787] For example, every morning at 9 a.m., employees will receive a notification on their smartphones saying, "We recommend that you take Friday off."

[0788] Prompt Sentence Examples

[0789] Give instructions to the generative AI model using prompt sentences like the following:

[0790] "Design a program that evaluates employee fatigue levels based on employee health data (weight, diet, sleep, meeting attendance time, and emotional data) and generates vacation recommendations and work adjustment suggestions."

[0791] This will enable the realization of a system that can effectively monitor employees' health by comprehensively taking into account not only physical data but also emotional data, meeting data, etc., and recommend vacation time and work adjustments at the appropriate time.

[0792] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0793] Step 1: Data collection

[0794] The user wears a smartwatch and collects weight, diet, and sleep data in their daily lives.

[0795] Input: Biometric data collected from the user's daily life.

[0796] Specific operation: Every morning, the user steps on the scale to measure their weight and manually enters their dietary data using a dedicated app.

[0797] Output: Collected weight data, dietary data, and sleep data are recorded on the smartwatch.

[0798] Step 2: Send and save data

[0799] The device automatically sends the collected data to the server at a set time. The data is encrypted.

[0800] Input: Data transferred from the smartwatch (weight data, diet data, sleep data).

[0801] Specific operation: The smartphone uploads data to the server at 1:00 AM every day.

[0802] Output: Data encrypted and stored on the server.

[0803] Step 3: Data analysis

[0804] The server stores the received data and analyzes it using a generative AI model.

[0805] Input: Weight data, dietary data, and sleep data stored on the server.

[0806] What it does: The server uses machine learning algorithms to analyze the data and calculate a fatigue score.

[0807] Output: Fatigue score based on weight fluctuations, dietary balance, and sleep quality.

[0808] Step 4: Collecting emotion data

[0809] Users collect emotional data using facial recognition cameras and voice recognition.

[0810] Input: Emotion data from the user's face recognition camera and voice recognition device.

[0811] Specific operation: The user takes a picture of their face with a facial recognition camera at 3:00 pm every day to collect emotional data.

[0812] Output: The collected emotion data is recorded on a smart device.

[0813] Step 5: Analyze the sentiment data

[0814] The emotion engine analyzes the collected emotion data, quantifies it, and stores it on the server.

[0815] Input: Emotion data transferred from smart devices.

[0816] Specific operation: The emotion engine analyzes facial expressions and voice to quantify the user's emotional state.

[0817] Output: The analysis results are sent to the server as numerical data and saved.

[0818] Step 6: Fatigue assessment and generation of recommendations

[0819] The server calculates a fatigue score based on the analysis results, and if this exceeds a certain threshold, generates a suggestion.

[0820] Input: Weight data, dietary data, sleep data, emotion data stored on the server, and analysis results from the generative model.

[0821] How it works: The server analyzes all data and uses a generative model to calculate a fatigue score. If the score exceeds a threshold, it generates suggestions for taking time off or adjusting work schedules.

[0822] Output: Data including fatigue score and suggested sentence.

[0823] Step 7: Notification methods

[0824] A notification means notifies the proposal to the terminals of employees and managers.

[0825] Input: Proposal and notification data from the server.

[0826] What it does: Employees will receive a notification on their smartphones saying, "We recommend you take time off on Friday." Managers will also receive a related report.

[0827] Output: Notifications displayed on employee and manager devices.

[0828] The above process allows for detailed and comprehensive monitoring of employee health status, allowing timely recommendations for leave and work adjustments to be made.

[0829] (Application example 2)

[0830] 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."

[0831] In factory environments, it is difficult to monitor workers' health in real time and schedule appropriate leave and work adjustments. This can lead to accumulated fatigue and stress, which can lead to increased accidents and reduced production efficiency. Conventional systems only collect single data such as body temperature and heart rate, making it difficult to accurately assess workers' overall health. Furthermore, because fatigue assessments do not take into account changes in emotional state, workers' mental health is often overlooked.

[0832] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting body temperature data, heart rate data, blood pressure data, voice data, and facial expression data obtained from a data collection device, means for transmitting the data collected from the data collection device to the server, means for analyzing the data stored in the server using a generative model and calculating a fatigue score, means for collecting emotion data from voice and facial expression using an emotion analysis engine and reflecting the emotion data in the fatigue score, and means for generating and notifying suggestions for taking vacation or adjusting work schedules in real time based on the fatigue score. This enables a comprehensive evaluation of workers' health conditions in real time, and enables improved production efficiency and reduced accidents through appropriate vacation and work schedule adjustments.

[0833] "Employee health status" refers to the physical and mental condition of workers, specifically body temperature, heart rate, blood pressure, quality of sleep, diet, emotional state, etc.

[0834] "Data collection devices" are equipment used to collect employee health data, specifically wearable devices such as smartwatches and smart helmets.

[0835] "Server" refers to a computer system that is capable of storing and analyzing collected data and is used to centrally manage and analyze collected data.

[0836] "Generative model" refers to a mathematical model that uses machine learning algorithms to analyze data and calculate a fatigue score.

[0837] The "fatigue score" is a numerical representation of an employee's level of fatigue, calculated by taking into account factors such as body temperature, heart rate, blood pressure, time spent in meetings, and emotional data.

[0838] An "emotion analysis engine" refers to software that analyzes voice data and facial expression data to quantify an employee's emotional state.

[0839] "Emotional data" refers to numerical or categorical data that express an employee's emotional state, and is obtained using voice analysis and facial recognition technology.

[0840] "Leave and work adjustment suggestions" refers to specific recommendations for appropriate leave and work schedule adjustments based on an employee's fatigue score.

[0841] The system of the present invention is designed to monitor the health status of factory workers in real time and promote appropriate leave taking and work adjustments. The system includes a data collection device, a server, a generative model, a notification means, and a sentiment analysis engine.

[0842] System Components and Operation

[0843] 1. Data Collection Equipment

[0844] The user wears a smart helmet equipped with temperature sensors, heart rate sensors, blood pressure sensors, a microphone, and a camera, which collects data on body temperature, heart rate, blood pressure, voice, and facial expression. This data is then sent to the user's smartphone via Bluetooth.

[0845] 2. Data transmission and storage

[0846] The collected data is sent to a server daily. The data is encrypted to protect the privacy of the data. The server associates the received data with each user's ID and stores it in a database.

[0847] 3. Data Analysis

[0848] The server periodically extracts the stored data and analyzes it based on a generative model. The generative model is designed using machine learning algorithms and comprehensively evaluates body temperature, heart rate, blood pressure, meeting participation time, emotional data, etc. to calculate a fatigue score. The server also evaluates how much time the user is spending in meetings.

[0849] 4. Sentiment Analysis Engine and Sentiment Evaluation

[0850] The user periodically collects emotional data using the microphone and camera in the smart helmet. The emotion analysis engine uses voice analysis and facial recognition technology to recognize the user's emotional state, converting it into a numerical value and storing it. The server stores the emotional data collected by the emotion analysis engine in a database and reflects it in the calculation of the fatigue score.

[0851] 5. Fatigue assessment and suggestions

[0852] The server evaluates the fatigue state of each user based on the fatigue score calculated by the generative model. If the fatigue score exceeds a certain threshold, it generates suggestions for taking vacation or adjusting work schedules and notifies the user via a notification method on their smartphone. For example, it may send a notification to the user saying, "We recommend taking vacation this Friday." It may also send a report to management saying, "Worker A's fatigue level is high, and weekend vacation is recommended."

[0853] Specific examples

[0854] Below is an example of a day's work and data processing.

[0855] 7:00 AM - Temperature data collection

[0856] After waking up, the user puts on the smart helmet and measures their body temperature.

[0857] Body temperature data is automatically recorded on a smartphone.

[0858] 13:00 noon - Heart rate data collection

[0859] After lunch, the user measures his / her heart rate.

[0860] Heart rate data is stored on your smartphone.

[0861] 15:00 noon - Emotion data collection

[0862] The user collects emotion data using the camera in the smart helmet.

[0863] The emotion analysis engine analyzes the emotion data, converts it into numbers, and sends it to the server.

[0864] 10:00 PM - Blood pressure data collection

[0865] The smart helmet measures the user's blood pressure before they go to sleep.

[0866] Blood pressure data is automatically synced to your smartphone.

[0867] 1:00 the next day - Data transmission and storage

[0868] The smartphone sends the collected data to the server daily.

[0869] The server associates the received data with each user's ID and stores it in a database.

[0870] 3:00 the next day - Data analysis

[0871] The server extracts the stored data and calculates a fatigue score using a generative model.

[0872] 9:00 the next day - Suggestions and notifications

[0873] The server generates suggestions based on the fatigue score and sends notifications such as "take vacation recommended" to the user and manager.

[0874] Prompt Sentence Examples

[0875] "Predict the user's fatigue level based on the following data: Body temperature: 36.5, Heart rate: 80, Blood pressure: 120 / 80, Emotion score: 7"

[0876] In this way, by combining it with an emotion analysis engine, it is possible to monitor the health status of factory workers in more detail and make timely recommendations for leave and work adjustments.

[0877] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0878] Step 1:

[0879] The user wears a smart helmet and collects data on body temperature, heart rate, blood pressure, voice, and facial expression. The various sensors in the smart helmet record this data in real time. The input is the signal from the various sensors, and the output is the raw health data recorded in the smart helmet.

[0880] Step 2:

[0881] The terminal (user's smartphone) receives health data collected from the smart helmet via Bluetooth and temporarily stores it. The input is raw data from the smart helmet, and the output is data stored on the smartphone.

[0882] Step 3:

[0883] The device sends all collected data to the server at a set time each day. The data is encrypted before being sent. The input is the data stored on the smartphone, and the output is the encrypted data stored on the server.

[0884] Step 4:

[0885] The server associates the received data with each user's ID and stores it in a database. The input is encrypted data, and the output is the data for each user stored in the database.

[0886] Step 5:

[0887] The server periodically extracts user data from the database and analyzes it using a generative model. The generative model is designed using a machine learning algorithm and comprehensively evaluates body temperature, heart rate, blood pressure, meeting participation time, emotional data, etc. to calculate a fatigue score. The input is the data extracted from the database, and the output is the calculated fatigue score.

[0888] Step 6:

[0889] The server uses an emotion analysis engine to collect emotion data from voice data and facial expression data and integrate it into a generative model. The emotion analysis engine quantifies the emotion data using voice recognition and facial recognition technology. The input is voice data and facial expression data, and the output is quantified emotion data.

[0890] Step 7:

[0891] The server incorporates the emotional data into the fatigue score calculation to generate a more accurate fatigue score. The input is the quantified emotional data and other health data, and the output is an updated fatigue score.

[0892] Step 8:

[0893] The server generates suggestions for taking time off or adjusting work schedules based on the fatigue score calculated by the generative model. The input is the fatigue score, and the output is suggestions for taking time off or adjusting work schedules.

[0894] Step 9:

[0895] The server notifies the generated proposals to the user's and manager's devices. Specific proposals for taking leave or adjusting work schedules are sent to the user's smartphone via the notification means. The input is the proposal content, and the output is a notification displayed on the user's and manager's device.

[0896] Through these steps, a system will be created that comprehensively assesses workers' health status in real time and suggests appropriate leave and work adjustments as needed.

[0897] 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.

[0898] 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.

[0899] 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.

[0900] [Third embodiment]

[0901] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0902] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0903] 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).

[0904] 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.

[0905] 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.

[0906] 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).

[0907] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for 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.

[0908] 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.

[0909] 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.

[0910] 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.

[0911] 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.

[0912] 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."

[0913] The system of the present invention is designed to monitor employee health status and promote appropriate leave taking and work adjustments. This system includes a data collection device, a server, a generative model, and a notification means. The following describes in detail how this system is implemented.

[0914] System Components and Operation

[0915] 1. Data Collection Equipment

[0916] User: Each employee wears a smartwatch, which collects weight, diet, and sleep data.

[0917] Device: The data collected by the smartwatch is automatically sent to employees' smartphones or tablets. Employees can also manually enter meal data using a dedicated app.

[0918] 2. Data transmission and storage

[0919] Device: At a set time each day, all collected data is sent to the server. The data is encrypted and transmitted to protect the privacy of the data.

[0920] Server: The server associates the received data with each employee's ID and stores it in a database, allowing all of each employee's weight, diet, and sleep data to be managed centrally.

[0921] 3. Data Analysis

[0922] Server: The server periodically extracts the stored data and analyzes it according to a generative model, which is designed using machine learning algorithms to calculate a fatigue score by taking into account weight fluctuations, dietary balance, sleep quality, and meeting participation time.

[0923] Generative model: Meeting data is taken from each employee's calendar information and added to the analysis. This meeting data is important for assessing how much time employees spend in meetings.

[0924] 4. Fatigue assessment and suggestions

[0925] Server: Evaluates the fatigue level of each employee based on the fatigue score calculated by the generative model. If the fatigue score exceeds a certain threshold, it generates suggestions for taking time off or adjusting work schedules.

[0926] Notification method: The server notifies the generated proposal to the employee and manager's devices. For example, a notification such as "We recommend you take a vacation this Friday" is sent to the employee's smartphone. Also, a report is sent to the manager saying, "Employee A is highly fatigued and we recommend that he take a weekend vacation."

[0927] Specific examples

[0928] Daily flow and data processing example

[0929] 7:00 AM - Weight data collection

[0930] User: After waking up, an employee steps on a scale linked to a smartwatch to measure their weight.

[0931] Device: Weight data is automatically recorded on your smartphone.

[0932] 13:00 noon - Collection of dietary data

[0933] User: After employees have lunch, they enter their meal details using a dedicated app.

[0934] Device: The entered meal data is saved on your smartphone.

[0935] 10:00 PM - Sleep data collection

[0936] User: Employees start sleep tracking on their smartwatch before going to bed.

[0937] Device: The smartwatch records your sleep data and syncs it to your smartphone the next morning.

[0938] 1:00 the next day - Data transmission and storage

[0939] Device: The smartphone sends the collected data to the server daily.

[0940] Server: The received data is linked to each employee's ID and stored in a database.

[0941] 3:00 the next day - Data analysis

[0942] Server: Extracts the stored data and calculates the fatigue score using a generative model.

[0943] 9:00 the next day - Suggestions and notifications

[0944] Server: Generates suggestions based on fatigue scores and sends notifications such as "Take time off recommended" to employees and managers.

[0945] In this way, a system can be created that supports the physical and mental health of employees by continuously and in detail monitoring their health status and recommending time off or work adjustments at the appropriate time.

[0946] The processing flow will be explained below.

[0947] Step 1: Data collection

[0948] User: Wears the smartwatch, weighs himself on a scale, manually enters his food intake into the app, and starts sleep tracking before going to bed.

[0949] Device: The smartwatch records weight, food, and sleep data, which is automatically synced to the user's smartphone.

[0950] Step 2: Send data

[0951] Device: At the end of each day, collected weight, food, and sleep data is sent to a server. The data is encrypted to protect privacy.

[0952] Step 3: Save data

[0953] Server: The received data is linked to each user's ID and stored in a database. The stored data includes date, weight, dietary details, and sleep information.

[0954] Step 4: Data Preprocessing

[0955] Server: Periodically extracts the stored data and converts it into the format required for analysis, for example by aggregating daily data into weekly data.

[0956] Step 5: Analysis with generative models

[0957] Server: Data extracted from the database is fed into a generative model to comprehensively analyze sleep quality, dietary balance, weight fluctuations, meeting attendance times, and more.

[0958] Step 6: Calculating your fatigue score

[0959] Server: The generative model uses the data to calculate a fatigue score for each user, which serves as an indicator of the user's health status.

[0960] Step 7: Proposal Generation

[0961] Server: Generates suggestions for taking time off or adjusting work load based on the calculated fatigue score. Specifically, it recommends taking time off if the fatigue score is high, and suggests redistributing tasks if the workload is high.

[0962] Step 8: Sending notifications

[0963] Server: Notifies the user and manager of the proposed schedule. For example, a notification such as "We recommend you take vacation next Friday" is sent to the user's smartphone. In addition, a report is sent to the manager stating, "User A is experiencing high levels of fatigue, so please adjust his or her work schedule."

[0964] Step 9: Gather feedback

[0965] User: Acts on the suggestions and provides feedback on the results in a dedicated app. For example, if a user takes a vacation, the app records the user's physical condition and mood for that day.

[0966] Terminal: Collects user feedback data and reflects it in the next analysis process.

[0967] Through these steps, a system can be created that can maintain the physical and mental health of employees by continuously monitoring their health status and recommending time off or work adjustments at the appropriate time.

[0968] Example 1

[0969] 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."

[0970] In modern companies, continuously monitoring employee health and encouraging appropriate leave and work adjustments is a challenging issue. This issue directly impacts employee productivity and well-being, so it must be resolved quickly. Furthermore, traditional health monitoring systems often have low data collection and analysis efficiency, and lack the ability to provide personalized recommendations based on individual employee conditions.

[0971] 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.

[0972] In this invention, the server includes means for collecting weight data, dietary data, and sleep data obtained from a data collection device, means for encrypting the data collected from the data collection device and transmitting it to the server, means for analyzing the data stored in the server using a generative model to calculate a fatigue score, means for generating and notifying suggestions for taking vacation or adjusting work schedules based on the fatigue score, means for the server to periodically extract and analyze data, and means for the terminal to receive and display suggestions from the server to the user. This enables detailed monitoring of employee health conditions and makes it possible to make appropriate suggestions for taking vacation or adjusting work schedules based on individual circumstances.

[0973] "Data collection device" refers to equipment used to collect weight data, dietary data, and sleep data.

[0974] "Weight data" refers to information about employees' weight, and is primarily numerical data measured using devices such as smartwatches and scales.

[0975] "Dietary data" refers to information about employees' daily dietary habits, including calories and nutrients, which is collected through a dedicated app.

[0976] "Sleep data" refers to information about employees' sleep patterns and quality, primarily tracked by devices such as smartwatches.

[0977] A "server" is a computer system for storing and analyzing collected data.

[0978] "Encryption" is the technique of converting data into a special format to protect its privacy and security.

[0979] A "generative model" is a program that uses machine learning algorithms to analyze data and generate predictions and suggestions.

[0980] The "fatigue score" is an indicator of an employee's level of fatigue, calculated by analyzing weight data, dietary data, sleep data, etc.

[0981] "Suggestions" refer to recommendations to employees to take time off or adjust their work schedules based on their fatigue scores.

[0982] "Notification" is the act of sending information such as suggestions or warnings to employees and managers.

[0983] "Meeting data" refers to information about meetings listed on employees' calendars, including participation time and frequency.

[0984] "Terminal" refers to a mobile information terminal such as a smartphone or tablet, which is a device that collects, transmits, and receives notifications about data.

[0985] This invention is a system that monitors the health status of employees and encourages them to take appropriate leave and adjust their work schedules. The invention is implemented using a data collection device, a server, a generative model, a terminal, and a notification means.

[0986] Data collection equipment

[0987] User: Each employee wears a smartwatch that collects weight, diet, and sleep data.

[0988] Device: Data collected by the smartwatch is automatically sent to employees' smartphones or tablets. Employees can also manually enter meal data using a dedicated app.

[0989] Hardware: Smartwatches used include Apple Watch, Fitbit, and Garmin.

[0990] Software: A dedicated app (such as MyFitnessPal) is used to input dietary data.

[0991] Data transmission and storage

[0992] Device: The smartphone sends all collected data to the server at a set time each day. The data is encrypted and transmitted to protect privacy. This encryption is done using AES-256.

[0993] Server: The server associates the received data with each employee's ID and stores it in a database using MySQL or PostgreSQL.

[0994] Data analysis

[0995] Server: The server periodically extracts the stored data and analyzes it according to the generative model, which is designed using a machine learning algorithm and implemented in TensorFlow or PyTorch.

[0996] Generative model: Meeting data is taken from each employee's calendar information and added to the analysis. Meeting data is important for assessing how much time an employee spends in meetings.

[0997] Fatigue assessment and suggestions

[0998] Server: Evaluates the fatigue level of each employee based on the fatigue score calculated by the generative model. If the fatigue score exceeds a certain threshold, it generates suggestions for taking time off or adjusting work schedules.

[0999] Notification method: The server notifies the generated proposal to the employee and manager's devices. For example, a notification saying "We recommend you take a vacation this Friday" is sent to the employee's smartphone. Also, a report saying "Employee A is highly fatigued and we recommend that he / she take a weekend vacation" is sent to the manager.

[1000] Specific examples

[1001] Daily flow and data processing example

[1002] 7:00 AM - Weight data collection

[1003] User: After waking up, an employee steps on a scale linked to a smartwatch to measure their weight.

[1004] Device: Weight data is automatically recorded on your smartphone.

[1005] 13:00 noon - Collection of dietary data

[1006] User: After employees have lunch, they enter their meal details using a dedicated app.

[1007] Device: The entered meal data is saved on your smartphone.

[1008] 10:00 PM - Sleep data collection

[1009] User: Employees start sleep tracking on their smartwatch before going to bed.

[1010] Device: The smartwatch records your sleep data and syncs it to your smartphone the next morning.

[1011] 1:00 the next day - Data transmission and storage

[1012] Device: The smartphone sends the collected data to the server daily.

[1013] Server: The received data is linked to each employee's ID and stored in a database.

[1014] 3:00 the next day - Data analysis

[1015] Server: Extracts the stored data and calculates the fatigue score using a generative model.

[1016] 9:00 the next day - Suggestions and notifications

[1017] Server: Generates suggestions based on fatigue scores and sends notifications such as "Take time off recommended" to employees and managers.

[1018] An example of a prompt sentence is, "After lunch, please enter your meal data in the dedicated app. Then, based on the fatigue score you submit, we will notify you of suggestions for taking time off."

[1019] This invention supports the physical and mental health of employees by continuously and in detail monitoring their health status and recommending time off or work adjustments at the appropriate time.

[1020] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1021] Step 1: Data collection

[1022] Subject: User

[1023] Specific operations: The user steps on a scale connected to a smartwatch to measure their weight. After lunch, they manually enter their meal details using a dedicated app. Before going to bed, they start sleep tracking on the smartwatch.

[1024] Input: Weight data measured by a scale, food data entered into a dedicated app, and sleep data tracked by a smartwatch.

[1025] Output: The respective data is recorded on the smartwatch and smartphone.

[1026] Step 2: Send data

[1027] Subject: Device

[1028] How it works: The smartwatch sends the collected data to a smartphone via Bluetooth or Wi-Fi, and the smartphone encrypts and sends the data to a server daily.

[1029] Input: Weight data, food data, and sleep data sent from the smartwatch.

[1030] Output: The encrypted data is sent from the smartphone to the server.

[1031] Step 3: Receiving and storing data

[1032] Subject: Server

[1033] Specific operation: The server receives the encrypted data sent from the smartphone, verifies that the data format is correct, and then associates it with each employee's ID and stores it in a database.

[1034] Input: Encrypted weight data, diet data, sleep data, and employee ID information.

[1035] Output: Data associated with each employee's ID is saved in the database.

[1036] Step 4: Data extraction and analysis

[1037] Subject: Server

[1038] Specific operation: The server periodically extracts weight, diet, and sleep data for each employee from the database. The extracted data is passed to the generative model for analysis.

[1039] Input: Weight data, dietary data, and sleep data stored in a database.

[1040] Output: Fatigue score as the analysis result.

[1041] Step 5: Integrating Meeting Data

[1042] Subject: Generative Model

[1043] What it does: The generative model retrieves meeting data from an employee's calendar information and adds it to the fatigue score analysis.

[1044] Input: Employee weight data, diet data, sleep data, and calendar meeting data.

[1045] Output: A calculated fatigue score based on the combined data.

[1046] Step 6: Fatigue assessment and recommendations

[1047] Subject: Server

[1048] Specific operation: Evaluate each employee's fatigue level based on the fatigue score calculated by the generative model. If the fatigue score exceeds a certain threshold, generate suggestions for taking time off or adjusting work schedules.

[1049] Input: Fatigue score calculated by the generative model.

[1050] Output: Suggestions for taking leave or adjusting work schedules.

[1051] Step 7: Proposal Notification

[1052] Subject: Server

[1053] Specific operation: The server notifies the employee and manager of the proposal, including details of taking leave and adjusting work schedules.

[1054] Input: Generated leave and work adjustment proposals.

[1055] Output: Proposals sent as push notifications and emails to employee and manager devices.

[1056] In this way, a system can be created that continuously and in detail monitors employees' health status and makes timely recommendations for leave and work adjustments.

[1057] (Application example 1)

[1058] 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."

[1059] Conventional health monitoring systems have difficulty accurately assessing employee fatigue levels due to insufficient management of employee physical condition. Furthermore, relying solely on fixed data collection devices has the drawback of being unable to collect real-time health data on-site or quickly propose appropriate work adjustments. Accumulating worker fatigue, particularly in factories, can lead to reduced productivity and potentially adversely affect safety.

[1060] 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.

[1061] In this invention, the server includes means for collecting weight data, dietary data, and sleep data obtained from a data collection device, means for transmitting the data collected from the data collection device to the server, means for analyzing the data stored in the server using a generative model to calculate a fatigue score, means for generating and notifying suggestions for taking time off or adjusting work schedules based on the fatigue score, and means for collecting and transmitting additional health data obtained from a patrolling mobile robot. This allows for more detailed and real-time monitoring of employee health conditions, enabling appropriate and prompt suggestions for taking time off or adjusting work schedules.

[1062] A "data collection device" is a device worn by an employee to collect weight data, dietary data, sleep data, and the like.

[1063] A "smartwatch" is a type of data collection device that is worn on an employee's wrist and collects various types of biometric data.

[1064] The "mobile robot" is a robot that patrols the factory and collects health data from workers' smartwatches.

[1065] The "server" is a device that collects and stores various data, and is a central processing unit that calculates fatigue scores and generates suggestions using generative models.

[1066] A "generative model" is a machine learning algorithm used to analyze collected data and calculate an employee's fatigue score.

[1067] The "fatigue score" is a value indicating an employee's level of fatigue calculated by the generative model based on weight data, dietary data, sleep data, meeting data, etc.

[1068] "Suggestions for taking vacation or adjusting work schedules" are notifications that recommend taking vacation or adjusting work schedules to maintain employees' health based on their fatigue score.

[1069] The present invention is a system that monitors the health status of employees and encourages them to take appropriate vacations and adjust their work schedules. This system includes a data collection device, a mobile robot, a server, a generative model, and a notification means. The program processing of this system is described in detail below.

[1070] System components and operation description

[1071] 1. Data Collection Equipment

[1072] User: Employees wear smartwatches that collect weight, diet, and sleep data.

[1073] Device: The data collected by the smartwatch is automatically sent to employees' smartphones or tablets. Employees can also manually enter meal data using a dedicated app.

[1074] 2. Data transmission and storage

[1075] Device: All collected data is sent to the server on a daily basis. The data is encrypted and transmitted to protect the privacy of the data.

[1076] Server: The server associates the received data with each employee's ID and stores it in a database, allowing all of each employee's weight, diet, and sleep data to be managed centrally.

[1077] 3. Data Analysis with Generative Models

[1078] Server: The server periodically extracts the stored data and analyzes it according to a generative model, which is designed using machine learning algorithms to calculate a fatigue score by taking into account weight fluctuations, dietary balance, sleep quality, and meeting participation time.

[1079] Generative model: Data analysis also includes meeting data obtained from calendar information to more precisely assess employee fatigue levels.

[1080] 4. Fatigue assessment and suggestions

[1081] Server: Evaluates the fatigue level of each employee based on the fatigue score calculated by the generative model. If the fatigue score exceeds a certain threshold, it generates suggestions for taking time off or adjusting work schedules.

[1082] Notification method: The server notifies the generated suggestions to the employees' and managers' devices. For example, a notification such as "We recommend you take a vacation this Friday" is sent to the employee's smartphone. Also, a report is sent to the manager saying, "Employee A's fatigue level is high, so we recommend that he or she take a weekend vacation."

[1083] 5. Additional data collection by mobile robots

[1084] Robot: The robot roams the factory floor, collecting real-time health data from workers' smartwatches and transmitting it to a server using its own Wi-Fi module.

[1085] Hardware and software used

[1086] Hardware

[1087] Smartwatches: Apple Watch, Fitbit, etc.

[1088] Mobile robots: such as Fetch Robotics' Fetch Mobile Manipulator.

[1089] Server: Linux-based dedicated server.

[1090] software

[1091] Generative model: Python machine learning library (TensorFlow or PyTorch)

[1092] Database: MySQL, PostgreSQL, etc.

[1093] Notification method: Voice synthesis technology such as Google Text-to-Speech.

[1094] Specific examples

[1095] Example prompts for generative AI models

[1096] Create a generative model that calculates fatigue levels based on workers' health data and suggests appropriate breaks and work adjustments.

[1097] Data points:

[1098] Weight data: 70 kg

[1099] Dietary data: Calories 2000 kcal

[1100] Sleep data: 6 hours

[1101] prompt:

[1102] 1. How to calculate worker fatigue?

[1103] 2. How do you assess your daily workload?

[1104] 3. How do we create specific proposals for breaks and work adjustments?

[1105] This system allows for detailed and real-time monitoring of employee health conditions, enabling appropriate and prompt leave proposals and work adjustments, contributing to improved productivity throughout the factory and ensuring employee safety.

[1106] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1107] Step 1:

[1108] The user wears a smartwatch to collect weight, diet, and sleep data. The smartwatch collects this data in real time and automatically transmits it to a smartphone. The input is biometric data, and the output is data stored on the smartphone.

[1109] Step 2:

[1110] The smartphone, which is the terminal, periodically sends the collected data to the server on a daily basis. The data is encrypted to protect privacy. The input is the data stored on the smartphone, and the output is the encrypted data sent to the server.

[1111] Step 3:

[1112] The server links the received data to each employee's ID and stores it in a database. This allows the server to centrally manage weight data, dietary data, and sleep data. The input is encrypted health data, and the output is organized data stored in the database.

[1113] Step 4:

[1114] The server periodically extracts data from the database and analyzes it using a generative model. The generative model, which uses a machine learning algorithm, analyzes weight fluctuations, dietary balance, sleep quality, and meeting participation time to calculate a fatigue score. The input is each employee's health data and meeting data, and the output is a fatigue score.

[1115] Step 5:

[1116] Based on the fatigue score calculated by the generative model, the server evaluates the employee's fatigue state. If the fatigue score exceeds a certain threshold, the server generates suggestions for taking time off or adjusting work schedules. The input is the fatigue score, and the output is the suggestion.

[1117] Step 6:

[1118] As a notification method, the server notifies the generated suggestions to the devices of employees and managers. For example, a notification such as "We recommend you take vacation this Friday" is sent to an employee's smartphone. The input is the suggestion content, and the output is the notification to employees and managers.

[1119] Step 7:

[1120] The mobile robot patrols the factory and collects additional health data from the smartwatch. The robot transmits this data to a server via its WiFi module. The input is the real-time health data of employees, and the output is the data transmitted to the server.

[1121] Step 8:

[1122] The server receives additional health data sent from the mobile robot and stores it in a database. It also updates the fatigue score in real time by reflecting the additional data in the generative model. The input is the health data from the mobile robot, and the output is the updated data stored in the database.

[1123] 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.

[1124] The system of the present invention is designed to monitor employee health status and promote appropriate leave taking and work adjustments. This system includes a data collection device, a server, a generative model, a notification means, and an emotion engine. The following describes in detail how this system is implemented.

[1125] System Components and Operation

[1126] 1. Data Collection Equipment

[1127] User: Each employee wears a smartwatch, which collects weight, diet, and sleep data.

[1128] Device: The data collected by the smartwatch is automatically sent to employees' smartphones or tablets. Employees can also manually enter meal data using a dedicated app.

[1129] 2. Data transmission and storage

[1130] Device: At a set time each day, all collected data is sent to the server. The data is encrypted and transmitted to protect the privacy of the data.

[1131] Server: The server associates the received data with each employee's ID and stores it in a database, allowing all of each employee's weight, diet, and sleep data to be managed centrally.

[1132] 3. Data Analysis

[1133] Server: The server periodically extracts the stored data and analyzes it according to the generative model. The generative model is designed using a machine learning algorithm and calculates a fatigue score by taking into account weight fluctuations, dietary balance, sleep quality, and meeting participation time. Emotion data from the emotion engine is also analyzed.

[1134] Generative model: Meeting data is taken from each employee's calendar information and added to the analysis. This meeting data is important for assessing how much time employees spend in meetings.

[1135] 4. Emotion Engine and Emotion Evaluation

[1136] User: Emotional data is collected periodically via smartphone or PC using facial recognition cameras and voice recognition.

[1137] Emotion engine: Recognizes the user's emotions using voice and facial expression analysis, converts them into numerical values, and stores them.

[1138] Server: Emotion data collected by the emotion engine is stored in a database and reflected in the calculation of fatigue scores.

[1139] 5. Fatigue assessment and suggestions

[1140] Server: Evaluates the fatigue level of each employee based on the fatigue score calculated by the generative model. If the fatigue score exceeds a certain threshold, it generates suggestions for taking time off or adjusting work schedules.

[1141] Notification method: The server notifies the generated proposal to the employee and manager's devices. For example, a notification such as "We recommend you take a vacation this Friday" is sent to the employee's smartphone. Also, a report is sent to the manager saying, "Employee A is highly fatigued and we recommend that he take a weekend vacation."

[1142] Specific examples

[1143] Daily flow and data processing example

[1144] 7:00 AM - Weight data collection

[1145] User: After waking up, an employee steps on a scale linked to a smartwatch to measure their weight.

[1146] Device: Weight data is automatically recorded on your smartphone.

[1147] 13:00 noon - Collection of dietary data

[1148] User: After employees have lunch, they enter their meal details using a dedicated app.

[1149] Device: The entered meal data is saved on your smartphone.

[1150] 15:00 noon - Emotion data collection

[1151] User: Employees use facial recognition cameras to collect emotional data.

[1152] Emotion engine: Analyzes emotional data, converts the user's emotional state into a numerical value, and sends it to the server.

[1153] 10:00 PM - Sleep data collection

[1154] User: Employees start sleep tracking on their smartwatch before going to bed.

[1155] Device: The smartwatch records your sleep data and syncs it to your smartphone the next morning.

[1156] 1:00 the next day - Data transmission and storage

[1157] Device: The smartphone sends the collected data to the server daily.

[1158] Server: The received data is linked to each employee's ID and stored in a database.

[1159] 3:00 the next day - Data analysis

[1160] Server: Extracts the stored data and calculates a fatigue score using a generative model. Emotional data is also included in the analysis to calculate a more accurate fatigue score.

[1161] 9:00 the next day - Suggestions and notifications

[1162] Server: Generates suggestions based on fatigue scores and sends notifications such as "Take time off recommended" to employees and managers.

[1163] In this way, by combining the emotion engine, a system can be created that can monitor employees' health in more detail and recommend time off or work adjustments at the appropriate time, thereby more effectively maintaining employees' physical and mental health.

[1164] The processing flow will be explained below.

[1165] Step 1: Data collection

[1166] User: Wears the smartwatch, weighs himself on a scale, manually enters his food intake into the app, and starts sleep tracking before going to bed.

[1167] Device: The smartwatch records weight, food, and sleep data, which is automatically synced to the user's smartphone.

[1168] Step 2: Collecting emotion data

[1169] User: Emotion data is collected periodically using a facial recognition camera or voice input. For example, the user records emotion data in front of the camera at 3:00 PM every day.

[1170] Emotion engine: Recognizes the user's emotions using voice and facial expression analysis, and generates numerical data.

[1171] Step 3: Send data

[1172] Device: At the end of each day, collected weight, food, sleep, and emotional data is sent to a server. The data is encrypted to protect privacy.

[1173] Step 4: Save Data

[1174] Server: The received data is linked to each user's ID and stored in a database. The stored data includes date, weight, dietary details, sleep information, and emotional data.

[1175] Step 5: Data Preprocessing

[1176] Server: Periodically extracts the stored data and converts it into the format required for analysis, for example by aggregating daily data into weekly data.

[1177] Step 6: Analysis with generative models

[1178] Server: Data extracted from the database is fed into a generative model to comprehensively analyze sleep quality, dietary balance, weight fluctuations, meeting attendance times, emotional data, and more.

[1179] Step 7: Calculating your fatigue score

[1180] Server: The generative model uses the data to calculate a fatigue score for each user, which serves as an indicator of the user's health status.

[1181] Step 8: Proposal Generation

[1182] Server: Generates suggestions for taking time off or adjusting work load based on the calculated fatigue score. Specifically, it recommends taking time off if the fatigue score is high, and suggests redistributing tasks if the workload is high.

[1183] Step 9: Sending notifications

[1184] Server: Notifies the user and manager of the proposed schedule. For example, a notification such as "We recommend you take vacation next Friday" is sent to the user's smartphone. In addition, a report is sent to the manager stating, "User A is experiencing high levels of fatigue, so please adjust his or her work schedule."

[1185] Step 10: Gather feedback

[1186] User: Acts on the suggestions and provides feedback on the results in a dedicated app. For example, if a user takes a vacation, the app records the user's physical condition and mood for that day.

[1187] Terminal: Collects user feedback data and reflects it in the next analysis process.

[1188] Through these steps, a system can be built that can maintain the physical and mental health of employees by continuously monitoring their health status and recommending time off or work adjustments at the appropriate time.The addition of an emotion engine will also enable more detailed health management by evaluating fluctuations in emotional stress and happiness.

[1189] Example 2

[1190] 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."

[1191] It is important to centrally monitor employees' health and make suggestions for appropriate leave and work adjustments. However, conventional systems only collect and analyze physical data such as weight, diet, and sleep, and do not take into account factors such as emotional data or meeting participation status, making it difficult to accurately and comprehensively assess fatigue levels.

[1192] The identification process by the identification 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 weight data, dietary data, and sleep data obtained from a data collection device, means for transmitting the data collected from the data collection device to the server, means for analyzing the data stored in the server using a generative model and calculating a fatigue score, means for generating and notifying suggestions for taking vacation or adjusting work schedules based on the fatigue score, and means for collecting emotion data using face recognition and voice recognition, analyzing the data using an emotion engine, and reflecting the results in the fatigue score. This enables a more accurate and comprehensive fatigue assessment by comprehensively taking into account not only physical data but also emotion data, meeting data, and the like.

[1193] A "data collection device" is a device used to collect employee weight data, dietary data, sleep data, emotional data, etc., and specifically refers to a smartwatch or dedicated application.

[1194] The "server" is a computer system that stores collected data, analyzes it using a generative model, and calculates a fatigue score.

[1195] A "generative model" is a program that uses machine learning algorithms to analyze collected data and calculate a fatigue score, taking into account factors such as weight fluctuations, dietary balance, sleep quality, and meeting attendance time.

[1196] The "fatigue score" is a numerical representation of an employee's health status, and is an index calculated using a generative model based on weight data, dietary data, sleep data, emotional data, and meeting data.

[1197] "Notification method" refers to the means used to notify employees and managers of generated vacation and work adjustment proposals, specifically notifications sent to smartphones, tablets, and PCs.

[1198] The "emotion engine" is a program that analyzes emotional data collected using facial and voice recognition technology, quantifies it, and reflects it in a fatigue score.

[1199] MODE FOR CARRYING OUT THE INVENTION

[1200] The present invention is a system designed to monitor the health status of employees and encourage them to take appropriate leave and adjust their work schedules. How the system is implemented will be explained below.

[1201] Hardware and software used

[1202] The system includes the following components:

[1203] Data collection device: smartwatch, dedicated application

[1204] Server: a computer system that stores and analyzes data

[1205] Generative model: a program that implements a machine learning algorithm

[1206] Emotion Engine: An emotion analysis program using facial and voice recognition technology

[1207] Notification method: smartphone, tablet, PC

[1208] Examples of data collection devices

[1209] The user wears a smartwatch and collects weight, diet, and sleep data in their daily lives.

[1210] For example, every morning a user steps on a scale linked to a smartwatch to measure their weight.

[1211] Users manually enter their meal data using a dedicated app.

[1212] Data transmission and storage

[1213] The device (smartphone or tablet) automatically sends the collected data to the server at a set time. The data is encrypted to protect privacy.

[1214] For example, every day at 1:00 AM, your smartphone sends all the data collected during the day to a server.

[1215] Data analysis

[1216] The server stores the received data and analyzes it using a generative model. A machine learning algorithm is used to calculate a fatigue score based on weight fluctuations, dietary balance, sleep quality, and meeting participation time.

[1217] The generative model retrieves meeting data from employees' calendar information and adds it to the analysis.

[1218] Emotion data collection and analysis

[1219] Users collect emotion data using a facial recognition camera and voice recognition.

[1220] For example, every day at 3 p.m., a facial recognition camera will photograph your face and collect emotional data.

[1221] The emotion engine analyzes the collected emotion data, quantifies it, and stores it on the server.

[1222] Fatigue assessment and suggestion generation

[1223] The server calculates a fatigue score based on the analysis results, and if this exceeds a certain threshold, it generates suggestions for taking time off or adjusting work schedules.

[1224] Notification means

[1225] A notification means notifies the proposal to the terminals of employees and managers.

[1226] For example, every morning at 9 a.m., employees will receive a notification on their smartphones saying, "We recommend that you take Friday off."

[1227] Prompt Sentence Examples

[1228] Give instructions to the generative AI model using prompt sentences like the following:

[1229] "Design a program that evaluates employee fatigue levels based on employee health data (weight, diet, sleep, meeting attendance time, and emotional data) and generates vacation recommendations and work adjustment suggestions."

[1230] This will enable the realization of a system that can effectively monitor employees' health by comprehensively taking into account not only physical data but also emotional data, meeting data, etc., and recommend vacation time and work adjustments at the appropriate time.

[1231] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1232] Step 1: Data collection

[1233] The user wears a smartwatch and collects weight, diet, and sleep data in their daily lives.

[1234] Input: Biometric data collected from the user's daily life.

[1235] Specific operation: Every morning, the user steps on the scale to measure their weight and manually enters their dietary data using a dedicated app.

[1236] Output: Collected weight data, dietary data, and sleep data are recorded on the smartwatch.

[1237] Step 2: Send and save data

[1238] The device automatically sends the collected data to the server at a set time. The data is encrypted.

[1239] Input: Data transferred from the smartwatch (weight data, diet data, sleep data).

[1240] Specific operation: The smartphone uploads data to the server at 1:00 AM every day.

[1241] Output: Data encrypted and stored on the server.

[1242] Step 3: Data analysis

[1243] The server stores the received data and analyzes it using a generative AI model.

[1244] Input: Weight data, dietary data, and sleep data stored on the server.

[1245] What it does: The server uses machine learning algorithms to analyze the data and calculate a fatigue score.

[1246] Output: Fatigue score based on weight fluctuations, dietary balance, and sleep quality.

[1247] Step 4: Collecting emotion data

[1248] Users collect emotional data using facial recognition cameras and voice recognition.

[1249] Input: Emotion data from the user's face recognition camera and voice recognition device.

[1250] Specific operation: The user takes a picture of their face with a facial recognition camera at 3:00 pm every day to collect emotional data.

[1251] Output: The collected emotion data is recorded on a smart device.

[1252] Step 5: Analyze the sentiment data

[1253] The emotion engine analyzes the collected emotion data, quantifies it, and stores it on the server.

[1254] Input: Emotion data transferred from smart devices.

[1255] Specific operation: The emotion engine analyzes facial expressions and voice to quantify the user's emotional state.

[1256] Output: The analysis results are sent to the server as numerical data and saved.

[1257] Step 6: Fatigue assessment and generation of recommendations

[1258] The server calculates a fatigue score based on the analysis results, and if this exceeds a certain threshold, generates a suggestion.

[1259] Input: Weight data, dietary data, sleep data, emotion data stored on the server, and analysis results from the generative model.

[1260] How it works: The server analyzes all data and uses a generative model to calculate a fatigue score. If the score exceeds a threshold, it generates suggestions for taking time off or adjusting work schedules.

[1261] Output: Data including fatigue score and suggested sentence.

[1262] Step 7: Notification methods

[1263] A notification means notifies the proposal to the terminals of employees and managers.

[1264] Input: Proposal and notification data from the server.

[1265] What it does: Employees will receive a notification on their smartphones saying, "We recommend you take time off on Friday." Managers will also receive a related report.

[1266] Output: Notifications displayed on employee and manager devices.

[1267] The above process allows for detailed and comprehensive monitoring of employee health status, allowing timely recommendations for leave and work adjustments to be made.

[1268] (Application example 2)

[1269] 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."

[1270] In factory environments, it is difficult to monitor workers' health in real time and schedule appropriate leave and work adjustments. This can lead to accumulated fatigue and stress, which can lead to increased accidents and reduced production efficiency. Conventional systems only collect single data such as body temperature and heart rate, making it difficult to accurately assess workers' overall health. Furthermore, because fatigue assessments do not take into account changes in emotional state, workers' mental health is often overlooked.

[1271] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting body temperature data, heart rate data, blood pressure data, voice data, and facial expression data obtained from a data collection device, means for transmitting the data collected from the data collection device to the server, means for analyzing the data stored in the server using a generative model and calculating a fatigue score, means for collecting emotion data from voice and facial expression using an emotion analysis engine and reflecting the emotion data in the fatigue score, and means for generating and notifying suggestions for taking vacation or adjusting work schedules in real time based on the fatigue score. This enables a comprehensive evaluation of workers' health conditions in real time, and enables improved production efficiency and reduced accidents through appropriate vacation and work schedule adjustments.

[1272] "Employee health status" refers to the physical and mental condition of workers, specifically body temperature, heart rate, blood pressure, quality of sleep, diet, emotional state, etc.

[1273] "Data collection devices" are equipment used to collect employee health data, specifically wearable devices such as smartwatches and smart helmets.

[1274] "Server" refers to a computer system that is capable of storing and analyzing collected data and is used to centrally manage and analyze collected data.

[1275] "Generative model" refers to a mathematical model that uses machine learning algorithms to analyze data and calculate a fatigue score.

[1276] The "fatigue score" is a numerical representation of an employee's level of fatigue, calculated by taking into account factors such as body temperature, heart rate, blood pressure, time spent in meetings, and emotional data.

[1277] An "emotion analysis engine" refers to software that analyzes voice data and facial expression data to quantify an employee's emotional state.

[1278] "Emotional data" refers to numerical or categorical data that express an employee's emotional state, and is obtained using voice analysis and facial recognition technology.

[1279] "Leave and work adjustment suggestions" refers to specific recommendations for appropriate leave and work schedule adjustments based on an employee's fatigue score.

[1280] The system of the present invention is designed to monitor the health status of factory workers in real time and promote appropriate leave taking and work adjustments. The system includes a data collection device, a server, a generative model, a notification means, and a sentiment analysis engine.

[1281] System Components and Operation

[1282] 1. Data Collection Equipment

[1283] The user wears a smart helmet equipped with temperature sensors, heart rate sensors, blood pressure sensors, a microphone, and a camera, which collects data on body temperature, heart rate, blood pressure, voice, and facial expression. This data is then sent to the user's smartphone via Bluetooth.

[1284] 2. Data transmission and storage

[1285] The collected data is sent to a server daily. The data is encrypted to protect the privacy of the data. The server associates the received data with each user's ID and stores it in a database.

[1286] 3. Data Analysis

[1287] The server periodically extracts the stored data and analyzes it based on a generative model. The generative model is designed using machine learning algorithms and comprehensively evaluates body temperature, heart rate, blood pressure, meeting participation time, emotional data, etc. to calculate a fatigue score. The server also evaluates how much time the user is spending in meetings.

[1288] 4. Sentiment Analysis Engine and Sentiment Evaluation

[1289] The user periodically collects emotional data using the microphone and camera in the smart helmet. The emotion analysis engine uses voice analysis and facial recognition technology to recognize the user's emotional state, converting it into a numerical value and storing it. The server stores the emotional data collected by the emotion analysis engine in a database and reflects it in the calculation of the fatigue score.

[1290] 5. Fatigue assessment and suggestions

[1291] The server evaluates the fatigue state of each user based on the fatigue score calculated by the generative model. If the fatigue score exceeds a certain threshold, it generates suggestions for taking vacation or adjusting work schedules and notifies the user via a notification method on their smartphone. For example, it may send a notification to the user saying, "We recommend taking vacation this Friday." It may also send a report to management saying, "Worker A's fatigue level is high, and weekend vacation is recommended."

[1292] Specific examples

[1293] Below is an example of a day's work and data processing.

[1294] 7:00 AM - Temperature data collection

[1295] After waking up, the user puts on the smart helmet and measures their body temperature.

[1296] Body temperature data is automatically recorded on a smartphone.

[1297] 13:00 noon - Heart rate data collection

[1298] After lunch, the user measures his / her heart rate.

[1299] Heart rate data is stored on your smartphone.

[1300] 15:00 noon - Emotion data collection

[1301] The user collects emotion data using the camera in the smart helmet.

[1302] The emotion analysis engine analyzes the emotion data, converts it into numbers, and sends it to the server.

[1303] 10:00 PM - Blood pressure data collection

[1304] The smart helmet measures the user's blood pressure before they go to sleep.

[1305] Blood pressure data is automatically synced to your smartphone.

[1306] 1:00 the next day - Data transmission and storage

[1307] The smartphone sends the collected data to the server daily.

[1308] The server associates the received data with each user's ID and stores it in a database.

[1309] 3:00 the next day - Data analysis

[1310] The server extracts the stored data and calculates a fatigue score using a generative model.

[1311] 9:00 the next day - Suggestions and notifications

[1312] The server generates suggestions based on the fatigue score and sends notifications such as "take vacation recommended" to the user and manager.

[1313] Prompt Sentence Examples

[1314] "Predict the user's fatigue level based on the following data: Body temperature: 36.5, Heart rate: 80, Blood pressure: 120 / 80, Emotion score: 7"

[1315] In this way, by combining it with an emotion analysis engine, it is possible to monitor the health status of factory workers in more detail and make timely recommendations for leave and work adjustments.

[1316] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1317] Step 1:

[1318] The user wears a smart helmet and collects data on body temperature, heart rate, blood pressure, voice, and facial expression. The various sensors in the smart helmet record this data in real time. The input is the signal from the various sensors, and the output is the raw health data recorded in the smart helmet.

[1319] Step 2:

[1320] The terminal (user's smartphone) receives health data collected from the smart helmet via Bluetooth and temporarily stores it. The input is raw data from the smart helmet, and the output is data stored on the smartphone.

[1321] Step 3:

[1322] The device sends all collected data to the server at a set time each day. The data is encrypted before being sent. The input is the data stored on the smartphone, and the output is the encrypted data stored on the server.

[1323] Step 4:

[1324] The server associates the received data with each user's ID and stores it in a database. The input is encrypted data, and the output is the data for each user stored in the database.

[1325] Step 5:

[1326] The server periodically extracts user data from the database and analyzes it using a generative model. The generative model is designed using a machine learning algorithm and comprehensively evaluates body temperature, heart rate, blood pressure, meeting participation time, emotional data, etc. to calculate a fatigue score. The input is the data extracted from the database, and the output is the calculated fatigue score.

[1327] Step 6:

[1328] The server uses an emotion analysis engine to collect emotion data from voice data and facial expression data and integrate it into a generative model. The emotion analysis engine quantifies the emotion data using voice recognition and facial recognition technology. The input is voice data and facial expression data, and the output is quantified emotion data.

[1329] Step 7:

[1330] The server incorporates the emotional data into the fatigue score calculation to generate a more accurate fatigue score. The input is the quantified emotional data and other health data, and the output is an updated fatigue score.

[1331] Step 8:

[1332] The server generates suggestions for taking time off or adjusting work schedules based on the fatigue score calculated by the generative model. The input is the fatigue score, and the output is suggestions for taking time off or adjusting work schedules.

[1333] Step 9:

[1334] The server notifies the generated proposals to the user's and manager's devices. Specific proposals for taking leave or adjusting work schedules are sent to the user's smartphone via the notification means. The input is the proposal content, and the output is a notification displayed on the user's and manager's device.

[1335] Through these steps, a system will be created that comprehensively assesses workers' health status in real time and suggests appropriate leave and work adjustments as needed.

[1336] 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.

[1337] 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.

[1338] 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.

[1339] [Fourth embodiment]

[1340] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1341] 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.

[1342] 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).

[1343] 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.

[1344] 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.

[1345] 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).

[1346] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for 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.

[1347] 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.

[1348] 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.

[1349] 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.

[1350] 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.

[1351] 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.

[1352] 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."

[1353] The system of the present invention is designed to monitor employee health status and promote appropriate leave taking and work adjustments. This system includes a data collection device, a server, a generative model, and a notification means. The following describes in detail how this system is implemented.

[1354] System Components and Operation

[1355] 1. Data Collection Equipment

[1356] User: Each employee wears a smartwatch, which collects weight, diet, and sleep data.

[1357] Device: The data collected by the smartwatch is automatically sent to employees' smartphones or tablets. Employees can also manually enter meal data using a dedicated app.

[1358] 2. Data transmission and storage

[1359] Device: At a set time each day, all collected data is sent to the server. The data is encrypted and transmitted to protect the privacy of the data.

[1360] Server: The server associates the received data with each employee's ID and stores it in a database, allowing all of each employee's weight, diet, and sleep data to be managed centrally.

[1361] 3. Data Analysis

[1362] Server: The server periodically extracts the stored data and analyzes it according to a generative model, which is designed using machine learning algorithms to calculate a fatigue score by taking into account weight fluctuations, dietary balance, sleep quality, and meeting participation time.

[1363] Generative model: Meeting data is taken from each employee's calendar information and added to the analysis. This meeting data is important for assessing how much time employees spend in meetings.

[1364] 4. Fatigue assessment and suggestions

[1365] Server: Evaluates the fatigue level of each employee based on the fatigue score calculated by the generative model. If the fatigue score exceeds a certain threshold, it generates suggestions for taking time off or adjusting work schedules.

[1366] Notification method: The server notifies the generated proposal to the employee and manager's devices. For example, a notification such as "We recommend you take a vacation this Friday" is sent to the employee's smartphone. Also, a report is sent to the manager saying, "Employee A is highly fatigued and we recommend that he take a weekend vacation."

[1367] Specific examples

[1368] Daily flow and data processing example

[1369] 7:00 AM - Weight data collection

[1370] User: After waking up, an employee steps on a scale linked to a smartwatch to measure their weight.

[1371] Device: Weight data is automatically recorded on your smartphone.

[1372] 13:00 noon - Collection of dietary data

[1373] User: After employees have lunch, they enter their meal details using a dedicated app.

[1374] Device: The entered meal data is saved on your smartphone.

[1375] 10:00 PM - Sleep data collection

[1376] User: Employees start sleep tracking on their smartwatch before going to bed.

[1377] Device: The smartwatch records your sleep data and syncs it to your smartphone the next morning.

[1378] 1:00 the next day - Data transmission and storage

[1379] Device: The smartphone sends the collected data to the server daily.

[1380] Server: The received data is linked to each employee's ID and stored in a database.

[1381] 3:00 the next day - Data analysis

[1382] Server: Extracts the stored data and calculates the fatigue score using a generative model.

[1383] 9:00 the next day - Suggestions and notifications

[1384] Server: Generates suggestions based on fatigue scores and sends notifications such as "Take time off recommended" to employees and managers.

[1385] In this way, a system can be created that supports the physical and mental health of employees by continuously and in detail monitoring their health status and recommending time off or work adjustments at the appropriate time.

[1386] The processing flow will be explained below.

[1387] Step 1: Data collection

[1388] User: Wears the smartwatch, weighs himself on a scale, manually enters his food intake into the app, and starts sleep tracking before going to bed.

[1389] Device: The smartwatch records weight, food, and sleep data, which is automatically synced to the user's smartphone.

[1390] Step 2: Send data

[1391] Device: At the end of each day, collected weight, food, and sleep data is sent to a server. The data is encrypted to protect privacy.

[1392] Step 3: Save data

[1393] Server: The received data is linked to each user's ID and stored in a database. The stored data includes date, weight, dietary details, and sleep information.

[1394] Step 4: Data Preprocessing

[1395] Server: Periodically extracts the stored data and converts it into the format required for analysis, for example by aggregating daily data into weekly data.

[1396] Step 5: Analysis with generative models

[1397] Server: Data extracted from the database is fed into a generative model to comprehensively analyze sleep quality, dietary balance, weight fluctuations, meeting attendance times, and more.

[1398] Step 6: Calculating your fatigue score

[1399] Server: The generative model uses the data to calculate a fatigue score for each user, which serves as an indicator of the user's health status.

[1400] Step 7: Proposal Generation

[1401] Server: Generates suggestions for taking time off or adjusting work load based on the calculated fatigue score. Specifically, it recommends taking time off if the fatigue score is high, and suggests redistributing tasks if the workload is high.

[1402] Step 8: Sending notifications

[1403] Server: Notifies the user and manager of the proposed schedule. For example, a notification such as "We recommend you take vacation next Friday" is sent to the user's smartphone. In addition, a report is sent to the manager stating, "User A is experiencing high levels of fatigue, so please adjust his or her work schedule."

[1404] Step 9: Gather feedback

[1405] User: Acts on the suggestions and provides feedback on the results in a dedicated app. For example, if a user takes a vacation, the app records the user's physical condition and mood for that day.

[1406] Terminal: Collects user feedback data and reflects it in the next analysis process.

[1407] Through these steps, a system can be created that can maintain the physical and mental health of employees by continuously monitoring their health status and recommending time off or work adjustments at the appropriate time.

[1408] Example 1

[1409] 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."

[1410] In modern companies, continuously monitoring employee health and encouraging appropriate leave and work adjustments is a challenging issue. This issue directly impacts employee productivity and well-being, so it must be resolved quickly. Furthermore, traditional health monitoring systems often have low data collection and analysis efficiency, and lack the ability to provide personalized recommendations based on individual employee conditions.

[1411] 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.

[1412] In this invention, the server includes means for collecting weight data, dietary data, and sleep data obtained from a data collection device, means for encrypting the data collected from the data collection device and transmitting it to the server, means for analyzing the data stored in the server using a generative model to calculate a fatigue score, means for generating and notifying suggestions for taking vacation or adjusting work schedules based on the fatigue score, means for the server to periodically extract and analyze data, and means for the terminal to receive and display suggestions from the server to the user. This enables detailed monitoring of employee health conditions and makes it possible to make appropriate suggestions for taking vacation or adjusting work schedules based on individual circumstances.

[1413] "Data collection device" refers to equipment used to collect weight data, dietary data, and sleep data.

[1414] "Weight data" refers to information about employees' weight, and is primarily numerical data measured using devices such as smartwatches and scales.

[1415] "Dietary data" refers to information about employees' daily dietary habits, including calories and nutrients, which is collected through a dedicated app.

[1416] "Sleep data" refers to information about employees' sleep patterns and quality, primarily tracked by devices such as smartwatches.

[1417] A "server" is a computer system for storing and analyzing collected data.

[1418] "Encryption" is the technique of converting data into a special format to protect its privacy and security.

[1419] A "generative model" is a program that uses machine learning algorithms to analyze data and generate predictions and suggestions.

[1420] The "fatigue score" is an indicator of an employee's level of fatigue, calculated by analyzing weight data, dietary data, sleep data, etc.

[1421] "Suggestions" refer to recommendations to employees to take time off or adjust their work schedules based on their fatigue scores.

[1422] "Notification" is the act of sending information such as suggestions or warnings to employees and managers.

[1423] "Meeting data" refers to information about meetings listed on employees' calendars, including participation time and frequency.

[1424] "Terminal" refers to a mobile information terminal such as a smartphone or tablet, which is a device that collects, transmits, and receives notifications about data.

[1425] This invention is a system that monitors the health status of employees and encourages them to take appropriate leave and adjust their work schedules. The invention is implemented using a data collection device, a server, a generative model, a terminal, and a notification means.

[1426] Data collection equipment

[1427] User: Each employee wears a smartwatch that collects weight, diet, and sleep data.

[1428] Device: Data collected by the smartwatch is automatically sent to employees' smartphones or tablets. Employees can also manually enter meal data using a dedicated app.

[1429] Hardware: Smartwatches used include Apple Watch, Fitbit, and Garmin.

[1430] Software: A dedicated app (such as MyFitnessPal) is used to input dietary data.

[1431] Data transmission and storage

[1432] Device: The smartphone sends all collected data to the server at a set time each day. The data is encrypted and transmitted to protect privacy. This encryption is done using AES-256.

[1433] Server: The server associates the received data with each employee's ID and stores it in a database using MySQL or PostgreSQL.

[1434] Data analysis

[1435] Server: The server periodically extracts the stored data and analyzes it according to the generative model, which is designed using a machine learning algorithm and implemented in TensorFlow or PyTorch.

[1436] Generative model: Meeting data is taken from each employee's calendar information and added to the analysis. Meeting data is important for assessing how much time an employee spends in meetings.

[1437] Fatigue assessment and suggestions

[1438] Server: Evaluates the fatigue level of each employee based on the fatigue score calculated by the generative model. If the fatigue score exceeds a certain threshold, it generates suggestions for taking time off or adjusting work schedules.

[1439] Notification method: The server notifies the generated proposal to the employee and manager's devices. For example, a notification saying "We recommend you take a vacation this Friday" is sent to the employee's smartphone. Also, a report saying "Employee A is highly fatigued and we recommend that he / she take a weekend vacation" is sent to the manager.

[1440] Specific examples

[1441] Daily flow and data processing example

[1442] 7:00 AM - Weight data collection

[1443] User: After waking up, an employee steps on a scale linked to a smartwatch to measure their weight.

[1444] Device: Weight data is automatically recorded on your smartphone.

[1445] 13:00 noon - Collection of dietary data

[1446] User: After employees have lunch, they enter their meal details using a dedicated app.

[1447] Device: The entered meal data is saved on your smartphone.

[1448] 10:00 PM - Sleep data collection

[1449] User: Employees start sleep tracking on their smartwatch before going to bed.

[1450] Device: The smartwatch records your sleep data and syncs it to your smartphone the next morning.

[1451] 1:00 the next day - Data transmission and storage

[1452] Device: The smartphone sends the collected data to the server daily.

[1453] Server: The received data is linked to each employee's ID and stored in a database.

[1454] 3:00 the next day - Data analysis

[1455] Server: Extracts the stored data and calculates the fatigue score using a generative model.

[1456] 9:00 the next day - Suggestions and notifications

[1457] Server: Generates suggestions based on fatigue scores and sends notifications such as "Take time off recommended" to employees and managers.

[1458] An example of a prompt sentence is, "After lunch, please enter your meal data in the dedicated app. Then, based on the fatigue score you submit, we will notify you of suggestions for taking time off."

[1459] This invention supports the physical and mental health of employees by continuously and in detail monitoring their health status and recommending time off or work adjustments at the appropriate time.

[1460] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1461] Step 1: Data collection

[1462] Subject: User

[1463] Specific operations: The user steps on a scale connected to a smartwatch to measure their weight. After lunch, they manually enter their meal details using a dedicated app. Before going to bed, they start sleep tracking on the smartwatch.

[1464] Input: Weight data measured by a scale, food data entered into a dedicated app, and sleep data tracked by a smartwatch.

[1465] Output: The respective data is recorded on the smartwatch and smartphone.

[1466] Step 2: Send data

[1467] Subject: Device

[1468] How it works: The smartwatch sends the collected data to a smartphone via Bluetooth or Wi-Fi, and the smartphone encrypts and sends the data to a server daily.

[1469] Input: Weight data, food data, and sleep data sent from the smartwatch.

[1470] Output: The encrypted data is sent from the smartphone to the server.

[1471] Step 3: Receiving and storing data

[1472] Subject: Server

[1473] Specific operation: The server receives the encrypted data sent from the smartphone, verifies that the data format is correct, and then associates it with each employee's ID and stores it in a database.

[1474] Input: Encrypted weight data, diet data, sleep data, and employee ID information.

[1475] Output: Data associated with each employee's ID is saved in the database.

[1476] Step 4: Data extraction and analysis

[1477] Subject: Server

[1478] Specific operation: The server periodically extracts weight, diet, and sleep data for each employee from the database. The extracted data is passed to the generative model for analysis.

[1479] Input: Weight data, dietary data, and sleep data stored in a database.

[1480] Output: Fatigue score as the analysis result.

[1481] Step 5: Integrating Meeting Data

[1482] Subject: Generative Model

[1483] What it does: The generative model retrieves meeting data from an employee's calendar information and adds it to the fatigue score analysis.

[1484] Input: Employee weight data, diet data, sleep data, and calendar meeting data.

[1485] Output: A calculated fatigue score based on the combined data.

[1486] Step 6: Fatigue assessment and recommendations

[1487] Subject: Server

[1488] Specific operation: Evaluate each employee's fatigue level based on the fatigue score calculated by the generative model. If the fatigue score exceeds a certain threshold, generate suggestions for taking time off or adjusting work schedules.

[1489] Input: Fatigue score calculated by the generative model.

[1490] Output: Suggestions for taking leave or adjusting work schedules.

[1491] Step 7: Proposal Notification

[1492] Subject: Server

[1493] Specific operation: The server notifies the employee and manager of the proposal, including details of taking leave and adjusting work schedules.

[1494] Input: Generated leave and work adjustment proposals.

[1495] Output: Proposals sent as push notifications and emails to employee and manager devices.

[1496] In this way, a system can be created that continuously and in detail monitors employees' health status and makes timely recommendations for leave and work adjustments.

[1497] (Application example 1)

[1498] 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."

[1499] Conventional health monitoring systems have difficulty accurately assessing employee fatigue levels due to insufficient management of employee physical condition. Furthermore, relying solely on fixed data collection devices has the drawback of being unable to collect real-time health data on-site or quickly propose appropriate work adjustments. Accumulating worker fatigue, particularly in factories, can lead to reduced productivity and potentially adversely affect safety.

[1500] 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.

[1501] In this invention, the server includes means for collecting weight data, dietary data, and sleep data obtained from a data collection device, means for transmitting the data collected from the data collection device to the server, means for analyzing the data stored in the server using a generative model to calculate a fatigue score, means for generating and notifying suggestions for taking time off or adjusting work schedules based on the fatigue score, and means for collecting and transmitting additional health data obtained from a patrolling mobile robot. This allows for more detailed and real-time monitoring of employee health conditions, enabling appropriate and prompt suggestions for taking time off or adjusting work schedules.

[1502] A "data collection device" is a device worn by an employee to collect weight data, dietary data, sleep data, and the like.

[1503] A "smartwatch" is a type of data collection device that is worn on an employee's wrist and collects various types of biometric data.

[1504] The "mobile robot" is a robot that patrols the factory and collects health data from workers' smartwatches.

[1505] The "server" is a device that collects and stores various data, and is a central processing unit that calculates fatigue scores and generates suggestions using generative models.

[1506] A "generative model" is a machine learning algorithm used to analyze collected data and calculate an employee's fatigue score.

[1507] The "fatigue score" is a value indicating an employee's level of fatigue calculated by the generative model based on weight data, dietary data, sleep data, meeting data, etc.

[1508] "Suggestions for taking vacation or adjusting work schedules" are notifications that recommend taking vacation or adjusting work schedules to maintain employees' health based on their fatigue score.

[1509] The present invention is a system that monitors the health status of employees and encourages them to take appropriate vacations and adjust their work schedules. This system includes a data collection device, a mobile robot, a server, a generative model, and a notification means. The program processing of this system is described in detail below.

[1510] System components and operation description

[1511] 1. Data Collection Equipment

[1512] User: Employees wear smartwatches that collect weight, diet, and sleep data.

[1513] Device: The data collected by the smartwatch is automatically sent to employees' smartphones or tablets. Employees can also manually enter meal data using a dedicated app.

[1514] 2. Data transmission and storage

[1515] Device: All collected data is sent to the server on a daily basis. The data is encrypted and transmitted to protect the privacy of the data.

[1516] Server: The server associates the received data with each employee's ID and stores it in a database, allowing all of each employee's weight, diet, and sleep data to be managed centrally.

[1517] 3. Data Analysis with Generative Models

[1518] Server: The server periodically extracts the stored data and analyzes it according to a generative model, which is designed using machine learning algorithms to calculate a fatigue score by taking into account weight fluctuations, dietary balance, sleep quality, and meeting participation time.

[1519] Generative model: Data analysis also includes meeting data obtained from calendar information to more precisely assess employee fatigue levels.

[1520] 4. Fatigue assessment and suggestions

[1521] Server: Evaluates the fatigue level of each employee based on the fatigue score calculated by the generative model. If the fatigue score exceeds a certain threshold, it generates suggestions for taking time off or adjusting work schedules.

[1522] Notification method: The server notifies the generated suggestions to the employees' and managers' devices. For example, a notification such as "We recommend you take a vacation this Friday" is sent to the employee's smartphone. Also, a report is sent to the manager saying, "Employee A's fatigue level is high, so we recommend that he or she take a weekend vacation."

[1523] 5. Additional data collection by mobile robots

[1524] Robot: The robot roams the factory floor, collecting real-time health data from workers' smartwatches and transmitting it to a server using its own Wi-Fi module.

[1525] Hardware and software used

[1526] Hardware

[1527] Smartwatches: Apple Watch, Fitbit, etc.

[1528] Mobile robots: such as Fetch Robotics' Fetch Mobile Manipulator.

[1529] Server: Linux-based dedicated server.

[1530] software

[1531] Generative model: Python machine learning library (TensorFlow or PyTorch)

[1532] Database: MySQL, PostgreSQL, etc.

[1533] Notification method: Voice synthesis technology such as Google Text-to-Speech.

[1534] Specific examples

[1535] Example prompts for generative AI models

[1536] Create a generative model that calculates fatigue levels based on workers' health data and suggests appropriate breaks and work adjustments.

[1537] Data points:

[1538] Weight data: 70 kg

[1539] Dietary data: Calories 2000 kcal

[1540] Sleep data: 6 hours

[1541] prompt:

[1542] 1. How to calculate worker fatigue?

[1543] 2. How do you assess your daily workload?

[1544] 3. How do we create specific proposals for breaks and work adjustments?

[1545] This system allows for detailed and real-time monitoring of employee health conditions, enabling appropriate and prompt leave proposals and work adjustments, contributing to improved productivity throughout the factory and ensuring employee safety.

[1546] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1547] Step 1:

[1548] The user wears a smartwatch to collect weight, diet, and sleep data. The smartwatch collects this data in real time and automatically transmits it to a smartphone. The input is biometric data, and the output is data stored on the smartphone.

[1549] Step 2:

[1550] The smartphone, which is the terminal, periodically sends the collected data to the server on a daily basis. The data is encrypted to protect privacy. The input is the data stored on the smartphone, and the output is the encrypted data sent to the server.

[1551] Step 3:

[1552] The server links the received data to each employee's ID and stores it in a database. This allows the server to centrally manage weight data, dietary data, and sleep data. The input is encrypted health data, and the output is organized data stored in the database.

[1553] Step 4:

[1554] The server periodically extracts data from the database and analyzes it using a generative model. The generative model, which uses a machine learning algorithm, analyzes weight fluctuations, dietary balance, sleep quality, and meeting participation time to calculate a fatigue score. The input is each employee's health data and meeting data, and the output is a fatigue score.

[1555] Step 5:

[1556] Based on the fatigue score calculated by the generative model, the server evaluates the employee's fatigue state. If the fatigue score exceeds a certain threshold, the server generates suggestions for taking time off or adjusting work schedules. The input is the fatigue score, and the output is the suggestion.

[1557] Step 6:

[1558] As a notification method, the server notifies the generated suggestions to the devices of employees and managers. For example, a notification such as "We recommend you take vacation this Friday" is sent to an employee's smartphone. The input is the suggestion content, and the output is the notification to employees and managers.

[1559] Step 7:

[1560] The mobile robot patrols the factory and collects additional health data from the smartwatch. The robot transmits this data to a server via its WiFi module. The input is the real-time health data of employees, and the output is the data transmitted to the server.

[1561] Step 8:

[1562] The server receives additional health data sent from the mobile robot and stores it in a database. It also updates the fatigue score in real time by reflecting the additional data in the generative model. The input is the health data from the mobile robot, and the output is the updated data stored in the database.

[1563] 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.

[1564] The system of the present invention is designed to monitor employee health status and promote appropriate leave taking and work adjustments. This system includes a data collection device, a server, a generative model, a notification means, and an emotion engine. The following describes in detail how this system is implemented.

[1565] System Components and Operation

[1566] 1. Data Collection Equipment

[1567] User: Each employee wears a smartwatch, which collects weight, diet, and sleep data.

[1568] Device: The data collected by the smartwatch is automatically sent to employees' smartphones or tablets. Employees can also manually enter meal data using a dedicated app.

[1569] 2. Data transmission and storage

[1570] Device: At a set time each day, all collected data is sent to the server. The data is encrypted and transmitted to protect the privacy of the data.

[1571] Server: The server associates the received data with each employee's ID and stores it in a database, allowing all of each employee's weight, diet, and sleep data to be managed centrally.

[1572] 3. Data Analysis

[1573] Server: The server periodically extracts the stored data and analyzes it according to the generative model. The generative model is designed using a machine learning algorithm and calculates a fatigue score by taking into account weight fluctuations, dietary balance, sleep quality, and meeting participation time. Emotion data from the emotion engine is also analyzed.

[1574] Generative model: Meeting data is taken from each employee's calendar information and added to the analysis. This meeting data is important for assessing how much time employees spend in meetings.

[1575] 4. Emotion Engine and Emotion Evaluation

[1576] User: Emotional data is collected periodically via smartphone or PC using facial recognition cameras and voice recognition.

[1577] Emotion engine: Recognizes the user's emotions using voice and facial expression analysis, converts them into numerical values, and stores them.

[1578] Server: Emotion data collected by the emotion engine is stored in a database and reflected in the calculation of fatigue scores.

[1579] 5. Fatigue assessment and suggestions

[1580] Server: Evaluates the fatigue level of each employee based on the fatigue score calculated by the generative model. If the fatigue score exceeds a certain threshold, it generates suggestions for taking time off or adjusting work schedules.

[1581] Notification method: The server notifies the generated proposal to the employee and manager's devices. For example, a notification such as "We recommend you take a vacation this Friday" is sent to the employee's smartphone. Also, a report is sent to the manager saying, "Employee A is highly fatigued and we recommend that he take a weekend vacation."

[1582] Specific examples

[1583] Daily flow and data processing example

[1584] 7:00 AM - Weight data collection

[1585] User: After waking up, an employee steps on a scale linked to a smartwatch to measure their weight.

[1586] Device: Weight data is automatically recorded on your smartphone.

[1587] 13:00 noon - Collection of dietary data

[1588] User: After employees have lunch, they enter their meal details using a dedicated app.

[1589] Device: The entered meal data is saved on your smartphone.

[1590] 15:00 noon - Emotion data collection

[1591] User: Employees use facial recognition cameras to collect emotional data.

[1592] Emotion engine: Analyzes emotional data, converts the user's emotional state into a numerical value, and sends it to the server.

[1593] 10:00 PM - Sleep data collection

[1594] User: Employees start sleep tracking on their smartwatch before going to bed.

[1595] Device: The smartwatch records your sleep data and syncs it to your smartphone the next morning.

[1596] 1:00 the next day - Data transmission and storage

[1597] Device: The smartphone sends the collected data to the server daily.

[1598] Server: The received data is linked to each employee's ID and stored in a database.

[1599] 3:00 the next day - Data analysis

[1600] Server: Extracts the stored data and calculates a fatigue score using a generative model. Emotional data is also included in the analysis to calculate a more accurate fatigue score.

[1601] 9:00 the next day - Suggestions and notifications

[1602] Server: Generates suggestions based on fatigue scores and sends notifications such as "Take time off recommended" to employees and managers.

[1603] In this way, by combining the emotion engine, a system can be created that can monitor employees' health in more detail and recommend time off or work adjustments at the appropriate time, thereby more effectively maintaining employees' physical and mental health.

[1604] The processing flow will be explained below.

[1605] Step 1: Data collection

[1606] User: Wears the smartwatch, weighs himself on a scale, manually enters his food intake into the app, and starts sleep tracking before going to bed.

[1607] Device: The smartwatch records weight, food, and sleep data, which is automatically synced to the user's smartphone.

[1608] Step 2: Collecting emotion data

[1609] User: Emotion data is collected periodically using a facial recognition camera or voice input. For example, the user records emotion data in front of the camera at 3:00 PM every day.

[1610] Emotion engine: Recognizes the user's emotions using voice and facial expression analysis, and generates numerical data.

[1611] Step 3: Send data

[1612] Device: At the end of each day, collected weight, food, sleep, and emotional data is sent to a server. The data is encrypted to protect privacy.

[1613] Step 4: Save Data

[1614] Server: The received data is linked to each user's ID and stored in a database. The stored data includes date, weight, dietary details, sleep information, and emotional data.

[1615] Step 5: Data Preprocessing

[1616] Server: Periodically extracts the stored data and converts it into the format required for analysis, for example by aggregating daily data into weekly data.

[1617] Step 6: Analysis with generative models

[1618] Server: Data extracted from the database is fed into a generative model to comprehensively analyze sleep quality, dietary balance, weight fluctuations, meeting attendance times, emotional data, and more.

[1619] Step 7: Calculating your fatigue score

[1620] Server: The generative model uses the data to calculate a fatigue score for each user, which serves as an indicator of the user's health status.

[1621] Step 8: Proposal Generation

[1622] Server: Generates suggestions for taking time off or adjusting work load based on the calculated fatigue score. Specifically, it recommends taking time off if the fatigue score is high, and suggests redistributing tasks if the workload is high.

[1623] Step 9: Sending notifications

[1624] Server: Notifies the user and manager of the proposed schedule. For example, a notification such as "We recommend you take vacation next Friday" is sent to the user's smartphone. In addition, a report is sent to the manager stating, "User A is experiencing high levels of fatigue, so please adjust his or her work schedule."

[1625] Step 10: Gather feedback

[1626] User: Acts on the suggestions and provides feedback on the results in a dedicated app. For example, if a user takes a vacation, the app records the user's physical condition and mood for that day.

[1627] Terminal: Collects user feedback data and reflects it in the next analysis process.

[1628] Through these steps, a system can be built that can maintain the physical and mental health of employees by continuously monitoring their health status and recommending time off or work adjustments at the appropriate time.The addition of an emotion engine will also enable more detailed health management by evaluating fluctuations in emotional stress and happiness.

[1629] Example 2

[1630] 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."

[1631] It is important to centrally monitor employees' health and make suggestions for appropriate leave and work adjustments. However, conventional systems only collect and analyze physical data such as weight, diet, and sleep, and do not take into account factors such as emotional data or meeting participation status, making it difficult to accurately and comprehensively assess fatigue levels.

[1632] The identification process by the identification 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 weight data, dietary data, and sleep data obtained from a data collection device, means for transmitting the data collected from the data collection device to the server, means for analyzing the data stored in the server using a generative model and calculating a fatigue score, means for generating and notifying suggestions for taking vacation or adjusting work schedules based on the fatigue score, and means for collecting emotion data using face recognition and voice recognition, analyzing the data using an emotion engine, and reflecting the results in the fatigue score. This enables a more accurate and comprehensive fatigue assessment by comprehensively taking into account not only physical data but also emotion data, meeting data, and the like.

[1633] A "data collection device" is a device used to collect employee weight data, dietary data, sleep data, emotional data, etc., and specifically refers to a smartwatch or dedicated application.

[1634] The "server" is a computer system that stores collected data, analyzes it using a generative model, and calculates a fatigue score.

[1635] A "generative model" is a program that uses machine learning algorithms to analyze collected data and calculate a fatigue score, taking into account factors such as weight fluctuations, dietary balance, sleep quality, and meeting attendance time.

[1636] The "fatigue score" is a numerical representation of an employee's health status, and is an index calculated using a generative model based on weight data, dietary data, sleep data, emotional data, and meeting data.

[1637] "Notification method" refers to the means used to notify employees and managers of generated vacation and work adjustment proposals, specifically notifications sent to smartphones, tablets, and PCs.

[1638] The "emotion engine" is a program that analyzes emotional data collected using facial and voice recognition technology, quantifies it, and reflects it in a fatigue score.

[1639] MODE FOR CARRYING OUT THE INVENTION

[1640] The present invention is a system designed to monitor the health status of employees and encourage them to take appropriate leave and adjust their work schedules. How the system is implemented will be explained below.

[1641] Hardware and software used

[1642] The system includes the following components:

[1643] Data collection device: smartwatch, dedicated application

[1644] Server: a computer system that stores and analyzes data

[1645] Generative model: a program that implements a machine learning algorithm

[1646] Emotion Engine: An emotion analysis program using facial and voice recognition technology

[1647] Notification method: smartphone, tablet, PC

[1648] Examples of data collection devices

[1649] The user wears a smartwatch and collects weight, diet, and sleep data in their daily lives.

[1650] For example, every morning a user steps on a scale linked to a smartwatch to measure their weight.

[1651] Users manually enter their meal data using a dedicated app.

[1652] Data transmission and storage

[1653] The device (smartphone or tablet) automatically sends the collected data to the server at a set time. The data is encrypted to protect privacy.

[1654] For example, every day at 1:00 AM, your smartphone sends all the data collected during the day to a server.

[1655] Data analysis

[1656] The server stores the received data and analyzes it using a generative model. A machine learning algorithm is used to calculate a fatigue score based on weight fluctuations, dietary balance, sleep quality, and meeting participation time.

[1657] The generative model retrieves meeting data from employees' calendar information and adds it to the analysis.

[1658] Emotion data collection and analysis

[1659] Users collect emotion data using a facial recognition camera and voice recognition.

[1660] For example, every day at 3 p.m., a facial recognition camera will photograph your face and collect emotional data.

[1661] The emotion engine analyzes the collected emotion data, quantifies it, and stores it on the server.

[1662] Fatigue assessment and suggestion generation

[1663] The server calculates a fatigue score based on the analysis results, and if this exceeds a certain threshold, it generates suggestions for taking time off or adjusting work schedules.

[1664] Notification means

[1665] A notification means notifies the proposal to the terminals of employees and managers.

[1666] For example, every morning at 9 a.m., employees will receive a notification on their smartphones saying, "We recommend that you take Friday off."

[1667] Prompt Sentence Examples

[1668] Give instructions to the generative AI model using prompt sentences like the following:

[1669] "Design a program that evaluates employee fatigue levels based on employee health data (weight, diet, sleep, meeting attendance time, and emotional data) and generates vacation recommendations and work adjustment suggestions."

[1670] This will enable the realization of a system that can effectively monitor employees' health by comprehensively taking into account not only physical data but also emotional data, meeting data, etc., and recommend vacation time and work adjustments at the appropriate time.

[1671] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1672] Step 1: Data collection

[1673] The user wears a smartwatch and collects weight, diet, and sleep data in their daily lives.

[1674] Input: Biometric data collected from the user's daily life.

[1675] Specific operation: Every morning, the user steps on the scale to measure their weight and manually enters their dietary data using a dedicated app.

[1676] Output: Collected weight data, dietary data, and sleep data are recorded on the smartwatch.

[1677] Step 2: Send and save data

[1678] The device automatically sends the collected data to the server at a set time. The data is encrypted.

[1679] Input: Data transferred from the smartwatch (weight data, diet data, sleep data).

[1680] Specific operation: The smartphone uploads data to the server at 1:00 AM every day.

[1681] Output: Data encrypted and stored on the server.

[1682] Step 3: Data analysis

[1683] The server stores the received data and analyzes it using a generative AI model.

[1684] Input: Weight data, dietary data, and sleep data stored on the server.

[1685] What it does: The server uses machine learning algorithms to analyze the data and calculate a fatigue score.

[1686] Output: Fatigue score based on weight fluctuations, dietary balance, and sleep quality.

[1687] Step 4: Collecting emotion data

[1688] Users collect emotional data using facial recognition cameras and voice recognition.

[1689] Input: Emotion data from the user's face recognition camera and voice recognition device.

[1690] Specific operation: The user takes a picture of their face with a facial recognition camera at 3:00 pm every day to collect emotional data.

[1691] Output: The collected emotion data is recorded on a smart device.

[1692] Step 5: Analyze the sentiment data

[1693] The emotion engine analyzes the collected emotion data, quantifies it, and stores it on the server.

[1694] Input: Emotion data transferred from smart devices.

[1695] Specific operation: The emotion engine analyzes facial expressions and voice to quantify the user's emotional state.

[1696] Output: The analysis results are sent to the server as numerical data and saved.

[1697] Step 6: Fatigue assessment and generation of recommendations

[1698] The server calculates a fatigue score based on the analysis results, and if this exceeds a certain threshold, generates a suggestion.

[1699] Input: Weight data, dietary data, sleep data, emotion data stored on the server, and analysis results from the generative model.

[1700] How it works: The server analyzes all data and uses a generative model to calculate a fatigue score. If the score exceeds a threshold, it generates suggestions for taking time off or adjusting work schedules.

[1701] Output: Data including fatigue score and suggested sentence.

[1702] Step 7: Notification methods

[1703] A notification means notifies the proposal to the terminals of employees and managers.

[1704] Input: Proposal and notification data from the server.

[1705] What it does: Employees will receive a notification on their smartphones saying, "We recommend you take time off on Friday." Managers will also receive a related report.

[1706] Output: Notifications displayed on employee and manager devices.

[1707] The above process allows for detailed and comprehensive monitoring of employee health status, allowing timely recommendations for leave and work adjustments to be made.

[1708] (Application example 2)

[1709] 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."

[1710] In factory environments, it is difficult to monitor workers' health in real time and schedule appropriate leave and work adjustments. This can lead to accumulated fatigue and stress, which can lead to increased accidents and reduced production efficiency. Conventional systems only collect single data such as body temperature and heart rate, making it difficult to accurately assess workers' overall health. Furthermore, because fatigue assessments do not take into account changes in emotional state, workers' mental health is often overlooked.

[1711] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting body temperature data, heart rate data, blood pressure data, voice data, and facial expression data obtained from a data collection device, means for transmitting the data collected from the data collection device to the server, means for analyzing the data stored in the server using a generative model and calculating a fatigue score, means for collecting emotion data from voice and facial expression using an emotion analysis engine and reflecting the emotion data in the fatigue score, and means for generating and notifying suggestions for taking vacation or adjusting work schedules in real time based on the fatigue score. This enables a comprehensive evaluation of workers' health conditions in real time, and enables improved production efficiency and reduced accidents through appropriate vacation and work schedule adjustments.

[1712] "Employee health status" refers to the physical and mental condition of workers, specifically body temperature, heart rate, blood pressure, quality of sleep, diet, emotional state, etc.

[1713] "Data collection devices" are equipment used to collect employee health data, specifically wearable devices such as smartwatches and smart helmets.

[1714] "Server" refers to a computer system that is capable of storing and analyzing collected data and is used to centrally manage and analyze collected data.

[1715] "Generative model" refers to a mathematical model that uses machine learning algorithms to analyze data and calculate a fatigue score.

[1716] The "fatigue score" is a numerical representation of an employee's level of fatigue, calculated by taking into account factors such as body temperature, heart rate, blood pressure, time spent in meetings, and emotional data.

[1717] An "emotion analysis engine" refers to software that analyzes voice data and facial expression data to quantify an employee's emotional state.

[1718] "Emotional data" refers to numerical or categorical data that express an employee's emotional state, and is obtained using voice analysis and facial recognition technology.

[1719] "Leave and work adjustment suggestions" refers to specific recommendations for appropriate leave and work schedule adjustments based on an employee's fatigue score.

[1720] The system of the present invention is designed to monitor the health status of factory workers in real time and promote appropriate leave taking and work adjustments. The system includes a data collection device, a server, a generative model, a notification means, and a sentiment analysis engine.

[1721] System Components and Operation

[1722] 1. Data Collection Equipment

[1723] The user wears a smart helmet equipped with temperature sensors, heart rate sensors, blood pressure sensors, a microphone, and a camera, which collects data on body temperature, heart rate, blood pressure, voice, and facial expression. This data is then sent to the user's smartphone via Bluetooth.

[1724] 2. Data transmission and storage

[1725] The collected data is sent to a server daily. The data is encrypted to protect the privacy of the data. The server associates the received data with each user's ID and stores it in a database.

[1726] 3. Data Analysis

[1727] The server periodically extracts the stored data and analyzes it based on a generative model. The generative model is designed using machine learning algorithms and comprehensively evaluates body temperature, heart rate, blood pressure, meeting participation time, emotional data, etc. to calculate a fatigue score. The server also evaluates how much time the user is spending in meetings.

[1728] 4. Sentiment Analysis Engine and Sentiment Evaluation

[1729] The user periodically collects emotional data using the microphone and camera in the smart helmet. The emotion analysis engine uses voice analysis and facial recognition technology to recognize the user's emotional state, converting it into a numerical value and storing it. The server stores the emotional data collected by the emotion analysis engine in a database and reflects it in the calculation of the fatigue score.

[1730] 5. Fatigue assessment and suggestions

[1731] The server evaluates the fatigue state of each user based on the fatigue score calculated by the generative model. If the fatigue score exceeds a certain threshold, it generates suggestions for taking vacation or adjusting work schedules and notifies the user via a notification method on their smartphone. For example, it may send a notification to the user saying, "We recommend taking vacation this Friday." It may also send a report to management saying, "Worker A's fatigue level is high, and weekend vacation is recommended."

[1732] Specific examples

[1733] Below is an example of a day's work and data processing.

[1734] 7:00 AM - Temperature data collection

[1735] After waking up, the user puts on the smart helmet and measures their body temperature.

[1736] Body temperature data is automatically recorded on a smartphone.

[1737] 13:00 noon - Heart rate data collection

[1738] After lunch, the user measures his / her heart rate.

[1739] Heart rate data is stored on your smartphone.

[1740] 15:00 noon - Emotion data collection

[1741] The user collects emotion data using the camera in the smart helmet.

[1742] The emotion analysis engine analyzes the emotion data, converts it into numbers, and sends it to the server.

[1743] 10:00 PM - Blood pressure data collection

[1744] The smart helmet measures the user's blood pressure before they go to sleep.

[1745] Blood pressure data is automatically synced to your smartphone.

[1746] 1:00 the next day - Data transmission and storage

[1747] The smartphone sends the collected data to the server daily.

[1748] The server associates the received data with each user's ID and stores it in a database.

[1749] 3:00 the next day - Data analysis

[1750] The server extracts the stored data and calculates a fatigue score using a generative model.

[1751] 9:00 the next day - Suggestions and notifications

[1752] The server generates suggestions based on the fatigue score and sends notifications such as "take vacation recommended" to the user and manager.

[1753] Prompt Sentence Examples

[1754] "Predict the user's fatigue level based on the following data: Body temperature: 36.5, Heart rate: 80, Blood pressure: 120 / 80, Emotion score: 7"

[1755] In this way, by combining it with an emotion analysis engine, it is possible to monitor the health status of factory workers in more detail and make timely recommendations for leave and work adjustments.

[1756] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1757] Step 1:

[1758] The user wears a smart helmet and collects data on body temperature, heart rate, blood pressure, voice, and facial expression. The various sensors in the smart helmet record this data in real time. The input is the signal from the various sensors, and the output is the raw health data recorded in the smart helmet.

[1759] Step 2:

[1760] The terminal (user's smartphone) receives health data collected from the smart helmet via Bluetooth and temporarily stores it. The input is raw data from the smart helmet, and the output is data stored on the smartphone.

[1761] Step 3:

[1762] The device sends all collected data to the server at a set time each day. The data is encrypted before being sent. The input is the data stored on the smartphone, and the output is the encrypted data stored on the server.

[1763] Step 4:

[1764] The server associates the received data with each user's ID and stores it in a database. The input is encrypted data, and the output is the data for each user stored in the database.

[1765] Step 5:

[1766] The server periodically extracts user data from the database and analyzes it using a generative model. The generative model is designed using a machine learning algorithm and comprehensively evaluates body temperature, heart rate, blood pressure, meeting participation time, emotional data, etc. to calculate a fatigue score. The input is the data extracted from the database, and the output is the calculated fatigue score.

[1767] Step 6:

[1768] The server uses an emotion analysis engine to collect emotion data from voice data and facial expression data and integrate it into a generative model. The emotion analysis engine quantifies the emotion data using voice recognition and facial recognition technology. The input is voice data and facial expression data, and the output is quantified emotion data.

[1769] Step 7:

[1770] The server incorporates the emotional data into the fatigue score calculation to generate a more accurate fatigue score. The input is the quantified emotional data and other health data, and the output is an updated fatigue score.

[1771] Step 8:

[1772] The server generates suggestions for taking time off or adjusting work schedules based on the fatigue score calculated by the generative model. The input is the fatigue score, and the output is suggestions for taking time off or adjusting work schedules.

[1773] Step 9:

[1774] The server notifies the generated proposals to the user's and manager's devices. Specific proposals for taking leave or adjusting work schedules are sent to the user's smartphone via the notification means. The input is the proposal content, and the output is a notification displayed on the user's and manager's device.

[1775] Through these steps, a system will be created that comprehensively assesses workers' health status in real time and suggests appropriate leave and work adjustments as needed.

[1776] 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.

[1777] 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.

[1778] 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.

[1779] 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.

[1780] 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.

[1781] 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.

[1782] 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).

[1783] 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.

[1784] 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."

[1785] 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.

[1786] 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).

[1787] 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.

[1788] 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.

[1789] 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.

[1790] 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.

[1791] 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.

[1792] 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.

[1793] 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.

[1794] 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.

[1795] 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.

[1796] 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.

[1797] The following is further disclosed regarding the above embodiment.

[1798] (Claim 1)

[1799] A system for monitoring the health status of employees,

[1800] means for collecting weight data, dietary data, and sleep data obtained from a data collection device;

[1801] means for transmitting the data collected from the data collection device to a server;

[1802] means for analyzing the data stored in the server using a generative model and calculating a fatigue score;

[1803] A means for generating and notifying suggestions for taking leave or adjusting work based on the fatigue score;

[1804] A system including:

[1805] (Claim 2)

[1806] 10. The system of claim 1, wherein the data collection device comprises a smartwatch.

[1807] (Claim 3)

[1808] 10. The system of claim 1, further comprising means for integrating calendar meeting data and incorporating it into the fatigue score.

[1809] "Example 1"

[1810] (Claim 1)

[1811] A system for monitoring the health status of employees,

[1812] means for collecting weight data, dietary data, and sleep data obtained from a data collection device;

[1813] means for encrypting the data collected from the data collection device and transmitting the encrypted data to a server;

[1814] means for analyzing the data stored in the server using a generative model and calculating a fatigue score;

[1815] A means for generating and notifying suggestions for taking leave or adjusting work based on the fatigue score;

[1816] means for the server to periodically extract and analyze data;

[1817] means for the terminal to receive a notification from the server and display it to the user;

[1818] A system including:

[1819] (Claim 2)

[1820] 10. The system of claim 1, wherein the data collection device comprises a smartwatch.

[1821] (Claim 3)

[1822] 10. The system of claim 1, further comprising means for integrating calendar meeting data and incorporating it into the fatigue score.

[1823] "Application Example 1"

[1824] (Claim 1)

[1825] A system for monitoring the health status of employees,

[1826] means for collecting weight data, dietary data, and sleep data obtained from a data collection device;

[1827] means for transmitting the data collected from the data collection device to a server;

[1828] means for analyzing the data stored in the server using a generative model and calculating a fatigue score;

[1829] A means for generating and notifying suggestions for taking leave or adjusting work based on the fatigue score;

[1830] means for collecting and transmitting additional health data obtained from the patrolling mobile robot;

[1831] A system including:

[1832] (Claim 2)

[1833] 10. The system of claim 1, wherein the data collection device comprises a smartwatch.

[1834] (Claim 3)

[1835] 10. The system of claim 1, further comprising means for integrating calendar meeting data and incorporating it into the fatigue score.

[1836] "Example 2: Combining Emotion Engines"

[1837] (Claim 1)

[1838] A system for monitoring the health status of employees,

[1839] means for collecting weight data, dietary data, and sleep data obtained from a data collection device;

[1840] means for transmitting the data collected from the data collection device to a server;

[1841] means for analyzing the data stored in the server using a generative model and calculating a fatigue score;

[1842] A means for generating and notifying suggestions for taking leave or adjusting work based on the fatigue score;

[1843] A means for collecting emotional data using facial and voice recognition, analyzing it with an emotion engine, and reflecting it in a fatigue score;

[1844] A system including:

[1845] (Claim 2)

[1846] 10. The system of claim 1, wherein the data collection device comprises a smartwatch.

[1847] (Claim 3)

[1848] 10. The system of claim 1, further comprising means for integrating calendar meeting data and incorporating it into the fatigue score.

[1849] "Application example 2 when combining emotion engines"

[1850] (Claim 1)

[1851] A system for monitoring the health status of employees,

[1852] means for collecting body temperature data, heart rate data, blood pressure data, voice data, and facial expression data obtained from a data collection device;

[1853] means for transmitting the data collected from the data collection device to a server;

[1854] means for analyzing the data stored in the server using a generative model and calculating a fatigue score;

[1855] a means for collecting emotional data from voice and facial expressions using an emotion analysis engine and reflecting the emotional data in a fatigue score;

[1856] A means for generating and notifying suggestions for taking leave or adjusting work schedules in real time based on the fatigue score;

[1857] A system including:

[1858] (Claim 2)

[1859] 10. The system of claim 1, wherein the data collection device comprises a smart helmet.

[1860] (Claim 3)

[1861] 10. The system of claim 1, further comprising means for using an emotion analysis engine to collect emotion data from voice analysis and facial recognition techniques, and for incorporating the emotion data into a fatigue score. [Explanation of symbols]

[1862] 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 system for monitoring the health status of employees, means for collecting weight data, dietary data, and sleep data obtained from a data collection device; means for transmitting the data collected from the data collection device to a server; means for analyzing the data stored in the server using a generative model and calculating a fatigue score; A means for generating and notifying suggestions for taking leave or adjusting work based on the fatigue score; A system including:

2. The system of claim 1 , wherein the data collection device comprises a smartwatch.

3. 10. The system of claim 1, further comprising means for integrating calendar meeting data and incorporating it into the fatigue score.

Images