System

Abstract

To provide a system capable of realizing health management of a driver and securement of safety in a vehicle with high accuracy.SOLUTION: Means for acquiring videos of the outside and inside of the vehicle in real time using the out-camera and the In Camera of the smartphone, means for analyzing a health condition of the driver by a generation model, means for detecting poor physical condition and drowsiness of the driver based on an analysis result and generating an alert, means for notifying the driver of the generated alert by voice or visually, and means for counting the number of persons getting on and off the vehicle by the In Camera, the system includes a means for transmitting the data to a cloud server, a means for generating an alert when there is a difference between the number of passengers getting on and off the vehicle, and a means for notifying the driver of the generated alert by voice or visually.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 problem that this invention aims to solve is to prevent accidents by detecting driver drowsiness or physical condition in real time and issuing appropriate alerts. Furthermore, to prevent tragic accidents such as children being left behind in a vehicle, the invention aims to provide a means to identify people left behind in the vehicle by managing the number of passengers getting on and off the vehicle and issuing an alert if there is a discrepancy. Furthermore, there is a need for integration with these systems to strengthen child safety management when children use shuttle buses for kindergartens and nursery schools. [Means for solving the problem]

[0005] The present invention includes a means for capturing real-time video of the vehicle exterior and interior using a smartphone's exterior and interior cameras, a means for transmitting the captured video data to a cloud server and analyzing the driver's health condition using a generative model, a means for detecting the driver's poor physical condition or drowsiness based on the analysis results and generating an alert, and a means for notifying the driver of the generated alert audio or visually. The present invention also includes a means for counting the number of passengers in the vehicle and the number of passengers exiting the vehicle using the interior camera and transmitting the data to a cloud server, a means for generating an alert if there is a discrepancy between the number of passengers and the number of passengers exiting the vehicle, and a means for notifying the driver of the generated alert audio or visually. The present invention also includes a means for linking the data on the number of passengers in the vehicle and the number of passengers exiting the vehicle detected by the interior camera with a kindergarten or nursery school's passenger management system, which generates an alert to prevent children from being locked inside the vehicle and notifies parents remotely. The present invention also includes a means for performing a more detailed analysis of the driver's physical condition, taking into account driving speed, weather, and time, and generating an alert encouraging appropriate rest if an abnormality is detected in the driver's health condition. This enables highly accurate management of the driver's health and ensuring safety in the vehicle.

[0006] A "smartphone" is a portable terminal equipped with mobile communication and computer functions, and is a device that can use various applications.

[0007] An "outside camera" is an outward-facing camera mounted on a device such as a smartphone, and is a means for capturing images outside the vehicle.

[0008] An "in-camera" is an inward-facing camera mounted on a device such as a smartphone, and is a means of capturing images of the inside of the car and the driver's facial expressions.

[0009] "Real-time" is a concept that refers to processing and analysis being carried out close to the moment the data is generated.

[0010] "Video data" refers to images and video information captured through a camera.

[0011] A "cloud server" is a remote server that can be accessed via the Internet and is a device that stores and analyzes data.

[0012] A "generative model" refers to an algorithm or program that analyzes data using machine learning or artificial intelligence techniques.

[0013] "Health condition" is information that indicates the physical and psychological state of the driver.

[0014] An "alert" refers to a warning signal or notification message that indicates an abnormal situation.

[0015] "Occupancy" refers to the number of people in a vehicle.

[0016] "Number of people getting off" refers to the number of people getting off the vehicle.

[0017] "Interconnection" refers to the way different systems or devices are linked together to function.

[0018] An "occupant management system" refers to a system for managing information about people riding in a specific vehicle.

[0019] "Entrapment in a vehicle" refers to a situation in which a person or object is unintentionally left inside a vehicle.

[0020] "Parents" refers to guardians who leave their children at kindergartens or daycare centers.

[0021] "Traveling speed" refers to the speed at which a vehicle is traveling.

[0022] "Weather" refers to the weather conditions at that time.

[0023] A "rest" refers to a driver temporarily stepping away from driving to rest their body.

[0024] "Children" refers to minors of kindergarten or nursery school age. [Brief explanation of the drawings]

[0025] [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

[0026] 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.

[0027] First, the terms used in the following description will be explained.

[0028] 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).

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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."

[0033] [First embodiment]

[0034] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0035] 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.

[0036] 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).

[0037] 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.

[0038] 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.

[0039] 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.

[0040] 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.

[0041] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0042] 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.

[0043] 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.

[0044] 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.

[0045] 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."

[0046] The present invention relates to a healthcare and safety management system using a smartphone. This system monitors the situation outside and inside a vehicle in real time to prevent the driver from becoming ill or children from being locked inside the vehicle. A specific embodiment of this system will be described below.

[0047] Video acquisition and analysis

[0048] The device (smartphone) uses an external and internal camera to capture images of the interior and exterior of the vehicle in real time. The external camera captures the road conditions outside the vehicle, while the internal camera captures the interior of the vehicle, as well as the driver's facial expressions and movements. This allows for an accurate understanding of the driver's physical condition and the situation inside the vehicle.

[0049] The server receives the video data sent from the device and analyzes it in real time using a generative model. The AI ​​model detects drowsiness or poor physical condition from the driver's facial expression and generates an appropriate alert. This alert is then notified to the driver, prompting them to take appropriate action.

[0050] Alert Notification

[0051] The device receives alert notifications from the server and notifies the user in real time via audio and visual means. For example, if the driver feels drowsy, the smartphone will sound an alarm and display a message saying, "Signs of drowsiness have been detected. Please take a break." In this way, the alert can alert the driver to danger and encourage them to take appropriate action.

[0052] Managing the number of passengers getting on and off

[0053] The device uses the front camera to count the number of passengers getting on and off the bus in real time. This data is periodically sent to a server and managed by the server. For example, if the front camera counts three children on a kindergarten bus when they board, and only two get off when they exit, the device will send that data to the server.

[0054] The server generates an alert when there is a discrepancy between the number of passengers getting on and off the vehicle. As a means of notifying the discrepancy, the server detects the discrepancy and generates an alert. This alert is sent to the terminal and notified to the driver. For example, a message saying "One child remains in the vehicle. Please check." is notified.

[0055] Linking kindergartens and nurseries

[0056] The device connects the data on the number of passengers boarding and exiting the vehicle detected by the in-vehicle camera to the kindergarten or nursery school's passenger management system. This generates an alert to prevent children from being locked inside the vehicle and notifies parents remotely. Parents can remotely check their children's boarding and exiting status from their smartphones, giving them peace of mind when leaving their children in the care of their parents.

[0057] Detailed analysis of health status

[0058] The server then analyzes the driver's health in more detail, taking into account information such as driving speed, weather, and time. This information is then used to generate alerts to encourage the driver to take breaks at appropriate times. For example, if the driver is driving for a long time or in bad weather, fatigue may increase, so the server generates an alert saying, "We recommend taking a break."

[0059] As described above, the system of the present invention utilizes a smartphone camera and generative models to comprehensively support driver health management and in-vehicle safety. This system can prevent accidents and provide a safe driving environment.

[0060] The processing flow will be explained below.

[0061] Step 1:

[0062] Device: Activate the smartphone's rear camera and front camera. The rear camera captures images of the outside of the vehicle, while the front camera captures the driver's facial expression and the situation inside the vehicle.

[0063] Step 2:

[0064] Terminal: The video data acquired by the camera is sent to the cloud server in real time, continuously at regular intervals.

[0065] Step 3:

[0066] Server: Analyzes the received video data using a generative model. Specifically, it analyzes the driver's facial expressions, counts the number of people in the car, and understands road conditions.

[0067] Step 4:

[0068] Server: Evaluates the driver's health based on the analysis results. If signs of drowsiness or abnormalities are detected, an alert is generated.

[0069] Step 5:

[0070] Server: Compares the number of passengers boarding and alighting, and generates an alert if there is a discrepancy between the number of passengers boarding and alighting.

[0071] Step 6:

[0072] Terminal: Receives alert notifications from the server. Depending on the alert content, the user is notified by voice and visual means.

[0073] Step 7:

[0074] User: The driver or parent / guardian sees the alert and takes necessary action, such as taking a break or checking for children left in the car.

[0075] Step 8:

[0076] Terminal: The in-vehicle camera continuously monitors the situation inside the vehicle, and in particular in kindergarten and nursery school shuttle buses, it counts the number of people getting on and off the bus and links with the management system.

[0077] Step 9:

[0078] Server: Performs additional analysis based on driving speed, weather, and time to assess driver fatigue and health.

[0079] Step 10:

[0080] Device: Generates an alert to prompt the user to take a break at an appropriate time. For example, it displays a message saying, "You have been driving for a long time. Please take a break."

[0081] In this way, at every step, the system monitors the driver's health and the safety of the vehicle in real time and prompts appropriate action.

[0082] Example 1

[0083] 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."

[0084] There is a need for a means to prevent accidents caused by drivers' poor health or drowsiness while driving, as well as situations where children are left behind in the car. There is also a need for a system to manage the number of passengers boarding and exiting a vehicle, ensuring the safe transportation of children, especially at kindergartens and daycare centers. Conventional technologies have not provided effective solutions to these issues comprehensively.

[0085] 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.

[0086] In this invention, the server includes: means for capturing images of the interior and exterior of the vehicle in real time using the smartphone's exterior and interior cameras; means for transmitting the captured image data to a cloud server and analyzing the driver's health condition using a generative AI model; means for detecting the driver's poor physical condition or drowsiness based on the analysis results and generating an alert; means for notifying the driver of the generated alert audio or visually; means for counting the number of passengers in the vehicle and the number of passengers exiting the vehicle using the interior camera and transmitting the data to the cloud server; means for generating an alert if there is a discrepancy between the number of passengers in the vehicle and the number of passengers exiting the vehicle; means for notifying the driver of the generated alert audio or visually; means for linking the data on the number of passengers entering and exiting the vehicle with a kindergarten or nursery school's passenger management system; and means for performing a more detailed analysis of the driver's physical condition taking into account driving speed, weather, and time. This enables comprehensive management of the driver's physical condition and in-vehicle safety.

[0087] An "outside camera" is a camera installed on a smartphone or other device that is primarily used to capture external scenery and surrounding conditions.

[0088] An "in-camera" is a camera installed in a smartphone or other device that is primarily used to capture the interior of the device or the user's face.

[0089] A "cloud server" is a server that can be accessed remotely via the Internet and is a computer system used to store, process, and analyze data.

[0090] A "generative AI model" is an AI (artificial intelligence) model that uses machine learning and deep learning to learn and infer, and is a system that generates specific results or analyses based on input data.

[0091] An "alert" is a message or signal, which may be in the form of an audio or visual notification, that notifies the user when the system detects a particular condition.

[0092] An "occupant management system" is a system used to manage boarding and disembarking passengers, particularly in kindergartens and daycare centers, by recording the number of passengers boarding and disembarking and handling safety information.

[0093] "Health status" refers to the driver's physical and mental condition, which is analyzed to detect factors related to physical condition, including distraction, fatigue, and drowsiness while driving.

[0094] "Real-time" refers to a state in which data and information are acquired and processed immediately, and the results are reflected without delay.

[0095] Step 1: Generate a program for this system

[0096] The device (smartphone) uses an external and internal camera to monitor the situation outside and inside the vehicle in real time. The specific hardware used is the smartphone's built-in camera. On the software side, a video capture application is required, and this application has the function of sending captured video data to a cloud server.

[0097] The server is located in the cloud and analyzes the received video data. A generative AI model is used for the analysis. This AI model analyzes the driver's health status and is used to detect poor physical condition or drowsiness. Specific software used is a deep learning framework (e.g., TensorFlow or PyTorch).

[0098] Step 2: Explain the generated program's processing in natural language

[0099] The device uses the smartphone's rear and front cameras to capture real-time video footage of the interior and exterior of the vehicle. The rear camera captures the road conditions outside the vehicle, while the front camera captures the interior of the vehicle, as well as the driver's facial expressions and movements. This video data is acquired by the smartphone's video capture application.

[0100] The device transmits the captured video data to the cloud server in real time using the HTTPS protocol. The device efficiently compresses the video data and transmits it securely to the server.

[0101] The server analyzes the received video data using a deep learning framework (e.g., TensorFlow or PyTorch). Using a generative AI model, it detects drowsiness or poor physical condition from the driver's facial expressions and movements. Based on the analysis results, the server generates appropriate alerts.

[0102] The device notifies the user of the alert notification received from the server in real time using audio and visuals. For example, if the driver feels drowsy, the smartphone will sound an alarm and display a message saying, "Signs of drowsiness have been detected. Please take a break." The notification uses the smartphone's notification API.

[0103] The device uses the front camera to count the number of people entering and exiting the vehicle in real time, using a people-counting algorithm built into the smartphone.

[0104] The server generates an alert if there is a discrepancy between the number of passengers getting on and off the vehicle, and sends the alert to the device. The server then links the data sent to the passenger management system of the kindergarten or nursery school. This link generates an alert to prevent children from being locked inside the vehicle.

[0105] Step 3: Add examples to your description

[0106] Example 1: Driver health management

[0107] Scenario: A driver is driving for a long time and the front camera captures the driver with their eyes closed or blinking frequently.

[0108] Server analysis: A generative AI model analyzes the video and detects signs of drowsiness.

[0109] Alert notification: The server generates an alert saying "Signs of drowsiness have been detected. Please take a break." and sends it to the device.

[0110] User notification: The device notifies the user with an audible alarm and a visual message.

[0111] Example prompt:

[0112] "Please explain how to analyze video data of the driver's face captured by an in-car camera, detect signs of drowsiness or poor physical condition, and generate an alert."

[0113] Example 2: Preventing children from being locked inside a car

[0114] Scenario: While driving a kindergarten bus, the in-camera counts three children as they board, but only two get off when they disembark.

[0115] Server analysis: The server compares the number of passengers boarding and alighting and detects any discrepancies.

[0116] Alert notification: The server generates an alert saying "There is a child left in the car. Please check." and sends it to the device.

[0117] User notification: The device notifies the user with an audible alarm and a visual message.

[0118] Example prompt:

[0119] "Explain how in-car cameras can be used to count the number of children getting in and out of the car and generate an alert if any children remain in the car."

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

[0121] Step 1:

[0122] The device captures images of the exterior and interior of the vehicle in real time using the smartphone's exterior and interior cameras. The captured image data is divided into exterior images from the exterior camera and interior images from the interior camera. Specifically, the smartphone's video capture software captures images at a rate of 30 frames per second and stores them as data.

[0123] Input: Interior and exterior view of the car

[0124] Output: Real-time captured video data

[0125] Step 2:

[0126] The device compresses the captured video data and sends it to the cloud server using the HTTPS protocol, using H.264 encoding technology to minimize data transmission delays.

[0127] Input: Real-time video data

[0128] Output: Compressed video data

[0129] Step 3:

[0130] The server decodes the received compressed video data and analyzes it using a generative AI model. The decoded video data is used to detect the driver's facial region and track facial expressions, eye movements, head movements, etc. Deep learning technology is then used to detect driver drowsiness or poor physical condition from this information.

[0131] Input: Compressed video data

[0132] Output: Driver health condition analysis results

[0133] Step 4:

[0134] The server generates necessary alerts based on the analysis results. For example, if the driver's eyes are closed for more than three consecutive seconds, it generates a text alert saying, "Signs of drowsiness detected. Please take a break." It also generates audio alerts based on certain signals.

[0135] Input: Driver health analysis results

[0136] Output: Generated alert (text and audio)

[0137] Step 5:

[0138] The device notifies the user of the alert notification received from the server in real time via audio and visual means. Specifically, an alarm sounds from the smartphone speaker and a message appears on the display saying, "Signs of drowsiness have been detected. Please take a break." This is done using the smartphone's notification API.

[0139] Input: Generated alert (text and audio)

[0140] Output: An alert to be sent to the user

[0141] Step 6:

[0142] The device uses the front camera to count the number of people entering and exiting the vehicle in real time, using a people-counting algorithm built into the smartphone, and sends the results to a cloud server.

[0143] Input: In-car video data

[0144] Output: Real-time passenger count data for boarding and alighting

[0145] Step 7:

[0146] The server analyzes the received data on the number of passengers boarding and alighting, and generates an alert if there is a discrepancy. For example, if three children were counted when the passenger boarded the vehicle and only two got off when the passenger disembarked, the server generates an alert saying, "One child remains in the vehicle. Please check," and sends it to the device.

[0147] Input: Real-time passenger count data for boarding and alighting

[0148] Output: Alert notifying passengers of mismatch between boarding and alighting counts

[0149] Step 8:

[0150] The device will then notify the driver of the received alert notification in real time via audio and visual means, and will use the smartphone's speaker or screen to display a message saying, "A child has been left in the vehicle. Please check."

[0151] Input: Alert for mismatch between passenger numbers

[0152] Output: Alert to the driver

[0153] Step 9:

[0154] The server synchronizes the counted number of passengers boarding and alighting with the kindergarten or nursery school's passenger management system. Data is sent via an API, and information between the systems is updated instantly. If there is a discrepancy in the number of passengers, an alert is generated in the kindergarten's system.

[0155] Input: Real-time passenger count data for boarding and alighting

[0156] Output: Synchronized data to linked systems and generated alerts

[0157] In this way, the system analyzes input data at each step and generates and notifies appropriate alerts, thereby ensuring safety while driving and managing the situation inside the vehicle.

[0158] (Application example 1)

[0159] 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."

[0160] Conventional self-driving and manually driven vehicles lack systems that properly manage the health of drivers and passengers, as well as the safety of those inside the vehicle. In particular, there are issues with drivers becoming fatigued due to long driving hours or bad weather, children being locked inside the vehicle, and passengers becoming unwell. To address these issues, it is necessary to provide a system that monitors the situation inside and outside the vehicle in real time, analyzes the health status of passengers, and generates appropriate alerts.

[0161] 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.

[0162] In this invention, the server includes: means for capturing video of the interior and exterior of the vehicle in real time using the smart device's external and internal cameras; means for transmitting the captured video data to a remote server and analyzing the driver's health status using a generative model; means for detecting the driver's poor physical condition or drowsiness based on the analysis results and generating a warning; means for notifying the driver of the generated warning audio or visually; means for counting the number of passengers inside and outside the vehicle using the internal camera and transmitting the data to the remote server; means for generating a warning if there is a discrepancy between the number of passengers inside and outside the vehicle; means for notifying the driver of the generated warning audio or visually; means for comprehensively monitoring the conditions inside and outside the vehicle and managing the health and safety of passengers; means for further analyzing the health of passengers taking into account driving speed, weather, and time; means for generating a warning urging passengers to take an appropriate break if an abnormality is detected in their health status; and means for notifying passengers of the generated warning audio or visually. This makes it possible to comprehensively manage the health and safety of drivers and passengers and provide appropriate alerts even in autonomous vehicles.

[0163] A "smart device" is a mobile information terminal that has communication functions and a camera, such as a smartphone or a head-mounted display.

[0164] An "outside camera" is a camera installed on a smart device that captures external images.

[0165] An "in-camera" is a camera installed in a smart device that captures internal images.

[0166] A "remote server" is a group of computers that are placed on the cloud and receive and analyze data via the Internet.

[0167] A "generative model" is an algorithm that uses machine learning or deep learning models to predict or generate a specific outcome from input data.

[0168] "Health condition" refers to the physical condition of the driver or passenger, such as physical condition, illness, or drowsiness.

[0169] "Warning" is a notification message that informs the driver or passengers of any abnormalities or matters requiring attention that the system has detected.

[0170] "Voice notification" is a function that notifies the driver and passengers of warnings by voice.

[0171] "Visual notification" is a function that notifies drivers and passengers of warnings through visual means such as a screen or light.

[0172] "Occupancy" refers to the total number of people on board the vehicle.

[0173] "Number of people getting off" is the total number of people who got off the vehicle.

[0174] "Situation monitoring" means observing and understanding the environment inside and outside the vehicle, as well as people's movements, in real time.

[0175] "Illness" refers to a state in which one's health condition is different from normal and it is deemed dangerous to continue driving or traveling.

[0176] A "passenger management system" is a system for managing boarding and disembarking situations at educational institutions and other facilities.

[0177] "Running speed" refers to the speed at which a vehicle moves.

[0178] "Weather" refers to the atmospheric conditions at a given time, including sunny, rainy, snowy, foggy, etc.

[0179] A "break" is a time or action taken to temporarily stop driving or traveling and rest your body and mind.

[0180] This invention is a system that monitors the situation inside and outside the vehicle in real time and provides comprehensive support for passenger health management and safety. It mainly uses smart devices and a remote server to analyze the health status of the driver and passengers in an autonomous vehicle and generate and notify alerts as necessary. Specific embodiments are described below.

[0181] Hardware Configuration

[0182] The system includes the following major hardware components:

[0183] 1. Smart Devices

[0184] Outer camera: Captures footage outside the vehicle.

[0185] In-camera: Captures footage from inside the car.

[0186] Audio output device: Used to notify audio warnings.

[0187] Display: Used to display visual warnings.

[0188] 2. Remote Server

[0189] Cloud Computing: The provision of computational resources.

[0190] Database: Storage and management of collected data.

[0191] Software Configuration

[0192] The system is implemented using the following major software components:

[0193] 1. Generative Model (AI Model)

[0194] Used to analyze the health status of drivers and passengers.

[0195] Machine learning framework used: TensorFlow / Keras.

[0196] 2. Data Processing and Analysis

[0197] Image processing library: Preprocesses image data using OpenCV.

[0198] Communication library: Communicate with remote servers using the requests module.

[0199] Data flow and processing steps

[0200] The basic data flow and processing procedures of the system are as follows:

[0201] 1. Acquiring footage

[0202] The smart device's external and internal cameras capture images of the vehicle's exterior and interior in real time, and the image data is converted into an appropriate format (e.g., JPEG or PNG).

[0203] 2. Transmission of video data

[0204] The video data is sent to a remote server via a communication library, where it is temporarily stored in a database for analysis.

[0205] 3. Health status analysis

[0206] The received video data is analyzed by a generative model to determine the health status of the driver and passengers. An example of a prompt sentence is given to the generative model: "Please detect whether drowsiness is felt in this video frame."

[0207] 4. Alert generation and notification

[0208] If the analysis detects any abnormalities in the driver or passengers, such as poor physical condition or drowsiness, the server generates a warning, which is then provided to the driver or passenger in real time via an audio output device or display.

[0209] Usage example

[0210] To illustrate, consider the following scenario:

[0211] If drowsiness is detected from the facial expression of a driver who has been driving for a long time, an audio and visual warning will be displayed saying, "Signs of drowsiness have been detected. Please take a break."

[0212] On educational institution shuttle buses, the in-camera counts the number of passengers getting on and off the bus, and if there are children who have not yet disembarked when the bus disembarks, a warning is generated saying, "There are passengers in the bus who have not yet disembarked. Please check."

[0213] If the system determines that the driver is becoming fatigued during long drives in bad weather, the system will send a notification saying, "We recommend that you take a break."

[0214] This configuration provides a system that can comprehensively monitor conditions inside and outside the vehicle, improving the health and safety of drivers and passengers.

[0215] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0216] Step 1:

[0217] The terminal (smart device) operates the outer and inner cameras to capture images of the outside and inside of the vehicle in real time.

[0218] Input: Video footage from inside and outside the car.

[0219] Data processing: Convert the video into the appropriate format (e.g. JPEG, PNG).

[0220] Output: Captured video data.

[0221] Step 2:

[0222] The video data acquired by the terminal is sent to a remote server using a communication library.

[0223] Input: Acquired video data.

[0224] Data calculation: Transfer of video data.

[0225] Output: Video data sent to the server.

[0226] Step 3:

[0227] The server stores the received video data in a database.

[0228] Input: Transmitted video data.

[0229] Data processing: Store in a database.

[0230] Output: Video data stored in a database.

[0231] Step 4:

[0232] The server uses a generative model to analyze the health status of the driver and passengers from the captured video data.

[0233] Input: Stored video data.

[0234] Data calculation: health status analysis, for example, based on the prompt "Detect whether you feel drowsy in this video frame."

[0235] Output: Analysis results (health status assessment).

[0236] Step 5:

[0237] If the server detects an abnormality based on the analysis results, it generates an alert.

[0238] Input: Analysis results.

[0239] Data operation: Generate warning.

[0240] Output: The warning message generated.

[0241] Step 6:

[0242] The server sends the generated alert to the device.

[0243] Input: Warning message.

[0244] Data calculation: Transfer of warning messages.

[0245] Output: The warning message sent to the terminal.

[0246] Step 7:

[0247] The device will notify the driver or passengers of the warning message received via audio or visual means.

[0248] Input: Warning message.

[0249] Data calculation: Notification through audio output device or display.

[0250] Output: A warning message is sent to the driver and passengers.

[0251] 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.

[0252] The present invention relates to a healthcare and safety management system that uses a smartphone and an emotion engine. This system monitors the situation outside and inside the vehicle, including the user's emotional state, in real time to prevent the driver from becoming ill or children from being trapped inside the vehicle. A specific embodiment of this system will be described below.

[0253] Video acquisition and analysis

[0254] The device (smartphone) uses an external and internal camera to capture images of the vehicle's exterior and interior in real time. The external camera captures road conditions outside the vehicle, while the internal camera captures the driver's facial expressions and the situation inside the vehicle. This allows for an accurate understanding of the driver's physical condition and the situation inside the vehicle.

[0255] Video data transmission and analysis

[0256] The server receives video data from the device and analyzes it in real time using a generative model and emotion engine. The emotion engine analyzes the driver's emotional state from their facial expressions and evaluates it by integrating it with their health condition. For example, it can detect changes such as increased stress during long driving sessions or the appearance of fatigue.

[0257] Alert Notification

[0258] Based on the analysis results, the server generates an alert if it detects any abnormalities in the driver's health or emotional state. The generated alert is notified to the driver via audio or visual means via the device. For example, a message such as "Your stress level is increasing. Please take a break" is displayed.

[0259] Managing the number of passengers getting on and off

[0260] The device uses the in-car camera to count the number of passengers getting on and off the vehicle in real time and sends the data to a cloud server, allowing for accurate management of the number of passengers on board.

[0261] The server compares the number of passengers boarding and alighting, and generates an alert if there is a discrepancy. For example, if a child is left behind on a kindergarten bus, an alert will be generated saying, "One child remains in the bus. Please check."

[0262] Linking with kindergartens and nurseries

[0263] The device connects the data on the number of passengers boarding and exiting the vehicle detected by the in-vehicle camera to the kindergarten or nursery school's passenger management system. This generates an alert to prevent children from being locked inside the vehicle and notifies parents remotely. Parents can remotely check their children's boarding and exiting status from their smartphones, giving them peace of mind when leaving their children in the care of their parents.

[0264] Detailed analysis of health and emotional state

[0265] The server then takes into account information such as driving speed, weather, and time of day to perform a more detailed analysis of the driver's health and emotional state. This allows the server to generate alerts to encourage the driver to take breaks at appropriate times. For example, if stress or fatigue increases during long drives in bad weather or at night, the server will generate an alert saying, "We recommend taking a break."

[0266] Responding to emergencies

[0267] The server automatically notifies external authorities if the driver is in an emergency based on the acquired video data and the analysis results of the emotion engine. The content of the notification can be customized, allowing the situation to be quickly communicated to specific contacts.

[0268] As described above, the system of the present invention utilizes a smartphone camera, generative model, and emotion engine to comprehensively support driver health and emotion management. This system can prevent accidents and provide a safe driving environment.

[0269] The processing flow will be explained below.

[0270] Step 1:

[0271] Device: Activate the smartphone's rear camera and front camera. The rear camera captures images of the outside of the vehicle, while the front camera captures the driver's facial expression and the situation inside the vehicle.

[0272] Step 2:

[0273] Terminal: Sends acquired video data to the cloud server at regular intervals.

[0274] Step 3:

[0275] Server: The cloud server inputs the received video data into the generative model and emotion engine in real time for analysis.

[0276] Step 4:

[0277] Server: Evaluates the driver's health and emotional state (e.g., stress level and fatigue level) from their facial expressions and movements.

[0278] Step 5:

[0279] Server: Based on the analysis results, if an abnormality is detected in the driver's health or emotional state, an alert is generated. For example, if the driver's face shows signs of fatigue or stress, an alert is generated saying, "Your stress level is rising. Please take a break."

[0280] Step 6:

[0281] Device: Receives alerts from the server and notifies the user audio and visually. A message is displayed on the smartphone screen and an audio alert is played.

[0282] Step 7:

[0283] Terminal: Using the in-camera, it continuously counts the number of passengers getting on and off the vehicle and sends this data to a cloud server.

[0284] Step 8:

[0285] Server: If there is a discrepancy between the number of passengers getting on and off, for example if a child is left behind on a shuttle bus, an alert is generated. This alert will say, "There is one child left in the bus. Please check."

[0286] Step 9:

[0287] Terminal: The boarding and alighting data is linked to the kindergarten or nursery school's passenger management system, which then remotely notifies parents of their children's boarding and alighting information.

[0288] Step 10:

[0289] Server: Integrates data such as driving speed, weather, and time to perform a more detailed analysis of the driver's health and emotional state. Based on the analysis results, it generates additional alerts as needed. For example, an alert saying, "You've been driving for a long time. We recommend you take a break."

[0290] Step 11:

[0291] User: The driver reviews the generated alert and takes appropriate action, such as taking a break or checking for children left in the car.

[0292] Step 12:

[0293] Server: Based on the acquired video data and the analysis results of the emotion engine, if the driver is in an emergency, the server automatically notifies external authorities. The content of the notification can be customized to quickly inform specific contacts of the situation.

[0294] Example 2

[0295] 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."

[0296] In recent years, managing the health and emotional state of drivers has become an important issue. In particular, the risk of accidents due to fatigue and stress caused by long driving hours is increasing. Dangerous situations such as children being left behind in cars are also becoming a problem. Conventional technologies have the difficulty of detecting these problems in real time and generating alerts at the appropriate time.

[0297] 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.

[0298] In this invention, the server includes: means for capturing images of the interior and exterior of the vehicle in real time using the smartphone's exterior and interior cameras; means for transmitting the captured image data to a cloud server and analyzing the driver's health and emotional state using a generative AI model and an emotion engine; means for detecting the driver's poor physical condition or stress based on the analysis results and generating an alert; means for notifying the driver of the generated alert audio or visually; means for counting the number of passengers in the vehicle and the number of passengers exiting the vehicle using the interior camera and transmitting the data to the cloud server; means for generating an alert if there is a discrepancy between the number of passengers in the vehicle and the number of passengers exiting the vehicle; means for notifying the driver of the generated alert audio or visually; means for performing a detailed analysis of the driver's health and emotional state taking into account driving speed, weather, and time; and means for automatically reporting to an external agency in the event of an emergency. This enables real-time management of the driver's health and safety in the vehicle, and enables rapid response to emergencies.

[0299] A "smartphone" is a portable, multi-functional electronic device with internet connectivity and a camera.

[0300] An "outside camera" is a camera installed on the outside of a smartphone to capture external scenery and objects.

[0301] An "in-camera" is a camera installed inside a smartphone that captures the user's face and the interior of the device.

[0302] "Video data" refers to a series of visual information acquired by the outer camera and the inner camera.

[0303] A "cloud server" is a remote server accessible via the Internet, a group of devices that store and process data.

[0304] A "generative AI model" is an algorithmic model of artificial intelligence that analyzes input data and generates specific results or predictions.

[0305] The "emotion engine" is software that analyzes video data and identifies the emotional state of the subject.

[0306] "Analysis results" refers to the information and data obtained after the generative AI model and emotion engine process the video data.

[0307] An "alert" is a warning message that is generated to notify of an abnormal situation and is displayed visually or audibly.

[0308] "Number of passengers" refers to the total number of people on board the vehicle.

[0309] "Number of people getting off" refers to the total number of people who got off the vehicle.

[0310] "Traveling speed" refers to the speed at which a vehicle is moving in the direction of travel.

[0311] An "emergency situation" refers to an unexpected dangerous situation or a serious problem with the driver's health.

[0312] "External agencies" refers to rescue services and parties that may be contacted in an emergency.

[0313] The present invention relates to a healthcare and safety management system that uses a smartphone and an emotion engine. This system monitors the situation outside and inside the vehicle, including the user's emotional state, in real time to prevent the driver from becoming ill or children from being trapped inside the vehicle. A specific embodiment of this system will be described below.

[0314] Video acquisition and analysis

[0315] The device (smartphone) uses an external and internal camera to capture images of the outside and inside of the vehicle in real time. The external camera captures the road conditions outside the vehicle, while the internal camera captures the driver's facial expression and the situation inside the vehicle. This allows for an accurate understanding of the driver's physical condition and the situation inside the vehicle.

[0316] Examples:

[0317] The outer camera captures road conditions during rainy weather.

[0318] The in-camera detects the driver's tired expression.

[0319] Video data transmission and analysis

[0320] The device sends the captured video data to a server, which then analyzes the video data in real time using a generative AI model and an emotion engine. The emotion engine analyzes the driver's emotional state from their facial expressions, and the generative AI model recognizes specific elements contained in the video.

[0321] Examples:

[0322] The generative AI model is given the prompt sentence, "How tired is this driver currently?"

[0323] The emotion engine generates the result "Exhaustion: 80%".

[0324] Alert generation and notification

[0325] If the server detects an abnormality based on the analysis results, it generates an alert, which is then sent to the driver via their device. Notifications are made via audio, vibration, and visual (screen display).

[0326] Examples:

[0327] A voice message will be played saying, "Your stress levels are high, please take a break."

[0328] The same message will be displayed on the device screen.

[0329] Managing the number of passengers getting on and off

[0330] The device uses the in-car camera to count the number of passengers getting on and off the vehicle in real time and sends the data to a server, which analyzes the data and checks for any abnormalities.

[0331] Examples:

[0332] The device detects that 10 children have boarded a kindergarten shuttle bus.

[0333] When passengers exit the vehicle, the server detects that only nine passengers have exited and generates an alert saying, "There is one child left in the vehicle. Please check."

[0334] Detailed analysis of health and emotional state

[0335] The server takes into account driving speed, weather, and time information, performs detailed analysis of the driver's health and emotional state, and generates appropriate alerts based on the results.

[0336] Examples:

[0337] If you are driving for a long time at night in bad weather, an alert will be generated saying, "You are tired. We recommend you take a break."

[0338] Responding to emergencies

[0339] The server has the ability to automatically notify external agencies in the event of an emergency based on the acquired video data and the analysis results of the emotion engine. The content of the notification can be customized, and the situation can be quickly communicated to specific contacts.

[0340] Examples:

[0341] If the driver loses consciousness, an emergency situation will occur and an automatic call will be sent to emergency services, along with footage from inside the vehicle and the driver's current location.

[0342] This system utilizes a smartphone camera, generative AI models, and an emotion engine to comprehensively support driver health and emotion management, preventing accidents and providing a safe driving environment.

[0343] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0344] System program processing flow

[0345] Step 1: Acquire footage

[0346] The device uses the external and internal cameras to capture images of the outside and inside of the vehicle in real time.

[0347] Input: External environment (road conditions), in-car environment (driver's facial expression, etc.)

[0348] Data processing / calculation: The outer camera captures external images, and the inner camera captures internal images.

[0349] Output: Out-camera video data, in-camera video data

[0350] Specific behavior:

[0351] The device captures video at 24 frames per second.

[0352] Step 2: Sending video data

[0353] The terminal transmits the acquired video data to a server via the Internet.

[0354] Input: Out-camera video data, in-camera video data

[0355] Data processing / calculation: Packetize video data and send it over the Internet

[0356] Output: Video data received by the server

[0357] Specific behavior:

[0358] The device uses Wi-Fi or LTE networks to upload video data to a server.

[0359] Step 3: Analyzing the video data

[0360] The server sends the received video data to the generative AI model and emotion engine for real-time analysis.

[0361] Input: Video data received by the server

[0362] Data processing / calculation: Analysis using generative AI models and emotion engines

[0363] Output: Analysis results (driver's health, emotional state, etc.)

[0364] Specific behavior:

[0365] The server sends a prompt to the generative AI model, saying, "Analyze the driver's stress level from their facial expression."

[0366] The emotion engine outputs the analysis result "Driver's stress level: High."

[0367] Step 4: Alert Generation

[0368] If an abnormality is detected based on the analysis results, the server generates an alert.

[0369] Input: Analysis results

[0370] Data processing / calculation: Generate alert messages based on analysis results

[0371] Output: Alert message

[0372] Specific behavior:

[0373] The server generates an alert message saying "Your stress level is high and you need to take a break."

[0374] Step 5: Alert Notification

[0375] The terminal notifies the driver of alert messages sent from the server.

[0376] Input: Alert message from the server

[0377] Data processing / calculation: Converted into audio, vibration, and visual notification formats

[0378] Output: Notification to the driver

[0379] Specific behavior:

[0380] The device plays a voice message saying, "Your stress level is high, please take a break."

[0381] The terminal will display the same message on the screen.

[0382] Step 6: Managing passenger numbers

[0383] The device uses the in-camera to count the number of passengers getting on and off the vehicle in real time and sends the data to a server.

[0384] Input: In-camera video data

[0385] Data processing / calculation: Analyze video data and count people

[0386] Output: Number of passengers boarding and alighting data

[0387] Specific behavior:

[0388] When the terminal detects one person on board, it sends the data "+1 person" to the server.

[0389] The server confirms that one person has left the vehicle when they get off, and receives the data "-1 person."

[0390] Step 7: Anomaly detection and notification

[0391] The server compares the number of passengers boarding and alighting, and if there is a discrepancy, it generates an alert and notifies the user via the terminal.

[0392] Input: Number of passengers boarding and alighting data

[0393] Data processing / calculation: Detect discrepancies in headcount data and generate alert messages

[0394] Output: Alert message

[0395] Specific behavior:

[0396] The server generates an alert message saying "There is a child left in the car. Please check."

[0397] The device will notify you of the message with audio and visual notifications.

[0398] Step 8: Detailed analysis of your health and emotional state

[0399] The server takes into account driving speed, weather and time information to perform a more detailed analysis of the driver's health and emotional state.

[0400] Input: Driving speed, weather, and time information

[0401] Data processing / calculation: Integrates analytical information to provide a detailed assessment of health and emotional status

[0402] Output: Detailed analysis results

[0403] Specific behavior:

[0404] The server evaluates, "The current weather is rainy, and the stress level is high because you are driving at night."

[0405] The server generates an alert message saying "We recommend you take a break."

[0406] Step 9: Emergency response

[0407] The server has a means to automatically notify external agencies in the event of an emergency.

[0408] Input: Emergency trigger (e.g., sudden deterioration in health condition)

[0409] Data processing / calculation: Creation of emergency messages and transmission to external agencies

[0410] Output: Report message to external organization

[0411] Specific behavior:

[0412] The server generates a message saying, "The driver has lost consciousness. The current location is point xx."

[0413] The server will notify the configured contacts via SMS or phone call.

[0414] (Application example 2)

[0415] 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."

[0416] In conventional factories, there is a lack of means to monitor the health and mental state of workers in real time, so workers may not notice if they are overworked or stressed, posing a significant risk to work quality and safety. Furthermore, if a sudden health problem occurs, it is difficult to respond quickly, making it difficult to guarantee the safety of workers.

[0417] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for acquiring video of the work environment and workers in real time using a camera of a smart device; means for transmitting the acquired video data to the server and analyzing the health status of the workers using a generative model; means for detecting poor physical condition and stress level of the workers based on the analysis results and generating an alert; means for notifying the workers of the generated alert audio or visually; means for counting the number of people in the workplace using a camera and transmitting the data to the server; means for generating an alert if there is an abnormality in the number of people; and means for notifying the workers of the generated alert audio or visually. This makes it possible to monitor and manage the health status and safety of workers in real time.

[0418] A "smart device" is a portable information terminal equipped with communication and camera functions.

[0419] A "camera" is an electronic device for acquiring video data.

[0420] "Real time" means processing that is performed in real time without delay.

[0421] "Video data" refers to recorded data in digital format that includes image information.

[0422] A "server" is a computer that stores and analyzes data over a network.

[0423] A "generative model" is an algorithm that generates a particular outcome based on data analysis.

[0424] "Health" means the balance or state of the body and mind.

[0425] "Analysis" is the process of extracting meaningful information and patterns from data.

[0426] "Stress level" is an index that indicates the degree of mental stress on a worker.

[0427] An "alert" is a notification or warning that draws attention.

[0428] "Voice notification" is a means of conveying information using voice.

[0429] "Visual notification" is a method of conveying information using visual information.

[0430] A "worker" is a person who performs work in a factory or work site.

[0431] "Counting people" means measuring the number of individuals present in a particular area.

[0432] "Abnormal" means a state or situation that is different from the normal.

[0433] A "management system" is a system that uses data to monitor and control business operations and tasks.

[0434] "Environmental conditions" are factors that affect the working environment, such as temperature, humidity, and noise.

[0435] "Encouraging breaks" means encouraging people to take a break by temporarily stopping their work.

[0436] "Real-time monitoring and management" means observing and controlling the actual state without any time delay.

[0437] This invention relates to a health management and safety monitoring system for factories that uses smart devices and an emotion analysis engine. The system aims to improve work safety and efficiency by monitoring the health and mental state of workers in real time and responding immediately if an abnormality is detected.

[0438] 1. Video Acquisition and Analysis

[0439] Terminals (smart devices and factory robots) use built-in cameras to capture images of the work environment and workers in real time. This camera can also capture the facial expressions and movements of workers and the surrounding environment. For example, a smartphone camera or a surveillance camera installed in a factory can be used.

[0440] 2. Video data transmission and analysis

[0441] The server receives the video data sent from the device and analyzes it in real time using a generative model and an emotion analysis engine. This analysis evaluates the worker's health and emotional state. For example, it uses image analysis technology using OpenCV and a customized emotion analysis engine.

[0442] 3. Alert Notification

[0443] If the server detects any abnormalities in the worker's health or emotional state based on the analysis results, it generates an alert. This alert is notified to the worker via audio or visual means via their device. For example, a message such as "Your stress level is rising. Please take a break" is displayed.

[0444] 4. Number of people management

[0445] The device uses a camera to count the number of people in the workplace in real time and sends the data to a server, allowing for accurate management of the number of people in the workplace. For example, it uses person detection technology using OpenCV.

[0446] 5. Linking with management systems

[0447] The device then connects the camera's count data to a management system, which can then generate alerts to proactively prevent worker absences and safety risks, and notify managers remotely. For example, this information can be sent to a cloud-based management platform.

[0448] 6. Detailed analysis of health and emotional status

[0449] The server then analyzes the worker's health and emotional state in more detail, taking into account environmental conditions and time, and generates alerts to encourage workers to take breaks at appropriate times. For example, the server can generate alerts taking into account weather and temperature information.

[0450] Specific examples and examples of prompts for generative AI models

[0451] For example, if Employee A working in a factory continues to work under high stress without taking a break, the system immediately issues an alert saying, "Your stress level is rising. Please take a break." If the emotion engine detects fatigue in Employee B's facial expression, it will notify him, "You need to pay attention to your health. Please take a short break."

[0452] Example prompts for generative AI models

[0453] Please create a Python program that analyzes video data of workers in real time and detects their emotional state and stress level from their facial expressions. Please also add a function to issue an alert when the stress level is high.

[0454] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0455] Step 1:

[0456] The terminal uses a built-in camera to capture images of the work environment and the worker in real time. The input is the video data captured by the camera. The output is real-time video frames. Specifically, the camera module periodically captures video and sends the data to the processor.

[0457] Step 2:

[0458] The terminal transmits the captured video data to the server. The input is the real-time video frame captured in step 1. The output is the video data transmitted to the server. Specifically, the terminal's communication module converts the video data into packets and transmits them to the server via the network.

[0459] Step 3:

[0460] The server inputs the received video data into the generative model and emotion analysis engine. The input is the video data sent from the device. The output is the analysis results related to the emotional state and health status. Specifically, the analysis module in the server applies the generative model and analyzes facial expressions using the emotion engine.

[0461] Step 4:

[0462] The server detects the worker's poor physical condition and stress level based on the analysis results of the emotion engine and generates an alert. The input is the analysis result obtained in step 3. The output is the generated alert message. Specifically, the analysis result is evaluated, and logic is activated to generate an alert if stress or fatigue exceeds a reference value.

[0463] Step 5:

[0464] The server sends the generated alert to the terminal. The input is the alert message generated in step 4. The output is the alert sent to the terminal. As a specific operation, the alert message is sent to the terminal via the network.

[0465] Step 6:

[0466] The terminal notifies the worker of the received alert by voice or visual means. The input is the alert message sent in step 5. The output is the notification to the worker. Specifically, the terminal displays a message on its display and plays a warning sound from its speaker.

[0467] Step 7:

[0468] The device uses a built-in camera to count the number of people in the workplace in real time and transmits the data to a server. The input is the video data captured by the camera. The output is people count data. Specifically, a person detection algorithm is applied and the counting results are transmitted to the server.

[0469] Step 8:

[0470] The server links the people count data with the management system. The input is the people count data sent in step 7. The output is the number of people data linked to the management system. Specifically, the number of people information is saved in a database within the management system.

[0471] Step 9:

[0472] The server performs a more detailed analysis of the worker's health and emotional state, taking into account environmental conditions and time. The inputs are the analysis results obtained in step 3 and environmental condition data. The output is the detailed analysis results. Specifically, additional conditions are incorporated into the analysis model to perform a more accurate health state assessment.

[0473] Step 10:

[0474] The server generates an alert to encourage appropriate breaks based on the detailed analysis results. The input is the detailed analysis results obtained in step 9. The output is the generated alert message. Specifically, the server generates a message encouraging breaks when certain conditions are met.

[0475] Step 11:

[0476] If there is an abnormality in the number of workers, the server generates an alert and sends it to the terminal. The input is the people count data and reference value sent in step 7. The output is an alert message for the abnormality. Specifically, the server compares the reference value with the number of workers data, and if a difference is found, an alert is generated.

[0477] Step 12:

[0478] The terminal notifies the worker of the received abnormal number of workers alert by voice or visual means. The input is the alert message sent in step 11. The output is a notification to the worker. Specifically, the terminal displays a message on its display and plays a warning sound from its speaker.

[0479] This series of processes makes it possible to monitor the health and safety of workers in real time and respond quickly if an abnormality is detected.

[0480] 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.

[0481] 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.

[0482] 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.

[0483] [Second embodiment]

[0484] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0485] 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.

[0486] 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).

[0487] 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.

[0488] 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.

[0489] 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).

[0490] 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.

[0491] 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.

[0492] 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.

[0493] 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.

[0494] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0495] 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."

[0496] The present invention relates to a healthcare and safety management system using a smartphone. This system monitors the situation outside and inside a vehicle in real time to prevent the driver from becoming ill or children from being locked inside the vehicle. A specific embodiment of this system will be described below.

[0497] Video acquisition and analysis

[0498] The device (smartphone) uses an external and internal camera to capture images of the interior and exterior of the vehicle in real time. The external camera captures the road conditions outside the vehicle, while the internal camera captures the interior of the vehicle, as well as the driver's facial expressions and movements. This allows for an accurate understanding of the driver's physical condition and the situation inside the vehicle.

[0499] The server receives the video data sent from the device and analyzes it in real time using a generative model. The AI ​​model detects drowsiness or poor physical condition from the driver's facial expression and generates an appropriate alert. This alert is then notified to the driver, prompting them to take appropriate action.

[0500] Alert Notification

[0501] The device receives alert notifications from the server and notifies the user in real time via audio and visual means. For example, if the driver feels drowsy, the smartphone will sound an alarm and display a message saying, "Signs of drowsiness have been detected. Please take a break." In this way, the alert can alert the driver to danger and encourage them to take appropriate action.

[0502] Managing the number of passengers getting on and off

[0503] The device uses the front camera to count the number of passengers getting on and off the bus in real time. This data is periodically sent to a server and managed by the server. For example, if the front camera counts three children on a kindergarten bus when they board, and only two get off when they exit, the device will send that data to the server.

[0504] The server generates an alert when there is a discrepancy between the number of passengers getting on and off the vehicle. As a means of notifying the discrepancy, the server detects the discrepancy and generates an alert. This alert is sent to the terminal and notified to the driver. For example, a message saying "One child remains in the vehicle. Please check." is notified.

[0505] Linking kindergartens and nurseries

[0506] The device connects the data on the number of passengers boarding and exiting the vehicle detected by the in-vehicle camera to the kindergarten or nursery school's passenger management system. This generates an alert to prevent children from being locked inside the vehicle and notifies parents remotely. Parents can remotely check their children's boarding and exiting status from their smartphones, giving them peace of mind when leaving their children in the care of their parents.

[0507] Detailed analysis of health status

[0508] The server then analyzes the driver's health in more detail, taking into account information such as driving speed, weather, and time. This information is then used to generate alerts to encourage the driver to take breaks at appropriate times. For example, if the driver is driving for a long time or in bad weather, fatigue may increase, so the server generates an alert saying, "We recommend taking a break."

[0509] As described above, the system of the present invention utilizes a smartphone camera and generative models to comprehensively support driver health management and in-vehicle safety. This system can prevent accidents and provide a safe driving environment.

[0510] The processing flow will be explained below.

[0511] Step 1:

[0512] Device: Activate the smartphone's rear camera and front camera. The rear camera captures images of the outside of the vehicle, while the front camera captures the driver's facial expression and the situation inside the vehicle.

[0513] Step 2:

[0514] Terminal: The video data acquired by the camera is sent to the cloud server in real time, continuously at regular intervals.

[0515] Step 3:

[0516] Server: Analyzes the received video data using a generative model. Specifically, it analyzes the driver's facial expressions, counts the number of people in the car, and understands road conditions.

[0517] Step 4:

[0518] Server: Evaluates the driver's health based on the analysis results. If signs of drowsiness or abnormalities are detected, an alert is generated.

[0519] Step 5:

[0520] Server: Compares the number of passengers boarding and alighting, and generates an alert if there is a discrepancy between the number of passengers boarding and alighting.

[0521] Step 6:

[0522] Terminal: Receives alert notifications from the server. Depending on the alert content, the user is notified by voice and visual means.

[0523] Step 7:

[0524] User: The driver or parent / guardian sees the alert and takes necessary action, such as taking a break or checking for children left in the car.

[0525] Step 8:

[0526] Terminal: The in-vehicle camera continuously monitors the situation inside the vehicle, and in particular in kindergarten and nursery school shuttle buses, it counts the number of people getting on and off the bus and links with the management system.

[0527] Step 9:

[0528] Server: Performs additional analysis based on driving speed, weather, and time to assess driver fatigue and health.

[0529] Step 10:

[0530] Device: Generates an alert to prompt the user to take a break at an appropriate time. For example, it displays a message saying, "You have been driving for a long time. Please take a break."

[0531] In this way, at every step, the system monitors the driver's health and the safety of the vehicle in real time and prompts appropriate action.

[0532] Example 1

[0533] 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."

[0534] There is a need for a means to prevent accidents caused by drivers' poor health or drowsiness while driving, as well as situations where children are left behind in the car. There is also a need for a system to manage the number of passengers boarding and exiting a vehicle, ensuring the safe transportation of children, especially at kindergartens and daycare centers. Conventional technologies have not provided effective solutions to these issues comprehensively.

[0535] 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.

[0536] In this invention, the server includes: means for capturing images of the interior and exterior of the vehicle in real time using the smartphone's exterior and interior cameras; means for transmitting the captured image data to a cloud server and analyzing the driver's health condition using a generative AI model; means for detecting the driver's poor physical condition or drowsiness based on the analysis results and generating an alert; means for notifying the driver of the generated alert audio or visually; means for counting the number of passengers in the vehicle and the number of passengers exiting the vehicle using the interior camera and transmitting the data to the cloud server; means for generating an alert if there is a discrepancy between the number of passengers in the vehicle and the number of passengers exiting the vehicle; means for notifying the driver of the generated alert audio or visually; means for linking the data on the number of passengers entering and exiting the vehicle with a kindergarten or nursery school's passenger management system; and means for performing a more detailed analysis of the driver's physical condition taking into account driving speed, weather, and time. This enables comprehensive management of the driver's physical condition and in-vehicle safety.

[0537] An "outside camera" is a camera installed on a smartphone or other device that is primarily used to capture external scenery and surrounding conditions.

[0538] An "in-camera" is a camera installed in a smartphone or other device that is primarily used to capture the interior of the device or the user's face.

[0539] A "cloud server" is a server that can be accessed remotely via the Internet and is a computer system used to store, process, and analyze data.

[0540] A "generative AI model" is an AI (artificial intelligence) model that uses machine learning and deep learning to learn and infer, and is a system that generates specific results or analyses based on input data.

[0541] An "alert" is a message or signal, which may be in the form of an audio or visual notification, that notifies the user when the system detects a particular condition.

[0542] An "occupant management system" is a system used to manage boarding and disembarking passengers, particularly in kindergartens and daycare centers, by recording the number of passengers boarding and disembarking and handling safety information.

[0543] "Health status" refers to the driver's physical and mental condition, which is analyzed to detect factors related to physical condition, including distraction, fatigue, and drowsiness while driving.

[0544] "Real-time" refers to a state in which data and information are acquired and processed immediately, and the results are reflected without delay.

[0545] Step 1: Generate a program for this system

[0546] The device (smartphone) uses an external and internal camera to monitor the situation outside and inside the vehicle in real time. The specific hardware used is the smartphone's built-in camera. On the software side, a video capture application is required, and this application has the function of sending captured video data to a cloud server.

[0547] The server is located in the cloud and analyzes the received video data. A generative AI model is used for the analysis. This AI model analyzes the driver's health status and is used to detect poor physical condition or drowsiness. Specific software used is a deep learning framework (e.g., TensorFlow or PyTorch).

[0548] Step 2: Explain the generated program's processing in natural language

[0549] The device uses the smartphone's rear and front cameras to capture real-time video footage of the interior and exterior of the vehicle. The rear camera captures the road conditions outside the vehicle, while the front camera captures the interior of the vehicle, as well as the driver's facial expressions and movements. This video data is acquired by the smartphone's video capture application.

[0550] The device transmits the captured video data to the cloud server in real time using the HTTPS protocol. The device efficiently compresses the video data and transmits it securely to the server.

[0551] The server analyzes the received video data using a deep learning framework (e.g., TensorFlow or PyTorch). Using a generative AI model, it detects drowsiness or poor physical condition from the driver's facial expressions and movements. Based on the analysis results, the server generates appropriate alerts.

[0552] The device notifies the user of the alert notification received from the server in real time using audio and visuals. For example, if the driver feels drowsy, the smartphone will sound an alarm and display a message saying, "Signs of drowsiness have been detected. Please take a break." The notification uses the smartphone's notification API.

[0553] The device uses the front camera to count the number of people entering and exiting the vehicle in real time, using a people-counting algorithm built into the smartphone.

[0554] The server generates an alert if there is a discrepancy between the number of passengers getting on and off the vehicle, and sends the alert to the device. The server then links the data sent to the passenger management system of the kindergarten or nursery school. This link generates an alert to prevent children from being locked inside the vehicle.

[0555] Step 3: Add examples to your description

[0556] Example 1: Driver health management

[0557] Scenario: A driver is driving for a long time and the front camera captures the driver with their eyes closed or blinking frequently.

[0558] Server analysis: A generative AI model analyzes the video and detects signs of drowsiness.

[0559] Alert notification: The server generates an alert saying "Signs of drowsiness have been detected. Please take a break." and sends it to the device.

[0560] User notification: The device notifies the user with an audible alarm and a visual message.

[0561] Example prompt:

[0562] "Please explain how to analyze video data of the driver's face captured by an in-car camera, detect signs of drowsiness or poor physical condition, and generate an alert."

[0563] Example 2: Preventing children from being locked inside a car

[0564] Scenario: While driving a kindergarten bus, the in-camera counts three children as they board, but only two get off when they disembark.

[0565] Server analysis: The server compares the number of passengers boarding and alighting and detects any discrepancies.

[0566] Alert notification: The server generates an alert saying "There is a child left in the car. Please check." and sends it to the device.

[0567] User notification: The device notifies the user with an audible alarm and a visual message.

[0568] Example prompt:

[0569] "Explain how in-car cameras can be used to count the number of children getting in and out of the car and generate an alert if any children remain in the car."

[0570] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0571] Step 1:

[0572] The device captures images of the exterior and interior of the vehicle in real time using the smartphone's exterior and interior cameras. The captured image data is divided into exterior images from the exterior camera and interior images from the interior camera. Specifically, the smartphone's video capture software captures images at a rate of 30 frames per second and stores them as data.

[0573] Input: Interior and exterior view of the car

[0574] Output: Real-time captured video data

[0575] Step 2:

[0576] The device compresses the captured video data and sends it to the cloud server using the HTTPS protocol, using H.264 encoding technology to minimize data transmission delays.

[0577] Input: Real-time video data

[0578] Output: Compressed video data

[0579] Step 3:

[0580] The server decodes the received compressed video data and analyzes it using a generative AI model. The decoded video data is used to detect the driver's facial region and track facial expressions, eye movements, head movements, etc. Deep learning technology is then used to detect driver drowsiness or poor physical condition from this information.

[0581] Input: Compressed video data

[0582] Output: Driver health condition analysis results

[0583] Step 4:

[0584] The server generates necessary alerts based on the analysis results. For example, if the driver's eyes are closed for more than three consecutive seconds, it generates a text alert saying, "Signs of drowsiness detected. Please take a break." It also generates audio alerts based on certain signals.

[0585] Input: Driver health analysis results

[0586] Output: Generated alert (text and audio)

[0587] Step 5:

[0588] The device notifies the user of the alert notification received from the server in real time via audio and visual means. Specifically, an alarm sounds from the smartphone speaker and a message appears on the display saying, "Signs of drowsiness have been detected. Please take a break." This is done using the smartphone's notification API.

[0589] Input: Generated alert (text and audio)

[0590] Output: An alert to be sent to the user

[0591] Step 6:

[0592] The device uses the front camera to count the number of people entering and exiting the vehicle in real time, using a people-counting algorithm built into the smartphone, and sends the results to a cloud server.

[0593] Input: In-car video data

[0594] Output: Real-time passenger count data for boarding and alighting

[0595] Step 7:

[0596] The server analyzes the received data on the number of passengers boarding and alighting, and generates an alert if there is a discrepancy. For example, if three children were counted when the passenger boarded the vehicle and only two got off when the passenger disembarked, the server generates an alert saying, "One child remains in the vehicle. Please check," and sends it to the device.

[0597] Input: Real-time passenger count data for boarding and alighting

[0598] Output: Alert notifying passengers of mismatch between boarding and alighting counts

[0599] Step 8:

[0600] The device will then notify the driver of the received alert notification in real time via audio and visual means, and will use the smartphone's speaker or screen to display a message saying, "A child has been left in the vehicle. Please check."

[0601] Input: Alert for mismatch between passenger numbers

[0602] Output: Alert to the driver

[0603] Step 9:

[0604] The server synchronizes the counted number of passengers boarding and alighting with the kindergarten or nursery school's passenger management system. Data is sent via an API, and information between the systems is updated instantly. If there is a discrepancy in the number of passengers, an alert is generated in the kindergarten's system.

[0605] Input: Real-time passenger count data for boarding and alighting

[0606] Output: Synchronized data to linked systems and generated alerts

[0607] In this way, the system analyzes input data at each step and generates and notifies appropriate alerts, thereby ensuring safety while driving and managing the situation inside the vehicle.

[0608] (Application example 1)

[0609] 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."

[0610] Conventional self-driving and manually driven vehicles lack systems that properly manage the health of drivers and passengers, as well as the safety of those inside the vehicle. In particular, there are issues with drivers becoming fatigued due to long driving hours or bad weather, children being locked inside the vehicle, and passengers becoming unwell. To address these issues, it is necessary to provide a system that monitors the situation inside and outside the vehicle in real time, analyzes the health status of passengers, and generates appropriate alerts.

[0611] 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.

[0612] In this invention, the server includes: means for capturing video of the interior and exterior of the vehicle in real time using the smart device's external and internal cameras; means for transmitting the captured video data to a remote server and analyzing the driver's health status using a generative model; means for detecting the driver's poor physical condition or drowsiness based on the analysis results and generating a warning; means for notifying the driver of the generated warning audio or visually; means for counting the number of passengers inside and outside the vehicle using the internal camera and transmitting the data to the remote server; means for generating a warning if there is a discrepancy between the number of passengers inside and outside the vehicle; means for notifying the driver of the generated warning audio or visually; means for comprehensively monitoring the conditions inside and outside the vehicle and managing the health and safety of passengers; means for further analyzing the health of passengers taking into account driving speed, weather, and time; means for generating a warning urging passengers to take an appropriate break if an abnormality is detected in their health status; and means for notifying passengers of the generated warning audio or visually. This makes it possible to comprehensively manage the health and safety of drivers and passengers and provide appropriate alerts even in autonomous vehicles.

[0613] A "smart device" is a mobile information terminal that has communication functions and a camera, such as a smartphone or a head-mounted display.

[0614] An "outside camera" is a camera installed on a smart device that captures external images.

[0615] An "in-camera" is a camera installed in a smart device that captures internal images.

[0616] A "remote server" is a group of computers that are placed on the cloud and receive and analyze data via the Internet.

[0617] A "generative model" is an algorithm that uses machine learning or deep learning models to predict or generate a specific outcome from input data.

[0618] "Health condition" refers to the physical condition of the driver or passenger, such as physical condition, illness, or drowsiness.

[0619] "Warning" is a notification message that informs the driver or passengers of any abnormalities or matters requiring attention that the system has detected.

[0620] "Voice notification" is a function that notifies the driver and passengers of warnings by voice.

[0621] "Visual notification" is a function that notifies drivers and passengers of warnings through visual means such as a screen or light.

[0622] "Occupancy" refers to the total number of people on board the vehicle.

[0623] "Number of people getting off" is the total number of people who got off the vehicle.

[0624] "Situation monitoring" means observing and understanding the environment inside and outside the vehicle, as well as people's movements, in real time.

[0625] "Illness" refers to a state in which one's health condition is different from normal and it is deemed dangerous to continue driving or traveling.

[0626] A "passenger management system" is a system for managing boarding and disembarking situations at educational institutions and other facilities.

[0627] "Running speed" refers to the speed at which a vehicle moves.

[0628] "Weather" refers to the atmospheric conditions at a given time, including sunny, rainy, snowy, foggy, etc.

[0629] A "break" is a time or action taken to temporarily stop driving or traveling and rest your body and mind.

[0630] This invention is a system that monitors the situation inside and outside the vehicle in real time and provides comprehensive support for passenger health management and safety. It mainly uses smart devices and a remote server to analyze the health status of the driver and passengers in an autonomous vehicle and generate and notify alerts as necessary. Specific embodiments are described below.

[0631] Hardware Configuration

[0632] The system includes the following major hardware components:

[0633] 1. Smart Devices

[0634] Outer camera: Captures footage outside the vehicle.

[0635] In-camera: Captures footage from inside the car.

[0636] Audio output device: Used to notify audio warnings.

[0637] Display: Used to display visual warnings.

[0638] 2. Remote Server

[0639] Cloud Computing: The provision of computational resources.

[0640] Database: Storage and management of collected data.

[0641] Software Configuration

[0642] The system is implemented using the following major software components:

[0643] 1. Generative Model (AI Model)

[0644] Used to analyze the health status of drivers and passengers.

[0645] Machine learning framework used: TensorFlow / Keras.

[0646] 2. Data Processing and Analysis

[0647] Image processing library: Preprocesses image data using OpenCV.

[0648] Communication library: Communicate with remote servers using the requests module.

[0649] Data flow and processing steps

[0650] The basic data flow and processing procedures of the system are as follows:

[0651] 1. Acquiring footage

[0652] The smart device's external and internal cameras capture images of the vehicle's exterior and interior in real time, and the image data is converted into an appropriate format (e.g., JPEG or PNG).

[0653] 2. Transmission of video data

[0654] The video data is sent to a remote server via a communication library, where it is temporarily stored in a database for analysis.

[0655] 3. Health status analysis

[0656] The received video data is analyzed by a generative model to determine the health status of the driver and passengers. An example of a prompt sentence is given to the generative model: "Please detect whether drowsiness is felt in this video frame."

[0657] 4. Alert generation and notification

[0658] If the analysis detects any abnormalities in the driver or passengers, such as poor physical condition or drowsiness, the server generates a warning, which is then provided to the driver or passenger in real time via an audio output device or display.

[0659] Usage example

[0660] To illustrate, consider the following scenario:

[0661] If drowsiness is detected from the facial expression of a driver who has been driving for a long time, an audio and visual warning will be displayed saying, "Signs of drowsiness have been detected. Please take a break."

[0662] On educational institution shuttle buses, the in-camera counts the number of passengers getting on and off the bus, and if there are children who have not yet disembarked when the bus disembarks, a warning is generated saying, "There are passengers in the bus who have not yet disembarked. Please check."

[0663] If the system determines that the driver is becoming fatigued during long drives in bad weather, the system will send a notification saying, "We recommend that you take a break."

[0664] This configuration provides a system that can comprehensively monitor conditions inside and outside the vehicle, improving the health and safety of drivers and passengers.

[0665] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0666] Step 1:

[0667] The terminal (smart device) operates the outer and inner cameras to capture images of the outside and inside of the vehicle in real time.

[0668] Input: Video footage from inside and outside the car.

[0669] Data processing: Convert the video into the appropriate format (e.g. JPEG, PNG).

[0670] Output: Captured video data.

[0671] Step 2:

[0672] The video data acquired by the terminal is sent to a remote server using a communication library.

[0673] Input: Acquired video data.

[0674] Data calculation: Transfer of video data.

[0675] Output: Video data sent to the server.

[0676] Step 3:

[0677] The server stores the received video data in a database.

[0678] Input: Transmitted video data.

[0679] Data processing: Store in a database.

[0680] Output: Video data stored in a database.

[0681] Step 4:

[0682] The server uses a generative model to analyze the health status of the driver and passengers from the captured video data.

[0683] Input: Stored video data.

[0684] Data calculation: health status analysis, for example, based on the prompt "Detect whether you feel drowsy in this video frame."

[0685] Output: Analysis results (health status assessment).

[0686] Step 5:

[0687] If the server detects an abnormality based on the analysis results, it generates an alert.

[0688] Input: Analysis results.

[0689] Data operation: Generate warning.

[0690] Output: The warning message generated.

[0691] Step 6:

[0692] The server sends the generated alert to the device.

[0693] Input: Warning message.

[0694] Data calculation: Transfer of warning messages.

[0695] Output: The warning message sent to the terminal.

[0696] Step 7:

[0697] The device will notify the driver or passengers of the warning message received via audio or visual means.

[0698] Input: Warning message.

[0699] Data calculation: Notification through audio output device or display.

[0700] Output: A warning message is sent to the driver and passengers.

[0701] 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.

[0702] The present invention relates to a healthcare and safety management system that uses a smartphone and an emotion engine. This system monitors the situation outside and inside the vehicle, including the user's emotional state, in real time to prevent the driver from becoming ill or children from being trapped inside the vehicle. A specific embodiment of this system will be described below.

[0703] Video acquisition and analysis

[0704] The device (smartphone) uses an external and internal camera to capture images of the vehicle's exterior and interior in real time. The external camera captures road conditions outside the vehicle, while the internal camera captures the driver's facial expressions and the situation inside the vehicle. This allows for an accurate understanding of the driver's physical condition and the situation inside the vehicle.

[0705] Video data transmission and analysis

[0706] The server receives video data from the device and analyzes it in real time using a generative model and emotion engine. The emotion engine analyzes the driver's emotional state from their facial expressions and evaluates it by integrating it with their health condition. For example, it can detect changes such as increased stress during long driving sessions or the appearance of fatigue.

[0707] Alert Notification

[0708] Based on the analysis results, the server generates an alert if it detects any abnormalities in the driver's health or emotional state. The generated alert is notified to the driver via audio or visual means via the device. For example, a message such as "Your stress level is increasing. Please take a break" is displayed.

[0709] Managing the number of passengers getting on and off

[0710] The device uses the in-car camera to count the number of passengers getting on and off the vehicle in real time and sends the data to a cloud server, allowing for accurate management of the number of passengers on board.

[0711] The server compares the number of passengers boarding and alighting, and generates an alert if there is a discrepancy. For example, if a child is left behind on a kindergarten bus, an alert will be generated saying, "One child remains in the bus. Please check."

[0712] Linking with kindergartens and nurseries

[0713] The device connects the data on the number of passengers boarding and exiting the vehicle detected by the in-vehicle camera to the kindergarten or nursery school's passenger management system. This generates an alert to prevent children from being locked inside the vehicle and notifies parents remotely. Parents can remotely check their children's boarding and exiting status from their smartphones, giving them peace of mind when leaving their children in the care of their parents.

[0714] Detailed analysis of health and emotional state

[0715] The server then takes into account information such as driving speed, weather, and time of day to perform a more detailed analysis of the driver's health and emotional state. This allows the server to generate alerts to encourage the driver to take breaks at appropriate times. For example, if stress or fatigue increases during long drives in bad weather or at night, the server will generate an alert saying, "We recommend taking a break."

[0716] Responding to emergencies

[0717] The server automatically notifies external authorities if the driver is in an emergency based on the acquired video data and the analysis results of the emotion engine. The content of the notification can be customized, allowing the situation to be quickly communicated to specific contacts.

[0718] As described above, the system of the present invention utilizes a smartphone camera, generative model, and emotion engine to comprehensively support driver health and emotion management. This system can prevent accidents and provide a safe driving environment.

[0719] The processing flow will be explained below.

[0720] Step 1:

[0721] Device: Activate the smartphone's rear camera and front camera. The rear camera captures images of the outside of the vehicle, while the front camera captures the driver's facial expression and the situation inside the vehicle.

[0722] Step 2:

[0723] Terminal: Sends acquired video data to the cloud server at regular intervals.

[0724] Step 3:

[0725] Server: The cloud server inputs the received video data into the generative model and emotion engine in real time for analysis.

[0726] Step 4:

[0727] Server: Evaluates the driver's health and emotional state (e.g., stress level and fatigue level) from their facial expressions and movements.

[0728] Step 5:

[0729] Server: Based on the analysis results, if an abnormality is detected in the driver's health or emotional state, an alert is generated. For example, if the driver's face shows signs of fatigue or stress, an alert is generated saying, "Your stress level is rising. Please take a break."

[0730] Step 6:

[0731] Device: Receives alerts from the server and notifies the user audio and visually. A message is displayed on the smartphone screen and an audio alert is played.

[0732] Step 7:

[0733] Terminal: Using the in-camera, it continuously counts the number of passengers getting on and off the vehicle and sends this data to a cloud server.

[0734] Step 8:

[0735] Server: If there is a discrepancy between the number of passengers getting on and off, for example if a child is left behind on a shuttle bus, an alert is generated. This alert will say, "There is one child left in the bus. Please check."

[0736] Step 9:

[0737] Terminal: The boarding and alighting data is linked to the kindergarten or nursery school's passenger management system, which then remotely notifies parents of their children's boarding and alighting information.

[0738] Step 10:

[0739] Server: Integrates data such as driving speed, weather, and time to perform a more detailed analysis of the driver's health and emotional state. Based on the analysis results, it generates additional alerts as needed. For example, an alert saying, "You've been driving for a long time. We recommend you take a break."

[0740] Step 11:

[0741] User: The driver reviews the generated alert and takes appropriate action, such as taking a break or checking for children left in the car.

[0742] Step 12:

[0743] Server: Based on the acquired video data and the analysis results of the emotion engine, if the driver is in an emergency, the server automatically notifies external authorities. The content of the notification can be customized to quickly inform specific contacts of the situation.

[0744] Example 2

[0745] 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."

[0746] In recent years, managing the health and emotional state of drivers has become an important issue. In particular, the risk of accidents due to fatigue and stress caused by long driving hours is increasing. Dangerous situations such as children being left behind in cars are also becoming a problem. Conventional technologies have the difficulty of detecting these problems in real time and generating alerts at the appropriate time.

[0747] 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.

[0748] In this invention, the server includes: means for capturing images of the interior and exterior of the vehicle in real time using the smartphone's exterior and interior cameras; means for transmitting the captured image data to a cloud server and analyzing the driver's health and emotional state using a generative AI model and an emotion engine; means for detecting the driver's poor physical condition or stress based on the analysis results and generating an alert; means for notifying the driver of the generated alert audio or visually; means for counting the number of passengers in the vehicle and the number of passengers exiting the vehicle using the interior camera and transmitting the data to the cloud server; means for generating an alert if there is a discrepancy between the number of passengers in the vehicle and the number of passengers exiting the vehicle; means for notifying the driver of the generated alert audio or visually; means for performing a detailed analysis of the driver's health and emotional state taking into account driving speed, weather, and time; and means for automatically reporting to an external agency in the event of an emergency. This enables real-time management of the driver's health and safety in the vehicle, and enables rapid response to emergencies.

[0749] A "smartphone" is a portable, multi-functional electronic device with internet connectivity and a camera.

[0750] An "outside camera" is a camera installed on the outside of a smartphone to capture external scenery and objects.

[0751] An "in-camera" is a camera installed inside a smartphone that captures the user's face and the interior of the device.

[0752] "Video data" refers to a series of visual information acquired by the outer camera and the inner camera.

[0753] A "cloud server" is a remote server accessible via the Internet, a group of devices that store and process data.

[0754] A "generative AI model" is an algorithmic model of artificial intelligence that analyzes input data and generates specific results or predictions.

[0755] The "emotion engine" is software that analyzes video data and identifies the emotional state of the subject.

[0756] "Analysis results" refers to the information and data obtained after the generative AI model and emotion engine process the video data.

[0757] An "alert" is a warning message that is generated to notify of an abnormal situation and is displayed visually or audibly.

[0758] "Number of passengers" refers to the total number of people on board the vehicle.

[0759] "Number of people getting off" refers to the total number of people who got off the vehicle.

[0760] "Traveling speed" refers to the speed at which a vehicle is moving in the direction of travel.

[0761] An "emergency situation" refers to an unexpected dangerous situation or a serious problem with the driver's health.

[0762] "External agencies" refers to rescue services and parties that may be contacted in an emergency.

[0763] The present invention relates to a healthcare and safety management system that uses a smartphone and an emotion engine. This system monitors the situation outside and inside the vehicle, including the user's emotional state, in real time to prevent the driver from becoming ill or children from being trapped inside the vehicle. A specific embodiment of this system will be described below.

[0764] Video acquisition and analysis

[0765] The device (smartphone) uses an external and internal camera to capture images of the outside and inside of the vehicle in real time. The external camera captures the road conditions outside the vehicle, while the internal camera captures the driver's facial expression and the situation inside the vehicle. This allows for an accurate understanding of the driver's physical condition and the situation inside the vehicle.

[0766] Examples:

[0767] The outer camera captures road conditions during rainy weather.

[0768] The in-camera detects the driver's tired expression.

[0769] Video data transmission and analysis

[0770] The device sends the captured video data to a server, which then analyzes the video data in real time using a generative AI model and an emotion engine. The emotion engine analyzes the driver's emotional state from their facial expressions, and the generative AI model recognizes specific elements contained in the video.

[0771] Examples:

[0772] The generative AI model is given the prompt sentence, "How tired is this driver currently?"

[0773] The emotion engine generates the result "Exhaustion: 80%".

[0774] Alert generation and notification

[0775] If the server detects an abnormality based on the analysis results, it generates an alert, which is then sent to the driver via their device. Notifications are made via audio, vibration, and visual (screen display).

[0776] Examples:

[0777] A voice message will be played saying, "Your stress levels are high, please take a break."

[0778] The same message will be displayed on the device screen.

[0779] Managing the number of passengers getting on and off

[0780] The device uses the in-car camera to count the number of passengers getting on and off the vehicle in real time and sends the data to a server, which analyzes the data and checks for any abnormalities.

[0781] Examples:

[0782] The device detects that 10 children have boarded a kindergarten shuttle bus.

[0783] When passengers exit the vehicle, the server detects that only nine passengers have exited and generates an alert saying, "There is one child left in the vehicle. Please check."

[0784] Detailed analysis of health and emotional state

[0785] The server takes into account driving speed, weather, and time information, performs detailed analysis of the driver's health and emotional state, and generates appropriate alerts based on the results.

[0786] Examples:

[0787] If you are driving for a long time at night in bad weather, an alert will be generated saying, "You are tired. We recommend you take a break."

[0788] Responding to emergencies

[0789] The server has the ability to automatically notify external agencies in the event of an emergency based on the acquired video data and the analysis results of the emotion engine. The content of the notification can be customized, and the situation can be quickly communicated to specific contacts.

[0790] Examples:

[0791] If the driver loses consciousness, an emergency situation will occur and an automatic call will be sent to emergency services, along with footage from inside the vehicle and the driver's current location.

[0792] This system utilizes a smartphone camera, generative AI models, and an emotion engine to comprehensively support driver health and emotion management, preventing accidents and providing a safe driving environment.

[0793] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0794] System program processing flow

[0795] Step 1: Acquire footage

[0796] The device uses the external and internal cameras to capture images of the outside and inside of the vehicle in real time.

[0797] Input: External environment (road conditions), in-car environment (driver's facial expression, etc.)

[0798] Data processing / calculation: The outer camera captures external images, and the inner camera captures internal images.

[0799] Output: Out-camera video data, in-camera video data

[0800] Specific behavior:

[0801] The device captures video at 24 frames per second.

[0802] Step 2: Sending video data

[0803] The terminal transmits the acquired video data to a server via the Internet.

[0804] Input: Out-camera video data, in-camera video data

[0805] Data processing / calculation: Packetize video data and send it over the Internet

[0806] Output: Video data received by the server

[0807] Specific behavior:

[0808] The device uses Wi-Fi or LTE networks to upload video data to a server.

[0809] Step 3: Analyzing the video data

[0810] The server sends the received video data to the generative AI model and emotion engine for real-time analysis.

[0811] Input: Video data received by the server

[0812] Data processing / calculation: Analysis using generative AI models and emotion engines

[0813] Output: Analysis results (driver's health, emotional state, etc.)

[0814] Specific behavior:

[0815] The server sends a prompt to the generative AI model, saying, "Analyze the driver's stress level from their facial expression."

[0816] The emotion engine outputs the analysis result "Driver's stress level: High."

[0817] Step 4: Alert Generation

[0818] If an abnormality is detected based on the analysis results, the server generates an alert.

[0819] Input: Analysis results

[0820] Data processing / calculation: Generate alert messages based on analysis results

[0821] Output: Alert message

[0822] Specific behavior:

[0823] The server generates an alert message saying "Your stress level is high and you need to take a break."

[0824] Step 5: Alert Notification

[0825] The terminal notifies the driver of alert messages sent from the server.

[0826] Input: Alert message from the server

[0827] Data processing / calculation: Converted into audio, vibration, and visual notification formats

[0828] Output: Notification to the driver

[0829] Specific behavior:

[0830] The device plays a voice message saying, "Your stress level is high, please take a break."

[0831] The terminal will display the same message on the screen.

[0832] Step 6: Managing passenger numbers

[0833] The device uses the in-camera to count the number of passengers getting on and off the vehicle in real time and sends the data to a server.

[0834] Input: In-camera video data

[0835] Data processing / calculation: Analyze video data and count people

[0836] Output: Number of passengers boarding and alighting data

[0837] Specific behavior:

[0838] When the terminal detects one person on board, it sends the data "+1 person" to the server.

[0839] The server confirms that one person has left the vehicle when they get off, and receives the data "-1 person."

[0840] Step 7: Anomaly detection and notification

[0841] The server compares the number of passengers boarding and alighting, and if there is a discrepancy, it generates an alert and notifies the user via the terminal.

[0842] Input: Number of passengers boarding and alighting data

[0843] Data processing / calculation: Detect discrepancies in headcount data and generate alert messages

[0844] Output: Alert message

[0845] Specific behavior:

[0846] The server generates an alert message saying "There is a child left in the car. Please check."

[0847] The device will notify you of the message with audio and visual notifications.

[0848] Step 8: Detailed analysis of your health and emotional state

[0849] The server takes into account driving speed, weather and time information to perform a more detailed analysis of the driver's health and emotional state.

[0850] Input: Driving speed, weather, and time information

[0851] Data processing / calculation: Integrates analytical information to provide a detailed assessment of health and emotional status

[0852] Output: Detailed analysis results

[0853] Specific behavior:

[0854] The server evaluates, "The current weather is rainy, and the stress level is high because you are driving at night."

[0855] The server generates an alert message saying "We recommend you take a break."

[0856] Step 9: Emergency response

[0857] The server has a means to automatically notify external agencies in the event of an emergency.

[0858] Input: Emergency trigger (e.g., sudden deterioration in health condition)

[0859] Data processing / calculation: Creation of emergency messages and transmission to external agencies

[0860] Output: Report message to external organization

[0861] Specific behavior:

[0862] The server generates a message saying, "The driver has lost consciousness. The current location is point xx."

[0863] The server will notify the configured contacts via SMS or phone call.

[0864] (Application example 2)

[0865] 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."

[0866] In conventional factories, there is a lack of means to monitor the health and mental state of workers in real time, so workers may not notice if they are overworked or stressed, posing a significant risk to work quality and safety. Furthermore, if a sudden health problem occurs, it is difficult to respond quickly, making it difficult to guarantee the safety of workers.

[0867] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for acquiring video of the work environment and workers in real time using a camera of a smart device; means for transmitting the acquired video data to the server and analyzing the health status of the workers using a generative model; means for detecting poor physical condition and stress level of the workers based on the analysis results and generating an alert; means for notifying the workers of the generated alert audio or visually; means for counting the number of people in the workplace using a camera and transmitting the data to the server; means for generating an alert if there is an abnormality in the number of people; and means for notifying the workers of the generated alert audio or visually. This makes it possible to monitor and manage the health status and safety of workers in real time.

[0868] A "smart device" is a portable information terminal equipped with communication and camera functions.

[0869] A "camera" is an electronic device for acquiring video data.

[0870] "Real time" means processing that is performed in real time without delay.

[0871] "Video data" refers to recorded data in digital format that includes image information.

[0872] A "server" is a computer that stores and analyzes data over a network.

[0873] A "generative model" is an algorithm that generates a particular outcome based on data analysis.

[0874] "Health" means the balance or state of the body and mind.

[0875] "Analysis" is the process of extracting meaningful information and patterns from data.

[0876] "Stress level" is an index that indicates the degree of mental stress on a worker.

[0877] An "alert" is a notification or warning that draws attention.

[0878] "Voice notification" is a means of conveying information using voice.

[0879] "Visual notification" is a method of conveying information using visual information.

[0880] A "worker" is a person who performs work in a factory or work site.

[0881] "Counting people" means measuring the number of individuals present in a particular area.

[0882] "Abnormal" means a state or situation that is different from the normal.

[0883] A "management system" is a system that uses data to monitor and control business operations and tasks.

[0884] "Environmental conditions" are factors that affect the working environment, such as temperature, humidity, and noise.

[0885] "Encouraging breaks" means encouraging people to take a break by temporarily stopping their work.

[0886] "Real-time monitoring and management" means observing and controlling the actual state without any time delay.

[0887] This invention relates to a health management and safety monitoring system for factories that uses smart devices and an emotion analysis engine. The system aims to improve work safety and efficiency by monitoring the health and mental state of workers in real time and responding immediately if an abnormality is detected.

[0888] 1. Video Acquisition and Analysis

[0889] Terminals (smart devices and factory robots) use built-in cameras to capture images of the work environment and workers in real time. This camera can also capture the facial expressions and movements of workers and the surrounding environment. For example, a smartphone camera or a surveillance camera installed in a factory can be used.

[0890] 2. Video data transmission and analysis

[0891] The server receives the video data sent from the device and analyzes it in real time using a generative model and an emotion analysis engine. This analysis evaluates the worker's health and emotional state. For example, it uses image analysis technology using OpenCV and a customized emotion analysis engine.

[0892] 3. Alert Notification

[0893] If the server detects any abnormalities in the worker's health or emotional state based on the analysis results, it generates an alert. This alert is notified to the worker via audio or visual means via their device. For example, a message such as "Your stress level is rising. Please take a break" is displayed.

[0894] 4. Number of people management

[0895] The device uses a camera to count the number of people in the workplace in real time and sends the data to a server, allowing for accurate management of the number of people in the workplace. For example, it uses person detection technology using OpenCV.

[0896] 5. Linking with management systems

[0897] The device then connects the camera's count data to a management system, which can then generate alerts to proactively prevent worker absences and safety risks, and notify managers remotely. For example, this information can be sent to a cloud-based management platform.

[0898] 6. Detailed analysis of health and emotional status

[0899] The server then analyzes the worker's health and emotional state in more detail, taking into account environmental conditions and time, and generates alerts to encourage workers to take breaks at appropriate times. For example, the server can generate alerts taking into account weather and temperature information.

[0900] Specific examples and examples of prompts for generative AI models

[0901] For example, if Employee A working in a factory continues to work under high stress without taking a break, the system immediately issues an alert saying, "Your stress level is rising. Please take a break." If the emotion engine detects fatigue in Employee B's facial expression, it will notify him, "You need to pay attention to your health. Please take a short break."

[0902] Example prompts for generative AI models

[0903] Please create a Python program that analyzes video data of workers in real time and detects their emotional state and stress level from their facial expressions. Please also add a function to issue an alert when the stress level is high.

[0904] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0905] Step 1:

[0906] The terminal uses a built-in camera to capture images of the work environment and the worker in real time. The input is the video data captured by the camera. The output is real-time video frames. Specifically, the camera module periodically captures video and sends the data to the processor.

[0907] Step 2:

[0908] The terminal transmits the captured video data to the server. The input is the real-time video frame captured in step 1. The output is the video data transmitted to the server. Specifically, the terminal's communication module converts the video data into packets and transmits them to the server via the network.

[0909] Step 3:

[0910] The server inputs the received video data into the generative model and emotion analysis engine. The input is the video data sent from the device. The output is the analysis results related to the emotional state and health status. Specifically, the analysis module in the server applies the generative model and analyzes facial expressions using the emotion engine.

[0911] Step 4:

[0912] The server detects the worker's poor physical condition and stress level based on the analysis results of the emotion engine and generates an alert. The input is the analysis result obtained in step 3. The output is the generated alert message. Specifically, the analysis result is evaluated, and logic is activated to generate an alert if stress or fatigue exceeds a reference value.

[0913] Step 5:

[0914] The server sends the generated alert to the terminal. The input is the alert message generated in step 4. The output is the alert sent to the terminal. As a specific operation, the alert message is sent to the terminal via the network.

[0915] Step 6:

[0916] The terminal notifies the worker of the received alert by voice or visual means. The input is the alert message sent in step 5. The output is the notification to the worker. Specifically, the terminal displays a message on its display and plays a warning sound from its speaker.

[0917] Step 7:

[0918] The device uses a built-in camera to count the number of people in the workplace in real time and transmits the data to a server. The input is the video data captured by the camera. The output is people count data. Specifically, a person detection algorithm is applied and the counting results are transmitted to the server.

[0919] Step 8:

[0920] The server links the people count data with the management system. The input is the people count data sent in step 7. The output is the number of people data linked to the management system. Specifically, the number of people information is saved in a database within the management system.

[0921] Step 9:

[0922] The server performs a more detailed analysis of the worker's health and emotional state, taking into account environmental conditions and time. The inputs are the analysis results obtained in step 3 and environmental condition data. The output is the detailed analysis results. Specifically, additional conditions are incorporated into the analysis model to perform a more accurate health state assessment.

[0923] Step 10:

[0924] The server generates an alert to encourage appropriate breaks based on the detailed analysis results. The input is the detailed analysis results obtained in step 9. The output is the generated alert message. Specifically, the server generates a message encouraging breaks when certain conditions are met.

[0925] Step 11:

[0926] If there is an abnormality in the number of workers, the server generates an alert and sends it to the terminal. The input is the people count data and reference value sent in step 7. The output is an alert message for the abnormality. Specifically, the server compares the reference value with the number of workers data, and if a difference is found, an alert is generated.

[0927] Step 12:

[0928] The terminal notifies the worker of the received abnormal number of workers alert by voice or visual means. The input is the alert message sent in step 11. The output is a notification to the worker. Specifically, the terminal displays a message on its display and plays a warning sound from its speaker.

[0929] This series of processes makes it possible to monitor the health and safety of workers in real time and respond quickly if an abnormality is detected.

[0930] 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.

[0931] 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.

[0932] 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.

[0933] [Third embodiment]

[0934] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0935] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0936] 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).

[0937] 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.

[0938] 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.

[0939] 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).

[0940] 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.

[0941] 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.

[0942] 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.

[0943] 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.

[0944] 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.

[0945] 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."

[0946] The present invention relates to a healthcare and safety management system using a smartphone. This system monitors the situation outside and inside a vehicle in real time to prevent the driver from becoming ill or children from being locked inside the vehicle. A specific embodiment of this system will be described below.

[0947] Video acquisition and analysis

[0948] The device (smartphone) uses an external and internal camera to capture images of the interior and exterior of the vehicle in real time. The external camera captures the road conditions outside the vehicle, while the internal camera captures the interior of the vehicle, as well as the driver's facial expressions and movements. This allows for an accurate understanding of the driver's physical condition and the situation inside the vehicle.

[0949] The server receives the video data sent from the device and analyzes it in real time using a generative model. The AI ​​model detects drowsiness or poor physical condition from the driver's facial expression and generates an appropriate alert. This alert is then notified to the driver, prompting them to take appropriate action.

[0950] Alert Notification

[0951] The device receives alert notifications from the server and notifies the user in real time via audio and visual means. For example, if the driver feels drowsy, the smartphone will sound an alarm and display a message saying, "Signs of drowsiness have been detected. Please take a break." In this way, the alert can alert the driver to danger and encourage them to take appropriate action.

[0952] Managing the number of passengers getting on and off

[0953] The device uses the front camera to count the number of passengers getting on and off the bus in real time. This data is periodically sent to a server and managed by the server. For example, if the front camera counts three children on a kindergarten bus when they board, and only two get off when they exit, the device will send that data to the server.

[0954] The server generates an alert when there is a discrepancy between the number of passengers getting on and off the vehicle. As a means of notifying the discrepancy, the server detects the discrepancy and generates an alert. This alert is sent to the terminal and notified to the driver. For example, a message saying "One child remains in the vehicle. Please check." is notified.

[0955] Linking kindergartens and nurseries

[0956] The device connects the data on the number of passengers boarding and exiting the vehicle detected by the in-vehicle camera to the kindergarten or nursery school's passenger management system. This generates an alert to prevent children from being locked inside the vehicle and notifies parents remotely. Parents can remotely check their children's boarding and exiting status from their smartphones, giving them peace of mind when leaving their children in the care of their parents.

[0957] Detailed analysis of health status

[0958] The server then analyzes the driver's health in more detail, taking into account information such as driving speed, weather, and time. This information is then used to generate alerts to encourage the driver to take breaks at appropriate times. For example, if the driver is driving for a long time or in bad weather, fatigue may increase, so the server generates an alert saying, "We recommend taking a break."

[0959] As described above, the system of the present invention utilizes a smartphone camera and generative models to comprehensively support driver health management and in-vehicle safety. This system can prevent accidents and provide a safe driving environment.

[0960] The processing flow will be explained below.

[0961] Step 1:

[0962] Device: Activate the smartphone's rear camera and front camera. The rear camera captures images of the outside of the vehicle, while the front camera captures the driver's facial expression and the situation inside the vehicle.

[0963] Step 2:

[0964] Terminal: The video data acquired by the camera is sent to the cloud server in real time, continuously at regular intervals.

[0965] Step 3:

[0966] Server: Analyzes the received video data using a generative model. Specifically, it analyzes the driver's facial expressions, counts the number of people in the car, and understands road conditions.

[0967] Step 4:

[0968] Server: Evaluates the driver's health based on the analysis results. If signs of drowsiness or abnormalities are detected, an alert is generated.

[0969] Step 5:

[0970] Server: Compares the number of passengers boarding and alighting, and generates an alert if there is a discrepancy between the number of passengers boarding and alighting.

[0971] Step 6:

[0972] Terminal: Receives alert notifications from the server. Depending on the alert content, the user is notified by voice and visual means.

[0973] Step 7:

[0974] User: The driver or parent / guardian sees the alert and takes necessary action, such as taking a break or checking for children left in the car.

[0975] Step 8:

[0976] Terminal: The in-vehicle camera continuously monitors the situation inside the vehicle, and in particular in kindergarten and nursery school shuttle buses, it counts the number of people getting on and off the bus and links with the management system.

[0977] Step 9:

[0978] Server: Performs additional analysis based on driving speed, weather, and time to assess driver fatigue and health.

[0979] Step 10:

[0980] Device: Generates an alert to prompt the user to take a break at an appropriate time. For example, it displays a message saying, "You have been driving for a long time. Please take a break."

[0981] In this way, at every step, the system monitors the driver's health and the safety of the vehicle in real time and prompts appropriate action.

[0982] Example 1

[0983] 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."

[0984] There is a need for a means to prevent accidents caused by drivers' poor health or drowsiness while driving, as well as situations where children are left behind in the car. There is also a need for a system to manage the number of passengers boarding and exiting a vehicle, ensuring the safe transportation of children, especially at kindergartens and daycare centers. Conventional technologies have not provided effective solutions to these issues comprehensively.

[0985] 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.

[0986] In this invention, the server includes: means for capturing images of the interior and exterior of the vehicle in real time using the smartphone's exterior and interior cameras; means for transmitting the captured image data to a cloud server and analyzing the driver's health condition using a generative AI model; means for detecting the driver's poor physical condition or drowsiness based on the analysis results and generating an alert; means for notifying the driver of the generated alert audio or visually; means for counting the number of passengers in the vehicle and the number of passengers exiting the vehicle using the interior camera and transmitting the data to the cloud server; means for generating an alert if there is a discrepancy between the number of passengers in the vehicle and the number of passengers exiting the vehicle; means for notifying the driver of the generated alert audio or visually; means for linking the data on the number of passengers entering and exiting the vehicle with a kindergarten or nursery school's passenger management system; and means for performing a more detailed analysis of the driver's physical condition taking into account driving speed, weather, and time. This enables comprehensive management of the driver's physical condition and in-vehicle safety.

[0987] An "outside camera" is a camera installed on a smartphone or other device that is primarily used to capture external scenery and surrounding conditions.

[0988] An "in-camera" is a camera installed in a smartphone or other device that is primarily used to capture the interior of the device or the user's face.

[0989] A "cloud server" is a server that can be accessed remotely via the Internet and is a computer system used to store, process, and analyze data.

[0990] A "generative AI model" is an AI (artificial intelligence) model that uses machine learning and deep learning to learn and infer, and is a system that generates specific results or analyses based on input data.

[0991] An "alert" is a message or signal, which may be in the form of an audio or visual notification, that notifies the user when the system detects a particular condition.

[0992] An "occupant management system" is a system used to manage boarding and disembarking passengers, particularly in kindergartens and daycare centers, by recording the number of passengers boarding and disembarking and handling safety information.

[0993] "Health status" refers to the driver's physical and mental condition, which is analyzed to detect factors related to physical condition, including distraction, fatigue, and drowsiness while driving.

[0994] "Real-time" refers to a state in which data and information are acquired and processed immediately, and the results are reflected without delay.

[0995] Step 1: Generate a program for this system

[0996] The device (smartphone) uses an external and internal camera to monitor the situation outside and inside the vehicle in real time. The specific hardware used is the smartphone's built-in camera. On the software side, a video capture application is required, and this application has the function of sending captured video data to a cloud server.

[0997] The server is located in the cloud and analyzes the received video data. A generative AI model is used for the analysis. This AI model analyzes the driver's health status and is used to detect poor physical condition or drowsiness. Specific software used is a deep learning framework (e.g., TensorFlow or PyTorch).

[0998] Step 2: Explain the generated program's processing in natural language

[0999] The device uses the smartphone's rear and front cameras to capture real-time video footage of the interior and exterior of the vehicle. The rear camera captures the road conditions outside the vehicle, while the front camera captures the interior of the vehicle, as well as the driver's facial expressions and movements. This video data is acquired by the smartphone's video capture application.

[1000] The device transmits the captured video data to the cloud server in real time using the HTTPS protocol. The device efficiently compresses the video data and transmits it securely to the server.

[1001] The server analyzes the received video data using a deep learning framework (e.g., TensorFlow or PyTorch). Using a generative AI model, it detects drowsiness or poor physical condition from the driver's facial expressions and movements. Based on the analysis results, the server generates appropriate alerts.

[1002] The device notifies the user of the alert notification received from the server in real time using audio and visuals. For example, if the driver feels drowsy, the smartphone will sound an alarm and display a message saying, "Signs of drowsiness have been detected. Please take a break." The notification uses the smartphone's notification API.

[1003] The device uses the front camera to count the number of people entering and exiting the vehicle in real time, using a people-counting algorithm built into the smartphone.

[1004] The server generates an alert if there is a discrepancy between the number of passengers getting on and off the vehicle, and sends the alert to the device. The server then links the data sent to the passenger management system of the kindergarten or nursery school. This link generates an alert to prevent children from being locked inside the vehicle.

[1005] Step 3: Add examples to your description

[1006] Example 1: Driver health management

[1007] Scenario: A driver is driving for a long time and the front camera captures the driver with their eyes closed or blinking frequently.

[1008] Server analysis: A generative AI model analyzes the video and detects signs of drowsiness.

[1009] Alert notification: The server generates an alert saying "Signs of drowsiness have been detected. Please take a break." and sends it to the device.

[1010] User notification: The device notifies the user with an audible alarm and a visual message.

[1011] Example prompt:

[1012] "Please explain how to analyze video data of the driver's face captured by an in-car camera, detect signs of drowsiness or poor physical condition, and generate an alert."

[1013] Example 2: Preventing children from being locked inside a car

[1014] Scenario: While driving a kindergarten bus, the in-camera counts three children as they board, but only two get off when they disembark.

[1015] Server analysis: The server compares the number of passengers boarding and alighting and detects any discrepancies.

[1016] Alert notification: The server generates an alert saying "There is a child left in the car. Please check." and sends it to the device.

[1017] User notification: The device notifies the user with an audible alarm and a visual message.

[1018] Example prompt:

[1019] "Explain how in-car cameras can be used to count the number of children getting in and out of the car and generate an alert if any children remain in the car."

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

[1021] Step 1:

[1022] The device captures images of the exterior and interior of the vehicle in real time using the smartphone's exterior and interior cameras. The captured image data is divided into exterior images from the exterior camera and interior images from the interior camera. Specifically, the smartphone's video capture software captures images at a rate of 30 frames per second and stores them as data.

[1023] Input: Interior and exterior view of the car

[1024] Output: Real-time captured video data

[1025] Step 2:

[1026] The device compresses the captured video data and sends it to the cloud server using the HTTPS protocol, using H.264 encoding technology to minimize data transmission delays.

[1027] Input: Real-time video data

[1028] Output: Compressed video data

[1029] Step 3:

[1030] The server decodes the received compressed video data and analyzes it using a generative AI model. The decoded video data is used to detect the driver's facial region and track facial expressions, eye movements, head movements, etc. Deep learning technology is then used to detect driver drowsiness or poor physical condition from this information.

[1031] Input: Compressed video data

[1032] Output: Driver health condition analysis results

[1033] Step 4:

[1034] The server generates necessary alerts based on the analysis results. For example, if the driver's eyes are closed for more than three consecutive seconds, it generates a text alert saying, "Signs of drowsiness detected. Please take a break." It also generates audio alerts based on certain signals.

[1035] Input: Driver health analysis results

[1036] Output: Generated alert (text and audio)

[1037] Step 5:

[1038] The device notifies the user of the alert notification received from the server in real time via audio and visual means. Specifically, an alarm sounds from the smartphone speaker and a message appears on the display saying, "Signs of drowsiness have been detected. Please take a break." This is done using the smartphone's notification API.

[1039] Input: Generated alert (text and audio)

[1040] Output: An alert to be sent to the user

[1041] Step 6:

[1042] The device uses the front camera to count the number of people entering and exiting the vehicle in real time, using a people-counting algorithm built into the smartphone, and sends the results to a cloud server.

[1043] Input: In-car video data

[1044] Output: Real-time passenger count data for boarding and alighting

[1045] Step 7:

[1046] The server analyzes the received data on the number of passengers boarding and alighting, and generates an alert if there is a discrepancy. For example, if three children were counted when the passenger boarded the vehicle and only two got off when the passenger disembarked, the server generates an alert saying, "One child remains in the vehicle. Please check," and sends it to the device.

[1047] Input: Real-time passenger count data for boarding and alighting

[1048] Output: Alert notifying passengers of mismatch between boarding and alighting counts

[1049] Step 8:

[1050] The device will then notify the driver of the received alert notification in real time via audio and visual means, and will use the smartphone's speaker or screen to display a message saying, "A child has been left in the vehicle. Please check."

[1051] Input: Alert for mismatch between passenger numbers

[1052] Output: Alert to the driver

[1053] Step 9:

[1054] The server synchronizes the counted number of passengers boarding and alighting with the kindergarten or nursery school's passenger management system. Data is sent via an API, and information between the systems is updated instantly. If there is a discrepancy in the number of passengers, an alert is generated in the kindergarten's system.

[1055] Input: Real-time passenger count data for boarding and alighting

[1056] Output: Synchronized data to linked systems and generated alerts

[1057] In this way, the system analyzes input data at each step and generates and notifies appropriate alerts, thereby ensuring safety while driving and managing the situation inside the vehicle.

[1058] (Application example 1)

[1059] 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."

[1060] Conventional self-driving and manually driven vehicles lack systems that properly manage the health of drivers and passengers, as well as the safety of those inside the vehicle. In particular, there are issues with drivers becoming fatigued due to long driving hours or bad weather, children being locked inside the vehicle, and passengers becoming unwell. To address these issues, it is necessary to provide a system that monitors the situation inside and outside the vehicle in real time, analyzes the health status of passengers, and generates appropriate alerts.

[1061] 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.

[1062] In this invention, the server includes: means for capturing video of the interior and exterior of the vehicle in real time using the smart device's external and internal cameras; means for transmitting the captured video data to a remote server and analyzing the driver's health status using a generative model; means for detecting the driver's poor physical condition or drowsiness based on the analysis results and generating a warning; means for notifying the driver of the generated warning audio or visually; means for counting the number of passengers inside and outside the vehicle using the internal camera and transmitting the data to the remote server; means for generating a warning if there is a discrepancy between the number of passengers inside and outside the vehicle; means for notifying the driver of the generated warning audio or visually; means for comprehensively monitoring the conditions inside and outside the vehicle and managing the health and safety of passengers; means for further analyzing the health of passengers taking into account driving speed, weather, and time; means for generating a warning urging passengers to take an appropriate break if an abnormality is detected in their health status; and means for notifying passengers of the generated warning audio or visually. This makes it possible to comprehensively manage the health and safety of drivers and passengers and provide appropriate alerts even in autonomous vehicles.

[1063] A "smart device" is a mobile information terminal that has communication functions and a camera, such as a smartphone or a head-mounted display.

[1064] An "outside camera" is a camera installed on a smart device that captures external images.

[1065] An "in-camera" is a camera installed in a smart device that captures internal images.

[1066] A "remote server" is a group of computers that are placed on the cloud and receive and analyze data via the Internet.

[1067] A "generative model" is an algorithm that uses machine learning or deep learning models to predict or generate a specific outcome from input data.

[1068] "Health condition" refers to the physical condition of the driver or passenger, such as physical condition, illness, or drowsiness.

[1069] "Warning" is a notification message that informs the driver or passengers of any abnormalities or matters requiring attention that the system has detected.

[1070] "Voice notification" is a function that notifies the driver and passengers of warnings by voice.

[1071] "Visual notification" is a function that notifies drivers and passengers of warnings through visual means such as a screen or light.

[1072] "Occupancy" refers to the total number of people on board the vehicle.

[1073] "Number of people getting off" is the total number of people who got off the vehicle.

[1074] "Situation monitoring" means observing and understanding the environment inside and outside the vehicle, as well as people's movements, in real time.

[1075] "Illness" refers to a state in which one's health condition is different from normal and it is deemed dangerous to continue driving or traveling.

[1076] A "passenger management system" is a system for managing boarding and disembarking situations at educational institutions and other facilities.

[1077] "Running speed" refers to the speed at which a vehicle moves.

[1078] "Weather" refers to the atmospheric conditions at a given time, including sunny, rainy, snowy, foggy, etc.

[1079] A "break" is a time or action taken to temporarily stop driving or traveling and rest your body and mind.

[1080] This invention is a system that monitors the situation inside and outside the vehicle in real time and provides comprehensive support for passenger health management and safety. It mainly uses smart devices and a remote server to analyze the health status of the driver and passengers in an autonomous vehicle and generate and notify alerts as necessary. Specific embodiments are described below.

[1081] Hardware Configuration

[1082] The system includes the following major hardware components:

[1083] 1. Smart Devices

[1084] Outer camera: Captures footage outside the vehicle.

[1085] In-camera: Captures footage from inside the car.

[1086] Audio output device: Used to notify audio warnings.

[1087] Display: Used to display visual warnings.

[1088] 2. Remote Server

[1089] Cloud Computing: The provision of computational resources.

[1090] Database: Storage and management of collected data.

[1091] Software Configuration

[1092] The system is implemented using the following major software components:

[1093] 1. Generative Model (AI Model)

[1094] Used to analyze the health status of drivers and passengers.

[1095] Machine learning framework used: TensorFlow / Keras.

[1096] 2. Data Processing and Analysis

[1097] Image processing library: Preprocesses image data using OpenCV.

[1098] Communication library: Communicate with remote servers using the requests module.

[1099] Data flow and processing steps

[1100] The basic data flow and processing procedures of the system are as follows:

[1101] 1. Acquiring footage

[1102] The smart device's external and internal cameras capture images of the vehicle's exterior and interior in real time, and the image data is converted into an appropriate format (e.g., JPEG or PNG).

[1103] 2. Transmission of video data

[1104] The video data is sent to a remote server via a communication library, where it is temporarily stored in a database for analysis.

[1105] 3. Health status analysis

[1106] The received video data is analyzed by a generative model to determine the health status of the driver and passengers. An example of a prompt sentence is given to the generative model: "Please detect whether drowsiness is felt in this video frame."

[1107] 4. Alert generation and notification

[1108] If the analysis detects any abnormalities in the driver or passengers, such as poor physical condition or drowsiness, the server generates a warning, which is then provided to the driver or passenger in real time via an audio output device or display.

[1109] Usage example

[1110] To illustrate, consider the following scenario:

[1111] If drowsiness is detected from the facial expression of a driver who has been driving for a long time, an audio and visual warning will be displayed saying, "Signs of drowsiness have been detected. Please take a break."

[1112] On educational institution shuttle buses, the in-camera counts the number of passengers getting on and off the bus, and if there are children who have not yet disembarked when the bus disembarks, a warning is generated saying, "There are passengers in the bus who have not yet disembarked. Please check."

[1113] If the system determines that the driver is becoming fatigued during long drives in bad weather, the system will send a notification saying, "We recommend that you take a break."

[1114] This configuration provides a system that can comprehensively monitor conditions inside and outside the vehicle, improving the health and safety of drivers and passengers.

[1115] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1116] Step 1:

[1117] The terminal (smart device) operates the outer and inner cameras to capture images of the outside and inside of the vehicle in real time.

[1118] Input: Video footage from inside and outside the car.

[1119] Data processing: Convert the video into the appropriate format (e.g. JPEG, PNG).

[1120] Output: Captured video data.

[1121] Step 2:

[1122] The video data acquired by the terminal is sent to a remote server using a communication library.

[1123] Input: Acquired video data.

[1124] Data calculation: Transfer of video data.

[1125] Output: Video data sent to the server.

[1126] Step 3:

[1127] The server stores the received video data in a database.

[1128] Input: Transmitted video data.

[1129] Data processing: Store in a database.

[1130] Output: Video data stored in a database.

[1131] Step 4:

[1132] The server uses a generative model to analyze the health status of the driver and passengers from the captured video data.

[1133] Input: Stored video data.

[1134] Data calculation: health status analysis, for example, based on the prompt "Detect whether you feel drowsy in this video frame."

[1135] Output: Analysis results (health status assessment).

[1136] Step 5:

[1137] If the server detects an abnormality based on the analysis results, it generates an alert.

[1138] Input: Analysis results.

[1139] Data operation: Generate warning.

[1140] Output: The warning message generated.

[1141] Step 6:

[1142] The server sends the generated alert to the device.

[1143] Input: Warning message.

[1144] Data calculation: Transfer of warning messages.

[1145] Output: The warning message sent to the terminal.

[1146] Step 7:

[1147] The device will notify the driver or passengers of the warning message received via audio or visual means.

[1148] Input: Warning message.

[1149] Data calculation: Notification through audio output device or display.

[1150] Output: A warning message is sent to the driver and passengers.

[1151] 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.

[1152] The present invention relates to a healthcare and safety management system that uses a smartphone and an emotion engine. This system monitors the situation outside and inside the vehicle, including the user's emotional state, in real time to prevent the driver from becoming ill or children from being trapped inside the vehicle. A specific embodiment of this system will be described below.

[1153] Video acquisition and analysis

[1154] The device (smartphone) uses an external and internal camera to capture images of the vehicle's exterior and interior in real time. The external camera captures road conditions outside the vehicle, while the internal camera captures the driver's facial expressions and the situation inside the vehicle. This allows for an accurate understanding of the driver's physical condition and the situation inside the vehicle.

[1155] Video data transmission and analysis

[1156] The server receives video data from the device and analyzes it in real time using a generative model and emotion engine. The emotion engine analyzes the driver's emotional state from their facial expressions and evaluates it by integrating it with their health condition. For example, it can detect changes such as increased stress during long driving sessions or the appearance of fatigue.

[1157] Alert Notification

[1158] Based on the analysis results, the server generates an alert if it detects any abnormalities in the driver's health or emotional state. The generated alert is notified to the driver via audio or visual means via the device. For example, a message such as "Your stress level is increasing. Please take a break" is displayed.

[1159] Managing the number of passengers getting on and off

[1160] The device uses the in-car camera to count the number of passengers getting on and off the vehicle in real time and sends the data to a cloud server, allowing for accurate management of the number of passengers on board.

[1161] The server compares the number of passengers boarding and alighting, and generates an alert if there is a discrepancy. For example, if a child is left behind on a kindergarten bus, an alert will be generated saying, "One child remains in the bus. Please check."

[1162] Linking with kindergartens and nurseries

[1163] The device connects the data on the number of passengers boarding and exiting the vehicle detected by the in-vehicle camera to the kindergarten or nursery school's passenger management system. This generates an alert to prevent children from being locked inside the vehicle and notifies parents remotely. Parents can remotely check their children's boarding and exiting status from their smartphones, giving them peace of mind when leaving their children in the care of their parents.

[1164] Detailed analysis of health and emotional state

[1165] The server then takes into account information such as driving speed, weather, and time of day to perform a more detailed analysis of the driver's health and emotional state. This allows the server to generate alerts to encourage the driver to take breaks at appropriate times. For example, if stress or fatigue increases during long drives in bad weather or at night, the server will generate an alert saying, "We recommend taking a break."

[1166] Responding to emergencies

[1167] The server automatically notifies external authorities if the driver is in an emergency based on the acquired video data and the analysis results of the emotion engine. The content of the notification can be customized, allowing the situation to be quickly communicated to specific contacts.

[1168] As described above, the system of the present invention utilizes a smartphone camera, generative model, and emotion engine to comprehensively support driver health and emotion management. This system can prevent accidents and provide a safe driving environment.

[1169] The processing flow will be explained below.

[1170] Step 1:

[1171] Device: Activate the smartphone's rear camera and front camera. The rear camera captures images of the outside of the vehicle, while the front camera captures the driver's facial expression and the situation inside the vehicle.

[1172] Step 2:

[1173] Terminal: Sends acquired video data to the cloud server at regular intervals.

[1174] Step 3:

[1175] Server: The cloud server inputs the received video data into the generative model and emotion engine in real time for analysis.

[1176] Step 4:

[1177] Server: Evaluates the driver's health and emotional state (e.g., stress level and fatigue level) from their facial expressions and movements.

[1178] Step 5:

[1179] Server: Based on the analysis results, if an abnormality is detected in the driver's health or emotional state, an alert is generated. For example, if the driver's face shows signs of fatigue or stress, an alert is generated saying, "Your stress level is rising. Please take a break."

[1180] Step 6:

[1181] Device: Receives alerts from the server and notifies the user audio and visually. A message is displayed on the smartphone screen and an audio alert is played.

[1182] Step 7:

[1183] Terminal: Using the in-camera, it continuously counts the number of passengers getting on and off the vehicle and sends this data to a cloud server.

[1184] Step 8:

[1185] Server: If there is a discrepancy between the number of passengers getting on and off, for example if a child is left behind on a shuttle bus, an alert is generated. This alert will say, "There is one child left in the bus. Please check."

[1186] Step 9:

[1187] Terminal: The boarding and alighting data is linked to the kindergarten or nursery school's passenger management system, which then remotely notifies parents of their children's boarding and alighting information.

[1188] Step 10:

[1189] Server: Integrates data such as driving speed, weather, and time to perform a more detailed analysis of the driver's health and emotional state. Based on the analysis results, it generates additional alerts as needed. For example, an alert saying, "You've been driving for a long time. We recommend you take a break."

[1190] Step 11:

[1191] User: The driver reviews the generated alert and takes appropriate action, such as taking a break or checking for children left in the car.

[1192] Step 12:

[1193] Server: Based on the acquired video data and the analysis results of the emotion engine, if the driver is in an emergency, the server automatically notifies external authorities. The content of the notification can be customized to quickly inform specific contacts of the situation.

[1194] Example 2

[1195] 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."

[1196] In recent years, managing the health and emotional state of drivers has become an important issue. In particular, the risk of accidents due to fatigue and stress caused by long driving hours is increasing. Dangerous situations such as children being left behind in cars are also becoming a problem. Conventional technologies have the difficulty of detecting these problems in real time and generating alerts at the appropriate time.

[1197] 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.

[1198] In this invention, the server includes: means for capturing images of the interior and exterior of the vehicle in real time using the smartphone's exterior and interior cameras; means for transmitting the captured image data to a cloud server and analyzing the driver's health and emotional state using a generative AI model and an emotion engine; means for detecting the driver's poor physical condition or stress based on the analysis results and generating an alert; means for notifying the driver of the generated alert audio or visually; means for counting the number of passengers in the vehicle and the number of passengers exiting the vehicle using the interior camera and transmitting the data to the cloud server; means for generating an alert if there is a discrepancy between the number of passengers in the vehicle and the number of passengers exiting the vehicle; means for notifying the driver of the generated alert audio or visually; means for performing a detailed analysis of the driver's health and emotional state taking into account driving speed, weather, and time; and means for automatically reporting to an external agency in the event of an emergency. This enables real-time management of the driver's health and safety in the vehicle, and enables rapid response to emergencies.

[1199] A "smartphone" is a portable, multi-functional electronic device with internet connectivity and a camera.

[1200] An "outside camera" is a camera installed on the outside of a smartphone to capture external scenery and objects.

[1201] An "in-camera" is a camera installed inside a smartphone that captures the user's face and the interior of the device.

[1202] "Video data" refers to a series of visual information acquired by the outer camera and the inner camera.

[1203] A "cloud server" is a remote server accessible via the Internet, a group of devices that store and process data.

[1204] A "generative AI model" is an algorithmic model of artificial intelligence that analyzes input data and generates specific results or predictions.

[1205] The "emotion engine" is software that analyzes video data and identifies the emotional state of the subject.

[1206] "Analysis results" refers to the information and data obtained after the generative AI model and emotion engine process the video data.

[1207] An "alert" is a warning message that is generated to notify of an abnormal situation and is displayed visually or audibly.

[1208] "Number of passengers" refers to the total number of people on board the vehicle.

[1209] "Number of people getting off" refers to the total number of people who got off the vehicle.

[1210] "Traveling speed" refers to the speed at which a vehicle is moving in the direction of travel.

[1211] An "emergency situation" refers to an unexpected dangerous situation or a serious problem with the driver's health.

[1212] "External agencies" refers to rescue services and parties that may be contacted in an emergency.

[1213] The present invention relates to a healthcare and safety management system that uses a smartphone and an emotion engine. This system monitors the situation outside and inside the vehicle, including the user's emotional state, in real time to prevent the driver from becoming ill or children from being trapped inside the vehicle. A specific embodiment of this system will be described below.

[1214] Video acquisition and analysis

[1215] The device (smartphone) uses an external and internal camera to capture images of the outside and inside of the vehicle in real time. The external camera captures the road conditions outside the vehicle, while the internal camera captures the driver's facial expression and the situation inside the vehicle. This allows for an accurate understanding of the driver's physical condition and the situation inside the vehicle.

[1216] Examples:

[1217] The outer camera captures road conditions during rainy weather.

[1218] The in-camera detects the driver's tired expression.

[1219] Video data transmission and analysis

[1220] The device sends the captured video data to a server, which then analyzes the video data in real time using a generative AI model and an emotion engine. The emotion engine analyzes the driver's emotional state from their facial expressions, and the generative AI model recognizes specific elements contained in the video.

[1221] Examples:

[1222] The generative AI model is given the prompt sentence, "How tired is this driver currently?"

[1223] The emotion engine generates the result "Exhaustion: 80%".

[1224] Alert generation and notification

[1225] If the server detects an abnormality based on the analysis results, it generates an alert, which is then sent to the driver via their device. Notifications are made via audio, vibration, and visual (screen display).

[1226] Examples:

[1227] A voice message will be played saying, "Your stress levels are high, please take a break."

[1228] The same message will be displayed on the device screen.

[1229] Managing the number of passengers getting on and off

[1230] The device uses the in-car camera to count the number of passengers getting on and off the vehicle in real time and sends the data to a server, which analyzes the data and checks for any abnormalities.

[1231] Examples:

[1232] The device detects that 10 children have boarded a kindergarten shuttle bus.

[1233] When passengers exit the vehicle, the server detects that only nine passengers have exited and generates an alert saying, "There is one child left in the vehicle. Please check."

[1234] Detailed analysis of health and emotional state

[1235] The server takes into account driving speed, weather, and time information, performs detailed analysis of the driver's health and emotional state, and generates appropriate alerts based on the results.

[1236] Examples:

[1237] If you are driving for a long time at night in bad weather, an alert will be generated saying, "You are tired. We recommend you take a break."

[1238] Responding to emergencies

[1239] The server has the ability to automatically notify external agencies in the event of an emergency based on the acquired video data and the analysis results of the emotion engine. The content of the notification can be customized, and the situation can be quickly communicated to specific contacts.

[1240] Examples:

[1241] If the driver loses consciousness, an emergency situation will occur and an automatic call will be sent to emergency services, along with footage from inside the vehicle and the driver's current location.

[1242] This system utilizes a smartphone camera, generative AI models, and an emotion engine to comprehensively support driver health and emotion management, preventing accidents and providing a safe driving environment.

[1243] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1244] System program processing flow

[1245] Step 1: Acquire footage

[1246] The device uses the external and internal cameras to capture images of the outside and inside of the vehicle in real time.

[1247] Input: External environment (road conditions), in-car environment (driver's facial expression, etc.)

[1248] Data processing / calculation: The outer camera captures external images, and the inner camera captures internal images.

[1249] Output: Out-camera video data, in-camera video data

[1250] Specific behavior:

[1251] The device captures video at 24 frames per second.

[1252] Step 2: Sending video data

[1253] The terminal transmits the acquired video data to a server via the Internet.

[1254] Input: Out-camera video data, in-camera video data

[1255] Data processing / calculation: Packetize video data and send it over the Internet

[1256] Output: Video data received by the server

[1257] Specific behavior:

[1258] The device uses Wi-Fi or LTE networks to upload video data to a server.

[1259] Step 3: Analyzing the video data

[1260] The server sends the received video data to the generative AI model and emotion engine for real-time analysis.

[1261] Input: Video data received by the server

[1262] Data processing / calculation: Analysis using generative AI models and emotion engines

[1263] Output: Analysis results (driver's health, emotional state, etc.)

[1264] Specific behavior:

[1265] The server sends a prompt to the generative AI model, saying, "Analyze the driver's stress level from their facial expression."

[1266] The emotion engine outputs the analysis result "Driver's stress level: High."

[1267] Step 4: Alert Generation

[1268] If an abnormality is detected based on the analysis results, the server generates an alert.

[1269] Input: Analysis results

[1270] Data processing / calculation: Generate alert messages based on analysis results

[1271] Output: Alert message

[1272] Specific behavior:

[1273] The server generates an alert message saying "Your stress level is high and you need to take a break."

[1274] Step 5: Alert Notification

[1275] The terminal notifies the driver of alert messages sent from the server.

[1276] Input: Alert message from the server

[1277] Data processing / calculation: Converted into audio, vibration, and visual notification formats

[1278] Output: Notification to the driver

[1279] Specific behavior:

[1280] The device plays a voice message saying, "Your stress level is high, please take a break."

[1281] The terminal will display the same message on the screen.

[1282] Step 6: Managing passenger numbers

[1283] The device uses the in-camera to count the number of passengers getting on and off the vehicle in real time and sends the data to a server.

[1284] Input: In-camera video data

[1285] Data processing / calculation: Analyze video data and count people

[1286] Output: Number of passengers boarding and alighting data

[1287] Specific behavior:

[1288] When the terminal detects one person on board, it sends the data "+1 person" to the server.

[1289] The server confirms that one person has left the vehicle when they get off, and receives the data "-1 person."

[1290] Step 7: Anomaly detection and notification

[1291] The server compares the number of passengers boarding and alighting, and if there is a discrepancy, it generates an alert and notifies the user via the terminal.

[1292] Input: Number of passengers boarding and alighting data

[1293] Data processing / calculation: Detect discrepancies in headcount data and generate alert messages

[1294] Output: Alert message

[1295] Specific behavior:

[1296] The server generates an alert message saying "There is a child left in the car. Please check."

[1297] The device will notify you of the message with audio and visual notifications.

[1298] Step 8: Detailed analysis of your health and emotional state

[1299] The server takes into account driving speed, weather and time information to perform a more detailed analysis of the driver's health and emotional state.

[1300] Input: Driving speed, weather, and time information

[1301] Data processing / calculation: Integrates analytical information to provide a detailed assessment of health and emotional status

[1302] Output: Detailed analysis results

[1303] Specific behavior:

[1304] The server evaluates, "The current weather is rainy, and the stress level is high because you are driving at night."

[1305] The server generates an alert message saying "We recommend you take a break."

[1306] Step 9: Emergency response

[1307] The server has a means to automatically notify external agencies in the event of an emergency.

[1308] Input: Emergency trigger (e.g., sudden deterioration in health condition)

[1309] Data processing / calculation: Creation of emergency messages and transmission to external agencies

[1310] Output: Report message to external organization

[1311] Specific behavior:

[1312] The server generates a message saying, "The driver has lost consciousness. The current location is point xx."

[1313] The server will notify the configured contacts via SMS or phone call.

[1314] (Application example 2)

[1315] 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."

[1316] In conventional factories, there is a lack of means to monitor the health and mental state of workers in real time, so workers may not notice if they are overworked or stressed, posing a significant risk to work quality and safety. Furthermore, if a sudden health problem occurs, it is difficult to respond quickly, making it difficult to guarantee the safety of workers.

[1317] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for acquiring video of the work environment and workers in real time using a camera of a smart device; means for transmitting the acquired video data to the server and analyzing the health status of the workers using a generative model; means for detecting poor physical condition and stress level of the workers based on the analysis results and generating an alert; means for notifying the workers of the generated alert audio or visually; means for counting the number of people in the workplace using a camera and transmitting the data to the server; means for generating an alert if there is an abnormality in the number of people; and means for notifying the workers of the generated alert audio or visually. This makes it possible to monitor and manage the health status and safety of workers in real time.

[1318] A "smart device" is a portable information terminal equipped with communication and camera functions.

[1319] A "camera" is an electronic device for acquiring video data.

[1320] "Real time" means processing that is performed in real time without delay.

[1321] "Video data" refers to recorded data in digital format that includes image information.

[1322] A "server" is a computer that stores and analyzes data over a network.

[1323] A "generative model" is an algorithm that generates a particular outcome based on data analysis.

[1324] "Health" means the balance or state of the body and mind.

[1325] "Analysis" is the process of extracting meaningful information and patterns from data.

[1326] "Stress level" is an index that indicates the degree of mental stress on a worker.

[1327] An "alert" is a notification or warning that draws attention.

[1328] "Voice notification" is a means of conveying information using voice.

[1329] "Visual notification" is a method of conveying information using visual information.

[1330] A "worker" is a person who performs work in a factory or work site.

[1331] "Counting people" means measuring the number of individuals present in a particular area.

[1332] "Abnormal" means a state or situation that is different from the normal.

[1333] A "management system" is a system that uses data to monitor and control business operations and tasks.

[1334] "Environmental conditions" are factors that affect the working environment, such as temperature, humidity, and noise.

[1335] "Encouraging breaks" means encouraging people to take a break by temporarily stopping their work.

[1336] "Real-time monitoring and management" means observing and controlling the actual state without any time delay.

[1337] This invention relates to a health management and safety monitoring system for factories that uses smart devices and an emotion analysis engine. The system aims to improve work safety and efficiency by monitoring the health and mental state of workers in real time and responding immediately if an abnormality is detected.

[1338] 1. Video Acquisition and Analysis

[1339] Terminals (smart devices and factory robots) use built-in cameras to capture images of the work environment and workers in real time. This camera can also capture the facial expressions and movements of workers and the surrounding environment. For example, a smartphone camera or a surveillance camera installed in a factory can be used.

[1340] 2. Video data transmission and analysis

[1341] The server receives the video data sent from the device and analyzes it in real time using a generative model and an emotion analysis engine. This analysis evaluates the worker's health and emotional state. For example, it uses image analysis technology using OpenCV and a customized emotion analysis engine.

[1342] 3. Alert Notification

[1343] If the server detects any abnormalities in the worker's health or emotional state based on the analysis results, it generates an alert. This alert is notified to the worker via audio or visual means via their device. For example, a message such as "Your stress level is rising. Please take a break" is displayed.

[1344] 4. Number of people management

[1345] The device uses a camera to count the number of people in the workplace in real time and sends the data to a server, allowing for accurate management of the number of people in the workplace. For example, it uses person detection technology using OpenCV.

[1346] 5. Linking with management systems

[1347] The device then connects the camera's count data to a management system, which can then generate alerts to proactively prevent worker absences and safety risks, and notify managers remotely. For example, this information can be sent to a cloud-based management platform.

[1348] 6. Detailed analysis of health and emotional status

[1349] The server then analyzes the worker's health and emotional state in more detail, taking into account environmental conditions and time, and generates alerts to encourage workers to take breaks at appropriate times. For example, the server can generate alerts taking into account weather and temperature information.

[1350] Specific examples and examples of prompts for generative AI models

[1351] For example, if Employee A working in a factory continues to work under high stress without taking a break, the system immediately issues an alert saying, "Your stress level is rising. Please take a break." If the emotion engine detects fatigue in Employee B's facial expression, it will notify him, "You need to pay attention to your health. Please take a short break."

[1352] Example prompts for generative AI models

[1353] Please create a Python program that analyzes video data of workers in real time and detects their emotional state and stress level from their facial expressions. Please also add a function to issue an alert when the stress level is high.

[1354] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1355] Step 1:

[1356] The terminal uses a built-in camera to capture images of the work environment and the worker in real time. The input is the video data captured by the camera. The output is real-time video frames. Specifically, the camera module periodically captures video and sends the data to the processor.

[1357] Step 2:

[1358] The terminal transmits the captured video data to the server. The input is the real-time video frame captured in step 1. The output is the video data transmitted to the server. Specifically, the terminal's communication module converts the video data into packets and transmits them to the server via the network.

[1359] Step 3:

[1360] The server inputs the received video data into the generative model and emotion analysis engine. The input is the video data sent from the device. The output is the analysis results related to the emotional state and health status. Specifically, the analysis module in the server applies the generative model and analyzes facial expressions using the emotion engine.

[1361] Step 4:

[1362] The server detects the worker's poor physical condition and stress level based on the analysis results of the emotion engine and generates an alert. The input is the analysis result obtained in step 3. The output is the generated alert message. Specifically, the analysis result is evaluated, and logic is activated to generate an alert if stress or fatigue exceeds a reference value.

[1363] Step 5:

[1364] The server sends the generated alert to the terminal. The input is the alert message generated in step 4. The output is the alert sent to the terminal. As a specific operation, the alert message is sent to the terminal via the network.

[1365] Step 6:

[1366] The terminal notifies the worker of the received alert by voice or visual means. The input is the alert message sent in step 5. The output is the notification to the worker. Specifically, the terminal displays a message on its display and plays a warning sound from its speaker.

[1367] Step 7:

[1368] The device uses a built-in camera to count the number of people in the workplace in real time and transmits the data to a server. The input is the video data captured by the camera. The output is people count data. Specifically, a person detection algorithm is applied and the counting results are transmitted to the server.

[1369] Step 8:

[1370] The server links the people count data with the management system. The input is the people count data sent in step 7. The output is the number of people data linked to the management system. Specifically, the number of people information is saved in a database within the management system.

[1371] Step 9:

[1372] The server performs a more detailed analysis of the worker's health and emotional state, taking into account environmental conditions and time. The inputs are the analysis results obtained in step 3 and environmental condition data. The output is the detailed analysis results. Specifically, additional conditions are incorporated into the analysis model to perform a more accurate health state assessment.

[1373] Step 10:

[1374] The server generates an alert to encourage appropriate breaks based on the detailed analysis results. The input is the detailed analysis results obtained in step 9. The output is the generated alert message. Specifically, the server generates a message encouraging breaks when certain conditions are met.

[1375] Step 11:

[1376] If there is an abnormality in the number of workers, the server generates an alert and sends it to the terminal. The input is the people count data and reference value sent in step 7. The output is an alert message for the abnormality. Specifically, the server compares the reference value with the number of workers data, and if a difference is found, an alert is generated.

[1377] Step 12:

[1378] The terminal notifies the worker of the received abnormal number of workers alert by voice or visual means. The input is the alert message sent in step 11. The output is a notification to the worker. Specifically, the terminal displays a message on its display and plays a warning sound from its speaker.

[1379] This series of processes makes it possible to monitor the health and safety of workers in real time and respond quickly if an abnormality is detected.

[1380] 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.

[1381] 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.

[1382] 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.

[1383] [Fourth embodiment]

[1384] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1385] 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.

[1386] 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).

[1387] 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.

[1388] 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.

[1389] 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).

[1390] 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.

[1391] 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.

[1392] 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.

[1393] 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.

[1394] 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.

[1395] 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.

[1396] 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."

[1397] The present invention relates to a healthcare and safety management system using a smartphone. This system monitors the situation outside and inside a vehicle in real time to prevent the driver from becoming ill or children from being locked inside the vehicle. A specific embodiment of this system will be described below.

[1398] Video acquisition and analysis

[1399] The device (smartphone) uses an external and internal camera to capture images of the interior and exterior of the vehicle in real time. The external camera captures the road conditions outside the vehicle, while the internal camera captures the interior of the vehicle, as well as the driver's facial expressions and movements. This allows for an accurate understanding of the driver's physical condition and the situation inside the vehicle.

[1400] The server receives the video data sent from the device and analyzes it in real time using a generative model. The AI ​​model detects drowsiness or poor physical condition from the driver's facial expression and generates an appropriate alert. This alert is then notified to the driver, prompting them to take appropriate action.

[1401] Alert Notification

[1402] The device receives alert notifications from the server and notifies the user in real time via audio and visual means. For example, if the driver feels drowsy, the smartphone will sound an alarm and display a message saying, "Signs of drowsiness have been detected. Please take a break." In this way, the alert can alert the driver to danger and encourage them to take appropriate action.

[1403] Managing the number of passengers getting on and off

[1404] The device uses the front camera to count the number of passengers getting on and off the bus in real time. This data is periodically sent to a server and managed by the server. For example, if the front camera counts three children on a kindergarten bus when they board, and only two get off when they exit, the device will send that data to the server.

[1405] The server generates an alert when there is a discrepancy between the number of passengers getting on and off the vehicle. As a means of notifying the discrepancy, the server detects the discrepancy and generates an alert. This alert is sent to the terminal and notified to the driver. For example, a message saying "One child remains in the vehicle. Please check." is notified.

[1406] Linking kindergartens and nurseries

[1407] The device connects the data on the number of passengers boarding and exiting the vehicle detected by the in-vehicle camera to the kindergarten or nursery school's passenger management system. This generates an alert to prevent children from being locked inside the vehicle and notifies parents remotely. Parents can remotely check their children's boarding and exiting status from their smartphones, giving them peace of mind when leaving their children in the care of their parents.

[1408] Detailed analysis of health status

[1409] The server then analyzes the driver's health in more detail, taking into account information such as driving speed, weather, and time. This information is then used to generate alerts to encourage the driver to take breaks at appropriate times. For example, if the driver is driving for a long time or in bad weather, fatigue may increase, so the server generates an alert saying, "We recommend taking a break."

[1410] As described above, the system of the present invention utilizes a smartphone camera and generative models to comprehensively support driver health management and in-vehicle safety. This system can prevent accidents and provide a safe driving environment.

[1411] The processing flow will be explained below.

[1412] Step 1:

[1413] Device: Activate the smartphone's rear camera and front camera. The rear camera captures images of the outside of the vehicle, while the front camera captures the driver's facial expression and the situation inside the vehicle.

[1414] Step 2:

[1415] Terminal: The video data acquired by the camera is sent to the cloud server in real time, continuously at regular intervals.

[1416] Step 3:

[1417] Server: Analyzes the received video data using a generative model. Specifically, it analyzes the driver's facial expressions, counts the number of people in the car, and understands road conditions.

[1418] Step 4:

[1419] Server: Evaluates the driver's health based on the analysis results. If signs of drowsiness or abnormalities are detected, an alert is generated.

[1420] Step 5:

[1421] Server: Compares the number of passengers boarding and alighting, and generates an alert if there is a discrepancy between the number of passengers boarding and alighting.

[1422] Step 6:

[1423] Terminal: Receives alert notifications from the server. Depending on the alert content, the user is notified by voice and visual means.

[1424] Step 7:

[1425] User: The driver or parent / guardian sees the alert and takes necessary action, such as taking a break or checking for children left in the car.

[1426] Step 8:

[1427] Terminal: The in-vehicle camera continuously monitors the situation inside the vehicle, and in particular in kindergarten and nursery school shuttle buses, it counts the number of people getting on and off the bus and links with the management system.

[1428] Step 9:

[1429] Server: Performs additional analysis based on driving speed, weather, and time to assess driver fatigue and health.

[1430] Step 10:

[1431] Device: Generates an alert to prompt the user to take a break at an appropriate time. For example, it displays a message saying, "You have been driving for a long time. Please take a break."

[1432] In this way, at every step, the system monitors the driver's health and the safety of the vehicle in real time and prompts appropriate action.

[1433] Example 1

[1434] 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."

[1435] There is a need for a means to prevent accidents caused by drivers' poor health or drowsiness while driving, as well as situations where children are left behind in the car. There is also a need for a system to manage the number of passengers boarding and exiting a vehicle, ensuring the safe transportation of children, especially at kindergartens and daycare centers. Conventional technologies have not provided effective solutions to these issues comprehensively.

[1436] 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.

[1437] In this invention, the server includes: means for capturing images of the interior and exterior of the vehicle in real time using the smartphone's exterior and interior cameras; means for transmitting the captured image data to a cloud server and analyzing the driver's health condition using a generative AI model; means for detecting the driver's poor physical condition or drowsiness based on the analysis results and generating an alert; means for notifying the driver of the generated alert audio or visually; means for counting the number of passengers in the vehicle and the number of passengers exiting the vehicle using the interior camera and transmitting the data to the cloud server; means for generating an alert if there is a discrepancy between the number of passengers in the vehicle and the number of passengers exiting the vehicle; means for notifying the driver of the generated alert audio or visually; means for linking the data on the number of passengers entering and exiting the vehicle with a kindergarten or nursery school's passenger management system; and means for performing a more detailed analysis of the driver's physical condition taking into account driving speed, weather, and time. This enables comprehensive management of the driver's physical condition and in-vehicle safety.

[1438] An "outside camera" is a camera installed on a smartphone or other device that is primarily used to capture external scenery and surrounding conditions.

[1439] An "in-camera" is a camera installed in a smartphone or other device that is primarily used to capture the interior of the device or the user's face.

[1440] A "cloud server" is a server that can be accessed remotely via the Internet and is a computer system used to store, process, and analyze data.

[1441] A "generative AI model" is an AI (artificial intelligence) model that uses machine learning and deep learning to learn and infer, and is a system that generates specific results or analyses based on input data.

[1442] An "alert" is a message or signal, which may be in the form of an audio or visual notification, that notifies the user when the system detects a particular condition.

[1443] An "occupant management system" is a system used to manage boarding and disembarking passengers, particularly in kindergartens and daycare centers, by recording the number of passengers boarding and disembarking and handling safety information.

[1444] "Health status" refers to the driver's physical and mental condition, which is analyzed to detect factors related to physical condition, including distraction, fatigue, and drowsiness while driving.

[1445] "Real-time" refers to a state in which data and information are acquired and processed immediately, and the results are reflected without delay.

[1446] Step 1: Generate a program for this system

[1447] The device (smartphone) uses an external and internal camera to monitor the situation outside and inside the vehicle in real time. The specific hardware used is the smartphone's built-in camera. On the software side, a video capture application is required, and this application has the function of sending captured video data to a cloud server.

[1448] The server is located in the cloud and analyzes the received video data. A generative AI model is used for the analysis. This AI model analyzes the driver's health status and is used to detect poor physical condition or drowsiness. Specific software used is a deep learning framework (e.g., TensorFlow or PyTorch).

[1449] Step 2: Explain the generated program's processing in natural language

[1450] The device uses the smartphone's rear and front cameras to capture real-time video footage of the interior and exterior of the vehicle. The rear camera captures the road conditions outside the vehicle, while the front camera captures the interior of the vehicle, as well as the driver's facial expressions and movements. This video data is acquired by the smartphone's video capture application.

[1451] The device transmits the captured video data to the cloud server in real time using the HTTPS protocol. The device efficiently compresses the video data and transmits it securely to the server.

[1452] The server analyzes the received video data using a deep learning framework (e.g., TensorFlow or PyTorch). Using a generative AI model, it detects drowsiness or poor physical condition from the driver's facial expressions and movements. Based on the analysis results, the server generates appropriate alerts.

[1453] The device notifies the user of the alert notification received from the server in real time using audio and visuals. For example, if the driver feels drowsy, the smartphone will sound an alarm and display a message saying, "Signs of drowsiness have been detected. Please take a break." The notification uses the smartphone's notification API.

[1454] The device uses the front camera to count the number of people entering and exiting the vehicle in real time, using a people-counting algorithm built into the smartphone.

[1455] The server generates an alert if there is a discrepancy between the number of passengers getting on and off the vehicle, and sends the alert to the device. The server then links the data sent to the passenger management system of the kindergarten or nursery school. This link generates an alert to prevent children from being locked inside the vehicle.

[1456] Step 3: Add examples to your description

[1457] Example 1: Driver health management

[1458] Scenario: A driver is driving for a long time and the front camera captures the driver with their eyes closed or blinking frequently.

[1459] Server analysis: A generative AI model analyzes the video and detects signs of drowsiness.

[1460] Alert notification: The server generates an alert saying "Signs of drowsiness have been detected. Please take a break." and sends it to the device.

[1461] User notification: The device notifies the user with an audible alarm and a visual message.

[1462] Example prompt:

[1463] "Please explain how to analyze video data of the driver's face captured by an in-car camera, detect signs of drowsiness or poor physical condition, and generate an alert."

[1464] Example 2: Preventing children from being locked inside a car

[1465] Scenario: While driving a kindergarten bus, the in-camera counts three children as they board, but only two get off when they disembark.

[1466] Server analysis: The server compares the number of passengers boarding and alighting and detects any discrepancies.

[1467] Alert notification: The server generates an alert saying "There is a child left in the car. Please check." and sends it to the device.

[1468] User notification: The device notifies the user with an audible alarm and a visual message.

[1469] Example prompt:

[1470] "Explain how in-car cameras can be used to count the number of children getting in and out of the car and generate an alert if any children remain in the car."

[1471] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1472] Step 1:

[1473] The device captures images of the exterior and interior of the vehicle in real time using the smartphone's exterior and interior cameras. The captured image data is divided into exterior images from the exterior camera and interior images from the interior camera. Specifically, the smartphone's video capture software captures images at a rate of 30 frames per second and stores them as data.

[1474] Input: Interior and exterior view of the car

[1475] Output: Real-time captured video data

[1476] Step 2:

[1477] The device compresses the captured video data and sends it to the cloud server using the HTTPS protocol, using H.264 encoding technology to minimize data transmission delays.

[1478] Input: Real-time video data

[1479] Output: Compressed video data

[1480] Step 3:

[1481] The server decodes the received compressed video data and analyzes it using a generative AI model. The decoded video data is used to detect the driver's facial region and track facial expressions, eye movements, head movements, etc. Deep learning technology is then used to detect driver drowsiness or poor physical condition from this information.

[1482] Input: Compressed video data

[1483] Output: Driver health condition analysis results

[1484] Step 4:

[1485] The server generates necessary alerts based on the analysis results. For example, if the driver's eyes are closed for more than three consecutive seconds, it generates a text alert saying, "Signs of drowsiness detected. Please take a break." It also generates audio alerts based on certain signals.

[1486] Input: Driver health analysis results

[1487] Output: Generated alert (text and audio)

[1488] Step 5:

[1489] The device notifies the user of the alert notification received from the server in real time via audio and visual means. Specifically, an alarm sounds from the smartphone speaker and a message appears on the display saying, "Signs of drowsiness have been detected. Please take a break." This is done using the smartphone's notification API.

[1490] Input: Generated alert (text and audio)

[1491] Output: An alert to be sent to the user

[1492] Step 6:

[1493] The device uses the front camera to count the number of people entering and exiting the vehicle in real time, using a people-counting algorithm built into the smartphone, and sends the results to a cloud server.

[1494] Input: In-car video data

[1495] Output: Real-time passenger count data for boarding and alighting

[1496] Step 7:

[1497] The server analyzes the received data on the number of passengers boarding and alighting, and generates an alert if there is a discrepancy. For example, if three children were counted when the passenger boarded the vehicle and only two got off when the passenger disembarked, the server generates an alert saying, "One child remains in the vehicle. Please check," and sends it to the device.

[1498] Input: Real-time passenger count data for boarding and alighting

[1499] Output: Alert notifying passengers of mismatch between boarding and alighting counts

[1500] Step 8:

[1501] The device will then notify the driver of the received alert notification in real time via audio and visual means, and will use the smartphone's speaker or screen to display a message saying, "A child has been left in the vehicle. Please check."

[1502] Input: Alert for mismatch between passenger numbers

[1503] Output: Alert to the driver

[1504] Step 9:

[1505] The server synchronizes the counted number of passengers boarding and alighting with the kindergarten or nursery school's passenger management system. Data is sent via an API, and information between the systems is updated instantly. If there is a discrepancy in the number of passengers, an alert is generated in the kindergarten's system.

[1506] Input: Real-time passenger count data for boarding and alighting

[1507] Output: Synchronized data to linked systems and generated alerts

[1508] In this way, the system analyzes input data at each step and generates and notifies appropriate alerts, thereby ensuring safety while driving and managing the situation inside the vehicle.

[1509] (Application example 1)

[1510] 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."

[1511] Conventional self-driving and manually driven vehicles lack systems that properly manage the health of drivers and passengers, as well as the safety of those inside the vehicle. In particular, there are issues with drivers becoming fatigued due to long driving hours or bad weather, children being locked inside the vehicle, and passengers becoming unwell. To address these issues, it is necessary to provide a system that monitors the situation inside and outside the vehicle in real time, analyzes the health status of passengers, and generates appropriate alerts.

[1512] 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.

[1513] In this invention, the server includes: means for capturing video of the interior and exterior of the vehicle in real time using the smart device's external and internal cameras; means for transmitting the captured video data to a remote server and analyzing the driver's health status using a generative model; means for detecting the driver's poor physical condition or drowsiness based on the analysis results and generating a warning; means for notifying the driver of the generated warning audio or visually; means for counting the number of passengers inside and outside the vehicle using the internal camera and transmitting the data to the remote server; means for generating a warning if there is a discrepancy between the number of passengers inside and outside the vehicle; means for notifying the driver of the generated warning audio or visually; means for comprehensively monitoring the conditions inside and outside the vehicle and managing the health and safety of passengers; means for further analyzing the health of passengers taking into account driving speed, weather, and time; means for generating a warning urging passengers to take an appropriate break if an abnormality is detected in their health status; and means for notifying passengers of the generated warning audio or visually. This makes it possible to comprehensively manage the health and safety of drivers and passengers and provide appropriate alerts even in autonomous vehicles.

[1514] A "smart device" is a mobile information terminal that has communication functions and a camera, such as a smartphone or a head-mounted display.

[1515] An "outside camera" is a camera installed on a smart device that captures external images.

[1516] An "in-camera" is a camera installed in a smart device that captures internal images.

[1517] A "remote server" is a group of computers that are placed on the cloud and receive and analyze data via the Internet.

[1518] A "generative model" is an algorithm that uses machine learning or deep learning models to predict or generate a specific outcome from input data.

[1519] "Health condition" refers to the physical condition of the driver or passenger, such as physical condition, illness, or drowsiness.

[1520] "Warning" is a notification message that informs the driver or passengers of any abnormalities or matters requiring attention that the system has detected.

[1521] "Voice notification" is a function that notifies the driver and passengers of warnings by voice.

[1522] "Visual notification" is a function that notifies drivers and passengers of warnings through visual means such as a screen or light.

[1523] "Occupancy" refers to the total number of people on board the vehicle.

[1524] "Number of people getting off" is the total number of people who got off the vehicle.

[1525] "Situation monitoring" means observing and understanding the environment inside and outside the vehicle, as well as people's movements, in real time.

[1526] "Illness" refers to a state in which one's health condition is different from normal and it is deemed dangerous to continue driving or traveling.

[1527] A "passenger management system" is a system for managing boarding and disembarking situations at educational institutions and other facilities.

[1528] "Running speed" refers to the speed at which a vehicle moves.

[1529] "Weather" refers to the atmospheric conditions at a given time, including sunny, rainy, snowy, foggy, etc.

[1530] A "break" is a time or action taken to temporarily stop driving or traveling and rest your body and mind.

[1531] This invention is a system that monitors the situation inside and outside the vehicle in real time and provides comprehensive support for passenger health management and safety. It mainly uses smart devices and a remote server to analyze the health status of the driver and passengers in an autonomous vehicle and generate and notify alerts as necessary. Specific embodiments are described below.

[1532] Hardware Configuration

[1533] The system includes the following major hardware components:

[1534] 1. Smart Devices

[1535] Outer camera: Captures footage outside the vehicle.

[1536] In-camera: Captures footage from inside the car.

[1537] Audio output device: Used to notify audio warnings.

[1538] Display: Used to display visual warnings.

[1539] 2. Remote Server

[1540] Cloud Computing: The provision of computational resources.

[1541] Database: Storage and management of collected data.

[1542] Software Configuration

[1543] The system is implemented using the following major software components:

[1544] 1. Generative Model (AI Model)

[1545] Used to analyze the health status of drivers and passengers.

[1546] Machine learning framework used: TensorFlow / Keras.

[1547] 2. Data Processing and Analysis

[1548] Image processing library: Preprocesses image data using OpenCV.

[1549] Communication library: Communicate with remote servers using the requests module.

[1550] Data flow and processing steps

[1551] The basic data flow and processing procedures of the system are as follows:

[1552] 1. Acquiring footage

[1553] The smart device's external and internal cameras capture images of the vehicle's exterior and interior in real time, and the image data is converted into an appropriate format (e.g., JPEG or PNG).

[1554] 2. Transmission of video data

[1555] The video data is sent to a remote server via a communication library, where it is temporarily stored in a database for analysis.

[1556] 3. Health status analysis

[1557] The received video data is analyzed by a generative model to determine the health status of the driver and passengers. An example of a prompt sentence is given to the generative model: "Please detect whether drowsiness is felt in this video frame."

[1558] 4. Alert generation and notification

[1559] If the analysis detects any abnormalities in the driver or passengers, such as poor physical condition or drowsiness, the server generates a warning, which is then provided to the driver or passenger in real time via an audio output device or display.

[1560] Usage example

[1561] To illustrate, consider the following scenario:

[1562] If drowsiness is detected from the facial expression of a driver who has been driving for a long time, an audio and visual warning will be displayed saying, "Signs of drowsiness have been detected. Please take a break."

[1563] On educational institution shuttle buses, the in-camera counts the number of passengers getting on and off the bus, and if there are children who have not yet disembarked when the bus disembarks, a warning is generated saying, "There are passengers in the bus who have not yet disembarked. Please check."

[1564] If the system determines that the driver is becoming fatigued during long drives in bad weather, the system will send a notification saying, "We recommend that you take a break."

[1565] This configuration provides a system that can comprehensively monitor conditions inside and outside the vehicle, improving the health and safety of drivers and passengers.

[1566] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1567] Step 1:

[1568] The terminal (smart device) operates the outer and inner cameras to capture images of the outside and inside of the vehicle in real time.

[1569] Input: Video footage from inside and outside the car.

[1570] Data processing: Convert the video into the appropriate format (e.g. JPEG, PNG).

[1571] Output: Captured video data.

[1572] Step 2:

[1573] The video data acquired by the terminal is sent to a remote server using a communication library.

[1574] Input: Acquired video data.

[1575] Data calculation: Transfer of video data.

[1576] Output: Video data sent to the server.

[1577] Step 3:

[1578] The server stores the received video data in a database.

[1579] Input: Transmitted video data.

[1580] Data processing: Store in a database.

[1581] Output: Video data stored in a database.

[1582] Step 4:

[1583] The server uses a generative model to analyze the health status of the driver and passengers from the captured video data.

[1584] Input: Stored video data.

[1585] Data calculation: health status analysis, for example, based on the prompt "Detect whether you feel drowsy in this video frame."

[1586] Output: Analysis results (health status assessment).

[1587] Step 5:

[1588] If the server detects an abnormality based on the analysis results, it generates an alert.

[1589] Input: Analysis results.

[1590] Data operation: Generate warning.

[1591] Output: The warning message generated.

[1592] Step 6:

[1593] The server sends the generated alert to the device.

[1594] Input: Warning message.

[1595] Data calculation: Transfer of warning messages.

[1596] Output: The warning message sent to the terminal.

[1597] Step 7:

[1598] The device will notify the driver or passengers of the warning message received via audio or visual means.

[1599] Input: Warning message.

[1600] Data calculation: Notification through audio output device or display.

[1601] Output: A warning message is sent to the driver and passengers.

[1602] 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.

[1603] The present invention relates to a healthcare and safety management system that uses a smartphone and an emotion engine. This system monitors the situation outside and inside the vehicle, including the user's emotional state, in real time to prevent the driver from becoming ill or children from being trapped inside the vehicle. A specific embodiment of this system will be described below.

[1604] Video acquisition and analysis

[1605] The device (smartphone) uses an external and internal camera to capture images of the vehicle's exterior and interior in real time. The external camera captures road conditions outside the vehicle, while the internal camera captures the driver's facial expressions and the situation inside the vehicle. This allows for an accurate understanding of the driver's physical condition and the situation inside the vehicle.

[1606] Video data transmission and analysis

[1607] The server receives video data from the device and analyzes it in real time using a generative model and emotion engine. The emotion engine analyzes the driver's emotional state from their facial expressions and evaluates it by integrating it with their health condition. For example, it can detect changes such as increased stress during long driving sessions or the appearance of fatigue.

[1608] Alert Notification

[1609] Based on the analysis results, the server generates an alert if it detects any abnormalities in the driver's health or emotional state. The generated alert is notified to the driver via audio or visual means via the device. For example, a message such as "Your stress level is increasing. Please take a break" is displayed.

[1610] Managing the number of passengers getting on and off

[1611] The device uses the in-car camera to count the number of passengers getting on and off the vehicle in real time and sends the data to a cloud server, allowing for accurate management of the number of passengers on board.

[1612] The server compares the number of passengers boarding and alighting, and generates an alert if there is a discrepancy. For example, if a child is left behind on a kindergarten bus, an alert will be generated saying, "One child remains in the bus. Please check."

[1613] Linking with kindergartens and nurseries

[1614] The device connects the data on the number of passengers boarding and exiting the vehicle detected by the in-vehicle camera to the kindergarten or nursery school's passenger management system. This generates an alert to prevent children from being locked inside the vehicle and notifies parents remotely. Parents can remotely check their children's boarding and exiting status from their smartphones, giving them peace of mind when leaving their children in the care of their parents.

[1615] Detailed analysis of health and emotional state

[1616] The server then takes into account information such as driving speed, weather, and time of day to perform a more detailed analysis of the driver's health and emotional state. This allows the server to generate alerts to encourage the driver to take breaks at appropriate times. For example, if stress or fatigue increases during long drives in bad weather or at night, the server will generate an alert saying, "We recommend taking a break."

[1617] Responding to emergencies

[1618] The server automatically notifies external authorities if the driver is in an emergency based on the acquired video data and the analysis results of the emotion engine. The content of the notification can be customized, allowing the situation to be quickly communicated to specific contacts.

[1619] As described above, the system of the present invention utilizes a smartphone camera, generative model, and emotion engine to comprehensively support driver health and emotion management. This system can prevent accidents and provide a safe driving environment.

[1620] The processing flow will be explained below.

[1621] Step 1:

[1622] Device: Activate the smartphone's rear camera and front camera. The rear camera captures images of the outside of the vehicle, while the front camera captures the driver's facial expression and the situation inside the vehicle.

[1623] Step 2:

[1624] Terminal: Sends acquired video data to the cloud server at regular intervals.

[1625] Step 3:

[1626] Server: The cloud server inputs the received video data into the generative model and emotion engine in real time for analysis.

[1627] Step 4:

[1628] Server: Evaluates the driver's health and emotional state (e.g., stress level and fatigue level) from their facial expressions and movements.

[1629] Step 5:

[1630] Server: Based on the analysis results, if an abnormality is detected in the driver's health or emotional state, an alert is generated. For example, if the driver's face shows signs of fatigue or stress, an alert is generated saying, "Your stress level is rising. Please take a break."

[1631] Step 6:

[1632] Device: Receives alerts from the server and notifies the user audio and visually. A message is displayed on the smartphone screen and an audio alert is played.

[1633] Step 7:

[1634] Terminal: Using the in-camera, it continuously counts the number of passengers getting on and off the vehicle and sends this data to a cloud server.

[1635] Step 8:

[1636] Server: If there is a discrepancy between the number of passengers getting on and off, for example if a child is left behind on a shuttle bus, an alert is generated. This alert will say, "There is one child left in the bus. Please check."

[1637] Step 9:

[1638] Terminal: The boarding and alighting data is linked to the kindergarten or nursery school's passenger management system, which then remotely notifies parents of their children's boarding and alighting information.

[1639] Step 10:

[1640] Server: Integrates data such as driving speed, weather, and time to perform a more detailed analysis of the driver's health and emotional state. Based on the analysis results, it generates additional alerts as needed. For example, an alert saying, "You've been driving for a long time. We recommend you take a break."

[1641] Step 11:

[1642] User: The driver reviews the generated alert and takes appropriate action, such as taking a break or checking for children left in the car.

[1643] Step 12:

[1644] Server: Based on the acquired video data and the analysis results of the emotion engine, if the driver is in an emergency, the server automatically notifies external authorities. The content of the notification can be customized to quickly inform specific contacts of the situation.

[1645] Example 2

[1646] 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."

[1647] In recent years, managing the health and emotional state of drivers has become an important issue. In particular, the risk of accidents due to fatigue and stress caused by long driving hours is increasing. Dangerous situations such as children being left behind in cars are also becoming a problem. Conventional technologies have the difficulty of detecting these problems in real time and generating alerts at the appropriate time.

[1648] 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.

[1649] In this invention, the server includes: means for capturing images of the interior and exterior of the vehicle in real time using the smartphone's exterior and interior cameras; means for transmitting the captured image data to a cloud server and analyzing the driver's health and emotional state using a generative AI model and an emotion engine; means for detecting the driver's poor physical condition or stress based on the analysis results and generating an alert; means for notifying the driver of the generated alert audio or visually; means for counting the number of passengers in the vehicle and the number of passengers exiting the vehicle using the interior camera and transmitting the data to the cloud server; means for generating an alert if there is a discrepancy between the number of passengers in the vehicle and the number of passengers exiting the vehicle; means for notifying the driver of the generated alert audio or visually; means for performing a detailed analysis of the driver's health and emotional state taking into account driving speed, weather, and time; and means for automatically reporting to an external agency in the event of an emergency. This enables real-time management of the driver's health and safety in the vehicle, and enables rapid response to emergencies.

[1650] A "smartphone" is a portable, multi-functional electronic device with internet connectivity and a camera.

[1651] An "outside camera" is a camera installed on the outside of a smartphone to capture external scenery and objects.

[1652] An "in-camera" is a camera installed inside a smartphone that captures the user's face and the interior of the device.

[1653] "Video data" refers to a series of visual information acquired by the outer camera and the inner camera.

[1654] A "cloud server" is a remote server accessible via the Internet, a group of devices that store and process data.

[1655] A "generative AI model" is an algorithmic model of artificial intelligence that analyzes input data and generates specific results or predictions.

[1656] The "emotion engine" is software that analyzes video data and identifies the emotional state of the subject.

[1657] "Analysis results" refers to the information and data obtained after the generative AI model and emotion engine process the video data.

[1658] An "alert" is a warning message that is generated to notify of an abnormal situation and is displayed visually or audibly.

[1659] "Number of passengers" refers to the total number of people on board the vehicle.

[1660] "Number of people getting off" refers to the total number of people who got off the vehicle.

[1661] "Traveling speed" refers to the speed at which a vehicle is moving in the direction of travel.

[1662] An "emergency situation" refers to an unexpected dangerous situation or a serious problem with the driver's health.

[1663] "External agencies" refers to rescue services and parties that may be contacted in an emergency.

[1664] The present invention relates to a healthcare and safety management system that uses a smartphone and an emotion engine. This system monitors the situation outside and inside the vehicle, including the user's emotional state, in real time to prevent the driver from becoming ill or children from being trapped inside the vehicle. A specific embodiment of this system will be described below.

[1665] Video acquisition and analysis

[1666] The device (smartphone) uses an external and internal camera to capture images of the outside and inside of the vehicle in real time. The external camera captures the road conditions outside the vehicle, while the internal camera captures the driver's facial expression and the situation inside the vehicle. This allows for an accurate understanding of the driver's physical condition and the situation inside the vehicle.

[1667] Examples:

[1668] The outer camera captures road conditions during rainy weather.

[1669] The in-camera detects the driver's tired expression.

[1670] Video data transmission and analysis

[1671] The device sends the captured video data to a server, which then analyzes the video data in real time using a generative AI model and an emotion engine. The emotion engine analyzes the driver's emotional state from their facial expressions, and the generative AI model recognizes specific elements contained in the video.

[1672] Examples:

[1673] The generative AI model is given the prompt sentence, "How tired is this driver currently?"

[1674] The emotion engine generates the result "Exhaustion: 80%".

[1675] Alert generation and notification

[1676] If the server detects an abnormality based on the analysis results, it generates an alert, which is then sent to the driver via their device. Notifications are made via audio, vibration, and visual (screen display).

[1677] Examples:

[1678] A voice message will be played saying, "Your stress levels are high, please take a break."

[1679] The same message will be displayed on the device screen.

[1680] Managing the number of passengers getting on and off

[1681] The device uses the in-car camera to count the number of passengers getting on and off the vehicle in real time and sends the data to a server, which analyzes the data and checks for any abnormalities.

[1682] Examples:

[1683] The device detects that 10 children have boarded a kindergarten shuttle bus.

[1684] When passengers exit the vehicle, the server detects that only nine passengers have exited and generates an alert saying, "There is one child left in the vehicle. Please check."

[1685] Detailed analysis of health and emotional state

[1686] The server takes into account driving speed, weather, and time information, performs detailed analysis of the driver's health and emotional state, and generates appropriate alerts based on the results.

[1687] Examples:

[1688] If you are driving for a long time at night in bad weather, an alert will be generated saying, "You are tired. We recommend you take a break."

[1689] Responding to emergencies

[1690] The server has the ability to automatically notify external agencies in the event of an emergency based on the acquired video data and the analysis results of the emotion engine. The content of the notification can be customized, and the situation can be quickly communicated to specific contacts.

[1691] Examples:

[1692] If the driver loses consciousness, an emergency situation will occur and an automatic call will be sent to emergency services, along with footage from inside the vehicle and the driver's current location.

[1693] This system utilizes a smartphone camera, generative AI models, and an emotion engine to comprehensively support driver health and emotion management, preventing accidents and providing a safe driving environment.

[1694] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1695] System program processing flow

[1696] Step 1: Acquire footage

[1697] The device uses the external and internal cameras to capture images of the outside and inside of the vehicle in real time.

[1698] Input: External environment (road conditions), in-car environment (driver's facial expression, etc.)

[1699] Data processing / calculation: The outer camera captures external images, and the inner camera captures internal images.

[1700] Output: Out-camera video data, in-camera video data

[1701] Specific behavior:

[1702] The device captures video at 24 frames per second.

[1703] Step 2: Sending video data

[1704] The terminal transmits the acquired video data to a server via the Internet.

[1705] Input: Out-camera video data, in-camera video data

[1706] Data processing / calculation: Packetize video data and send it over the Internet

[1707] Output: Video data received by the server

[1708] Specific behavior:

[1709] The device uses Wi-Fi or LTE networks to upload video data to a server.

[1710] Step 3: Analyzing the video data

[1711] The server sends the received video data to the generative AI model and emotion engine for real-time analysis.

[1712] Input: Video data received by the server

[1713] Data processing / calculation: Analysis using generative AI models and emotion engines

[1714] Output: Analysis results (driver's health, emotional state, etc.)

[1715] Specific behavior:

[1716] The server sends a prompt to the generative AI model, saying, "Analyze the driver's stress level from their facial expression."

[1717] The emotion engine outputs the analysis result "Driver's stress level: High."

[1718] Step 4: Alert Generation

[1719] If an abnormality is detected based on the analysis results, the server generates an alert.

[1720] Input: Analysis results

[1721] Data processing / calculation: Generate alert messages based on analysis results

[1722] Output: Alert message

[1723] Specific behavior:

[1724] The server generates an alert message saying "Your stress level is high and you need to take a break."

[1725] Step 5: Alert Notification

[1726] The terminal notifies the driver of alert messages sent from the server.

[1727] Input: Alert message from the server

[1728] Data processing / calculation: Converted into audio, vibration, and visual notification formats

[1729] Output: Notification to the driver

[1730] Specific behavior:

[1731] The device plays a voice message saying, "Your stress level is high, please take a break."

[1732] The terminal will display the same message on the screen.

[1733] Step 6: Managing passenger numbers

[1734] The device uses the in-camera to count the number of passengers getting on and off the vehicle in real time and sends the data to a server.

[1735] Input: In-camera video data

[1736] Data processing / calculation: Analyze video data and count people

[1737] Output: Number of passengers boarding and alighting data

[1738] Specific behavior:

[1739] When the terminal detects one person on board, it sends the data "+1 person" to the server.

[1740] The server confirms that one person has left the vehicle when they get off, and receives the data "-1 person."

[1741] Step 7: Anomaly detection and notification

[1742] The server compares the number of passengers boarding and alighting, and if there is a discrepancy, it generates an alert and notifies the user via the terminal.

[1743] Input: Number of passengers boarding and alighting data

[1744] Data processing / calculation: Detect discrepancies in headcount data and generate alert messages

[1745] Output: Alert message

[1746] Specific behavior:

[1747] The server generates an alert message saying "There is a child left in the car. Please check."

[1748] The device will notify you of the message with audio and visual notifications.

[1749] Step 8: Detailed analysis of your health and emotional state

[1750] The server takes into account driving speed, weather and time information to perform a more detailed analysis of the driver's health and emotional state.

[1751] Input: Driving speed, weather, and time information

[1752] Data processing / calculation: Integrates analytical information to provide a detailed assessment of health and emotional status

[1753] Output: Detailed analysis results

[1754] Specific behavior:

[1755] The server evaluates, "The current weather is rainy, and the stress level is high because you are driving at night."

[1756] The server generates an alert message saying "We recommend you take a break."

[1757] Step 9: Emergency response

[1758] The server has a means to automatically notify external agencies in the event of an emergency.

[1759] Input: Emergency trigger (e.g., sudden deterioration in health condition)

[1760] Data processing / calculation: Creation of emergency messages and transmission to external agencies

[1761] Output: Report message to external organization

[1762] Specific behavior:

[1763] The server generates a message saying, "The driver has lost consciousness. The current location is point xx."

[1764] The server will notify the configured contacts via SMS or phone call.

[1765] (Application example 2)

[1766] 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."

[1767] In conventional factories, there is a lack of means to monitor the health and mental state of workers in real time, so workers may not notice if they are overworked or stressed, posing a significant risk to work quality and safety. Furthermore, if a sudden health problem occurs, it is difficult to respond quickly, making it difficult to guarantee the safety of workers.

[1768] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for acquiring video of the work environment and workers in real time using a camera of a smart device; means for transmitting the acquired video data to the server and analyzing the health status of the workers using a generative model; means for detecting poor physical condition and stress level of the workers based on the analysis results and generating an alert; means for notifying the workers of the generated alert audio or visually; means for counting the number of people in the workplace using a camera and transmitting the data to the server; means for generating an alert if there is an abnormality in the number of people; and means for notifying the workers of the generated alert audio or visually. This makes it possible to monitor and manage the health status and safety of workers in real time.

[1769] A "smart device" is a portable information terminal equipped with communication and camera functions.

[1770] A "camera" is an electronic device for acquiring video data.

[1771] "Real time" means processing that is performed in real time without delay.

[1772] "Video data" refers to recorded data in digital format that includes image information.

[1773] A "server" is a computer that stores and analyzes data over a network.

[1774] A "generative model" is an algorithm that generates a particular outcome based on data analysis.

[1775] "Health" means the balance or state of the body and mind.

[1776] "Analysis" is the process of extracting meaningful information and patterns from data.

[1777] "Stress level" is an index that indicates the degree of mental stress on a worker.

[1778] An "alert" is a notification or warning that draws attention.

[1779] "Voice notification" is a means of conveying information using voice.

[1780] "Visual notification" is a method of conveying information using visual information.

[1781] A "worker" is a person who performs work in a factory or work site.

[1782] "Counting people" means measuring the number of individuals present in a particular area.

[1783] "Abnormal" means a state or situation that is different from the normal.

[1784] A "management system" is a system that uses data to monitor and control business operations and tasks.

[1785] "Environmental conditions" are factors that affect the working environment, such as temperature, humidity, and noise.

[1786] "Encouraging breaks" means encouraging people to take a break by temporarily stopping their work.

[1787] "Real-time monitoring and management" means observing and controlling the actual state without any time delay.

[1788] This invention relates to a health management and safety monitoring system for factories that uses smart devices and an emotion analysis engine. The system aims to improve work safety and efficiency by monitoring the health and mental state of workers in real time and responding immediately if an abnormality is detected.

[1789] 1. Video Acquisition and Analysis

[1790] Terminals (smart devices and factory robots) use built-in cameras to capture images of the work environment and workers in real time. This camera can also capture the facial expressions and movements of workers and the surrounding environment. For example, a smartphone camera or a surveillance camera installed in a factory can be used.

[1791] 2. Video data transmission and analysis

[1792] The server receives the video data sent from the device and analyzes it in real time using a generative model and an emotion analysis engine. This analysis evaluates the worker's health and emotional state. For example, it uses image analysis technology using OpenCV and a customized emotion analysis engine.

[1793] 3. Alert Notification

[1794] If the server detects any abnormalities in the worker's health or emotional state based on the analysis results, it generates an alert. This alert is notified to the worker via audio or visual means via their device. For example, a message such as "Your stress level is rising. Please take a break" is displayed.

[1795] 4. Number of people management

[1796] The device uses a camera to count the number of people in the workplace in real time and sends the data to a server, allowing for accurate management of the number of people in the workplace. For example, it uses person detection technology using OpenCV.

[1797] 5. Linking with management systems

[1798] The device then connects the camera's count data to a management system, which can then generate alerts to proactively prevent worker absences and safety risks, and notify managers remotely. For example, this information can be sent to a cloud-based management platform.

[1799] 6. Detailed analysis of health and emotional status

[1800] The server then analyzes the worker's health and emotional state in more detail, taking into account environmental conditions and time, and generates alerts to encourage workers to take breaks at appropriate times. For example, the server can generate alerts taking into account weather and temperature information.

[1801] Specific examples and examples of prompts for generative AI models

[1802] For example, if Employee A working in a factory continues to work under high stress without taking a break, the system immediately issues an alert saying, "Your stress level is rising. Please take a break." If the emotion engine detects fatigue in Employee B's facial expression, it will notify him, "You need to pay attention to your health. Please take a short break."

[1803] Example prompts for generative AI models

[1804] Please create a Python program that analyzes video data of workers in real time and detects their emotional state and stress level from their facial expressions. Please also add a function to issue an alert when the stress level is high.

[1805] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1806] Step 1:

[1807] The terminal uses a built-in camera to capture images of the work environment and the worker in real time. The input is the video data captured by the camera. The output is real-time video frames. Specifically, the camera module periodically captures video and sends the data to the processor.

[1808] Step 2:

[1809] The terminal transmits the captured video data to the server. The input is the real-time video frame captured in step 1. The output is the video data transmitted to the server. Specifically, the terminal's communication module converts the video data into packets and transmits them to the server via the network.

[1810] Step 3:

[1811] The server inputs the received video data into the generative model and emotion analysis engine. The input is the video data sent from the device. The output is the analysis results related to the emotional state and health status. Specifically, the analysis module in the server applies the generative model and analyzes facial expressions using the emotion engine.

[1812] Step 4:

[1813] The server detects the worker's poor physical condition and stress level based on the analysis results of the emotion engine and generates an alert. The input is the analysis result obtained in step 3. The output is the generated alert message. Specifically, the analysis result is evaluated, and logic is activated to generate an alert if stress or fatigue exceeds a reference value.

[1814] Step 5:

[1815] The server sends the generated alert to the terminal. The input is the alert message generated in step 4. The output is the alert sent to the terminal. As a specific operation, the alert message is sent to the terminal via the network.

[1816] Step 6:

[1817] The terminal notifies the worker of the received alert by voice or visual means. The input is the alert message sent in step 5. The output is the notification to the worker. Specifically, the terminal displays a message on its display and plays a warning sound from its speaker.

[1818] Step 7:

[1819] The device uses a built-in camera to count the number of people in the workplace in real time and transmits the data to a server. The input is the video data captured by the camera. The output is people count data. Specifically, a person detection algorithm is applied and the counting results are transmitted to the server.

[1820] Step 8:

[1821] The server links the people count data with the management system. The input is the people count data sent in step 7. The output is the number of people data linked to the management system. Specifically, the number of people information is saved in a database within the management system.

[1822] Step 9:

[1823] The server performs a more detailed analysis of the worker's health and emotional state, taking into account environmental conditions and time. The inputs are the analysis results obtained in step 3 and environmental condition data. The output is the detailed analysis results. Specifically, additional conditions are incorporated into the analysis model to perform a more accurate health state assessment.

[1824] Step 10:

[1825] The server generates an alert to encourage appropriate breaks based on the detailed analysis results. The input is the detailed analysis results obtained in step 9. The output is the generated alert message. Specifically, the server generates a message encouraging breaks when certain conditions are met.

[1826] Step 11:

[1827] If there is an abnormality in the number of workers, the server generates an alert and sends it to the terminal. The input is the people count data and reference value sent in step 7. The output is an alert message for the abnormality. Specifically, the server compares the reference value with the number of workers data, and if a difference is found, an alert is generated.

[1828] Step 12:

[1829] The terminal notifies the worker of the received abnormal number of workers alert by voice or visual means. The input is the alert message sent in step 11. The output is a notification to the worker. Specifically, the terminal displays a message on its display and plays a warning sound from its speaker.

[1830] This series of processes makes it possible to monitor the health and safety of workers in real time and respond quickly if an abnormality is detected.

[1831] 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.

[1832] 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.

[1833] 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.

[1834] 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.

[1835] FIG. 9 illustrates 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 behaviors 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.

[1836] 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.

[1837] 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).

[1838] 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.

[1839] 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."

[1840] 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.

[1841] 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).

[1842] 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.

[1843] 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.

[1844] 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.

[1845] 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.

[1846] 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.

[1847] 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.

[1848] 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.

[1849] 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.

[1850] 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.

[1851] 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.

[1852] The following is further disclosed regarding the above embodiment.

[1853] (Claim 1)

[1854] A means for acquiring images of the outside and inside of the vehicle in real time using an outer camera and an inner camera of a smartphone;

[1855] A means for transmitting the acquired video data to a cloud server and analyzing the driver's health condition using a generative model;

[1856] Based on the analysis results, a means of detecting driver drowsiness or poor physical condition and generating an alert;

[1857] A means of notifying the driver audibly or visually of the generated alert; and

[1858] A means for counting the number of passengers in and out of the vehicle using an in-camera and transmitting the data to a cloud server;

[1859] A means to generate an alert if there is a discrepancy between the number of passengers boarding and alighting;

[1860] A means of notifying the driver audibly or visually of the generated alert; and

[1861] A system including:

[1862] (Claim 2)

[1863] A means for linking the data on the number of passengers and the number of passengers alighting detected by the in-camera with the passenger management system of the kindergarten or nursery school;

[1864] The linked management system will provide a means to generate alerts to prevent children from being locked inside the car.

[1865] a means for remotely notifying a parent of the generated alert;

[1866] 10. The system of claim 1, comprising:

[1867] (Claim 3)

[1868] A means of analyzing the driver's physical condition in more detail, taking into account driving speed, weather and time;

[1869] A means of generating an alert to prompt the driver to take appropriate rest if abnormalities in health are detected;

[1870] 10. The system of claim 1, comprising:

[1871] "Example 1"

[1872] (Claim 1)

[1873] A means for acquiring images of the outside and inside of the vehicle in real time using an outer camera and an inner camera of a smartphone;

[1874] A means for transmitting the acquired video data to a cloud server and analyzing the driver's health condition using a generative AI model;

[1875] Based on the analysis results, a means of detecting driver drowsiness or poor physical condition and generating an alert;

[1876] A means of notifying the driver audibly or visually of the generated alert; and

[1877] A means for counting the number of passengers in and out of the vehicle using an in-camera and transmitting the data to a cloud server;

[1878] A means to generate an alert if there is a discrepancy between the number of passengers boarding and alighting;

[1879] A means of notifying the driver audibly or visually of the generated alert; and

[1880] A means for linking the data on the number of passengers boarding and alighting with the passenger management system of kindergartens and nursery schools;

[1881] A means of analyzing the driver's physical condition in more detail, taking into account driving speed, weather and time;

[1882] A system including:

[1883] (Claim 2)

[1884] The linked management system will provide a means to generate alerts to prevent children from being locked inside the car.

[1885] a means for remotely notifying a parent of the generated alert;

[1886] 10. The system of claim 1, comprising:

[1887] (Claim 3)

[1888] A means of generating an alert to prompt the driver to take appropriate rest if abnormalities in health are detected;

[1889] 10. The system of claim 1, comprising:

[1890] "Application Example 1"

[1891] (Claim 1)

[1892] A means for acquiring images of the outside and inside of the vehicle in real time using an outer camera and an inner camera of the smart device;

[1893] A means for transmitting the acquired video data to a remote server and analyzing the driver's health condition using a generative model;

[1894] A means for detecting driver physical condition or drowsiness and generating a warning based on the analysis results;

[1895] a means of notifying the driver audibly or visually of the generated warning;

[1896] A means for counting the number of passengers in and out of the vehicle using an in-camera and transmitting the data to a remote server;

[1897] means for generating an alert if there is a discrepancy between the number of passengers boarding and alighting;

[1898] a means of notifying the driver audibly or visually of the generated warning;

[1899] A means of comprehensively monitoring the situation outside and inside the vehicle and managing the health and safety of passengers;

[1900] A means of further analyzing passenger health status, taking into account travel speed, weather and time of day;

[1901] a means for generating a warning to prompt passengers to take appropriate rest if abnormalities in their health are detected;

[1902] a means for audibly or visually notifying passengers of the generated warning;

[1903] A system including:

[1904] (Claim 2)

[1905] A means for linking the data on the number of passengers boarding and alighting detected by the in-camera with the passenger management system of the educational institution;

[1906] A means for generating warnings to prevent passengers from being trapped inside the vehicle through an interlocking management system;

[1907] a means for remotely notifying a parent of the generated alert;

[1908] 10. The system of claim 1, comprising:

[1909] (Claim 3)

[1910] A means for performing a more detailed analysis of the passenger's physical condition, taking into account the travel speed, weather, and time of day;

[1911] a means for generating a warning to prompt passengers to take appropriate rest if abnormalities in their health are detected;

[1912] 10. The system of claim 1, comprising:

[1913] "Example 2: Combining Emotion Engines"

[1914] (Claim 1)

[1915] A means for acquiring images of the outside and inside of the vehicle in real time using an outer camera and an inner camera of a smartphone;

[1916] A means for transmitting the acquired video data to a cloud server and analyzing the driver's health and emotional state using a generative AI model and an emotion engine;

[1917] Based on the analysis results, a means of detecting driver ill-health or stress and generating an alert;

[1918] A means of notifying the driver audibly or visually of the generated alert; and

[1919] A means for counting the number of passengers in and out of the vehicle using an in-camera and transmitting the data to a cloud server;

[1920] A means to generate an alert if there is a discrepancy between the number of passengers boarding and alighting;

[1921] A means of notifying the driver audibly or visually of the generated alert; and

[1922] A means of detailed analysis of the driver's health and emotional state, taking into account driving speed, weather and time;

[1923] A means of automatically notifying external authorities in the event of an emergency;

[1924] A system including:

[1925] (Claim 2)

[1926] A means for linking the data on the number of passengers and the number of passengers alighting detected by the in-camera with the passenger management system of the kindergarten or nursery school;

[1927] The linked management system will provide a means to generate alerts to prevent children from being locked inside the car.

[1928] a means for remotely notifying a parent of the generated alert;

[1929] 10. The system of claim 1, comprising:

[1930] (Claim 3)

[1931] a means for further analyzing the driver's physical and emotional state, taking into account driving speed, weather and time;

[1932] A means for generating an alert to prompt the driver to take appropriate rest if abnormalities in health and emotional state are detected;

[1933] 10. The system of claim 1, comprising:

[1934] "Application example 2 when combining emotion engines"

[1935] (Claim 1)

[1936] A means for acquiring images of the work environment and workers in real time using a camera on a smart device;

[1937] a means for transmitting the acquired video data to a server and analyzing the worker's health condition using a generative model;

[1938] Based on the analysis results,...

Claims

1. A means for acquiring images of the outside and inside of the vehicle in real time using an outer camera and an inner camera of a smartphone; A means for transmitting the acquired video data to a cloud server and analyzing the driver's health condition using a generative model; Based on the analysis results, a means of detecting driver drowsiness or poor physical condition and generating an alert; A means of notifying the driver audibly or visually of the generated alert; and A means for counting the number of passengers in and out of the vehicle using an in-camera and transmitting the data to a cloud server; A means to generate an alert if there is a discrepancy between the number of passengers boarding and alighting; A means of notifying the driver audibly or visually of the generated alert; and A system including:

2. A means for linking the data on the number of passengers and the number of passengers alighting detected by the in-camera with the passenger management system of the kindergarten or nursery school; The linked management system will provide a means to generate alerts to prevent children from being locked inside the car. a means for remotely notifying a parent of the generated alert; The system of claim 1 , comprising:

3. A means of analyzing the driver's physical condition in more detail, taking into account driving speed, weather and time; A means of generating an alert to prompt the driver to take appropriate rest if abnormalities in health are detected; The system of claim 1 , comprising:

Images