System

Abstract

A system is provided.SOLUTION: A system comprising: sensor means for capturing the face and actions of a driver in real time; processing means for preprocessing data obtained from the sensor means; analyzing means for analyzing the data preprocessed by the processing means and detecting signs of drowsy driving or distraction of the driver; and alert generating means for generating and transmitting an alert to a terminal if an anomaly is detected by the analyzing means.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 effectively prevent drowsy driving and inattentive driving by drivers engaged in the long-distance truck and transportation industries, and to reduce traffic accidents by managing the health status of drivers. Conventional technologies have difficulty in monitoring the driver's attention and health status in real time and taking immediate appropriate measures, which results in the risk of serious accidents. An effective system to solve this problem is needed. [Means for solving the problem]

[0005] In order to solve the above problems, the present invention employs the following configuration. First, sensor means is provided for capturing the driver's face and movements in real time. Next, processing means is provided for preprocessing data acquired from the sensor means. Then, analysis means is provided for analyzing the preprocessed data and detecting signs of the driver drowsing at the wheel or being distracted. The system further includes warning generation means for generating a warning and transmitting it to a terminal when an abnormality is detected by the analysis means. The system also includes communication means for communicating data in real time between the sensor means and the analysis means. Finally, the system provides a system including display means for displaying the warning message generated by the warning generation means and notifying the driver. This configuration makes it possible to prevent the driver from drowsing at the wheel or being distracted, and to appropriately manage the driver's health.

[0006] "Sensor means" refers to a device or system for capturing the driver's face and movements in real time.

[0007] "Processing means" refers to a device or system for pre-processing data obtained from the sensor means.

[0008] "Analysis means" refers to a device or system that analyzes the pre-processed data and detects signs of driver drowsiness or distraction.

[0009] The "warning generation means" refers to a device or system that generates a warning when an abnormality is detected by the analysis means and sends it to the terminal.

[0010] "Communication means" refers to a device or system for communicating data in real time between the sensor means and the analysis means.

[0011] The "display means" refers to a device or system for displaying the warning message generated by the warning generation means and notifying the driver. [Brief explanation of the drawings]

[0012] [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

[0013] 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.

[0014] First, the terms used in the following description will be explained.

[0015] 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).

[0016] 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.

[0017] 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.

[0018] 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.

[0019] 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."

[0020] [First embodiment]

[0021] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0022] 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.

[0023] 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).

[0024] 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.

[0025] 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.

[0026] 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.

[0027] 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.

[0028] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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."

[0033] The present invention provides a system for effectively preventing drowsy driving and inattentive driving by drivers engaged in the long-distance truck and transportation industries, and for managing the health status of the drivers. The system includes the following components:

[0034] 1. Sensor means

[0035] The sensor means installed in the terminal has the function of capturing the driver's face and movements in real time. Specifically, an AI camera installed in the vehicle continuously collects the driver's face, blink frequency, gaze direction, facial expression, head position, etc. This video data is very important as it will be analyzed in detail later.

[0036] 2. Processing means

[0037] The server pre-processes the data sent from the sensor means, including noise removal, image correction, and facial position information extraction, thereby improving the quality of the data input to the analysis means.

[0038] 3. Analysis method

[0039] The server then inputs the pre-processed data into the Generative AI's analysis engine, which uses neural networks to analyze the driver's facial expressions and movement patterns to detect signs of drowsiness or distraction. This analysis is performed in real time, and the results are available immediately.

[0040] 4. Warning generation means

[0041] If an abnormality is detected by the analysis means, the server generates a warning message, such as "Caution: Signs of drowsiness detected. Please take a break immediately." This message is sent to the terminal and notifies the driver.

[0042] 5. Means of communication

[0043] Data is communicated in real time between the sensor means and the analysis means. The communication means minimizes data delays and achieves high-speed data transfer.

[0044] 6. Display means

[0045] The warning message generated by the warning generating means is notified to the driver by the display means of the terminal, and the driver is required to check the displayed message and take appropriate action.

[0046] About program processing

[0047] Processing of Sensor Means

[0048] Processing performed by the device

[0049] An AI camera installed on the device captures the driver's face in real time and collects video data, which is temporarily stored on the device and then sequentially sent to a server.

[0050] Data Preprocessing

[0051] Processing performed by the server

[0052] The server preprocesses the data received from the device, removing noise and correcting images, generating high-quality data suitable for analysis.

[0053] Data analysis

[0054] Processing performed by the server

[0055] The server inputs the pre-processed data into an analytical engine using a generative AI neural network, which analyzes the driver's facial and movement patterns to detect signs of drowsiness or distraction in real time.

[0056] Generate warnings

[0057] Processing performed by the server

[0058] If the analysis engine detects any symptoms, the server will determine the abnormality and immediately generate a warning message, which will be sent to the device and also notified to the operation manager.

[0059] Displaying warnings

[0060] Processing performed by the device

[0061] The terminal receives a warning message from the server and displays it to the driver. It is also possible to alert the driver by using voice notifications, etc.

[0062] Specific examples

[0063] For example, if a driver's blinking frequency decreases and their gaze becomes fixed within a certain period of time, this data is sent from the sensor means to the server. The server preprocesses this data and inputs it into the analysis engine of the generation AI. If the analysis engine detects signs of drowsy driving, the server generates a warning message saying "Signs of drowsy driving have been detected. Please take a break" and sends it to the device. The device displays this warning message to warn the driver. The driver confirms this warning and takes an appropriate break to ensure safe driving.

[0064] In this way, the system of the present invention can prevent the driver from falling asleep or driving carelessly, and can appropriately manage the driver's health condition.

[0065] The processing flow will be explained below.

[0066] Step 1:

[0067] Terminal handling

[0068] An AI camera installed on the device captures the driver's face in real time and collects video data. Specifically, the camera captures video at 20 frames per second and detects blinking frequency, gaze direction, and facial orientation.

[0069] Step 2:

[0070] Terminal handling

[0071] The collected video data is temporarily stored in the internal memory, and when it reaches an appropriate buffer size, it is sent to the server in real time using a communication means.

[0072] Step 3:

[0073] Server Processing

[0074] The server decodes the video data received from the device and performs pre-processing, which includes noise reduction, image sharpening, cropping of necessary parts, etc.

[0075] Step 4:

[0076] Server Processing

[0077] The preprocessed data is input into the generative AI's analysis engine, which uses a neural network to analyze the driver's facial expressions and movement patterns, such as blink frequency, gaze direction, and head position, to detect signs of drowsiness or distraction.

[0078] Step 5:

[0079] Server Processing

[0080] If an abnormality is detected based on the analysis results, the server generates a warning message, such as "Warning: Signs of drowsiness detected. Please take a break immediately."

[0081] Step 6:

[0082] Server Processing

[0083] The generated warning message is sent to the device, and a notification is also sent to the operation manager via email or SMS.

[0084] Step 7:

[0085] Terminal handling

[0086] The device receives the warning message from the server and displays it to the driver. Specifically, the warning message is displayed on the display and, in some cases, an audio notification is also given.

[0087] Step 8:

[0088] User Action

[0089] The user (driver) checks the warning message. Based on the warning message, the driver takes appropriate action, such as stopping at a service area or rest area to take a break.

[0090] Step 9:

[0091] Server Processing

[0092] As a follow-up, the server continues to monitor the driver's condition using generative AI, and based on the analysis results, generates messages to provide additional rest advice or driving advice at the appropriate time.

[0093] Step 10:

[0094] Server Processing

[0095] The generated follow-up message is sent to the terminal.

[0096] Step 11:

[0097] Terminal handling

[0098] The device receives a follow-up message and displays it to the driver, such as "Please take a break at the next service area."

[0099] Through these steps, the system helps prevent drivers from falling asleep or becoming distracted, supporting their health and safe driving.

[0100] Example 1

[0101] 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."

[0102] There is a need to prevent drivers from falling asleep or becoming distracted while driving long distances and ensure safe driving, but conventional systems have had difficulty monitoring the driver's health condition in real time and issuing prompt warnings. In particular, there are challenges in accurately and promptly detecting abnormalities due to inadequate data quality and communication delays.

[0103] 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.

[0104] In this invention, the server includes a sensor means for capturing the face and movements of the driver in real time, a terminal for saving data acquired from the sensor means and transmitting it via a network, a processing means for pre-processing data received from the terminal, an analysis means for analyzing the data pre-processed by the processing means and detecting signs of the driver drowsing at the wheel or being distracted, and a warning generation means for generating a warning when an abnormality is detected by the analysis means and transmitting the warning to the terminal. This makes it possible to monitor the driver's health condition in real time and to quickly issue a warning when drowsing at the wheel or being distracted is detected.

[0105] The "sensor means" is a device for capturing the driver's face and movements in real time.

[0106] A "terminal" is a device that stores data acquired from a sensor means and transmits the data to a server via a network.

[0107] "Processing means" refers to functions and devices for pre-processing data received from a terminal.

[0108] "Analysis means" refers to functions and devices for analyzing the pre-processed data and detecting signs of driver drowsiness or distraction.

[0109] The "warning generation means" is a function and device for generating a warning when an abnormality is detected by the analysis means and transmitting the warning to the terminal.

[0110] "Communication means" refers to functions and devices for communicating data in real time between the sensor means and the analysis means.

[0111] The "display means" refers to a function and device for displaying the warning message generated by the warning generation means and notifying the driver.

[0112] "Audio notification means" refers to a function and device for conveying a warning message to the driver by voice.

[0113] The present invention provides a system for preventing drivers from falling asleep or becoming distracted while driving long distances and ensuring safe driving. The system includes a sensor means, a terminal, a processing means, an analysis means, a warning generation means, a communication means, a display means, and a voice notification means.

[0114] Sensor Means

[0115] Processing performed by the device

[0116] The sensor means includes an AI camera that captures the driver's face and movements in real time. Specific examples of the sensor means include the ability to continuously collect facial expressions, blink frequency, gaze direction, facial expressions, and head position. Based on this information, the device can instantly assess the driver's condition.

[0117] Terminal

[0118] Processing performed by the device

[0119] The terminal is a device that temporarily stores data acquired from the sensor means and transmits it to a server via a network. The network used is a high-speed, highly stable Wi-Fi 6 or 5G mobile network. The MQTT protocol is used for data compression and transmission. It also has a retransmission function and performs error handling to avoid transmission errors.

[0120] Processing means

[0121] Processing performed by the server

[0122] The server preprocesses the video data received from the device and improves the quality of the data by performing noise reduction and image correction. Gaussian blur is used for noise reduction, and a color correction algorithm is applied for image correction. Haarcascades is also used to extract face position information.

[0123] Analysis means

[0124] Processing performed by the server

[0125] The preprocessed data is then input into the generative AI model's analysis engine, which analyzes the driver's face and movement patterns using a convolutional neural network (CNN) based on ResNet50. This allows for real-time detection of signs of drowsiness or distraction.

[0126] Warning generation means

[0127] Processing performed by the server

[0128] If the analysis engine detects an abnormality, the server immediately generates a warning message, which includes specific instructions such as "Signs of drowsy driving have been detected. Please take a break." This message is sent to the device and also notifies the operation manager.

[0129] communication means

[0130] Processing performed by the device

[0131] It provides the functionality to communicate data between sensor means and analysis means in real time, minimizing data latency by using a high-performance communication protocol.

[0132] Display means

[0133] Processing performed by the device

[0134] The terminal receives warning messages from the server and displays them to the driver, including pop-up messages and warnings in the vehicle's infotainment system.

[0135] Audio notification means

[0136] Processing performed by the device

[0137] The device is equipped with a function to communicate warning messages to the driver by voice, allowing the driver to be warned by both visual and audible means.

[0138] Examples and prompts

[0139] For example, if a driver blinks less than five times in 30 seconds and their gaze is fixed in a certain direction while driving long distances, the AI ​​camera detects this and collects data. The collected data is sent to the server, where it undergoes preprocessing and is then input into the analysis engine of the generative AI model. If the analysis engine detects signs of drowsy driving, the server generates a warning message stating, "Signs of drowsy driving have been detected. Please take a break," and sends it to the device. The device then displays this warning message and notifies the driver via voice. The driver can then acknowledge this warning and take appropriate breaks to ensure safe driving.

[0140] Example prompts to input to a generative AI model:

[0141] "Please detect signs of drowsiness or distraction from facial video data of a driver while driving. Specifically, if the blinking frequency is less than five times in 30 seconds and the driver's gaze is fixed in a certain direction, please recognize this as a sign of drowsy driving and immediately generate a warning message."

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

[0143] Step 1:

[0144] Data collection by sensor means

[0145] This is a process performed by the device. An AI camera installed on the device captures the driver's face and movements in real time and collects video data. Specifically, the AI ​​camera analyzes frames per second to obtain data such as blink frequency, gaze direction, facial expressions, and head position. The input is a video of the driver's face, and the output is an analyzable data file.

[0146] Step 2:

[0147] Temporarily storing data and preparing it for transmission

[0148] This is a process performed by the device. The collected data is temporarily stored in the device. The stored data is compressed in preparation for transmission. Specifically, a compression algorithm is used to reduce the data size so that the video data can be uploaded to cloud storage. The input is the video data acquired from the sensor, and the output is a compressed data file.

[0149] Step 3:

[0150] Sending data

[0151] This is a process performed by the device. The saved data is sent to the server via the network. Wi-Fi 6 or 5G mobile networks are used as the communication method, and the MQTT protocol is used to minimize data delays. If data transmission fails, it is retransmitted. The input is a compressed data file, and the output is a notification of successful transmission to the server.

[0152] Step 4:

[0153] Data Preprocessing

[0154] This is a process performed by the server. The server preprocesses the video data received from the device, removing noise and correcting the image. Specifically, it uses Gaussian blur to remove noise and applies a color correction algorithm to improve image quality. It also uses Haarcascades to extract facial position information. The input is the video data received from the device, and the output is preprocessed, high-quality data.

[0155] Step 5:

[0156] Data analysis

[0157] This is a process performed by the server. The preprocessed data is input into the analysis engine of the generative AI model. The analysis engine uses a convolutional neural network (CNN) based on ResNet50 to analyze the driver's facial expressions and movement patterns. The analysis results detect signs of drowsiness or distraction. The input is preprocessed high-quality data, and the output is the analysis result, indicating whether or not there are any abnormalities.

[0158] Step 6:

[0159] Generate warnings

[0160] This is a process performed by the server. If an abnormality is detected by the analysis engine, the server immediately generates a warning message. The warning message contains specific instructions such as "Signs of drowsy driving have been detected. Please take a break." This message is sent to the terminal and also notified to the operation manager. The input is the abnormality detection notification as the analysis result, and the output is the generated warning message.

[0161] Step 7:

[0162] Warning display and notification

[0163] This is a process performed by the terminal. The terminal receives a warning message from the server and displays it on the driver's display, and also notifies the driver by voice. Specifically, a pop-up message appears on the terminal screen, and an audio warning is issued at the same time. The input is the warning message, and the output is a visual and audio notification to the driver.

[0164] (Application example 1)

[0165] 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."

[0166] Conventional systems designed to prevent drivers and operators from falling asleep or becoming distracted have limitations in their ability to effectively detect and warn in real time. In particular, in logistics centers and factories, where there are many operators, efficient monitoring is difficult, and improvements in work efficiency and safety are required. Another problem is that warnings are only transmitted visually, making them difficult to reliably reach the operators. The objective of this invention is to solve these issues and provide a safe and efficient work environment.

[0167] 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.

[0168] In this invention, the server includes a sensor means for capturing the face and movements of an operator in real time, a processing means for preprocessing data acquired from the sensor means, an analysis means for analyzing the data preprocessed by the processing means and detecting signs of drowsiness or distraction, a warning generation means for generating a warning and transmitting it to a terminal when an abnormality is detected by the analysis means, a display means for displaying the warning message generated by the warning generation means and notifying the operator, and a communication means for communicating data between the sensor means and the analysis means in real time, thereby making it possible to effectively detect drowsiness or distraction of an operator in real time and to convey a warning visually and audibly.

[0169] "Operator" refers to an employee who operates forklifts and other equipment at a logistics center or factory.

[0170] "Drowsiness" refers to a state in which a worker temporarily loses consciousness unintentionally, and is a factor that threatens safety, especially during work.

[0171] "Distraction" refers to a state in which one is not concentrating on a task, and is manifested by, for example, fixating one's gaze elsewhere.

[0172] "Sensor means" refers to a camera or other device for capturing the operator's face and movements in real time.

[0173] The "processing means" refers to hardware and software for preprocessing data acquired from the sensor means, and specifically refers to devices and programs that perform noise removal and image correction.

[0174] "Analysis means" refers to a generative AI engine or neural network that analyzes the data preprocessed by the processing means and detects signs of drowsiness or distraction.

[0175] The "warning generation means" refers to a system for generating a warning message and transmitting it to a terminal when an abnormality is detected by the analysis means.

[0176] The "display means" refers to a display or audio notification device for displaying the warning message generated by the warning generation means and notifying the operator.

[0177] "Communication means" refers to communication technologies such as Wi-Fi and Bluetooth that allow data to be transmitted in real time between the sensor means and the analysis means.

[0178] The present invention provides a system for detecting operator drowsiness or distraction in real time, and specific embodiments thereof are described below. The system aims to improve safety and efficiency in environments where many operators work, such as logistics centers and factories.

[0179] 1. System Configuration

[0180] The system includes the following components:

[0181] 1. Sensor means

[0182] A camera mounted on the smart glasses captures the operator's face and movements in real time, and this data is continuously captured while the operator is performing their task.

[0183] 2. Processing means

[0184] The data acquired from the sensor means is first pre-processed on the terminal, which includes noise removal and image correction to generate high-quality data.

[0185] 3. Analysis method

[0186] The pre-processed data is sent to a server where a generative AI engine runs, which uses neural networks to analyze the data and detect signs of operator drowsiness or distraction in real time.

[0187] 4. Warning generation means

[0188] If an abnormality is detected by the analysis means, the server immediately generates a warning message, which is sent to the operator's terminal.

[0189] 5. Display means

[0190] The warning message generated by the warning generating means is displayed on the display of the smart glasses and also uses audio notification to ensure awareness by the operator.

[0191] 6. Means of communication

[0192] Wi-Fi, Bluetooth, etc. are used to communicate data between the sensor means and the analysis means in real time, ensuring immediacy and efficiency of data.

[0193] 2. Program Overview

[0194] The server runs a program that integrates each of these means. Specifically, it receives video data from the smart glasses, preprocesses the data, analyzes it using a generative AI engine, and generates and displays warning messages as necessary.

[0195] Hardware and software used

[0196] Smart glasses: Devices worn by operators to capture their faces and movements (e.g., Garmin Varia Vision, Google Glass)

[0197] AI camera: a camera built into smart glasses

[0198] Neural Networks: Generative AI Engine with TensorFlow

[0199] Communication method: Wi-Fi and Bluetooth data communication technology

[0200] Server: A computer system for processing and analyzing data.

[0201] 3. Processing Details

[0202] Pretreatment

[0203] The device pre-processes the video data received from the smart glasses, including noise reduction and image correction, to produce high-quality data suitable for analysis.

[0204] Data analysis

[0205] The server feeds the pre-processed data into a generative AI engine, which uses neural networks to analyze the operator's facial expressions and movement patterns to detect signs of drowsiness or distraction.

[0206] Alert generation and display

[0207] If an abnormality is detected, the server generates a warning message and sends it to the terminal, which then displays the warning message on the smart glasses display and alerts the operator using audio notification.

[0208] Examples and prompts

[0209] For example, if an operator's blink rate decreases and their gaze becomes fixed over a certain period of time, the generative AI engine will detect signs of drowsiness from this data. In this case, the following prompt sentence will be input to the generative AI model:

[0210] "The operator blinks less frequently over a period of time, indicating a more fixed gaze. Use this data to detect signs of drowsy driving."

[0211] Analysis is performed based on this prompt text, and if an abnormality is detected, a warning message is generated stating, "Signs of drowsiness have been detected. Please take a break," and the operator is notified visually and audibly.

[0212] In this way, the system of the present invention can effectively detect operator drowsiness or distraction, providing a safe and efficient working environment.

[0213] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0214] Step 1:

[0215] Activating the sensor function

[0216] The smart glasses used by the user are turned on, and the built-in camera begins capturing the operator's face and movements in real time. The input is video data of the operator's face and movements, and the output is video data temporarily stored in the smart glasses.

[0217] Step 2:

[0218] Data Preprocessing

[0219] The device preprocesses the video data acquired from the smart glasses. The input is temporarily stored video data, and it performs noise removal, image correction, and facial position extraction. The output is high-quality video data suitable for analysis.

[0220] Step 3:

[0221] Sending data

[0222] The terminal transmits the preprocessed data to the server. The input is the preprocessed high-quality video data, which is transmitted to the server using a communication means. The output is the video data received by the server.

[0223] Step 4:

[0224] Data analysis

[0225] The server inputs the preprocessed data into a generative AI engine that analyzes the operator's face and movement patterns. The input is the data received by the server, which uses a neural network to analyze signs of drowsiness or distraction. The output is the analysis results.

[0226] Step 5:

[0227] Anomaly detection and alert generation

[0228] If an abnormality is detected based on the analysis results, the server generates a warning message. The input is the analysis results, and the server generates a warning message based on the detected abnormality (e.g., drowsiness or distraction). The output is the generated warning message.

[0229] Step 6:

[0230] Sending a warning message

[0231] The server sends the generated warning message to the terminal. The input is the generated warning message, which is sent to the terminal using a communication means. The output is the warning message received by the terminal.

[0232] Step 7:

[0233] Displaying a warning message

[0234] The terminal displays the received warning message using the smart glasses' display and audio notification function. The input is the warning message received by the terminal and notifies the user through visual and audio. The output is the warning information conveyed to the operator.

[0235] Specifically, if the operator's blinking frequency decreases and their gaze becomes fixed within a certain period of time, the server inputs the following prompt sentence into the generative AI model: "The operator's blinking frequency decreases over a certain period of time, indicating that their gaze is fixed. Please use this data to detect signs of drowsy driving." If signs of drowsiness are detected, the smart glasses' display will display "Signs of drowsiness have been detected. Please take a break." and an audio notification will also be given.

[0236] 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.

[0237] The present invention provides a system for effectively preventing drowsy driving and distracted driving of drivers in the long-distance trucking and transportation industries, and managing the health and emotional state of the driver. The system includes the following components:

[0238] 1. Sensor means

[0239] The sensor means installed in the device has the function of capturing the driver's face and movements in real time. Specifically, an AI camera installed in the vehicle continuously collects the driver's face, blink frequency, gaze direction, facial expression, head position, etc. This data is used for analysis to detect drowsy driving and distraction, as well as for the emotion engine.

[0240] 2. Processing means

[0241] The server pre-processes the data sent by the sensor means, including noise removal, image correction, and facial location extraction, to improve the quality of the data provided to the subsequent analysis means and emotion engine.

[0242] 3. Analysis method

[0243] The server inputs the preprocessed data into the generative AI's analysis engine, which uses a neural network to analyze the driver's facial expressions and movement patterns. This analysis detects signs of driver drowsiness or distraction in real time.

[0244] 4. Emotion Engine

[0245] Furthermore, the server is equipped with an emotion engine that detects the driver's emotional state using the data preprocessed by the processing means, and analyzes the driver's emotions, such as tiredness, stress, and relaxation, in real time.

[0246] 5. Alert generation means

[0247] If an abnormality is detected by the analysis means or emotion engine, the server generates a warning message. The content of the generated warning message is adjusted based on the driver's emotional state. For example, if the driver is feeling stressed, a warning message urging them to relax is generated.

[0248] 6. Means of communication

[0249] It also includes a communication means for communicating data in real time between the sensor means, processing means, analysis means, and emotion engine, so that all data is shared without delay, enabling rapid analysis and emotion recognition.

[0250] 7. Display means

[0251] The warning message generated by the warning generating means is notified to the driver by the display means of the terminal, and the driver can check the displayed message and take appropriate action.

[0252] About program processing

[0253] Processing of Sensor Means

[0254] Processing performed by the device

[0255] An AI camera installed on the device captures the driver's face in real time and collects data on their movements and facial expressions. This data is temporarily stored on the device and then sequentially sent to a server.

[0256] Data Preprocessing

[0257] Processing performed by the server

[0258] The server preprocesses the data received from the device, removing noise and correcting the image, resulting in high-quality data.

[0259] Data Analysis and Emotion Recognition

[0260] Processing performed by the server

[0261] The preprocessed data is input into an analysis engine and emotion engine powered by generative AI. The analysis engine detects signs of driver drowsiness or distraction, while the emotion engine recognizes the driver's emotional state. For example, if a driver's blinking rate decreases and their gaze becomes fixed within a certain period of time, the analysis engine will detect signs of drowsiness, and the emotion engine will recognize that the driver is fatigued.

[0262] Generate warnings

[0263] Processing performed by the server

[0264] Based on the results of the analysis and emotion recognition, if an abnormality is detected or a specific emotional state is identified, the server will generate a warning message, such as "Signs of drowsy driving detected. Please take a break immediately," and may also include additional advice depending on the driver's emotional state.

[0265] Displaying warnings

[0266] Processing performed by the device

[0267] The terminal receives a warning message from the server and displays it to the driver. For example, the warning message is displayed on the screen and an audio notification is also provided.

[0268] In this way, the system of the present invention supports safe driving and health management by implementing measures that take into account the driver's drowsy driving, careless driving, and even emotional state.

[0269] The processing flow will be explained below.

[0270] Step 1:

[0271] Terminal handling

[0272] An AI camera installed on the device captures the driver's face in real time and collects video data. Specifically, the camera captures video at 20 frames per second and detects blinking frequency, gaze direction, and facial orientation.

[0273] Step 2:

[0274] Terminal handling

[0275] The collected video data is temporarily stored in the internal memory, and when it reaches an appropriate buffer size, it is sent to the server in real time using a communication means.

[0276] Step 3:

[0277] Server Processing

[0278] The server decodes the video data received from the device and performs preprocessing, which includes noise reduction, image sharpening, cropping of necessary areas, etc. It also performs preprocessing such as extracting facial position information and the number of blinks.

[0279] Step 4:

[0280] Server Processing

[0281] The preprocessed data is input into the generative AI's analysis engine, which uses a neural network to analyze the driver's facial expressions and movement patterns. This analysis detects signs of drowsiness or distraction based on factors such as blink frequency and gaze direction.

[0282] Step 5:

[0283] Server Processing

[0284] The analyzed data is also sent to the emotion engine in parallel, which infers the driver's emotional state from facial expression changes and movements to determine whether the driver is tired, stressed, relaxed, etc.

[0285] Step 6:

[0286] Server Processing

[0287] If an abnormality is detected by the analysis means or emotion engine, the server generates a warning message. At this time, the content of the warning message is adjusted based on the driver's emotional state recognized by the emotion engine. For example, if the driver is fatigued, the message generated will read, "Signs of drowsy driving have been detected. Please take a break immediately."

[0288] Step 7:

[0289] Server Processing

[0290] The generated warning message is sent to the device, and a notification is also sent to the operation manager via email or SMS at the same time.

[0291] Step 8:

[0292] Terminal handling

[0293] The terminal receives warning messages from the server and displays them to the driver. Specifically, the warning message is displayed on the display and, if necessary, an audio notification is also provided.

[0294] Step 9:

[0295] User Action

[0296] The user (driver) checks the warning message and takes appropriate action, such as stopping at a service area or rest area to take a break.

[0297] Step 10:

[0298] Server Processing

[0299] As a follow-up, the server continues to monitor the driver's state using generative AI and emotion engines, and generates messages based on the analysis results to provide additional rest advice or driving advice at the appropriate time.

[0300] Step 11:

[0301] Server Processing

[0302] The generated follow-up message is sent to the terminal, for example, a message such as "Please take a break at the next service area."

[0303] Step 12:

[0304] Terminal handling

[0305] The device receives the follow-up message and displays it to the driver, who is expected to take appropriate driving actions based on it.

[0306] This system effectively prevents drivers from falling asleep or becoming distracted, and supports comprehensive safe driving by taking into account the driver's health and emotional state.

[0307] Example 2

[0308] 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."

[0309] The purpose of this invention is to provide a system that can effectively prevent drowsy driving and inattentive driving of drivers engaged in long-distance trucking and transportation businesses, and can also manage the health and emotional state of drivers in real time, thereby reducing traffic accidents and maintaining the health of drivers.

[0310] 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.

[0311] In this invention, the server includes a sensor means for capturing the driver's face and movements in real time, an information processing means for preprocessing the data acquired from the sensor means, and an analysis means for analyzing the data preprocessed by the processing means to detect signs of the driver's drowsiness or distraction and their emotional state. This makes it possible to detect signs of the driver's drowsiness or distraction early and generate appropriate warnings to notify the driver. Furthermore, detecting the driver's emotional state makes it possible to manage the driver's stress and fatigue in real time.

[0312] The "sensor means" is a device that captures the driver's face and movements in real time and collects data such as blink frequency, gaze direction, facial expression, and head position.

[0313] "Information processing means" refers to a device or program for preprocessing data acquired from the sensor means, specifically performing noise removal, image correction, extraction of facial position information, etc.

[0314] "Analysis means" refers to devices or programs that analyze pre-processed data using an analytical engine and emotion engine powered by generative AI to detect signs of drowsiness or distraction in the driver and their emotional state.

[0315] The "warning generation means" is a device or program that generates a warning message and notifies the driver when an abnormality is detected by the analysis means.

[0316] The "communication means" is a device for communicating data in real time between the sensor means, the information processing means, the analysis means, and the emotion engine.

[0317] The "display means" is a device for displaying and notifying the driver of the warning message generated by the warning generation means.

[0318] The present invention provides a system for effectively preventing drowsy driving and inattentive driving of drivers engaged in long-distance trucking and transportation businesses, and for managing the health and emotional state of the driver in real time. Specific embodiments of the system are described below.

[0319] 1. Sensor means

[0320] Processing performed by the device

[0321] The device is equipped with an AI camera that captures the driver's face and movements in real time. The AI ​​camera monitors blinking frequency, gaze direction, facial expressions, head position, and other data in real time, collecting this data. The collected data is temporarily stored in the device and then sequentially sent to a server.

[0322] 2. Data Preprocessing

[0323] Processing performed by the server

[0324] The server receives the data sent from the device and performs noise reduction and image correction using software such as OpenCV and Python scripts. Preprocessing includes noise reduction, adjusting image brightness and contrast, and extracting facial position information.

[0325] 3. Data Analysis and Emotion Recognition

[0326] Processing performed by the server

[0327] The preprocessed data is input into an analysis engine and emotion engine using generative AI. Specific software used is TensorFlow and Keras. The analysis engine uses a neural network to analyze the driver's facial expressions and movement patterns to detect signs of drowsiness or distraction in real time. The emotion engine also recognizes the driver's emotional state (fatigue, stress, relaxation, etc.). The driver's condition is determined based on the results of this analysis.

[0328] 4. Warning generation means

[0329] Processing performed by the server

[0330] If the server detects an abnormality based on the results of the analysis engine and emotion engine, it generates a warning message for the driver. The generated warning message is adjusted based on the driver's emotional state. For example, it may include a warning such as "Signs of drowsy driving have been detected. Please take a break immediately" or advice such as "Fatigue has been detected. Please take a deep breath to promote relaxation."

[0331] 5. Warning Display

[0332] Processing performed by the device

[0333] The terminal receives warning messages from the server and displays them to the driver, either as a text message on the display or as a voice notification, allowing the driver to check the message and take appropriate action.

[0334] 6. Means of communication

[0335] It includes a means for communicating data in real time between the sensor means, information processing means, analysis means, and emotion engine, which allows all data to be shared without delay, enabling rapid analysis and emotion recognition.

[0336] Examples of concrete examples and prompts

[0337] For example, if a driver's blinking rate decreases and their gaze becomes fixed within a certain period of time, the analysis engine will detect signs of drowsiness while the emotion engine will recognize that the driver is fatigued. Based on this, a warning message will be generated and sent to the driver via the device's display and speaker, stating, "Signs of drowsiness at the wheel have been detected. Please take a break immediately."

[0338] Example prompt for a generative AI model:

[0339] "It captures the driver's face and analyzes their behavior in real time, including blinking frequency, gaze direction, and facial expressions. If an abnormality is detected, it generates an appropriate warning message and displays it on the device."

[0340] In this way, this system prevents drivers from falling asleep or being careless while driving, and supports health management.

[0341] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0342] Step 1:

[0343] Data collection

[0344] Processing performed by the device

[0345] An AI camera installed on the device captures the driver's face in real time, collecting data on the driver's facial movements, blink frequency, gaze direction, facial expressions, head position, and other specific behaviors.

[0346] Input: Driver image and motion data

[0347] Output: Collected image and behavioral data

[0348] Step 2:

[0349] Sending data

[0350] Processing performed by the device

[0351] The collected data is temporarily stored in the terminal and then transmitted to the server. Specifically, when a certain data buffer is filled, the terminal transmits the data to the server according to a data transmission protocol.

[0352] Input: Collected image and behavioral data

[0353] Output: Data sent to the server

[0354] Step 3:

[0355] Pretreatment

[0356] Processing performed by the server

[0357] The server preprocesses the data received from the device, including noise reduction, image correction, brightness and contrast adjustment, and facial position extraction.

[0358] Input: Image data and motion data sent from the device

[0359] Output: Preprocessed, high-quality data

[0360] Step 4:

[0361] Analysis and Emotion Recognition

[0362] Processing performed by the server

[0363] The preprocessed data is input into the generative AI's analysis engine and emotion engine. The analysis engine uses a neural network to detect signs of driver drowsiness or distraction, while the emotion engine recognizes the driver's emotional state (fatigue, stress, relaxation, etc.).

[0364] Input: Preprocessed, high-quality data

[0365] Output: Analysis of drowsy driving, distraction symptoms, and emotional state

[0366] Step 5:

[0367] Warning generation

[0368] Processing performed by the server

[0369] If an anomaly is detected based on the results of the analysis engine and emotion engine, the server generates a warning message, which is tailored to the driver's emotional state.

[0370] Input: Parsed result data

[0371] Output: Warning message

[0372] Step 6:

[0373] Warning display

[0374] Processing performed by the device

[0375] Methods for displaying the warning message received by the terminal from the server to the driver include displaying a text message on the display and an audio notification.

[0376] Input: The warning message sent by the server

[0377] Output: Warning message displayed by the driver

[0378] Through these steps, the system can prevent drowsy or inattentive driving, generate appropriate warnings and promptly notify the driver, and also manage the driver's health and emotional state in real time.

[0379] (Application example 2)

[0380] 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."

[0381] Conventional drowsy driving prevention systems have focused on capturing and analyzing the driver's face and movements, but have not yet reached the point of recognizing the driver's emotional state and health status in real time. As a result, it has been difficult to accurately grasp the driver's emotional state, such as distraction, fatigue, and stress, and provide appropriate warnings and notifications, resulting in issues that make it difficult to ensure sufficient safety. Therefore, the present invention aims to provide a system that recognizes not only signs of drowsy driving and distraction, but also the driver's emotional state in real time and provides appropriate warnings.

[0382] 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 a sensing means for capturing the driver's face and movements in real time, a processing means for preprocessing the data acquired from the sensing means, an analysis means for analyzing the data preprocessed by the processing means and detecting signs of the driver drowsing at the wheel or being distracted, an emotion recognition means for recognizing the driver's emotional state in real time by the analysis means, a warning generation means for generating a warning and sending it to a terminal when an abnormality is detected, and a display means for displaying the generated warning message. This makes it possible to prevent the driver from drowsing at the wheel or being distracted, and to provide an appropriate warning based on the driver's emotional state.

[0383] "Sensing means" refers to devices and technologies that capture the driver's face and movements in real time.

[0384] "Processing means" refers to devices and technologies that preprocess data acquired from the sensing means and perform noise removal and image correction.

[0385] "Analytical means" refers to devices and technologies that analyze pre-processed data to detect signs of driver drowsiness or distraction.

[0386] "Emotion recognition means" refers to devices and technologies that recognize the emotional state of a driver in real time from data obtained by the analysis means.

[0387] "Warning generation means" refers to a device or technology that generates a warning and sends it to a terminal when an abnormality is detected by the analysis means or emotion recognition means.

[0388] "Display means" refers to devices and techniques that display the generated warning message and notify the driver.

[0389] "Communication Means" refers to devices and technologies that communicate data in real time between the Sensing Means and the Analysis Means or Emotion Recognition Means.

[0390] "Audio output means" refers to a device and technology that notifies the driver of the generated warning message by voice.

[0391] The present invention is a system for preventing drowsiness and distraction at the wheel, and supports safe driving by monitoring the driver's health and emotional state in real time. The system includes the following components:

[0392] Sensing Method

[0393] This is a device that uses a camera installed on a terminal or vehicle (e.g., a smartphone or in-car camera) to capture the driver's face and movements in real time, collecting information such as the driver's facial expression, blink frequency, gaze direction, and head position.

[0394] Processing means

[0395] The server or device preprocesses the data acquired from the sensing means, including noise removal and image correction, to generate high-quality data that is useful for subsequent analysis.

[0396] analytical means

[0397] The preprocessed data is analyzed by the server. The data is input into an analysis engine that uses a generative AI model to detect signs of driver drowsiness or distraction in real time. For example, if a decrease in blinking frequency and fixed gaze are detected within a certain period of time, this is analyzed as a sign of drowsy driving.

[0398] emotion recognition means

[0399] Using another generative AI model, the emotion engine uses the data pre-processed by the processing means to recognize the driver's emotional state in real time, for example, whether the driver is tired, stressed or relaxed.

[0400] Warning generation means

[0401] If an abnormality is detected by the analysis or emotion recognition methods, the server automatically generates a warning message, such as "Signs of drowsy driving have been detected. Please take a break immediately." Additional advice based on the driver's emotional state may also be included.

[0402] communication means

[0403] It includes a communication device for communicating data in real time between the sensing means, processing means, analysis means, and emotion recognition means, allowing all data to be shared without delay, enabling rapid analysis and emotion recognition.

[0404] Display means

[0405] The generated warning message is displayed on the display screen of the terminal or on the head-mounted display. The warning may also be given by voice through the voice output means. This allows the driver to check the warning message and take appropriate action.

[0406] Hardware and software used

[0407] In this invention, specific hardware includes a camera (e.g., a smartphone camera or a car camera) and a head-mounted display, and software includes image processing using OpenCV and execution of generative AI models using TensorFlow and Keras.

[0408] Examples of concrete examples and prompts

[0409] A concrete example is the following prompt:

[0410] "If a driver exhibits a decrease in blinking rate and gaze fixation within a certain period of time, signs of drowsy driving are detected."

[0411] "A system that analyzes driver behavior data captured by a camera in smart glasses in real time to detect signs of drowsy driving or distraction."

[0412] This enables the system to optimize driver safety while driving and also improve the overall efficiency of operations.

[0413] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0414] Step 1:

[0415] The sensing means captures the driver's face and movements in real time. The input is camera footage, and the output is captured image data. A camera (e.g., a smartphone camera or an in-car camera) periodically captures images and sends them to a terminal.

[0416] Step 2:

[0417] The device preprocesses the image data acquired from the sensing means. The input is the captured image data, and the output is the preprocessed image data. Preprocessing includes noise removal, image correction, face detection, etc., and is performed using OpenCV.

[0418] Step 3:

[0419] The server inputs the preprocessed image data into the generative AI model. The input is the preprocessed image data, and the output is the analysis results. Using TensorFlow and Keras, the analysis engine analyzes the data to detect signs of driver drowsiness or distraction.

[0420] Step 4:

[0421] The server uses an emotion recognition means to recognize the driver's emotional state from the analysis results. The input is the analysis results, and the output is the data of the driver's emotional state. Another generative AI model is used to evaluate the driver's fatigue, stress, and relaxation states in real time.

[0422] Step 5:

[0423] The server generates a warning message based on the results of the analysis and emotion recognition. The input is data on the driver's emotional state, and the output is a warning message. The warning generation means automatically creates a warning message based on signs of drowsy driving and stress levels.

[0424] Step 6:

[0425] The server transmits the generated warning message to the terminal in real time. The input is the warning message, and the output is data communication to the terminal. The warning message is transmitted to the terminal without delay using the communication means.

[0426] Step 7:

[0427] The terminal notifies the driver of a warning message using a display means. The input is the received warning message, and the output is the displayed warning message. The warning message is displayed on a display or head-mounted display, and the driver is also notified by voice using a voice output means.

[0428] 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.

[0429] 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.

[0430] 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.

[0431] [Second embodiment]

[0432] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0433] 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.

[0434] 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).

[0435] 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.

[0436] 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.

[0437] 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).

[0438] 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.

[0439] 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.

[0440] 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.

[0441] 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.

[0442] 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.

[0443] 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."

[0444] The present invention provides a system for effectively preventing drowsy driving and inattentive driving by drivers engaged in the long-distance truck and transportation industries, and for managing the health status of the drivers. The system includes the following components:

[0445] 1. Sensor means

[0446] The sensor means installed in the terminal has the function of capturing the driver's face and movements in real time. Specifically, an AI camera installed in the vehicle continuously collects the driver's face, blink frequency, gaze direction, facial expression, head position, etc. This video data is very important as it will be analyzed in detail later.

[0447] 2. Processing means

[0448] The server pre-processes the data sent from the sensor means, including noise removal, image correction, and facial position information extraction, thereby improving the quality of the data input to the analysis means.

[0449] 3. Analysis method

[0450] The server then inputs the pre-processed data into the Generative AI's analysis engine, which uses neural networks to analyze the driver's facial expressions and movement patterns to detect signs of drowsiness or distraction. This analysis is performed in real time, and the results are available immediately.

[0451] 4. Warning generation means

[0452] If an abnormality is detected by the analysis means, the server generates a warning message, such as "Caution: Signs of drowsiness detected. Please take a break immediately." This message is sent to the terminal and notifies the driver.

[0453] 5. Means of communication

[0454] Data is communicated in real time between the sensor means and the analysis means. The communication means minimizes data delays and achieves high-speed data transfer.

[0455] 6. Display means

[0456] The warning message generated by the warning generating means is notified to the driver by the display means of the terminal, and the driver is required to check the displayed message and take appropriate action.

[0457] About program processing

[0458] Processing of Sensor Means

[0459] Processing performed by the device

[0460] An AI camera installed on the device captures the driver's face in real time and collects video data, which is temporarily stored on the device and then sequentially sent to a server.

[0461] Data Preprocessing

[0462] Processing performed by the server

[0463] The server preprocesses the data received from the device, removing noise and correcting images, generating high-quality data suitable for analysis.

[0464] Data analysis

[0465] Processing performed by the server

[0466] The server inputs the pre-processed data into an analytical engine using a generative AI neural network, which analyzes the driver's facial and movement patterns to detect signs of drowsiness or distraction in real time.

[0467] Generate warnings

[0468] Processing performed by the server

[0469] If the analysis engine detects any symptoms, the server will determine the abnormality and immediately generate a warning message, which will be sent to the device and also notified to the operation manager.

[0470] Displaying warnings

[0471] Processing performed by the device

[0472] The terminal receives a warning message from the server and displays it to the driver. It is also possible to alert the driver by using voice notifications, etc.

[0473] Specific examples

[0474] For example, if a driver's blinking frequency decreases and their gaze becomes fixed within a certain period of time, this data is sent from the sensor means to the server. The server preprocesses this data and inputs it into the analysis engine of the generation AI. If the analysis engine detects signs of drowsy driving, the server generates a warning message saying "Signs of drowsy driving have been detected. Please take a break" and sends it to the device. The device displays this warning message to warn the driver. The driver confirms this warning and takes an appropriate break to ensure safe driving.

[0475] In this way, the system of the present invention can prevent the driver from falling asleep or driving carelessly, and can appropriately manage the driver's health condition.

[0476] The processing flow will be explained below.

[0477] Step 1:

[0478] Terminal handling

[0479] An AI camera installed on the device captures the driver's face in real time and collects video data. Specifically, the camera captures video at 20 frames per second and detects blinking frequency, gaze direction, and facial orientation.

[0480] Step 2:

[0481] Terminal handling

[0482] The collected video data is temporarily stored in the internal memory, and when it reaches an appropriate buffer size, it is sent to the server in real time using a communication means.

[0483] Step 3:

[0484] Server Processing

[0485] The server decodes the video data received from the device and performs pre-processing, which includes noise reduction, image sharpening, cropping of necessary parts, etc.

[0486] Step 4:

[0487] Server Processing

[0488] The preprocessed data is input into the generative AI's analysis engine, which uses a neural network to analyze the driver's facial expressions and movement patterns, such as blink frequency, gaze direction, and head position, to detect signs of drowsiness or distraction.

[0489] Step 5:

[0490] Server Processing

[0491] If an abnormality is detected based on the analysis results, the server generates a warning message, such as "Warning: Signs of drowsiness detected. Please take a break immediately."

[0492] Step 6:

[0493] Server Processing

[0494] The generated warning message is sent to the device, and a notification is also sent to the operation manager via email or SMS.

[0495] Step 7:

[0496] Terminal handling

[0497] The device receives the warning message from the server and displays it to the driver. Specifically, the warning message is displayed on the display and, in some cases, an audio notification is also given.

[0498] Step 8:

[0499] User Action

[0500] The user (driver) checks the warning message. Based on the warning message, the driver takes appropriate action, such as stopping at a service area or rest area to take a break.

[0501] Step 9:

[0502] Server Processing

[0503] As a follow-up, the server continues to monitor the driver's condition using generative AI, and based on the analysis results, generates messages to provide additional rest advice or driving advice at the appropriate time.

[0504] Step 10:

[0505] Server Processing

[0506] The generated follow-up message is sent to the terminal.

[0507] Step 11:

[0508] Terminal handling

[0509] The device receives a follow-up message and displays it to the driver, such as "Please take a break at the next service area."

[0510] Through these steps, the system helps prevent drivers from falling asleep or becoming distracted, supporting their health and safe driving.

[0511] Example 1

[0512] 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."

[0513] There is a need to prevent drivers from falling asleep or becoming distracted while driving long distances and ensure safe driving, but conventional systems have had difficulty monitoring the driver's health condition in real time and issuing prompt warnings. In particular, there are challenges in accurately and promptly detecting abnormalities due to inadequate data quality and communication delays.

[0514] 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.

[0515] In this invention, the server includes a sensor means for capturing the face and movements of the driver in real time, a terminal for saving data acquired from the sensor means and transmitting it via a network, a processing means for pre-processing data received from the terminal, an analysis means for analyzing the data pre-processed by the processing means and detecting signs of the driver drowsing at the wheel or being distracted, and a warning generation means for generating a warning when an abnormality is detected by the analysis means and transmitting the warning to the terminal. This makes it possible to monitor the driver's health condition in real time and to quickly issue a warning when drowsing at the wheel or being distracted is detected.

[0516] The "sensor means" is a device for capturing the driver's face and movements in real time.

[0517] A "terminal" is a device that stores data acquired from a sensor means and transmits the data to a server via a network.

[0518] "Processing means" refers to functions and devices for pre-processing data received from a terminal.

[0519] "Analysis means" refers to functions and devices for analyzing the pre-processed data and detecting signs of driver drowsiness or distraction.

[0520] The "warning generation means" is a function and device for generating a warning when an abnormality is detected by the analysis means and transmitting the warning to the terminal.

[0521] "Communication means" refers to functions and devices for communicating data in real time between the sensor means and the analysis means.

[0522] The "display means" refers to a function and device for displaying the warning message generated by the warning generation means and notifying the driver.

[0523] "Audio notification means" refers to a function and device for conveying a warning message to the driver by voice.

[0524] The present invention provides a system for preventing drivers from falling asleep or becoming distracted while driving long distances and ensuring safe driving. The system includes a sensor means, a terminal, a processing means, an analysis means, a warning generation means, a communication means, a display means, and a voice notification means.

[0525] Sensor Means

[0526] Processing performed by the device

[0527] The sensor means includes an AI camera that captures the driver's face and movements in real time. Specific examples of the sensor means include the ability to continuously collect facial expressions, blink frequency, gaze direction, facial expressions, and head position. Based on this information, the device can instantly assess the driver's condition.

[0528] Terminal

[0529] Processing performed by the device

[0530] The terminal is a device that temporarily stores data acquired from the sensor means and transmits it to a server via a network. The network used is a high-speed, highly stable Wi-Fi 6 or 5G mobile network. The MQTT protocol is used for data compression and transmission. It also has a retransmission function and performs error handling to avoid transmission errors.

[0531] Processing means

[0532] Processing performed by the server

[0533] The server preprocesses the video data received from the device and improves the quality of the data by performing noise reduction and image correction. Gaussian blur is used for noise reduction, and a color correction algorithm is applied for image correction. Haarcascades is also used to extract face position information.

[0534] Analysis means

[0535] Processing performed by the server

[0536] The preprocessed data is then input into the generative AI model's analysis engine, which analyzes the driver's face and movement patterns using a convolutional neural network (CNN) based on ResNet50. This allows for real-time detection of signs of drowsiness or distraction.

[0537] Warning generation means

[0538] Processing performed by the server

[0539] If the analysis engine detects an abnormality, the server immediately generates a warning message, which includes specific instructions such as "Signs of drowsy driving have been detected. Please take a break." This message is sent to the device and also notifies the operation manager.

[0540] communication means

[0541] Processing performed by the device

[0542] It provides the functionality to communicate data between sensor means and analysis means in real time, minimizing data latency by using a high-performance communication protocol.

[0543] Display means

[0544] Processing performed by the device

[0545] The terminal receives warning messages from the server and displays them to the driver, including pop-up messages and warnings in the vehicle's infotainment system.

[0546] Audio notification means

[0547] Processing performed by the device

[0548] The device is equipped with a function to communicate warning messages to the driver by voice, allowing the driver to be warned by both visual and audible means.

[0549] Examples and prompts

[0550] For example, if a driver blinks less than five times in 30 seconds and their gaze is fixed in a certain direction while driving long distances, the AI ​​camera detects this and collects data. The collected data is sent to the server, where it undergoes preprocessing and is then input into the analysis engine of the generative AI model. If the analysis engine detects signs of drowsy driving, the server generates a warning message stating, "Signs of drowsy driving have been detected. Please take a break," and sends it to the device. The device then displays this warning message and notifies the driver via voice. The driver can then acknowledge this warning and take appropriate breaks to ensure safe driving.

[0551] Example prompts to input to a generative AI model:

[0552] "Please detect signs of drowsiness or distraction from facial video data of a driver while driving. Specifically, if the blinking frequency is less than five times in 30 seconds and the driver's gaze is fixed in a certain direction, please recognize this as a sign of drowsy driving and immediately generate a warning message."

[0553] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0554] Step 1:

[0555] Data collection by sensor means

[0556] This is a process performed by the device. An AI camera installed on the device captures the driver's face and movements in real time and collects video data. Specifically, the AI ​​camera analyzes frames per second to obtain data such as blink frequency, gaze direction, facial expressions, and head position. The input is a video of the driver's face, and the output is an analyzable data file.

[0557] Step 2:

[0558] Temporarily storing data and preparing it for transmission

[0559] This is a process performed by the device. The collected data is temporarily stored in the device. The stored data is compressed in preparation for transmission. Specifically, a compression algorithm is used to reduce the data size so that the video data can be uploaded to cloud storage. The input is the video data acquired from the sensor, and the output is a compressed data file.

[0560] Step 3:

[0561] Sending data

[0562] This is a process performed by the device. The saved data is sent to the server via the network. Wi-Fi 6 or 5G mobile networks are used as the communication method, and the MQTT protocol is used to minimize data delays. If data transmission fails, it is retransmitted. The input is a compressed data file, and the output is a notification of successful transmission to the server.

[0563] Step 4:

[0564] Data Preprocessing

[0565] This is a process performed by the server. The server preprocesses the video data received from the device, removing noise and correcting the image. Specifically, it uses Gaussian blur to remove noise and applies a color correction algorithm to improve image quality. It also uses Haarcascades to extract facial position information. The input is the video data received from the device, and the output is preprocessed, high-quality data.

[0566] Step 5:

[0567] Data analysis

[0568] This is a process performed by the server. The preprocessed data is input into the analysis engine of the generative AI model. The analysis engine uses a convolutional neural network (CNN) based on ResNet50 to analyze the driver's facial expressions and movement patterns. The analysis results detect signs of drowsiness or distraction. The input is preprocessed high-quality data, and the output is the analysis result, indicating whether or not there are any abnormalities.

[0569] Step 6:

[0570] Generate warnings

[0571] This is a process performed by the server. If an abnormality is detected by the analysis engine, the server immediately generates a warning message. The warning message contains specific instructions such as "Signs of drowsy driving have been detected. Please take a break." This message is sent to the terminal and also notified to the operation manager. The input is the abnormality detection notification as the analysis result, and the output is the generated warning message.

[0572] Step 7:

[0573] Warning display and notification

[0574] This is a process performed by the terminal. The terminal receives a warning message from the server and displays it on the driver's display, and also notifies the driver by voice. Specifically, a pop-up message appears on the terminal screen, and an audio warning is issued at the same time. The input is the warning message, and the output is a visual and audio notification to the driver.

[0575] (Application example 1)

[0576] 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."

[0577] Conventional systems designed to prevent drivers and operators from falling asleep or becoming distracted have limitations in their ability to effectively detect and warn in real time. In particular, in logistics centers and factories, where there are many operators, efficient monitoring is difficult, and improvements in work efficiency and safety are required. Another problem is that warnings are only transmitted visually, making them difficult to reliably reach the operators. The objective of this invention is to solve these issues and provide a safe and efficient work environment.

[0578] 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.

[0579] In this invention, the server includes a sensor means for capturing the face and movements of an operator in real time, a processing means for preprocessing data acquired from the sensor means, an analysis means for analyzing the data preprocessed by the processing means and detecting signs of drowsiness or distraction, a warning generation means for generating a warning and transmitting it to a terminal when an abnormality is detected by the analysis means, a display means for displaying the warning message generated by the warning generation means and notifying the operator, and a communication means for communicating data between the sensor means and the analysis means in real time, thereby making it possible to effectively detect drowsiness or distraction of an operator in real time and to convey a warning visually and audibly.

[0580] "Operator" refers to an employee who operates forklifts and other equipment at a logistics center or factory.

[0581] "Drowsiness" refers to a state in which a worker temporarily loses consciousness unintentionally, and is a factor that threatens safety, especially during work.

[0582] "Distraction" refers to a state in which one is not concentrating on a task, and is manifested by, for example, fixating one's gaze elsewhere.

[0583] "Sensor means" refers to a camera or other device for capturing the operator's face and movements in real time.

[0584] The "processing means" refers to hardware and software for preprocessing data acquired from the sensor means, and specifically refers to devices and programs that perform noise removal and image correction.

[0585] "Analysis means" refers to a generative AI engine or neural network that analyzes the data preprocessed by the processing means and detects signs of drowsiness or distraction.

[0586] The "warning generation means" refers to a system for generating a warning message and transmitting it to a terminal when an abnormality is detected by the analysis means.

[0587] The "display means" refers to a display or audio notification device for displaying the warning message generated by the warning generation means and notifying the operator.

[0588] "Communication means" refers to communication technologies such as Wi-Fi and Bluetooth that allow data to be transmitted in real time between the sensor means and the analysis means.

[0589] The present invention provides a system for detecting operator drowsiness or distraction in real time, and specific embodiments thereof are described below. The system aims to improve safety and efficiency in environments where many operators work, such as logistics centers and factories.

[0590] 1. System Configuration

[0591] The system includes the following components:

[0592] 1. Sensor means

[0593] A camera mounted on the smart glasses captures the operator's face and movements in real time, and this data is continuously captured while the operator is performing their task.

[0594] 2. Processing means

[0595] The data acquired from the sensor means is first pre-processed on the terminal, which includes noise removal and image correction to generate high-quality data.

[0596] 3. Analysis method

[0597] The pre-processed data is sent to a server where a generative AI engine runs, which uses neural networks to analyze the data and detect signs of operator drowsiness or distraction in real time.

[0598] 4. Warning generation means

[0599] If an abnormality is detected by the analysis means, the server immediately generates a warning message, which is sent to the operator's terminal.

[0600] 5. Display means

[0601] The warning message generated by the warning generating means is displayed on the display of the smart glasses and also uses audio notification to ensure awareness by the operator.

[0602] 6. Means of communication

[0603] Wi-Fi, Bluetooth, etc. are used to communicate data between the sensor means and the analysis means in real time, ensuring immediacy and efficiency of data.

[0604] 2. Program Overview

[0605] The server runs a program that integrates each of these means. Specifically, it receives video data from the smart glasses, preprocesses the data, analyzes it using a generative AI engine, and generates and displays warning messages as necessary.

[0606] Hardware and software used

[0607] Smart glasses: Devices worn by operators to capture their faces and movements (e.g., Garmin Varia Vision, Google Glass)

[0608] AI camera: a camera built into smart glasses

[0609] Neural Networks: Generative AI Engine with TensorFlow

[0610] Communication method: Wi-Fi and Bluetooth data communication technology

[0611] Server: A computer system for processing and analyzing data.

[0612] 3. Processing Details

[0613] Pretreatment

[0614] The device pre-processes the video data received from the smart glasses, including noise reduction and image correction, to produce high-quality data suitable for analysis.

[0615] Data analysis

[0616] The server feeds the pre-processed data into a generative AI engine, which uses neural networks to analyze the operator's facial expressions and movement patterns to detect signs of drowsiness or distraction.

[0617] Alert generation and display

[0618] If an abnormality is detected, the server generates a warning message and sends it to the terminal, which then displays the warning message on the smart glasses display and alerts the operator using audio notification.

[0619] Examples and prompts

[0620] For example, if an operator's blink rate decreases and their gaze becomes fixed over a certain period of time, the generative AI engine will detect signs of drowsiness from this data. In this case, the following prompt sentence will be input to the generative AI model:

[0621] "The operator blinks less frequently over a period of time, indicating a more fixed gaze. Use this data to detect signs of drowsy driving."

[0622] Analysis is performed based on this prompt text, and if an abnormality is detected, a warning message is generated stating, "Signs of drowsiness have been detected. Please take a break," and the operator is notified visually and audibly.

[0623] In this way, the system of the present invention can effectively detect operator drowsiness or distraction, providing a safe and efficient working environment.

[0624] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0625] Step 1:

[0626] Activating the sensor function

[0627] The smart glasses used by the user are turned on, and the built-in camera begins capturing the operator's face and movements in real time. The input is video data of the operator's face and movements, and the output is video data temporarily stored in the smart glasses.

[0628] Step 2:

[0629] Data Preprocessing

[0630] The device preprocesses the video data acquired from the smart glasses. The input is temporarily stored video data, and it performs noise removal, image correction, and facial position extraction. The output is high-quality video data suitable for analysis.

[0631] Step 3:

[0632] Sending data

[0633] The terminal transmits the preprocessed data to the server. The input is the preprocessed high-quality video data, which is transmitted to the server using a communication means. The output is the video data received by the server.

[0634] Step 4:

[0635] Data analysis

[0636] The server inputs the preprocessed data into a generative AI engine that analyzes the operator's face and movement patterns. The input is the data received by the server, which uses a neural network to analyze signs of drowsiness or distraction. The output is the analysis results.

[0637] Step 5:

[0638] Anomaly detection and alert generation

[0639] If an abnormality is detected based on the analysis results, the server generates a warning message. The input is the analysis results, and the server generates a warning message based on the detected abnormality (e.g., drowsiness or distraction). The output is the generated warning message.

[0640] Step 6:

[0641] Sending a warning message

[0642] The server sends the generated warning message to the terminal. The input is the generated warning message, which is sent to the terminal using a communication means. The output is the warning message received by the terminal.

[0643] Step 7:

[0644] Displaying a warning message

[0645] The terminal displays the received warning message using the smart glasses' display and audio notification function. The input is the warning message received by the terminal and notifies the user through visual and audio. The output is the warning information conveyed to the operator.

[0646] Specifically, if the operator's blinking frequency decreases and their gaze becomes fixed within a certain period of time, the server inputs the following prompt sentence into the generative AI model: "The operator's blinking frequency decreases over a certain period of time, indicating that their gaze is fixed. Please use this data to detect signs of drowsy driving." If signs of drowsiness are detected, the smart glasses' display will display "Signs of drowsiness have been detected. Please take a break." and an audio notification will also be given.

[0647] 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.

[0648] The present invention provides a system for effectively preventing drowsy driving and distracted driving of drivers in the long-distance trucking and transportation industries, and managing the health and emotional state of the driver. The system includes the following components:

[0649] 1. Sensor means

[0650] The sensor means installed in the device has the function of capturing the driver's face and movements in real time. Specifically, an AI camera installed in the vehicle continuously collects the driver's face, blink frequency, gaze direction, facial expression, head position, etc. This data is used for analysis to detect drowsy driving and distraction, as well as for the emotion engine.

[0651] 2. Processing means

[0652] The server pre-processes the data sent by the sensor means, including noise removal, image correction, and facial location extraction, to improve the quality of the data provided to the subsequent analysis means and emotion engine.

[0653] 3. Analysis method

[0654] The server inputs the preprocessed data into the generative AI's analysis engine, which uses a neural network to analyze the driver's facial expressions and movement patterns. This analysis detects signs of driver drowsiness or distraction in real time.

[0655] 4. Emotion Engine

[0656] Furthermore, the server is equipped with an emotion engine that detects the driver's emotional state using the data preprocessed by the processing means, and analyzes the driver's emotions, such as tiredness, stress, and relaxation, in real time.

[0657] 5. Alert generation means

[0658] If an abnormality is detected by the analysis means or emotion engine, the server generates a warning message. The content of the generated warning message is adjusted based on the driver's emotional state. For example, if the driver is feeling stressed, a warning message urging them to relax is generated.

[0659] 6. Means of communication

[0660] It also includes a communication means for communicating data in real time between the sensor means, processing means, analysis means, and emotion engine, so that all data is shared without delay, enabling rapid analysis and emotion recognition.

[0661] 7. Display means

[0662] The warning message generated by the warning generating means is notified to the driver by the display means of the terminal, and the driver can check the displayed message and take appropriate action.

[0663] About program processing

[0664] Processing of Sensor Means

[0665] Processing performed by the device

[0666] An AI camera installed on the device captures the driver's face in real time and collects data on their movements and facial expressions. This data is temporarily stored on the device and then sequentially sent to a server.

[0667] Data Preprocessing

[0668] Processing performed by the server

[0669] The server preprocesses the data received from the device, removing noise and correcting the image, resulting in high-quality data.

[0670] Data Analysis and Emotion Recognition

[0671] Processing performed by the server

[0672] The preprocessed data is input into an analysis engine and emotion engine powered by generative AI. The analysis engine detects signs of driver drowsiness or distraction, while the emotion engine recognizes the driver's emotional state. For example, if a driver's blinking rate decreases and their gaze becomes fixed within a certain period of time, the analysis engine will detect signs of drowsiness, and the emotion engine will recognize that the driver is fatigued.

[0673] Generate warnings

[0674] Processing performed by the server

[0675] Based on the results of the analysis and emotion recognition, if an abnormality is detected or a specific emotional state is identified, the server will generate a warning message, such as "Signs of drowsy driving detected. Please take a break immediately," and may also include additional advice depending on the driver's emotional state.

[0676] Displaying warnings

[0677] Processing performed by the device

[0678] The terminal receives a warning message from the server and displays it to the driver. For example, the warning message is displayed on the screen and an audio notification is also provided.

[0679] In this way, the system of the present invention supports safe driving and health management by implementing measures that take into account the driver's drowsy driving, careless driving, and even emotional state.

[0680] The processing flow will be explained below.

[0681] Step 1:

[0682] Terminal handling

[0683] An AI camera installed on the device captures the driver's face in real time and collects video data. Specifically, the camera captures video at 20 frames per second and detects blinking frequency, gaze direction, and facial orientation.

[0684] Step 2:

[0685] Terminal handling

[0686] The collected video data is temporarily stored in the internal memory, and when it reaches an appropriate buffer size, it is sent to the server in real time using a communication means.

[0687] Step 3:

[0688] Server Processing

[0689] The server decodes the video data received from the device and performs preprocessing, which includes noise reduction, image sharpening, cropping of necessary areas, etc. It also performs preprocessing such as extracting facial position information and the number of blinks.

[0690] Step 4:

[0691] Server Processing

[0692] The preprocessed data is input into the generative AI's analysis engine, which uses a neural network to analyze the driver's facial expressions and movement patterns. This analysis detects signs of drowsiness or distraction based on factors such as blink frequency and gaze direction.

[0693] Step 5:

[0694] Server Processing

[0695] The analyzed data is also sent to the emotion engine in parallel, which infers the driver's emotional state from facial expression changes and movements to determine whether the driver is tired, stressed, relaxed, etc.

[0696] Step 6:

[0697] Server Processing

[0698] If an abnormality is detected by the analysis means or emotion engine, the server generates a warning message. At this time, the content of the warning message is adjusted based on the driver's emotional state recognized by the emotion engine. For example, if the driver is fatigued, the message generated will read, "Signs of drowsy driving have been detected. Please take a break immediately."

[0699] Step 7:

[0700] Server Processing

[0701] The generated warning message is sent to the device, and a notification is also sent to the operation manager via email or SMS at the same time.

[0702] Step 8:

[0703] Terminal handling

[0704] The terminal receives warning messages from the server and displays them to the driver. Specifically, the warning message is displayed on the display and, if necessary, an audio notification is also provided.

[0705] Step 9:

[0706] User Action

[0707] The user (driver) checks the warning message and takes appropriate action, such as stopping at a service area or rest area to take a break.

[0708] Step 10:

[0709] Server Processing

[0710] As a follow-up, the server continues to monitor the driver's state using generative AI and emotion engines, and generates messages based on the analysis results to provide additional rest advice or driving advice at the appropriate time.

[0711] Step 11:

[0712] Server Processing

[0713] The generated follow-up message is sent to the terminal, for example, a message such as "Please take a break at the next service area."

[0714] Step 12:

[0715] Terminal handling

[0716] The device receives the follow-up message and displays it to the driver, who is expected to take appropriate driving actions based on it.

[0717] This system effectively prevents drivers from falling asleep or becoming distracted, and supports comprehensive safe driving by taking into account the driver's health and emotional state.

[0718] Example 2

[0719] 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."

[0720] The purpose of this invention is to provide a system that can effectively prevent drowsy driving and inattentive driving of drivers engaged in long-distance trucking and transportation businesses, and can also manage the health and emotional state of drivers in real time, thereby reducing traffic accidents and maintaining the health of drivers.

[0721] 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.

[0722] In this invention, the server includes a sensor means for capturing the driver's face and movements in real time, an information processing means for preprocessing the data acquired from the sensor means, and an analysis means for analyzing the data preprocessed by the processing means to detect signs of the driver's drowsiness or distraction and their emotional state. This makes it possible to detect signs of the driver's drowsiness or distraction early and generate appropriate warnings to notify the driver. Furthermore, detecting the driver's emotional state makes it possible to manage the driver's stress and fatigue in real time.

[0723] The "sensor means" is a device that captures the driver's face and movements in real time and collects data such as blink frequency, gaze direction, facial expression, and head position.

[0724] "Information processing means" refers to a device or program for preprocessing data acquired from the sensor means, specifically performing noise removal, image correction, extraction of facial position information, etc.

[0725] "Analysis means" refers to devices or programs that analyze pre-processed data using an analytical engine and emotion engine powered by generative AI to detect signs of drowsiness or distraction in the driver and their emotional state.

[0726] The "warning generation means" is a device or program that generates a warning message and notifies the driver when an abnormality is detected by the analysis means.

[0727] The "communication means" is a device for communicating data in real time between the sensor means, the information processing means, the analysis means, and the emotion engine.

[0728] The "display means" is a device for displaying and notifying the driver of the warning message generated by the warning generation means.

[0729] The present invention provides a system for effectively preventing drowsy driving and inattentive driving of drivers engaged in long-distance trucking and transportation businesses, and for managing the health and emotional state of the driver in real time. Specific embodiments of the system are described below.

[0730] 1. Sensor means

[0731] Processing performed by the device

[0732] The device is equipped with an AI camera that captures the driver's face and movements in real time. The AI ​​camera monitors blinking frequency, gaze direction, facial expressions, head position, and other data in real time, collecting this data. The collected data is temporarily stored in the device and then sequentially sent to a server.

[0733] 2. Data Preprocessing

[0734] Processing performed by the server

[0735] The server receives the data sent from the device and performs noise reduction and image correction using software such as OpenCV and Python scripts. Preprocessing includes noise reduction, adjusting image brightness and contrast, and extracting facial position information.

[0736] 3. Data Analysis and Emotion Recognition

[0737] Processing performed by the server

[0738] The preprocessed data is input into an analysis engine and emotion engine using generative AI. Specific software used is TensorFlow and Keras. The analysis engine uses a neural network to analyze the driver's facial expressions and movement patterns to detect signs of drowsiness or distraction in real time. The emotion engine also recognizes the driver's emotional state (fatigue, stress, relaxation, etc.). The driver's condition is determined based on the results of this analysis.

[0739] 4. Warning generation means

[0740] Processing performed by the server

[0741] If the server detects an abnormality based on the results of the analysis engine and emotion engine, it generates a warning message for the driver. The generated warning message is adjusted based on the driver's emotional state. For example, it may include a warning such as "Signs of drowsy driving have been detected. Please take a break immediately" or advice such as "Fatigue has been detected. Please take a deep breath to promote relaxation."

[0742] 5. Warning Display

[0743] Processing performed by the device

[0744] The terminal receives warning messages from the server and displays them to the driver, either as a text message on the display or as a voice notification, allowing the driver to check the message and take appropriate action.

[0745] 6. Means of communication

[0746] It includes a means for communicating data in real time between the sensor means, information processing means, analysis means, and emotion engine, which allows all data to be shared without delay, enabling rapid analysis and emotion recognition.

[0747] Examples of concrete examples and prompts

[0748] For example, if a driver's blinking rate decreases and their gaze becomes fixed within a certain period of time, the analysis engine will detect signs of drowsiness while the emotion engine will recognize that the driver is fatigued. Based on this, a warning message will be generated and sent to the driver via the device's display and speaker, stating, "Signs of drowsiness at the wheel have been detected. Please take a break immediately."

[0749] Example prompt for a generative AI model:

[0750] "It captures the driver's face and analyzes their behavior in real time, including blinking frequency, gaze direction, and facial expressions. If an abnormality is detected, it generates an appropriate warning message and displays it on the device."

[0751] In this way, this system prevents drivers from falling asleep or being careless while driving, and supports health management.

[0752] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0753] Step 1:

[0754] Data collection

[0755] Processing performed by the device

[0756] An AI camera installed on the device captures the driver's face in real time, collecting data on the driver's facial movements, blink frequency, gaze direction, facial expressions, head position, and other specific behaviors.

[0757] Input: Driver image and motion data

[0758] Output: Collected image and behavioral data

[0759] Step 2:

[0760] Sending data

[0761] Processing performed by the device

[0762] The collected data is temporarily stored in the terminal and then transmitted to the server. Specifically, when a certain data buffer is filled, the terminal transmits the data to the server according to a data transmission protocol.

[0763] Input: Collected image and behavioral data

[0764] Output: Data sent to the server

[0765] Step 3:

[0766] Pretreatment

[0767] Processing performed by the server

[0768] The server preprocesses the data received from the device, including noise reduction, image correction, brightness and contrast adjustment, and facial position extraction.

[0769] Input: Image data and motion data sent from the device

[0770] Output: Preprocessed, high-quality data

[0771] Step 4:

[0772] Analysis and Emotion Recognition

[0773] Processing performed by the server

[0774] The preprocessed data is input into the generative AI's analysis engine and emotion engine. The analysis engine uses a neural network to detect signs of driver drowsiness or distraction, while the emotion engine recognizes the driver's emotional state (fatigue, stress, relaxation, etc.).

[0775] Input: Preprocessed, high-quality data

[0776] Output: Analysis of drowsy driving, distraction symptoms, and emotional state

[0777] Step 5:

[0778] Warning generation

[0779] Processing performed by the server

[0780] If an anomaly is detected based on the results of the analysis engine and emotion engine, the server generates a warning message, which is tailored to the driver's emotional state.

[0781] Input: Parsed result data

[0782] Output: Warning message

[0783] Step 6:

[0784] Warning display

[0785] Processing performed by the device

[0786] Methods for displaying the warning message received by the terminal from the server to the driver include displaying a text message on the display and an audio notification.

[0787] Input: The warning message sent by the server

[0788] Output: Warning message displayed by the driver

[0789] Through these steps, the system can prevent drowsy or inattentive driving, generate appropriate warnings and promptly notify the driver, and also manage the driver's health and emotional state in real time.

[0790] (Application example 2)

[0791] 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."

[0792] Conventional drowsy driving prevention systems have focused on capturing and analyzing the driver's face and movements, but have not yet reached the point of recognizing the driver's emotional state and health status in real time. As a result, it has been difficult to accurately grasp the driver's emotional state, such as distraction, fatigue, and stress, and provide appropriate warnings and notifications, resulting in issues that make it difficult to ensure sufficient safety. Therefore, the present invention aims to provide a system that recognizes not only signs of drowsy driving and distraction, but also the driver's emotional state in real time and provides appropriate warnings.

[0793] 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 a sensing means for capturing the driver's face and movements in real time, a processing means for preprocessing the data acquired from the sensing means, an analysis means for analyzing the data preprocessed by the processing means and detecting signs of the driver drowsing at the wheel or being distracted, an emotion recognition means for recognizing the driver's emotional state in real time by the analysis means, a warning generation means for generating a warning and sending it to a terminal when an abnormality is detected, and a display means for displaying the generated warning message. This makes it possible to prevent the driver from drowsing at the wheel or being distracted, and to provide an appropriate warning based on the driver's emotional state.

[0794] "Sensing means" refers to devices and technologies that capture the driver's face and movements in real time.

[0795] "Processing means" refers to devices and technologies that preprocess data acquired from the sensing means and perform noise removal and image correction.

[0796] "Analytical means" refers to devices and technologies that analyze pre-processed data to detect signs of driver drowsiness or distraction.

[0797] "Emotion recognition means" refers to devices and technologies that recognize the emotional state of a driver in real time from data obtained by the analysis means.

[0798] "Warning generation means" refers to a device or technology that generates a warning and sends it to a terminal when an abnormality is detected by the analysis means or emotion recognition means.

[0799] "Display means" refers to devices and techniques that display the generated warning message and notify the driver.

[0800] "Communication Means" refers to devices and technologies that communicate data in real time between the Sensing Means and the Analysis Means or Emotion Recognition Means.

[0801] "Audio output means" refers to a device and technology that notifies the driver of the generated warning message by voice.

[0802] The present invention is a system for preventing drowsiness and distraction at the wheel, and supports safe driving by monitoring the driver's health and emotional state in real time. The system includes the following components:

[0803] Sensing Method

[0804] This is a device that uses a camera installed on a terminal or vehicle (e.g., a smartphone or in-car camera) to capture the driver's face and movements in real time, collecting information such as the driver's facial expression, blink frequency, gaze direction, and head position.

[0805] Processing means

[0806] The server or device preprocesses the data acquired from the sensing means, including noise removal and image correction, to generate high-quality data that is useful for subsequent analysis.

[0807] analytical means

[0808] The preprocessed data is analyzed by the server. The data is input into an analysis engine that uses a generative AI model to detect signs of driver drowsiness or distraction in real time. For example, if a decrease in blinking frequency and fixed gaze are detected within a certain period of time, this is analyzed as a sign of drowsy driving.

[0809] emotion recognition means

[0810] Using another generative AI model, the emotion engine uses the data pre-processed by the processing means to recognize the driver's emotional state in real time, for example, whether the driver is tired, stressed or relaxed.

[0811] Warning generation means

[0812] If an abnormality is detected by the analysis or emotion recognition methods, the server automatically generates a warning message, such as "Signs of drowsy driving have been detected. Please take a break immediately." Additional advice based on the driver's emotional state may also be included.

[0813] communication means

[0814] It includes a communication device for communicating data in real time between the sensing means, processing means, analysis means, and emotion recognition means, allowing all data to be shared without delay, enabling rapid analysis and emotion recognition.

[0815] Display means

[0816] The generated warning message is displayed on the display screen of the terminal or on the head-mounted display. The warning may also be given by voice through the voice output means. This allows the driver to check the warning message and take appropriate action.

[0817] Hardware and software used

[0818] In this invention, specific hardware includes a camera (e.g., a smartphone camera or a car camera) and a head-mounted display, and software includes image processing using OpenCV and execution of generative AI models using TensorFlow and Keras.

[0819] Examples of concrete examples and prompts

[0820] A concrete example is the following prompt:

[0821] "If a driver exhibits a decrease in blinking rate and gaze fixation within a certain period of time, signs of drowsy driving are detected."

[0822] "A system that analyzes driver behavior data captured by a camera in smart glasses in real time to detect signs of drowsy driving or distraction."

[0823] This enables the system to optimize driver safety while driving and also improve the overall efficiency of operations.

[0824] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0825] Step 1:

[0826] The sensing means captures the driver's face and movements in real time. The input is camera footage, and the output is captured image data. A camera (e.g., a smartphone camera or an in-car camera) periodically captures images and sends them to a terminal.

[0827] Step 2:

[0828] The device preprocesses the image data acquired from the sensing means. The input is the captured image data, and the output is the preprocessed image data. Preprocessing includes noise removal, image correction, face detection, etc., and is performed using OpenCV.

[0829] Step 3:

[0830] The server inputs the preprocessed image data into the generative AI model. The input is the preprocessed image data, and the output is the analysis results. Using TensorFlow and Keras, the analysis engine analyzes the data to detect signs of driver drowsiness or distraction.

[0831] Step 4:

[0832] The server uses an emotion recognition means to recognize the driver's emotional state from the analysis results. The input is the analysis results, and the output is the data of the driver's emotional state. Another generative AI model is used to evaluate the driver's fatigue, stress, and relaxation states in real time.

[0833] Step 5:

[0834] The server generates a warning message based on the results of the analysis and emotion recognition. The input is data on the driver's emotional state, and the output is a warning message. The warning generation means automatically creates a warning message based on signs of drowsy driving and stress levels.

[0835] Step 6:

[0836] The server transmits the generated warning message to the terminal in real time. The input is the warning message, and the output is data communication to the terminal. The warning message is transmitted to the terminal without delay using the communication means.

[0837] Step 7:

[0838] The terminal notifies the driver of a warning message using a display means. The input is the received warning message, and the output is the displayed warning message. The warning message is displayed on a display or head-mounted display, and the driver is also notified by voice using a voice output means.

[0839] 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.

[0840] 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.

[0841] 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.

[0842] [Third embodiment]

[0843] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0844] 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.

[0845] 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).

[0846] 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.

[0847] 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.

[0848] 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).

[0849] 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.

[0850] 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.

[0851] 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.

[0852] 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.

[0853] 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.

[0854] 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."

[0855] The present invention provides a system for effectively preventing drowsy driving and inattentive driving by drivers engaged in the long-distance truck and transportation industries, and for managing the health status of the drivers. The system includes the following components:

[0856] 1. Sensor means

[0857] The sensor means installed in the terminal has the function of capturing the driver's face and movements in real time. Specifically, an AI camera installed in the vehicle continuously collects the driver's face, blink frequency, gaze direction, facial expression, head position, etc. This video data is very important as it will be analyzed in detail later.

[0858] 2. Processing means

[0859] The server pre-processes the data sent from the sensor means, including noise removal, image correction, and facial position information extraction, thereby improving the quality of the data input to the analysis means.

[0860] 3. Analysis method

[0861] The server then inputs the pre-processed data into the Generative AI's analysis engine, which uses neural networks to analyze the driver's facial expressions and movement patterns to detect signs of drowsiness or distraction. This analysis is performed in real time, and the results are available immediately.

[0862] 4. Warning generation means

[0863] If an abnormality is detected by the analysis means, the server generates a warning message, such as "Caution: Signs of drowsiness detected. Please take a break immediately." This message is sent to the terminal and notifies the driver.

[0864] 5. Means of communication

[0865] Data is communicated in real time between the sensor means and the analysis means. The communication means minimizes data delays and achieves high-speed data transfer.

[0866] 6. Display means

[0867] The warning message generated by the warning generating means is notified to the driver by the display means of the terminal, and the driver is required to check the displayed message and take appropriate action.

[0868] About program processing

[0869] Processing of Sensor Means

[0870] Processing performed by the device

[0871] An AI camera installed on the device captures the driver's face in real time and collects video data, which is temporarily stored on the device and then sequentially sent to a server.

[0872] Data Preprocessing

[0873] Processing performed by the server

[0874] The server preprocesses the data received from the device, removing noise and correcting images, generating high-quality data suitable for analysis.

[0875] Data analysis

[0876] Processing performed by the server

[0877] The server inputs the pre-processed data into an analytical engine using a generative AI neural network, which analyzes the driver's facial and movement patterns to detect signs of drowsiness or distraction in real time.

[0878] Generate warnings

[0879] Processing performed by the server

[0880] If the analysis engine detects any symptoms, the server will determine the abnormality and immediately generate a warning message, which will be sent to the device and also notified to the operation manager.

[0881] Displaying warnings

[0882] Processing performed by the device

[0883] The terminal receives a warning message from the server and displays it to the driver. It is also possible to alert the driver by using voice notifications, etc.

[0884] Specific examples

[0885] For example, if a driver's blinking frequency decreases and their gaze becomes fixed within a certain period of time, this data is sent from the sensor means to the server. The server preprocesses this data and inputs it into the analysis engine of the generation AI. If the analysis engine detects signs of drowsy driving, the server generates a warning message saying "Signs of drowsy driving have been detected. Please take a break" and sends it to the device. The device displays this warning message to warn the driver. The driver confirms this warning and takes an appropriate break to ensure safe driving.

[0886] In this way, the system of the present invention can prevent the driver from falling asleep or driving carelessly, and can appropriately manage the driver's health condition.

[0887] The processing flow will be explained below.

[0888] Step 1:

[0889] Terminal handling

[0890] An AI camera installed on the device captures the driver's face in real time and collects video data. Specifically, the camera captures video at 20 frames per second and detects blinking frequency, gaze direction, and facial orientation.

[0891] Step 2:

[0892] Terminal handling

[0893] The collected video data is temporarily stored in the internal memory, and when it reaches an appropriate buffer size, it is sent to the server in real time using a communication means.

[0894] Step 3:

[0895] Server Processing

[0896] The server decodes the video data received from the device and performs pre-processing, which includes noise reduction, image sharpening, cropping of necessary parts, etc.

[0897] Step 4:

[0898] Server Processing

[0899] The preprocessed data is input into the generative AI's analysis engine, which uses a neural network to analyze the driver's facial expressions and movement patterns, such as blink frequency, gaze direction, and head position, to detect signs of drowsiness or distraction.

[0900] Step 5:

[0901] Server Processing

[0902] If an abnormality is detected based on the analysis results, the server generates a warning message, such as "Warning: Signs of drowsiness detected. Please take a break immediately."

[0903] Step 6:

[0904] Server Processing

[0905] The generated warning message is sent to the device, and a notification is also sent to the operation manager via email or SMS.

[0906] Step 7:

[0907] Terminal handling

[0908] The device receives the warning message from the server and displays it to the driver. Specifically, the warning message is displayed on the display and, in some cases, an audio notification is also given.

[0909] Step 8:

[0910] User Action

[0911] The user (driver) checks the warning message. Based on the warning message, the driver takes appropriate action, such as stopping at a service area or rest area to take a break.

[0912] Step 9:

[0913] Server Processing

[0914] As a follow-up, the server continues to monitor the driver's condition using generative AI, and based on the analysis results, generates messages to provide additional rest advice or driving advice at the appropriate time.

[0915] Step 10:

[0916] Server Processing

[0917] The generated follow-up message is sent to the terminal.

[0918] Step 11:

[0919] Terminal handling

[0920] The device receives a follow-up message and displays it to the driver, such as "Please take a break at the next service area."

[0921] Through these steps, the system helps prevent drivers from falling asleep or becoming distracted, supporting their health and safe driving.

[0922] Example 1

[0923] 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."

[0924] There is a need to prevent drivers from falling asleep or becoming distracted while driving long distances and ensure safe driving, but conventional systems have had difficulty monitoring the driver's health condition in real time and issuing prompt warnings. In particular, there are challenges in accurately and promptly detecting abnormalities due to inadequate data quality and communication delays.

[0925] 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.

[0926] In this invention, the server includes a sensor means for capturing the face and movements of the driver in real time, a terminal for saving data acquired from the sensor means and transmitting it via a network, a processing means for pre-processing data received from the terminal, an analysis means for analyzing the data pre-processed by the processing means and detecting signs of the driver drowsing at the wheel or being distracted, and a warning generation means for generating a warning when an abnormality is detected by the analysis means and transmitting the warning to the terminal. This makes it possible to monitor the driver's health condition in real time and to quickly issue a warning when drowsing at the wheel or being distracted is detected.

[0927] The "sensor means" is a device for capturing the driver's face and movements in real time.

[0928] A "terminal" is a device that stores data acquired from a sensor means and transmits the data to a server via a network.

[0929] "Processing means" refers to functions and devices for pre-processing data received from a terminal.

[0930] "Analysis means" refers to functions and devices for analyzing the pre-processed data and detecting signs of driver drowsiness or distraction.

[0931] The "warning generation means" is a function and device for generating a warning when an abnormality is detected by the analysis means and transmitting the warning to the terminal.

[0932] "Communication means" refers to functions and devices for communicating data in real time between the sensor means and the analysis means.

[0933] The "display means" refers to a function and device for displaying the warning message generated by the warning generation means and notifying the driver.

[0934] "Audio notification means" refers to a function and device for conveying a warning message to the driver by voice.

[0935] The present invention provides a system for preventing drivers from falling asleep or becoming distracted while driving long distances and ensuring safe driving. The system includes a sensor means, a terminal, a processing means, an analysis means, a warning generation means, a communication means, a display means, and a voice notification means.

[0936] Sensor Means

[0937] Processing performed by the device

[0938] The sensor means includes an AI camera that captures the driver's face and movements in real time. Specific examples of the sensor means include the ability to continuously collect facial expressions, blink frequency, gaze direction, facial expressions, and head position. Based on this information, the device can instantly assess the driver's condition.

[0939] Terminal

[0940] Processing performed by the device

[0941] The terminal is a device that temporarily stores data acquired from the sensor means and transmits it to a server via a network. The network used is a high-speed, highly stable Wi-Fi 6 or 5G mobile network. The MQTT protocol is used for data compression and transmission. It also has a retransmission function and performs error handling to avoid transmission errors.

[0942] Processing means

[0943] Processing performed by the server

[0944] The server preprocesses the video data received from the device and improves the quality of the data by performing noise reduction and image correction. Gaussian blur is used for noise reduction, and a color correction algorithm is applied for image correction. Haarcascades is also used to extract face position information.

[0945] Analysis means

[0946] Processing performed by the server

[0947] The preprocessed data is then input into the generative AI model's analysis engine, which analyzes the driver's face and movement patterns using a convolutional neural network (CNN) based on ResNet50. This allows for real-time detection of signs of drowsiness or distraction.

[0948] Warning generation means

[0949] Processing performed by the server

[0950] If the analysis engine detects an abnormality, the server immediately generates a warning message, which includes specific instructions such as "Signs of drowsy driving have been detected. Please take a break." This message is sent to the device and also notifies the operation manager.

[0951] communication means

[0952] Processing performed by the device

[0953] It provides the functionality to communicate data between sensor means and analysis means in real time, minimizing data latency by using a high-performance communication protocol.

[0954] Display means

[0955] Processing performed by the device

[0956] The terminal receives warning messages from the server and displays them to the driver, including pop-up messages and warnings in the vehicle's infotainment system.

[0957] Audio notification means

[0958] Processing performed by the device

[0959] The device is equipped with a function to communicate warning messages to the driver by voice, allowing the driver to be warned by both visual and audible means.

[0960] Examples and prompts

[0961] For example, if a driver blinks less than five times in 30 seconds and their gaze is fixed in a certain direction while driving long distances, the AI ​​camera detects this and collects data. The collected data is sent to the server, where it undergoes preprocessing and is then input into the analysis engine of the generative AI model. If the analysis engine detects signs of drowsy driving, the server generates a warning message stating, "Signs of drowsy driving have been detected. Please take a break," and sends it to the device. The device then displays this warning message and notifies the driver via voice. The driver can then acknowledge this warning and take appropriate breaks to ensure safe driving.

[0962] Example prompts to input to a generative AI model:

[0963] "Please detect signs of drowsiness or distraction from facial video data of a driver while driving. Specifically, if the blinking frequency is less than five times in 30 seconds and the driver's gaze is fixed in a certain direction, please recognize this as a sign of drowsy driving and immediately generate a warning message."

[0964] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0965] Step 1:

[0966] Data collection by sensor means

[0967] This is a process performed by the device. An AI camera installed on the device captures the driver's face and movements in real time and collects video data. Specifically, the AI ​​camera analyzes frames per second to obtain data such as blink frequency, gaze direction, facial expressions, and head position. The input is a video of the driver's face, and the output is an analyzable data file.

[0968] Step 2:

[0969] Temporarily storing data and preparing it for transmission

[0970] This is a process performed by the device. The collected data is temporarily stored in the device. The stored data is compressed in preparation for transmission. Specifically, a compression algorithm is used to reduce the data size so that the video data can be uploaded to cloud storage. The input is the video data acquired from the sensor, and the output is a compressed data file.

[0971] Step 3:

[0972] Sending data

[0973] This is a process performed by the device. The saved data is sent to the server via the network. Wi-Fi 6 or 5G mobile networks are used as the communication method, and the MQTT protocol is used to minimize data delays. If data transmission fails, it is retransmitted. The input is a compressed data file, and the output is a notification of successful transmission to the server.

[0974] Step 4:

[0975] Data Preprocessing

[0976] This is a process performed by the server. The server preprocesses the video data received from the device, removing noise and correcting the image. Specifically, it uses Gaussian blur to remove noise and applies a color correction algorithm to improve image quality. It also uses Haarcascades to extract facial position information. The input is the video data received from the device, and the output is preprocessed, high-quality data.

[0977] Step 5:

[0978] Data analysis

[0979] This is a process performed by the server. The preprocessed data is input into the analysis engine of the generative AI model. The analysis engine uses a convolutional neural network (CNN) based on ResNet50 to analyze the driver's facial expressions and movement patterns. The analysis results detect signs of drowsiness or distraction. The input is preprocessed high-quality data, and the output is the analysis result, indicating whether or not there are any abnormalities.

[0980] Step 6:

[0981] Generate warnings

[0982] This is a process performed by the server. If an abnormality is detected by the analysis engine, the server immediately generates a warning message. The warning message contains specific instructions such as "Signs of drowsy driving have been detected. Please take a break." This message is sent to the terminal and also notified to the operation manager. The input is the abnormality detection notification as the analysis result, and the output is the generated warning message.

[0983] Step 7:

[0984] Warning display and notification

[0985] This is a process performed by the terminal. The terminal receives a warning message from the server and displays it on the driver's display, and also notifies the driver by voice. Specifically, a pop-up message appears on the terminal screen, and an audio warning is issued at the same time. The input is the warning message, and the output is a visual and audio notification to the driver.

[0986] (Application example 1)

[0987] 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."

[0988] Conventional systems designed to prevent drivers and operators from falling asleep or becoming distracted have limitations in their ability to effectively detect and warn in real time. In particular, in logistics centers and factories, where there are many operators, efficient monitoring is difficult, and improvements in work efficiency and safety are required. Another problem is that warnings are only transmitted visually, making them difficult to reliably reach the operators. The objective of this invention is to solve these issues and provide a safe and efficient work environment.

[0989] 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.

[0990] In this invention, the server includes a sensor means for capturing the face and movements of an operator in real time, a processing means for preprocessing data acquired from the sensor means, an analysis means for analyzing the data preprocessed by the processing means and detecting signs of drowsiness or distraction, a warning generation means for generating a warning and transmitting it to a terminal when an abnormality is detected by the analysis means, a display means for displaying the warning message generated by the warning generation means and notifying the operator, and a communication means for communicating data between the sensor means and the analysis means in real time, thereby making it possible to effectively detect drowsiness or distraction of an operator in real time and to convey a warning visually and audibly.

[0991] "Operator" refers to an employee who operates forklifts and other equipment at a logistics center or factory.

[0992] "Drowsiness" refers to a state in which a worker temporarily loses consciousness unintentionally, and is a factor that threatens safety, especially during work.

[0993] "Distraction" refers to a state in which one is not concentrating on a task, and is manifested by, for example, fixating one's gaze elsewhere.

[0994] "Sensor means" refers to a camera or other device for capturing the operator's face and movements in real time.

[0995] The "processing means" refers to hardware and software for preprocessing data acquired from the sensor means, and specifically refers to devices and programs that perform noise removal and image correction.

[0996] "Analysis means" refers to a generative AI engine or neural network that analyzes the data preprocessed by the processing means and detects signs of drowsiness or distraction.

[0997] The "warning generation means" refers to a system for generating a warning message and transmitting it to a terminal when an abnormality is detected by the analysis means.

[0998] The "display means" refers to a display or audio notification device for displaying the warning message generated by the warning generation means and notifying the operator.

[0999] "Communication means" refers to communication technologies such as Wi-Fi and Bluetooth that allow data to be transmitted in real time between the sensor means and the analysis means.

[1000] The present invention provides a system for detecting operator drowsiness or distraction in real time, and specific embodiments thereof are described below. The system aims to improve safety and efficiency in environments where many operators work, such as logistics centers and factories.

[1001] 1. System Configuration

[1002] The system includes the following components:

[1003] 1. Sensor means

[1004] A camera mounted on the smart glasses captures the operator's face and movements in real time, and this data is continuously captured while the operator is performing their task.

[1005] 2. Processing means

[1006] The data acquired from the sensor means is first pre-processed on the terminal, which includes noise removal and image correction to generate high-quality data.

[1007] 3. Analysis method

[1008] The pre-processed data is sent to a server where a generative AI engine runs, which uses neural networks to analyze the data and detect signs of operator drowsiness or distraction in real time.

[1009] 4. Warning generation means

[1010] If an abnormality is detected by the analysis means, the server immediately generates a warning message, which is sent to the operator's terminal.

[1011] 5. Display means

[1012] The warning message generated by the warning generating means is displayed on the display of the smart glasses and also uses audio notification to ensure awareness by the operator.

[1013] 6. Means of communication

[1014] Wi-Fi, Bluetooth, etc. are used to communicate data between the sensor means and the analysis means in real time, ensuring immediacy and efficiency of data.

[1015] 2. Program Overview

[1016] The server runs a program that integrates each of these means. Specifically, it receives video data from the smart glasses, preprocesses the data, analyzes it using a generative AI engine, and generates and displays warning messages as necessary.

[1017] Hardware and software used

[1018] Smart glasses: Devices worn by operators to capture their faces and movements (e.g., Garmin Varia Vision, Google Glass)

[1019] AI camera: a camera built into smart glasses

[1020] Neural Networks: Generative AI Engine with TensorFlow

[1021] Communication method: Wi-Fi and Bluetooth data communication technology

[1022] Server: A computer system for processing and analyzing data.

[1023] 3. Processing Details

[1024] Pretreatment

[1025] The device pre-processes the video data received from the smart glasses, including noise reduction and image correction, to produce high-quality data suitable for analysis.

[1026] Data analysis

[1027] The server feeds the pre-processed data into a generative AI engine, which uses neural networks to analyze the operator's facial expressions and movement patterns to detect signs of drowsiness or distraction.

[1028] Alert generation and display

[1029] If an abnormality is detected, the server generates a warning message and sends it to the terminal, which then displays the warning message on the smart glasses display and alerts the operator using audio notification.

[1030] Examples and prompts

[1031] For example, if an operator's blink rate decreases and their gaze becomes fixed over a certain period of time, the generative AI engine will detect signs of drowsiness from this data. In this case, the following prompt sentence will be input to the generative AI model:

[1032] "The operator blinks less frequently over a period of time, indicating a more fixed gaze. Use this data to detect signs of drowsy driving."

[1033] Analysis is performed based on this prompt text, and if an abnormality is detected, a warning message is generated stating, "Signs of drowsiness have been detected. Please take a break," and the operator is notified visually and audibly.

[1034] In this way, the system of the present invention can effectively detect operator drowsiness or distraction, providing a safe and efficient working environment.

[1035] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1036] Step 1:

[1037] Activating the sensor function

[1038] The smart glasses used by the user are turned on, and the built-in camera begins capturing the operator's face and movements in real time. The input is video data of the operator's face and movements, and the output is video data temporarily stored in the smart glasses.

[1039] Step 2:

[1040] Data Preprocessing

[1041] The device preprocesses the video data acquired from the smart glasses. The input is temporarily stored video data, and it performs noise removal, image correction, and facial position extraction. The output is high-quality video data suitable for analysis.

[1042] Step 3:

[1043] Sending data

[1044] The terminal transmits the preprocessed data to the server. The input is the preprocessed high-quality video data, which is transmitted to the server using a communication means. The output is the video data received by the server.

[1045] Step 4:

[1046] Data analysis

[1047] The server inputs the preprocessed data into a generative AI engine that analyzes the operator's face and movement patterns. The input is the data received by the server, which uses a neural network to analyze signs of drowsiness or distraction. The output is the analysis results.

[1048] Step 5:

[1049] Anomaly detection and alert generation

[1050] If an abnormality is detected based on the analysis results, the server generates a warning message. The input is the analysis results, and the server generates a warning message based on the detected abnormality (e.g., drowsiness or distraction). The output is the generated warning message.

[1051] Step 6:

[1052] Sending a warning message

[1053] The server sends the generated warning message to the terminal. The input is the generated warning message, which is sent to the terminal using a communication means. The output is the warning message received by the terminal.

[1054] Step 7:

[1055] Displaying a warning message

[1056] The terminal displays the received warning message using the smart glasses' display and audio notification function. The input is the warning message received by the terminal and notifies the user through visual and audio. The output is the warning information conveyed to the operator.

[1057] Specifically, if the operator's blinking frequency decreases and their gaze becomes fixed within a certain period of time, the server inputs the following prompt sentence into the generative AI model: "The operator's blinking frequency decreases over a certain period of time, indicating that their gaze is fixed. Please use this data to detect signs of drowsy driving." If signs of drowsiness are detected, the smart glasses' display will display "Signs of drowsiness have been detected. Please take a break." and an audio notification will also be given.

[1058] 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.

[1059] The present invention provides a system for effectively preventing drowsy driving and distracted driving of drivers in the long-distance trucking and transportation industries, and managing the health and emotional state of the driver. The system includes the following components:

[1060] 1. Sensor means

[1061] The sensor means installed in the device has the function of capturing the driver's face and movements in real time. Specifically, an AI camera installed in the vehicle continuously collects the driver's face, blink frequency, gaze direction, facial expression, head position, etc. This data is used for analysis to detect drowsy driving and distraction, as well as for the emotion engine.

[1062] 2. Processing means

[1063] The server pre-processes the data sent by the sensor means, including noise removal, image correction, and facial location extraction, to improve the quality of the data provided to the subsequent analysis means and emotion engine.

[1064] 3. Analysis method

[1065] The server inputs the preprocessed data into the generative AI's analysis engine, which uses a neural network to analyze the driver's facial expressions and movement patterns. This analysis detects signs of driver drowsiness or distraction in real time.

[1066] 4. Emotion Engine

[1067] Furthermore, the server is equipped with an emotion engine that detects the driver's emotional state using the data preprocessed by the processing means, and analyzes the driver's emotions, such as tiredness, stress, and relaxation, in real time.

[1068] 5. Alert generation means

[1069] If an abnormality is detected by the analysis means or emotion engine, the server generates a warning message. The content of the generated warning message is adjusted based on the driver's emotional state. For example, if the driver is feeling stressed, a warning message urging them to relax is generated.

[1070] 6. Means of communication

[1071] It also includes a communication means for communicating data in real time between the sensor means, processing means, analysis means, and emotion engine, so that all data is shared without delay, enabling rapid analysis and emotion recognition.

[1072] 7. Display means

[1073] The warning message generated by the warning generating means is notified to the driver by the display means of the terminal, and the driver can check the displayed message and take appropriate action.

[1074] About program processing

[1075] Processing of Sensor Means

[1076] Processing performed by the device

[1077] An AI camera installed on the device captures the driver's face in real time and collects data on their movements and facial expressions. This data is temporarily stored on the device and then sequentially sent to a server.

[1078] Data Preprocessing

[1079] Processing performed by the server

[1080] The server preprocesses the data received from the device, removing noise and correcting the image, resulting in high-quality data.

[1081] Data Analysis and Emotion Recognition

[1082] Processing performed by the server

[1083] The preprocessed data is input into an analysis engine and emotion engine powered by generative AI. The analysis engine detects signs of driver drowsiness or distraction, while the emotion engine recognizes the driver's emotional state. For example, if a driver's blinking rate decreases and their gaze becomes fixed within a certain period of time, the analysis engine will detect signs of drowsiness, and the emotion engine will recognize that the driver is fatigued.

[1084] Generate warnings

[1085] Processing performed by the server

[1086] Based on the results of the analysis and emotion recognition, if an abnormality is detected or a specific emotional state is identified, the server will generate a warning message, such as "Signs of drowsy driving detected. Please take a break immediately," and may also include additional advice depending on the driver's emotional state.

[1087] Displaying warnings

[1088] Processing performed by the device

[1089] The terminal receives a warning message from the server and displays it to the driver. For example, the warning message is displayed on the screen and an audio notification is also provided.

[1090] In this way, the system of the present invention supports safe driving and health management by implementing measures that take into account the driver's drowsy driving, careless driving, and even emotional state.

[1091] The processing flow will be explained below.

[1092] Step 1:

[1093] Terminal handling

[1094] An AI camera installed on the device captures the driver's face in real time and collects video data. Specifically, the camera captures video at 20 frames per second and detects blinking frequency, gaze direction, and facial orientation.

[1095] Step 2:

[1096] Terminal handling

[1097] The collected video data is temporarily stored in the internal memory, and when it reaches an appropriate buffer size, it is sent to the server in real time using a communication means.

[1098] Step 3:

[1099] Server Processing

[1100] The server decodes the video data received from the device and performs preprocessing, which includes noise reduction, image sharpening, cropping of necessary areas, etc. It also performs preprocessing such as extracting facial position information and the number of blinks.

[1101] Step 4:

[1102] Server Processing

[1103] The preprocessed data is input into the generative AI's analysis engine, which uses a neural network to analyze the driver's facial expressions and movement patterns. This analysis detects signs of drowsiness or distraction based on factors such as blink frequency and gaze direction.

[1104] Step 5:

[1105] Server Processing

[1106] The analyzed data is also sent to the emotion engine in parallel, which infers the driver's emotional state from facial expression changes and movements to determine whether the driver is tired, stressed, relaxed, etc.

[1107] Step 6:

[1108] Server Processing

[1109] If an abnormality is detected by the analysis means or emotion engine, the server generates a warning message. At this time, the content of the warning message is adjusted based on the driver's emotional state recognized by the emotion engine. For example, if the driver is fatigued, the message generated will read, "Signs of drowsy driving have been detected. Please take a break immediately."

[1110] Step 7:

[1111] Server Processing

[1112] The generated warning message is sent to the device, and a notification is also sent to the operation manager via email or SMS at the same time.

[1113] Step 8:

[1114] Terminal handling

[1115] The terminal receives warning messages from the server and displays them to the driver. Specifically, the warning message is displayed on the display and, if necessary, an audio notification is also provided.

[1116] Step 9:

[1117] User Action

[1118] The user (driver) checks the warning message and takes appropriate action, such as stopping at a service area or rest area to take a break.

[1119] Step 10:

[1120] Server Processing

[1121] As a follow-up, the server continues to monitor the driver's state using generative AI and emotion engines, and generates messages based on the analysis results to provide additional rest advice or driving advice at the appropriate time.

[1122] Step 11:

[1123] Server Processing

[1124] The generated follow-up message is sent to the terminal, for example, a message such as "Please take a break at the next service area."

[1125] Step 12:

[1126] Terminal handling

[1127] The device receives the follow-up message and displays it to the driver, who is expected to take appropriate driving actions based on it.

[1128] This system effectively prevents drivers from falling asleep or becoming distracted, and supports comprehensive safe driving by taking into account the driver's health and emotional state.

[1129] Example 2

[1130] 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."

[1131] The purpose of this invention is to provide a system that can effectively prevent drowsy driving and inattentive driving of drivers engaged in long-distance trucking and transportation businesses, and can also manage the health and emotional state of drivers in real time, thereby reducing traffic accidents and maintaining the health of drivers.

[1132] 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.

[1133] In this invention, the server includes a sensor means for capturing the driver's face and movements in real time, an information processing means for preprocessing the data acquired from the sensor means, and an analysis means for analyzing the data preprocessed by the processing means to detect signs of the driver's drowsiness or distraction and their emotional state. This makes it possible to detect signs of the driver's drowsiness or distraction early and generate appropriate warnings to notify the driver. Furthermore, detecting the driver's emotional state makes it possible to manage the driver's stress and fatigue in real time.

[1134] The "sensor means" is a device that captures the driver's face and movements in real time and collects data such as blink frequency, gaze direction, facial expression, and head position.

[1135] "Information processing means" refers to a device or program for preprocessing data acquired from the sensor means, specifically performing noise removal, image correction, extraction of facial position information, etc.

[1136] "Analysis means" refers to devices or programs that analyze pre-processed data using an analytical engine and emotion engine powered by generative AI to detect signs of drowsiness or distraction in the driver and their emotional state.

[1137] The "warning generation means" is a device or program that generates a warning message and notifies the driver when an abnormality is detected by the analysis means.

[1138] The "communication means" is a device for communicating data in real time between the sensor means, the information processing means, the analysis means, and the emotion engine.

[1139] The "display means" is a device for displaying and notifying the driver of the warning message generated by the warning generation means.

[1140] The present invention provides a system for effectively preventing drowsy driving and inattentive driving of drivers engaged in long-distance trucking and transportation businesses, and for managing the health and emotional state of the driver in real time. Specific embodiments of the system are described below.

[1141] 1. Sensor means

[1142] Processing performed by the device

[1143] The device is equipped with an AI camera that captures the driver's face and movements in real time. The AI ​​camera monitors blinking frequency, gaze direction, facial expressions, head position, and other data in real time, collecting this data. The collected data is temporarily stored in the device and then sequentially sent to a server.

[1144] 2. Data Preprocessing

[1145] Processing performed by the server

[1146] The server receives the data sent from the device and performs noise reduction and image correction using software such as OpenCV and Python scripts. Preprocessing includes noise reduction, adjusting image brightness and contrast, and extracting facial position information.

[1147] 3. Data Analysis and Emotion Recognition

[1148] Processing performed by the server

[1149] The preprocessed data is input into an analysis engine and emotion engine using generative AI. Specific software used is TensorFlow and Keras. The analysis engine uses a neural network to analyze the driver's facial expressions and movement patterns to detect signs of drowsiness or distraction in real time. The emotion engine also recognizes the driver's emotional state (fatigue, stress, relaxation, etc.). The driver's condition is determined based on the results of this analysis.

[1150] 4. Warning generation means

[1151] Processing performed by the server

[1152] If the server detects an abnormality based on the results of the analysis engine and emotion engine, it generates a warning message for the driver. The generated warning message is adjusted based on the driver's emotional state. For example, it may include a warning such as "Signs of drowsy driving have been detected. Please take a break immediately" or advice such as "Fatigue has been detected. Please take a deep breath to promote relaxation."

[1153] 5. Warning Display

[1154] Processing performed by the device

[1155] The terminal receives warning messages from the server and displays them to the driver, either as a text message on the display or as a voice notification, allowing the driver to check the message and take appropriate action.

[1156] 6. Means of communication

[1157] It includes a means for communicating data in real time between the sensor means, information processing means, analysis means, and emotion engine, which allows all data to be shared without delay, enabling rapid analysis and emotion recognition.

[1158] Examples of concrete examples and prompts

[1159] For example, if a driver's blinking rate decreases and their gaze becomes fixed within a certain period of time, the analysis engine will detect signs of drowsiness while the emotion engine will recognize that the driver is fatigued. Based on this, a warning message will be generated and sent to the driver via the device's display and speaker, stating, "Signs of drowsiness at the wheel have been detected. Please take a break immediately."

[1160] Example prompt for a generative AI model:

[1161] "It captures the driver's face and analyzes their behavior in real time, including blinking frequency, gaze direction, and facial expressions. If an abnormality is detected, it generates an appropriate warning message and displays it on the device."

[1162] In this way, this system prevents drivers from falling asleep or being careless while driving, and supports health management.

[1163] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1164] Step 1:

[1165] Data collection

[1166] Processing performed by the device

[1167] An AI camera installed on the device captures the driver's face in real time, collecting data on the driver's facial movements, blink frequency, gaze direction, facial expressions, head position, and other specific behaviors.

[1168] Input: Driver image and motion data

[1169] Output: Collected image and behavioral data

[1170] Step 2:

[1171] Sending data

[1172] Processing performed by the device

[1173] The collected data is temporarily stored in the terminal and then transmitted to the server. Specifically, when a certain data buffer is filled, the terminal transmits the data to the server according to a data transmission protocol.

[1174] Input: Collected image and behavioral data

[1175] Output: Data sent to the server

[1176] Step 3:

[1177] Pretreatment

[1178] Processing performed by the server

[1179] The server preprocesses the data received from the device, including noise reduction, image correction, brightness and contrast adjustment, and facial position extraction.

[1180] Input: Image data and motion data sent from the device

[1181] Output: Preprocessed, high-quality data

[1182] Step 4:

[1183] Analysis and Emotion Recognition

[1184] Processing performed by the server

[1185] The preprocessed data is input into the generative AI's analysis engine and emotion engine. The analysis engine uses a neural network to detect signs of driver drowsiness or distraction, while the emotion engine recognizes the driver's emotional state (fatigue, stress, relaxation, etc.).

[1186] Input: Preprocessed, high-quality data

[1187] Output: Analysis of drowsy driving, distraction symptoms, and emotional state

[1188] Step 5:

[1189] Warning generation

[1190] Processing performed by the server

[1191] If an anomaly is detected based on the results of the analysis engine and emotion engine, the server generates a warning message, which is tailored to the driver's emotional state.

[1192] Input: Parsed result data

[1193] Output: Warning message

[1194] Step 6:

[1195] Warning display

[1196] Processing performed by the device

[1197] Methods for displaying the warning message received by the terminal from the server to the driver include displaying a text message on the display and an audio notification.

[1198] Input: The warning message sent by the server

[1199] Output: Warning message displayed by the driver

[1200] Through these steps, the system can prevent drowsy or inattentive driving, generate appropriate warnings and promptly notify the driver, and also manage the driver's health and emotional state in real time.

[1201] (Application example 2)

[1202] 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."

[1203] Conventional drowsy driving prevention systems have focused on capturing and analyzing the driver's face and movements, but have not yet reached the point of recognizing the driver's emotional state and health status in real time. As a result, it has been difficult to accurately grasp the driver's emotional state, such as distraction, fatigue, and stress, and provide appropriate warnings and notifications, resulting in issues that make it difficult to ensure sufficient safety. Therefore, the present invention aims to provide a system that recognizes not only signs of drowsy driving and distraction, but also the driver's emotional state in real time and provides appropriate warnings.

[1204] 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 a sensing means for capturing the driver's face and movements in real time, a processing means for preprocessing the data acquired from the sensing means, an analysis means for analyzing the data preprocessed by the processing means and detecting signs of the driver drowsing at the wheel or being distracted, an emotion recognition means for recognizing the driver's emotional state in real time by the analysis means, a warning generation means for generating a warning and sending it to a terminal when an abnormality is detected, and a display means for displaying the generated warning message. This makes it possible to prevent the driver from drowsing at the wheel or being distracted, and to provide an appropriate warning based on the driver's emotional state.

[1205] "Sensing means" refers to devices and technologies that capture the driver's face and movements in real time.

[1206] "Processing means" refers to devices and technologies that preprocess data acquired from the sensing means and perform noise removal and image correction.

[1207] "Analytical means" refers to devices and technologies that analyze pre-processed data to detect signs of driver drowsiness or distraction.

[1208] "Emotion recognition means" refers to devices and technologies that recognize the emotional state of a driver in real time from data obtained by the analysis means.

[1209] "Warning generation means" refers to a device or technology that generates a warning and sends it to a terminal when an abnormality is detected by the analysis means or emotion recognition means.

[1210] "Display means" refers to devices and techniques that display the generated warning message and notify the driver.

[1211] "Communication Means" refers to devices and technologies that communicate data in real time between the Sensing Means and the Analysis Means or Emotion Recognition Means.

[1212] "Audio output means" refers to a device and technology that notifies the driver of the generated warning message by voice.

[1213] The present invention is a system for preventing drowsiness and distraction at the wheel, and supports safe driving by monitoring the driver's health and emotional state in real time. The system includes the following components:

[1214] Sensing Method

[1215] This is a device that uses a camera installed on a terminal or vehicle (e.g., a smartphone or in-car camera) to capture the driver's face and movements in real time, collecting information such as the driver's facial expression, blink frequency, gaze direction, and head position.

[1216] Processing means

[1217] The server or device preprocesses the data acquired from the sensing means, including noise removal and image correction, to generate high-quality data that is useful for subsequent analysis.

[1218] analytical means

[1219] The preprocessed data is analyzed by the server. The data is input into an analysis engine that uses a generative AI model to detect signs of driver drowsiness or distraction in real time. For example, if a decrease in blinking frequency and fixed gaze are detected within a certain period of time, this is analyzed as a sign of drowsy driving.

[1220] emotion recognition means

[1221] Using another generative AI model, the emotion engine uses the data pre-processed by the processing means to recognize the driver's emotional state in real time, for example, whether the driver is tired, stressed or relaxed.

[1222] Warning generation means

[1223] If an abnormality is detected by the analysis or emotion recognition methods, the server automatically generates a warning message, such as "Signs of drowsy driving have been detected. Please take a break immediately." Additional advice based on the driver's emotional state may also be included.

[1224] communication means

[1225] It includes a communication device for communicating data in real time between the sensing means, processing means, analysis means, and emotion recognition means, allowing all data to be shared without delay, enabling rapid analysis and emotion recognition.

[1226] Display means

[1227] The generated warning message is displayed on the display screen of the terminal or on the head-mounted display. The warning may also be given by voice through the voice output means. This allows the driver to check the warning message and take appropriate action.

[1228] Hardware and software used

[1229] In this invention, specific hardware includes a camera (e.g., a smartphone camera or a car camera) and a head-mounted display, and software includes image processing using OpenCV and execution of generative AI models using TensorFlow and Keras.

[1230] Examples of concrete examples and prompts

[1231] A concrete example is the following prompt:

[1232] "If a driver exhibits a decrease in blinking rate and gaze fixation within a certain period of time, signs of drowsy driving are detected."

[1233] "A system that analyzes driver behavior data captured by a camera in smart glasses in real time to detect signs of drowsy driving or distraction."

[1234] This enables the system to optimize driver safety while driving and also improve the overall efficiency of operations.

[1235] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1236] Step 1:

[1237] The sensing means captures the driver's face and movements in real time. The input is camera footage, and the output is captured image data. A camera (e.g., a smartphone camera or an in-car camera) periodically captures images and sends them to a terminal.

[1238] Step 2:

[1239] The device preprocesses the image data acquired from the sensing means. The input is the captured image data, and the output is the preprocessed image data. Preprocessing includes noise removal, image correction, face detection, etc., and is performed using OpenCV.

[1240] Step 3:

[1241] The server inputs the preprocessed image data into the generative AI model. The input is the preprocessed image data, and the output is the analysis results. Using TensorFlow and Keras, the analysis engine analyzes the data to detect signs of driver drowsiness or distraction.

[1242] Step 4:

[1243] The server uses an emotion recognition means to recognize the driver's emotional state from the analysis results. The input is the analysis results, and the output is the data of the driver's emotional state. Another generative AI model is used to evaluate the driver's fatigue, stress, and relaxation states in real time.

[1244] Step 5:

[1245] The server generates a warning message based on the results of the analysis and emotion recognition. The input is data on the driver's emotional state, and the output is a warning message. The warning generation means automatically creates a warning message based on signs of drowsy driving and stress levels.

[1246] Step 6:

[1247] The server transmits the generated warning message to the terminal in real time. The input is the warning message, and the output is data communication to the terminal. The warning message is transmitted to the terminal without delay using the communication means.

[1248] Step 7:

[1249] The terminal notifies the driver of a warning message using a display means. The input is the received warning message, and the output is the displayed warning message. The warning message is displayed on a display or head-mounted display, and the driver is also notified by voice using a voice output means.

[1250] 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.

[1251] 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.

[1252] 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.

[1253] [Fourth embodiment]

[1254] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1255] 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.

[1256] 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).

[1257] 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.

[1258] 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.

[1259] 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).

[1260] 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.

[1261] 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.

[1262] 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.

[1263] 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.

[1264] 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.

[1265] 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.

[1266] 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."

[1267] The present invention provides a system for effectively preventing drowsy driving and inattentive driving by drivers engaged in the long-distance truck and transportation industries, and for managing the health status of the drivers. The system includes the following components:

[1268] 1. Sensor means

[1269] The sensor means installed in the terminal has the function of capturing the driver's face and movements in real time. Specifically, an AI camera installed in the vehicle continuously collects the driver's face, blink frequency, gaze direction, facial expression, head position, etc. This video data is very important as it will be analyzed in detail later.

[1270] 2. Processing means

[1271] The server pre-processes the data sent from the sensor means, including noise removal, image correction, and facial position information extraction, thereby improving the quality of the data input to the analysis means.

[1272] 3. Analysis method

[1273] The server then inputs the pre-processed data into the Generative AI's analysis engine, which uses neural networks to analyze the driver's facial expressions and movement patterns to detect signs of drowsiness or distraction. This analysis is performed in real time, and the results are available immediately.

[1274] 4. Warning generation means

[1275] If an abnormality is detected by the analysis means, the server generates a warning message, such as "Caution: Signs of drowsiness detected. Please take a break immediately." This message is sent to the terminal and notifies the driver.

[1276] 5. Means of communication

[1277] Data is communicated in real time between the sensor means and the analysis means. The communication means minimizes data delays and achieves high-speed data transfer.

[1278] 6. Display means

[1279] The warning message generated by the warning generating means is notified to the driver by the display means of the terminal, and the driver is required to check the displayed message and take appropriate action.

[1280] About program processing

[1281] Processing of Sensor Means

[1282] Processing performed by the device

[1283] An AI camera installed on the device captures the driver's face in real time and collects video data, which is temporarily stored on the device and then sequentially sent to a server.

[1284] Data Preprocessing

[1285] Processing performed by the server

[1286] The server preprocesses the data received from the device, removing noise and correcting images, generating high-quality data suitable for analysis.

[1287] Data analysis

[1288] Processing performed by the server

[1289] The server inputs the pre-processed data into an analytical engine using a generative AI neural network, which analyzes the driver's facial and movement patterns to detect signs of drowsiness or distraction in real time.

[1290] Generate warnings

[1291] Processing performed by the server

[1292] If the analysis engine detects any symptoms, the server will determine the abnormality and immediately generate a warning message, which will be sent to the device and also notified to the operation manager.

[1293] Displaying warnings

[1294] Processing performed by the device

[1295] The terminal receives a warning message from the server and displays it to the driver. It is also possible to alert the driver by using voice notifications, etc.

[1296] Specific examples

[1297] For example, if a driver's blinking frequency decreases and their gaze becomes fixed within a certain period of time, this data is sent from the sensor means to the server. The server preprocesses this data and inputs it into the analysis engine of the generation AI. If the analysis engine detects signs of drowsy driving, the server generates a warning message saying "Signs of drowsy driving have been detected. Please take a break" and sends it to the device. The device displays this warning message to warn the driver. The driver confirms this warning and takes an appropriate break to ensure safe driving.

[1298] In this way, the system of the present invention can prevent the driver from falling asleep or driving carelessly, and can appropriately manage the driver's health condition.

[1299] The processing flow will be explained below.

[1300] Step 1:

[1301] Terminal handling

[1302] An AI camera installed on the device captures the driver's face in real time and collects video data. Specifically, the camera captures video at 20 frames per second and detects blinking frequency, gaze direction, and facial orientation.

[1303] Step 2:

[1304] Terminal handling

[1305] The collected video data is temporarily stored in the internal memory, and when it reaches an appropriate buffer size, it is sent to the server in real time using a communication means.

[1306] Step 3:

[1307] Server Processing

[1308] The server decodes the video data received from the device and performs pre-processing, which includes noise reduction, image sharpening, cropping of necessary parts, etc.

[1309] Step 4:

[1310] Server Processing

[1311] The preprocessed data is input into the generative AI's analysis engine, which uses a neural network to analyze the driver's facial expressions and movement patterns, such as blink frequency, gaze direction, and head position, to detect signs of drowsiness or distraction.

[1312] Step 5:

[1313] Server Processing

[1314] If an abnormality is detected based on the analysis results, the server generates a warning message, such as "Warning: Signs of drowsiness detected. Please take a break immediately."

[1315] Step 6:

[1316] Server Processing

[1317] The generated warning message is sent to the device, and a notification is also sent to the operation manager via email or SMS.

[1318] Step 7:

[1319] Terminal handling

[1320] The device receives the warning message from the server and displays it to the driver. Specifically, the warning message is displayed on the display and, in some cases, an audio notification is also given.

[1321] Step 8:

[1322] User Action

[1323] The user (driver) checks the warning message. Based on the warning message, the driver takes appropriate action, such as stopping at a service area or rest area to take a break.

[1324] Step 9:

[1325] Server Processing

[1326] As a follow-up, the server continues to monitor the driver's condition using generative AI, and based on the analysis results, generates messages to provide additional rest advice or driving advice at the appropriate time.

[1327] Step 10:

[1328] Server Processing

[1329] The generated follow-up message is sent to the terminal.

[1330] Step 11:

[1331] Terminal handling

[1332] The device receives a follow-up message and displays it to the driver, such as "Please take a break at the next service area."

[1333] Through these steps, the system helps prevent drivers from falling asleep or becoming distracted, supporting their health and safe driving.

[1334] Example 1

[1335] 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."

[1336] There is a need to prevent drivers from falling asleep or becoming distracted while driving long distances and ensure safe driving, but conventional systems have had difficulty monitoring the driver's health condition in real time and issuing prompt warnings. In particular, there are challenges in accurately and promptly detecting abnormalities due to inadequate data quality and communication delays.

[1337] 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.

[1338] In this invention, the server includes a sensor means for capturing the face and movements of the driver in real time, a terminal for saving data acquired from the sensor means and transmitting it via a network, a processing means for pre-processing data received from the terminal, an analysis means for analyzing the data pre-processed by the processing means and detecting signs of the driver drowsing at the wheel or being distracted, and a warning generation means for generating a warning when an abnormality is detected by the analysis means and transmitting the warning to the terminal. This makes it possible to monitor the driver's health condition in real time and to quickly issue a warning when drowsing at the wheel or being distracted is detected.

[1339] The "sensor means" is a device for capturing the driver's face and movements in real time.

[1340] A "terminal" is a device that stores data acquired from a sensor means and transmits the data to a server via a network.

[1341] "Processing means" refers to functions and devices for pre-processing data received from a terminal.

[1342] "Analysis means" refers to functions and devices for analyzing the pre-processed data and detecting signs of driver drowsiness or distraction.

[1343] The "warning generation means" is a function and device for generating a warning when an abnormality is detected by the analysis means and transmitting the warning to the terminal.

[1344] "Communication means" refers to functions and devices for communicating data in real time between the sensor means and the analysis means.

[1345] The "display means" refers to a function and device for displaying the warning message generated by the warning generation means and notifying the driver.

[1346] "Audio notification means" refers to a function and device for conveying a warning message to the driver by voice.

[1347] The present invention provides a system for preventing drivers from falling asleep or becoming distracted while driving long distances and ensuring safe driving. The system includes a sensor means, a terminal, a processing means, an analysis means, a warning generation means, a communication means, a display means, and a voice notification means.

[1348] Sensor Means

[1349] Processing performed by the device

[1350] The sensor means includes an AI camera that captures the driver's face and movements in real time. Specific examples of the sensor means include the ability to continuously collect facial expressions, blink frequency, gaze direction, facial expressions, and head position. Based on this information, the device can instantly assess the driver's condition.

[1351] Terminal

[1352] Processing performed by the device

[1353] The terminal is a device that temporarily stores data acquired from the sensor means and transmits it to a server via a network. The network used is a high-speed, highly stable Wi-Fi 6 or 5G mobile network. The MQTT protocol is used for data compression and transmission. It also has a retransmission function and performs error handling to avoid transmission errors.

[1354] Processing means

[1355] Processing performed by the server

[1356] The server preprocesses the video data received from the device and improves the quality of the data by performing noise reduction and image correction. Gaussian blur is used for noise reduction, and a color correction algorithm is applied for image correction. Haarcascades is also used to extract face position information.

[1357] Analysis means

[1358] Processing performed by the server

[1359] The preprocessed data is then input into the generative AI model's analysis engine, which analyzes the driver's face and movement patterns using a convolutional neural network (CNN) based on ResNet50. This allows for real-time detection of signs of drowsiness or distraction.

[1360] Warning generation means

[1361] Processing performed by the server

[1362] If the analysis engine detects an abnormality, the server immediately generates a warning message, which includes specific instructions such as "Signs of drowsy driving have been detected. Please take a break." This message is sent to the device and also notifies the operation manager.

[1363] communication means

[1364] Processing performed by the device

[1365] It provides the functionality to communicate data between sensor means and analysis means in real time, minimizing data latency by using a high-performance communication protocol.

[1366] Display means

[1367] Processing performed by the device

[1368] The terminal receives warning messages from the server and displays them to the driver, including pop-up messages and warnings in the vehicle's infotainment system.

[1369] Audio notification means

[1370] Processing performed by the device

[1371] The device is equipped with a function to communicate warning messages to the driver by voice, allowing the driver to be warned by both visual and audible means.

[1372] Examples and prompts

[1373] For example, if a driver blinks less than five times in 30 seconds and their gaze is fixed in a certain direction while driving long distances, the AI ​​camera detects this and collects data. The collected data is sent to the server, where it undergoes preprocessing and is then input into the analysis engine of the generative AI model. If the analysis engine detects signs of drowsy driving, the server generates a warning message stating, "Signs of drowsy driving have been detected. Please take a break," and sends it to the device. The device then displays this warning message and notifies the driver via voice. The driver can then acknowledge this warning and take appropriate breaks to ensure safe driving.

[1374] Example prompts to input to a generative AI model:

[1375] "Please detect signs of drowsiness or distraction from facial video data of a driver while driving. Specifically, if the blinking frequency is less than five times in 30 seconds and the driver's gaze is fixed in a certain direction, please recognize this as a sign of drowsy driving and immediately generate a warning message."

[1376] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1377] Step 1:

[1378] Data collection by sensor means

[1379] This is a process performed by the device. An AI camera installed on the device captures the driver's face and movements in real time and collects video data. Specifically, the AI ​​camera analyzes frames per second to obtain data such as blink frequency, gaze direction, facial expressions, and head position. The input is a video of the driver's face, and the output is an analyzable data file.

[1380] Step 2:

[1381] Temporarily storing data and preparing it for transmission

[1382] This is a process performed by the device. The collected data is temporarily stored in the device. The stored data is compressed in preparation for transmission. Specifically, a compression algorithm is used to reduce the data size so that the video data can be uploaded to cloud storage. The input is the video data acquired from the sensor, and the output is a compressed data file.

[1383] Step 3:

[1384] Sending data

[1385] This is a process performed by the device. The saved data is sent to the server via the network. Wi-Fi 6 or 5G mobile networks are used as the communication method, and the MQTT protocol is used to minimize data delays. If data transmission fails, it is retransmitted. The input is a compressed data file, and the output is a notification of successful transmission to the server.

[1386] Step 4:

[1387] Data Preprocessing

[1388] This is a process performed by the server. The server preprocesses the video data received from the device, removing noise and correcting the image. Specifically, it uses Gaussian blur to remove noise and applies a color correction algorithm to improve image quality. It also uses Haarcascades to extract facial position information. The input is the video data received from the device, and the output is preprocessed, high-quality data.

[1389] Step 5:

[1390] Data analysis

[1391] This is a process performed by the server. The preprocessed data is input into the analysis engine of the generative AI model. The analysis engine uses a convolutional neural network (CNN) based on ResNet50 to analyze the driver's facial expressions and movement patterns. The analysis results detect signs of drowsiness or distraction. The input is preprocessed high-quality data, and the output is the analysis result, indicating whether or not there are any abnormalities.

[1392] Step 6:

[1393] Generate warnings

[1394] This is a process performed by the server. If an abnormality is detected by the analysis engine, the server immediately generates a warning message. The warning message contains specific instructions such as "Signs of drowsy driving have been detected. Please take a break." This message is sent to the terminal and also notified to the operation manager. The input is the abnormality detection notification as the analysis result, and the output is the generated warning message.

[1395] Step 7:

[1396] Warning display and notification

[1397] This is a process performed by the terminal. The terminal receives a warning message from the server and displays it on the driver's display, and also notifies the driver by voice. Specifically, a pop-up message appears on the terminal screen, and an audio warning is issued at the same time. The input is the warning message, and the output is a visual and audio notification to the driver.

[1398] (Application example 1)

[1399] 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."

[1400] Conventional systems designed to prevent drivers and operators from falling asleep or becoming distracted have limitations in their ability to effectively detect and warn in real time. In particular, in logistics centers and factories, where there are many operators, efficient monitoring is difficult, and improvements in work efficiency and safety are required. Another problem is that warnings are only transmitted visually, making them difficult to reliably reach the operators. The objective of this invention is to solve these issues and provide a safe and efficient work environment.

[1401] 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.

[1402] In this invention, the server includes a sensor means for capturing the face and movements of an operator in real time, a processing means for preprocessing data acquired from the sensor means, an analysis means for analyzing the data preprocessed by the processing means and detecting signs of drowsiness or distraction, a warning generation means for generating a warning and transmitting it to a terminal when an abnormality is detected by the analysis means, a display means for displaying the warning message generated by the warning generation means and notifying the operator, and a communication means for communicating data between the sensor means and the analysis means in real time, thereby making it possible to effectively detect drowsiness or distraction of an operator in real time and to convey a warning visually and audibly.

[1403] "Operator" refers to an employee who operates forklifts and other equipment at a logistics center or factory.

[1404] "Drowsiness" refers to a state in which a worker temporarily loses consciousness unintentionally, and is a factor that threatens safety, especially during work.

[1405] "Distraction" refers to a state in which one is not concentrating on a task, and is manifested by, for example, fixating one's gaze elsewhere.

[1406] "Sensor means" refers to a camera or other device for capturing the operator's face and movements in real time.

[1407] The "processing means" refers to hardware and software for preprocessing data acquired from the sensor means, and specifically refers to devices and programs that perform noise removal and image correction.

[1408] "Analysis means" refers to a generative AI engine or neural network that analyzes the data preprocessed by the processing means and detects signs of drowsiness or distraction.

[1409] The "warning generation means" refers to a system for generating a warning message and transmitting it to a terminal when an abnormality is detected by the analysis means.

[1410] The "display means" refers to a display or audio notification device for displaying the warning message generated by the warning generation means and notifying the operator.

[1411] "Communication means" refers to communication technologies such as Wi-Fi and Bluetooth that allow data to be transmitted in real time between the sensor means and the analysis means.

[1412] The present invention provides a system for detecting operator drowsiness or distraction in real time, and specific embodiments thereof are described below. The system aims to improve safety and efficiency in environments where many operators work, such as logistics centers and factories.

[1413] 1. System Configuration

[1414] The system includes the following components:

[1415] 1. Sensor means

[1416] A camera mounted on the smart glasses captures the operator's face and movements in real time, and this data is continuously captured while the operator is performing their task.

[1417] 2. Processing means

[1418] The data acquired from the sensor means is first pre-processed on the terminal, which includes noise removal and image correction to generate high-quality data.

[1419] 3. Analysis method

[1420] The pre-processed data is sent to a server where a generative AI engine runs, which uses neural networks to analyze the data and detect signs of operator drowsiness or distraction in real time.

[1421] 4. Warning generation means

[1422] If an abnormality is detected by the analysis means, the server immediately generates a warning message, which is sent to the operator's terminal.

[1423] 5. Display means

[1424] The warning message generated by the warning generating means is displayed on the display of the smart glasses and also uses audio notification to ensure awareness by the operator.

[1425] 6. Means of communication

[1426] Wi-Fi, Bluetooth, etc. are used to communicate data between the sensor means and the analysis means in real time, ensuring immediacy and efficiency of data.

[1427] 2. Program Overview

[1428] The server runs a program that integrates each of these means. Specifically, it receives video data from the smart glasses, preprocesses the data, analyzes it using a generative AI engine, and generates and displays warning messages as necessary.

[1429] Hardware and software used

[1430] Smart glasses: Devices worn by operators to capture their faces and movements (e.g., Garmin Varia Vision, Google Glass)

[1431] AI camera: a camera built into smart glasses

[1432] Neural Networks: Generative AI Engine with TensorFlow

[1433] Communication method: Wi-Fi and Bluetooth data communication technology

[1434] Server: A computer system for processing and analyzing data.

[1435] 3. Processing Details

[1436] Pretreatment

[1437] The device pre-processes the video data received from the smart glasses, including noise reduction and image correction, to produce high-quality data suitable for analysis.

[1438] Data analysis

[1439] The server feeds the pre-processed data into a generative AI engine, which uses neural networks to analyze the operator's facial expressions and movement patterns to detect signs of drowsiness or distraction.

[1440] Alert generation and display

[1441] If an abnormality is detected, the server generates a warning message and sends it to the terminal, which then displays the warning message on the smart glasses display and alerts the operator using audio notification.

[1442] Examples and prompts

[1443] For example, if an operator's blink rate decreases and their gaze becomes fixed over a certain period of time, the generative AI engine will detect signs of drowsiness from this data. In this case, the following prompt sentence will be input to the generative AI model:

[1444] "The operator blinks less frequently over a period of time, indicating a more fixed gaze. Use this data to detect signs of drowsy driving."

[1445] Analysis is performed based on this prompt text, and if an abnormality is detected, a warning message is generated stating, "Signs of drowsiness have been detected. Please take a break," and the operator is notified visually and audibly.

[1446] In this way, the system of the present invention can effectively detect operator drowsiness or distraction, providing a safe and efficient working environment.

[1447] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1448] Step 1:

[1449] Activating the sensor function

[1450] The smart glasses used by the user are turned on, and the built-in camera begins capturing the operator's face and movements in real time. The input is video data of the operator's face and movements, and the output is video data temporarily stored in the smart glasses.

[1451] Step 2:

[1452] Data Preprocessing

[1453] The device preprocesses the video data acquired from the smart glasses. The input is temporarily stored video data, and it performs noise removal, image correction, and facial position extraction. The output is high-quality video data suitable for analysis.

[1454] Step 3:

[1455] Sending data

[1456] The terminal transmits the preprocessed data to the server. The input is the preprocessed high-quality video data, which is transmitted to the server using a communication means. The output is the video data received by the server.

[1457] Step 4:

[1458] Data analysis

[1459] The server inputs the preprocessed data into a generative AI engine that analyzes the operator's face and movement patterns. The input is the data received by the server, which uses a neural network to analyze signs of drowsiness or distraction. The output is the analysis results.

[1460] Step 5:

[1461] Anomaly detection and alert generation

[1462] If an abnormality is detected based on the analysis results, the server generates a warning message. The input is the analysis results, and the server generates a warning message based on the detected abnormality (e.g., drowsiness or distraction). The output is the generated warning message.

[1463] Step 6:

[1464] Sending a warning message

[1465] The server sends the generated warning message to the terminal. The input is the generated warning message, which is sent to the terminal using a communication means. The output is the warning message received by the terminal.

[1466] Step 7:

[1467] Displaying a warning message

[1468] The terminal displays the received warning message using the smart glasses' display and audio notification function. The input is the warning message received by the terminal and notifies the user through visual and audio. The output is the warning information conveyed to the operator.

[1469] Specifically, if the operator's blinking frequency decreases and their gaze becomes fixed within a certain period of time, the server inputs the following prompt sentence into the generative AI model: "The operator's blinking frequency decreases over a certain period of time, indicating that their gaze is fixed. Please use this data to detect signs of drowsy driving." If signs of drowsiness are detected, the smart glasses' display will display "Signs of drowsiness have been detected. Please take a break." and an audio notification will also be given.

[1470] 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.

[1471] The present invention provides a system for effectively preventing drowsy driving and distracted driving of drivers in the long-distance trucking and transportation industries, and managing the health and emotional state of the driver. The system includes the following components:

[1472] 1. Sensor means

[1473] The sensor means installed in the device has the function of capturing the driver's face and movements in real time. Specifically, an AI camera installed in the vehicle continuously collects the driver's face, blink frequency, gaze direction, facial expression, head position, etc. This data is used for analysis to detect drowsy driving and distraction, as well as for the emotion engine.

[1474] 2. Processing means

[1475] The server pre-processes the data sent by the sensor means, including noise removal, image correction, and facial location extraction, to improve the quality of the data provided to the subsequent analysis means and emotion engine.

[1476] 3. Analysis method

[1477] The server inputs the preprocessed data into the generative AI's analysis engine, which uses a neural network to analyze the driver's facial expressions and movement patterns. This analysis detects signs of driver drowsiness or distraction in real time.

[1478] 4. Emotion Engine

[1479] Furthermore, the server is equipped with an emotion engine that detects the driver's emotional state using the data preprocessed by the processing means, and analyzes the driver's emotions, such as tiredness, stress, and relaxation, in real time.

[1480] 5. Alert generation means

[1481] If an abnormality is detected by the analysis means or emotion engine, the server generates a warning message. The content of the generated warning message is adjusted based on the driver's emotional state. For example, if the driver is feeling stressed, a warning message urging them to relax is generated.

[1482] 6. Means of communication

[1483] It also includes a communication means for communicating data in real time between the sensor means, processing means, analysis means, and emotion engine, so that all data is shared without delay, enabling rapid analysis and emotion recognition.

[1484] 7. Display means

[1485] The warning message generated by the warning generating means is notified to the driver by the display means of the terminal, and the driver can check the displayed message and take appropriate action.

[1486] About program processing

[1487] Processing of Sensor Means

[1488] Processing performed by the device

[1489] An AI camera installed on the device captures the driver's face in real time and collects data on their movements and facial expressions. This data is temporarily stored on the device and then sequentially sent to a server.

[1490] Data Preprocessing

[1491] Processing performed by the server

[1492] The server preprocesses the data received from the device, removing noise and correcting the image, resulting in high-quality data.

[1493] Data Analysis and Emotion Recognition

[1494] Processing performed by the server

[1495] The preprocessed data is input into an analysis engine and emotion engine powered by generative AI. The analysis engine detects signs of driver drowsiness or distraction, while the emotion engine recognizes the driver's emotional state. For example, if a driver's blinking rate decreases and their gaze becomes fixed within a certain period of time, the analysis engine will detect signs of drowsiness, and the emotion engine will recognize that the driver is fatigued.

[1496] Generate warnings

[1497] Processing performed by the server

[1498] Based on the results of the analysis and emotion recognition, if an abnormality is detected or a specific emotional state is identified, the server will generate a warning message, such as "Signs of drowsy driving detected. Please take a break immediately," and may also include additional advice depending on the driver's emotional state.

[1499] Displaying warnings

[1500] Processing performed by the device

[1501] The terminal receives a warning message from the server and displays it to the driver. For example, the warning message is displayed on the screen and an audio notification is also provided.

[1502] In this way, the system of the present invention supports safe driving and health management by implementing measures that take into account the driver's drowsy driving, careless driving, and even emotional state.

[1503] The processing flow will be explained below.

[1504] Step 1:

[1505] Terminal handling

[1506] An AI camera installed on the device captures the driver's face in real time and collects video data. Specifically, the camera captures video at 20 frames per second and detects blinking frequency, gaze direction, and facial orientation.

[1507] Step 2:

[1508] Terminal handling

[1509] The collected video data is temporarily stored in the internal memory, and when it reaches an appropriate buffer size, it is sent to the server in real time using a communication means.

[1510] Step 3:

[1511] Server Processing

[1512] The server decodes the video data received from the device and performs preprocessing, which includes noise reduction, image sharpening, cropping of necessary areas, etc. It also performs preprocessing such as extracting facial position information and the number of blinks.

[1513] Step 4:

[1514] Server Processing

[1515] The preprocessed data is input into the generative AI's analysis engine, which uses a neural network to analyze the driver's facial expressions and movement patterns. This analysis detects signs of drowsiness or distraction based on factors such as blink frequency and gaze direction.

[1516] Step 5:

[1517] Server Processing

[1518] The analyzed data is also sent to the emotion engine in parallel, which infers the driver's emotional state from facial expression changes and movements to determine whether the driver is tired, stressed, relaxed, etc.

[1519] Step 6:

[1520] Server Processing

[1521] If an abnormality is detected by the analysis means or emotion engine, the server generates a warning message. At this time, the content of the warning message is adjusted based on the driver's emotional state recognized by the emotion engine. For example, if the driver is fatigued, the message generated will read, "Signs of drowsy driving have been detected. Please take a break immediately."

[1522] Step 7:

[1523] Server Processing

[1524] The generated warning message is sent to the device, and a notification is also sent to the operation manager via email or SMS at the same time.

[1525] Step 8:

[1526] Terminal handling

[1527] The terminal receives warning messages from the server and displays them to the driver. Specifically, the warning message is displayed on the display and, if necessary, an audio notification is also provided.

[1528] Step 9:

[1529] User Action

[1530] The user (driver) checks the warning message and takes appropriate action, such as stopping at a service area or rest area to take a break.

[1531] Step 10:

[1532] Server Processing

[1533] As a follow-up, the server continues to monitor the driver's state using generative AI and emotion engines, and generates messages based on the analysis results to provide additional rest advice or driving advice at the appropriate time.

[1534] Step 11:

[1535] Server Processing

[1536] The generated follow-up message is sent to the terminal, for example, a message such as "Please take a break at the next service area."

[1537] Step 12:

[1538] Terminal handling

[1539] The device receives the follow-up message and displays it to the driver, who is expected to take appropriate driving actions based on it.

[1540] This system effectively prevents drivers from falling asleep or becoming distracted, and supports comprehensive safe driving by taking into account the driver's health and emotional state.

[1541] Example 2

[1542] 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."

[1543] The purpose of this invention is to provide a system that can effectively prevent drowsy driving and inattentive driving of drivers engaged in long-distance trucking and transportation businesses, and can also manage the health and emotional state of drivers in real time, thereby reducing traffic accidents and maintaining the health of drivers.

[1544] 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.

[1545] In this invention, the server includes a sensor means for capturing the driver's face and movements in real time, an information processing means for preprocessing the data acquired from the sensor means, and an analysis means for analyzing the data preprocessed by the processing means to detect signs of the driver's drowsiness or distraction and their emotional state. This makes it possible to detect signs of the driver's drowsiness or distraction early and generate appropriate warnings to notify the driver. Furthermore, detecting the driver's emotional state makes it possible to manage the driver's stress and fatigue in real time.

[1546] The "sensor means" is a device that captures the driver's face and movements in real time and collects data such as blink frequency, gaze direction, facial expression, and head position.

[1547] "Information processing means" refers to a device or program for preprocessing data acquired from the sensor means, specifically performing noise removal, image correction, extraction of facial position information, etc.

[1548] "Analysis means" refers to devices or programs that analyze pre-processed data using an analytical engine and emotion engine powered by generative AI to detect signs of drowsiness or distraction in the driver and their emotional state.

[1549] The "warning generation means" is a device or program that generates a warning message and notifies the driver when an abnormality is detected by the analysis means.

[1550] The "communication means" is a device for communicating data in real time between the sensor means, the information processing means, the analysis means, and the emotion engine.

[1551] The "display means" is a device for displaying and notifying the driver of the warning message generated by the warning generation means.

[1552] The present invention provides a system for effectively preventing drowsy driving and inattentive driving of drivers engaged in long-distance trucking and transportation businesses, and for managing the health and emotional state of the driver in real time. Specific embodiments of the system are described below.

[1553] 1. Sensor means

[1554] Processing performed by the device

[1555] The device is equipped with an AI camera that captures the driver's face and movements in real time. The AI ​​camera monitors blinking frequency, gaze direction, facial expressions, head position, and other data in real time, collecting this data. The collected data is temporarily stored in the device and then sequentially sent to a server.

[1556] 2. Data Preprocessing

[1557] Processing performed by the server

[1558] The server receives the data sent from the device and performs noise reduction and image correction using software such as OpenCV and Python scripts. Preprocessing includes noise reduction, adjusting image brightness and contrast, and extracting facial position information.

[1559] 3. Data Analysis and Emotion Recognition

[1560] Processing performed by the server

[1561] The preprocessed data is input into an analysis engine and emotion engine using generative AI. Specific software used is TensorFlow and Keras. The analysis engine uses a neural network to analyze the driver's facial expressions and movement patterns to detect signs of drowsiness or distraction in real time. The emotion engine also recognizes the driver's emotional state (fatigue, stress, relaxation, etc.). The driver's condition is determined based on the results of this analysis.

[1562] 4. Warning generation means

[1563] Processing performed by the server

[1564] If the server detects an abnormality based on the results of the analysis engine and emotion engine, it generates a warning message for the driver. The generated warning message is adjusted based on the driver's emotional state. For example, it may include a warning such as "Signs of drowsy driving have been detected. Please take a break immediately" or advice such as "Fatigue has been detected. Please take a deep breath to promote relaxation."

[1565] 5. Warning Display

[1566] Processing performed by the device

[1567] The terminal receives warning messages from the server and displays them to the driver, either as a text message on the display or as a voice notification, allowing the driver to check the message and take appropriate action.

[1568] 6. Means of communication

[1569] It includes a means for communicating data in real time between the sensor means, information processing means, analysis means, and emotion engine, which allows all data to be shared without delay, enabling rapid analysis and emotion recognition.

[1570] Examples of concrete examples and prompts

[1571] For example, if a driver's blinking rate decreases and their gaze becomes fixed within a certain period of time, the analysis engine will detect signs of drowsiness while the emotion engine will recognize that the driver is fatigued. Based on this, a warning message will be generated and sent to the driver via the device's display and speaker, stating, "Signs of drowsiness at the wheel have been detected. Please take a break immediately."

[1572] Example prompt for a generative AI model:

[1573] "It captures the driver's face and analyzes their behavior in real time, including blinking frequency, gaze direction, and facial expressions. If an abnormality is detected, it generates an appropriate warning message and displays it on the device."

[1574] In this way, this system prevents drivers from falling asleep or being careless while driving, and supports health management.

[1575] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1576] Step 1:

[1577] Data collection

[1578] Processing performed by the device

[1579] An AI camera installed on the device captures the driver's face in real time, collecting data on the driver's facial movements, blink frequency, gaze direction, facial expressions, head position, and other specific behaviors.

[1580] Input: Driver image and motion data

[1581] Output: Collected image and behavioral data

[1582] Step 2:

[1583] Sending data

[1584] Processing performed by the device

[1585] The collected data is temporarily stored in the terminal and then transmitted to the server. Specifically, when a certain data buffer is filled, the terminal transmits the data to the server according to a data transmission protocol.

[1586] Input: Collected image and behavioral data

[1587] Output: Data sent to the server

[1588] Step 3:

[1589] Pretreatment

[1590] Processing performed by the server

[1591] The server preprocesses the data received from the device, including noise reduction, image correction, brightness and contrast adjustment, and facial position extraction.

[1592] Input: Image data and motion data sent from the device

[1593] Output: Preprocessed, high-quality data

[1594] Step 4:

[1595] Analysis and Emotion Recognition

[1596] Processing performed by the server

[1597] The preprocessed data is input into the generative AI's analysis engine and emotion engine. The analysis engine uses a neural network to detect signs of driver drowsiness or distraction, while the emotion engine recognizes the driver's emotional state (fatigue, stress, relaxation, etc.).

[1598] Input: Preprocessed, high-quality data

[1599] Output: Analysis of drowsy driving, distraction symptoms, and emotional state

[1600] Step 5:

[1601] Warning generation

[1602] Processing performed by the server

[1603] If an anomaly is detected based on the results of the analysis engine and emotion engine, the server generates a warning message, which is tailored to the driver's emotional state.

[1604] Input: Parsed result data

[1605] Output: Warning message

[1606] Step 6:

[1607] Warning display

[1608] Processing performed by the device

[1609] Methods for displaying the warning message received by the terminal from the server to the driver include displaying a text message on the display and an audio notification.

[1610] Input: The warning message sent by the server

[1611] Output: Warning message displayed by the driver

[1612] Through these steps, the system can prevent drowsy or inattentive driving, generate appropriate warnings and promptly notify the driver, and also manage the driver's health and emotional state in real time.

[1613] (Application example 2)

[1614] 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."

[1615] Conventional drowsy driving prevention systems have focused on capturing and analyzing the driver's face and movements, but have not yet reached the point of recognizing the driver's emotional state and health status in real time. As a result, it has been difficult to accurately grasp the driver's emotional state, such as distraction, fatigue, and stress, and provide appropriate warnings and notifications, resulting in issues that make it difficult to ensure sufficient safety. Therefore, the present invention aims to provide a system that recognizes not only signs of drowsy driving and distraction, but also the driver's emotional state in real time and provides appropriate warnings.

[1616] 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 a sensing means for capturing the driver's face and movements in real time, a processing means for preprocessing the data acquired from the sensing means, an analysis means for analyzing the data preprocessed by the processing means and detecting signs of the driver drowsing at the wheel or being distracted, an emotion recognition means for recognizing the driver's emotional state in real time by the analysis means, a warning generation means for generating a warning and sending it to a terminal when an abnormality is detected, and a display means for displaying the generated warning message. This makes it possible to prevent the driver from drowsing at the wheel or being distracted, and to provide an appropriate warning based on the driver's emotional state.

[1617] "Sensing means" refers to devices and technologies that capture the driver's face and movements in real time.

[1618] "Processing means" refers to devices and technologies that preprocess data acquired from the sensing means and perform noise removal and image correction.

[1619] "Analytical means" refers to devices and technologies that analyze pre-processed data to detect signs of driver drowsiness or distraction.

[1620] "Emotion recognition means" refers to devices and technologies that recognize the emotional state of a driver in real time from data obtained by the analysis means.

[1621] "Warning generation means" refers to a device or technology that generates a warning and sends it to a terminal when an abnormality is detected by the analysis means or emotion recognition means.

[1622] "Display means" refers to devices and techniques that display the generated warning message and notify the driver.

[1623] "Communication Means" refers to devices and technologies that communicate data in real time between the Sensing Means and the Analysis Means or Emotion Recognition Means.

[1624] "Audio output means" refers to a device and technology that notifies the driver of the generated warning message by voice.

[1625] The present invention is a system for preventing drowsiness and distraction at the wheel, and supports safe driving by monitoring the driver's health and emotional state in real time. The system includes the following components:

[1626] Sensing Method

[1627] This is a device that uses a camera installed on a terminal or vehicle (e.g., a smartphone or in-car camera) to capture the driver's face and movements in real time, collecting information such as the driver's facial expression, blink frequency, gaze direction, and head position.

[1628] Processing means

[1629] The server or device preprocesses the data acquired from the sensing means, including noise removal and image correction, to generate high-quality data that is useful for subsequent analysis.

[1630] analytical means

[1631] The preprocessed data is analyzed by the server. The data is input into an analysis engine that uses a generative AI model to detect signs of driver drowsiness or distraction in real time. For example, if a decrease in blinking frequency and fixed gaze are detected within a certain period of time, this is analyzed as a sign of drowsy driving.

[1632] emotion recognition means

[1633] Using another generative AI model, the emotion engine uses the data pre-processed by the processing means to recognize the driver's emotional state in real time, for example, whether the driver is tired, stressed or relaxed.

[1634] Warning generation means

[1635] If an abnormality is detected by the analysis or emotion recognition methods, the server automatically generates a warning message, such as "Signs of drowsy driving have been detected. Please take a break immediately." Additional advice based on the driver's emotional state may also be included.

[1636] communication means

[1637] It includes a communication device for communicating data in real time between the sensing means, processing means, analysis means, and emotion recognition means, allowing all data to be shared without delay, enabling rapid analysis and emotion recognition.

[1638] Display means

[1639] The generated warning message is displayed on the display screen of the terminal or on the head-mounted display. The warning may also be given by voice through the voice output means. This allows the driver to check the warning message and take appropriate action.

[1640] Hardware and software used

[1641] In this invention, specific hardware includes a camera (e.g., a smartphone camera or a car camera) and a head-mounted display, and software includes image processing using OpenCV and execution of generative AI models using TensorFlow and Keras.

[1642] Examples of concrete examples and prompts

[1643] A concrete example is the following prompt:

[1644] "If a driver exhibits a decrease in blinking rate and gaze fixation within a certain period of time, signs of drowsy driving are detected."

[1645] "A system that analyzes driver behavior data captured by a camera in smart glasses in real time to detect signs of drowsy driving or distraction."

[1646] This enables the system to optimize driver safety while driving and also improve the overall efficiency of operations.

[1647] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1648] Step 1:

[1649] The sensing means captures the driver's face and movements in real time. The input is camera footage, and the output is captured image data. A camera (e.g., a smartphone camera or an in-car camera) periodically captures images and sends them to a terminal.

[1650] Step 2:

[1651] The device preprocesses the image data acquired from the sensing means. The input is the captured image data, and the output is the preprocessed image data. Preprocessing includes noise removal, image correction, face detection, etc., and is performed using OpenCV.

[1652] Step 3:

[1653] The server inputs the preprocessed image data into the generative AI model. The input is the preprocessed image data, and the output is the analysis results. Using TensorFlow and Keras, the analysis engine analyzes the data to detect signs of driver drowsiness or distraction.

[1654] Step 4:

[1655] The server uses an emotion recognition means to recognize the driver's emotional state from the analysis results. The input is the analysis results, and the output is the data of the driver's emotional state. Another generative AI model is used to evaluate the driver's fatigue, stress, and relaxation states in real time.

[1656] Step 5:

[1657] The server generates a warning message based on the results of the analysis and emotion recognition. The input is data on the driver's emotional state, and the output is a warning message. The warning generation means automatically creates a warning message based on signs of drowsy driving and stress levels.

[1658] Step 6:

[1659] The server transmits the generated warning message to the terminal in real time. The input is the warning message, and the output is data communication to the terminal. The warning message is transmitted to the terminal without delay using the communication means.

[1660] Step 7:

[1661] The terminal notifies the driver of a warning message using a display means. The input is the received warning message, and the output is the displayed warning message. The warning message is displayed on a display or head-mounted display, and the driver is also notified by voice using a voice output means.

[1662] 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.

[1663] 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.

[1664] 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.

[1665] 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.

[1666] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1667] 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.

[1668] 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).

[1669] 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.

[1670] 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."

[1671] 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.

[1672] 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).

[1673] 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.

[1674] 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.

[1675] 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.

[1676] 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.

[1677] 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.

[1678] 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.

[1679] 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.

[1680] 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.

[1681] 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.

[1682] 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.

[1683] The following is further disclosed regarding the above embodiment.

[1684] (Claim 1)

[1685] a sensor means for capturing the driver's face and movements in real time;

[1686] processing means for pre-processing data acquired from said sensor means;

[1687] an analysis means for analyzing the data preprocessed by the processing means and detecting signs of drowsiness or distraction of the driver;

[1688] The system further includes an alert generation means for generating an alert and transmitting the alert to a terminal when an abnormality is detected by the analysis means.

[1689] (Claim 2)

[1690] 10. The system of claim 1, further comprising communication means for communicating data in real time between said sensor means and said analysis means.

[1691] (Claim 3)

[1692] 2. The system according to claim 1, further comprising a display means for displaying the warning message generated by the warning generating means to notify a driver.

[1693] "Example 1"

[1694] (Claim 1)

[1695] a sensor means for capturing the driver's face and movements in real time;

[1696] a terminal for storing data acquired from the sensor means and transmitting the data via a network;

[1697] processing means for pre-processing data received from said terminal;

[1698] an analysis means for analyzing the data preprocessed by the processing means and detecting signs of drowsiness or distraction of the driver;

[1699] The system further includes an alert generation means for generating an alert and transmitting the alert to a terminal when an abnormality is detected by the analysis means.

[1700] (Claim 2)

[1701] 10. The system of claim 1, further comprising communication means for communicating data in real time between said sensor means and said analysis means.

[1702] (Claim 3)

[1703] 2. The system according to claim 1, further comprising a display means and an audio notification means for displaying the warning message generated by the warning generation means and notifying the driver.

[1704] "Application Example 1"

[1705] (Claim 1)

[1706] a sensor means for capturing the face and movements of an operator in real time;

[1707] processing means for pre-processing data acquired from said sensor means;

[1708] an analysis means for analyzing the data preprocessed by the processing means and detecting signs of drowsiness or distraction;

[1709] a warning generation means for generating a warning when an abnormality is detected by the analysis means and transmitting the warning to a terminal;

[1710] The system further includes a display means for displaying the warning message generated by the warning generating means and notifying an operator.

[1711] (Claim 2)

[1712] 10. The system of claim 1, further comprising communication means for communicating data in real time between said sensor means and said analysis means.

[1713] (Claim 3)

[1714] 10. The system of claim 1, wherein the display means further comprises means for displaying a warning to an operator using a display of the smart glasses and an audio notification.

[1715] "Example 2: Combining Emotion Engines"

[1716] (Claim 1)

[1717] a sensor means for capturing the driver's face and movements in real time;

[1718] an information processing means for preprocessing data acquired from the sensor means;

[1719] an analysis means for analyzing the data preprocessed by the processing means to detect signs of drowsiness or distraction of the driver and the driver's emotional state;

[1720] The system further includes an alert generation means for generating an alert and transmitting the alert to a terminal when an abnormality is detected by the analysis means.

[1721] (Claim 2)

[1722] 10. The system of claim 1, further comprising communication means for communicating data in real time between said sensor means, processing means, analysis means and emotion engine.

[1723] (Claim 3)

[1724] 2. The system according to claim 1, further comprising a display means for displaying the warning message generated by the warning generating means to notify a driver.

[1725] "Application example 2 when combining emotion engines"

[1726] (Claim 1)

[1727] A sensing means for capturing the driver's face and movements in real time;

[1728] processing means for pre-processing data acquired from the sensing means;

[1729] an analysis means for analyzing the data preprocessed by the processing means and detecting signs of driver drowsiness or distraction;

[1730] emotion recognition means for recognizing the emotional state of the driver in real time by the analysis means;

[1731] a warning generation means for generating a warning when an abnormality is detected by the analysis means or the emotion recognition means and transmitting the warning to a terminal;

[1732] The system includes a display means for displaying the generated warning message.

[1733] (Claim 2)

[1734] 10. The system of claim 1, further comprising a communication means for communicating data in real time between said sensing means and said analyzing means or emotion recognition means.

[1735] (Claim 3)

[1736] 10. The system of claim 1, further comprising an audio output means for announcing the generated warning message to a driver as an audio notification. [Explanation of symbols]

[1737] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a sensor means for capturing the driver's face and movements in real time; processing means for pre-processing data acquired from said sensor means; an analysis means for analyzing the data preprocessed by the processing means and detecting signs of drowsiness or distraction of the driver; The system further includes an alert generation means for generating an alert and transmitting the alert to a terminal when an abnormality is detected by the analysis means.

2. The system of claim 1 further comprising communication means for communicating data in real time between said sensor means and said analysis means.

3. 2. The system according to claim 1, further comprising display means for displaying the warning message generated by said warning generating means to notify a driver.

Images