System

Abstract

A system is provided.SOLUTION: A system, comprising: means for inputting health information of a worker; means for analyzing the health information and evaluating a health condition of the worker; means for replacing night work with a generative AI model based on a result of the evaluation; means for feeding back a result of work performed by the generative AI model; and means for continuously monitoring the health information.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] The present invention addresses the issue of night work having a negative impact on employees' health and lifestyles in a society with a declining birthrate and an aging population. In particular, it aims to improve the situation in which employees engaged in night work suffer from a deterioration in health and increased stress, and to provide a means to address the labor shortage. [Means for solving the problem]

[0005] The present invention solves the above-mentioned problems with a system that includes a means for inputting employee health data, a means for analyzing the health data and evaluating the employee's health status, a means for substituting nighttime work using a generative AI model based on the evaluation results, a means for providing feedback on the results of the work performed by the generative AI model, and a means for continuously monitoring the health data. Specifically, in industries such as construction, transportation, and IT maintenance, the generative AI model performs nighttime work on behalf of employees and provides the results to employees and managers. Furthermore, by continuously monitoring health data, the system can promote employee health management and recommend appropriate rest as needed, thereby maintaining long-term health and addressing the social challenges of a declining birthrate and aging population.

[0006] An "employee" is a person who performs work for a company or organization based on an employment contract.

[0007] "Health data" is information collected to assess an individual's health status, including, for example, sleep duration, stress level, and heart rate.

[0008] "Analysis" is the process of examining collected data in detail and deriving meaning and trends.

[0009] "Assessing health status" refers to determining an individual's current health status based on collected health data.

[0010] A "generative AI model" is an algorithm or system designed to automatically solve a specific task or problem using artificial intelligence techniques.

[0011] "Night work" is work activity carried out outside normal working hours, especially at night.

[0012] "Substitution" means performing work or tasks that would normally be done by humans using other means (in this case, AI).

[0013] "Feedback" is information used to evaluate and report the results of a process or activity, and to use it as a basis for future improvements and decisions.

[0014] "Monitoring" means continuously observing and recording changes and trends in a specific subject (in this case, health status).

[0015] A "system" is a set of devices or a group of devices that combine multiple parts or elements to achieve a specific purpose.

[0016] A "report format" is a way of organizing information or data and presenting it in a standardized style or format.

[0017] A "manager" is a person in a position to supervise, guide, and manage the work of an organization.

[0018] "Continuous" means occurring constantly for a period of time; continuing without interruption. [Brief explanation of the drawings]

[0019] [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

[0020] 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.

[0021] First, the terms used in the following description will be explained.

[0022] 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).

[0023] 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.

[0024] 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.

[0025] 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.

[0026] 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."

[0027] [First embodiment]

[0028] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0029] 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.

[0030] 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).

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0036] 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.

[0037] 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.

[0038] 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.

[0039] 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."

[0040] This invention provides a method for building a system that uses AI to replace nighttime work while protecting the health of employees. This system is cloud-based and primarily consists of a server, terminals (PCs, smartphones, etc.), and users (employees and managers).

[0041] Explanation of program processing

[0042] 1. Data Entry

[0043] (User): Logs in to the system using a terminal and enters individual health data, such as sleep time, stress level, and heart rate. In addition, the user also enters their work schedule and nighttime work details.

[0044] 2. Data Analysis

[0045] (Server): Analyzes the received health data and work information. The analysis engine evaluates the employee's health status based on the health data, and if it determines that the employee's stress level or risk of overwork is high, it determines whether night work should be replaced.

[0046] 3. Task assignment

[0047] (Server): Based on the analysis results, the AI ​​model extracts tasks that can be processed and assigns them to the generating AI. This applies to a wide variety of tasks, such as night-time monitoring of IT systems and operating self-driving vehicles in transportation operations.

[0048] 4. AI-powered business execution

[0049] (Generative AI model): Executes assigned tasks. The AI ​​model performs designated nighttime duties with minimal human intervention. For example, in security work, it analyzes surveillance camera footage and notifies administrators if it detects any suspicious activity.

[0050] 5. Results feedback

[0051] (Server): Aggregates the results of the tasks performed by the generative AI model and generates a report. This report is sent to the user and administrator, detailing the progress and issues of the tasks.

[0052] 6. Health monitoring

[0053] (Server): Continuously inputs and analyzes health data. If an abnormality is detected, such as prolonged periods of high stress or lack of sleep, the server notifies the user and encourages them to rest if necessary.

[0054] Specific examples

[0055] For the transportation industry

[0056] (User): A transportation worker enters health data on their device. For example, they may learn that they have recently been getting less sleep and their stress levels have increased.

[0057] (Server): Analyzes health data and determines that the employee is overworked. At the same time, checks the nighttime delivery schedule and determines that nighttime delivery work can be performed by an autonomous truck.

[0058] (Server): Assigns nighttime delivery tasks to the generative AI model, which then sends instructions to the self-driving truck to operate the designated route.

[0059] (Generative AI model): Self-driving trucks carry out deliveries at night and monitor the progress of all routes.

[0060] (Server): Once the delivery is completed, the server aggregates the results of the work and sends a report to the user and administrator. The report includes the start time, end time, mileage, truck status, etc.

[0061] (Server): Continuously monitor the employee's health status and send notifications to encourage the employee to take necessary rest.

[0062] In this way, using generative AI to replace nighttime work will enable efficient work execution while protecting the health of employees.

[0063] The processing flow will be explained below.

[0064] Step 1:

[0065] (User): Logs in to the system using a terminal and enters personal health data (e.g., sleep time, stress level, heart rate) into a dedicated form. The user also enters the schedule and details of night work.

[0066] Step 2:

[0067] (Server): Receives login information and entered health data. The received data is stored in a database and prepared for the next analysis step.

[0068] Step 3:

[0069] (Server): The received data is fed into an analytics engine to assess the employee's health status. This assessment uses an algorithm that compares past and current health data to determine stress levels and risk of overwork.

[0070] Step 4:

[0071] (Server): Based on the health assessment results, it determines whether night work should be replaced by an AI. For example, if the stress level is very high or the employee is not getting enough sleep, it determines that night work should be shifted to an AI.

[0072] Step 5:

[0073] (Server): Creates a task list generated from the analysis results and assigns tasks to the generative AI model. Here, appropriate work tasks are assigned to AI suitable for nighttime work (for example, AI for monitoring self-driving trucks or IT systems).

[0074] Step 6:

[0075] (Generative AI model): Carries out assigned tasks. For example, in the case of a self-driving truck, the AI ​​automatically drives the designated route and completes the delivery mission.

[0076] Step 7:

[0077] (Server): Receives and analyzes data on the results of work execution (e.g., operation start time, end time, whether or not an abnormality occurred, etc.) from the AI ​​model. This confirms whether the work was completed successfully.

[0078] Step 8:

[0079] (Server): Organizes the results of the work and compiles them into a report. The report includes details of the work, the time it took to complete it, and the AI's performance.

[0080] Step 9:

[0081] (Server): Sends the generated report to the user and administrator. The user can check the report on their own device and confirm the results of their work.

[0082] Step 10:

[0083] (Server): Continuously monitors employee health data and analyzes new data as it is entered. If an abnormality is detected in the employee's health, the server notifies the user and provides appropriate rest or medical advice.

[0084] Example 1

[0085] 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."

[0086] In modern society, maintaining employee health while maintaining work efficiency is a major challenge. Night work, in particular, places a significant burden on employees' health, so appropriate health management and alternative work methods are required. However, systems that monitor employee health status in real time, detect overwork or high stress levels early, and use AI to substitute for night work as necessary are not yet widespread. As a result, there is a risk that appropriate health management will not be carried out and employees' health will be damaged.

[0087] 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.

[0088] In this invention, the server includes means for inputting employee health data, means for analyzing the health data and evaluating the employee's health status, means for substituting night work using an AI model based on the evaluation results, means for feeding back the results of the work performed by the AI ​​model, means for continuously monitoring the health data, means for detecting overwork or high stress based on the health data and the evaluation results and sending an alert, and means for operating an autonomous vehicle or monitoring system as a substitute for the night work. This enables real-time monitoring of employee health status and appropriate work substitution.

[0089] "Employee health data" refers to information that indicates an employee's health status, such as the employee's sleep time, stress level, and heart rate.

[0090] The "system" refers to a set of devices and software used to input, analyze, and evaluate employee health data, perform tasks using AI models, provide feedback on the results, and continuously monitor health data.

[0091] An "AI model" is a set of algorithms and data that uses artificial intelligence to perform a specific task, which in this case replaces night work.

[0092] "Feedback means" refers to the process and devices for aggregating the results of work performed by the AI ​​model and providing them to employees and managers as reports.

[0093] "Analytics Engine" means software and algorithms used to analyze received health data and assess employee health status.

[0094] "Means for detecting overwork or high stress" refers to processes and devices for determining whether an employee is in a state of overwork or high stress from the received health data and assessment results and generating an alert.

[0095] An "autonomous vehicle" is a vehicle that uses an AI model to automatically carry out transportation operations at night.

[0096] A "surveillance system" is a collection of cameras, sensors, and AI models used to operate them to perform nighttime surveillance operations.

[0097] This invention provides a system that uses AI to replace nighttime work while protecting the health of employees. This system is cloud-based and primarily consists of a server, terminals (PCs, smartphones, etc.), and users (employees and managers).

[0098] Hardware and Software Examples

[0099] The entire system consists of the following major components:

[0100] 1. Devices: PCs and smartphones used by employees. These serve as interfaces for entering health data and work schedules. Specific devices include Windows PCs, Macs, iPhones, and Android smartphones.

[0101] 2. Server: A central management system that receives data, analyzes it, runs AI models, and provides feedback on the results. This server environment is built using cloud services such as AWS (Amazon Web Services) and Google Cloud.

[0102] 3. Generative AI models: Artificial intelligence to replace nighttime operations. For example, they perform specific tasks such as controlling autonomous vehicles in transportation and monitoring systems in IT maintenance. These AI models are developed using deep learning frameworks such as TensorFlow and PyTorch.

[0103] Details of data processing and calculation

[0104] The specific data processing and calculations that the system performs are shown below.

[0105] 1. Data entry: A user logs in to the system using a terminal and enters health data (sleep time, stress level, heart rate, etc.) and work schedule. The terminal then sends this data to the server.

[0106] 2. Data analysis: The server receives the entered health data and work schedule. The analysis engine evaluates the employee's health status based on the received data. Specifically, it uses machine learning algorithms to calculate stress levels and the risk of overwork.

[0107] 3. Task allocation: The server extracts tasks that can be handled by the AI ​​model based on the analysis results. For example, if an employee is determined to be overworked, it assigns a nighttime delivery task to an autonomous vehicle. This allocation process is optimized by a specific scheduling algorithm within the server.

[0108] 4. AI execution: Generative AI models execute assigned tasks, such as driving a self-driving vehicle along a designated route, monitoring real-time conditions along the way, and responding appropriately if anomalies are detected.

[0109] 5. Result feedback: The server aggregates the results of the tasks performed by the AI ​​model and generates a feedback report that is sent to employees and managers. The report includes the start and end times of the trip, the mileage, and the condition of the truck.

[0110] 6. Health monitoring: The server monitors the health data continuously input by the user. If an abnormality is detected, such as prolonged high stress or lack of sleep, the server will send a notification to the user to encourage them to get adequate rest.

[0111] Specific examples

[0112] Below is a specific scenario in the transportation industry.

[0113] 1. User: A transportation worker uses a smartphone to enter the average number of hours of sleep he or she has had in the past week as "6 hours" and his or her stress level as "high." He or she also registers a schedule for the next night's delivery work.

[0114] 2. Server: The server analyzes the received data and determines that the employee is overworked. As a result, it decides to replace the nighttime delivery work with an autonomous vehicle.

[0115] 3. Server: Tasks are assigned to the generative AI model and route information is sent to the autonomous vehicle.

[0116] 4. Generative AI model: The autonomous vehicle will follow a designated route and monitor the situation in real time during the journey.

[0117] 5. Server: Once the delivery is completed, the server aggregates the operation logs and generates a detailed report, which is sent to employees and managers.

[0118] 6. Server: Continue to monitor employee health and send reminders to rest when necessary.

[0119] In this way, using generative AI models to replace night shift work enables efficient work execution while protecting the health of employees.

[0120] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0121] Step 1:

[0122] (Data Entry)

[0123] Users log in to the system using a terminal (PC or smartphone). Next, they use a dedicated input form to enter their own health data (sleep time, stress level, heart rate, etc.) and work schedule. The entered data is sent from the terminal to the server. A specific example of input data is information such as "sleep time: 6 hours, stress level: high." Input: Employee's health data and work schedule; Output: Raw data sent to the server.

[0124] Step 2:

[0125] (Data Analysis)

[0126] The server receives the health data and work schedule sent from the device. The received data is analyzed by an analysis engine. The analysis engine evaluates the employee's health status using, for example, a machine learning algorithm. Specifically, it calculates overwork risk and stress level based on the input sleep time and stress level. The analysis results are saved on the server as the employee's health evaluation. Input: raw data, output: health evaluation results.

[0127] Step 3:

[0128] (Task assignment)

[0129] Based on the health assessment results, the server extracts tasks that the AI ​​model can handle. For example, if an employee is determined to be overworked, a replacement will be needed for nighttime work. The server uses a scheduling algorithm to assign tasks, such as nighttime delivery, to an autonomous vehicle. The assigned task information is sent to the generative AI model. Input: Health assessment results, Output: Task information sent to the AI ​​model.

[0130] Step 4:

[0131] (Work execution using AI)

[0132] The generative AI model carries out tasks based on task information received from the server. For example, it sends instructions for nighttime delivery to an autonomous vehicle and has it operate along a specified route. The generative AI model collects data in real time from the vehicle's various sensors (GPS, camera, etc.) and monitors the operating status. If an abnormality is detected, it takes immediate action. Input: task information, output: results of the performed task (operation record). Specific actions include periodically checking the vehicle's location and detecting and avoiding obstacles.

[0133] Step 5:

[0134] (Result feedback)

[0135] The server aggregates the results of the tasks performed by the generative AI model. For example, it analyzes the autonomous vehicle's operation log (mileage, operating time, fuel consumption, etc.) and generates a detailed report. The generated report is sent to employees and managers via email or a dedicated dashboard. The report describes the progress and issues with the task execution. Input: Results of the performed task, Output: Detailed task report.

[0136] Step 6:

[0137] (Health monitoring)

[0138] The server monitors health data continuously input by employees. For example, an analysis engine continuously evaluates the data, and if a state of high stress or lack of sleep continues for a long period of time, the server generates a warning and notifies the employee. The notification includes suggestions for rest and advice to improve health status. Input: Continuously input health data, Output: Health status evaluation and warning message.

[0139] The above processing steps realize a system that monitors employee health in real time, replaces night work with a generative AI model as needed, and balances employee health with work efficiency.

[0140] (Application example 1)

[0141] 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."

[0142] Employees working at night can experience health problems such as sleep deprivation and excessive stress. Security work at night also requires the rapid detection and response of suspicious activity, which can be a burden on employees. It is necessary to perform security work efficiently and effectively while protecting the health of employees.

[0143] 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.

[0144] In this invention, the server includes means for inputting employee health data, means for analyzing the health data and evaluating the employee's health status, means for substituting night work using a generative AI model based on the evaluation results, means for providing feedback on the results of the work performed by the generative AI model, means for continuously monitoring the health data, means for the generative AI model to link with smart devices and analyze and notify night work in real time, means for engaging in security work using the generative AI model to monitor crime prevention and detect suspicious behavior, and means for providing the results of the security work to a manager in the form of a report, thereby enabling security work to be performed efficiently and effectively while protecting the health of employees.

[0145] "Employee health data" refers to biometric information and health status such as sleep time, stress level, and heart rate entered by employees.

[0146] "Means of analysis" refers to analytical engines and algorithms that evaluate employees' health status based on their health data and determine the risk of overwork or stress.

[0147] "Generative AI models" refer to artificial intelligence algorithms used to automate and replace the night-time work that would normally be performed by employees.

[0148] "Means for providing feedback" refers to the function of aggregating the results of work performed by the generative AI model and providing them to employees and managers in the form of a report.

[0149] "Means of monitoring" refers to a system that continuously collects and monitors employee health data and notifies employees when abnormalities are detected.

[0150] "Smart device" refers to a portable electronic device such as a smartphone, smart glasses, or a head-mounted display.

[0151] "Security surveillance" refers to the act of monitoring and analyzing suspicious behavior or events within a facility or area in real time using security equipment such as surveillance cameras.

[0152] "Suspicious behavior" refers to behavior or actions that are different from normal behavior and may pose a security risk.

[0153] "Report format" refers to the format of a report in which business results and security monitoring results are organized and recorded in written or digital form and provided to a manager.

[0154] The present invention relates to a system that efficiently and effectively performs security operations while protecting the health of employees. This system is operated on a cloud basis and is primarily composed of a server, terminals (smartphones, smart glasses, etc.), and users (security guards and administrators).

[0155] System Configuration

[0156] The server includes means for inputting employee health data, means for analyzing the health data and evaluating the health status of employees, means for substituting night work using a generative AI model based on the evaluation results, means for feeding back the results of work performed by the generative AI model, means for continuously monitoring the health data, means for the generative AI model to link with smart devices and analyze and notify night work in real time, means for using the generative AI model to engage in security work, perform crime prevention monitoring and detect suspicious behavior, and means for providing the results of the security work to an administrator in the form of a report.

[0157] Processing flow

[0158] Users wear smart glasses and input their health data (sleep time, stress level, heart rate, etc.). The health data is sent to a server and analyzed by an analysis engine. Based on the analysis results, the employee's health condition is evaluated, and if the employee is overworked or stressed, the generative AI model will replace them in night work.

[0159] The generative AI model works in conjunction with smart glasses to analyze the surrounding situation in real time. For example, it analyzes surveillance camera footage and, if it detects suspicious behavior, it will alert the user via audio notification. The results of the operations performed by the generative AI model are aggregated on a server and provided to the administrator in the form of a report.

[0160] Hardware and software used

[0161] Smart glasses: Using handheld electronic devices such as Google Glass or Vuzix Blade.

[0162] Cloud server: Use AWS or Google Cloud Platform.

[0163] Programming language: Python is used.

[0164] Database: Data management is performed using MySQL or PostgreSQL.

[0165] Analysis engine: Data analysis is performed using TensorFlow and PyTorch.

[0166] Specific examples

[0167] As a concrete example, a security guard who patrols the area around a warehouse at night from 11:00 PM to 7:00 AM wears smart glasses and inputs his health data. The analysis engine determines that the guard has a high heart rate and little sleep, and the generative AI model takes over the patrol. The AI ​​model analyzes surveillance camera footage and, if it detects any suspicious behavior, notifies the guard via voice. The patrol history and detection results are sent to the manager as a report.

[0168] Prompt Sentence Examples

[0169] I'm a security guard. I got 4 hours of sleep last night, my stress level is 8, and my heart rate is 110. My patrol schedule tonight is from 10 PM to 6 AM in the warehouse area. Thank you.

[0170] In this way, by using the system based on the present invention, it is possible to carry out security operations efficiently and effectively while protecting the health of employees.

[0171] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0172] Step 1:

[0173] The user puts on the smart glasses and inputs health data (sleep time, stress level, heart rate, etc.). This data is sent to the server through the smart glasses. For example, input data may include 4 hours of sleep last night, a stress level of 8, and a heart rate of 110. This provides the server with the employee's latest health status.

[0174] Step 2:

[0175] The server processes the received health data using an analysis engine (TensorFlow or PyTorch). The analysis engine evaluates each data point, such as sleep time, stress level, and heart rate, to make a comprehensive assessment of the employee's health condition. This analysis outputs results such as whether the employee is overworked or under high stress.

[0176] Step 3:

[0177] Based on the analysis results, the server determines whether the generative AI model should be used to replace the employee in nighttime work. If the employee's health condition is assessed as poor, the generative AI model issues instructions to replace the employee in nighttime patrol work. The generative AI model gains a detailed understanding of the patrol task and becomes capable of performing it automatically.

[0178] Step 4:

[0179] The generative AI model monitors the surroundings in real time through the smart glasses. It analyzes surveillance camera footage and sends an audio notification to the user when it detects suspicious behavior or anomalies. The input data are real-time video streams and surveillance camera data, and the output is the detection of suspicious behavior and an audio notification.

[0180] Step 5:

[0181] The server aggregates the results of the patrol operations performed by the generative AI model, including video logs from surveillance cameras, records of suspicious behavior detection, and user notification history. This data is stored in a database (MySQL or PostgreSQL) and used for subsequent processing.

[0182] Step 6:

[0183] The server generates reports based on the aggregated results of the work. The reports detail the progress of each patrol session, the results of any suspicious behavior detected, and the response status. The reports are provided to users and administrators in digital format.

[0184] Step 7:

[0185] The server continuously monitors employee health data. Each time new data is entered, the analytics engine reassesss the health status and, if necessary, substitutes tasks using a generative AI model. This ensures that employees are protected from overwork and stress.

[0186] Prompt Sentence Examples

[0187] I'm a security guard. I got 4 hours of sleep last night, my stress level is 8, and my heart rate is 110. My patrol schedule tonight is from 10 PM to 6 AM in the warehouse area. Thank you.

[0188] 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.

[0189] This invention is a system that analyzes employee health and emotional data, evaluates the employee's health and emotional state, and uses a generative AI model to replace nighttime work. This system is cloud-based and primarily consists of a server, terminals (PCs, smartphones, etc.), users (employees and managers), and an emotion engine.

[0190] Program processing explanation

[0191] 1. Data Entry

[0192] (User): Logs in to the system using a terminal and enters individual health data (e.g., sleep time, stress level, heart rate) and emotional data (e.g., real-time emotional state, self-reported emotional score) into a dedicated form. The user also enters the schedule and content of their night work.

[0193] 2. Data Analysis

[0194] (Server): Receives login information and entered health and emotion data. The received data is stored in a database and prepared for the next analysis step.

[0195] (Server): The data is fed into the data analysis engine to evaluate the employee's health and emotional state. The emotional engine determines the employee's psychological state based on the analysis of the emotional data. The health data and emotional data are integrated to evaluate the employee's overall stress level and psychological burden.

[0196] 3. Task assignment

[0197] (Server): Based on the analysis results, the generative AI model extracts tasks that can be processed and assigns them to the generative AI. Examples of applications include nighttime monitoring of IT systems and operating self-driving vehicles in transportation. Priority is given to employees with particularly unstable emotional states, with AI taking over their tasks.

[0198] 4. AI-powered business execution

[0199] (Generative AI model): Carries out assigned tasks. For example, in the case of a self-driving truck, AI automatically drives the designated route and completes the delivery. In addition, in monitoring IT systems, AI detects system anomalies in real time and automatically responds when an anomaly occurs.

[0200] 5. Results feedback

[0201] (Server): Aggregates the results of tasks performed by the generative AI model and generates a report. This report is sent to the user and administrator, detailing the task's progress and any issues. The report also includes the results of the emotion engine's evaluation of the user's emotional state.

[0202] 6. Health monitoring

[0203] (Server): Continuously inputs and analyzes health and emotional data. If an abnormality is detected, such as prolonged periods of high stress or persistent emotional problems, the server notifies the user and provides rest or medical advice as needed. It also sends notifications recommending mental health support and appropriate measures.

[0204] Specific examples

[0205] For the transportation industry

[0206] (User): A transportation worker enters health and emotional data on their own device, such as their recent short sleep time, high stress level, and unstable emotional state.

[0207] (Server): Analyzes health and emotional data to determine that the employee is overworked and emotionally unstable. At the same time, checks the nighttime delivery schedule and determines that nighttime delivery work can be performed by self-driving trucks.

[0208] (Server): Assigns nighttime delivery tasks to the generative AI model, which then sends instructions to the self-driving truck to operate the designated route.

[0209] (Generative AI model): Self-driving trucks carry out deliveries at night and monitor the progress of all routes.

[0210] (Server): Once the delivery is completed, the results are compiled and a report is sent to the user and administrator. The report includes the start and end times of the delivery, the distance traveled, the condition of the truck, and an evaluation of the employee's health and emotional state.

[0211] (Server): Continuously monitors the employee's health and emotional state, sends notifications to encourage the employee to take necessary rest, and provides mental health support and recommends appropriate measures.

[0212] In this way, using generative AI and emotion engines to replace night shifts allows employees to work efficiently while protecting their health and emotional state.

[0213] The processing flow will be explained below.

[0214] Step 1:

[0215] (User): Logs in to the system using a terminal and enters personal health data (e.g., sleep time, stress level, heart rate) and emotional data (e.g., real-time emotional state, self-reported emotional score) into a dedicated form. In addition, the user also enters the schedule and content of their night work.

[0216] Step 2:

[0217] (Server): Receives login information, health data, emotional data, night work schedule and details entered by the user and stores them in a database.

[0218] Step 3:

[0219] (Server): The stored health data and emotion data are input into the analysis engine. The analysis engine uses the health algorithm and emotion engine to evaluate the user's health and emotion state.

[0220] Step 4:

[0221] (Server): Based on the evaluation results, the generated stress level and risk of overwork are determined. The emotion engine analyzes the emotion data to determine the user's psychological state, and if necessary, evaluates the user as having a high psychological load.

[0222] Step 5:

[0223] (Server): Based on the analysis of health and emotional status, it determines whether night shifts require substitution. For example, if the stress level is high and the emotional state is unstable, it determines that AI substitution is necessary.

[0224] Step 6:

[0225] (Server): Based on the analysis results, extracts tasks that the generative AI model can handle (e.g., night-time monitoring of IT systems, operating autonomous trucks in transportation operations, etc.) and assigns the tasks to the generative AI model.

[0226] Step 7:

[0227] (Generative AI model): Carries out assigned tasks. For example, in the case of a self-driving truck, AI automatically drives the designated route and completes the delivery. In addition, in monitoring IT systems, AI detects system anomalies in real time and automatically responds when an anomaly occurs.

[0228] Step 8:

[0229] (Server): Receives and analyzes data on the results of the task execution (e.g., operation start time, end time, whether or not an abnormality occurred, etc.) from the generated AI model. This confirms whether the task was completed successfully.

[0230] Step 9:

[0231] (Server): Organizes the results of the work and compiles them into a report. The report includes details of the work, the time it took to complete it, the AI's performance, and the emotional state evaluation results from the emotion engine.

[0232] Step 10:

[0233] (Server): Sends the generated report to the user and administrator. The user can check the report on their own device and check the results of their work performance and their own health and emotional state.

[0234] Step 11:

[0235] (Server): Continuously monitors the user's health and emotional data, analyzing each new data entry. If an abnormality in the user's health is detected, the server notifies the user and provides appropriate rest and medical advice. If an abnormality in the user's emotional state is detected, the server sends a notification recommending mental health support and appropriate measures.

[0236] Example 2

[0237] 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."

[0238] In today's work environment, night shifts and continuous work can worsen employees' health and emotional state. However, there are limited systems in place to properly manage employees' health and emotional state and substitute for their work as needed. Therefore, there is a need for a way to maintain work efficiency while caring for employees' health and emotions.

[0239] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0240] In this invention, the server includes a means for inputting employee health information and emotional information, a means for analyzing the employee health information and emotional information and evaluating the employee's health and emotional state, and a means for substituting night work using a generative AI model based on the evaluation results. This makes it possible to monitor the employee's health and emotional state in real time and to substitute work using AI at the appropriate time.

[0241] "Employee" refers to a person who belongs to a particular organization and is engaged in a particular job by that organization.

[0242] "Health information" refers to information that indicates an employee's physical health status, and specifically includes data such as sleep time, heart rate, blood pressure, and stress level.

[0243] "Emotional information" refers to information that indicates an employee's mental or emotional state, including data such as self-reported emotional scores and real-time emotional states.

[0244] A "generative AI model" is a machine learning model that uses generative artificial intelligence techniques to perform specific tasks, such as operating autonomous driving or surveillance systems.

[0245] "Night work" refers to work performed outside of normal business hours, and specifically includes nighttime delivery work and system monitoring work.

[0246] "Means of input" refers to the devices or methods by which employees provide health and emotional information to the system, including terminals, login forms, etc.

[0247] "Means for evaluation" refers to a device or method for analyzing input data and determining the health status or emotional state of an employee, and includes a data analysis engine and an emotion engine.

[0248] "Alternative means" refers to devices or methods that use generative AI models to perform tasks performed by employees, such as operating a self-driving truck at night.

[0249] "Feedback means" refers to devices or methods for collecting the results of tasks performed by a generative AI model and providing them to relevant parties, including report generation devices and notification systems.

[0250] "Monitoring means" refers to devices and methods for continuously monitoring employee health and emotional information and detecting abnormalities, including continuous data collection systems.

[0251] This invention is a system that analyzes employee health and emotional information, evaluates the employee's health and emotional state, and uses a generative AI model to replace nighttime work. This system is cloud-based and primarily consists of a server, terminals (PCs, smartphones, etc.), users (employees and managers), and an emotion engine.

[0252] First, a user logs in to the system using a terminal. At this time, the user enters health information (e.g., sleep time, stress level, heart rate) and emotional information (e.g., real-time emotional state, self-reported emotional score) into a dedicated input form. The user also enters the schedule and details of night work. The terminal then sends this data to the server.

[0253] The server then stores the received login information, health information, and emotional information in a database. The data analysis engine then evaluates the employee's health status. This analysis is performed using Python's pandas library and scikit-learn. The data analysis engine calculates various health indicators (e.g., average sleep duration, heart rate variability, stress index).

[0254] The server then uses an emotion engine to assess the employee's psychological state based on the input emotion information. It uses natural language processing models (e.g., BERT and GPT-3) to calculate an emotion score from text-based self-reports. It integrates health and emotion information to assess the employee's overall stress level and psychological burden. This comprehensive assessment utilizes a data warehouse and business intelligence tools (e.g., Tableau).

[0255] Based on the analysis results, the server extracts tasks that the generative AI model can handle. This includes, for example, nighttime delivery work. The server assigns the extracted tasks to the generative AI model. The generative AI model is instructed on the details of the task (e.g., delivery route, delivery time). Instructions are given via an API.

[0256] The generative AI model carries out the assigned task. For example, in the case of a self-driving truck, the AI ​​automatically drives the designated route and completes the delivery mission. Machine learning frameworks such as TensorFlow and PyTorch are used for autonomous driving.

[0257] After the task is completed, the server aggregates the results of the task performed by the generative AI model. The task results (e.g., delivery completion time, distance traveled, fuel consumption) are generated as a report and sent to the user and administrator. The report details the task's progress, any issues, and the emotional state evaluation results of the emotion engine. The report is sent using the SMTP protocol.

[0258] The server continuously inputs and analyzes employee health and emotional information to detect abnormalities. For example, if high stress or emotional problems persist for a long period of time, the server will notify the user and provide rest or medical advice as necessary. Notifications are sent via SMS or email.

[0259] Example: Transportation industry

[0260] A transportation employee enters health information (e.g., recent short sleep duration) and emotional information (e.g., high stress, emotional instability) on their own device. The server receives this data and stores it in a database. Next, a data analysis engine is used to determine whether the employee is overworked. Based on the analysis results, it is determined that nighttime delivery work can be performed by an autonomous truck. The server assigns nighttime delivery tasks to a generative AI model. The generative AI model sends instructions to the autonomous truck to operate the specified route. The autonomous truck carries out the nighttime delivery, monitoring the delivery status of the entire route as it drives. Once the delivery is completed, the work results are compiled and a report is sent to the user and administrator. The report includes the start and end times of the trip, the mileage, the truck's condition, and an evaluation of the employee's health and emotional state. The server continuously monitors the employee's health and emotional state and sends notifications to encourage them to take necessary rest. It also provides mental health support and recommends appropriate measures.

[0261] Prompt Sentence Examples

[0262] "Please explain how a generative AI model could replace transportation tasks when employees are overworked and in an unstable emotional state."

[0263] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0264] Step 1:

[0265] A user logs in to the system using a terminal. The information entered here is a user ID and password, which are used for user authentication. The terminal sends the data entered in the login form to the server, and a login session begins. The output is a login session ID.

[0266] Step 2:

[0267] After logging in, users enter their health and emotional information into a dedicated form. Health information input items include sleep time, stress level, and heart rate, while emotional information input items include real-time emotional state and self-reported emotional score. Additionally, users also enter their nighttime work schedule and details. The device formats this data and sends it to the server. The output is formatted data.

[0268] Step 3:

[0269] The server stores the received health and emotion information in a database, where the stored data is organized for each individual employee. The input of the received data is formatted data, and the output is the stored data in the database.

[0270] Step 4:

[0271] The server inputs the stored data into a data analysis engine, which uses Python's pandas library and scikit-learn to analyze employee health status. The input data is health information, and the data analysis engine calculates average sleep time, heart rate variability, stress index, etc. The output is the analyzed health indicators.

[0272] Step 5:

[0273] The server analyzes the emotional information using an emotion engine. The emotion engine uses a natural language processing model (e.g., BERT or GPT-3) to calculate an emotion score from the input text-based emotion data. The input data is the emotional information, and the output is the emotion score.

[0274] Step 6:

[0275] The server integrates health and emotional information to assess employees' overall stress levels and psychological workload. Data warehouses and business intelligence tools (e.g., Tableau) are used for this assessment. The inputs are the analyzed health indicators and emotional scores, and the output is the overall assessment result.

[0276] Step 7:

[0277] The server extracts tasks that the generative AI model can process based on the overall evaluation results. For example, if an employee's health condition is deteriorating, the server selects nighttime work (e.g., nighttime delivery work) for that employee as a criterion. The input is the overall evaluation result, and the output is the extracted tasks.

[0278] Step 8:

[0279] The server assigns the extracted tasks to the generative AI model. The generative AI model is instructed on task details (e.g., delivery route, delivery time). Instructions are given through an API. The input is task details, and the output is the assignment of the task to the generative AI model.

[0280] Step 9:

[0281] Generative AI models carry out assigned tasks. For example, in the case of a self-driving truck, the AI ​​automatically drives a designated route and completes delivery tasks. Machine learning frameworks such as TensorFlow and PyTorch are used for autonomous driving. The input is the details of the task, and the output is the completed task result.

[0282] Step 10:

[0283] The server aggregates the results of the tasks performed by the generative AI model. It generates a report of the task results (e.g., delivery completion time, distance traveled, fuel consumption) and sends it to the user and administrator. The report details the task progress and issues, as well as the emotional state evaluation results from the emotion engine. The input is the completed task results, and the output is the generated report.

[0284] Step 11:

[0285] The server continuously inputs and analyzes employee health and emotional information to detect abnormalities. If high stress or emotional problems persist for a long period of time, the server notifies the user and provides rest or medical advice as needed. Notifications are sent via SMS or email. The input is the results of continuous data analysis, and the output is a notification to the user.

[0286] Prompt Sentence Examples

[0287] "Please explain how a generative AI model could replace transportation tasks when employees are overworked and in an unstable emotional state."

[0288] (Application example 2)

[0289] 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."

[0290] Factories are required to operate 24 hours a day, so managing employee health and maintaining work efficiency, especially during night shifts, is a key issue. However, employees accumulate fatigue due to long working hours, and are prone to overwork and emotional instability, especially during night shifts. This increases the risk of work errors and accidents, leading to reduced manufacturing efficiency and quality issues. Inadequate health management not only results in reduced productivity, but also has a negative impact on employee health. Therefore, there is an urgent need to provide a system that monitors employee health and emotional states in real time and, if necessary, automatically substitutes for night shifts.

[0291] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0292] In this invention, the server includes a means for inputting employee health data and emotional data, a means for analyzing the health data and emotional data and evaluating the employee's health and emotional state, a means for substituting night work using a generative AI model based on the evaluation results, a means for providing feedback on the results of work performed by the generative AI model, and a means for continuously monitoring the health data and emotional data. This makes it possible to evaluate employee health and emotional states in real time and, if necessary, substituting night work with an automated system. This is expected to reduce employee overwork and emotional instability, improve productivity, and maintain quality.

[0293] "Employee health data" refers to information about an employee's physical health, primarily including data such as sleep duration, stress level, and heart rate.

[0294] "Emotional data" refers to information about an employee's psychological state, including data such as real-time emotional state and self-reported emotional scores.

[0295] The "assessment means" is a component of the system that is responsible for analyzing the input health data and emotional data and evaluating the employee's health and emotional state.

[0296] A "generative AI model" is an artificial intelligence model that can perform specific tasks using machine learning technology and is used to replace night shift work based on the evaluation of employees' health and emotional state.

[0297] "Feedback mechanism" is a system component responsible for aggregating the results of work performed by the generative AI model and providing them to employees and managers in the form of reports.

[0298] "Monitoring means" refers to a system component that is responsible for continuously collecting and analyzing employee health and emotional data and monitoring their condition.

[0299] The "manufacturing industry" refers to the industry that produces various products, and since employees often perform complex and repetitive tasks, it is necessary to manage their health and maintain work efficiency.

[0300] "Night work" refers to work performed at night, outside of normal daytime working hours, and tends to place a greater physical and mental burden on employees.

[0301] The "reporting format" refers to a format in which the results of work performed by a generative AI model are organized and presented in a visually and easily understandable manner, making it easier for employees and managers to grasp the progress and results of work.

[0302] This invention is a system that allows factory workers to work night shifts more safely and efficiently. The system collects and analyzes employee health and emotional data, and then uses a generative AI model to substitute for night shift work as needed, thereby maintaining employee health and work efficiency.

[0303] System Configuration

[0304] This system is primarily composed of a server, terminals (such as smartphones), employees and managers, and a generative AI model.

[0305] Data Entry

[0306] Employees log in to the system using their smartphones and enter their health and emotional data. The health data includes sleep duration, stress level, and heart rate, while the emotional data includes real-time emotional state and self-reported emotional scores. This data entry is done using a dedicated form.

[0307] Data analysis

[0308] The server receives the login information and the entered health and emotion data and stores them in a database. The analysis engine analyzes this data and evaluates the employee's health and emotional state. This analysis is performed using scripts written in programming languages ​​such as Python. Sentiment analysis is also performed using a natural language processing API.

[0309] Task assignment

[0310] The server uses a generative AI model based on the analysis results to identify tasks that can be performed and assign them to the generative AI. For example, an AI model using TensorFlow can replace night shifts based on an employee's health and emotional state. Tasks include welding, assembly, and inspection work.

[0311] AI-powered business execution

[0312] The generative AI model then carries out the assigned tasks, for example, sending instructions to a robot to automate part of a manufacturing line, reducing the workload of employees by allowing the robot to take over nighttime work.

[0313] Results feedback

[0314] The server aggregates the results of the tasks performed by the generative AI model and generates a report, which is provided to employees and managers via a smartphone application. The report includes information such as the start and end times of tasks, the tasks performed, and evaluation results.

[0315] Health monitoring

[0316] The server continuously inputs and analyzes health and emotional data to monitor the employee's condition. If an abnormality is detected, an alert is sent to the employee using a notification service such as Twilio, and medical advice or rest is provided as necessary.

[0317] Specific examples

[0318] If employees use their smartphones to enter how much sleep they got last night and their current mood,

[0319] The prompt text is as follows:

[0320] Please enter the amount of sleep you got last night.

[0321] "How are you feeling right now? (Choices: happy, neutral, sad)"

[0322] An example of how an analytics engine analyzes data is using Python scripts to calculate average heart rate and stress levels, while a generative AI model assigns tasks using TensorFlow to recommend tasks based on an employee's stress level and emotion score.

[0323] The above is an embodiment of the present invention, which provides a method for achieving efficient business performance while protecting the health and safety of employees.

[0324] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0325] Step 1:

[0326] Users log in to the system using a device (smartphone) and enter their health and emotional data into a dedicated form. The input data includes health data such as sleep time, stress level, and heart rate, as well as their real-time emotional state and self-reported emotional score. This data is stored on the device and sent to the server.

[0327] Inputs: Sleep time, stress level, heart rate, emotional state, emotional score

[0328] Output: Save input data on the device and send data to the server

[0329] Specific behavior:

[0330] The user enters data into a dedicated form

[0331] Data is temporarily stored on the device

[0332] Send data to the server

[0333] Step 2:

[0334] The server receives the login information and the entered health and emotion data and stores it in a database, where the data for each employee is stored and ready for analysis.

[0335] Input: Data sent from the terminal

[0336] Output: Save data to database

[0337] Specific behavior:

[0338] The server receives the data

[0339] Save data to a database

[0340] Step 3:

[0341] The server's data analysis engine analyzes the health and emotion data stored in the database. For analysis, it runs Python scripts to evaluate stress levels and emotional states. It also uses a natural language processing API for emotion analysis.

[0342] Input: Health and emotion data in a database

[0343] Output: Evaluation results (stress level, emotional state)

[0344] Specific behavior:

[0345] Data analysis performed using Python scripts

[0346] Emotion analysis API for assessing emotional states

[0347] Step 4:

[0348] Based on the analysis results, the server extracts tasks that can be processed using the generative AI model and assigns them to the generative AI. Tasks include automation of manufacturing lines, welding, assembly, inspection, etc.

[0349] Input: Evaluation results (stress level, emotional state)

[0350] Output: Task assignment by the generative AI model

[0351] Specific behavior:

[0352] Run generative AI models with TensorFlow

[0353] Task extraction and assignment

[0354] Step 5:

[0355] The generative AI model executes the assigned task, for example, sending instructions to a robot to automate part of a manufacturing line and take over overnight work. The robot then carries out the assigned task and monitors its progress.

[0356] Input: Task instructions from a generative AI model

[0357] Output: Work results (work completion status)

[0358] Specific behavior:

[0359] Task instructions for robots

[0360] Execution and monitoring of work

[0361] Step 6:

[0362] The server collects the results of the tasks performed by the AI ​​model and aggregates and generates a report. This report is provided to employees and managers via a smartphone application. The report includes the start time, end time, task content, and evaluation results of the task.

[0363] Input: Business results from generative AI models

[0364] Output: Business result report

[0365] Specific behavior:

[0366] Collection of business results

[0367] Report generation and distribution

[0368] Step 7:

[0369] The server continuously inputs and analyzes health and emotional data to monitor the employee's condition, and if an abnormality is detected, a notification service is used to send an alert to the employee, who can then provide medical advice or rest as needed.

[0370] Input: Continuous health and emotional data

[0371] Output: Monitoring results (alerts, medical advice)

[0372] Specific behavior:

[0373] Continuous data entry and analysis

[0374] Sending alerts and taking action when an abnormality is detected

[0375] 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.

[0376] 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.

[0377] 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.

[0378] [Second embodiment]

[0379] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0380] 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.

[0381] 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).

[0382] 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.

[0383] 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.

[0384] 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).

[0385] 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.

[0386] 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.

[0387] 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.

[0388] 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.

[0389] In the smart glasses 214, 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.

[0390] 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."

[0391] This invention provides a method for building a system that uses AI to replace nighttime work while protecting the health of employees. This system is cloud-based and primarily consists of a server, terminals (PCs, smartphones, etc.), and users (employees and managers).

[0392] Explanation of program processing

[0393] 1. Data Entry

[0394] (User): Logs in to the system using a terminal and enters individual health data, such as sleep time, stress level, and heart rate. In addition, the user also enters their work schedule and nighttime work details.

[0395] 2. Data Analysis

[0396] (Server): Analyzes the received health data and work information. The analysis engine evaluates the employee's health status based on the health data, and if it determines that the employee's stress level or risk of overwork is high, it determines whether night work should be replaced.

[0397] 3. Task assignment

[0398] (Server): Based on the analysis results, the AI ​​model extracts tasks that can be processed and assigns them to the generating AI. This applies to a wide variety of tasks, such as night-time monitoring of IT systems and operating self-driving vehicles in transportation operations.

[0399] 4. AI-powered business execution

[0400] (Generative AI model): Executes assigned tasks. The AI ​​model performs designated nighttime duties with minimal human intervention. For example, in security work, it analyzes surveillance camera footage and notifies administrators if it detects any suspicious activity.

[0401] 5. Results feedback

[0402] (Server): Aggregates the results of the tasks performed by the generative AI model and generates a report. This report is sent to the user and administrator, detailing the progress and issues of the tasks.

[0403] 6. Health monitoring

[0404] (Server): Continuously inputs and analyzes health data. If an abnormality is detected, such as prolonged periods of high stress or lack of sleep, the server notifies the user and encourages them to rest if necessary.

[0405] Specific examples

[0406] For the transportation industry

[0407] (User): A transportation worker enters health data on their device. For example, they may learn that they have recently been getting less sleep and their stress levels have increased.

[0408] (Server): Analyzes health data and determines that the employee is overworked. At the same time, checks the nighttime delivery schedule and determines that nighttime delivery work can be performed by an autonomous truck.

[0409] (Server): Assigns nighttime delivery tasks to the generative AI model, which then sends instructions to the self-driving truck to operate the designated route.

[0410] (Generative AI model): Self-driving trucks carry out deliveries at night and monitor the progress of all routes.

[0411] (Server): Once the delivery is completed, the server aggregates the results of the work and sends a report to the user and administrator. The report includes the start time, end time, mileage, truck status, etc.

[0412] (Server): Continuously monitor the employee's health status and send notifications to encourage the employee to take necessary rest.

[0413] In this way, using generative AI to replace nighttime work will enable efficient work execution while protecting the health of employees.

[0414] The processing flow will be explained below.

[0415] Step 1:

[0416] (User): Logs in to the system using a terminal and enters personal health data (e.g., sleep time, stress level, heart rate) into a dedicated form. The user also enters the schedule and details of night work.

[0417] Step 2:

[0418] (Server): Receives login information and entered health data. The received data is stored in a database and prepared for the next analysis step.

[0419] Step 3:

[0420] (Server): The received data is fed into an analytics engine to assess the employee's health status. This assessment uses an algorithm that compares past and current health data to determine stress levels and risk of overwork.

[0421] Step 4:

[0422] (Server): Based on the health assessment results, it determines whether night work should be replaced by an AI. For example, if the stress level is very high or the employee is not getting enough sleep, it determines that night work should be shifted to an AI.

[0423] Step 5:

[0424] (Server): Creates a task list generated from the analysis results and assigns tasks to the generative AI model. Here, appropriate work tasks are assigned to AI suitable for nighttime work (for example, AI for monitoring self-driving trucks or IT systems).

[0425] Step 6:

[0426] (Generative AI model): Carries out assigned tasks. For example, in the case of a self-driving truck, the AI ​​automatically drives the designated route and completes the delivery mission.

[0427] Step 7:

[0428] (Server): Receives and analyzes data on the results of work execution (e.g., operation start time, end time, whether or not an abnormality occurred, etc.) from the AI ​​model. This confirms whether the work was completed successfully.

[0429] Step 8:

[0430] (Server): Organizes the results of the work and compiles them into a report. The report includes details of the work, the time it took to complete it, and the AI's performance.

[0431] Step 9:

[0432] (Server): Sends the generated report to the user and administrator. The user can check the report on their own device and confirm the results of their work.

[0433] Step 10:

[0434] (Server): Continuously monitors employee health data and analyzes new data as it is entered. If an abnormality is detected in the employee's health, the server notifies the user and provides appropriate rest or medical advice.

[0435] Example 1

[0436] 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."

[0437] In modern society, maintaining employee health while maintaining work efficiency is a major challenge. Night work, in particular, places a significant burden on employees' health, so appropriate health management and alternative work methods are required. However, systems that monitor employee health status in real time, detect overwork or high stress levels early, and use AI to substitute for night work as necessary are not yet widespread. As a result, there is a risk that appropriate health management will not be carried out and employees' health will be damaged.

[0438] 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.

[0439] In this invention, the server includes means for inputting employee health data, means for analyzing the health data and evaluating the employee's health status, means for substituting night work using an AI model based on the evaluation results, means for feeding back the results of the work performed by the AI ​​model, means for continuously monitoring the health data, means for detecting overwork or high stress based on the health data and the evaluation results and sending an alert, and means for operating an autonomous vehicle or monitoring system as a substitute for the night work. This enables real-time monitoring of employee health status and appropriate work substitution.

[0440] "Employee health data" refers to information that indicates an employee's health status, such as the employee's sleep time, stress level, and heart rate.

[0441] The "system" refers to a set of devices and software used to input, analyze, and evaluate employee health data, perform tasks using AI models, provide feedback on the results, and continuously monitor health data.

[0442] An "AI model" is a set of algorithms and data that uses artificial intelligence to perform a specific task, which in this case replaces night work.

[0443] "Feedback means" refers to the process and devices for aggregating the results of work performed by the AI ​​model and providing them to employees and managers as reports.

[0444] "Analytics Engine" means software and algorithms used to analyze received health data and assess employee health status.

[0445] "Means for detecting overwork or high stress" refers to processes and devices for determining whether an employee is in a state of overwork or high stress from the received health data and assessment results and generating an alert.

[0446] An "autonomous vehicle" is a vehicle that uses an AI model to automatically carry out transportation operations at night.

[0447] A "surveillance system" is a collection of cameras, sensors, and AI models used to operate them to perform nighttime surveillance operations.

[0448] This invention provides a system that uses AI to replace nighttime work while protecting the health of employees. This system is cloud-based and primarily consists of a server, terminals (PCs, smartphones, etc.), and users (employees and managers).

[0449] Hardware and Software Examples

[0450] The entire system consists of the following major components:

[0451] 1. Devices: PCs and smartphones used by employees. These serve as interfaces for entering health data and work schedules. Specific devices include Windows PCs, Macs, iPhones, and Android smartphones.

[0452] 2. Server: A central management system that receives data, analyzes it, runs AI models, and provides feedback on the results. This server environment is built using cloud services such as AWS (Amazon Web Services) and Google Cloud.

[0453] 3. Generative AI models: Artificial intelligence to replace nighttime operations. For example, they perform specific tasks such as controlling autonomous vehicles in transportation and monitoring systems in IT maintenance. These AI models are developed using deep learning frameworks such as TensorFlow and PyTorch.

[0454] Details of data processing and calculation

[0455] The specific data processing and calculations that the system performs are shown below.

[0456] 1. Data entry: A user logs in to the system using a terminal and enters health data (sleep time, stress level, heart rate, etc.) and work schedule. The terminal then sends this data to the server.

[0457] 2. Data analysis: The server receives the entered health data and work schedule. The analysis engine evaluates the employee's health status based on the received data. Specifically, it uses machine learning algorithms to calculate stress levels and the risk of overwork.

[0458] 3. Task allocation: The server extracts tasks that can be handled by the AI ​​model based on the analysis results. For example, if an employee is determined to be overworked, it assigns a nighttime delivery task to an autonomous vehicle. This allocation process is optimized by a specific scheduling algorithm within the server.

[0459] 4. AI execution: Generative AI models execute assigned tasks, such as driving a self-driving vehicle along a designated route, monitoring real-time conditions along the way, and responding appropriately if anomalies are detected.

[0460] 5. Result feedback: The server aggregates the results of the tasks performed by the AI ​​model and generates a feedback report that is sent to employees and managers. The report includes the start and end times of the trip, the mileage, and the condition of the truck.

[0461] 6. Health monitoring: The server monitors the health data continuously input by the user. If an abnormality is detected, such as prolonged high stress or lack of sleep, the server will send a notification to the user to encourage them to get adequate rest.

[0462] Specific examples

[0463] Below is a specific scenario in the transportation industry.

[0464] 1. User: A transportation worker uses a smartphone to enter the average number of hours of sleep he or she has had in the past week as "6 hours" and his or her stress level as "high." He or she also registers a schedule for the next night's delivery work.

[0465] 2. Server: The server analyzes the received data and determines that the employee is overworked. As a result, it decides to replace the nighttime delivery work with an autonomous vehicle.

[0466] 3. Server: Tasks are assigned to the generative AI model and route information is sent to the autonomous vehicle.

[0467] 4. Generative AI model: The autonomous vehicle will follow a designated route and monitor the situation in real time during the journey.

[0468] 5. Server: Once the delivery is completed, the server aggregates the operation logs and generates a detailed report, which is sent to employees and managers.

[0469] 6. Server: Continue to monitor employee health and send reminders to rest when necessary.

[0470] In this way, using generative AI models to replace night shift work enables efficient work execution while protecting the health of employees.

[0471] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0472] Step 1:

[0473] (Data Entry)

[0474] Users log in to the system using a terminal (PC or smartphone). Next, they use a dedicated input form to enter their own health data (sleep time, stress level, heart rate, etc.) and work schedule. The entered data is sent from the terminal to the server. A specific example of input data is information such as "sleep time: 6 hours, stress level: high." Input: Employee's health data and work schedule; Output: Raw data sent to the server.

[0475] Step 2:

[0476] (Data Analysis)

[0477] The server receives the health data and work schedule sent from the device. The received data is analyzed by an analysis engine. The analysis engine evaluates the employee's health status using, for example, a machine learning algorithm. Specifically, it calculates overwork risk and stress level based on the input sleep time and stress level. The analysis results are saved on the server as the employee's health evaluation. Input: raw data, output: health evaluation results.

[0478] Step 3:

[0479] (Task assignment)

[0480] Based on the health assessment results, the server extracts tasks that the AI ​​model can handle. For example, if an employee is determined to be overworked, a replacement will be needed for nighttime work. The server uses a scheduling algorithm to assign tasks, such as nighttime delivery, to an autonomous vehicle. The assigned task information is sent to the generative AI model. Input: Health assessment results, Output: Task information sent to the AI ​​model.

[0481] Step 4:

[0482] (Work execution using AI)

[0483] The generative AI model carries out tasks based on task information received from the server. For example, it sends instructions for nighttime delivery to an autonomous vehicle and has it operate along a specified route. The generative AI model collects data in real time from the vehicle's various sensors (GPS, camera, etc.) and monitors the operating status. If an abnormality is detected, it takes immediate action. Input: task information, output: results of the performed task (operation record). Specific actions include periodically checking the vehicle's location and detecting and avoiding obstacles.

[0484] Step 5:

[0485] (Result feedback)

[0486] The server aggregates the results of the tasks performed by the generative AI model. For example, it analyzes the autonomous vehicle's operation log (mileage, operating time, fuel consumption, etc.) and generates a detailed report. The generated report is sent to employees and managers via email or a dedicated dashboard. The report describes the progress and issues with the task execution. Input: Results of the performed task, Output: Detailed task report.

[0487] Step 6:

[0488] (Health monitoring)

[0489] The server monitors health data continuously input by employees. For example, an analysis engine continuously evaluates the data, and if a state of high stress or lack of sleep continues for a long period of time, the server generates a warning and notifies the employee. The notification includes suggestions for rest and advice to improve health status. Input: Continuously input health data, Output: Health status evaluation and warning message.

[0490] The above processing steps realize a system that monitors employee health in real time, replaces night work with a generative AI model as needed, and balances employee health with work efficiency.

[0491] (Application example 1)

[0492] 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."

[0493] Employees working at night can experience health problems such as sleep deprivation and excessive stress. Security work at night also requires the rapid detection and response of suspicious activity, which can be a burden on employees. It is necessary to perform security work efficiently and effectively while protecting the health of employees.

[0494] 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.

[0495] In this invention, the server includes means for inputting employee health data, means for analyzing the health data and evaluating the employee's health status, means for substituting night work using a generative AI model based on the evaluation results, means for providing feedback on the results of the work performed by the generative AI model, means for continuously monitoring the health data, means for the generative AI model to link with smart devices and analyze and notify night work in real time, means for engaging in security work using the generative AI model to monitor crime prevention and detect suspicious behavior, and means for providing the results of the security work to a manager in the form of a report, thereby enabling security work to be performed efficiently and effectively while protecting the health of employees.

[0496] "Employee health data" refers to biometric information and health status such as sleep time, stress level, and heart rate entered by employees.

[0497] "Means of analysis" refers to analytical engines and algorithms that evaluate employees' health status based on their health data and determine the risk of overwork or stress.

[0498] "Generative AI models" refer to artificial intelligence algorithms used to automate and replace the night-time work that would normally be performed by employees.

[0499] "Means for providing feedback" refers to the function of aggregating the results of work performed by the generative AI model and providing them to employees and managers in the form of a report.

[0500] "Means of monitoring" refers to a system that continuously collects and monitors employee health data and notifies employees when abnormalities are detected.

[0501] "Smart device" refers to a portable electronic device such as a smartphone, smart glasses, or a head-mounted display.

[0502] "Security surveillance" refers to the act of monitoring and analyzing suspicious behavior or events within a facility or area in real time using security equipment such as surveillance cameras.

[0503] "Suspicious behavior" refers to behavior or actions that are different from normal behavior and may pose a security risk.

[0504] "Report format" refers to the format of a report in which business results and security monitoring results are organized and recorded in written or digital form and provided to a manager.

[0505] The present invention relates to a system that efficiently and effectively performs security operations while protecting the health of employees. This system is operated on a cloud basis and is primarily composed of a server, terminals (smartphones, smart glasses, etc.), and users (security guards and administrators).

[0506] System Configuration

[0507] The server includes means for inputting employee health data, means for analyzing the health data and evaluating the health status of employees, means for substituting night work using a generative AI model based on the evaluation results, means for feeding back the results of work performed by the generative AI model, means for continuously monitoring the health data, means for the generative AI model to link with smart devices and analyze and notify night work in real time, means for using the generative AI model to engage in security work, perform crime prevention monitoring and detect suspicious behavior, and means for providing the results of the security work to an administrator in the form of a report.

[0508] Processing flow

[0509] Users wear smart glasses and input their health data (sleep time, stress level, heart rate, etc.). The health data is sent to a server and analyzed by an analysis engine. Based on the analysis results, the employee's health condition is evaluated, and if the employee is overworked or stressed, the generative AI model will replace them in night work.

[0510] The generative AI model works in conjunction with smart glasses to analyze the surrounding situation in real time. For example, it analyzes surveillance camera footage and, if it detects suspicious behavior, it will alert the user via audio notification. The results of the operations performed by the generative AI model are aggregated on a server and provided to the administrator in the form of a report.

[0511] Hardware and software used

[0512] Smart glasses: Using handheld electronic devices such as Google Glass or Vuzix Blade.

[0513] Cloud server: Use AWS or Google Cloud Platform.

[0514] Programming language: Python is used.

[0515] Database: Data management is performed using MySQL or PostgreSQL.

[0516] Analysis engine: Data analysis is performed using TensorFlow and PyTorch.

[0517] Specific examples

[0518] As a concrete example, a security guard who patrols the area around a warehouse at night from 11:00 PM to 7:00 AM wears smart glasses and inputs his health data. The analysis engine determines that the guard has a high heart rate and little sleep, and the generative AI model takes over the patrol. The AI ​​model analyzes surveillance camera footage and, if it detects any suspicious behavior, notifies the guard via voice. The patrol history and detection results are sent to the manager as a report.

[0519] Prompt Sentence Examples

[0520] I'm a security guard. I got 4 hours of sleep last night, my stress level is 8, and my heart rate is 110. My patrol schedule tonight is from 10 PM to 6 AM in the warehouse area. Thank you.

[0521] In this way, by using the system based on the present invention, it is possible to carry out security operations efficiently and effectively while protecting the health of employees.

[0522] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0523] Step 1:

[0524] The user puts on the smart glasses and inputs health data (sleep time, stress level, heart rate, etc.). This data is sent to the server through the smart glasses. For example, input data may include 4 hours of sleep last night, a stress level of 8, and a heart rate of 110. This provides the server with the employee's latest health status.

[0525] Step 2:

[0526] The server processes the received health data using an analysis engine (TensorFlow or PyTorch). The analysis engine evaluates each data point, such as sleep time, stress level, and heart rate, to make a comprehensive assessment of the employee's health condition. This analysis outputs results such as whether the employee is overworked or under high stress.

[0527] Step 3:

[0528] Based on the analysis results, the server determines whether the generative AI model should be used to replace the employee in nighttime work. If the employee's health condition is assessed as poor, the generative AI model issues instructions to replace the employee in nighttime patrol work. The generative AI model gains a detailed understanding of the patrol task and becomes capable of performing it automatically.

[0529] Step 4:

[0530] The generative AI model monitors the surroundings in real time through the smart glasses. It analyzes surveillance camera footage and sends an audio notification to the user when it detects suspicious behavior or anomalies. The input data are real-time video streams and surveillance camera data, and the output is the detection of suspicious behavior and an audio notification.

[0531] Step 5:

[0532] The server aggregates the results of the patrol operations performed by the generative AI model, including video logs from surveillance cameras, records of suspicious behavior detection, and user notification history. This data is stored in a database (MySQL or PostgreSQL) and used for subsequent processing.

[0533] Step 6:

[0534] The server generates reports based on the aggregated results of the work. The reports detail the progress of each patrol session, the results of any suspicious behavior detected, and the response status. The reports are provided to users and administrators in digital format.

[0535] Step 7:

[0536] The server continuously monitors employee health data. Each time new data is entered, the analytics engine reassesss the health status and, if necessary, substitutes tasks using a generative AI model. This ensures that employees are protected from overwork and stress.

[0537] Prompt Sentence Examples

[0538] I'm a security guard. I got 4 hours of sleep last night, my stress level is 8, and my heart rate is 110. My patrol schedule tonight is from 10 PM to 6 AM in the warehouse area. Thank you.

[0539] 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.

[0540] This invention is a system that analyzes employee health and emotional data, evaluates the employee's health and emotional state, and uses a generative AI model to replace nighttime work. This system is cloud-based and primarily consists of a server, terminals (PCs, smartphones, etc.), users (employees and managers), and an emotion engine.

[0541] Program processing explanation

[0542] 1. Data Entry

[0543] (User): Logs in to the system using a terminal and enters individual health data (e.g., sleep time, stress level, heart rate) and emotional data (e.g., real-time emotional state, self-reported emotional score) into a dedicated form. The user also enters the schedule and content of their night work.

[0544] 2. Data Analysis

[0545] (Server): Receives login information and entered health and emotion data. The received data is stored in a database and prepared for the next analysis step.

[0546] (Server): The data is fed into the data analysis engine to evaluate the employee's health and emotional state. The emotional engine determines the employee's psychological state based on the analysis of the emotional data. The health data and emotional data are integrated to evaluate the employee's overall stress level and psychological burden.

[0547] 3. Task assignment

[0548] (Server): Based on the analysis results, the generative AI model extracts tasks that can be processed and assigns them to the generative AI. Examples of applications include nighttime monitoring of IT systems and operating self-driving vehicles in transportation. Priority is given to employees with particularly unstable emotional states, with AI taking over their tasks.

[0549] 4. AI-powered business execution

[0550] (Generative AI model): Carries out assigned tasks. For example, in the case of a self-driving truck, AI automatically drives the designated route and completes the delivery. In addition, in monitoring IT systems, AI detects system anomalies in real time and automatically responds when an anomaly occurs.

[0551] 5. Results feedback

[0552] (Server): Aggregates the results of tasks performed by the generative AI model and generates a report. This report is sent to the user and administrator, detailing the task's progress and any issues. The report also includes the results of the emotion engine's evaluation of the user's emotional state.

[0553] 6. Health monitoring

[0554] (Server): Continuously inputs and analyzes health and emotional data. If an abnormality is detected, such as prolonged periods of high stress or persistent emotional problems, the server notifies the user and provides rest or medical advice as needed. It also sends notifications recommending mental health support and appropriate measures.

[0555] Specific examples

[0556] For the transportation industry

[0557] (User): A transportation worker enters health and emotional data on their own device, such as their recent short sleep time, high stress level, and unstable emotional state.

[0558] (Server): Analyzes health and emotional data to determine that the employee is overworked and emotionally unstable. At the same time, checks the nighttime delivery schedule and determines that nighttime delivery work can be performed by self-driving trucks.

[0559] (Server): Assigns nighttime delivery tasks to the generative AI model, which then sends instructions to the self-driving truck to operate the designated route.

[0560] (Generative AI model): Self-driving trucks carry out deliveries at night and monitor the progress of all routes.

[0561] (Server): Once the delivery is completed, the results are compiled and a report is sent to the user and administrator. The report includes the start and end times of the delivery, the distance traveled, the condition of the truck, and an evaluation of the employee's health and emotional state.

[0562] (Server): Continuously monitors the employee's health and emotional state, sends notifications to encourage the employee to take necessary rest, and provides mental health support and recommends appropriate measures.

[0563] In this way, using generative AI and emotion engines to replace night shifts allows employees to work efficiently while protecting their health and emotional state.

[0564] The processing flow will be explained below.

[0565] Step 1:

[0566] (User): Logs in to the system using a terminal and enters personal health data (e.g., sleep time, stress level, heart rate) and emotional data (e.g., real-time emotional state, self-reported emotional score) into a dedicated form. In addition, the user also enters the schedule and content of their night work.

[0567] Step 2:

[0568] (Server): Receives login information, health data, emotional data, night work schedule and details entered by the user and stores them in a database.

[0569] Step 3:

[0570] (Server): The stored health data and emotion data are input into the analysis engine. The analysis engine uses the health algorithm and emotion engine to evaluate the user's health and emotion state.

[0571] Step 4:

[0572] (Server): Based on the evaluation results, the generated stress level and risk of overwork are determined. The emotion engine analyzes the emotion data to determine the user's psychological state, and if necessary, evaluates the user as having a high psychological load.

[0573] Step 5:

[0574] (Server): Based on the analysis of health and emotional status, it determines whether night shifts require substitution. For example, if the stress level is high and the emotional state is unstable, it determines that AI substitution is necessary.

[0575] Step 6:

[0576] (Server): Based on the analysis results, extracts tasks that the generative AI model can handle (e.g., night-time monitoring of IT systems, operating autonomous trucks in transportation operations, etc.) and assigns the tasks to the generative AI model.

[0577] Step 7:

[0578] (Generative AI model): Carries out assigned tasks. For example, in the case of a self-driving truck, AI automatically drives the designated route and completes the delivery. In addition, in monitoring IT systems, AI detects system anomalies in real time and automatically responds when an anomaly occurs.

[0579] Step 8:

[0580] (Server): Receives and analyzes data on the results of the task execution (e.g., operation start time, end time, whether or not an abnormality occurred, etc.) from the generated AI model. This confirms whether the task was completed successfully.

[0581] Step 9:

[0582] (Server): Organizes the results of the work and compiles them into a report. The report includes details of the work, the time it took to complete it, the AI's performance, and the emotional state evaluation results from the emotion engine.

[0583] Step 10:

[0584] (Server): Sends the generated report to the user and administrator. The user can check the report on their own device and check the results of their work performance and their own health and emotional state.

[0585] Step 11:

[0586] (Server): Continuously monitors the user's health and emotional data, analyzing each new data entry. If an abnormality in the user's health is detected, the server notifies the user and provides appropriate rest and medical advice. If an abnormality in the user's emotional state is detected, the server sends a notification recommending mental health support and appropriate measures.

[0587] Example 2

[0588] 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."

[0589] In today's work environment, night shifts and continuous work can worsen employees' health and emotional state. However, there are limited systems in place to properly manage employees' health and emotional state and substitute for their work as needed. Therefore, there is a need for a way to maintain work efficiency while caring for employees' health and emotions.

[0590] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0591] In this invention, the server includes a means for inputting employee health information and emotional information, a means for analyzing the employee health information and emotional information and evaluating the employee's health and emotional state, and a means for substituting night work using a generative AI model based on the evaluation results. This makes it possible to monitor the employee's health and emotional state in real time and to substitute work using AI at the appropriate time.

[0592] "Employee" refers to a person who belongs to a particular organization and is engaged in a particular job by that organization.

[0593] "Health information" refers to information that indicates an employee's physical health status, and specifically includes data such as sleep time, heart rate, blood pressure, and stress level.

[0594] "Emotional information" refers to information that indicates an employee's mental or emotional state, including data such as self-reported emotional scores and real-time emotional states.

[0595] A "generative AI model" is a machine learning model that uses generative artificial intelligence techniques to perform specific tasks, such as operating autonomous driving or surveillance systems.

[0596] "Night work" refers to work performed outside of normal business hours, and specifically includes nighttime delivery work and system monitoring work.

[0597] "Means of input" refers to the devices or methods by which employees provide health and emotional information to the system, including terminals, login forms, etc.

[0598] "Means for evaluation" refers to a device or method for analyzing input data and determining the health status or emotional state of an employee, and includes a data analysis engine and an emotion engine.

[0599] "Alternative means" refers to devices or methods that use generative AI models to perform tasks performed by employees, such as operating a self-driving truck at night.

[0600] "Feedback means" refers to devices or methods for collecting the results of tasks performed by a generative AI model and providing them to relevant parties, including report generation devices and notification systems.

[0601] "Monitoring means" refers to devices and methods for continuously monitoring employee health and emotional information and detecting abnormalities, including continuous data collection systems.

[0602] This invention is a system that analyzes employee health and emotional information, evaluates the employee's health and emotional state, and uses a generative AI model to replace nighttime work. This system is cloud-based and primarily consists of a server, terminals (PCs, smartphones, etc.), users (employees and managers), and an emotion engine.

[0603] First, a user logs in to the system using a terminal. At this time, the user enters health information (e.g., sleep time, stress level, heart rate) and emotional information (e.g., real-time emotional state, self-reported emotional score) into a dedicated input form. The user also enters the schedule and details of night work. The terminal then sends this data to the server.

[0604] The server then stores the received login information, health information, and emotional information in a database. The data analysis engine then evaluates the employee's health status. This analysis is performed using Python's pandas library and scikit-learn. The data analysis engine calculates various health indicators (e.g., average sleep duration, heart rate variability, stress index).

[0605] The server then uses an emotion engine to assess the employee's psychological state based on the input emotion information. It uses natural language processing models (e.g., BERT and GPT-3) to calculate an emotion score from text-based self-reports. It integrates health and emotion information to assess the employee's overall stress level and psychological burden. This comprehensive assessment utilizes a data warehouse and business intelligence tools (e.g., Tableau).

[0606] Based on the analysis results, the server extracts tasks that the generative AI model can handle. This includes, for example, nighttime delivery work. The server assigns the extracted tasks to the generative AI model. The generative AI model is instructed on the details of the task (e.g., delivery route, delivery time). Instructions are given via an API.

[0607] The generative AI model carries out the assigned task. For example, in the case of a self-driving truck, the AI ​​automatically drives the designated route and completes the delivery mission. Machine learning frameworks such as TensorFlow and PyTorch are used for autonomous driving.

[0608] After the task is completed, the server aggregates the results of the task performed by the generative AI model. The task results (e.g., delivery completion time, distance traveled, fuel consumption) are generated as a report and sent to the user and administrator. The report details the task's progress, any issues, and the emotional state evaluation results of the emotion engine. The report is sent using the SMTP protocol.

[0609] The server continuously inputs and analyzes employee health and emotional information to detect abnormalities. For example, if high stress or emotional problems persist for a long period of time, the server will notify the user and provide rest or medical advice as necessary. Notifications are sent via SMS or email.

[0610] Example: Transportation industry

[0611] A transportation employee enters health information (e.g., recent short sleep duration) and emotional information (e.g., high stress, emotional instability) on their own device. The server receives this data and stores it in a database. Next, a data analysis engine is used to determine whether the employee is overworked. Based on the analysis results, it is determined that nighttime delivery work can be performed by an autonomous truck. The server assigns nighttime delivery tasks to a generative AI model. The generative AI model sends instructions to the autonomous truck to operate the specified route. The autonomous truck carries out the nighttime delivery, monitoring the delivery status of the entire route as it drives. Once the delivery is completed, the work results are compiled and a report is sent to the user and administrator. The report includes the start and end times of the trip, the mileage, the truck's condition, and an evaluation of the employee's health and emotional state. The server continuously monitors the employee's health and emotional state and sends notifications to encourage them to take necessary rest. It also provides mental health support and recommends appropriate measures.

[0612] Prompt Sentence Examples

[0613] "Please explain how a generative AI model could replace transportation tasks when employees are overworked and in an unstable emotional state."

[0614] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0615] Step 1:

[0616] A user logs in to the system using a terminal. The information entered here is a user ID and password, which are used for user authentication. The terminal sends the data entered in the login form to the server, and a login session begins. The output is a login session ID.

[0617] Step 2:

[0618] After logging in, users enter their health and emotional information into a dedicated form. Health information input items include sleep time, stress level, and heart rate, while emotional information input items include real-time emotional state and self-reported emotional score. Additionally, users also enter their nighttime work schedule and details. The device formats this data and sends it to the server. The output is formatted data.

[0619] Step 3:

[0620] The server stores the received health and emotion information in a database, where the stored data is organized for each individual employee. The input of the received data is formatted data, and the output is the stored data in the database.

[0621] Step 4:

[0622] The server inputs the stored data into a data analysis engine, which uses Python's pandas library and scikit-learn to analyze employee health status. The input data is health information, and the data analysis engine calculates average sleep time, heart rate variability, stress index, etc. The output is the analyzed health indicators.

[0623] Step 5:

[0624] The server analyzes the emotional information using an emotion engine. The emotion engine uses a natural language processing model (e.g., BERT or GPT-3) to calculate an emotion score from the input text-based emotion data. The input data is the emotional information, and the output is the emotion score.

[0625] Step 6:

[0626] The server integrates health and emotional information to assess employees' overall stress levels and psychological workload. Data warehouses and business intelligence tools (e.g., Tableau) are used for this assessment. The inputs are the analyzed health indicators and emotional scores, and the output is the overall assessment result.

[0627] Step 7:

[0628] The server extracts tasks that the generative AI model can process based on the overall evaluation results. For example, if an employee's health condition is deteriorating, the server selects nighttime work (e.g., nighttime delivery work) for that employee as a criterion. The input is the overall evaluation result, and the output is the extracted tasks.

[0629] Step 8:

[0630] The server assigns the extracted tasks to the generative AI model. The generative AI model is instructed on task details (e.g., delivery route, delivery time). Instructions are given through an API. The input is task details, and the output is the assignment of the task to the generative AI model.

[0631] Step 9:

[0632] Generative AI models carry out assigned tasks. For example, in the case of a self-driving truck, the AI ​​automatically drives a designated route and completes delivery tasks. Machine learning frameworks such as TensorFlow and PyTorch are used for autonomous driving. The input is the details of the task, and the output is the completed task result.

[0633] Step 10:

[0634] The server aggregates the results of the tasks performed by the generative AI model. It generates a report of the task results (e.g., delivery completion time, distance traveled, fuel consumption) and sends it to the user and administrator. The report details the task progress and issues, as well as the emotional state evaluation results from the emotion engine. The input is the completed task results, and the output is the generated report.

[0635] Step 11:

[0636] The server continuously inputs and analyzes employee health and emotional information to detect abnormalities. If high stress or emotional problems persist for a long period of time, the server notifies the user and provides rest or medical advice as needed. Notifications are sent via SMS or email. The input is the results of continuous data analysis, and the output is a notification to the user.

[0637] Prompt Sentence Examples

[0638] "Please explain how a generative AI model could replace transportation tasks when employees are overworked and in an unstable emotional state."

[0639] (Application example 2)

[0640] 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."

[0641] Factories are required to operate 24 hours a day, so managing employee health and maintaining work efficiency, especially during night shifts, is a key issue. However, employees accumulate fatigue due to long working hours, and are prone to overwork and emotional instability, especially during night shifts. This increases the risk of work errors and accidents, leading to reduced manufacturing efficiency and quality issues. Inadequate health management not only results in reduced productivity, but also has a negative impact on employee health. Therefore, there is an urgent need to provide a system that monitors employee health and emotional states in real time and, if necessary, automatically substitutes for night shifts.

[0642] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0643] In this invention, the server includes a means for inputting employee health data and emotional data, a means for analyzing the health data and emotional data and evaluating the employee's health and emotional state, a means for substituting night work using a generative AI model based on the evaluation results, a means for providing feedback on the results of work performed by the generative AI model, and a means for continuously monitoring the health data and emotional data. This makes it possible to evaluate employee health and emotional states in real time and, if necessary, substituting night work with an automated system. This is expected to reduce employee overwork and emotional instability, improve productivity, and maintain quality.

[0644] "Employee health data" refers to information about an employee's physical health, primarily including data such as sleep duration, stress level, and heart rate.

[0645] "Emotional data" refers to information about an employee's psychological state, including data such as real-time emotional state and self-reported emotional scores.

[0646] The "assessment means" is a component of the system that is responsible for analyzing the input health data and emotional data and evaluating the employee's health and emotional state.

[0647] A "generative AI model" is an artificial intelligence model that can perform specific tasks using machine learning technology and is used to replace night shift work based on the evaluation of employees' health and emotional state.

[0648] "Feedback mechanism" is a system component responsible for aggregating the results of work performed by the generative AI model and providing them to employees and managers in the form of reports.

[0649] "Monitoring means" refers to a system component that is responsible for continuously collecting and analyzing employee health and emotional data and monitoring their condition.

[0650] The "manufacturing industry" refers to the industry that produces various products, and since employees often perform complex and repetitive tasks, it is necessary to manage their health and maintain work efficiency.

[0651] "Night work" refers to work performed at night, outside of normal daytime working hours, and tends to place a greater physical and mental burden on employees.

[0652] The "reporting format" refers to a format in which the results of work performed by a generative AI model are organized and presented in a visually and easily understandable manner, making it easier for employees and managers to grasp the progress and results of work.

[0653] This invention is a system that allows factory workers to work night shifts more safely and efficiently. The system collects and analyzes employee health and emotional data, and then uses a generative AI model to substitute for night shift work as needed, thereby maintaining employee health and work efficiency.

[0654] System Configuration

[0655] This system is primarily composed of a server, terminals (such as smartphones), employees and managers, and a generative AI model.

[0656] Data Entry

[0657] Employees log in to the system using their smartphones and enter their health and emotional data. The health data includes sleep duration, stress level, and heart rate, while the emotional data includes real-time emotional state and self-reported emotional scores. This data entry is done using a dedicated form.

[0658] Data analysis

[0659] The server receives the login information and the entered health and emotion data and stores them in a database. The analysis engine analyzes this data and evaluates the employee's health and emotional state. This analysis is performed using scripts written in programming languages ​​such as Python. Sentiment analysis is also performed using a natural language processing API.

[0660] Task assignment

[0661] The server uses a generative AI model based on the analysis results to identify tasks that can be performed and assign them to the generative AI. For example, an AI model using TensorFlow can replace night shifts based on an employee's health and emotional state. Tasks include welding, assembly, and inspection work.

[0662] AI-powered business execution

[0663] The generative AI model then carries out the assigned tasks, for example, sending instructions to a robot to automate part of a manufacturing line, reducing the workload of employees by allowing the robot to take over nighttime work.

[0664] Results feedback

[0665] The server aggregates the results of the tasks performed by the generative AI model and generates a report, which is provided to employees and managers via a smartphone application. The report includes information such as the start and end times of tasks, the tasks performed, and evaluation results.

[0666] Health monitoring

[0667] The server continuously inputs and analyzes health and emotional data to monitor the employee's condition. If an abnormality is detected, an alert is sent to the employee using a notification service such as Twilio, and medical advice or rest is provided as necessary.

[0668] Specific examples

[0669] If employees use their smartphones to enter how much sleep they got last night and their current mood,

[0670] The prompt text is as follows:

[0671] Please enter the amount of sleep you got last night.

[0672] "How are you feeling right now? (Choices: happy, neutral, sad)"

[0673] An example of how an analytics engine analyzes data is using Python scripts to calculate average heart rate and stress levels, while a generative AI model assigns tasks using TensorFlow to recommend tasks based on an employee's stress level and emotion score.

[0674] The above is an embodiment of the present invention, which provides a method for achieving efficient business performance while protecting the health and safety of employees.

[0675] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0676] Step 1:

[0677] Users log in to the system using a device (smartphone) and enter their health and emotional data into a dedicated form. The input data includes health data such as sleep time, stress level, and heart rate, as well as their real-time emotional state and self-reported emotional score. This data is stored on the device and sent to the server.

[0678] Inputs: Sleep time, stress level, heart rate, emotional state, emotional score

[0679] Output: Save input data on the device and send data to the server

[0680] Specific behavior:

[0681] The user enters data into a dedicated form

[0682] Data is temporarily stored on the device

[0683] Send data to the server

[0684] Step 2:

[0685] The server receives the login information and the entered health and emotion data and stores it in a database, where the data for each employee is stored and ready for analysis.

[0686] Input: Data sent from the terminal

[0687] Output: Save data to database

[0688] Specific behavior:

[0689] The server receives the data

[0690] Save data to a database

[0691] Step 3:

[0692] The server's data analysis engine analyzes the health and emotion data stored in the database. For analysis, it runs Python scripts to evaluate stress levels and emotional states. It also uses a natural language processing API for emotion analysis.

[0693] Input: Health and emotion data in a database

[0694] Output: Evaluation results (stress level, emotional state)

[0695] Specific behavior:

[0696] Data analysis performed using Python scripts

[0697] Emotion analysis API for assessing emotional states

[0698] Step 4:

[0699] Based on the analysis results, the server extracts tasks that can be processed using the generative AI model and assigns them to the generative AI. Tasks include automation of manufacturing lines, welding, assembly, inspection, etc.

[0700] Input: Evaluation results (stress level, emotional state)

[0701] Output: Task assignment by the generative AI model

[0702] Specific behavior:

[0703] Run generative AI models with TensorFlow

[0704] Task extraction and assignment

[0705] Step 5:

[0706] The generative AI model executes the assigned task, for example, sending instructions to a robot to automate part of a manufacturing line and take over overnight work. The robot then carries out the assigned task and monitors its progress.

[0707] Input: Task instructions from a generative AI model

[0708] Output: Work results (work completion status)

[0709] Specific behavior:

[0710] Task instructions for robots

[0711] Execution and monitoring of work

[0712] Step 6:

[0713] The server collects the results of the tasks performed by the AI ​​model and aggregates and generates a report. This report is provided to employees and managers via a smartphone application. The report includes the start time, end time, task content, and evaluation results of the task.

[0714] Input: Business results from generative AI models

[0715] Output: Business result report

[0716] Specific behavior:

[0717] Collection of business results

[0718] Report generation and distribution

[0719] Step 7:

[0720] The server continuously inputs and analyzes health and emotional data to monitor the employee's condition, and if an abnormality is detected, a notification service is used to send an alert to the employee, who can then provide medical advice or rest as needed.

[0721] Input: Continuous health and emotional data

[0722] Output: Monitoring results (alerts, medical advice)

[0723] Specific behavior:

[0724] Continuous data entry and analysis

[0725] Sending alerts and taking action when an abnormality is detected

[0726] 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.

[0727] 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.

[0728] 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.

[0729] [Third embodiment]

[0730] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0731] 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.

[0732] 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).

[0733] 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.

[0734] 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.

[0735] 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).

[0736] 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.

[0737] 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.

[0738] 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.

[0739] 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.

[0740] 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.

[0741] 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."

[0742] This invention provides a method for building a system that uses AI to replace nighttime work while protecting the health of employees. This system is cloud-based and primarily consists of a server, terminals (PCs, smartphones, etc.), and users (employees and managers).

[0743] Explanation of program processing

[0744] 1. Data Entry

[0745] (User): Logs in to the system using a terminal and enters individual health data, such as sleep time, stress level, and heart rate. In addition, the user also enters their work schedule and nighttime work details.

[0746] 2. Data Analysis

[0747] (Server): Analyzes the received health data and work information. The analysis engine evaluates the employee's health status based on the health data, and if it determines that the employee's stress level or risk of overwork is high, it determines whether night work should be replaced.

[0748] 3. Task assignment

[0749] (Server): Based on the analysis results, the AI ​​model extracts tasks that can be processed and assigns them to the generating AI. This applies to a wide variety of tasks, such as night-time monitoring of IT systems and operating self-driving vehicles in transportation operations.

[0750] 4. AI-powered business execution

[0751] (Generative AI model): Executes assigned tasks. The AI ​​model performs designated nighttime duties with minimal human intervention. For example, in security work, it analyzes surveillance camera footage and notifies administrators if it detects any suspicious activity.

[0752] 5. Results feedback

[0753] (Server): Aggregates the results of the tasks performed by the generative AI model and generates a report. This report is sent to the user and administrator, detailing the progress and issues of the tasks.

[0754] 6. Health monitoring

[0755] (Server): Continuously inputs and analyzes health data. If an abnormality is detected, such as prolonged periods of high stress or lack of sleep, the server notifies the user and encourages them to rest if necessary.

[0756] Specific examples

[0757] For the transportation industry

[0758] (User): A transportation worker enters health data on their device. For example, they may learn that they have recently been getting less sleep and their stress levels have increased.

[0759] (Server): Analyzes health data and determines that the employee is overworked. At the same time, checks the nighttime delivery schedule and determines that nighttime delivery work can be performed by an autonomous truck.

[0760] (Server): Assigns nighttime delivery tasks to the generative AI model, which then sends instructions to the self-driving truck to operate the designated route.

[0761] (Generative AI model): Self-driving trucks carry out deliveries at night and monitor the progress of all routes.

[0762] (Server): Once the delivery is completed, the server aggregates the results of the work and sends a report to the user and administrator. The report includes the start time, end time, mileage, truck status, etc.

[0763] (Server): Continuously monitor the employee's health status and send notifications to encourage the employee to take necessary rest.

[0764] In this way, using generative AI to replace nighttime work will enable efficient work execution while protecting the health of employees.

[0765] The processing flow will be explained below.

[0766] Step 1:

[0767] (User): Logs in to the system using a terminal and enters personal health data (e.g., sleep time, stress level, heart rate) into a dedicated form. The user also enters the schedule and details of night work.

[0768] Step 2:

[0769] (Server): Receives login information and entered health data. The received data is stored in a database and prepared for the next analysis step.

[0770] Step 3:

[0771] (Server): The received data is fed into an analytics engine to assess the employee's health status. This assessment uses an algorithm that compares past and current health data to determine stress levels and risk of overwork.

[0772] Step 4:

[0773] (Server): Based on the health assessment results, it determines whether night work should be replaced by an AI. For example, if the stress level is very high or the employee is not getting enough sleep, it determines that night work should be shifted to an AI.

[0774] Step 5:

[0775] (Server): Creates a task list generated from the analysis results and assigns tasks to the generative AI model. Here, appropriate work tasks are assigned to AI suitable for nighttime work (for example, AI for monitoring self-driving trucks or IT systems).

[0776] Step 6:

[0777] (Generative AI model): Carries out assigned tasks. For example, in the case of a self-driving truck, the AI ​​automatically drives the designated route and completes the delivery mission.

[0778] Step 7:

[0779] (Server): Receives and analyzes data on the results of work execution (e.g., operation start time, end time, whether or not an abnormality occurred, etc.) from the AI ​​model. This confirms whether the work was completed successfully.

[0780] Step 8:

[0781] (Server): Organizes the results of the work and compiles them into a report. The report includes details of the work, the time it took to complete it, and the AI's performance.

[0782] Step 9:

[0783] (Server): Sends the generated report to the user and administrator. The user can check the report on their own device and confirm the results of their work.

[0784] Step 10:

[0785] (Server): Continuously monitors employee health data and analyzes new data as it is entered. If an abnormality is detected in the employee's health, the server notifies the user and provides appropriate rest or medical advice.

[0786] Example 1

[0787] 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."

[0788] In modern society, maintaining employee health while maintaining work efficiency is a major challenge. Night work, in particular, places a significant burden on employees' health, so appropriate health management and alternative work methods are required. However, systems that monitor employee health status in real time, detect overwork or high stress levels early, and use AI to substitute for night work as necessary are not yet widespread. As a result, there is a risk that appropriate health management will not be carried out and employees' health will be damaged.

[0789] 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.

[0790] In this invention, the server includes means for inputting employee health data, means for analyzing the health data and evaluating the employee's health status, means for substituting night work using an AI model based on the evaluation results, means for feeding back the results of the work performed by the AI ​​model, means for continuously monitoring the health data, means for detecting overwork or high stress based on the health data and the evaluation results and sending an alert, and means for operating an autonomous vehicle or monitoring system as a substitute for the night work. This enables real-time monitoring of employee health status and appropriate work substitution.

[0791] "Employee health data" refers to information that indicates an employee's health status, such as the employee's sleep time, stress level, and heart rate.

[0792] The "system" refers to a set of devices and software used to input, analyze, and evaluate employee health data, perform tasks using AI models, provide feedback on the results, and continuously monitor health data.

[0793] An "AI model" is a set of algorithms and data that uses artificial intelligence to perform a specific task, which in this case replaces night work.

[0794] "Feedback means" refers to the process and devices for aggregating the results of work performed by the AI ​​model and providing them to employees and managers as reports.

[0795] "Analytics Engine" means software and algorithms used to analyze received health data and assess employee health status.

[0796] "Means for detecting overwork or high stress" refers to processes and devices for determining whether an employee is in a state of overwork or high stress from the received health data and assessment results and generating an alert.

[0797] An "autonomous vehicle" is a vehicle that uses an AI model to automatically carry out transportation operations at night.

[0798] A "surveillance system" is a collection of cameras, sensors, and AI models used to operate them to perform nighttime surveillance operations.

[0799] This invention provides a system that uses AI to replace nighttime work while protecting the health of employees. This system is cloud-based and primarily consists of a server, terminals (PCs, smartphones, etc.), and users (employees and managers).

[0800] Hardware and Software Examples

[0801] The entire system consists of the following major components:

[0802] 1. Devices: PCs and smartphones used by employees. These serve as interfaces for entering health data and work schedules. Specific devices include Windows PCs, Macs, iPhones, and Android smartphones.

[0803] 2. Server: A central management system that receives data, analyzes it, runs AI models, and provides feedback on the results. This server environment is built using cloud services such as AWS (Amazon Web Services) and Google Cloud.

[0804] 3. Generative AI models: Artificial intelligence to replace nighttime operations. For example, they perform specific tasks such as controlling autonomous vehicles in transportation and monitoring systems in IT maintenance. These AI models are developed using deep learning frameworks such as TensorFlow and PyTorch.

[0805] Details of data processing and calculation

[0806] The specific data processing and calculations that the system performs are shown below.

[0807] 1. Data entry: A user logs in to the system using a terminal and enters health data (sleep time, stress level, heart rate, etc.) and work schedule. The terminal then sends this data to the server.

[0808] 2. Data analysis: The server receives the entered health data and work schedule. The analysis engine evaluates the employee's health status based on the received data. Specifically, it uses machine learning algorithms to calculate stress levels and the risk of overwork.

[0809] 3. Task allocation: The server extracts tasks that can be handled by the AI ​​model based on the analysis results. For example, if an employee is determined to be overworked, it assigns a nighttime delivery task to an autonomous vehicle. This allocation process is optimized by a specific scheduling algorithm within the server.

[0810] 4. AI execution: Generative AI models execute assigned tasks, such as driving a self-driving vehicle along a designated route, monitoring real-time conditions along the way, and responding appropriately if anomalies are detected.

[0811] 5. Result feedback: The server aggregates the results of the tasks performed by the AI ​​model and generates a feedback report that is sent to employees and managers. The report includes the start and end times of the trip, the mileage, and the condition of the truck.

[0812] 6. Health monitoring: The server monitors the health data continuously input by the user. If an abnormality is detected, such as prolonged high stress or lack of sleep, the server will send a notification to the user to encourage them to get adequate rest.

[0813] Specific examples

[0814] Below is a specific scenario in the transportation industry.

[0815] 1. User: A transportation worker uses a smartphone to enter the average number of hours of sleep he or she has had in the past week as "6 hours" and his or her stress level as "high." He or she also registers a schedule for the next night's delivery work.

[0816] 2. Server: The server analyzes the received data and determines that the employee is overworked. As a result, it decides to replace the nighttime delivery work with an autonomous vehicle.

[0817] 3. Server: Tasks are assigned to the generative AI model and route information is sent to the autonomous vehicle.

[0818] 4. Generative AI model: The autonomous vehicle will follow a designated route and monitor the situation in real time during the journey.

[0819] 5. Server: Once the delivery is completed, the server aggregates the operation logs and generates a detailed report, which is sent to employees and managers.

[0820] 6. Server: Continue to monitor employee health and send reminders to rest when necessary.

[0821] In this way, using generative AI models to replace night shift work enables efficient work execution while protecting the health of employees.

[0822] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0823] Step 1:

[0824] (Data Entry)

[0825] Users log in to the system using a terminal (PC or smartphone). Next, they use a dedicated input form to enter their own health data (sleep time, stress level, heart rate, etc.) and work schedule. The entered data is sent from the terminal to the server. A specific example of input data is information such as "sleep time: 6 hours, stress level: high." Input: Employee's health data and work schedule; Output: Raw data sent to the server.

[0826] Step 2:

[0827] (Data Analysis)

[0828] The server receives the health data and work schedule sent from the device. The received data is analyzed by an analysis engine. The analysis engine evaluates the employee's health status using, for example, a machine learning algorithm. Specifically, it calculates overwork risk and stress level based on the input sleep time and stress level. The analysis results are saved on the server as the employee's health evaluation. Input: raw data, output: health evaluation results.

[0829] Step 3:

[0830] (Task assignment)

[0831] Based on the health assessment results, the server extracts tasks that the AI ​​model can handle. For example, if an employee is determined to be overworked, a replacement will be needed for nighttime work. The server uses a scheduling algorithm to assign tasks, such as nighttime delivery, to an autonomous vehicle. The assigned task information is sent to the generative AI model. Input: Health assessment results, Output: Task information sent to the AI ​​model.

[0832] Step 4:

[0833] (Work execution using AI)

[0834] The generative AI model carries out tasks based on task information received from the server. For example, it sends instructions for nighttime delivery to an autonomous vehicle and has it operate along a specified route. The generative AI model collects data in real time from the vehicle's various sensors (GPS, camera, etc.) and monitors the operating status. If an abnormality is detected, it takes immediate action. Input: task information, output: results of the performed task (operation record). Specific actions include periodically checking the vehicle's location and detecting and avoiding obstacles.

[0835] Step 5:

[0836] (Result feedback)

[0837] The server aggregates the results of the tasks performed by the generative AI model. For example, it analyzes the autonomous vehicle's operation log (mileage, operating time, fuel consumption, etc.) and generates a detailed report. The generated report is sent to employees and managers via email or a dedicated dashboard. The report describes the progress and issues with the task execution. Input: Results of the performed task, Output: Detailed task report.

[0838] Step 6:

[0839] (Health monitoring)

[0840] The server monitors health data continuously input by employees. For example, an analysis engine continuously evaluates the data, and if a state of high stress or lack of sleep continues for a long period of time, the server generates a warning and notifies the employee. The notification includes suggestions for rest and advice to improve health status. Input: Continuously input health data, Output: Health status evaluation and warning message.

[0841] The above processing steps realize a system that monitors employee health in real time, replaces night work with a generative AI model as needed, and balances employee health with work efficiency.

[0842] (Application example 1)

[0843] 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."

[0844] Employees working at night can experience health problems such as sleep deprivation and excessive stress. Security work at night also requires the rapid detection and response of suspicious activity, which can be a burden on employees. It is necessary to perform security work efficiently and effectively while protecting the health of employees.

[0845] 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.

[0846] In this invention, the server includes means for inputting employee health data, means for analyzing the health data and evaluating the employee's health status, means for substituting night work using a generative AI model based on the evaluation results, means for providing feedback on the results of the work performed by the generative AI model, means for continuously monitoring the health data, means for the generative AI model to link with smart devices and analyze and notify night work in real time, means for engaging in security work using the generative AI model to monitor crime prevention and detect suspicious behavior, and means for providing the results of the security work to a manager in the form of a report, thereby enabling security work to be performed efficiently and effectively while protecting the health of employees.

[0847] "Employee health data" refers to biometric information and health status such as sleep time, stress level, and heart rate entered by employees.

[0848] "Means of analysis" refers to analytical engines and algorithms that evaluate employees' health status based on their health data and determine the risk of overwork or stress.

[0849] "Generative AI models" refer to artificial intelligence algorithms used to automate and replace the night-time work that would normally be performed by employees.

[0850] "Means for providing feedback" refers to the function of aggregating the results of work performed by the generative AI model and providing them to employees and managers in the form of a report.

[0851] "Means of monitoring" refers to a system that continuously collects and monitors employee health data and notifies employees when abnormalities are detected.

[0852] "Smart device" refers to a portable electronic device such as a smartphone, smart glasses, or a head-mounted display.

[0853] "Security surveillance" refers to the act of monitoring and analyzing suspicious behavior or events within a facility or area in real time using security equipment such as surveillance cameras.

[0854] "Suspicious behavior" refers to behavior or actions that are different from normal behavior and may pose a security risk.

[0855] "Report format" refers to the format of a report in which business results and security monitoring results are organized and recorded in written or digital form and provided to a manager.

[0856] The present invention relates to a system that efficiently and effectively performs security operations while protecting the health of employees. This system is operated on a cloud basis and is primarily composed of a server, terminals (smartphones, smart glasses, etc.), and users (security guards and administrators).

[0857] System Configuration

[0858] The server includes means for inputting employee health data, means for analyzing the health data and evaluating the health status of employees, means for substituting night work using a generative AI model based on the evaluation results, means for feeding back the results of work performed by the generative AI model, means for continuously monitoring the health data, means for the generative AI model to link with smart devices and analyze and notify night work in real time, means for using the generative AI model to engage in security work, perform crime prevention monitoring and detect suspicious behavior, and means for providing the results of the security work to an administrator in the form of a report.

[0859] Processing flow

[0860] Users wear smart glasses and input their health data (sleep time, stress level, heart rate, etc.). The health data is sent to a server and analyzed by an analysis engine. Based on the analysis results, the employee's health condition is evaluated, and if the employee is overworked or stressed, the generative AI model will replace them in night work.

[0861] The generative AI model works in conjunction with smart glasses to analyze the surrounding situation in real time. For example, it analyzes surveillance camera footage and, if it detects suspicious behavior, it will alert the user via audio notification. The results of the operations performed by the generative AI model are aggregated on a server and provided to the administrator in the form of a report.

[0862] Hardware and software used

[0863] Smart glasses: Using handheld electronic devices such as Google Glass or Vuzix Blade.

[0864] Cloud server: Use AWS or Google Cloud Platform.

[0865] Programming language: Python is used.

[0866] Database: Data management is performed using MySQL or PostgreSQL.

[0867] Analysis engine: Data analysis is performed using TensorFlow and PyTorch.

[0868] Specific examples

[0869] As a concrete example, a security guard who patrols the area around a warehouse at night from 11:00 PM to 7:00 AM wears smart glasses and inputs his health data. The analysis engine determines that the guard has a high heart rate and little sleep, and the generative AI model takes over the patrol. The AI ​​model analyzes surveillance camera footage and, if it detects any suspicious behavior, notifies the guard via voice. The patrol history and detection results are sent to the manager as a report.

[0870] Prompt Sentence Examples

[0871] I'm a security guard. I got 4 hours of sleep last night, my stress level is 8, and my heart rate is 110. My patrol schedule tonight is from 10 PM to 6 AM in the warehouse area. Thank you.

[0872] In this way, by using the system based on the present invention, it is possible to carry out security operations efficiently and effectively while protecting the health of employees.

[0873] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0874] Step 1:

[0875] The user puts on the smart glasses and inputs health data (sleep time, stress level, heart rate, etc.). This data is sent to the server through the smart glasses. For example, input data may include 4 hours of sleep last night, a stress level of 8, and a heart rate of 110. This provides the server with the employee's latest health status.

[0876] Step 2:

[0877] The server processes the received health data using an analysis engine (TensorFlow or PyTorch). The analysis engine evaluates each data point, such as sleep time, stress level, and heart rate, to make a comprehensive assessment of the employee's health condition. This analysis outputs results such as whether the employee is overworked or under high stress.

[0878] Step 3:

[0879] Based on the analysis results, the server determines whether the generative AI model should be used to replace the employee in nighttime work. If the employee's health condition is assessed as poor, the generative AI model issues instructions to replace the employee in nighttime patrol work. The generative AI model gains a detailed understanding of the patrol task and becomes capable of performing it automatically.

[0880] Step 4:

[0881] The generative AI model monitors the surroundings in real time through the smart glasses. It analyzes surveillance camera footage and sends an audio notification to the user when it detects suspicious behavior or anomalies. The input data are real-time video streams and surveillance camera data, and the output is the detection of suspicious behavior and an audio notification.

[0882] Step 5:

[0883] The server aggregates the results of the patrol operations performed by the generative AI model, including video logs from surveillance cameras, records of suspicious behavior detection, and user notification history. This data is stored in a database (MySQL or PostgreSQL) and used for subsequent processing.

[0884] Step 6:

[0885] The server generates reports based on the aggregated results of the work. The reports detail the progress of each patrol session, the results of any suspicious behavior detected, and the response status. The reports are provided to users and administrators in digital format.

[0886] Step 7:

[0887] The server continuously monitors employee health data. Each time new data is entered, the analytics engine reassesss the health status and, if necessary, substitutes tasks using a generative AI model. This ensures that employees are protected from overwork and stress.

[0888] Prompt Sentence Examples

[0889] I'm a security guard. I got 4 hours of sleep last night, my stress level is 8, and my heart rate is 110. My patrol schedule tonight is from 10 PM to 6 AM in the warehouse area. Thank you.

[0890] 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.

[0891] This invention is a system that analyzes employee health and emotional data, evaluates the employee's health and emotional state, and uses a generative AI model to replace nighttime work. This system is cloud-based and primarily consists of a server, terminals (PCs, smartphones, etc.), users (employees and managers), and an emotion engine.

[0892] Program processing explanation

[0893] 1. Data Entry

[0894] (User): Logs in to the system using a terminal and enters individual health data (e.g., sleep time, stress level, heart rate) and emotional data (e.g., real-time emotional state, self-reported emotional score) into a dedicated form. The user also enters the schedule and content of their night work.

[0895] 2. Data Analysis

[0896] (Server): Receives login information and entered health and emotion data. The received data is stored in a database and prepared for the next analysis step.

[0897] (Server): The data is fed into the data analysis engine to evaluate the employee's health and emotional state. The emotional engine determines the employee's psychological state based on the analysis of the emotional data. The health data and emotional data are integrated to evaluate the employee's overall stress level and psychological burden.

[0898] 3. Task assignment

[0899] (Server): Based on the analysis results, the generative AI model extracts tasks that can be processed and assigns them to the generative AI. Examples of applications include nighttime monitoring of IT systems and operating self-driving vehicles in transportation. Priority is given to employees with particularly unstable emotional states, with AI taking over their tasks.

[0900] 4. AI-powered business execution

[0901] (Generative AI model): Carries out assigned tasks. For example, in the case of a self-driving truck, AI automatically drives the designated route and completes the delivery. In addition, in monitoring IT systems, AI detects system anomalies in real time and automatically responds when an anomaly occurs.

[0902] 5. Results feedback

[0903] (Server): Aggregates the results of tasks performed by the generative AI model and generates a report. This report is sent to the user and administrator, detailing the task's progress and any issues. The report also includes the results of the emotion engine's evaluation of the user's emotional state.

[0904] 6. Health monitoring

[0905] (Server): Continuously inputs and analyzes health and emotional data. If an abnormality is detected, such as prolonged periods of high stress or persistent emotional problems, the server notifies the user and provides rest or medical advice as needed. It also sends notifications recommending mental health support and appropriate measures.

[0906] Specific examples

[0907] For the transportation industry

[0908] (User): A transportation worker enters health and emotional data on their own device, such as their recent short sleep time, high stress level, and unstable emotional state.

[0909] (Server): Analyzes health and emotional data to determine that the employee is overworked and emotionally unstable. At the same time, checks the nighttime delivery schedule and determines that nighttime delivery work can be performed by self-driving trucks.

[0910] (Server): Assigns nighttime delivery tasks to the generative AI model, which then sends instructions to the self-driving truck to operate the designated route.

[0911] (Generative AI model): Self-driving trucks carry out deliveries at night and monitor the progress of all routes.

[0912] (Server): Once the delivery is completed, the results are compiled and a report is sent to the user and administrator. The report includes the start and end times of the delivery, the distance traveled, the condition of the truck, and an evaluation of the employee's health and emotional state.

[0913] (Server): Continuously monitors the employee's health and emotional state, sends notifications to encourage the employee to take necessary rest, and provides mental health support and recommends appropriate measures.

[0914] In this way, using generative AI and emotion engines to replace night shifts allows employees to work efficiently while protecting their health and emotional state.

[0915] The processing flow will be explained below.

[0916] Step 1:

[0917] (User): Logs in to the system using a terminal and enters personal health data (e.g., sleep time, stress level, heart rate) and emotional data (e.g., real-time emotional state, self-reported emotional score) into a dedicated form. In addition, the user also enters the schedule and content of their night work.

[0918] Step 2:

[0919] (Server): Receives login information, health data, emotional data, night work schedule and details entered by the user and stores them in a database.

[0920] Step 3:

[0921] (Server): The stored health data and emotion data are input into the analysis engine. The analysis engine uses the health algorithm and emotion engine to evaluate the user's health and emotion state.

[0922] Step 4:

[0923] (Server): Based on the evaluation results, the generated stress level and risk of overwork are determined. The emotion engine analyzes the emotion data to determine the user's psychological state, and if necessary, evaluates the user as having a high psychological load.

[0924] Step 5:

[0925] (Server): Based on the analysis of health and emotional status, it determines whether night shifts require substitution. For example, if the stress level is high and the emotional state is unstable, it determines that AI substitution is necessary.

[0926] Step 6:

[0927] (Server): Based on the analysis results, extracts tasks that the generative AI model can handle (e.g., night-time monitoring of IT systems, operating autonomous trucks in transportation operations, etc.) and assigns the tasks to the generative AI model.

[0928] Step 7:

[0929] (Generative AI model): Carries out assigned tasks. For example, in the case of a self-driving truck, AI automatically drives the designated route and completes the delivery. In addition, in monitoring IT systems, AI detects system anomalies in real time and automatically responds when an anomaly occurs.

[0930] Step 8:

[0931] (Server): Receives and analyzes data on the results of the task execution (e.g., operation start time, end time, whether or not an abnormality occurred, etc.) from the generated AI model. This confirms whether the task was completed successfully.

[0932] Step 9:

[0933] (Server): Organizes the results of the work and compiles them into a report. The report includes details of the work, the time it took to complete it, the AI's performance, and the emotional state evaluation results from the emotion engine.

[0934] Step 10:

[0935] (Server): Sends the generated report to the user and administrator. The user can check the report on their own device and check the results of their work performance and their own health and emotional state.

[0936] Step 11:

[0937] (Server): Continuously monitors the user's health and emotional data, analyzing each new data entry. If an abnormality in the user's health is detected, the server notifies the user and provides appropriate rest and medical advice. If an abnormality in the user's emotional state is detected, the server sends a notification recommending mental health support and appropriate measures.

[0938] Example 2

[0939] 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."

[0940] In today's work environment, night shifts and continuous work can worsen employees' health and emotional state. However, there are limited systems in place to properly manage employees' health and emotional state and substitute for their work as needed. Therefore, there is a need for a way to maintain work efficiency while caring for employees' health and emotions.

[0941] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0942] In this invention, the server includes a means for inputting employee health information and emotional information, a means for analyzing the employee health information and emotional information and evaluating the employee's health and emotional state, and a means for substituting night work using a generative AI model based on the evaluation results. This makes it possible to monitor the employee's health and emotional state in real time and to substitute work using AI at the appropriate time.

[0943] "Employee" refers to a person who belongs to a particular organization and is engaged in a particular job by that organization.

[0944] "Health information" refers to information that indicates an employee's physical health status, and specifically includes data such as sleep time, heart rate, blood pressure, and stress level.

[0945] "Emotional information" refers to information that indicates an employee's mental or emotional state, including data such as self-reported emotional scores and real-time emotional states.

[0946] A "generative AI model" is a machine learning model that uses generative artificial intelligence techniques to perform specific tasks, such as operating autonomous driving or surveillance systems.

[0947] "Night work" refers to work performed outside of normal business hours, and specifically includes nighttime delivery work and system monitoring work.

[0948] "Means of input" refers to the devices or methods by which employees provide health and emotional information to the system, including terminals, login forms, etc.

[0949] "Means for evaluation" refers to a device or method for analyzing input data and determining the health status or emotional state of an employee, and includes a data analysis engine and an emotion engine.

[0950] "Alternative means" refers to devices or methods that use generative AI models to perform tasks performed by employees, such as operating a self-driving truck at night.

[0951] "Feedback means" refers to devices or methods for collecting the results of tasks performed by a generative AI model and providing them to relevant parties, including report generation devices and notification systems.

[0952] "Monitoring means" refers to devices and methods for continuously monitoring employee health and emotional information and detecting abnormalities, including continuous data collection systems.

[0953] This invention is a system that analyzes employee health and emotional information, evaluates the employee's health and emotional state, and uses a generative AI model to replace nighttime work. This system is cloud-based and primarily consists of a server, terminals (PCs, smartphones, etc.), users (employees and managers), and an emotion engine.

[0954] First, a user logs in to the system using a terminal. At this time, the user enters health information (e.g., sleep time, stress level, heart rate) and emotional information (e.g., real-time emotional state, self-reported emotional score) into a dedicated input form. The user also enters the schedule and details of night work. The terminal then sends this data to the server.

[0955] The server then stores the received login information, health information, and emotional information in a database. The data analysis engine then evaluates the employee's health status. This analysis is performed using Python's pandas library and scikit-learn. The data analysis engine calculates various health indicators (e.g., average sleep duration, heart rate variability, stress index).

[0956] The server then uses an emotion engine to assess the employee's psychological state based on the input emotion information. It uses natural language processing models (e.g., BERT and GPT-3) to calculate an emotion score from text-based self-reports. It integrates health and emotion information to assess the employee's overall stress level and psychological burden. This comprehensive assessment utilizes a data warehouse and business intelligence tools (e.g., Tableau).

[0957] Based on the analysis results, the server extracts tasks that the generative AI model can handle. This includes, for example, nighttime delivery work. The server assigns the extracted tasks to the generative AI model. The generative AI model is instructed on the details of the task (e.g., delivery route, delivery time). Instructions are given via an API.

[0958] The generative AI model carries out the assigned task. For example, in the case of a self-driving truck, the AI ​​automatically drives the designated route and completes the delivery mission. Machine learning frameworks such as TensorFlow and PyTorch are used for autonomous driving.

[0959] After the task is completed, the server aggregates the results of the task performed by the generative AI model. The task results (e.g., delivery completion time, distance traveled, fuel consumption) are generated as a report and sent to the user and administrator. The report details the task's progress, any issues, and the emotional state evaluation results of the emotion engine. The report is sent using the SMTP protocol.

[0960] The server continuously inputs and analyzes employee health and emotional information to detect abnormalities. For example, if high stress or emotional problems persist for a long period of time, the server will notify the user and provide rest or medical advice as necessary. Notifications are sent via SMS or email.

[0961] Example: Transportation industry

[0962] A transportation employee enters health information (e.g., recent short sleep duration) and emotional information (e.g., high stress, emotional instability) on their own device. The server receives this data and stores it in a database. Next, a data analysis engine is used to determine whether the employee is overworked. Based on the analysis results, it is determined that nighttime delivery work can be performed by an autonomous truck. The server assigns nighttime delivery tasks to a generative AI model. The generative AI model sends instructions to the autonomous truck to operate the specified route. The autonomous truck carries out the nighttime delivery, monitoring the delivery status of the entire route as it drives. Once the delivery is completed, the work results are compiled and a report is sent to the user and administrator. The report includes the start and end times of the trip, the mileage, the truck's condition, and an evaluation of the employee's health and emotional state. The server continuously monitors the employee's health and emotional state and sends notifications to encourage them to take necessary rest. It also provides mental health support and recommends appropriate measures.

[0963] Prompt Sentence Examples

[0964] "Please explain how a generative AI model could replace transportation tasks when employees are overworked and in an unstable emotional state."

[0965] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0966] Step 1:

[0967] A user logs in to the system using a terminal. The information entered here is a user ID and password, which are used for user authentication. The terminal sends the data entered in the login form to the server, and a login session begins. The output is a login session ID.

[0968] Step 2:

[0969] After logging in, users enter their health and emotional information into a dedicated form. Health information input items include sleep time, stress level, and heart rate, while emotional information input items include real-time emotional state and self-reported emotional score. Additionally, users also enter their nighttime work schedule and details. The device formats this data and sends it to the server. The output is formatted data.

[0970] Step 3:

[0971] The server stores the received health and emotion information in a database, where the stored data is organized for each individual employee. The input of the received data is formatted data, and the output is the stored data in the database.

[0972] Step 4:

[0973] The server inputs the stored data into a data analysis engine, which uses Python's pandas library and scikit-learn to analyze employee health status. The input data is health information, and the data analysis engine calculates average sleep time, heart rate variability, stress index, etc. The output is the analyzed health indicators.

[0974] Step 5:

[0975] The server analyzes the emotional information using an emotion engine. The emotion engine uses a natural language processing model (e.g., BERT or GPT-3) to calculate an emotion score from the input text-based emotion data. The input data is the emotional information, and the output is the emotion score.

[0976] Step 6:

[0977] The server integrates health and emotional information to assess employees' overall stress levels and psychological workload. Data warehouses and business intelligence tools (e.g., Tableau) are used for this assessment. The inputs are the analyzed health indicators and emotional scores, and the output is the overall assessment result.

[0978] Step 7:

[0979] The server extracts tasks that the generative AI model can process based on the overall evaluation results. For example, if an employee's health condition is deteriorating, the server selects nighttime work (e.g., nighttime delivery work) for that employee as a criterion. The input is the overall evaluation result, and the output is the extracted tasks.

[0980] Step 8:

[0981] The server assigns the extracted tasks to the generative AI model. The generative AI model is instructed on task details (e.g., delivery route, delivery time). Instructions are given through an API. The input is task details, and the output is the assignment of the task to the generative AI model.

[0982] Step 9:

[0983] Generative AI models carry out assigned tasks. For example, in the case of a self-driving truck, the AI ​​automatically drives a designated route and completes delivery tasks. Machine learning frameworks such as TensorFlow and PyTorch are used for autonomous driving. The input is the details of the task, and the output is the completed task result.

[0984] Step 10:

[0985] The server aggregates the results of the tasks performed by the generative AI model. It generates a report of the task results (e.g., delivery completion time, distance traveled, fuel consumption) and sends it to the user and administrator. The report details the task progress and issues, as well as the emotional state evaluation results from the emotion engine. The input is the completed task results, and the output is the generated report.

[0986] Step 11:

[0987] The server continuously inputs and analyzes employee health and emotional information to detect abnormalities. If high stress or emotional problems persist for a long period of time, the server notifies the user and provides rest or medical advice as needed. Notifications are sent via SMS or email. The input is the results of continuous data analysis, and the output is a notification to the user.

[0988] Prompt Sentence Examples

[0989] "Please explain how a generative AI model could replace transportation tasks when employees are overworked and in an unstable emotional state."

[0990] (Application example 2)

[0991] 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."

[0992] Factories are required to operate 24 hours a day, so managing employee health and maintaining work efficiency, especially during night shifts, is a key issue. However, employees accumulate fatigue due to long working hours, and are prone to overwork and emotional instability, especially during night shifts. This increases the risk of work errors and accidents, leading to reduced manufacturing efficiency and quality issues. Inadequate health management not only results in reduced productivity, but also has a negative impact on employee health. Therefore, there is an urgent need to provide a system that monitors employee health and emotional states in real time and, if necessary, automatically substitutes for night shifts.

[0993] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0994] In this invention, the server includes a means for inputting employee health data and emotional data, a means for analyzing the health data and emotional data and evaluating the employee's health and emotional state, a means for substituting night work using a generative AI model based on the evaluation results, a means for providing feedback on the results of work performed by the generative AI model, and a means for continuously monitoring the health data and emotional data. This makes it possible to evaluate employee health and emotional states in real time and, if necessary, substituting night work with an automated system. This is expected to reduce employee overwork and emotional instability, improve productivity, and maintain quality.

[0995] "Employee health data" refers to information about an employee's physical health, primarily including data such as sleep duration, stress level, and heart rate.

[0996] "Emotional data" refers to information about an employee's psychological state, including data such as real-time emotional state and self-reported emotional scores.

[0997] The "assessment means" is a component of the system that is responsible for analyzing the input health data and emotional data and evaluating the employee's health and emotional state.

[0998] A "generative AI model" is an artificial intelligence model that can perform specific tasks using machine learning technology and is used to replace night shift work based on the evaluation of employees' health and emotional state.

[0999] "Feedback mechanism" is a system component responsible for aggregating the results of work performed by the generative AI model and providing them to employees and managers in the form of reports.

[1000] "Monitoring means" refers to a system component that is responsible for continuously collecting and analyzing employee health and emotional data and monitoring their condition.

[1001] The "manufacturing industry" refers to the industry that produces various products, and since employees often perform complex and repetitive tasks, it is necessary to manage their health and maintain work efficiency.

[1002] "Night work" refers to work performed at night, outside of normal daytime working hours, and tends to place a greater physical and mental burden on employees.

[1003] The "reporting format" refers to a format in which the results of work performed by a generative AI model are organized and presented in a visually and easily understandable manner, making it easier for employees and managers to grasp the progress and results of work.

[1004] This invention is a system that allows factory workers to work night shifts more safely and efficiently. The system collects and analyzes employee health and emotional data, and then uses a generative AI model to substitute for night shift work as needed, thereby maintaining employee health and work efficiency.

[1005] System Configuration

[1006] This system is primarily composed of a server, terminals (such as smartphones), employees and managers, and a generative AI model.

[1007] Data Entry

[1008] Employees log in to the system using their smartphones and enter their health and emotional data. The health data includes sleep duration, stress level, and heart rate, while the emotional data includes real-time emotional state and self-reported emotional scores. This data entry is done using a dedicated form.

[1009] Data analysis

[1010] The server receives the login information and the entered health and emotion data and stores them in a database. The analysis engine analyzes this data and evaluates the employee's health and emotional state. This analysis is performed using scripts written in programming languages ​​such as Python. Sentiment analysis is also performed using a natural language processing API.

[1011] Task assignment

[1012] The server uses a generative AI model based on the analysis results to identify tasks that can be performed and assign them to the generative AI. For example, an AI model using TensorFlow can replace night shifts based on an employee's health and emotional state. Tasks include welding, assembly, and inspection work.

[1013] AI-powered business execution

[1014] The generative AI model then carries out the assigned tasks, for example, sending instructions to a robot to automate part of a manufacturing line, reducing the workload of employees by allowing the robot to take over nighttime work.

[1015] Results feedback

[1016] The server aggregates the results of the tasks performed by the generative AI model and generates a report, which is provided to employees and managers via a smartphone application. The report includes information such as the start and end times of tasks, the tasks performed, and evaluation results.

[1017] Health monitoring

[1018] The server continuously inputs and analyzes health and emotional data to monitor the employee's condition. If an abnormality is detected, an alert is sent to the employee using a notification service such as Twilio, and medical advice or rest is provided as necessary.

[1019] Specific examples

[1020] If employees use their smartphones to enter how much sleep they got last night and their current mood,

[1021] The prompt text is as follows:

[1022] Please enter the amount of sleep you got last night.

[1023] "How are you feeling right now? (Choices: happy, neutral, sad)"

[1024] An example of how an analytics engine analyzes data is using Python scripts to calculate average heart rate and stress levels, while a generative AI model assigns tasks using TensorFlow to recommend tasks based on an employee's stress level and emotion score.

[1025] The above is an embodiment of the present invention, which provides a method for achieving efficient business performance while protecting the health and safety of employees.

[1026] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1027] Step 1:

[1028] Users log in to the system using a device (smartphone) and enter their health and emotional data into a dedicated form. The input data includes health data such as sleep time, stress level, and heart rate, as well as their real-time emotional state and self-reported emotional score. This data is stored on the device and sent to the server.

[1029] Inputs: Sleep time, stress level, heart rate, emotional state, emotional score

[1030] Output: Save input data on the device and send data to the server

[1031] Specific behavior:

[1032] The user enters data into a dedicated form

[1033] Data is temporarily stored on the device

[1034] Send data to the server

[1035] Step 2:

[1036] The server receives the login information and the entered health and emotion data and stores it in a database, where the data for each employee is stored and ready for analysis.

[1037] Input: Data sent from the terminal

[1038] Output: Save data to database

[1039] Specific behavior:

[1040] The server receives the data

[1041] Save data to a database

[1042] Step 3:

[1043] The server's data analysis engine analyzes the health and emotion data stored in the database. For analysis, it runs Python scripts to evaluate stress levels and emotional states. It also uses a natural language processing API for emotion analysis.

[1044] Input: Health and emotion data in a database

[1045] Output: Evaluation results (stress level, emotional state)

[1046] Specific behavior:

[1047] Data analysis performed using Python scripts

[1048] Emotion analysis API for assessing emotional states

[1049] Step 4:

[1050] Based on the analysis results, the server extracts tasks that can be processed using the generative AI model and assigns them to the generative AI. Tasks include automation of manufacturing lines, welding, assembly, inspection, etc.

[1051] Input: Evaluation results (stress level, emotional state)

[1052] Output: Task assignment by the generative AI model

[1053] Specific behavior:

[1054] Run generative AI models with TensorFlow

[1055] Task extraction and assignment

[1056] Step 5:

[1057] The generative AI model executes the assigned task, for example, sending instructions to a robot to automate part of a manufacturing line and take over overnight work. The robot then carries out the assigned task and monitors its progress.

[1058] Input: Task instructions from a generative AI model

[1059] Output: Work results (work completion status)

[1060] Specific behavior:

[1061] Task instructions for robots

[1062] Execution and monitoring of work

[1063] Step 6:

[1064] The server collects the results of the tasks performed by the AI ​​model and aggregates and generates a report. This report is provided to employees and managers via a smartphone application. The report includes the start time, end time, task content, and evaluation results of the task.

[1065] Input: Business results from generative AI models

[1066] Output: Business result report

[1067] Specific behavior:

[1068] Collection of business results

[1069] Report generation and distribution

[1070] Step 7:

[1071] The server continuously inputs and analyzes health and emotional data to monitor the employee's condition, and if an abnormality is detected, a notification service is used to send an alert to the employee, who can then provide medical advice or rest as needed.

[1072] Input: Continuous health and emotional data

[1073] Output: Monitoring results (alerts, medical advice)

[1074] Specific behavior:

[1075] Continuous data entry and analysis

[1076] Sending alerts and taking action when an abnormality is detected

[1077] 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.

[1078] 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.

[1079] 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.

[1080] [Fourth embodiment]

[1081] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1082] 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.

[1083] 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).

[1084] 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.

[1085] 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.

[1086] 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).

[1087] 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.

[1088] 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.

[1089] 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.

[1090] 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.

[1091] 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.

[1092] 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.

[1093] 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."

[1094] This invention provides a method for building a system that uses AI to replace nighttime work while protecting the health of employees. This system is cloud-based and primarily consists of a server, terminals (PCs, smartphones, etc.), and users (employees and managers).

[1095] Explanation of program processing

[1096] 1. Data Entry

[1097] (User): Logs in to the system using a terminal and enters individual health data, such as sleep time, stress level, and heart rate. In addition, the user also enters their work schedule and nighttime work details.

[1098] 2. Data Analysis

[1099] (Server): Analyzes the received health data and work information. The analysis engine evaluates the employee's health status based on the health data, and if it determines that the employee's stress level or risk of overwork is high, it determines whether night work should be replaced.

[1100] 3. Task assignment

[1101] (Server): Based on the analysis results, the AI ​​model extracts tasks that can be processed and assigns them to the generating AI. This applies to a wide variety of tasks, such as night-time monitoring of IT systems and operating self-driving vehicles in transportation operations.

[1102] 4. AI-powered business execution

[1103] (Generative AI model): Executes assigned tasks. The AI ​​model performs designated nighttime duties with minimal human intervention. For example, in security work, it analyzes surveillance camera footage and notifies administrators if it detects any suspicious activity.

[1104] 5. Results feedback

[1105] (Server): Aggregates the results of the tasks performed by the generative AI model and generates a report. This report is sent to the user and administrator, detailing the progress and issues of the tasks.

[1106] 6. Health monitoring

[1107] (Server): Continuously inputs and analyzes health data. If an abnormality is detected, such as prolonged periods of high stress or lack of sleep, the server notifies the user and encourages them to rest if necessary.

[1108] Specific examples

[1109] For the transportation industry

[1110] (User): A transportation worker enters health data on their device. For example, they may learn that they have recently been getting less sleep and their stress levels have increased.

[1111] (Server): Analyzes health data and determines that the employee is overworked. At the same time, checks the nighttime delivery schedule and determines that nighttime delivery work can be performed by an autonomous truck.

[1112] (Server): Assigns nighttime delivery tasks to the generative AI model, which then sends instructions to the self-driving truck to operate the designated route.

[1113] (Generative AI model): Self-driving trucks carry out deliveries at night and monitor the progress of all routes.

[1114] (Server): Once the delivery is completed, the server aggregates the results of the work and sends a report to the user and administrator. The report includes the start time, end time, mileage, truck status, etc.

[1115] (Server): Continuously monitor the employee's health status and send notifications to encourage the employee to take necessary rest.

[1116] In this way, using generative AI to replace nighttime work will enable efficient work execution while protecting the health of employees.

[1117] The processing flow will be explained below.

[1118] Step 1:

[1119] (User): Logs in to the system using a terminal and enters personal health data (e.g., sleep time, stress level, heart rate) into a dedicated form. The user also enters the schedule and details of night work.

[1120] Step 2:

[1121] (Server): Receives login information and entered health data. The received data is stored in a database and prepared for the next analysis step.

[1122] Step 3:

[1123] (Server): The received data is fed into an analytics engine to assess the employee's health status. This assessment uses an algorithm that compares past and current health data to determine stress levels and risk of overwork.

[1124] Step 4:

[1125] (Server): Based on the health assessment results, it determines whether night work should be replaced by an AI. For example, if the stress level is very high or the employee is not getting enough sleep, it determines that night work should be shifted to an AI.

[1126] Step 5:

[1127] (Server): Creates a task list generated from the analysis results and assigns tasks to the generative AI model. Here, appropriate work tasks are assigned to AI suitable for nighttime work (for example, AI for monitoring self-driving trucks or IT systems).

[1128] Step 6:

[1129] (Generative AI model): Carries out assigned tasks. For example, in the case of a self-driving truck, the AI ​​automatically drives the designated route and completes the delivery mission.

[1130] Step 7:

[1131] (Server): Receives and analyzes data on the results of work execution (e.g., operation start time, end time, whether or not an abnormality occurred, etc.) from the AI ​​model. This confirms whether the work was completed successfully.

[1132] Step 8:

[1133] (Server): Organizes the results of the work and compiles them into a report. The report includes details of the work, the time it took to complete it, and the AI's performance.

[1134] Step 9:

[1135] (Server): Sends the generated report to the user and administrator. The user can check the report on their own device and confirm the results of their work.

[1136] Step 10:

[1137] (Server): Continuously monitors employee health data and analyzes new data as it is entered. If an abnormality is detected in the employee's health, the server notifies the user and provides appropriate rest or medical advice.

[1138] Example 1

[1139] 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."

[1140] In modern society, maintaining employee health while maintaining work efficiency is a major challenge. Night work, in particular, places a significant burden on employees' health, so appropriate health management and alternative work methods are required. However, systems that monitor employee health status in real time, detect overwork or high stress levels early, and use AI to substitute for night work as necessary are not yet widespread. As a result, there is a risk that appropriate health management will not be carried out and employees' health will be damaged.

[1141] 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.

[1142] In this invention, the server includes means for inputting employee health data, means for analyzing the health data and evaluating the employee's health status, means for substituting night work using an AI model based on the evaluation results, means for feeding back the results of the work performed by the AI ​​model, means for continuously monitoring the health data, means for detecting overwork or high stress based on the health data and the evaluation results and sending an alert, and means for operating an autonomous vehicle or monitoring system as a substitute for the night work. This enables real-time monitoring of employee health status and appropriate work substitution.

[1143] "Employee health data" refers to information that indicates an employee's health status, such as the employee's sleep time, stress level, and heart rate.

[1144] The "system" refers to a set of devices and software used to input, analyze, and evaluate employee health data, perform tasks using AI models, provide feedback on the results, and continuously monitor health data.

[1145] An "AI model" is a set of algorithms and data that uses artificial intelligence to perform a specific task, which in this case replaces night work.

[1146] "Feedback means" refers to the process and devices for aggregating the results of work performed by the AI ​​model and providing them to employees and managers as reports.

[1147] "Analytics Engine" means software and algorithms used to analyze received health data and assess employee health status.

[1148] "Means for detecting overwork or high stress" refers to processes and devices for determining whether an employee is in a state of overwork or high stress from the received health data and assessment results and generating an alert.

[1149] An "autonomous vehicle" is a vehicle that uses an AI model to automatically carry out transportation operations at night.

[1150] A "surveillance system" is a collection of cameras, sensors, and AI models used to operate them to perform nighttime surveillance operations.

[1151] This invention provides a system that uses AI to replace nighttime work while protecting the health of employees. This system is cloud-based and primarily consists of a server, terminals (PCs, smartphones, etc.), and users (employees and managers).

[1152] Hardware and Software Examples

[1153] The entire system consists of the following major components:

[1154] 1. Devices: PCs and smartphones used by employees. These serve as interfaces for entering health data and work schedules. Specific devices include Windows PCs, Macs, iPhones, and Android smartphones.

[1155] 2. Server: A central management system that receives data, analyzes it, runs AI models, and provides feedback on the results. This server environment is built using cloud services such as AWS (Amazon Web Services) and Google Cloud.

[1156] 3. Generative AI models: Artificial intelligence to replace nighttime operations. For example, they perform specific tasks such as controlling autonomous vehicles in transportation and monitoring systems in IT maintenance. These AI models are developed using deep learning frameworks such as TensorFlow and PyTorch.

[1157] Details of data processing and calculation

[1158] The specific data processing and calculations that the system performs are shown below.

[1159] 1. Data entry: A user logs in to the system using a terminal and enters health data (sleep time, stress level, heart rate, etc.) and work schedule. The terminal then sends this data to the server.

[1160] 2. Data analysis: The server receives the entered health data and work schedule. The analysis engine evaluates the employee's health status based on the received data. Specifically, it uses machine learning algorithms to calculate stress levels and the risk of overwork.

[1161] 3. Task allocation: The server extracts tasks that can be handled by the AI ​​model based on the analysis results. For example, if an employee is determined to be overworked, it assigns a nighttime delivery task to an autonomous vehicle. This allocation process is optimized by a specific scheduling algorithm within the server.

[1162] 4. AI execution: Generative AI models execute assigned tasks, such as driving a self-driving vehicle along a designated route, monitoring real-time conditions along the way, and responding appropriately if anomalies are detected.

[1163] 5. Result feedback: The server aggregates the results of the tasks performed by the AI ​​model and generates a feedback report that is sent to employees and managers. The report includes the start and end times of the trip, the mileage, and the condition of the truck.

[1164] 6. Health monitoring: The server monitors the health data continuously input by the user. If an abnormality is detected, such as prolonged high stress or lack of sleep, the server will send a notification to the user to encourage them to get adequate rest.

[1165] Specific examples

[1166] Below is a specific scenario in the transportation industry.

[1167] 1. User: A transportation worker uses a smartphone to enter the average number of hours of sleep he or she has had in the past week as "6 hours" and his or her stress level as "high." He or she also registers a schedule for the next night's delivery work.

[1168] 2. Server: The server analyzes the received data and determines that the employee is overworked. As a result, it decides to replace the nighttime delivery work with an autonomous vehicle.

[1169] 3. Server: Tasks are assigned to the generative AI model and route information is sent to the autonomous vehicle.

[1170] 4. Generative AI model: The autonomous vehicle will follow a designated route and monitor the situation in real time during the journey.

[1171] 5. Server: Once the delivery is completed, the server aggregates the operation logs and generates a detailed report, which is sent to employees and managers.

[1172] 6. Server: Continue to monitor employee health and send reminders to rest when necessary.

[1173] In this way, using generative AI models to replace night shift work enables efficient work execution while protecting the health of employees.

[1174] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1175] Step 1:

[1176] (Data Entry)

[1177] Users log in to the system using a terminal (PC or smartphone). Next, they use a dedicated input form to enter their own health data (sleep time, stress level, heart rate, etc.) and work schedule. The entered data is sent from the terminal to the server. A specific example of input data is information such as "sleep time: 6 hours, stress level: high." Input: Employee's health data and work schedule; Output: Raw data sent to the server.

[1178] Step 2:

[1179] (Data Analysis)

[1180] The server receives the health data and work schedule sent from the device. The received data is analyzed by an analysis engine. The analysis engine evaluates the employee's health status using, for example, a machine learning algorithm. Specifically, it calculates overwork risk and stress level based on the input sleep time and stress level. The analysis results are saved on the server as the employee's health evaluation. Input: raw data, output: health evaluation results.

[1181] Step 3:

[1182] (Task assignment)

[1183] Based on the health assessment results, the server extracts tasks that the AI ​​model can handle. For example, if an employee is determined to be overworked, a replacement will be needed for nighttime work. The server uses a scheduling algorithm to assign tasks, such as nighttime delivery, to an autonomous vehicle. The assigned task information is sent to the generative AI model. Input: Health assessment results, Output: Task information sent to the AI ​​model.

[1184] Step 4:

[1185] (Work execution using AI)

[1186] The generative AI model carries out tasks based on task information received from the server. For example, it sends instructions for nighttime delivery to an autonomous vehicle and has it operate along a specified route. The generative AI model collects data in real time from the vehicle's various sensors (GPS, camera, etc.) and monitors the operating status. If an abnormality is detected, it takes immediate action. Input: task information, output: results of the performed task (operation record). Specific actions include periodically checking the vehicle's location and detecting and avoiding obstacles.

[1187] Step 5:

[1188] (Result feedback)

[1189] The server aggregates the results of the tasks performed by the generative AI model. For example, it analyzes the autonomous vehicle's operation log (mileage, operating time, fuel consumption, etc.) and generates a detailed report. The generated report is sent to employees and managers via email or a dedicated dashboard. The report describes the progress and issues with the task execution. Input: Results of the performed task, Output: Detailed task report.

[1190] Step 6:

[1191] (Health monitoring)

[1192] The server monitors health data continuously input by employees. For example, an analysis engine continuously evaluates the data, and if a state of high stress or lack of sleep continues for a long period of time, the server generates a warning and notifies the employee. The notification includes suggestions for rest and advice to improve health status. Input: Continuously input health data, Output: Health status evaluation and warning message.

[1193] The above processing steps realize a system that monitors employee health in real time, replaces night work with a generative AI model as needed, and balances employee health with work efficiency.

[1194] (Application example 1)

[1195] 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."

[1196] Employees working at night can experience health problems such as sleep deprivation and excessive stress. Security work at night also requires the rapid detection and response of suspicious activity, which can be a burden on employees. It is necessary to perform security work efficiently and effectively while protecting the health of employees.

[1197] 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.

[1198] In this invention, the server includes means for inputting employee health data, means for analyzing the health data and evaluating the employee's health status, means for substituting night work using a generative AI model based on the evaluation results, means for providing feedback on the results of the work performed by the generative AI model, means for continuously monitoring the health data, means for the generative AI model to link with smart devices and analyze and notify night work in real time, means for engaging in security work using the generative AI model to monitor crime prevention and detect suspicious behavior, and means for providing the results of the security work to a manager in the form of a report, thereby enabling security work to be performed efficiently and effectively while protecting the health of employees.

[1199] "Employee health data" refers to biometric information and health status such as sleep time, stress level, and heart rate entered by employees.

[1200] "Means of analysis" refers to analytical engines and algorithms that evaluate employees' health status based on their health data and determine the risk of overwork or stress.

[1201] "Generative AI models" refer to artificial intelligence algorithms used to automate and replace the night-time work that would normally be performed by employees.

[1202] "Means for providing feedback" refers to the function of aggregating the results of work performed by the generative AI model and providing them to employees and managers in the form of a report.

[1203] "Means of monitoring" refers to a system that continuously collects and monitors employee health data and notifies employees when abnormalities are detected.

[1204] "Smart device" refers to a portable electronic device such as a smartphone, smart glasses, or a head-mounted display.

[1205] "Security surveillance" refers to the act of monitoring and analyzing suspicious behavior or events within a facility or area in real time using security equipment such as surveillance cameras.

[1206] "Suspicious behavior" refers to behavior or actions that are different from normal behavior and may pose a security risk.

[1207] "Report format" refers to the format of a report in which business results and security monitoring results are organized and recorded in written or digital form and provided to a manager.

[1208] The present invention relates to a system that efficiently and effectively performs security operations while protecting the health of employees. This system is operated on a cloud basis and is primarily composed of a server, terminals (smartphones, smart glasses, etc.), and users (security guards and administrators).

[1209] System Configuration

[1210] The server includes means for inputting employee health data, means for analyzing the health data and evaluating the health status of employees, means for substituting night work using a generative AI model based on the evaluation results, means for feeding back the results of work performed by the generative AI model, means for continuously monitoring the health data, means for the generative AI model to link with smart devices and analyze and notify night work in real time, means for using the generative AI model to engage in security work, perform crime prevention monitoring and detect suspicious behavior, and means for providing the results of the security work to an administrator in the form of a report.

[1211] Processing flow

[1212] Users wear smart glasses and input their health data (sleep time, stress level, heart rate, etc.). The health data is sent to a server and analyzed by an analysis engine. Based on the analysis results, the employee's health condition is evaluated, and if the employee is overworked or stressed, the generative AI model will replace them in night work.

[1213] The generative AI model works in conjunction with smart glasses to analyze the surrounding situation in real time. For example, it analyzes surveillance camera footage and, if it detects suspicious behavior, it will alert the user via audio notification. The results of the operations performed by the generative AI model are aggregated on a server and provided to the administrator in the form of a report.

[1214] Hardware and software used

[1215] Smart glasses: Using handheld electronic devices such as Google Glass or Vuzix Blade.

[1216] Cloud server: Use AWS or Google Cloud Platform.

[1217] Programming language: Python is used.

[1218] Database: Data management is performed using MySQL or PostgreSQL.

[1219] Analysis engine: Data analysis is performed using TensorFlow and PyTorch.

[1220] Specific examples

[1221] As a concrete example, a security guard who patrols the area around a warehouse at night from 11:00 PM to 7:00 AM wears smart glasses and inputs his health data. The analysis engine determines that the guard has a high heart rate and little sleep, and the generative AI model takes over the patrol. The AI ​​model analyzes surveillance camera footage and, if it detects any suspicious behavior, notifies the guard via voice. The patrol history and detection results are sent to the manager as a report.

[1222] Prompt Sentence Examples

[1223] I'm a security guard. I got 4 hours of sleep last night, my stress level is 8, and my heart rate is 110. My patrol schedule tonight is from 10 PM to 6 AM in the warehouse area. Thank you.

[1224] In this way, by using the system based on the present invention, it is possible to carry out security operations efficiently and effectively while protecting the health of employees.

[1225] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1226] Step 1:

[1227] The user puts on the smart glasses and inputs health data (sleep time, stress level, heart rate, etc.). This data is sent to the server through the smart glasses. For example, input data may include 4 hours of sleep last night, a stress level of 8, and a heart rate of 110. This provides the server with the employee's latest health status.

[1228] Step 2:

[1229] The server processes the received health data using an analysis engine (TensorFlow or PyTorch). The analysis engine evaluates each data point, such as sleep time, stress level, and heart rate, to make a comprehensive assessment of the employee's health condition. This analysis outputs results such as whether the employee is overworked or under high stress.

[1230] Step 3:

[1231] Based on the analysis results, the server determines whether the generative AI model should be used to replace the employee in nighttime work. If the employee's health condition is assessed as poor, the generative AI model issues instructions to replace the employee in nighttime patrol work. The generative AI model gains a detailed understanding of the patrol task and becomes capable of performing it automatically.

[1232] Step 4:

[1233] The generative AI model monitors the surroundings in real time through the smart glasses. It analyzes surveillance camera footage and sends an audio notification to the user when it detects suspicious behavior or anomalies. The input data are real-time video streams and surveillance camera data, and the output is the detection of suspicious behavior and an audio notification.

[1234] Step 5:

[1235] The server aggregates the results of the patrol operations performed by the generative AI model, including video logs from surveillance cameras, records of suspicious behavior detection, and user notification history. This data is stored in a database (MySQL or PostgreSQL) and used for subsequent processing.

[1236] Step 6:

[1237] The server generates reports based on the aggregated results of the work. The reports detail the progress of each patrol session, the results of any suspicious behavior detected, and the response status. The reports are provided to users and administrators in digital format.

[1238] Step 7:

[1239] The server continuously monitors employee health data. Each time new data is entered, the analytics engine reassesss the health status and, if necessary, substitutes tasks using a generative AI model. This ensures that employees are protected from overwork and stress.

[1240] Prompt Sentence Examples

[1241] I'm a security guard. I got 4 hours of sleep last night, my stress level is 8, and my heart rate is 110. My patrol schedule tonight is from 10 PM to 6 AM in the warehouse area. Thank you.

[1242] 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.

[1243] This invention is a system that analyzes employee health and emotional data, evaluates the employee's health and emotional state, and uses a generative AI model to replace nighttime work. This system is cloud-based and primarily consists of a server, terminals (PCs, smartphones, etc.), users (employees and managers), and an emotion engine.

[1244] Program processing explanation

[1245] 1. Data Entry

[1246] (User): Logs in to the system using a terminal and enters individual health data (e.g., sleep time, stress level, heart rate) and emotional data (e.g., real-time emotional state, self-reported emotional score) into a dedicated form. The user also enters the schedule and content of their night work.

[1247] 2. Data Analysis

[1248] (Server): Receives login information and entered health and emotion data. The received data is stored in a database and prepared for the next analysis step.

[1249] (Server): The data is fed into the data analysis engine to evaluate the employee's health and emotional state. The emotional engine determines the employee's psychological state based on the analysis of the emotional data. The health data and emotional data are integrated to evaluate the employee's overall stress level and psychological burden.

[1250] 3. Task assignment

[1251] (Server): Based on the analysis results, the generative AI model extracts tasks that can be processed and assigns them to the generative AI. Examples of applications include nighttime monitoring of IT systems and operating self-driving vehicles in transportation. Priority is given to employees with particularly unstable emotional states, with AI taking over their tasks.

[1252] 4. AI-powered business execution

[1253] (Generative AI model): Carries out assigned tasks. For example, in the case of a self-driving truck, AI automatically drives the designated route and completes the delivery. In addition, in monitoring IT systems, AI detects system anomalies in real time and automatically responds when an anomaly occurs.

[1254] 5. Results feedback

[1255] (Server): Aggregates the results of tasks performed by the generative AI model and generates a report. This report is sent to the user and administrator, detailing the task's progress and any issues. The report also includes the results of the emotion engine's evaluation of the user's emotional state.

[1256] 6. Health monitoring

[1257] (Server): Continuously inputs and analyzes health and emotional data. If an abnormality is detected, such as prolonged periods of high stress or persistent emotional problems, the server notifies the user and provides rest or medical advice as needed. It also sends notifications recommending mental health support and appropriate measures.

[1258] Specific examples

[1259] For the transportation industry

[1260] (User): A transportation worker enters health and emotional data on their own device, such as their recent short sleep time, high stress level, and unstable emotional state.

[1261] (Server): Analyzes health and emotional data to determine that the employee is overworked and emotionally unstable. At the same time, checks the nighttime delivery schedule and determines that nighttime delivery work can be performed by self-driving trucks.

[1262] (Server): Assigns nighttime delivery tasks to the generative AI model, which then sends instructions to the self-driving truck to operate the designated route.

[1263] (Generative AI model): Self-driving trucks carry out deliveries at night and monitor the progress of all routes.

[1264] (Server): Once the delivery is completed, the results are compiled and a report is sent to the user and administrator. The report includes the start and end times of the delivery, the distance traveled, the condition of the truck, and an evaluation of the employee's health and emotional state.

[1265] (Server): Continuously monitors the employee's health and emotional state, sends notifications to encourage the employee to take necessary rest, and provides mental health support and recommends appropriate measures.

[1266] In this way, using generative AI and emotion engines to replace night shifts allows employees to work efficiently while protecting their health and emotional state.

[1267] The processing flow will be explained below.

[1268] Step 1:

[1269] (User): Logs in to the system using a terminal and enters personal health data (e.g., sleep time, stress level, heart rate) and emotional data (e.g., real-time emotional state, self-reported emotional score) into a dedicated form. In addition, the user also enters the schedule and content of their night work.

[1270] Step 2:

[1271] (Server): Receives login information, health data, emotional data, night work schedule and details entered by the user and stores them in a database.

[1272] Step 3:

[1273] (Server): The stored health data and emotion data are input into the analysis engine. The analysis engine uses the health algorithm and emotion engine to evaluate the user's health and emotion state.

[1274] Step 4:

[1275] (Server): Based on the evaluation results, the generated stress level and risk of overwork are determined. The emotion engine analyzes the emotion data to determine the user's psychological state, and if necessary, evaluates the user as having a high psychological load.

[1276] Step 5:

[1277] (Server): Based on the analysis of health and emotional status, it determines whether night shifts require substitution. For example, if the stress level is high and the emotional state is unstable, it determines that AI substitution is necessary.

[1278] Step 6:

[1279] (Server): Based on the analysis results, extracts tasks that the generative AI model can handle (e.g., night-time monitoring of IT systems, operating autonomous trucks in transportation operations, etc.) and assigns the tasks to the generative AI model.

[1280] Step 7:

[1281] (Generative AI model): Carries out assigned tasks. For example, in the case of a self-driving truck, AI automatically drives the designated route and completes the delivery. In addition, in monitoring IT systems, AI detects system anomalies in real time and automatically responds when an anomaly occurs.

[1282] Step 8:

[1283] (Server): Receives and analyzes data on the results of the task execution (e.g., operation start time, end time, whether or not an abnormality occurred, etc.) from the generated AI model. This confirms whether the task was completed successfully.

[1284] Step 9:

[1285] (Server): Organizes the results of the work and compiles them into a report. The report includes details of the work, the time it took to complete it, the AI's performance, and the emotional state evaluation results from the emotion engine.

[1286] Step 10:

[1287] (Server): Sends the generated report to the user and administrator. The user can check the report on their own device and check the results of their work performance and their own health and emotional state.

[1288] Step 11:

[1289] (Server): Continuously monitors the user's health and emotional data, analyzing each new data entry. If an abnormality in the user's health is detected, the server notifies the user and provides appropriate rest and medical advice. If an abnormality in the user's emotional state is detected, the server sends a notification recommending mental health support and appropriate measures.

[1290] Example 2

[1291] 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."

[1292] In today's work environment, night shifts and continuous work can worsen employees' health and emotional state. However, there are limited systems in place to properly manage employees' health and emotional state and substitute for their work as needed. Therefore, there is a need for a way to maintain work efficiency while caring for employees' health and emotions.

[1293] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1294] In this invention, the server includes a means for inputting employee health information and emotional information, a means for analyzing the employee health information and emotional information and evaluating the employee's health and emotional state, and a means for substituting night work using a generative AI model based on the evaluation results. This makes it possible to monitor the employee's health and emotional state in real time and to substitute work using AI at the appropriate time.

[1295] "Employee" refers to a person who belongs to a particular organization and is engaged in a particular job by that organization.

[1296] "Health information" refers to information that indicates an employee's physical health status, and specifically includes data such as sleep time, heart rate, blood pressure, and stress level.

[1297] "Emotional information" refers to information that indicates an employee's mental or emotional state, including data such as self-reported emotional scores and real-time emotional states.

[1298] A "generative AI model" is a machine learning model that uses generative artificial intelligence techniques to perform specific tasks, such as operating autonomous driving or surveillance systems.

[1299] "Night work" refers to work performed outside of normal business hours, and specifically includes nighttime delivery work and system monitoring work.

[1300] "Means of input" refers to the devices or methods by which employees provide health and emotional information to the system, including terminals, login forms, etc.

[1301] "Means for evaluation" refers to a device or method for analyzing input data and determining the health status or emotional state of an employee, and includes a data analysis engine and an emotion engine.

[1302] "Alternative means" refers to devices or methods that use generative AI models to perform tasks performed by employees, such as operating a self-driving truck at night.

[1303] "Feedback means" refers to devices or methods for collecting the results of tasks performed by a generative AI model and providing them to relevant parties, including report generation devices and notification systems.

[1304] "Monitoring means" refers to devices and methods for continuously monitoring employee health and emotional information and detecting abnormalities, including continuous data collection systems.

[1305] This invention is a system that analyzes employee health and emotional information, evaluates the employee's health and emotional state, and uses a generative AI model to replace nighttime work. This system is cloud-based and primarily consists of a server, terminals (PCs, smartphones, etc.), users (employees and managers), and an emotion engine.

[1306] First, a user logs in to the system using a terminal. At this time, the user enters health information (e.g., sleep time, stress level, heart rate) and emotional information (e.g., real-time emotional state, self-reported emotional score) into a dedicated input form. The user also enters the schedule and details of night work. The terminal then sends this data to the server.

[1307] The server then stores the received login information, health information, and emotional information in a database. The data analysis engine then evaluates the employee's health status. This analysis is performed using Python's pandas library and scikit-learn. The data analysis engine calculates various health indicators (e.g., average sleep duration, heart rate variability, stress index).

[1308] The server then uses an emotion engine to assess the employee's psychological state based on the input emotion information. It uses natural language processing models (e.g., BERT and GPT-3) to calculate an emotion score from text-based self-reports. It integrates health and emotion information to assess the employee's overall stress level and psychological burden. This comprehensive assessment utilizes a data warehouse and business intelligence tools (e.g., Tableau).

[1309] Based on the analysis results, the server extracts tasks that the generative AI model can handle. This includes, for example, nighttime delivery work. The server assigns the extracted tasks to the generative AI model. The generative AI model is instructed on the details of the task (e.g., delivery route, delivery time). Instructions are given via an API.

[1310] The generative AI model carries out the assigned task. For example, in the case of a self-driving truck, the AI ​​automatically drives the designated route and completes the delivery mission. Machine learning frameworks such as TensorFlow and PyTorch are used for autonomous driving.

[1311] After the task is completed, the server aggregates the results of the task performed by the generative AI model. The task results (e.g., delivery completion time, distance traveled, fuel consumption) are generated as a report and sent to the user and administrator. The report details the task's progress, any issues, and the emotional state evaluation results of the emotion engine. The report is sent using the SMTP protocol.

[1312] The server continuously inputs and analyzes employee health and emotional information to detect abnormalities. For example, if high stress or emotional problems persist for a long period of time, the server will notify the user and provide rest or medical advice as necessary. Notifications are sent via SMS or email.

[1313] Example: Transportation industry

[1314] A transportation employee enters health information (e.g., recent short sleep duration) and emotional information (e.g., high stress, emotional instability) on their own device. The server receives this data and stores it in a database. Next, a data analysis engine is used to determine whether the employee is overworked. Based on the analysis results, it is determined that nighttime delivery work can be performed by an autonomous truck. The server assigns nighttime delivery tasks to a generative AI model. The generative AI model sends instructions to the autonomous truck to operate the specified route. The autonomous truck carries out the nighttime delivery, monitoring the delivery status of the entire route as it drives. Once the delivery is completed, the work results are compiled and a report is sent to the user and administrator. The report includes the start and end times of the trip, the mileage, the truck's condition, and an evaluation of the employee's health and emotional state. The server continuously monitors the employee's health and emotional state and sends notifications to encourage them to take necessary rest. It also provides mental health support and recommends appropriate measures.

[1315] Prompt Sentence Examples

[1316] "Please explain how a generative AI model could replace transportation tasks when employees are overworked and in an unstable emotional state."

[1317] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1318] Step 1:

[1319] A user logs in to the system using a terminal. The information entered here is a user ID and password, which are used for user authentication. The terminal sends the data entered in the login form to the server, and a login session begins. The output is a login session ID.

[1320] Step 2:

[1321] After logging in, users enter their health and emotional information into a dedicated form. Health information input items include sleep time, stress level, and heart rate, while emotional information input items include real-time emotional state and self-reported emotional score. Additionally, users also enter their nighttime work schedule and details. The device formats this data and sends it to the server. The output is formatted data.

[1322] Step 3:

[1323] The server stores the received health and emotion information in a database, where the stored data is organized for each individual employee. The input of the received data is formatted data, and the output is the stored data in the database.

[1324] Step 4:

[1325] The server inputs the stored data into a data analysis engine, which uses Python's pandas library and scikit-learn to analyze employee health status. The input data is health information, and the data analysis engine calculates average sleep time, heart rate variability, stress index, etc. The output is the analyzed health indicators.

[1326] Step 5:

[1327] The server analyzes the emotional information using an emotion engine. The emotion engine uses a natural language processing model (e.g., BERT or GPT-3) to calculate an emotion score from the input text-based emotion data. The input data is the emotional information, and the output is the emotion score.

[1328] Step 6:

[1329] The server integrates health and emotional information to assess employees' overall stress levels and psychological workload. Data warehouses and business intelligence tools (e.g., Tableau) are used for this assessment. The inputs are the analyzed health indicators and emotional scores, and the output is the overall assessment result.

[1330] Step 7:

[1331] The server extracts tasks that the generative AI model can process based on the overall evaluation results. For example, if an employee's health condition is deteriorating, the server selects nighttime work (e.g., nighttime delivery work) for that employee as a criterion. The input is the overall evaluation result, and the output is the extracted tasks.

[1332] Step 8:

[1333] The server assigns the extracted tasks to the generative AI model. The generative AI model is instructed on task details (e.g., delivery route, delivery time). Instructions are given through an API. The input is task details, and the output is the assignment of the task to the generative AI model.

[1334] Step 9:

[1335] Generative AI models carry out assigned tasks. For example, in the case of a self-driving truck, the AI ​​automatically drives a designated route and completes delivery tasks. Machine learning frameworks such as TensorFlow and PyTorch are used for autonomous driving. The input is the details of the task, and the output is the completed task result.

[1336] Step 10:

[1337] The server aggregates the results of the tasks performed by the generative AI model. It generates a report of the task results (e.g., delivery completion time, distance traveled, fuel consumption) and sends it to the user and administrator. The report details the task progress and issues, as well as the emotional state evaluation results from the emotion engine. The input is the completed task results, and the output is the generated report.

[1338] Step 11:

[1339] The server continuously inputs and analyzes employee health and emotional information to detect abnormalities. If high stress or emotional problems persist for a long period of time, the server notifies the user and provides rest or medical advice as needed. Notifications are sent via SMS or email. The input is the results of continuous data analysis, and the output is a notification to the user.

[1340] Prompt Sentence Examples

[1341] "Please explain how a generative AI model could replace transportation tasks when employees are overworked and in an unstable emotional state."

[1342] (Application example 2)

[1343] 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."

[1344] Factories are required to operate 24 hours a day, so managing employee health and maintaining work efficiency, especially during night shifts, is a key issue. However, employees accumulate fatigue due to long working hours, and are prone to overwork and emotional instability, especially during night shifts. This increases the risk of work errors and accidents, leading to reduced manufacturing efficiency and quality issues. Inadequate health management not only results in reduced productivity, but also has a negative impact on employee health. Therefore, there is an urgent need to provide a system that monitors employee health and emotional states in real time and, if necessary, automatically substitutes for night shifts.

[1345] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1346] In this invention, the server includes a means for inputting employee health data and emotional data, a means for analyzing the health data and emotional data and evaluating the employee's health and emotional state, a means for substituting night work using a generative AI model based on the evaluation results, a means for providing feedback on the results of work performed by the generative AI model, and a means for continuously monitoring the health data and emotional data. This makes it possible to evaluate employee health and emotional states in real time and, if necessary, substituting night work with an automated system. This is expected to reduce employee overwork and emotional instability, improve productivity, and maintain quality.

[1347] "Employee health data" refers to information about an employee's physical health, primarily including data such as sleep duration, stress level, and heart rate.

[1348] "Emotional data" refers to information about an employee's psychological state, including data such as real-time emotional state and self-reported emotional scores.

[1349] The "assessment means" is a component of the system that is responsible for analyzing the input health data and emotional data and evaluating the employee's health and emotional state.

[1350] A "generative AI model" is an artificial intelligence model that can perform specific tasks using machine learning technology and is used to replace night shift work based on the evaluation of employees' health and emotional state.

[1351] "Feedback mechanism" is a system component responsible for aggregating the results of work performed by the generative AI model and providing them to employees and managers in the form of reports.

[1352] "Monitoring means" refers to a system component that is responsible for continuously collecting and analyzing employee health and emotional data and monitoring their condition.

[1353] The "manufacturing industry" refers to the industry that produces various products, and since employees often perform complex and repetitive tasks, it is necessary to manage their health and maintain work efficiency.

[1354] "Night work" refers to work performed at night, outside of normal daytime working hours, and tends to place a greater physical and mental burden on employees.

[1355] The "reporting format" refers to a format in which the results of work performed by a generative AI model are organized and presented in a visually and easily understandable manner, making it easier for employees and managers to grasp the progress and results of work.

[1356] This invention is a system that allows factory workers to work night shifts more safely and efficiently. The system collects and analyzes employee health and emotional data, and then uses a generative AI model to substitute for night shift work as needed, thereby maintaining employee health and work efficiency.

[1357] System Configuration

[1358] This system is primarily composed of a server, terminals (such as smartphones), employees and managers, and a generative AI model.

[1359] Data Entry

[1360] Employees log in to the system using their smartphones and enter their health and emotional data. The health data includes sleep duration, stress level, and heart rate, while the emotional data includes real-time emotional state and self-reported emotional scores. This data entry is done using a dedicated form.

[1361] Data analysis

[1362] The server receives the login information and the entered health and emotion data and stores them in a database. The analysis engine analyzes this data and evaluates the employee's health and emotional state. This analysis is performed using scripts written in programming languages ​​such as Python. Sentiment analysis is also performed using a natural language processing API.

[1363] Task assignment

[1364] The server uses a generative AI model based on the analysis results to identify tasks that can be performed and assign them to the generative AI. For example, an AI model using TensorFlow can replace night shifts based on an employee's health and emotional state. Tasks include welding, assembly, and inspection work.

[1365] AI-powered business execution

[1366] The generative AI model then carries out the assigned tasks, for example, sending instructions to a robot to automate part of a manufacturing line, reducing the workload of employees by allowing the robot to take over nighttime work.

[1367] Results feedback

[1368] The server aggregates the results of the tasks performed by the generative AI model and generates a report, which is provided to employees and managers via a smartphone application. The report includes information such as the start and end times of tasks, the tasks performed, and evaluation results.

[1369] Health monitoring

[1370] The server continuously inputs and analyzes health and emotional data to monitor the employee's condition. If an abnormality is detected, an alert is sent to the employee using a notification service such as Twilio, and medical advice or rest is provided as necessary.

[1371] Specific examples

[1372] If employees use their smartphones to enter how much sleep they got last night and their current mood,

[1373] The prompt text is as follows:

[1374] Please enter the amount of sleep you got last night.

[1375] "How are you feeling right now? (Choices: happy, neutral, sad)"

[1376] An example of how an analytics engine analyzes data is using Python scripts to calculate average heart rate and stress levels, while a generative AI model assigns tasks using TensorFlow to recommend tasks based on an employee's stress level and emotion score.

[1377] The above is an embodiment of the present invention, which provides a method for achieving efficient business performance while protecting the health and safety of employees.

[1378] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1379] Step 1:

[1380] Users log in to the system using a device (smartphone) and enter their health and emotional data into a dedicated form. The input data includes health data such as sleep time, stress level, and heart rate, as well as their real-time emotional state and self-reported emotional score. This data is stored on the device and sent to the server.

[1381] Inputs: Sleep time, stress level, heart rate, emotional state, emotional score

[1382] Output: Save input data on the device and send data to the server

[1383] Specific behavior:

[1384] The user enters data into a dedicated form

[1385] Data is temporarily stored on the device

[1386] Send data to the server

[1387] Step 2:

[1388] The server receives the login information and the entered health and emotion data and stores it in a database, where the data for each employee is stored and ready for analysis.

[1389] Input: Data sent from the terminal

[1390] Output: Save data to database

[1391] Specific behavior:

[1392] The server receives the data

[1393] Save data to a database

[1394] Step 3:

[1395] The server's data analysis engine analyzes the health and emotion data stored in the database. For analysis, it runs Python scripts to evaluate stress levels and emotional states. It also uses a natural language processing API for emotion analysis.

[1396] Input: Health and emotion data in a database

[1397] Output: Evaluation results (stress level, emotional state)

[1398] Specific behavior:

[1399] Data analysis performed using Python scripts

[1400] Emotion analysis API for assessing emotional states

[1401] Step 4:

[1402] Based on the analysis results, the server extracts tasks that can be processed using the generative AI model and assigns them to the generative AI. Tasks include automation of manufacturing lines, welding, assembly, inspection, etc.

[1403] Input: Evaluation results (stress level, emotional state)

[1404] Output: Task assignment by the generative AI model

[1405] Specific behavior:

[1406] Run generative AI models with TensorFlow

[1407] Task extraction and assignment

[1408] Step 5:

[1409] The generative AI model executes the assigned task, for example, sending instructions to a robot to automate part of a manufacturing line and take over overnight work. The robot then carries out the assigned task and monitors its progress.

[1410] Input: Task instructions from a generative AI model

[1411] Output: Work results (work completion status)

[1412] Specific behavior:

[1413] Task instructions for robots

[1414] Execution and monitoring of work

[1415] Step 6:

[1416] The server collects the results of the tasks performed by the AI ​​model and aggregates and generates a report. This report is provided to employees and managers via a smartphone application. The report includes the start time, end time, task content, and evaluation results of the task.

[1417] Input: Business results from generative AI models

[1418] Output: Business result report

[1419] Specific behavior:

[1420] Collection of business results

[1421] Report generation and distribution

[1422] Step 7:

[1423] The server continuously inputs and analyzes health and emotional data to monitor the employee's condition, and if an abnormality is detected, a notification service is used to send an alert to the employee, who can then provide medical advice or rest as needed.

[1424] Input: Continuous health and emotional data

[1425] Output: Monitoring results (alerts, medical advice)

[1426] Specific behavior:

[1427] Continuous data entry and analysis

[1428] Sending alerts and taking action when an abnormality is detected

[1429] 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.

[1430] 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.

[1431] 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.

[1432] 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.

[1433] 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.

[1434] 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.

[1435] 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).

[1436] 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.

[1437] 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."

[1438] 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.

[1439] 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).

[1440] 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.

[1441] 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.

[1442] 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.

[1443] 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.

[1444] 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.

[1445] 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.

[1446] 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.

[1447] 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.

[1448] 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.

[1449] 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.

[1450] The following is further disclosed regarding the above embodiment.

[1451] (Claim 1)

[1452] a means of inputting employee health data;

[1453] means for analyzing the health data and assessing the employee's health status;

[1454] A means for substituting night work using a generative AI model based on the evaluation results;

[1455] A means for feeding back the results of the business executed by the generative AI model;

[1456] A system including means for continuously monitoring said health data.

[1457] (Claim 2)

[1458] The system of claim 1, wherein the means for replacing night work using a generative AI model is suitable for the construction industry, transportation industry, and IT maintenance industry.

[1459] (Claim 3)

[1460] 2. The system according to claim 1, wherein the feedback means provides work results to employees and managers in the form of reports.

[1461] "Example 1"

[1462] (Claim 1)

[1463] a means of inputting employee health data;

[1464] means for analyzing the health data and assessing the employee's health status;

[1465] A means for substituting night work using an AI model based on the evaluation results;

[1466] A means for feeding back the results of the work performed by the AI ​​model;

[1467] means for continuously monitoring said health data;

[1468] means for detecting overwork or high stress based on the health data and the evaluation results and sending an alert;

[1469] A means for operating an automated driving vehicle or a monitoring system as a substitute for the nighttime work;

[1470] A system including:

[1471] (Claim 2)

[1472] The system of claim 1, wherein the means for substituting night work using an AI model is suitable for the construction industry, transportation industry, and IT maintenance industry.

[1473] (Claim 3)

[1474] 2. The system according to claim 1, wherein the feedback means provides work results to employees and managers in the form of reports.

[1475] "Application Example 1"

[1476] (Claim 1)

[1477] a means of inputting employee health data;

[1478] means for analyzing the health data and assessing the employee's health status;

[1479] A means for substituting night work using a generative AI model based on the evaluation results;

[1480] A means for feeding back the results of the business executed by the generative AI model;

[1481] means for continuously monitoring said health data;

[1482] The generated AI model works with smart devices to analyze and notify nighttime operations in real time;

[1483] A means for engaging in security work using the generative AI model to monitor crime prevention and detect suspicious behavior;

[1484] The system further includes a means for providing the results of the security operations to an administrator in the form of a report.

[1485] (Claim 2)

[1486] The system of claim 1, wherein the means for replacing night work using a generative AI model corresponds to the construction industry, transportation industry, IT maintenance, and security work.

[1487] (Claim 3)

[1488] 2. The system of claim 1, wherein the feedback means provides work results to employees and managers in the form of a report, the report including details of patrol results and detected suspicious behavior.

[1489] "Example 2: Combining Emotion Engines"

[1490] (Claim 1)

[1491] a means for inputting employee health and emotional information;

[1492] means for analyzing the health information and emotional information to assess the employee's health and emotional state;

[1493] A means for substituting night work using a generative AI model based on the evaluation results;

[1494] A means for feeding back the results of the business executed by the generative AI model;

[1495] A system including means for continuously monitoring said health information and emotional information.

[1496] (Claim 2)

[1497] The system of claim 1, wherein the means for replacing night work using a generative AI model corresponds to the construction industry, transportation industry, and information technology maintenance industry.

[1498] (Claim 3)

[1499] 2. The system according to claim 1, wherein the feedback means provides work results to employees and managers in the form of reports.

[1500] "Application example 2 when combining emotion engines"

[1501] (Claim 1)

[1502] a means for inputting employee health and emotional data;

[1503] means for analyzing the health data and emotional data to assess the employee's health and emotional state;

[1504] A means for substituting night work using a generative AI model based on the evaluation results;

[1505] A means for feeding back the results of the business executed by the generative AI model;

[1506] A system including means for continuously monitoring said health data and emotional data.

[1507] (Claim 2)

[1508] The system of claim 1, wherein the means for replacing night work using a generative AI model corresponds to manufacturing, transportation, and information technology maintenance.

[1509] (Claim 3)

[1510] 2. The system according to claim 1, wherein the feedback means provides work results to employees and managers in the form of reports. [Explanation of symbols]

[1511] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a means of inputting employee health data; means for analyzing the health data and assessing the employee's health status; A means for substituting night work using a generative AI model based on the evaluation results; A means for feeding back the results of the business executed by the generative AI model; A system including means for continuously monitoring said health data.

2. The system of claim 1, wherein the means of replacing night work using a generative AI model is suitable for the construction industry, transportation industry, and IT maintenance industry.

3. 2. The system according to claim 1, wherein said feedback means provides work results to employees and managers in the form of reports.

Images