System

Abstract

A system is provided.SOLUTION: A system comprising: means for monitoring a status of a child attending a nursery facility by a face recognition camera; means for automatically contacting a parent of a child who has not attended the nursery facility by a predetermined time; means for receiving a response from the parent and updating the system based on the response; and means for notifying the parent when there is no response from the parent or when an abnormality is detected.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] In recent years, child safety at childcare facilities and on buses has become a major social issue. Ensuring the safety of children, particularly in the event of children being left behind on buses or forgetting to arrive at school, is a particular challenge. Furthermore, the shortage of childcare workers is becoming more serious, increasing the burden of safety management. Given this background, there is a demand for an effective system that can ensure child safety while reducing the burden on childcare workers. The present invention aims to solve these issues and ensure a high level of child safety in childcare facilities. [Means for solving the problem]

[0005] The present invention provides a system that includes a means for monitoring the attendance status of children at a childcare facility using a facial recognition camera, a means for automatically contacting parents of children who have not arrived by a specified time, a means for receiving responses from parents and updating the system based on the responses, and a means for notifying caregivers if there is no response from the parents or if an abnormality is detected. The system also includes a means for monitoring children's boarding times and behavior using cameras installed on buses that transport children to the childcare facility, and a means for notifying caregivers if there is no activity for a certain period of time or if an abnormality is detected, thereby ensuring the safety of children on the bus. Furthermore, the system includes a means for processing data from the facial recognition camera and cameras installed on buses and using AI technology to monitor children's safety, improving the accuracy and efficiency of the system. This reduces the burden on caregivers and increases children's safety.

[0006] A "facial recognition camera" is a device that uses a camera to capture a person's face and identifies the individual using a facial recognition algorithm.

[0007] "Childcare facilities" are places where children gather during the day and receive education and care. Specifically, this refers to nursery schools and kindergartens.

[0008] "Attendance status" is information indicating whether a child has arrived at the childcare facility and arrived within the designated time.

[0009] "Parent" refers to a child's parent or legal guardian, who is responsible for receiving communications regarding the child's attendance status.

[0010] "Automatic contact means" refers to a function in which the system automatically calls or sends a message to parents of children who do not arrive at school within a specified time.

[0011] "Childcare workers" refers to staff and teachers who look after children at childcare facilities.

[0012] "Means for detecting abnormalities" refers to a function that monitors children's arrival and departure status and their behavior on the bus, and detects any abnormalities (e.g., not arriving at school within the designated time, or no activity for a certain period of time).

[0013] A "school bus" refers to a bus provided for transporting children to and from a childcare facility.

[0014] "AI technology" refers to artificial intelligence technology, which is an algorithm and technology that learns from large amounts of data and automatically performs specific tasks (e.g., facial recognition, anomaly detection).

[0015] The "database" is a system for structuring and storing data such as attendance status and facial recognition results. [Brief explanation of the drawings]

[0016] [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

[0017] 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.

[0018] First, the terms used in the following description will be explained.

[0019] 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).

[0020] 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.

[0021] 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.

[0022] 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.

[0023] 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."

[0024] [First embodiment]

[0025] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0026] 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.

[0027] 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).

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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."

[0037] This invention uses facial recognition cameras, AI technology, and an automatic notification system to ensure the safety of children at childcare facilities and on school buses. The system aims to monitor children's attendance in real time and detect abnormalities early, while reducing the burden on caregivers.

[0038] An embodiment of a kindergarten attendance management system

[0039] System Overview

[0040] The server is the central control unit of the attendance management system, managing the database, running the facial recognition algorithm, and sending notifications.

[0041] The terminal (facial recognition camera) is installed at the entrance of the childcare facility, photographs the faces of children arriving at the facility, and identifies them in real time.

[0042] Users (caregivers and parents) receive information through the system's app and perform the necessary operations.

[0043] Program processing explanation

[0044] 1. The user (caregiver or administrator) starts the system and begins monitoring a new day of attendance.

[0045] The server reads the schedule of the daycare facility and starts managing the attendance status for today.

[0046] 2. The device (face recognition camera) takes real-time photos of children arriving at the childcare facility and identifies them using a facial recognition algorithm.

[0047] The server receives the facial recognition results and updates the child's attendance database.

[0048] 3. The server lists children who have not arrived by the designated arrival time (e.g., 9:00).

[0049] The server checks the attendance status and generates a list of children who have not arrived by the specified time.

[0050] 4. The server automatically sends a message to the parents of children who have not arrived at school by the specified time.

[0051] The server uses the generation AI to send a message to the parent's contacts, for example, "Your child is not attending school. Please tell us why."

[0052] 5. The user (parent) receives the message and replies via the smartphone app whether or not the child will attend school and the reason.

[0053] The server receives the response from the parents and updates the attendance database.

[0054] 6. The server notifies the caregiver if there is no response from the parent or if an abnormality is detected.

[0055] If an abnormality is detected, the server automatically sends a warning message to the caregiver's device.

[0056] Embodiment of school bus monitoring system

[0057] System Overview

[0058] The device (bus camera) is installed inside the school bus and monitors the children's boarding times and behavior.

[0059] The server collects data from the on-board cameras and runs algorithms to detect anomalies.

[0060] Users (caregivers) can view the internal camera footage from the bus in real time on their smartphones or tablets.

[0061] Program processing explanation

[0062] 1. The device (in-bus camera) records the time the child boards the bus and sends the data to the server.

[0063] The server receives the boarding time data and records it in a database.

[0064] 2. The device (in-bus camera) monitors the children's behavior and periodically sends data to the server.

[0065] The server receives behavioral data from the camera and uses AI technology to detect abnormalities.

[0066] 3. The server sends a notification to the caregiver if there is no activity for a certain period of time or if an abnormality is detected.

[0067] The server runs an anomaly detection algorithm and sends real-time notifications to caregivers if an anomaly is detected.

[0068] 4. The user (caregiver) receives a notification and checks the internal camera footage from the bus.

[0069] Childcare workers will check the situation on the bus through the app and respond as necessary.

[0070] Specific examples

[0071] As a concrete example, here is a simulation of a day at kindergarten:

[0072] At 8:00 a.m., the user (caregiver) starts the system and begins monitoring the day the children attend school.

[0073] When a child arrives at the entrance, a device (face recognition camera) takes a picture of their face and sends the data to the server.

[0074] At 8:30, the server performs facial recognition and updates the database of children who have already arrived at the school.

[0075] At 9:00, the server lists the children who have not attended school and automatically sends a message to their parents.

[0076] The user (parent) receives the message and replies from the app at 8:50 a.m. explaining the reason for attending school.

[0077] At 9:15, the server checks the response from the parents and updates the attendance database.

[0078] At 10:00, the device (the camera inside the bus) sends some data on the children's behavior to the server, which analyzes it.

[0079] At 10:30, the server detects an abnormality (e.g., a motionless child) and sends a notification to the user (caregiver).

[0080] The user (caregiver) receives the notification, checks the camera footage inside the bus, and takes the necessary action.

[0081] The above is an embodiment of the invention. The present invention can reduce the burden on caregivers and ensure a high level of child safety.

[0082] The processing flow will be explained below.

[0083] Processing steps of the attendance management system

[0084] System startup and preparation

[0085] Step 1:

[0086] The user (caregiver or administrator) starts the system and begins monitoring the new day of attendance.

[0087] The caregiver presses the "Start Day of School" button on the system screen to start the system.

[0088] The server checks the childcare facility's schedule and initializes the database based on today's date.

[0089] Facial recognition when attending kindergarten

[0090] Step 2:

[0091] The device (face recognition camera) takes real-time photos of children arriving at the daycare facility.

[0092] Cameras are installed at the entrance and automatically detect the faces of children arriving at the school.

[0093] The camera transmits the facial image data to a server.

[0094] Step 3:

[0095] The server runs a facial recognition algorithm to analyze the transmitted facial image data.

[0096] The server compares the facial image data with existing facial data in the database.

[0097] Get the matching child's ID and update the corresponding database entry to "already in school."

[0098] Checking attendance status and contacting

[0099] Step 4:

[0100] The server lists children who have not arrived by the designated arrival time (e.g., 9:00).

[0101] The server compares the childcare facility's schedule with the child's attendance data and lists children who have not attended.

[0102] Step 5:

[0103] The server sends an automatic message to the parents of children who are not attending school.

[0104] The server uses a generative AI to create a phone call or message and send it to the parent saying, "Your child has not come to school. Please let us know the reason."

[0105] Parental Response Management

[0106] Step 6:

[0107] The user (parent) receives the message and replies using a smartphone app to indicate whether or not the child will attend school and the reason for the attendance.

[0108] Parents check the notification in the app, enter the reason (e.g., "absent due to illness"), and submit.

[0109] Step 7:

[0110] The server receives the response from the parents and updates the attendance status database.

[0111] The server records the received reason in a database and updates the status of the corresponding child.

[0112] Notification in case of an abnormality

[0113] Step 8:

[0114] If the server does not receive a response from the parent within a certain period of time (e.g., 15 minutes) or detects an abnormality, it notifies the caregiver.

[0115] The server generates a warning message saying, "We are unable to confirm attendance for child ID 12345, who has not responded. Action is required."

[0116] The server sends this message to the childcare provider's terminal.

[0117] Processing steps of the school bus monitoring system

[0118] Ride data collection and monitoring

[0119] Step 1:

[0120] The device (camera inside the bus) records the time the child boards the bus and sends the data to the server.

[0121] Cameras are installed at the entrances to the buses and automatically capture images of children boarding.

[0122] The camera sends a facial image to a server and records the time of boarding.

[0123] Step 2:

[0124] The server receives the boarding time data and updates the boarding status database.

[0125] The server performs facial recognition and records the ID of the child riding and the time of boarding in a database.

[0126] Behavior monitoring and anomaly detection

[0127] Step 3:

[0128] The device (a camera inside the bus) periodically captures images of children's behavior and sends the data to a server.

[0129] The cameras inside the bus monitor the children's movements and capture and transmit image data at regular intervals.

[0130] Step 4:

[0131] The server receives behavioral data from the camera and uses AI technology to detect abnormalities.

[0132] The server analyzes behavioral data and detects abnormalities such as no activity for a certain period of time.

[0133] Notification and confirmation in case of an abnormality

[0134] Step 5:

[0135] If the server detects an abnormality, it will send a notification to the caregiver.

[0136] Based on the anomaly detection algorithm, the server generates a notification stating, "There has been no activity from ID12345 on the bus for more than 10 minutes. Check is required." and sends it to the caregiver's device.

[0137] Step 6:

[0138] The user (caregiver) receives a notification and checks the camera footage inside the bus.

[0139] Caregivers can check notifications on their smartphones or tablets and use the app's camera feed function to view real-time footage.

[0140] If necessary, the childcare provider will contact the bus driver or other staff to determine the actual situation and respond accordingly.

[0141] Based on these processing steps, the system of the present invention can ensure a high level of child safety in childcare facilities and on buses.

[0142] Example 1

[0143] 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."

[0144] Conventional attendance management systems at childcare facilities require manual confirmation of children's attendance status and communication of that information to parents and caregivers, which is extremely time-consuming and labor-intensive. Furthermore, bus attendance is also primarily monitored manually, making it difficult to detect abnormalities early on. This increases the burden on caregivers and makes it difficult to ensure the safety of children, which has been an issue.

[0145] 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.

[0146] In this invention, the server includes a means for monitoring the attendance status of children at the childcare facility using a face recognition camera, a means for automatically contacting the parents of children who have not arrived by a specified time, a means for receiving responses from the parents and updating the database based on the responses, and a means for notifying the childcare worker if there is no response from the parents or if an abnormality is detected. This reduces the burden on the childcare worker and ensures a high level of child safety.

[0147] A "facial recognition camera" is a camera that captures a child's face and identifies the child using a facial recognition algorithm.

[0148] "Childcare facility" refers to any facility that provides childcare, such as kindergartens and nursery schools.

[0149] "Attendance status" is information indicating whether or not a child has attended a childcare facility.

[0150] "Guardian" means a child's parent or legal guardian.

[0151] "Automatic notification" is the process by which a system uses generative AI models to automatically create and send messages to specific recipients.

[0152] A "database" is a collection of information that is used to systematically manage and store information in a system.

[0153] "Abnormal" refers to a state that differs from a child's normal behavior or situation, such as not showing up to school or not moving around on the bus.

[0154] "Notification" is an operation in which the system sends specific information to a terminal to notify it.

[0155] "Means" refers to a set of methods or devices used to achieve a particular purpose.

[0156] An "in-bus camera" is a camera installed inside a school bus to monitor children's boarding times and behavior.

[0157] "Artificial intelligence technology" refers to all technologies that use machine learning and data analysis algorithms to automatically process and analyze data and support decision-making.

[0158] MODE FOR CARRYING OUT THE INVENTION

[0159] System Overview

[0160] The system of the present invention uses facial recognition cameras, AI technology, and an automatic notification system to ensure the safety of children at childcare facilities and on buses. The system consists of a server, terminals (facial recognition cameras and bus cameras), and users (caregivers and parents), and aims to monitor children's attendance in real time and detect any abnormalities early, while reducing the burden on caregivers.

[0161] Hardware and software used

[0162] The server is the central control unit of the attendance management system, managing the database, running the facial recognition algorithm, and sending notifications. In this case, a generative AI model is used.

[0163] The terminal (facial recognition camera) is installed at the entrance of the childcare facility, photographs the faces of children arriving at the facility, and identifies them in real time.

[0164] The device (bus camera) is installed inside the school bus and monitors the children's boarding times and behavior.

[0165] Users (caregivers and parents) receive information through the system's app and perform the necessary operations.

[0166] Program processing explanation

[0167] 1. When the system is started, the server loads the childcare facility's schedule and begins managing the day's attendance status. The server uses a generative AI model to analyze various data and generate notification messages.

[0168] 2. The device (face recognition camera) takes a real-time picture of the child as they arrive at the daycare center and identifies them using a face recognition algorithm. The face recognition results are sent to the server, which updates the child attendance database.

[0169] 3. The device (in-bus camera) records the time the child boards the bus and sends the data to a server. The server records this in a database and uses AI technology to detect any abnormalities.

[0170] 4. The server creates a list of children who have not arrived by the designated time and automatically sends a message to their parents using a generative AI model to create a message for parents and send it via email, SMS, etc.

[0171] 5. The user (parent) receives the notification and replies via the smartphone app whether or not the child will attend school and the reason for their attendance. The server receives the reply from the parent and updates the attendance database.

[0172] 6. If the server detects an abnormality or if there is no response from the parent, it will notify the caregiver, allowing the caregiver to understand the situation in real time and respond quickly.

[0173] Specific examples

[0174] As a concrete example, here is a simulation of a day at kindergarten:

[0175] At 8:00 a.m., the user (caregiver) starts the system and begins monitoring the day the children attend school.

[0176] When a child arrives at the entrance, a device (face recognition camera) takes a picture of their face and sends the data to the server.

[0177] At 8:30, the server performs facial recognition and updates the database of children who have already arrived at the school.

[0178] At 9:00, the server will list the children who have not attended school and automatically send a message to their parents. Example prompt: "Your child has not attended school. Please tell us the reason."

[0179] The user (parent) receives the message and replies from the app at 8:50 a.m. explaining the reason for attending school.

[0180] At 9:15, the server checks the response from the parents and updates the attendance database.

[0181] At 10:00, the device (the camera inside the bus) sends some data on the children's behavior to the server, which analyzes it.

[0182] At 10:30, the server detects an abnormality (e.g., a motionless child) and sends a notification to the user (caregiver).

[0183] The user (caregiver) receives the notification, checks the camera footage inside the bus, and takes the necessary action.

[0184] The above is an embodiment of the invention, which reduces the burden on caregivers and ensures a high level of child safety.

[0185] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0186] Step 1:

[0187] The user (caregiver or administrator) starts the system and begins monitoring the new day of attendance.

[0188] Input: The user taps the system wake-up button and enters schedule information.

[0189] Specific operation: The system starts when the user presses the start button on the management screen on their smartphone or PC.

[0190] Data processing / calculation: The server retrieves the current date and schedule information from the internal database and displays it.

[0191] Output: The childcare facility schedule is displayed on the admin page.

[0192] Step 2:

[0193] The device (facial recognition camera) takes real-time photos of the faces of children arriving at the childcare facility and identifies them using a facial recognition algorithm.

[0194] Input: Child's face image, previously registered face image data.

[0195] Specific operation: The camera detects motion and captures the child's face automatically.

[0196] Data processing / computation: A facial recognition algorithm runs on the server and matches the captured facial image with existing data in a database.

[0197] Output: The attendance information of children who match the matched result is updated.

[0198] Step 3:

[0199] The server lists the children who have not arrived by the designated arrival time (e.g. 9:00).

[0200] Input: School attendance database, specified time.

[0201] Specific operation: The server scans the attendance database and extracts children whose attendance could not be confirmed.

[0202] Data processing / calculation: Filter the attendance status in the database and generate a list of children who have not attended.

[0203] Output: At 9:00, the list of children who have not yet attended school is complete.

[0204] Step 4:

[0205] The server automatically sends a message to the parents of the listed children who have not attended school.

[0206] Input: List of non-attendance students, parent contact information.

[0207] How it works: Using a generative AI model, messages are automatically generated for each parent.

[0208] Data processing / computation: The AI ​​model creates a message and sends it via email, SMS, etc.

[0209] Output: A message is sent to the parent contact.

[0210] Step 5:

[0211] The user (parent) receives a notification and replies via a smartphone app whether or not their child will attend school and the reason for doing so.

[0212] Input: Parent response message.

[0213] Specific actions: Parents check the notification on their smartphone, open the reply form within the app, enter the reason, and submit.

[0214] Data processing / calculation: The server receives the reply and updates the attendance database.

[0215] Output: The updated attendance database is displayed.

[0216] Step 6:

[0217] If the server detects an abnormality, it will notify the caregiver.

[0218] Input: If there is no reply from the parent within a certain period of time, the AI ​​detects an anomaly.

[0219] Specific operation: The server monitors the response status and anomaly detection results.

[0220] Data processing / calculation: If an abnormality is detected or there is no response for a certain period of time, a notification will be automatically generated to the caregiver.

[0221] Output: A warning message is displayed on the caregiver's device.

[0222] Step 7:

[0223] The device (camera inside the bus) records the time the child boards the bus and sends the data to the server.

[0224] Input: Child boarding time data.

[0225] What it does: Cameras monitor children on the bus and record the time they board.

[0226] Data processing / calculation: The server receives the boarding time data and records it in the database.

[0227] Output: The registered boarding time data is updated.

[0228] Step 8:

[0229] The device (a camera inside the bus) monitors the children's behavior and periodically sends data to the server.

[0230] Input: Child behavior data.

[0231] How it works: Cameras inside the bus monitor children's behavior and record video data.

[0232] Data processing / calculation: The server receives behavioral data from the camera and analyzes it using AI technology.

[0233] Output: The analysis results are recorded in a database.

[0234] Step 9:

[0235] If the server detects no activity for a certain period of time or detects an abnormality, it will send a notification to the caregiver.

[0236] Input: Child activity data, anomaly detection results.

[0237] What it does: The server monitors the analysis results and generates a notification if it detects an anomaly.

[0238] Data processing / calculation: Run anomaly detection algorithms and create notifications if anomalies are detected.

[0239] Output: An abnormality notification is sent to the caregiver's device.

[0240] Step 10:

[0241] The user (caregiver) receives a notification and checks the internal camera footage of the bus.

[0242] Input: Anomaly notification, camera footage.

[0243] Specific operations: Childcare workers check notifications through the app and view real-time camera footage from inside the bus.

[0244] Data processing / calculation: Camera video data is streamed and provided to caregivers.

[0245] Output: The childcare worker can grasp the situation inside the bus in real time.

[0246] The above are the specific processing steps of the system and their detailed operations.

[0247] (Application example 1)

[0248] 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."

[0249] Ensuring passenger safety is important in autonomous vehicles, but conventional systems have been insufficient in monitoring passenger status and the interior of the vehicle. It has also been difficult to detect abnormalities in the passenger status or the interior of the vehicle in a timely manner and take necessary measures. This has led to a demand for an efficient method to ensure a high level of passenger safety.

[0250] 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.

[0251] In this invention, the server includes a means for monitoring the riding status of passengers using a face recognition camera installed at the entrance of the means of transportation, a means for automatically contacting passengers who have not boarded by a predetermined time, and a means for receiving responses from passengers and updating the system based on the responses. This makes it possible to quickly contact passengers even if they have not boarded by the predetermined time, and to grasp the riding status of passengers in real time.

[0252] "Transportation" refers to any means of transportation for carrying passengers, including autonomous vehicles.

[0253] A "face recognition camera" is a camera device that photographs and identifies the faces of passengers.

[0254] "Riding status" refers to the process and results of passengers boarding a means of transportation.

[0255] "Predetermined Time" means a specific time set for a Passenger to board a Transportation Vehicle.

[0256] "Automatic contact means" refers to a device or program that automatically communicates without human intervention when contact is required.

[0257] "Response" means a response from a passenger or observer who has received a communication.

[0258] "Means for updating the system" means a device or program that keeps the database and settings up to date based on passenger responses.

[0259] "Supervisor" means a person who monitors the safety of a means of transport and its passengers and takes any necessary action.

[0260] "In-camera video analysis means" refers to a device or program that analyzes video captured by a camera and detects abnormal movements or specific actions.

[0261] "In-vehicle behavior" refers to the actions and movements of passengers within a mode of transportation.

[0262] "AI technology" refers to technology that uses artificial intelligence to process data and perform identification and anomaly detection.

[0263] This invention is a system for ensuring passenger safety in autonomous vehicles, which uses a facial recognition camera, AI technology, and an automatic notification system. The system is configured as follows:

[0264] System Overview

[0265] The server is the central control unit of the system, managing the database, running the facial recognition algorithm, and sending notifications. Specifically, a cloud-based system (e.g., AWS®, Google® Cloud) can be used.

[0266] The terminal (face recognition camera) is installed at the entrance of the transportation vehicle and takes pictures of the faces of passengers boarding the vehicle and identifies them in real time, using high-performance cameras and face recognition algorithms (e.g., OpenCV, TENSORFLOW®).

[0267] Users (passengers and observers) receive information and perform necessary operations via the system's app, which is designed to run on iOS and Android (registered trademark).

[0268] Program processing explanation

[0269] Ride monitoring

[0270] The device (a facial recognition camera) takes a picture of the passenger's face when boarding the transportation vehicle at the entrance and sends the data to a server, which uses a facial recognition algorithm to identify the passenger and update the passenger database. This process occurs in real time.

[0271] Automated Contact System

[0272] The server will list passengers who have not boarded by the designated time and automatically contact them. The server will then use a generative AI model to send a message to the passenger's contacts. For example, it could send a message saying, "You have not boarded. Please tell us why."

[0273] Passenger response

[0274] The user (passenger) receives the message and replies via the smartphone app whether or not they want to ride and the reason for the ride. The server receives this reply and updates the ride database.

[0275] Anomaly Detection System

[0276] The server receives data from the device (face recognition camera) and the in-car camera and uses AI technology to detect abnormalities. In particular, it analyzes unusually small movements and abnormal movements in real time, and if an abnormality is detected, it sends a notification to the monitor.

[0277] Specific implementation example

[0278] One day, an autonomous vehicle begins operation, and a facial recognition camera at the entrance monitors passengers. For example, Passenger A boards the vehicle at 8:00 AM, and the camera recognizes his face and sends the data to the server. At 8:30 AM, Passenger B, who has not boarded the vehicle, automatically receives a message saying, "You are not boarding. Please tell us the reason."

[0279] At 10:00 a.m., the camera detects unusual activity inside the vehicle (e.g., unusually little movement) and sends a notification to the supervisor, who then reviews the camera footage through the app and takes appropriate action.

[0280] Prompt Sentence Examples

[0281] "Apply a facial recognition algorithm to the input camera feed, identify the passenger's face, and send the results to a server."

[0282] "Apply anomaly detection algorithms to the in-car camera feed to detect anomalies and send you a notification."

[0283] As described above, this system can ensure a high level of passenger safety in self-driving vehicles.

[0284] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0285] Step 1:

[0286] The terminal (face recognition camera) takes a picture of the face of the passenger boarding the transportation at the entrance.

[0287] Input: Video feed from facial recognition camera.

[0288] Output: Passenger face image.

[0289] How it works: Using a high-performance camera (e.g., Sony IMX sensor), the system captures the faces of passengers in real time as they board the vehicle. This video feed is then used by subsequent facial recognition algorithms.

[0290] Step 2:

[0291] The facial image captured by the device (face recognition camera) is sent to the server.

[0292] Input: Passenger face image.

[0293] Output: Facial image data sent to the server.

[0294] Specific operation: Using the edge computing function on the device, the captured facial image is uploaded to the server in real time (e.g., using 5G communication).

[0295] Step 3:

[0296] The server uses a facial recognition algorithm to identify the passenger.

[0297] Input: Submitted face image data.

[0298] Output: Identified passenger information.

[0299] Specific operation: A facial recognition algorithm (e.g., OpenCV or TensorFlow) is executed on the server to recognize the passenger's face from the transmitted facial image data. The recognized face is reflected in the passenger database.

[0300] Step 4:

[0301] The server lists passengers who have not boarded by a specified time.

[0302] Input: Ride database.

[0303] Output: A list of passengers who have not boarded.

[0304] What it does: It checks the current trip database against the default schedule and compiles a list of passengers who have not boarded by a given time.

[0305] Step 5:

[0306] The server automatically contacts passengers who have not yet boarded the train.

[0307] Input: List of absent passengers, contact information, generative AI model.

[0308] Output: The contact message sent.

[0309] Specific operation: Using a generative AI model, automatically generate a message for passengers who have not yet boarded the car, saying "You have not boarded. Please tell us the reason." and send it to registered contacts (e.g., using the Twilio API).

[0310] Step 6:

[0311] The user (passenger) receives the message and replies via a smartphone app whether or not they would like to board and the reason for doing so.

[0312] Input: The contact message sent by the server.

[0313] Output: Reply message from passenger.

[0314] Specific operation: The user (passenger) receives a message via the smartphone app and responds with information about the ride status. This reply is sent to the server.

[0315] Step 7:

[0316] The server receives the passenger's reply and updates the ride database.

[0317] Input: Reply message from passenger, current ride database.

[0318] Output: Updated trip database.

[0319] Specific operation: The server analyzes the received reply message and updates the ride database, thereby keeping the ride status up to date in real time.

[0320] Step 8:

[0321] The device (in-vehicle camera) monitors the interior of the transportation vehicle and detects abnormal or infrequent movement.

[0322] Input: In-car camera video feed.

[0323] Output: Anomaly detection data.

[0324] How it works: Cameras installed inside the vehicle monitor passenger movements and analyze the captured footage using AI technology. If any unusual or minor movements are detected, the information is sent to a server.

[0325] Step 9:

[0326] The server detects an anomaly and sends a notification to the monitor.

[0327] Input: Anomaly detection data, monitor contact information.

[0328] Output: The error notification message sent.

[0329] Specific operation: The server receives the anomaly detection data, and if an anomaly is detected, it sends a notification to the monitor (for example, by email or SMS). The monitor receives this notification and takes the necessary action.

[0330] The above steps can ensure a high level of passenger safety in autonomous vehicles.

[0331] 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.

[0332] This invention uses facial recognition cameras, AI technology, an automatic notification system, and an emotion engine to ensure the safety of children in childcare facilities and on school buses. The combination of the emotion engine enables the system to recognize the emotions of children and users, enabling more accurate anomaly detection and response. The system aims to monitor children's safety in real time while reducing the burden on caregivers.

[0333] An embodiment of a kindergarten attendance management system

[0334] System Overview

[0335] The server serves as the central control unit of the attendance management system, managing the database, running the face recognition algorithm, and the emotion engine.

[0336] The terminal (facial recognition camera) is installed at the entrance of the childcare facility, photographs the faces of children arriving at the facility, and identifies them in real time.

[0337] Users (caregivers and parents) receive information through the system's app and perform the necessary operations.

[0338] The emotion engine provides additional functionality to analyze the emotions of children and parents and detect anomalies.

[0339] Program processing explanation

[0340] 1. The user (caregiver or administrator) starts the system and begins monitoring a new day of attendance.

[0341] The server reads the schedule of the daycare facility and starts managing the attendance status for today.

[0342] 2. The device (face recognition camera) takes real-time photos of children arriving at the childcare facility and identifies them using a facial recognition algorithm.

[0343] The server receives the facial recognition results and updates the child's attendance database.

[0344] 3. The emotion engine analyzes the child's emotions from the acquired facial images and behavioral data.

[0345] The server records the child's emotional state in a database based on the analysis results of the emotion engine.

[0346] 4. The server lists children who have not arrived by the designated arrival time (e.g., 9:00).

[0347] The server checks the attendance status and generates a list of children who have not arrived by the specified time.

[0348] 5. The server sends an automatic message to the parents of children who are not attending school.

[0349] The server uses a generative AI to create a phone call or message and send it to the parent saying, "Your child has not come to school. Please let us know the reason."

[0350] 6. The user (parent) receives the message and replies using the smartphone app whether or not the child will attend school and the reason.

[0351] The server receives the response from the parents and updates the attendance status database.

[0352] 7. The emotion engine analyzes the text data contained in the parent's reply and recognizes the parent's emotions.

[0353] The server records the parent's emotional state in a database based on the analysis results of the emotion engine.

[0354] 8. If the server does not receive a response from the parent within a certain period of time (e.g., 15 minutes) or detects an abnormality, it will notify the caregiver.

[0355] The server generates a warning message stating, "We are unable to confirm attendance for the child with unanswered ID 12345. Action is required," and sends it to the caregiver's device.

[0356] Embodiment of school bus monitoring system

[0357] System Overview

[0358] The device (bus camera) is installed inside the school bus and monitors the children's boarding times and behavior.

[0359] The server collects data from the on-board cameras and runs algorithms to detect anomalies.

[0360] Users (caregivers) can view the internal camera footage from the bus in real time on their smartphones or tablets.

[0361] The emotion engine analyzes the emotions of children on the bus and assists in anomaly detection.

[0362] Program processing explanation

[0363] 1. The device (in-bus camera) records the time the child boards the bus and sends the data to the server.

[0364] The server receives the boarding time data and updates the boarding status database.

[0365] 2. The device (in-bus camera) monitors the children's behavior and periodically sends data to the server.

[0366] The server receives behavioral data from the camera and uses AI technology to detect abnormalities.

[0367] 3. The emotion engine analyzes the emotions of the children on the bus from the acquired facial images and behavioral data.

[0368] The server records the child's emotional state in a database based on the analysis results of the emotion engine.

[0369] 4. If the server detects no activity for a certain period of time or detects an abnormality, it will send a notification to the caregiver.

[0370] The server runs an anomaly detection algorithm and sends real-time notifications to caregivers if an anomaly is detected.

[0371] 5. The user (caregiver) receives a notification and checks the camera footage inside the bus.

[0372] Childcare workers will check the situation on the bus through the app and respond as necessary.

[0373] Specific examples

[0374] As a concrete example, here is a simulation of a day at kindergarten:

[0375] At 8:00 a.m., the user (caregiver) starts the system and begins monitoring the day the children attend school.

[0376] When a child arrives at the entrance, a device (face recognition camera) takes a picture of their face and sends the data to the server.

[0377] At 8:30, the server performs facial recognition and updates the database of children who have already arrived at the school.

[0378] At 8:35, the emotion engine analyzes the facial image and behavioral data and recognizes the child's emotion as "anxiety."

[0379] At 9:00, the server lists the children who have not attended school and automatically sends a message to their parents.

[0380] The user (parent) receives the message and replies from the app at 8:50 a.m. explaining the reason for the child's absence, such as "I'm not feeling well."

[0381] At 9:15, the server checks the response from the parents and updates the attendance database.

[0382] The emotion engine analyzes the parents' replies and recognizes the emotion "worry."

[0383] At 10:00, the device (camera inside the bus) sends data on the children's behavior to the server, which analyzes it.

[0384] At 10:10, the emotion engine recognizes the emotion of the children on the bus as "excited."

[0385] At 10:30, the server detects an abnormality (e.g., a motionless child) and sends a notification to the user (caregiver).

[0386] The user (caregiver) receives the notification, checks the camera footage inside the bus, and takes the necessary action.

[0387] The above is an embodiment of the invention. By combining an emotion engine, it is possible to detect and respond to abnormalities with higher accuracy, thereby ensuring a high level of child safety while reducing the burden on caregivers.

[0388] The processing flow will be explained below.

[0389] Processing steps of the attendance management system

[0390] Step 1:

[0391] The user (caregiver or administrator) starts the system and begins monitoring the new day of attendance.

[0392] The caregiver presses the "Start Day of School" button on the system screen to start the system.

[0393] The server checks the daycare schedule, initializes the database based on today's date, and sets the "day of school start" status.

[0394] Step 2:

[0395] The device (face recognition camera) takes real-time photos of children arriving at the daycare facility.

[0396] A camera installed at the entrance automatically detects the faces of children arriving at the school and sends image data to a server in real time.

[0397] Step 3:

[0398] The server runs a facial recognition algorithm to analyze the transmitted facial image data.

[0399] The server compares the facial image data with existing facial data in the database.

[0400] Get the matching child's ID and update the corresponding database entry to "already in school."

[0401] Step 4:

[0402] The server sends the facial images and behavioral data to the emotion engine.

[0403] The emotion engine analyzes a child's emotions from facial expressions, movements, and other behavioral data.

[0404] Based on the analysis results, the server records the child's emotional state in a database.

[0405] Step 5:

[0406] The server lists children who have not arrived by the designated arrival time (e.g., 9:00).

[0407] The server checks the attendance status and generates a list of children who have not arrived by the specified time.

[0408] Step 6:

[0409] The server sends an automatic message to the parents of children who are not attending school.

[0410] The server uses a generative AI to create a phone call or message and send it to the parent saying, "Your child has not come to school. Please let us know the reason."

[0411] Step 7:

[0412] The user (parent) receives the message and replies using a smartphone app to indicate whether or not the child will attend school and the reason for the attendance.

[0413] Parents check the notification in the app, enter the reason (e.g., "absent due to illness"), and submit.

[0414] Step 8:

[0415] The server receives the response from the parents and updates the attendance status database.

[0416] The server records the received reason in a database and updates the corresponding child's status to "absent" or "late", etc.

[0417] Step 9:

[0418] The server sends the text data contained in the response from the parent to the emotion engine.

[0419] The emotion engine analyzes the parent's response and recognizes their emotional state (e.g., "worried" or "relieved").

[0420] Based on the analysis results, the server records the parent's emotional state in a database.

[0421] Step 10:

[0422] If the server does not receive a response from the parent within a certain period of time (e.g., 15 minutes) or detects an abnormality, it notifies the caregiver.

[0423] The server generates a warning message stating, "We are unable to confirm attendance for the child with unanswered ID 12345. Action is required," and sends it to the caregiver's device.

[0424] Processing steps of the school bus monitoring system

[0425] Step 1:

[0426] The device (camera inside the bus) records the time the child boards the bus and sends the data to the server.

[0427] A camera installed at the bus entrance automatically photographs children boarding the bus and sends the boarding time data to a server.

[0428] Step 2:

[0429] The server receives the boarding time data and updates the boarding status database.

[0430] The server performs facial recognition and records the ID of the child riding and the time of boarding in a database.

[0431] Step 3:

[0432] The device (a camera inside the bus) monitors the children's behavior and periodically sends data to the server.

[0433] Cameras inside the bus monitor children's movements in real time, capturing and transmitting image data at regular intervals.

[0434] Step 4:

[0435] The server receives behavioral data from the camera and uses AI technology to detect abnormalities.

[0436] The server analyzes behavioral data and detects abnormalities such as no activity for a certain period of time.

[0437] Step 5:

[0438] The server sends the facial images and behavioral data to the emotion engine.

[0439] The emotion engine analyzes the emotions of children on the bus from facial expressions, movements, and other behavioral data.

[0440] Based on the analysis results, the server records the child's emotional state in a database.

[0441] Step 6:

[0442] If the server detects an abnormality, it will send a notification to the caregiver.

[0443] Based on the anomaly detection algorithm, the server generates a notification stating, "There has been no activity from ID12345 on the bus for more than 10 minutes. Check is required." and sends it to the caregiver's device.

[0444] Step 7:

[0445] The user (caregiver) receives a notification and checks the camera footage inside the bus.

[0446] Caregivers can check notifications on their smartphones or tablets and use the app's camera feed function to view real-time footage.

[0447] If necessary, the childcare provider will contact the bus driver or other staff to determine the actual situation and respond accordingly.

[0448] Based on these processing steps, the system of the present invention can ensure a high level of safety for children in childcare facilities and on school buses. By combining it with an emotion engine, more accurate anomaly detection and appropriate responses can be achieved.

[0449] Example 2

[0450] 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."

[0451] Conventional child safety management systems in childcare facilities and vehicles used to transport children only monitor the children's arrival and departure status and behavior, but do not analyze and respond to their emotions. This makes it difficult to grasp the emotional state of children and their parents and to accurately detect and respond to abnormalities. In addition, notifications and contact with parents are done manually, which places a heavy burden on childcare workers and makes it difficult to respond in real time.

[0452] 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.

[0453] In this invention, the server includes means for monitoring the attendance status of children at the childcare facility using a face recognition camera, means for automatically contacting parents of children who have not arrived by a specified time, means for receiving responses from parents and updating the system based on the responses, means for notifying caregivers when there is no response from the parents or when an abnormality is detected, and means for analyzing the emotions of the children and parents using an emotion engine to detect abnormalities.This makes it possible to respond based on the emotional states of the children and parents, allowing for early detection of abnormalities and rapid response, as well as reducing the burden on caregivers.

[0454] A "face recognition camera" is a camera device that photographs the faces of children arriving at kindergarten and analyzes the images in real time.

[0455] "Automatic contact means" is a function that uses an automatic notification system to contact parents of children who have not arrived at the school by a specified time.

[0456] "Means for receiving responses from parents" refers to a function that inputs information provided by parents into the system and updates the attendance status database based on that information.

[0457] "Means for detecting abnormalities" refers to a function for identifying abnormal conditions based on the behavior and emotional analysis results of children and parents.

[0458] "Means for notifying caregivers" is a function that sends warnings and notifications to caregivers when an abnormality is detected or when there is no response from the parent.

[0459] The "emotion engine" is a function that analyzes the emotions of children and parents from facial images and text data and determines their state.

[0460] "Camera installed in a vehicle used for transporting children to school" refers to a camera device installed inside a bus or vehicle used for transporting children to school, to monitor the boarding time and behavior of children.

[0461] "Artificial intelligence technology" refers to algorithms and models that enable highly automated data analysis, recognition, prediction, and other processes.

[0462] A "generative AI model" is an AI system equipped with natural language generation technology that is used to create notification content for parents.

[0463] The present invention is a system for ensuring the safety of children in childcare facilities and vehicles that transport them to and from school, and uses facial recognition cameras, AI technology, an automatic notification system, and an emotion engine. Specific methods for implementing the invention are described below.

[0464] System Configuration

[0465] 1. Server

[0466] The server functions as the central control device of the attendance management system. Specifically, it performs the following processes:

[0467] Facial recognition algorithm: Analyzes image data sent from facial recognition cameras in real time to identify children.

[0468] Emotion engine: Analyzes the emotions of children and parents from captured facial images and behavioral data.

[0469] Automated notification system: Generates and sends messages to contact parents of children who have not arrived at school by the designated time. Uses generative AI models to create notifications in natural language.

[0470] Database management: Centrally manages attendance data, children's emotional data, parental response data, etc.

[0471] 2. Device (face recognition camera)

[0472] The facial recognition camera is installed at the entrance of the childcare facility and takes real-time pictures of the faces of children as they arrive. The captured facial images are immediately sent to a server. The camera also has a time stamp function that adds time information to the image data.

[0473] 3. Terminal (Bus Camera)

[0474] The cameras installed inside the buses will monitor the children's boarding times and activities in real time, and this data will also be sent to a server for analysis.

[0475] 4. Users (caregivers and guardians)

[0476] Parents and caregivers connect to the system through a smartphone or tablet app, and responses and information from parents are sent via the app, which updates the system accordingly.

[0477] Specific examples

[0478] Below is a specific scenario of daytime attendance management.

[0479] 8:00 AM: The childcare worker starts the system and starts monitoring the new day. The server loads the schedule based on today's date and starts managing the attendance status.

[0480] Arrival: When a child arrives at the entrance of the childcare facility, a facial recognition camera captures their face and sends the image to a server, which uses a facial recognition algorithm to identify the child and update the attendance database.

[0481] 8:35: The emotion engine analyzes the facial image and identifies the child's emotion as "anxiety." The server records this information in a database.

[0482] 9:00 AM: The server creates a list of children who have not arrived by the designated arrival time (e.g., 9:00 AM), and uses a generative AI model to automatically send a message to the parents stating, "Your child has not arrived. Please let us know the reason."

[0483] Parent response: The parent receives the message and replies from the app at 8:50 a.m., "I'm sick and will be absent." The server receives the parent's response and updates the attendance database.

[0484] Sentiment analysis: The emotion engine analyzes the parent's response and recognizes and records the emotion "worry."

[0485] Monitoring inside the bus: At 10:00, the camera inside the bus captures data on the children's behavior and sends it to the server, which analyzes it.

[0486] Anomaly detection: At 10:30, the server detects an anomaly (for example, a child not moving) and sends a notification to the caregiver saying, "An abnormal condition has been detected. Please check the situation on the bus."

[0487] Caregiver response: Caregivers receive a notification, check the camera footage on the bus, and take any necessary action.

[0488] Prompt Sentence Examples

[0489] "Your child has not attended school. Please let us know the reason."

[0490] The above is a concrete embodiment for carrying out the invention. The overall flow of the system and the function of each component are explained in detail to enable the realization of the invention.

[0491] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0492] The flow of this system's program processing

[0493] Step 1:

[0494] The user (caregiver or administrator) starts the system and begins monitoring the new day of attendance.

[0495] Input: System startup operation, today's date

[0496] Output: Read the childcare facility schedule and get ready to monitor attendance

[0497] Specific behavior:

[0498] The caregiver presses the "Start Monitoring" button using a dedicated management application.

[0499] The server gets today's date and reads the daycare schedule from the database.

[0500] The server starts monitoring the attendance status and displays when it is ready.

[0501] Step 2:

[0502] The device (face recognition camera) takes real-time photos of children arriving at the daycare facility and sends the facial image data to the server.

[0503] Input: Child's face image, time stamp

[0504] Output: Sending face image data to the server

[0505] Specific behavior:

[0506] When a child reaches the entrance, a facial recognition camera automatically captures their face.

[0507] Information about the time of photographing is added to the face image data.

[0508] Facial image data is sent from the camera to a server in real time.

[0509] Step 3:

[0510] The server analyzes the transmitted facial image data using a facial recognition algorithm and updates the attendance database.

[0511] Input: Face image data, time stamp

[0512] Output: Update the attendance database

[0513] Specific behavior:

[0514] The server inputs the facial image data into a facial recognition algorithm and matches it with the child's facial information registered in a database.

[0515] Based on the recognition results, the child's attendance record is added to the database, including the time of arrival and the facial image.

[0516] Step 4:

[0517] The emotion engine analyzes the child's emotions from the captured facial image, and the server records the results in a database.

[0518] Input: Facial image data, behavioral data

[0519] Output: Sentiment analysis results, update of sentiment database

[0520] Specific behavior:

[0521] The emotion engine analyzes the child's facial expressions from the facial image data and determines their emotional state (e.g., "joy," "anxiety," etc.).

[0522] The server receives the analysis results of the emotion engine and records the child's emotional state in a database.

[0523] Step 5:

[0524] The server lists the children who have not arrived by the designated arrival time (e.g. 9:00).

[0525] Input: attendance record, current time

[0526] Output: List of children not attending kindergarten

[0527] Specific behavior:

[0528] The server checks the attendance records and generates a list of children who have not arrived by the specified time.

[0529] Step 6:

[0530] The server automatically sends a message to the parents of children who are not attending school.

[0531] Input: List of children not attending kindergarten, prompt text

[0532] Output: Parental notification message

[0533] Specific behavior:

[0534] The server uses the generative AI model to create an automated notification about the non-attendance status, which includes the message, "Your child has not attended school. Please let us know the reason."

[0535] The generated notification will be sent to the parents via phone call or message.

[0536] Step 7:

[0537] The user (parent) receives the message and replies using the smartphone app, and the server records the information in a database.

[0538] Input: Parent's reply message

[0539] Output: Update the attendance status database

[0540] Specific behavior:

[0541] Parents check the notification on their smartphone app and reply by entering a reason, such as "I'm absent because I'm sick."

[0542] The server receives the response from the parents and updates the attendance status database.

[0543] Step 8:

[0544] The emotion engine analyzes the text contained in the responses from parents, and the server records the results in a database.

[0545] Input: Reply message

[0546] Output: Parent's emotion analysis results, emotion database update

[0547] Specific behavior:

[0548] The emotion engine analyzes the parent's reply message and recognizes emotions (e.g., "worried") from the text.

[0549] The server records the emotion analysis results in a database.

[0550] Step 9:

[0551] If the server does not receive a response from the parent within a certain period of time or detects an abnormality, it sends a notification to the caregiver.

[0552] Input: Response status, anomaly detection results

[0553] Output: Warning message to caregivers

[0554] Specific behavior:

[0555] The server continues to monitor if there is no response from the parent or if an abnormality is detected.

[0556] If there is no response within a certain period of time (e.g. 15 minutes), a warning message will be generated stating "We are unable to confirm attendance for child with unanswered ID 12345. Action is required." and sent to the caregiver.

[0557] (Application example 2)

[0558] 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."

[0559] Conventional worker management systems make it difficult for managers to grasp the attendance status and physical condition of each worker, making it difficult for managers to efficiently monitor worker safety and health. Furthermore, delays in responding to abnormalities can pose a risk to safety and the working environment, so a solution to these issues was needed.

[0560] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0561] In this invention, the server includes a means for monitoring the status of employees clocking in and out of the facility using a facial recognition camera, a means for automatically contacting the guardians of employees who have not arrived at work by a specified time, a means for receiving responses from the guardians and updating the system based on those responses, a means for notifying a manager if there is no response from the guardian or if an abnormality is detected, a means for analyzing the facial and behavioral data of workers and using an emotion engine to detect signs of fatigue or stress, and an automatic notification system for sending a real-time notification to a manager if an abnormality is detected. This allows the manager to understand not only the attendance status of workers but also their emotional state, enabling them to respond quickly if an abnormality occurs.

[0562] A "facial recognition camera" is a device that extracts facial features from received image data in order to identify a particular person.

[0563] "Facilities" refers to buildings and places where workers enter and exit in order to perform their work.

[0564] "Arriving at work" refers to the act of a worker arriving at the designated work location and beginning work.

[0565] "Clocking out" refers to the act of a worker leaving the designated work area and completing work.

[0566] "Manager" means a person who is responsible for supervising and managing the operation of workers or systems.

[0567] "Guardian" refers to a person who has the responsibility to supervise a worker who is a minor.

[0568] "Response" refers to the act of replying to a notification or the like.

[0569] An "abnormality" refers to an unexpected problem or deviation from normal business operations or behavior.

[0570] "Worker" means a person employed to perform a specific task at an establishment.

[0571] The "emotion engine" is software that analyzes a person's emotional state from received image data and behavioral data.

[0572] An "automatic notification system" is a system that automatically sends a notification to a pre-defined recipient when an abnormality is detected.

[0573] "Safety" refers to a state in which workers can perform their work without exposure to danger or risk.

[0574] "Fatigue" refers to a state in which a worker's physical and mental strength is exhausted due to work, making it difficult for them to perform their normal duties.

[0575] "Stress" refers to a state in which a worker feels pressure or tension due to their work or environment, making it difficult for them to carry out their normal work.

[0576] To implement this invention, several major components are required, including a facial recognition camera, an emotion engine for analyzing the emotional state of workers, an automatic notification system, and a database management system. A server-based system configuration is also essential to integrate these components.

[0577] System Hardware

[0578] 1. Facial recognition cameras (e.g., Logitech C920) are installed at entrances and key areas within the facility to monitor worker attendance and behavior in real time.

[0579] 2. A computer server (e.g., an AWS EC2 instance) acts as the central control unit, managing the database, running the facial recognition algorithm, and the emotion engine.

[0580] 3. Notification terminals (e.g., smartphones and tablets) are used by administrators to receive notifications from the system and respond in real time.

[0581] Software Components

[0582] 1. Facial recognition algorithms (e.g. OpenCV) are used to identify and identify faces from image data acquired from a camera.

[0583] 2. Emotion Engine is software that analyzes the emotional state of workers from image data and behavioral data.

[0584] 3. A database management system (e.g., SQLite) is used to store and manage employee attendance data and emotion analysis results.

[0585] 4. The automatic notification system provides a mechanism for sending real-time notifications to administrators when an abnormality is detected.

[0586] Program processing explanation

[0587] The server processes image data obtained from the facial recognition camera to identify workers and record their attendance status. It also inputs workers' facial and behavioral data into an emotion engine in real time to analyze signs of fatigue and stress. If an abnormality is detected, the server sends a real-time warning message to the administrator's notification terminal via an automatic notification system. Administrators can receive the notification and take appropriate measures.

[0588] Specific examples

[0589] At 8:00 AM, Worker A enters the facility and is captured by a facial recognition camera. The server uses a facial recognition algorithm to identify Worker A and update the attendance database. At 10:00 AM, the emotion engine analyzes Worker A's behavioral data and facial image to detect signs of fatigue. This information is recorded in the database, and at the same time, the server notifies the manager in real time through an automatic notification system. The manager receives the notification and can take appropriate action, such as encouraging Worker A to take a break.

[0590] Prompt Sentence Examples

[0591] "Generate a Python program to develop a safety and health management system using facial recognition and emotion analysis of workers in a logistics center. Use OpenCV for facial recognition and a custom Emotion Engine for emotion analysis, and add a function to send notifications when an anomaly is detected."

[0592] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0593] Step 1:

[0594] Image acquisition by face recognition camera

[0595] The terminal (face recognition camera) is installed at the entrance and exit of the facility and captures the facial images of workers as they pass through. The input is real-time video data captured by the camera, and the output is facial image data of the workers. Specifically, the camera periodically captures video and sends the data to a server.

[0596] Step 2:

[0597] Facial Recognition Processing

[0598] The server receives the facial image data sent from the terminal (face recognition camera) and identifies the worker using a facial recognition algorithm (e.g., OpenCV). The input is the facial image data, and the output is the ID of the identified worker. Specifically, the server runs the facial recognition algorithm, extracts features from the acquired facial image data, and compares them with known facial data in a database.

[0599] Step 3:

[0600] Update attendance database

[0601] The server updates the attendance database using the ID of the worker identified by the facial recognition process. The input is the ID of the identified worker, and the output is an updated attendance status database. Specifically, the server saves the identified worker's attendance time and ID in the database, and reflects the attendance status in real time.

[0602] Step 4:

[0603] Emotional state analysis

[0604] The server inputs the facial image data and behavioral data sent from the terminal (face recognition camera) into the emotion engine and analyzes the worker's emotional state. The input is facial image data and behavioral data, and the output is the detected emotional state (e.g., fatigue, stress, etc.). Specifically, the server uses the emotion engine to analyze facial expressions and behavioral patterns to determine the worker's emotions.

[0605] Step 5:

[0606] Anomaly detection and notification

[0607] The server detects anomalies based on the analysis results of the emotion engine, and if an anomaly is confirmed, it uses an automatic notification system to send a warning message to the administrator's notification terminal in real time. The input is the analysis result (emotional state), and the output is a warning message for the administrator. Specifically, the server runs the anomaly detection algorithm, and if an abnormal state such as fatigue or stress is detected, it generates a notification message and sends it to the administrator's smartphone or tablet.

[0608] Step 6:

[0609] Administrator response

[0610] The user (administrator) receives the notification message from the server and takes specific action through the app. The input is the notification message, and the output is the actual response procedure (e.g., instructing workers to take breaks). The specific action is for the administrator to check the notification and issue appropriate instructions to the workers.

[0611] Prompt Sentence Examples

[0612] "Generate a Python program to develop a safety and health management system using facial recognition and emotion analysis of workers in a logistics center. Use OpenCV for facial recognition and a custom Emotion Engine for emotion analysis, and add a function to send notifications when an anomaly is detected."

[0613] 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.

[0614] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0615] 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.

[0616] [Second embodiment]

[0617] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0618] 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.

[0619] 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).

[0620] 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.

[0621] 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.

[0622] 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).

[0623] 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.

[0624] 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.

[0625] 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.

[0626] 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.

[0627] 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.

[0628] 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."

[0629] This invention uses facial recognition cameras, AI technology, and an automatic notification system to ensure the safety of children at childcare facilities and on school buses. The system aims to monitor children's attendance in real time and detect abnormalities early, while reducing the burden on caregivers.

[0630] An embodiment of a kindergarten attendance management system

[0631] System Overview

[0632] The server is the central control unit of the attendance management system, managing the database, running the facial recognition algorithm, and sending notifications.

[0633] The terminal (facial recognition camera) is installed at the entrance of the childcare facility, photographs the faces of children arriving at the facility, and identifies them in real time.

[0634] Users (caregivers and parents) receive information through the system's app and perform the necessary operations.

[0635] Program processing explanation

[0636] 1. The user (caregiver or administrator) starts the system and begins monitoring a new day of attendance.

[0637] The server reads the schedule of the daycare facility and starts managing the attendance status for today.

[0638] 2. The device (face recognition camera) takes real-time photos of children arriving at the childcare facility and identifies them using a facial recognition algorithm.

[0639] The server receives the facial recognition results and updates the child's attendance database.

[0640] 3. The server lists children who have not arrived by the designated arrival time (e.g., 9:00).

[0641] The server checks the attendance status and generates a list of children who have not arrived by the specified time.

[0642] 4. The server automatically sends a message to the parents of children who have not arrived at school by the specified time.

[0643] The server uses the generation AI to send a message to the parent's contacts, for example, "Your child is not attending school. Please tell us why."

[0644] 5. The user (parent) receives the message and replies via the smartphone app whether or not the child will attend school and the reason.

[0645] The server receives the response from the parents and updates the attendance database.

[0646] 6. The server notifies the caregiver if there is no response from the parent or if an abnormality is detected.

[0647] If an abnormality is detected, the server automatically sends a warning message to the caregiver's device.

[0648] Embodiment of school bus monitoring system

[0649] System Overview

[0650] The device (bus camera) is installed inside the school bus and monitors the children's boarding times and behavior.

[0651] The server collects data from the on-board cameras and runs algorithms to detect anomalies.

[0652] Users (caregivers) can view the internal camera footage from the bus in real time on their smartphones or tablets.

[0653] Program processing explanation

[0654] 1. The device (in-bus camera) records the time the child boards the bus and sends the data to the server.

[0655] The server receives the boarding time data and records it in a database.

[0656] 2. The device (in-bus camera) monitors the children's behavior and periodically sends data to the server.

[0657] The server receives behavioral data from the camera and uses AI technology to detect abnormalities.

[0658] 3. The server sends a notification to the caregiver if there is no activity for a certain period of time or if an abnormality is detected.

[0659] The server runs an anomaly detection algorithm and sends real-time notifications to caregivers if an anomaly is detected.

[0660] 4. The user (caregiver) receives a notification and checks the internal camera footage from the bus.

[0661] Childcare workers will check the situation on the bus through the app and respond as necessary.

[0662] Specific examples

[0663] As a concrete example, here is a simulation of a day at kindergarten:

[0664] At 8:00 a.m., the user (caregiver) starts the system and begins monitoring the day the children attend school.

[0665] When a child arrives at the entrance, a device (face recognition camera) takes a picture of their face and sends the data to the server.

[0666] At 8:30, the server performs facial recognition and updates the database of children who have already arrived at the school.

[0667] At 9:00, the server lists the children who have not attended school and automatically sends a message to their parents.

[0668] The user (parent) receives the message and replies from the app at 8:50 a.m. explaining the reason for attending school.

[0669] At 9:15, the server checks the response from the parents and updates the attendance database.

[0670] At 10:00, the device (the camera inside the bus) sends some data on the children's behavior to the server, which analyzes it.

[0671] At 10:30, the server detects an abnormality (e.g., a motionless child) and sends a notification to the user (caregiver).

[0672] The user (caregiver) receives the notification, checks the camera footage inside the bus, and takes the necessary action.

[0673] The above is an embodiment of the invention. The present invention can reduce the burden on caregivers and ensure a high level of child safety.

[0674] The processing flow will be explained below.

[0675] Processing steps of the attendance management system

[0676] System startup and preparation

[0677] Step 1:

[0678] The user (caregiver or administrator) starts the system and begins monitoring the new day of attendance.

[0679] The caregiver presses the "Start Day of School" button on the system screen to start the system.

[0680] The server checks the childcare facility's schedule and initializes the database based on today's date.

[0681] Facial recognition when attending kindergarten

[0682] Step 2:

[0683] The device (face recognition camera) takes real-time photos of children arriving at the daycare facility.

[0684] Cameras are installed at the entrance and automatically detect the faces of children arriving at the school.

[0685] The camera transmits the facial image data to a server.

[0686] Step 3:

[0687] The server runs a facial recognition algorithm to analyze the transmitted facial image data.

[0688] The server compares the facial image data with existing facial data in the database.

[0689] Get the matching child's ID and update the corresponding database entry to "already in school."

[0690] Checking attendance status and contacting

[0691] Step 4:

[0692] The server lists children who have not arrived by the designated arrival time (e.g., 9:00).

[0693] The server compares the childcare facility's schedule with the child's attendance data and lists children who have not attended.

[0694] Step 5:

[0695] The server sends an automatic message to the parents of children who are not attending school.

[0696] The server uses a generative AI to create a phone call or message and send it to the parent saying, "Your child has not come to school. Please let us know the reason."

[0697] Parental Response Management

[0698] Step 6:

[0699] The user (parent) receives the message and replies using a smartphone app to indicate whether or not the child will attend school and the reason for the attendance.

[0700] Parents check the notification in the app, enter the reason (e.g., "absent due to illness"), and submit.

[0701] Step 7:

[0702] The server receives the response from the parents and updates the attendance status database.

[0703] The server records the received reason in a database and updates the status of the corresponding child.

[0704] Notification in case of an abnormality

[0705] Step 8:

[0706] If the server does not receive a response from the parent within a certain period of time (e.g., 15 minutes) or detects an abnormality, it notifies the caregiver.

[0707] The server generates a warning message saying, "We are unable to confirm attendance for child ID 12345, who has not responded. Action is required."

[0708] The server sends this message to the childcare provider's terminal.

[0709] Processing steps of the school bus monitoring system

[0710] Ride data collection and monitoring

[0711] Step 1:

[0712] The device (camera inside the bus) records the time the child boards the bus and sends the data to the server.

[0713] Cameras are installed at the entrances to the buses and automatically capture images of children boarding.

[0714] The camera sends a facial image to a server and records the time of boarding.

[0715] Step 2:

[0716] The server receives the boarding time data and updates the boarding status database.

[0717] The server performs facial recognition and records the ID of the child riding and the time of boarding in a database.

[0718] Behavior monitoring and anomaly detection

[0719] Step 3:

[0720] The device (a camera inside the bus) periodically captures images of children's behavior and sends the data to a server.

[0721] The cameras inside the bus monitor the children's movements and capture and transmit image data at regular intervals.

[0722] Step 4:

[0723] The server receives behavioral data from the camera and uses AI technology to detect abnormalities.

[0724] The server analyzes behavioral data and detects abnormalities such as no activity for a certain period of time.

[0725] Notification and confirmation in case of an abnormality

[0726] Step 5:

[0727] If the server detects an abnormality, it will send a notification to the caregiver.

[0728] Based on the anomaly detection algorithm, the server generates a notification stating, "There has been no activity from ID12345 on the bus for more than 10 minutes. Check is required." and sends it to the caregiver's device.

[0729] Step 6:

[0730] The user (caregiver) receives a notification and checks the camera footage inside the bus.

[0731] Caregivers can check notifications on their smartphones or tablets and use the app's camera feed function to view real-time footage.

[0732] If necessary, the childcare provider will contact the bus driver or other staff to determine the actual situation and respond accordingly.

[0733] Based on these processing steps, the system of the present invention can ensure a high level of child safety in childcare facilities and on buses.

[0734] Example 1

[0735] 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."

[0736] Conventional attendance management systems at childcare facilities require manual confirmation of children's attendance status and communication of that information to parents and caregivers, which is extremely time-consuming and labor-intensive. Furthermore, bus attendance is also primarily monitored manually, making it difficult to detect abnormalities early on. This increases the burden on caregivers and makes it difficult to ensure the safety of children, which has been an issue.

[0737] 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.

[0738] In this invention, the server includes a means for monitoring the attendance status of children at the childcare facility using a face recognition camera, a means for automatically contacting the parents of children who have not arrived by a specified time, a means for receiving responses from the parents and updating the database based on the responses, and a means for notifying the childcare worker if there is no response from the parents or if an abnormality is detected. This reduces the burden on the childcare worker and ensures a high level of child safety.

[0739] A "facial recognition camera" is a camera that captures a child's face and identifies the child using a facial recognition algorithm.

[0740] "Childcare facility" refers to any facility that provides childcare, such as kindergartens and nursery schools.

[0741] "Attendance status" is information indicating whether or not a child has attended a childcare facility.

[0742] "Guardian" means a child's parent or legal guardian.

[0743] "Automatic notification" is the process by which a system uses generative AI models to automatically create and send messages to specific recipients.

[0744] A "database" is a collection of information that is used to systematically manage and store information in a system.

[0745] "Abnormal" refers to a state that differs from a child's normal behavior or situation, such as not showing up to school or not moving around on the bus.

[0746] "Notification" is an operation in which the system sends specific information to a terminal to notify it.

[0747] "Means" refers to a set of methods or devices used to achieve a particular purpose.

[0748] An "in-bus camera" is a camera installed inside a school bus to monitor children's boarding times and behavior.

[0749] "Artificial intelligence technology" refers to all technologies that use machine learning and data analysis algorithms to automatically process and analyze data and support decision-making.

[0750] MODE FOR CARRYING OUT THE INVENTION

[0751] System Overview

[0752] The system of the present invention uses facial recognition cameras, AI technology, and an automatic notification system to ensure the safety of children at childcare facilities and on buses. The system consists of a server, terminals (facial recognition cameras and bus cameras), and users (caregivers and parents), and aims to monitor children's attendance in real time and detect any abnormalities early, while reducing the burden on caregivers.

[0753] Hardware and software used

[0754] The server is the central control unit of the attendance management system, managing the database, running the facial recognition algorithm, and sending notifications. In this case, a generative AI model is used.

[0755] The terminal (facial recognition camera) is installed at the entrance of the childcare facility, photographs the faces of children arriving at the facility, and identifies them in real time.

[0756] The device (bus camera) is installed inside the school bus and monitors the children's boarding times and behavior.

[0757] Users (caregivers and parents) receive information through the system's app and perform the necessary operations.

[0758] Program processing explanation

[0759] 1. When the system is started, the server loads the childcare facility's schedule and begins managing the day's attendance status. The server uses a generative AI model to analyze various data and generate notification messages.

[0760] 2. The device (face recognition camera) takes a real-time picture of the child as they arrive at the daycare center and identifies them using a face recognition algorithm. The face recognition results are sent to the server, which updates the child attendance database.

[0761] 3. The device (in-bus camera) records the time the child boards the bus and sends the data to a server. The server records this in a database and uses AI technology to detect any abnormalities.

[0762] 4. The server creates a list of children who have not arrived by the designated time and automatically sends a message to their parents using a generative AI model to create a message for parents and send it via email, SMS, etc.

[0763] 5. The user (parent) receives the notification and replies via the smartphone app whether or not the child will attend school and the reason for their attendance. The server receives the reply from the parent and updates the attendance database.

[0764] 6. If the server detects an abnormality or if there is no response from the parent, it will notify the caregiver, allowing the caregiver to understand the situation in real time and respond quickly.

[0765] Specific examples

[0766] As a concrete example, here is a simulation of a day at kindergarten:

[0767] At 8:00 a.m., the user (caregiver) starts the system and begins monitoring the day the children attend school.

[0768] When a child arrives at the entrance, a device (face recognition camera) takes a picture of their face and sends the data to the server.

[0769] At 8:30, the server performs facial recognition and updates the database of children who have already arrived at the school.

[0770] At 9:00, the server will list the children who have not attended school and automatically send a message to their parents. Example prompt: "Your child has not attended school. Please tell us the reason."

[0771] The user (parent) receives the message and replies from the app at 8:50 a.m. explaining the reason for attending school.

[0772] At 9:15, the server checks the response from the parents and updates the attendance database.

[0773] At 10:00, the device (the camera inside the bus) sends some data on the children's behavior to the server, which analyzes it.

[0774] At 10:30, the server detects an abnormality (e.g., a motionless child) and sends a notification to the user (caregiver).

[0775] The user (caregiver) receives the notification, checks the camera footage inside the bus, and takes the necessary action.

[0776] The above is an embodiment of the invention, which reduces the burden on caregivers and ensures a high level of child safety.

[0777] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0778] Step 1:

[0779] The user (caregiver or administrator) starts the system and begins monitoring the new day of attendance.

[0780] Input: The user taps the system wake-up button and enters schedule information.

[0781] Specific operation: The system starts when the user presses the start button on the management screen on their smartphone or PC.

[0782] Data processing / calculation: The server retrieves the current date and schedule information from the internal database and displays it.

[0783] Output: The childcare facility schedule is displayed on the admin page.

[0784] Step 2:

[0785] The device (facial recognition camera) takes real-time photos of the faces of children arriving at the childcare facility and identifies them using a facial recognition algorithm.

[0786] Input: Child's face image, previously registered face image data.

[0787] Specific operation: The camera detects motion and captures the child's face automatically.

[0788] Data processing / computation: A facial recognition algorithm runs on the server and matches the captured facial image with existing data in a database.

[0789] Output: The attendance information of children who match the matched result is updated.

[0790] Step 3:

[0791] The server lists the children who have not arrived by the designated arrival time (e.g. 9:00).

[0792] Input: School attendance database, specified time.

[0793] Specific operation: The server scans the attendance database and extracts children whose attendance could not be confirmed.

[0794] Data processing / calculation: Filter the attendance status in the database and generate a list of children who have not attended.

[0795] Output: At 9:00, the list of children who have not yet attended school is complete.

[0796] Step 4:

[0797] The server automatically sends a message to the parents of the listed children who have not attended school.

[0798] Input: List of non-attendance students, parent contact information.

[0799] How it works: Using a generative AI model, messages are automatically generated for each parent.

[0800] Data processing / computation: The AI ​​model creates a message and sends it via email, SMS, etc.

[0801] Output: A message is sent to the parent contact.

[0802] Step 5:

[0803] The user (parent) receives a notification and replies via a smartphone app whether or not their child will attend school and the reason for doing so.

[0804] Input: Parent response message.

[0805] Specific actions: Parents check the notification on their smartphone, open the reply form within the app, enter the reason, and submit.

[0806] Data processing / calculation: The server receives the reply and updates the attendance database.

[0807] Output: The updated attendance database is displayed.

[0808] Step 6:

[0809] If the server detects an abnormality, it will notify the caregiver.

[0810] Input: If there is no reply from the parent within a certain period of time, the AI ​​detects an anomaly.

[0811] Specific operation: The server monitors the response status and anomaly detection results.

[0812] Data processing / calculation: If an abnormality is detected or there is no response for a certain period of time, a notification will be automatically generated to the caregiver.

[0813] Output: A warning message is displayed on the caregiver's device.

[0814] Step 7:

[0815] The device (camera inside the bus) records the time the child boards the bus and sends the data to the server.

[0816] Input: Child boarding time data.

[0817] What it does: Cameras monitor children on the bus and record the time they board.

[0818] Data processing / calculation: The server receives the boarding time data and records it in the database.

[0819] Output: The registered boarding time data is updated.

[0820] Step 8:

[0821] The device (a camera inside the bus) monitors the children's behavior and periodically sends data to the server.

[0822] Input: Child behavior data.

[0823] How it works: Cameras inside the bus monitor children's behavior and record video data.

[0824] Data processing / calculation: The server receives behavioral data from the camera and analyzes it using AI technology.

[0825] Output: The analysis results are recorded in a database.

[0826] Step 9:

[0827] If the server detects no activity for a certain period of time or detects an abnormality, it will send a notification to the caregiver.

[0828] Input: Child activity data, anomaly detection results.

[0829] What it does: The server monitors the analysis results and generates a notification if it detects an anomaly.

[0830] Data processing / calculation: Run anomaly detection algorithms and create notifications if anomalies are detected.

[0831] Output: An abnormality notification is sent to the caregiver's device.

[0832] Step 10:

[0833] The user (caregiver) receives a notification and checks the internal camera footage of the bus.

[0834] Input: Anomaly notification, camera footage.

[0835] Specific operations: Childcare workers check notifications through the app and view real-time camera footage from inside the bus.

[0836] Data processing / calculation: Camera video data is streamed and provided to caregivers.

[0837] Output: The childcare worker can grasp the situation inside the bus in real time.

[0838] The above are the specific processing steps of the system and their detailed operations.

[0839] (Application example 1)

[0840] 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."

[0841] Ensuring passenger safety is important in autonomous vehicles, but conventional systems have been insufficient in monitoring passenger status and the interior of the vehicle. It has also been difficult to detect abnormalities in the passenger status or the interior of the vehicle in a timely manner and take necessary measures. This has led to a demand for an efficient method to ensure a high level of passenger safety.

[0842] 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.

[0843] In this invention, the server includes a means for monitoring the riding status of passengers using a face recognition camera installed at the entrance of the means of transportation, a means for automatically contacting passengers who have not boarded by a predetermined time, and a means for receiving responses from passengers and updating the system based on the responses. This makes it possible to quickly contact passengers even if they have not boarded by the predetermined time, and to grasp the riding status of passengers in real time.

[0844] "Transportation" refers to any means of transportation for carrying passengers, including autonomous vehicles.

[0845] A "face recognition camera" is a camera device that photographs and identifies the faces of passengers.

[0846] "Riding status" refers to the process and results of passengers boarding a means of transportation.

[0847] "Predetermined Time" means a specific time set for a Passenger to board a Transportation Vehicle.

[0848] "Automatic contact means" refers to a device or program that automatically communicates without human intervention when contact is required.

[0849] "Response" means a response from a passenger or observer who has received a communication.

[0850] "Means for updating the system" means a device or program that keeps the database and settings up to date based on passenger responses.

[0851] "Supervisor" means a person who monitors the safety of a means of transport and its passengers and takes any necessary action.

[0852] "In-camera video analysis means" refers to a device or program that analyzes video captured by a camera and detects abnormal movements or specific actions.

[0853] "In-vehicle behavior" refers to the actions and movements of passengers within a mode of transportation.

[0854] "AI technology" refers to technology that uses artificial intelligence to process data and perform identification and anomaly detection.

[0855] This invention is a system for ensuring passenger safety in autonomous vehicles, which uses a facial recognition camera, AI technology, and an automatic notification system. The system is configured as follows:

[0856] System Overview

[0857] The server is the central control unit of the system, managing the database, running the facial recognition algorithm, and sending notifications. Specifically, it can use a cloud-based system (e.g., AWS, Google Cloud).

[0858] The terminal (face recognition camera) is installed at the entrance of the transportation vehicle and takes pictures of the faces of passengers boarding the vehicle and identifies them in real time, using high-performance cameras and face recognition algorithms (e.g., OpenCV, TensorFlow).

[0859] Users (passengers and observers) receive information and perform necessary operations through the system's app, which is designed to work on both iOS and Android.

[0860] Program processing explanation

[0861] Ride monitoring

[0862] The device (a facial recognition camera) takes a picture of the passenger's face when boarding the transportation vehicle at the entrance and sends the data to a server, which uses a facial recognition algorithm to identify the passenger and update the passenger database. This process occurs in real time.

[0863] Automated Contact System

[0864] The server will list passengers who have not boarded by the designated time and automatically contact them. The server will then use a generative AI model to send a message to the passenger's contacts. For example, it could send a message saying, "You have not boarded. Please tell us why."

[0865] Passenger response

[0866] The user (passenger) receives the message and replies via the smartphone app whether or not they want to ride and the reason for the ride. The server receives this reply and updates the ride database.

[0867] Anomaly Detection System

[0868] The server receives data from the device (face recognition camera) and the in-car camera and uses AI technology to detect abnormalities. In particular, it analyzes unusually small movements and abnormal movements in real time, and if an abnormality is detected, it sends a notification to the monitor.

[0869] Specific implementation example

[0870] One day, an autonomous vehicle begins operation, and a facial recognition camera at the entrance monitors passengers. For example, Passenger A boards the vehicle at 8:00 AM, and the camera recognizes his face and sends the data to the server. At 8:30 AM, Passenger B, who has not boarded the vehicle, automatically receives a message saying, "You are not boarding. Please tell us the reason."

[0871] At 10:00 a.m., the camera detects unusual activity inside the vehicle (e.g., unusually little movement) and sends a notification to the supervisor, who then reviews the camera footage through the app and takes appropriate action.

[0872] Prompt Sentence Examples

[0873] "Apply a facial recognition algorithm to the input camera feed, identify the passenger's face, and send the results to a server."

[0874] "Apply anomaly detection algorithms to the in-car camera feed to detect anomalies and send you a notification."

[0875] As described above, this system can ensure a high level of passenger safety in self-driving vehicles.

[0876] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0877] Step 1:

[0878] The terminal (face recognition camera) takes a picture of the face of the passenger boarding the transportation at the entrance.

[0879] Input: Video feed from facial recognition camera.

[0880] Output: Passenger face image.

[0881] How it works: Using a high-performance camera (e.g., Sony IMX sensor), the system captures the faces of passengers in real time as they board the vehicle. This video feed is then used by subsequent facial recognition algorithms.

[0882] Step 2:

[0883] The facial image captured by the device (face recognition camera) is sent to the server.

[0884] Input: Passenger face image.

[0885] Output: Facial image data sent to the server.

[0886] Specific operation: Using the edge computing function on the device, the captured facial image is uploaded to the server in real time (e.g., using 5G communication).

[0887] Step 3:

[0888] The server uses a facial recognition algorithm to identify the passenger.

[0889] Input: Submitted face image data.

[0890] Output: Identified passenger information.

[0891] Specific operation: A facial recognition algorithm (e.g., OpenCV or TensorFlow) is executed on the server to recognize the passenger's face from the transmitted facial image data. The recognized face is reflected in the passenger database.

[0892] Step 4:

[0893] The server lists passengers who have not boarded by a specified time.

[0894] Input: Ride database.

[0895] Output: A list of passengers who have not boarded.

[0896] What it does: It checks the current trip database against the default schedule and compiles a list of passengers who have not boarded by a given time.

[0897] Step 5:

[0898] The server automatically contacts passengers who have not yet boarded the train.

[0899] Input: List of absent passengers, contact information, generative AI model.

[0900] Output: The contact message sent.

[0901] Specific operation: Using a generative AI model, automatically generate a message for passengers who have not yet boarded the car, saying "You have not boarded. Please tell us the reason." and send it to registered contacts (e.g., using the Twilio API).

[0902] Step 6:

[0903] The user (passenger) receives the message and replies via a smartphone app whether or not they would like to board and the reason for doing so.

[0904] Input: The contact message sent by the server.

[0905] Output: Reply message from passenger.

[0906] Specific operation: The user (passenger) receives a message via the smartphone app and responds with information about the ride status. This reply is sent to the server.

[0907] Step 7:

[0908] The server receives the passenger's reply and updates the ride database.

[0909] Input: Reply message from passenger, current ride database.

[0910] Output: Updated trip database.

[0911] Specific operation: The server analyzes the received reply message and updates the ride database, thereby keeping the ride status up to date in real time.

[0912] Step 8:

[0913] The device (in-vehicle camera) monitors the interior of the transportation vehicle and detects abnormal or infrequent movement.

[0914] Input: In-car camera video feed.

[0915] Output: Anomaly detection data.

[0916] How it works: Cameras installed inside the vehicle monitor passenger movements and analyze the captured footage using AI technology. If any unusual or minor movements are detected, the information is sent to a server.

[0917] Step 9:

[0918] The server detects an anomaly and sends a notification to the monitor.

[0919] Input: Anomaly detection data, monitor contact information.

[0920] Output: The error notification message sent.

[0921] Specific operation: The server receives the anomaly detection data, and if an anomaly is detected, it sends a notification to the monitor (for example, by email or SMS). The monitor receives this notification and takes the necessary action.

[0922] The above steps can ensure a high level of passenger safety in autonomous vehicles.

[0923] 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.

[0924] This invention uses facial recognition cameras, AI technology, an automatic notification system, and an emotion engine to ensure the safety of children in childcare facilities and on school buses. The combination of the emotion engine enables the system to recognize the emotions of children and users, enabling more accurate anomaly detection and response. The system aims to monitor children's safety in real time while reducing the burden on caregivers.

[0925] An embodiment of a kindergarten attendance management system

[0926] System Overview

[0927] The server serves as the central control unit of the attendance management system, managing the database, running the face recognition algorithm, and the emotion engine.

[0928] The terminal (facial recognition camera) is installed at the entrance of the childcare facility, photographs the faces of children arriving at the facility, and identifies them in real time.

[0929] Users (caregivers and parents) receive information through the system's app and perform the necessary operations.

[0930] The emotion engine provides additional functionality to analyze the emotions of children and parents and detect anomalies.

[0931] Program processing explanation

[0932] 1. The user (caregiver or administrator) starts the system and begins monitoring a new day of attendance.

[0933] The server reads the schedule of the daycare facility and starts managing the attendance status for today.

[0934] 2. The device (face recognition camera) takes real-time photos of children arriving at the childcare facility and identifies them using a facial recognition algorithm.

[0935] The server receives the facial recognition results and updates the child's attendance database.

[0936] 3. The emotion engine analyzes the child's emotions from the acquired facial images and behavioral data.

[0937] The server records the child's emotional state in a database based on the analysis results of the emotion engine.

[0938] 4. The server lists children who have not arrived by the designated arrival time (e.g., 9:00).

[0939] The server checks the attendance status and generates a list of children who have not arrived by the specified time.

[0940] 5. The server sends an automatic message to the parents of children who are not attending school.

[0941] The server uses a generative AI to create a phone call or message and send it to the parent saying, "Your child has not come to school. Please let us know the reason."

[0942] 6. The user (parent) receives the message and replies using the smartphone app whether or not the child will attend school and the reason.

[0943] The server receives the response from the parents and updates the attendance status database.

[0944] 7. The emotion engine analyzes the text data contained in the parent's reply and recognizes the parent's emotions.

[0945] The server records the parent's emotional state in a database based on the analysis results of the emotion engine.

[0946] 8. If the server does not receive a response from the parent within a certain period of time (e.g., 15 minutes) or detects an abnormality, it will notify the caregiver.

[0947] The server generates a warning message stating, "We are unable to confirm attendance for the child with unanswered ID 12345. Action is required," and sends it to the caregiver's device.

[0948] Embodiment of school bus monitoring system

[0949] System Overview

[0950] The device (bus camera) is installed inside the school bus and monitors the children's boarding times and behavior.

[0951] The server collects data from the on-board cameras and runs algorithms to detect anomalies.

[0952] Users (caregivers) can view the internal camera footage from the bus in real time on their smartphones or tablets.

[0953] The emotion engine analyzes the emotions of children on the bus and assists in anomaly detection.

[0954] Program processing explanation

[0955] 1. The device (in-bus camera) records the time the child boards the bus and sends the data to the server.

[0956] The server receives the boarding time data and updates the boarding status database.

[0957] 2. The device (in-bus camera) monitors the children's behavior and periodically sends data to the server.

[0958] The server receives behavioral data from the camera and uses AI technology to detect abnormalities.

[0959] 3. The emotion engine analyzes the emotions of the children on the bus from the acquired facial images and behavioral data.

[0960] The server records the child's emotional state in a database based on the analysis results of the emotion engine.

[0961] 4. If the server detects no activity for a certain period of time or detects an abnormality, it will send a notification to the caregiver.

[0962] The server runs an anomaly detection algorithm and sends real-time notifications to caregivers if an anomaly is detected.

[0963] 5. The user (caregiver) receives a notification and checks the camera footage inside the bus.

[0964] Childcare workers will check the situation on the bus through the app and respond as necessary.

[0965] Specific examples

[0966] As a concrete example, here is a simulation of a day at kindergarten:

[0967] At 8:00 a.m., the user (caregiver) starts the system and begins monitoring the day the children attend school.

[0968] When a child arrives at the entrance, a device (face recognition camera) takes a picture of their face and sends the data to the server.

[0969] At 8:30, the server performs facial recognition and updates the database of children who have already arrived at the school.

[0970] At 8:35, the emotion engine analyzes the facial image and behavioral data and recognizes the child's emotion as "anxiety."

[0971] At 9:00, the server lists the children who have not attended school and automatically sends a message to their parents.

[0972] The user (parent) receives the message and replies from the app at 8:50 a.m. explaining the reason for the child's absence, such as "I'm not feeling well."

[0973] At 9:15, the server checks the response from the parents and updates the attendance database.

[0974] The emotion engine analyzes the parents' replies and recognizes the emotion "worry."

[0975] At 10:00, the device (camera inside the bus) sends data on the children's behavior to the server, which analyzes it.

[0976] At 10:10, the emotion engine recognizes the emotion of the children on the bus as "excited."

[0977] At 10:30, the server detects an abnormality (e.g., a motionless child) and sends a notification to the user (caregiver).

[0978] The user (caregiver) receives the notification, checks the camera footage inside the bus, and takes the necessary action.

[0979] The above is an embodiment of the invention. By combining an emotion engine, it is possible to detect and respond to abnormalities with higher accuracy, thereby ensuring a high level of child safety while reducing the burden on caregivers.

[0980] The processing flow will be explained below.

[0981] Processing steps of the attendance management system

[0982] Step 1:

[0983] The user (caregiver or administrator) starts the system and begins monitoring the new day of attendance.

[0984] The caregiver presses the "Start Day of School" button on the system screen to start the system.

[0985] The server checks the daycare schedule, initializes the database based on today's date, and sets the "day of school start" status.

[0986] Step 2:

[0987] The device (face recognition camera) takes real-time photos of children arriving at the daycare facility.

[0988] A camera installed at the entrance automatically detects the faces of children arriving at the school and sends image data to a server in real time.

[0989] Step 3:

[0990] The server runs a facial recognition algorithm to analyze the transmitted facial image data.

[0991] The server compares the facial image data with existing facial data in the database.

[0992] Get the matching child's ID and update the corresponding database entry to "already in school."

[0993] Step 4:

[0994] The server sends the facial images and behavioral data to the emotion engine.

[0995] The emotion engine analyzes a child's emotions from facial expressions, movements, and other behavioral data.

[0996] Based on the analysis results, the server records the child's emotional state in a database.

[0997] Step 5:

[0998] The server lists children who have not arrived by the designated arrival time (e.g., 9:00).

[0999] The server checks the attendance status and generates a list of children who have not arrived by the specified time.

[1000] Step 6:

[1001] The server sends an automatic message to the parents of children who are not attending school.

[1002] The server uses a generative AI to create a phone call or message and send it to the parent saying, "Your child has not come to school. Please let us know the reason."

[1003] Step 7:

[1004] The user (parent) receives the message and replies using a smartphone app to indicate whether or not the child will attend school and the reason for the attendance.

[1005] Parents check the notification in the app, enter the reason (e.g., "absent due to illness"), and submit.

[1006] Step 8:

[1007] The server receives the response from the parents and updates the attendance status database.

[1008] The server records the received reason in a database and updates the corresponding child's status to "absent" or "late", etc.

[1009] Step 9:

[1010] The server sends the text data contained in the response from the parent to the emotion engine.

[1011] The emotion engine analyzes the parent's response and recognizes their emotional state (e.g., "worried" or "relieved").

[1012] Based on the analysis results, the server records the parent's emotional state in a database.

[1013] Step 10:

[1014] If the server does not receive a response from the parent within a certain period of time (e.g., 15 minutes) or detects an abnormality, it notifies the caregiver.

[1015] The server generates a warning message stating, "We are unable to confirm attendance for the child with unanswered ID 12345. Action is required," and sends it to the caregiver's device.

[1016] Processing steps of the school bus monitoring system

[1017] Step 1:

[1018] The device (camera inside the bus) records the time the child boards the bus and sends the data to the server.

[1019] A camera installed at the bus entrance automatically photographs children boarding the bus and sends the boarding time data to a server.

[1020] Step 2:

[1021] The server receives the boarding time data and updates the boarding status database.

[1022] The server performs facial recognition and records the ID of the child riding and the time of boarding in a database.

[1023] Step 3:

[1024] The device (a camera inside the bus) monitors the children's behavior and periodically sends data to the server.

[1025] Cameras inside the bus monitor children's movements in real time, capturing and transmitting image data at regular intervals.

[1026] Step 4:

[1027] The server receives behavioral data from the camera and uses AI technology to detect abnormalities.

[1028] The server analyzes behavioral data and detects abnormalities such as no activity for a certain period of time.

[1029] Step 5:

[1030] The server sends the facial images and behavioral data to the emotion engine.

[1031] The emotion engine analyzes the emotions of children on the bus from facial expressions, movements, and other behavioral data.

[1032] Based on the analysis results, the server records the child's emotional state in a database.

[1033] Step 6:

[1034] If the server detects an abnormality, it will send a notification to the caregiver.

[1035] Based on the anomaly detection algorithm, the server generates a notification stating, "There has been no activity from ID12345 on the bus for more than 10 minutes. Check is required." and sends it to the caregiver's device.

[1036] Step 7:

[1037] The user (caregiver) receives a notification and checks the camera footage inside the bus.

[1038] Caregivers can check notifications on their smartphones or tablets and use the app's camera feed function to view real-time footage.

[1039] If necessary, the childcare provider will contact the bus driver or other staff to determine the actual situation and respond accordingly.

[1040] Based on these processing steps, the system of the present invention can ensure a high level of safety for children in childcare facilities and on school buses. By combining it with an emotion engine, more accurate anomaly detection and appropriate responses can be achieved.

[1041] Example 2

[1042] 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."

[1043] Conventional child safety management systems in childcare facilities and vehicles used to transport children only monitor the children's arrival and departure status and behavior, but do not analyze and respond to their emotions. This makes it difficult to grasp the emotional state of children and their parents and to accurately detect and respond to abnormalities. In addition, notifications and contact with parents are done manually, which places a heavy burden on childcare workers and makes it difficult to respond in real time.

[1044] 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.

[1045] In this invention, the server includes means for monitoring the attendance status of children at the childcare facility using a face recognition camera, means for automatically contacting parents of children who have not arrived by a specified time, means for receiving responses from parents and updating the system based on the responses, means for notifying caregivers when there is no response from the parents or when an abnormality is detected, and means for analyzing the emotions of the children and parents using an emotion engine to detect abnormalities.This makes it possible to respond based on the emotional states of the children and parents, allowing for early detection of abnormalities and rapid response, as well as reducing the burden on caregivers.

[1046] A "face recognition camera" is a camera device that photographs the faces of children arriving at kindergarten and analyzes the images in real time.

[1047] "Automatic contact means" is a function that uses an automatic notification system to contact parents of children who have not arrived at the school by a specified time.

[1048] "Means for receiving responses from parents" refers to a function that inputs information provided by parents into the system and updates the attendance status database based on that information.

[1049] "Means for detecting abnormalities" refers to a function for identifying abnormal conditions based on the behavior and emotional analysis results of children and parents.

[1050] "Means for notifying caregivers" is a function that sends warnings and notifications to caregivers when an abnormality is detected or when there is no response from the parent.

[1051] The "emotion engine" is a function that analyzes the emotions of children and parents from facial images and text data and determines their state.

[1052] "Camera installed in a vehicle used for transporting children to school" refers to a camera device installed inside a bus or vehicle used for transporting children to school, to monitor the boarding time and behavior of children.

[1053] "Artificial intelligence technology" refers to algorithms and models that enable highly automated data analysis, recognition, prediction, and other processes.

[1054] A "generative AI model" is an AI system equipped with natural language generation technology that is used to create notification content for parents.

[1055] The present invention is a system for ensuring the safety of children in childcare facilities and vehicles that transport them to and from school, and uses facial recognition cameras, AI technology, an automatic notification system, and an emotion engine. Specific methods for implementing the invention are described below.

[1056] System Configuration

[1057] 1. Server

[1058] The server functions as the central control device of the attendance management system. Specifically, it performs the following processes:

[1059] Facial recognition algorithm: Analyzes image data sent from facial recognition cameras in real time to identify children.

[1060] Emotion engine: Analyzes the emotions of children and parents from captured facial images and behavioral data.

[1061] Automated notification system: Generates and sends messages to contact parents of children who have not arrived at school by the designated time. Uses generative AI models to create notifications in natural language.

[1062] Database management: Centrally manages attendance data, children's emotional data, parental response data, etc.

[1063] 2. Device (face recognition camera)

[1064] The facial recognition camera is installed at the entrance of the childcare facility and takes real-time pictures of the faces of children as they arrive. The captured facial images are immediately sent to a server. The camera also has a time stamp function that adds time information to the image data.

[1065] 3. Terminal (Bus Camera)

[1066] The cameras installed inside the buses will monitor the children's boarding times and activities in real time, and this data will also be sent to a server for analysis.

[1067] 4. Users (caregivers and guardians)

[1068] Parents and caregivers connect to the system through a smartphone or tablet app, and responses and information from parents are sent via the app, which updates the system accordingly.

[1069] Specific examples

[1070] Below is a specific scenario of daytime attendance management.

[1071] 8:00 AM: The childcare worker starts the system and starts monitoring the new day. The server loads the schedule based on today's date and starts managing the attendance status.

[1072] Arrival: When a child arrives at the entrance of the childcare facility, a facial recognition camera captures their face and sends the image to a server, which uses a facial recognition algorithm to identify the child and update the attendance database.

[1073] 8:35: The emotion engine analyzes the facial image and identifies the child's emotion as "anxiety." The server records this information in a database.

[1074] 9:00 AM: The server creates a list of children who have not arrived by the designated arrival time (e.g., 9:00 AM), and uses a generative AI model to automatically send a message to the parents stating, "Your child has not arrived. Please let us know the reason."

[1075] Parent response: The parent receives the message and replies from the app at 8:50 a.m., "I'm sick and will be absent." The server receives the parent's response and updates the attendance database.

[1076] Sentiment analysis: The emotion engine analyzes the parent's response and recognizes and records the emotion "worry."

[1077] Monitoring inside the bus: At 10:00, the camera inside the bus captures data on the children's behavior and sends it to the server, which analyzes it.

[1078] Anomaly detection: At 10:30, the server detects an anomaly (for example, a child not moving) and sends a notification to the caregiver saying, "An abnormal condition has been detected. Please check the situation on the bus."

[1079] Caregiver response: Caregivers receive a notification, check the camera footage on the bus, and take any necessary action.

[1080] Prompt Sentence Examples

[1081] "Your child has not attended school. Please let us know the reason."

[1082] The above is a concrete embodiment for carrying out the invention. The overall flow of the system and the function of each component are explained in detail to enable the realization of the invention.

[1083] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1084] The flow of this system's program processing

[1085] Step 1:

[1086] The user (caregiver or administrator) starts the system and begins monitoring the new day of attendance.

[1087] Input: System startup operation, today's date

[1088] Output: Read the childcare facility schedule and get ready to monitor attendance

[1089] Specific behavior:

[1090] The caregiver presses the "Start Monitoring" button using a dedicated management application.

[1091] The server gets today's date and reads the daycare schedule from the database.

[1092] The server starts monitoring the attendance status and displays when it is ready.

[1093] Step 2:

[1094] The device (face recognition camera) takes real-time photos of children arriving at the daycare facility and sends the facial image data to the server.

[1095] Input: Child's face image, time stamp

[1096] Output: Sending face image data to the server

[1097] Specific behavior:

[1098] When a child reaches the entrance, a facial recognition camera automatically captures their face.

[1099] Information about the time of photographing is added to the face image data.

[1100] Facial image data is sent from the camera to a server in real time.

[1101] Step 3:

[1102] The server analyzes the transmitted facial image data using a facial recognition algorithm and updates the attendance database.

[1103] Input: Face image data, time stamp

[1104] Output: Update the attendance database

[1105] Specific behavior:

[1106] The server inputs the facial image data into a facial recognition algorithm and matches it with the child's facial information registered in a database.

[1107] Based on the recognition results, the child's attendance record is added to the database, including the time of arrival and the facial image.

[1108] Step 4:

[1109] The emotion engine analyzes the child's emotions from the captured facial image, and the server records the results in a database.

[1110] Input: Facial image data, behavioral data

[1111] Output: Sentiment analysis results, update of sentiment database

[1112] Specific behavior:

[1113] The emotion engine analyzes the child's facial expressions from the facial image data and determines their emotional state (e.g., "joy," "anxiety," etc.).

[1114] The server receives the analysis results of the emotion engine and records the child's emotional state in a database.

[1115] Step 5:

[1116] The server lists the children who have not arrived by the designated arrival time (e.g. 9:00).

[1117] Input: attendance record, current time

[1118] Output: List of children not attending kindergarten

[1119] Specific behavior:

[1120] The server checks the attendance records and generates a list of children who have not arrived by the specified time.

[1121] Step 6:

[1122] The server automatically sends a message to the parents of children who are not attending school.

[1123] Input: List of children not attending kindergarten, prompt text

[1124] Output: Parental notification message

[1125] Specific behavior:

[1126] The server uses the generative AI model to create an automated notification about the non-attendance status, which includes the message, "Your child has not attended school. Please let us know the reason."

[1127] The generated notification will be sent to the parents via phone call or message.

[1128] Step 7:

[1129] The user (parent) receives the message and replies using the smartphone app, and the server records the information in a database.

[1130] Input: Parent's reply message

[1131] Output: Update the attendance status database

[1132] Specific behavior:

[1133] Parents check the notification on their smartphone app and reply by entering a reason, such as "I'm absent because I'm sick."

[1134] The server receives the response from the parents and updates the attendance status database.

[1135] Step 8:

[1136] The emotion engine analyzes the text contained in the responses from parents, and the server records the results in a database.

[1137] Input: Reply message

[1138] Output: Parent's emotion analysis results, emotion database update

[1139] Specific behavior:

[1140] The emotion engine analyzes the parent's reply message and recognizes emotions (e.g., "worried") from the text.

[1141] The server records the emotion analysis results in a database.

[1142] Step 9:

[1143] If the server does not receive a response from the parent within a certain period of time or detects an abnormality, it sends a notification to the caregiver.

[1144] Input: Response status, anomaly detection results

[1145] Output: Warning message to caregivers

[1146] Specific behavior:

[1147] The server continues to monitor if there is no response from the parent or if an abnormality is detected.

[1148] If there is no response within a certain period of time (e.g. 15 minutes), a warning message will be generated stating "We are unable to confirm attendance for child with unanswered ID 12345. Action is required." and sent to the caregiver.

[1149] (Application example 2)

[1150] 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."

[1151] Conventional worker management systems make it difficult for managers to grasp the attendance status and physical condition of each worker, making it difficult for managers to efficiently monitor worker safety and health. Furthermore, delays in responding to abnormalities can pose a risk to safety and the working environment, so a solution to these issues was needed.

[1152] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1153] In this invention, the server includes a means for monitoring the status of employees clocking in and out of the facility using a facial recognition camera, a means for automatically contacting the guardians of employees who have not arrived at work by a specified time, a means for receiving responses from the guardians and updating the system based on those responses, a means for notifying a manager if there is no response from the guardian or if an abnormality is detected, a means for analyzing the facial and behavioral data of workers and using an emotion engine to detect signs of fatigue or stress, and an automatic notification system for sending a real-time notification to a manager if an abnormality is detected. This allows the manager to understand not only the attendance status of workers but also their emotional state, enabling them to respond quickly if an abnormality occurs.

[1154] A "facial recognition camera" is a device that extracts facial features from received image data in order to identify a particular person.

[1155] "Facilities" refers to buildings and places where workers enter and exit in order to perform their work.

[1156] "Arriving at work" refers to the act of a worker arriving at the designated work location and beginning work.

[1157] "Clocking out" refers to the act of a worker leaving the designated work area and completing work.

[1158] "Manager" means a person who is responsible for supervising and managing the operation of workers or systems.

[1159] "Guardian" refers to a person who has the responsibility to supervise a worker who is a minor.

[1160] "Response" refers to the act of replying to a notification or the like.

[1161] An "abnormality" refers to an unexpected problem or deviation from normal business operations or behavior.

[1162] "Worker" means a person employed to perform a specific task at an establishment.

[1163] The "emotion engine" is software that analyzes a person's emotional state from received image data and behavioral data.

[1164] An "automatic notification system" is a system that automatically sends a notification to a pre-defined recipient when an abnormality is detected.

[1165] "Safety" refers to a state in which workers can perform their work without exposure to danger or risk.

[1166] "Fatigue" refers to a state in which a worker's physical and mental strength is exhausted due to work, making it difficult for them to perform their normal duties.

[1167] "Stress" refers to a state in which a worker feels pressure or tension due to their work or environment, making it difficult for them to carry out their normal work.

[1168] To implement this invention, several major components are required, including a facial recognition camera, an emotion engine for analyzing the emotional state of workers, an automatic notification system, and a database management system. A server-based system configuration is also essential to integrate these components.

[1169] System Hardware

[1170] 1. Facial recognition cameras (e.g., Logitech C920) are installed at entrances and key areas within the facility to monitor worker attendance and behavior in real time.

[1171] 2. A computer server (e.g., an AWS EC2 instance) acts as the central control unit, managing the database, running the facial recognition algorithm, and the emotion engine.

[1172] 3. Notification terminals (e.g., smartphones and tablets) are used by administrators to receive notifications from the system and respond in real time.

[1173] Software Components

[1174] 1. Facial recognition algorithms (e.g. OpenCV) are used to identify and identify faces from image data acquired from a camera.

[1175] 2. Emotion Engine is software that analyzes the emotional state of workers from image data and behavioral data.

[1176] 3. A database management system (e.g., SQLite) is used to store and manage employee attendance data and emotion analysis results.

[1177] 4. The automatic notification system provides a mechanism for sending real-time notifications to administrators when an abnormality is detected.

[1178] Program processing explanation

[1179] The server processes image data obtained from the facial recognition camera to identify workers and record their attendance status. It also inputs workers' facial and behavioral data into an emotion engine in real time to analyze signs of fatigue and stress. If an abnormality is detected, the server sends a real-time warning message to the administrator's notification terminal via an automatic notification system. Administrators can receive the notification and take appropriate measures.

[1180] Specific examples

[1181] At 8:00 AM, Worker A enters the facility and is captured by a facial recognition camera. The server uses a facial recognition algorithm to identify Worker A and update the attendance database. At 10:00 AM, the emotion engine analyzes Worker A's behavioral data and facial image to detect signs of fatigue. This information is recorded in the database, and at the same time, the server notifies the manager in real time through an automatic notification system. The manager receives the notification and can take appropriate action, such as encouraging Worker A to take a break.

[1182] Prompt Sentence Examples

[1183] "Generate a Python program to develop a safety and health management system using facial recognition and emotion analysis of workers in a logistics center. Use OpenCV for facial recognition and a custom Emotion Engine for emotion analysis, and add a function to send notifications when an anomaly is detected."

[1184] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1185] Step 1:

[1186] Image acquisition by face recognition camera

[1187] The terminal (face recognition camera) is installed at the entrance and exit of the facility and captures the facial images of workers as they pass through. The input is real-time video data captured by the camera, and the output is facial image data of the workers. Specifically, the camera periodically captures video and sends the data to a server.

[1188] Step 2:

[1189] Facial Recognition Processing

[1190] The server receives the facial image data sent from the terminal (face recognition camera) and identifies the worker using a facial recognition algorithm (e.g., OpenCV). The input is the facial image data, and the output is the ID of the identified worker. Specifically, the server runs the facial recognition algorithm, extracts features from the acquired facial image data, and compares them with known facial data in a database.

[1191] Step 3:

[1192] Update attendance database

[1193] The server updates the attendance database using the ID of the worker identified by the facial recognition process. The input is the ID of the identified worker, and the output is an updated attendance status database. Specifically, the server saves the identified worker's attendance time and ID in the database, and reflects the attendance status in real time.

[1194] Step 4:

[1195] Emotional state analysis

[1196] The server inputs the facial image data and behavioral data sent from the terminal (face recognition camera) into the emotion engine and analyzes the worker's emotional state. The input is facial image data and behavioral data, and the output is the detected emotional state (e.g., fatigue, stress, etc.). Specifically, the server uses the emotion engine to analyze facial expressions and behavioral patterns to determine the worker's emotions.

[1197] Step 5:

[1198] Anomaly detection and notification

[1199] The server detects anomalies based on the analysis results of the emotion engine, and if an anomaly is confirmed, it uses an automatic notification system to send a warning message to the administrator's notification terminal in real time. The input is the analysis result (emotional state), and the output is a warning message for the administrator. Specifically, the server runs the anomaly detection algorithm, and if an abnormal state such as fatigue or stress is detected, it generates a notification message and sends it to the administrator's smartphone or tablet.

[1200] Step 6:

[1201] Administrator response

[1202] The user (administrator) receives the notification message from the server and takes specific action through the app. The input is the notification message, and the output is the actual response procedure (e.g., instructing workers to take breaks). The specific action is for the administrator to check the notification and issue appropriate instructions to the workers.

[1203] Prompt Sentence Examples

[1204] "Generate a Python program to develop a safety and health management system using facial recognition and emotion analysis of workers in a logistics center. Use OpenCV for facial recognition and a custom Emotion Engine for emotion analysis, and add a function to send notifications when an anomaly is detected."

[1205] 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.

[1206] 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.

[1207] 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.

[1208] [Third embodiment]

[1209] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1210] 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.

[1211] 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).

[1212] 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.

[1213] 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.

[1214] 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).

[1215] 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.

[1216] 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.

[1217] 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.

[1218] 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.

[1219] 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.

[1220] 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."

[1221] This invention uses facial recognition cameras, AI technology, and an automatic notification system to ensure the safety of children at childcare facilities and on school buses. The system aims to monitor children's attendance in real time and detect abnormalities early, while reducing the burden on caregivers.

[1222] An embodiment of a kindergarten attendance management system

[1223] System Overview

[1224] The server is the central control unit of the attendance management system, managing the database, running the facial recognition algorithm, and sending notifications.

[1225] The terminal (facial recognition camera) is installed at the entrance of the childcare facility, photographs the faces of children arriving at the facility, and identifies them in real time.

[1226] Users (caregivers and parents) receive information through the system's app and perform the necessary operations.

[1227] Program processing explanation

[1228] 1. The user (caregiver or administrator) starts the system and begins monitoring a new day of attendance.

[1229] The server reads the schedule of the daycare facility and starts managing the attendance status for today.

[1230] 2. The device (face recognition camera) takes real-time photos of children arriving at the childcare facility and identifies them using a facial recognition algorithm.

[1231] The server receives the facial recognition results and updates the child's attendance database.

[1232] 3. The server lists children who have not arrived by the designated arrival time (e.g., 9:00).

[1233] The server checks the attendance status and generates a list of children who have not arrived by the specified time.

[1234] 4. The server automatically sends a message to the parents of children who have not arrived at school by the specified time.

[1235] The server uses the generation AI to send a message to the parent's contacts, for example, "Your child is not attending school. Please tell us why."

[1236] 5. The user (parent) receives the message and replies via the smartphone app whether or not the child will attend school and the reason.

[1237] The server receives the response from the parents and updates the attendance database.

[1238] 6. The server notifies the caregiver if there is no response from the parent or if an abnormality is detected.

[1239] If an abnormality is detected, the server automatically sends a warning message to the caregiver's device.

[1240] Embodiment of school bus monitoring system

[1241] System Overview

[1242] The device (bus camera) is installed inside the school bus and monitors the children's boarding times and behavior.

[1243] The server collects data from the on-board cameras and runs algorithms to detect anomalies.

[1244] Users (caregivers) can view the internal camera footage from the bus in real time on their smartphones or tablets.

[1245] Program processing explanation

[1246] 1. The device (in-bus camera) records the time the child boards the bus and sends the data to the server.

[1247] The server receives the boarding time data and records it in a database.

[1248] 2. The device (in-bus camera) monitors the children's behavior and periodically sends data to the server.

[1249] The server receives behavioral data from the camera and uses AI technology to detect abnormalities.

[1250] 3. The server sends a notification to the caregiver if there is no activity for a certain period of time or if an abnormality is detected.

[1251] The server runs an anomaly detection algorithm and sends real-time notifications to caregivers if an anomaly is detected.

[1252] 4. The user (caregiver) receives a notification and checks the internal camera footage from the bus.

[1253] Childcare workers will check the situation on the bus through the app and respond as necessary.

[1254] Specific examples

[1255] As a concrete example, here is a simulation of a day at kindergarten:

[1256] At 8:00 a.m., the user (caregiver) starts the system and begins monitoring the day the children attend school.

[1257] When a child arrives at the entrance, a device (face recognition camera) takes a picture of their face and sends the data to the server.

[1258] At 8:30, the server performs facial recognition and updates the database of children who have already arrived at the school.

[1259] At 9:00, the server lists the children who have not attended school and automatically sends a message to their parents.

[1260] The user (parent) receives the message and replies from the app at 8:50 a.m. explaining the reason for attending school.

[1261] At 9:15, the server checks the response from the parents and updates the attendance database.

[1262] At 10:00, the device (the camera inside the bus) sends some data on the children's behavior to the server, which analyzes it.

[1263] At 10:30, the server detects an abnormality (e.g., a motionless child) and sends a notification to the user (caregiver).

[1264] The user (caregiver) receives the notification, checks the camera footage inside the bus, and takes the necessary action.

[1265] The above is an embodiment of the invention. The present invention can reduce the burden on caregivers and ensure a high level of child safety.

[1266] The processing flow will be explained below.

[1267] Processing steps of the attendance management system

[1268] System startup and preparation

[1269] Step 1:

[1270] The user (caregiver or administrator) starts the system and begins monitoring the new day of attendance.

[1271] The caregiver presses the "Start Day of School" button on the system screen to start the system.

[1272] The server checks the childcare facility's schedule and initializes the database based on today's date.

[1273] Facial recognition when attending kindergarten

[1274] Step 2:

[1275] The device (face recognition camera) takes real-time photos of children arriving at the daycare facility.

[1276] Cameras are installed at the entrance and automatically detect the faces of children arriving at the school.

[1277] The camera transmits the facial image data to a server.

[1278] Step 3:

[1279] The server runs a facial recognition algorithm to analyze the transmitted facial image data.

[1280] The server compares the facial image data with existing facial data in the database.

[1281] Get the matching child's ID and update the corresponding database entry to "already in school."

[1282] Checking attendance status and contacting

[1283] Step 4:

[1284] The server lists children who have not arrived by the designated arrival time (e.g., 9:00).

[1285] The server compares the childcare facility's schedule with the child's attendance data and lists children who have not attended.

[1286] Step 5:

[1287] The server sends an automatic message to the parents of children who are not attending school.

[1288] The server uses a generative AI to create a phone call or message and send it to the parent saying, "Your child has not come to school. Please let us know the reason."

[1289] Parental Response Management

[1290] Step 6:

[1291] The user (parent) receives the message and replies using a smartphone app to indicate whether or not the child will attend school and the reason for the attendance.

[1292] Parents check the notification in the app, enter the reason (e.g., "absent due to illness"), and submit.

[1293] Step 7:

[1294] The server receives the response from the parents and updates the attendance status database.

[1295] The server records the received reason in a database and updates the status of the corresponding child.

[1296] Notification in case of an abnormality

[1297] Step 8:

[1298] If the server does not receive a response from the parent within a certain period of time (e.g., 15 minutes) or detects an abnormality, it notifies the caregiver.

[1299] The server generates a warning message saying, "We are unable to confirm attendance for child ID 12345, who has not responded. Action is required."

[1300] The server sends this message to the childcare provider's terminal.

[1301] Processing steps of the school bus monitoring system

[1302] Ride data collection and monitoring

[1303] Step 1:

[1304] The device (camera inside the bus) records the time the child boards the bus and sends the data to the server.

[1305] Cameras are installed at the entrances to the buses and automatically capture images of children boarding.

[1306] The camera sends a facial image to a server and records the time of boarding.

[1307] Step 2:

[1308] The server receives the boarding time data and updates the boarding status database.

[1309] The server performs facial recognition and records the ID of the child riding and the time of boarding in a database.

[1310] Behavior monitoring and anomaly detection

[1311] Step 3:

[1312] The device (a camera inside the bus) periodically captures images of children's behavior and sends the data to a server.

[1313] The cameras inside the bus monitor the children's movements and capture and transmit image data at regular intervals.

[1314] Step 4:

[1315] The server receives behavioral data from the camera and uses AI technology to detect abnormalities.

[1316] The server analyzes behavioral data and detects abnormalities such as no activity for a certain period of time.

[1317] Notification and confirmation in case of an abnormality

[1318] Step 5:

[1319] If the server detects an abnormality, it will send a notification to the caregiver.

[1320] Based on the anomaly detection algorithm, the server generates a notification stating, "There has been no activity from ID12345 on the bus for more than 10 minutes. Check is required." and sends it to the caregiver's device.

[1321] Step 6:

[1322] The user (caregiver) receives a notification and checks the camera footage inside the bus.

[1323] Caregivers can check notifications on their smartphones or tablets and use the app's camera feed function to view real-time footage.

[1324] If necessary, the childcare provider will contact the bus driver or other staff to determine the actual situation and respond accordingly.

[1325] Based on these processing steps, the system of the present invention can ensure a high level of child safety in childcare facilities and on buses.

[1326] Example 1

[1327] 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."

[1328] Conventional attendance management systems at childcare facilities require manual confirmation of children's attendance status and communication of that information to parents and caregivers, which is extremely time-consuming and labor-intensive. Furthermore, bus attendance is also primarily monitored manually, making it difficult to detect abnormalities early on. This increases the burden on caregivers and makes it difficult to ensure the safety of children, which has been an issue.

[1329] 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.

[1330] In this invention, the server includes a means for monitoring the attendance status of children at the childcare facility using a face recognition camera, a means for automatically contacting the parents of children who have not arrived by a specified time, a means for receiving responses from the parents and updating the database based on the responses, and a means for notifying the childcare worker if there is no response from the parents or if an abnormality is detected. This reduces the burden on the childcare worker and ensures a high level of child safety.

[1331] A "facial recognition camera" is a camera that captures a child's face and identifies the child using a facial recognition algorithm.

[1332] "Childcare facility" refers to any facility that provides childcare, such as kindergartens and nursery schools.

[1333] "Attendance status" is information indicating whether or not a child has attended a childcare facility.

[1334] "Guardian" means a child's parent or legal guardian.

[1335] "Automatic notification" is the process by which a system uses generative AI models to automatically create and send messages to specific recipients.

[1336] A "database" is a collection of information that is used to systematically manage and store information in a system.

[1337] "Abnormal" refers to a state that differs from a child's normal behavior or situation, such as not showing up to school or not moving around on the bus.

[1338] "Notification" is an operation in which the system sends specific information to a terminal to notify it.

[1339] "Means" refers to a set of methods or devices used to achieve a particular purpose.

[1340] An "in-bus camera" is a camera installed inside a school bus to monitor children's boarding times and behavior.

[1341] "Artificial intelligence technology" refers to all technologies that use machine learning and data analysis algorithms to automatically process and analyze data and support decision-making.

[1342] MODE FOR CARRYING OUT THE INVENTION

[1343] System Overview

[1344] The system of the present invention uses facial recognition cameras, AI technology, and an automatic notification system to ensure the safety of children at childcare facilities and on buses. The system consists of a server, terminals (facial recognition cameras and bus cameras), and users (caregivers and parents), and aims to monitor children's attendance in real time and detect any abnormalities early, while reducing the burden on caregivers.

[1345] Hardware and software used

[1346] The server is the central control unit of the attendance management system, managing the database, running the facial recognition algorithm, and sending notifications. In this case, a generative AI model is used.

[1347] The terminal (facial recognition camera) is installed at the entrance of the childcare facility, photographs the faces of children arriving at the facility, and identifies them in real time.

[1348] The device (bus camera) is installed inside the school bus and monitors the children's boarding times and behavior.

[1349] Users (caregivers and parents) receive information through the system's app and perform the necessary operations.

[1350] Program processing explanation

[1351] 1. When the system is started, the server loads the childcare facility's schedule and begins managing the day's attendance status. The server uses a generative AI model to analyze various data and generate notification messages.

[1352] 2. The device (face recognition camera) takes a real-time picture of the child as they arrive at the daycare center and identifies them using a face recognition algorithm. The face recognition results are sent to the server, which updates the child attendance database.

[1353] 3. The device (in-bus camera) records the time the child boards the bus and sends the data to a server. The server records this in a database and uses AI technology to detect any abnormalities.

[1354] 4. The server creates a list of children who have not arrived by the designated time and automatically sends a message to their parents using a generative AI model to create a message for parents and send it via email, SMS, etc.

[1355] 5. The user (parent) receives the notification and replies via the smartphone app whether or not the child will attend school and the reason for their attendance. The server receives the reply from the parent and updates the attendance database.

[1356] 6. If the server detects an abnormality or if there is no response from the parent, it will notify the caregiver, allowing the caregiver to understand the situation in real time and respond quickly.

[1357] Specific examples

[1358] As a concrete example, here is a simulation of a day at kindergarten:

[1359] At 8:00 a.m., the user (caregiver) starts the system and begins monitoring the day the children attend school.

[1360] When a child arrives at the entrance, a device (face recognition camera) takes a picture of their face and sends the data to the server.

[1361] At 8:30, the server performs facial recognition and updates the database of children who have already arrived at the school.

[1362] At 9:00, the server will list the children who have not attended school and automatically send a message to their parents. Example prompt: "Your child has not attended school. Please tell us the reason."

[1363] The user (parent) receives the message and replies from the app at 8:50 a.m. explaining the reason for attending school.

[1364] At 9:15, the server checks the response from the parents and updates the attendance database.

[1365] At 10:00, the device (the camera inside the bus) sends some data on the children's behavior to the server, which analyzes it.

[1366] At 10:30, the server detects an abnormality (e.g., a motionless child) and sends a notification to the user (caregiver).

[1367] The user (caregiver) receives the notification, checks the camera footage inside the bus, and takes the necessary action.

[1368] The above is an embodiment of the invention, which reduces the burden on caregivers and ensures a high level of child safety.

[1369] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1370] Step 1:

[1371] The user (caregiver or administrator) starts the system and begins monitoring the new day of attendance.

[1372] Input: The user taps the system wake-up button and enters schedule information.

[1373] Specific operation: The system starts when the user presses the start button on the management screen on their smartphone or PC.

[1374] Data processing / calculation: The server retrieves the current date and schedule information from the internal database and displays it.

[1375] Output: The childcare facility schedule is displayed on the admin page.

[1376] Step 2:

[1377] The device (facial recognition camera) takes real-time photos of the faces of children arriving at the childcare facility and identifies them using a facial recognition algorithm.

[1378] Input: Child's face image, previously registered face image data.

[1379] Specific operation: The camera detects motion and captures the child's face automatically.

[1380] Data processing / computation: A facial recognition algorithm runs on the server and matches the captured facial image with existing data in a database.

[1381] Output: The attendance information of children who match the matched result is updated.

[1382] Step 3:

[1383] The server lists the children who have not arrived by the designated arrival time (e.g. 9:00).

[1384] Input: School attendance database, specified time.

[1385] Specific operation: The server scans the attendance database and extracts children whose attendance could not be confirmed.

[1386] Data processing / calculation: Filter the attendance status in the database and generate a list of children who have not attended.

[1387] Output: At 9:00, the list of children who have not yet attended school is complete.

[1388] Step 4:

[1389] The server automatically sends a message to the parents of the listed children who have not attended school.

[1390] Input: List of non-attendance students, parent contact information.

[1391] How it works: Using a generative AI model, messages are automatically generated for each parent.

[1392] Data processing / computation: The AI ​​model creates a message and sends it via email, SMS, etc.

[1393] Output: A message is sent to the parent contact.

[1394] Step 5:

[1395] The user (parent) receives a notification and replies via a smartphone app whether or not their child will attend school and the reason for doing so.

[1396] Input: Parent response message.

[1397] Specific actions: Parents check the notification on their smartphone, open the reply form within the app, enter the reason, and submit.

[1398] Data processing / calculation: The server receives the reply and updates the attendance database.

[1399] Output: The updated attendance database is displayed.

[1400] Step 6:

[1401] If the server detects an abnormality, it will notify the caregiver.

[1402] Input: If there is no reply from the parent within a certain period of time, the AI ​​detects an anomaly.

[1403] Specific operation: The server monitors the response status and anomaly detection results.

[1404] Data processing / calculation: If an abnormality is detected or there is no response for a certain period of time, a notification will be automatically generated to the caregiver.

[1405] Output: A warning message is displayed on the caregiver's device.

[1406] Step 7:

[1407] The device (camera inside the bus) records the time the child boards the bus and sends the data to the server.

[1408] Input: Child boarding time data.

[1409] What it does: Cameras monitor children on the bus and record the time they board.

[1410] Data processing / calculation: The server receives the boarding time data and records it in the database.

[1411] Output: The registered boarding time data is updated.

[1412] Step 8:

[1413] The device (a camera inside the bus) monitors the children's behavior and periodically sends data to the server.

[1414] Input: Child behavior data.

[1415] How it works: Cameras inside the bus monitor children's behavior and record video data.

[1416] Data processing / calculation: The server receives behavioral data from the camera and analyzes it using AI technology.

[1417] Output: The analysis results are recorded in a database.

[1418] Step 9:

[1419] If the server detects no activity for a certain period of time or detects an abnormality, it will send a notification to the caregiver.

[1420] Input: Child activity data, anomaly detection results.

[1421] What it does: The server monitors the analysis results and generates a notification if it detects an anomaly.

[1422] Data processing / calculation: Run anomaly detection algorithms and create notifications if anomalies are detected.

[1423] Output: An abnormality notification is sent to the caregiver's device.

[1424] Step 10:

[1425] The user (caregiver) receives a notification and checks the internal camera footage of the bus.

[1426] Input: Anomaly notification, camera footage.

[1427] Specific operations: Childcare workers check notifications through the app and view real-time camera footage from inside the bus.

[1428] Data processing / calculation: Camera video data is streamed and provided to caregivers.

[1429] Output: The childcare worker can grasp the situation inside the bus in real time.

[1430] The above are the specific processing steps of the system and their detailed operations.

[1431] (Application example 1)

[1432] 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."

[1433] Ensuring passenger safety is important in autonomous vehicles, but conventional systems have been insufficient in monitoring passenger status and the interior of the vehicle. It has also been difficult to detect abnormalities in the passenger status or the interior of the vehicle in a timely manner and take necessary measures. This has led to a demand for an efficient method to ensure a high level of passenger safety.

[1434] 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.

[1435] In this invention, the server includes a means for monitoring the riding status of passengers using a face recognition camera installed at the entrance of the means of transportation, a means for automatically contacting passengers who have not boarded by a predetermined time, and a means for receiving responses from passengers and updating the system based on the responses. This makes it possible to quickly contact passengers even if they have not boarded by the predetermined time, and to grasp the riding status of passengers in real time.

[1436] "Transportation" refers to any means of transportation for carrying passengers, including autonomous vehicles.

[1437] A "face recognition camera" is a camera device that photographs and identifies the faces of passengers.

[1438] "Riding status" refers to the process and results of passengers boarding a means of transportation.

[1439] "Predetermined Time" means a specific time set for a Passenger to board a Transportation Vehicle.

[1440] "Automatic contact means" refers to a device or program that automatically communicates without human intervention when contact is required.

[1441] "Response" means a response from a passenger or observer who has received a communication.

[1442] "Means for updating the system" means a device or program that keeps the database and settings up to date based on passenger responses.

[1443] "Supervisor" means a person who monitors the safety of a means of transport and its passengers and takes any necessary action.

[1444] "In-camera video analysis means" refers to a device or program that analyzes video captured by a camera and detects abnormal movements or specific actions.

[1445] "In-vehicle behavior" refers to the actions and movements of passengers within a mode of transportation.

[1446] "AI technology" refers to technology that uses artificial intelligence to process data and perform identification and anomaly detection.

[1447] This invention is a system for ensuring passenger safety in autonomous vehicles, which uses a facial recognition camera, AI technology, and an automatic notification system. The system is configured as follows:

[1448] System Overview

[1449] The server is the central control unit of the system, managing the database, running the facial recognition algorithm, and sending notifications. Specifically, it can use a cloud-based system (e.g., AWS, Google Cloud).

[1450] The terminal (face recognition camera) is installed at the entrance of the transportation vehicle and takes pictures of the faces of passengers boarding the vehicle and identifies them in real time, using high-performance cameras and face recognition algorithms (e.g., OpenCV, TensorFlow).

[1451] Users (passengers and observers) receive information and perform necessary operations through the system's app, which is designed to work on both iOS and Android.

[1452] Program processing explanation

[1453] Ride monitoring

[1454] The device (a facial recognition camera) takes a picture of the passenger's face when boarding the transportation vehicle at the entrance and sends the data to a server, which uses a facial recognition algorithm to identify the passenger and update the passenger database. This process occurs in real time.

[1455] Automated Contact System

[1456] The server will list passengers who have not boarded by the designated time and automatically contact them. The server will then use a generative AI model to send a message to the passenger's contacts. For example, it could send a message saying, "You have not boarded. Please tell us why."

[1457] Passenger response

[1458] The user (passenger) receives the message and replies via the smartphone app whether or not they want to ride and the reason for the ride. The server receives this reply and updates the ride database.

[1459] Anomaly Detection System

[1460] The server receives data from the device (face recognition camera) and the in-car camera and uses AI technology to detect abnormalities. In particular, it analyzes unusually small movements and abnormal movements in real time, and if an abnormality is detected, it sends a notification to the monitor.

[1461] Specific implementation example

[1462] One day, an autonomous vehicle begins operation, and a facial recognition camera at the entrance monitors passengers. For example, Passenger A boards the vehicle at 8:00 AM, and the camera recognizes his face and sends the data to the server. At 8:30 AM, Passenger B, who has not boarded the vehicle, automatically receives a message saying, "You are not boarding. Please tell us the reason."

[1463] At 10:00 a.m., the camera detects unusual activity inside the vehicle (e.g., unusually little movement) and sends a notification to the supervisor, who then reviews the camera footage through the app and takes appropriate action.

[1464] Prompt Sentence Examples

[1465] "Apply a facial recognition algorithm to the input camera feed, identify the passenger's face, and send the results to a server."

[1466] "Apply anomaly detection algorithms to the in-car camera feed to detect anomalies and send you a notification."

[1467] As described above, this system can ensure a high level of passenger safety in self-driving vehicles.

[1468] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1469] Step 1:

[1470] The terminal (face recognition camera) takes a picture of the face of the passenger boarding the transportation at the entrance.

[1471] Input: Video feed from facial recognition camera.

[1472] Output: Passenger face image.

[1473] How it works: Using a high-performance camera (e.g., Sony IMX sensor), the system captures the faces of passengers in real time as they board the vehicle. This video feed is then used by subsequent facial recognition algorithms.

[1474] Step 2:

[1475] The facial image captured by the device (face recognition camera) is sent to the server.

[1476] Input: Passenger face image.

[1477] Output: Facial image data sent to the server.

[1478] Specific operation: Using the edge computing function on the device, the captured facial image is uploaded to the server in real time (e.g., using 5G communication).

[1479] Step 3:

[1480] The server uses a facial recognition algorithm to identify the passenger.

[1481] Input: Submitted face image data.

[1482] Output: Identified passenger information.

[1483] Specific operation: A facial recognition algorithm (e.g., OpenCV or TensorFlow) is executed on the server to recognize the passenger's face from the transmitted facial image data. The recognized face is reflected in the passenger database.

[1484] Step 4:

[1485] The server lists passengers who have not boarded by a specified time.

[1486] Input: Ride database.

[1487] Output: A list of passengers who have not boarded.

[1488] What it does: It checks the current trip database against the default schedule and compiles a list of passengers who have not boarded by a given time.

[1489] Step 5:

[1490] The server automatically contacts passengers who have not yet boarded the train.

[1491] Input: List of absent passengers, contact information, generative AI model.

[1492] Output: The contact message sent.

[1493] Specific operation: Using a generative AI model, automatically generate a message for passengers who have not yet boarded the car, saying "You have not boarded. Please tell us the reason." and send it to registered contacts (e.g., using the Twilio API).

[1494] Step 6:

[1495] The user (passenger) receives the message and replies via a smartphone app whether or not they would like to board and the reason for doing so.

[1496] Input: The contact message sent by the server.

[1497] Output: Reply message from passenger.

[1498] Specific operation: The user (passenger) receives a message via the smartphone app and responds with information about the ride status. This reply is sent to the server.

[1499] Step 7:

[1500] The server receives the passenger's reply and updates the ride database.

[1501] Input: Reply message from passenger, current ride database.

[1502] Output: Updated trip database.

[1503] Specific operation: The server analyzes the received reply message and updates the ride database, thereby keeping the ride status up to date in real time.

[1504] Step 8:

[1505] The device (in-vehicle camera) monitors the interior of the transportation vehicle and detects abnormal or infrequent movement.

[1506] Input: In-car camera video feed.

[1507] Output: Anomaly detection data.

[1508] How it works: Cameras installed inside the vehicle monitor passenger movements and analyze the captured footage using AI technology. If any unusual or minor movements are detected, the information is sent to a server.

[1509] Step 9:

[1510] The server detects an anomaly and sends a notification to the monitor.

[1511] Input: Anomaly detection data, monitor contact information.

[1512] Output: The error notification message sent.

[1513] Specific operation: The server receives the anomaly detection data, and if an anomaly is detected, it sends a notification to the monitor (for example, by email or SMS). The monitor receives this notification and takes the necessary action.

[1514] The above steps can ensure a high level of passenger safety in autonomous vehicles.

[1515] 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.

[1516] This invention uses facial recognition cameras, AI technology, an automatic notification system, and an emotion engine to ensure the safety of children in childcare facilities and on school buses. The combination of the emotion engine enables the system to recognize the emotions of children and users, enabling more accurate anomaly detection and response. The system aims to monitor children's safety in real time while reducing the burden on caregivers.

[1517] An embodiment of a kindergarten attendance management system

[1518] System Overview

[1519] The server serves as the central control unit of the attendance management system, managing the database, running the face recognition algorithm, and the emotion engine.

[1520] The terminal (facial recognition camera) is installed at the entrance of the childcare facility, photographs the faces of children arriving at the facility, and identifies them in real time.

[1521] Users (caregivers and parents) receive information through the system's app and perform the necessary operations.

[1522] The emotion engine provides additional functionality to analyze the emotions of children and parents and detect anomalies.

[1523] Program processing explanation

[1524] 1. The user (caregiver or administrator) starts the system and begins monitoring a new day of attendance.

[1525] The server reads the schedule of the daycare facility and starts managing the attendance status for today.

[1526] 2. The device (face recognition camera) takes real-time photos of children arriving at the childcare facility and identifies them using a facial recognition algorithm.

[1527] The server receives the facial recognition results and updates the child's attendance database.

[1528] 3. The emotion engine analyzes the child's emotions from the acquired facial images and behavioral data.

[1529] The server records the child's emotional state in a database based on the analysis results of the emotion engine.

[1530] 4. The server lists children who have not arrived by the designated arrival time (e.g., 9:00).

[1531] The server checks the attendance status and generates a list of children who have not arrived by the specified time.

[1532] 5. The server sends an automatic message to the parents of children who are not attending school.

[1533] The server uses a generative AI to create a phone call or message and send it to the parent saying, "Your child has not come to school. Please let us know the reason."

[1534] 6. The user (parent) receives the message and replies using the smartphone app whether or not the child will attend school and the reason.

[1535] The server receives the response from the parents and updates the attendance status database.

[1536] 7. The emotion engine analyzes the text data contained in the parent's reply and recognizes the parent's emotions.

[1537] The server records the parent's emotional state in a database based on the analysis results of the emotion engine.

[1538] 8. If the server does not receive a response from the parent within a certain period of time (e.g., 15 minutes) or detects an abnormality, it will notify the caregiver.

[1539] The server generates a warning message stating, "We are unable to confirm attendance for the child with unanswered ID 12345. Action is required," and sends it to the caregiver's device.

[1540] Embodiment of school bus monitoring system

[1541] System Overview

[1542] The device (bus camera) is installed inside the school bus and monitors the children's boarding times and behavior.

[1543] The server collects data from the on-board cameras and runs algorithms to detect anomalies.

[1544] Users (caregivers) can view the internal camera footage from the bus in real time on their smartphones or tablets.

[1545] The emotion engine analyzes the emotions of children on the bus and assists in anomaly detection.

[1546] Program processing explanation

[1547] 1. The device (in-bus camera) records the time the child boards the bus and sends the data to the server.

[1548] The server receives the boarding time data and updates the boarding status database.

[1549] 2. The device (in-bus camera) monitors the children's behavior and periodically sends data to the server.

[1550] The server receives behavioral data from the camera and uses AI technology to detect abnormalities.

[1551] 3. The emotion engine analyzes the emotions of the children on the bus from the acquired facial images and behavioral data.

[1552] The server records the child's emotional state in a database based on the analysis results of the emotion engine.

[1553] 4. If the server detects no activity for a certain period of time or detects an abnormality, it will send a notification to the caregiver.

[1554] The server runs an anomaly detection algorithm and sends real-time notifications to caregivers if an anomaly is detected.

[1555] 5. The user (caregiver) receives a notification and checks the camera footage inside the bus.

[1556] Childcare workers will check the situation on the bus through the app and respond as necessary.

[1557] Specific examples

[1558] As a concrete example, here is a simulation of a day at kindergarten:

[1559] At 8:00 a.m., the user (caregiver) starts the system and begins monitoring the day the children attend school.

[1560] When a child arrives at the entrance, a device (face recognition camera) takes a picture of their face and sends the data to the server.

[1561] At 8:30, the server performs facial recognition and updates the database of children who have already arrived at the school.

[1562] At 8:35, the emotion engine analyzes the facial image and behavioral data and recognizes the child's emotion as "anxiety."

[1563] At 9:00, the server lists the children who have not attended school and automatically sends a message to their parents.

[1564] The user (parent) receives the message and replies from the app at 8:50 a.m. explaining the reason for the child's absence, such as "I'm not feeling well."

[1565] At 9:15, the server checks the response from the parents and updates the attendance database.

[1566] The emotion engine analyzes the parents' replies and recognizes the emotion "worry."

[1567] At 10:00, the device (camera inside the bus) sends data on the children's behavior to the server, which analyzes it.

[1568] At 10:10, the emotion engine recognizes the emotion of the children on the bus as "excited."

[1569] At 10:30, the server detects an abnormality (e.g., a motionless child) and sends a notification to the user (caregiver).

[1570] The user (caregiver) receives the notification, checks the camera footage inside the bus, and takes the necessary action.

[1571] The above is an embodiment of the invention. By combining an emotion engine, it is possible to detect and respond to abnormalities with higher accuracy, thereby ensuring a high level of child safety while reducing the burden on caregivers.

[1572] The processing flow will be explained below.

[1573] Processing steps of the attendance management system

[1574] Step 1:

[1575] The user (caregiver or administrator) starts the system and begins monitoring the new day of attendance.

[1576] The caregiver presses the "Start Day of School" button on the system screen to start the system.

[1577] The server checks the daycare schedule, initializes the database based on today's date, and sets the "day of school start" status.

[1578] Step 2:

[1579] The device (face recognition camera) takes real-time photos of children arriving at the daycare facility.

[1580] A camera installed at the entrance automatically detects the faces of children arriving at the school and sends image data to a server in real time.

[1581] Step 3:

[1582] The server runs a facial recognition algorithm to analyze the transmitted facial image data.

[1583] The server compares the facial image data with existing facial data in the database.

[1584] Get the matching child's ID and update the corresponding database entry to "already in school."

[1585] Step 4:

[1586] The server sends the facial images and behavioral data to the emotion engine.

[1587] The emotion engine analyzes a child's emotions from facial expressions, movements, and other behavioral data.

[1588] Based on the analysis results, the server records the child's emotional state in a database.

[1589] Step 5:

[1590] The server lists children who have not arrived by the designated arrival time (e.g., 9:00).

[1591] The server checks the attendance status and generates a list of children who have not arrived by the specified time.

[1592] Step 6:

[1593] The server sends an automatic message to the parents of children who are not attending school.

[1594] The server uses a generative AI to create a phone call or message and send it to the parent saying, "Your child has not come to school. Please let us know the reason."

[1595] Step 7:

[1596] The user (parent) receives the message and replies using a smartphone app to indicate whether or not the child will attend school and the reason for the attendance.

[1597] Parents check the notification in the app, enter the reason (e.g., "absent due to illness"), and submit.

[1598] Step 8:

[1599] The server receives the response from the parents and updates the attendance status database.

[1600] The server records the received reason in a database and updates the corresponding child's status to "absent" or "late", etc.

[1601] Step 9:

[1602] The server sends the text data contained in the response from the parent to the emotion engine.

[1603] The emotion engine analyzes the parent's response and recognizes their emotional state (e.g., "worried" or "relieved").

[1604] Based on the analysis results, the server records the parent's emotional state in a database.

[1605] Step 10:

[1606] If the server does not receive a response from the parent within a certain period of time (e.g., 15 minutes) or detects an abnormality, it notifies the caregiver.

[1607] The server generates a warning message stating, "We are unable to confirm attendance for the child with unanswered ID 12345. Action is required," and sends it to the caregiver's device.

[1608] Processing steps of the school bus monitoring system

[1609] Step 1:

[1610] The device (camera inside the bus) records the time the child boards the bus and sends the data to the server.

[1611] A camera installed at the bus entrance automatically photographs children boarding the bus and sends the boarding time data to a server.

[1612] Step 2:

[1613] The server receives the boarding time data and updates the boarding status database.

[1614] The server performs facial recognition and records the ID of the child riding and the time of boarding in a database.

[1615] Step 3:

[1616] The device (a camera inside the bus) monitors the children's behavior and periodically sends data to the server.

[1617] Cameras inside the bus monitor children's movements in real time, capturing and transmitting image data at regular intervals.

[1618] Step 4:

[1619] The server receives behavioral data from the camera and uses AI technology to detect abnormalities.

[1620] The server analyzes behavioral data and detects abnormalities such as no activity for a certain period of time.

[1621] Step 5:

[1622] The server sends the facial images and behavioral data to the emotion engine.

[1623] The emotion engine analyzes the emotions of children on the bus from facial expressions, movements, and other behavioral data.

[1624] Based on the analysis results, the server records the child's emotional state in a database.

[1625] Step 6:

[1626] If the server detects an abnormality, it will send a notification to the caregiver.

[1627] Based on the anomaly detection algorithm, the server generates a notification stating, "There has been no activity from ID12345 on the bus for more than 10 minutes. Check is required." and sends it to the caregiver's device.

[1628] Step 7:

[1629] The user (caregiver) receives a notification and checks the camera footage inside the bus.

[1630] Caregivers can check notifications on their smartphones or tablets and use the app's camera feed function to view real-time footage.

[1631] If necessary, the childcare provider will contact the bus driver or other staff to determine the actual situation and respond accordingly.

[1632] Based on these processing steps, the system of the present invention can ensure a high level of safety for children in childcare facilities and on school buses. By combining it with an emotion engine, more accurate anomaly detection and appropriate responses can be achieved.

[1633] Example 2

[1634] 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."

[1635] Conventional child safety management systems in childcare facilities and vehicles used to transport children only monitor the children's arrival and departure status and behavior, but do not analyze and respond to their emotions. This makes it difficult to grasp the emotional state of children and their parents and to accurately detect and respond to abnormalities. In addition, notifications and contact with parents are done manually, which places a heavy burden on childcare workers and makes it difficult to respond in real time.

[1636] 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.

[1637] In this invention, the server includes means for monitoring the attendance status of children at the childcare facility using a face recognition camera, means for automatically contacting parents of children who have not arrived by a specified time, means for receiving responses from parents and updating the system based on the responses, means for notifying caregivers when there is no response from the parents or when an abnormality is detected, and means for analyzing the emotions of the children and parents using an emotion engine to detect abnormalities.This makes it possible to respond based on the emotional states of the children and parents, allowing for early detection of abnormalities and rapid response, as well as reducing the burden on caregivers.

[1638] A "face recognition camera" is a camera device that photographs the faces of children arriving at kindergarten and analyzes the images in real time.

[1639] "Automatic contact means" is a function that uses an automatic notification system to contact parents of children who have not arrived at the school by a specified time.

[1640] "Means for receiving responses from parents" refers to a function that inputs information provided by parents into the system and updates the attendance status database based on that information.

[1641] "Means for detecting abnormalities" refers to a function for identifying abnormal conditions based on the behavior and emotional analysis results of children and parents.

[1642] "Means for notifying caregivers" is a function that sends warnings and notifications to caregivers when an abnormality is detected or when there is no response from the parent.

[1643] The "emotion engine" is a function that analyzes the emotions of children and parents from facial images and text data and determines their state.

[1644] "Camera installed in a vehicle used for transporting children to school" refers to a camera device installed inside a bus or vehicle used for transporting children to school, to monitor the boarding time and behavior of children.

[1645] "Artificial intelligence technology" refers to algorithms and models that enable highly automated data analysis, recognition, prediction, and other processes.

[1646] A "generative AI model" is an AI system equipped with natural language generation technology that is used to create notification content for parents.

[1647] The present invention is a system for ensuring the safety of children in childcare facilities and vehicles that transport them to and from school, and uses facial recognition cameras, AI technology, an automatic notification system, and an emotion engine. Specific methods for implementing the invention are described below.

[1648] System Configuration

[1649] 1. Server

[1650] The server functions as the central control device of the attendance management system. Specifically, it performs the following processes:

[1651] Facial recognition algorithm: Analyzes image data sent from facial recognition cameras in real time to identify children.

[1652] Emotion engine: Analyzes the emotions of children and parents from captured facial images and behavioral data.

[1653] Automated notification system: Generates and sends messages to contact parents of children who have not arrived at school by the designated time. Uses generative AI models to create notifications in natural language.

[1654] Database management: Centrally manages attendance data, children's emotional data, parental response data, etc.

[1655] 2. Device (face recognition camera)

[1656] The facial recognition camera is installed at the entrance of the childcare facility and takes real-time pictures of the faces of children as they arrive. The captured facial images are immediately sent to a server. The camera also has a time stamp function that adds time information to the image data.

[1657] 3. Terminal (Bus Camera)

[1658] The cameras installed inside the buses will monitor the children's boarding times and activities in real time, and this data will also be sent to a server for analysis.

[1659] 4. Users (caregivers and guardians)

[1660] Parents and caregivers connect to the system through a smartphone or tablet app, and responses and information from parents are sent via the app, which updates the system accordingly.

[1661] Specific examples

[1662] Below is a specific scenario of daytime attendance management.

[1663] 8:00 AM: The childcare worker starts the system and starts monitoring the new day. The server loads the schedule based on today's date and starts managing the attendance status.

[1664] Arrival: When a child arrives at the entrance of the childcare facility, a facial recognition camera captures their face and sends the image to a server, which uses a facial recognition algorithm to identify the child and update the attendance database.

[1665] 8:35: The emotion engine analyzes the facial image and identifies the child's emotion as "anxiety." The server records this information in a database.

[1666] 9:00 AM: The server creates a list of children who have not arrived by the designated arrival time (e.g., 9:00 AM), and uses a generative AI model to automatically send a message to the parents stating, "Your child has not arrived. Please let us know the reason."

[1667] Parent response: The parent receives the message and replies from the app at 8:50 a.m., "I'm sick and will be absent." The server receives the parent's response and updates the attendance database.

[1668] Sentiment analysis: The emotion engine analyzes the parent's response and recognizes and records the emotion "worry."

[1669] Monitoring inside the bus: At 10:00, the camera inside the bus captures data on the children's behavior and sends it to the server, which analyzes it.

[1670] Anomaly detection: At 10:30, the server detects an anomaly (for example, a child not moving) and sends a notification to the caregiver saying, "An abnormal condition has been detected. Please check the situation on the bus."

[1671] Caregiver response: Caregivers receive a notification, check the camera footage on the bus, and take any necessary action.

[1672] Prompt Sentence Examples

[1673] "Your child has not attended school. Please let us know the reason."

[1674] The above is a concrete embodiment for carrying out the invention. The overall flow of the system and the function of each component are explained in detail to enable the realization of the invention.

[1675] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1676] The flow of this system's program processing

[1677] Step 1:

[1678] The user (caregiver or administrator) starts the system and begins monitoring the new day of attendance.

[1679] Input: System startup operation, today's date

[1680] Output: Read the childcare facility schedule and get ready to monitor attendance

[1681] Specific behavior:

[1682] The caregiver presses the "Start Monitoring" button using a dedicated management application.

[1683] The server gets today's date and reads the daycare schedule from the database.

[1684] The server starts monitoring the attendance status and displays when it is ready.

[1685] Step 2:

[1686] The device (face recognition camera) takes real-time photos of children arriving at the daycare facility and sends the facial image data to the server.

[1687] Input: Child's face image, time stamp

[1688] Output: Sending face image data to the server

[1689] Specific behavior:

[1690] When a child reaches the entrance, a facial recognition camera automatically captures their face.

[1691] Information about the time of photographing is added to the face image data.

[1692] Facial image data is sent from the camera to a server in real time.

[1693] Step 3:

[1694] The server analyzes the transmitted facial image data using a facial recognition algorithm and updates the attendance database.

[1695] Input: Face image data, time stamp

[1696] Output: Update the attendance database

[1697] Specific behavior:

[1698] The server inputs the facial image data into a facial recognition algorithm and matches it with the child's facial information registered in a database.

[1699] Based on the recognition results, the child's attendance record is added to the database, including the time of arrival and the facial image.

[1700] Step 4:

[1701] The emotion engine analyzes the child's emotions from the captured facial image, and the server records the results in a database.

[1702] Input: Facial image data, behavioral data

[1703] Output: Sentiment analysis results, update of sentiment database

[1704] Specific behavior:

[1705] The emotion engine analyzes the child's facial expressions from the facial image data and determines their emotional state (e.g., "joy," "anxiety," etc.).

[1706] The server receives the analysis results of the emotion engine and records the child's emotional state in a database.

[1707] Step 5:

[1708] The server lists the children who have not arrived by the designated arrival time (e.g. 9:00).

[1709] Input: attendance record, current time

[1710] Output: List of children not attending kindergarten

[1711] Specific behavior:

[1712] The server checks the attendance records and generates a list of children who have not arrived by the specified time.

[1713] Step 6:

[1714] The server automatically sends a message to the parents of children who are not attending school.

[1715] Input: List of children not attending kindergarten, prompt text

[1716] Output: Parental notification message

[1717] Specific behavior:

[1718] The server uses the generative AI model to create an automated notification about the non-attendance status, which includes the message, "Your child has not attended school. Please let us know the reason."

[1719] The generated notification will be sent to the parents via phone call or message.

[1720] Step 7:

[1721] The user (parent) receives the message and replies using the smartphone app, and the server records the information in a database.

[1722] Input: Parent's reply message

[1723] Output: Update the attendance status database

[1724] Specific behavior:

[1725] Parents check the notification on their smartphone app and reply by entering a reason, such as "I'm absent because I'm sick."

[1726] The server receives the response from the parents and updates the attendance status database.

[1727] Step 8:

[1728] The emotion engine analyzes the text contained in the responses from parents, and the server records the results in a database.

[1729] Input: Reply message

[1730] Output: Parent's emotion analysis results, emotion database update

[1731] Specific behavior:

[1732] The emotion engine analyzes the parent's reply message and recognizes emotions (e.g., "worried") from the text.

[1733] The server records the emotion analysis results in a database.

[1734] Step 9:

[1735] If the server does not receive a response from the parent within a certain period of time or detects an abnormality, it sends a notification to the caregiver.

[1736] Input: Response status, anomaly detection results

[1737] Output: Warning message to caregivers

[1738] Specific behavior:

[1739] The server continues to monitor if there is no response from the parent or if an abnormality is detected.

[1740] If there is no response within a certain period of time (e.g. 15 minutes), a warning message will be generated stating "We are unable to confirm attendance for child with unanswered ID 12345. Action is required." and sent to the caregiver.

[1741] (Application example 2)

[1742] 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."

[1743] Conventional worker management systems make it difficult for managers to grasp the attendance status and physical condition of each worker, making it difficult for managers to efficiently monitor worker safety and health. Furthermore, delays in responding to abnormalities can pose a risk to safety and the working environment, so a solution to these issues was needed.

[1744] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1745] In this invention, the server includes a means for monitoring the status of employees clocking in and out of the facility using a facial recognition camera, a means for automatically contacting the guardians of employees who have not arrived at work by a specified time, a means for receiving responses from the guardians and updating the system based on those responses, a means for notifying a manager if there is no response from the guardian or if an abnormality is detected, a means for analyzing the facial and behavioral data of workers and using an emotion engine to detect signs of fatigue or stress, and an automatic notification system for sending a real-time notification to a manager if an abnormality is detected. This allows the manager to understand not only the attendance status of workers but also their emotional state, enabling them to respond quickly if an abnormality occurs.

[1746] A "facial recognition camera" is a device that extracts facial features from received image data in order to identify a particular person.

[1747] "Facilities" refers to buildings and places where workers enter and exit in order to perform their work.

[1748] "Arriving at work" refers to the act of a worker arriving at the designated work location and beginning work.

[1749] "Clocking out" refers to the act of a worker leaving the designated work area and completing work.

[1750] "Manager" means a person who is responsible for supervising and managing the operation of workers or systems.

[1751] "Guardian" refers to a person who has the responsibility to supervise a worker who is a minor.

[1752] "Response" refers to the act of replying to a notification or the like.

[1753] An "abnormality" refers to an unexpected problem or deviation from normal business operations or behavior.

[1754] "Worker" means a person employed to perform a specific task at an establishment.

[1755] The "emotion engine" is software that analyzes a person's emotional state from received image data and behavioral data.

[1756] An "automatic notification system" is a system that automatically sends a notification to a pre-defined recipient when an abnormality is detected.

[1757] "Safety" refers to a state in which workers can perform their work without exposure to danger or risk.

[1758] "Fatigue" refers to a state in which a worker's physical and mental strength is exhausted due to work, making it difficult for them to perform their normal duties.

[1759] "Stress" refers to a state in which a worker feels pressure or tension due to their work or environment, making it difficult for them to carry out their normal work.

[1760] To implement this invention, several major components are required, including a facial recognition camera, an emotion engine for analyzing the emotional state of workers, an automatic notification system, and a database management system. A server-based system configuration is also essential to integrate these components.

[1761] System Hardware

[1762] 1. Facial recognition cameras (e.g., Logitech C920) are installed at entrances and key areas within the facility to monitor worker attendance and behavior in real time.

[1763] 2. A computer server (e.g., an AWS EC2 instance) acts as the central control unit, managing the database, running the facial recognition algorithm, and the emotion engine.

[1764] 3. Notification terminals (e.g., smartphones and tablets) are used by administrators to receive notifications from the system and respond in real time.

[1765] Software Components

[1766] 1. Facial recognition algorithms (e.g. OpenCV) are used to identify and identify faces from image data acquired from a camera.

[1767] 2. Emotion Engine is software that analyzes the emotional state of workers from image data and behavioral data.

[1768] 3. A database management system (e.g., SQLite) is used to store and manage employee attendance data and emotion analysis results.

[1769] 4. The automatic notification system provides a mechanism for sending real-time notifications to administrators when an abnormality is detected.

[1770] Program processing explanation

[1771] The server processes image data obtained from the facial recognition camera to identify workers and record their attendance status. It also inputs workers' facial and behavioral data into an emotion engine in real time to analyze signs of fatigue and stress. If an abnormality is detected, the server sends a real-time warning message to the administrator's notification terminal via an automatic notification system. Administrators can receive the notification and take appropriate measures.

[1772] Specific examples

[1773] At 8:00 AM, Worker A enters the facility and is captured by a facial recognition camera. The server uses a facial recognition algorithm to identify Worker A and update the attendance database. At 10:00 AM, the emotion engine analyzes Worker A's behavioral data and facial image to detect signs of fatigue. This information is recorded in the database, and at the same time, the server notifies the manager in real time through an automatic notification system. The manager receives the notification and can take appropriate action, such as encouraging Worker A to take a break.

[1774] Prompt Sentence Examples

[1775] "Generate a Python program to develop a safety and health management system using facial recognition and emotion analysis of workers in a logistics center. Use OpenCV for facial recognition and a custom Emotion Engine for emotion analysis, and add a function to send notifications when an anomaly is detected."

[1776] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1777] Step 1:

[1778] Image acquisition by face recognition camera

[1779] The terminal (face recognition camera) is installed at the entrance and exit of the facility and captures the facial images of workers as they pass through. The input is real-time video data captured by the camera, and the output is facial image data of the workers. Specifically, the camera periodically captures video and sends the data to a server.

[1780] Step 2:

[1781] Facial Recognition Processing

[1782] The server receives the facial image data sent from the terminal (face recognition camera) and identifies the worker using a facial recognition algorithm (e.g., OpenCV). The input is the facial image data, and the output is the ID of the identified worker. Specifically, the server runs the facial recognition algorithm, extracts features from the acquired facial image data, and compares them with known facial data in a database.

[1783] Step 3:

[1784] Update attendance database

[1785] The server updates the attendance database using the ID of the worker identified by the facial recognition process. The input is the ID of the identified worker, and the output is an updated attendance status database. Specifically, the server saves the identified worker's attendance time and ID in the database, and reflects the attendance status in real time.

[1786] Step 4:

[1787] Emotional state analysis

[1788] The server inputs the facial image data and behavioral data sent from the terminal (face recognition camera) into the emotion engine and analyzes the worker's emotional state. The input is facial image data and behavioral data, and the output is the detected emotional state (e.g., fatigue, stress, etc.). Specifically, the server uses the emotion engine to analyze facial expressions and behavioral patterns to determine the worker's emotions.

[1789] Step 5:

[1790] Anomaly detection and notification

[1791] The server detects anomalies based on the analysis results of the emotion engine, and if an anomaly is confirmed, it uses an automatic notification system to send a warning message to the administrator's notification terminal in real time. The input is the analysis result (emotional state), and the output is a warning message for the administrator. Specifically, the server runs the anomaly detection algorithm, and if an abnormal state such as fatigue or stress is detected, it generates a notification message and sends it to the administrator's smartphone or tablet.

[1792] Step 6:

[1793] Administrator response

[1794] The user (administrator) receives the notification message from the server and takes specific action through the app. The input is the notification message, and the output is the actual response procedure (e.g., instructing workers to take breaks). The specific action is for the administrator to check the notification and issue appropriate instructions to the workers.

[1795] Prompt Sentence Examples

[1796] "Generate a Python program to develop a safety and health management system using facial recognition and emotion analysis of workers in a logistics center. Use OpenCV for facial recognition and a custom Emotion Engine for emotion analysis, and add a function to send notifications when an anomaly is detected."

[1797] 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.

[1798] 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.

[1799] 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.

[1800] [Fourth embodiment]

[1801] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1802] 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.

[1803] 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).

[1804] 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.

[1805] 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.

[1806] 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).

[1807] 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.

[1808] 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.

[1809] 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.

[1810] 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.

[1811] 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.

[1812] 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.

[1813] 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."

[1814] This invention uses facial recognition cameras, AI technology, and an automatic notification system to ensure the safety of children at childcare facilities and on school buses. The system aims to monitor children's attendance in real time and detect abnormalities early, while reducing the burden on caregivers.

[1815] An embodiment of a kindergarten attendance management system

[1816] System Overview

[1817] The server is the central control unit of the attendance management system, managing the database, running the facial recognition algorithm, and sending notifications.

[1818] The terminal (facial recognition camera) is installed at the entrance of the childcare facility, photographs the faces of children arriving at the facility, and identifies them in real time.

[1819] Users (caregivers and parents) receive information through the system's app and perform the necessary operations.

[1820] Program processing explanation

[1821] 1. The user (caregiver or administrator) starts the system and begins monitoring a new day of attendance.

[1822] The server reads the schedule of the daycare facility and starts managing the attendance status for today.

[1823] 2. The device (face recognition camera) takes real-time photos of children arriving at the childcare facility and identifies them using a facial recognition algorithm.

[1824] The server receives the facial recognition results and updates the child's attendance database.

[1825] 3. The server lists children who have not arrived by the designated arrival time (e.g., 9:00).

[1826] The server checks the attendance status and generates a list of children who have not arrived by the specified time.

[1827] 4. The server automatically sends a message to the parents of children who have not arrived at school by the specified time.

[1828] The server uses the generation AI to send a message to the parent's contacts, for example, "Your child is not attending school. Please tell us why."

[1829] 5. The user (parent) receives the message and replies via the smartphone app whether or not the child will attend school and the reason.

[1830] The server receives the response from the parents and updates the attendance database.

[1831] 6. The server notifies the caregiver if there is no response from the parent or if an abnormality is detected.

[1832] If an abnormality is detected, the server automatically sends a warning message to the caregiver's device.

[1833] Embodiment of school bus monitoring system

[1834] System Overview

[1835] The device (bus camera) is installed inside the school bus and monitors the children's boarding times and behavior.

[1836] The server collects data from the on-board cameras and runs algorithms to detect anomalies.

[1837] Users (caregivers) can view the internal camera footage from the bus in real time on their smartphones or tablets.

[1838] Program processing explanation

[1839] 1. The device (in-bus camera) records the time the child boards the bus and sends the data to the server.

[1840] The server receives the boarding time data and records it in a database.

[1841] 2. The device (in-bus camera) monitors the children's behavior and periodically sends data to the server.

[1842] The server receives behavioral data from the camera and uses AI technology to detect abnormalities.

[1843] 3. The server sends a notification to the caregiver if there is no activity for a certain period of time or if an abnormality is detected.

[1844] The server runs an anomaly detection algorithm and sends real-time notifications to caregivers if an anomaly is detected.

[1845] 4. The user (caregiver) receives a notification and checks the internal camera footage from the bus.

[1846] Childcare workers will check the situation on the bus through the app and respond as necessary.

[1847] Specific examples

[1848] As a concrete example, here is a simulation of a day at kindergarten:

[1849] At 8:00 a.m., the user (caregiver) starts the system and begins monitoring the day the children attend school.

[1850] When a child arrives at the entrance, a device (face recognition camera) takes a picture of their face and sends the data to the server.

[1851] At 8:30, the server performs facial recognition and updates the database of children who have already arrived at the school.

[1852] At 9:00, the server lists the children who have not attended school and automatically sends a message to their parents.

[1853] The user (parent) receives the message and replies from the app at 8:50 a.m. explaining the reason for attending school.

[1854] At 9:15, the server checks the response from the parents and updates the attendance database.

[1855] At 10:00, the device (the camera inside the bus) sends some data on the children's behavior to the server, which analyzes it.

[1856] At 10:30, the server detects an abnormality (e.g., a motionless child) and sends a notification to the user (caregiver).

[1857] The user (caregiver) receives the notification, checks the camera footage inside the bus, and takes the necessary action.

[1858] The above is an embodiment of the invention. The present invention can reduce the burden on caregivers and ensure a high level of child safety.

[1859] The processing flow will be explained below.

[1860] Processing steps of the attendance management system

[1861] System startup and preparation

[1862] Step 1:

[1863] The user (caregiver or administrator) starts the system and begins monitoring the new day of attendance.

[1864] The caregiver presses the "Start Day of School" button on the system screen to start the system.

[1865] The server checks the childcare facility's schedule and initializes the database based on today's date.

[1866] Facial recognition when attending kindergarten

[1867] Step 2:

[1868] The device (face recognition camera) takes real-time photos of children arriving at the daycare facility.

[1869] Cameras are installed at the entrance and automatically detect the faces of children arriving at the school.

[1870] The camera transmits the facial image data to a server.

[1871] Step 3:

[1872] The server runs a facial recognition algorithm to analyze the transmitted facial image data.

[1873] The server compares the facial image data with existing facial data in the database.

[1874] Get the matching child's ID and update the corresponding database entry to "already in school."

[1875] Checking attendance status and contacting

[1876] Step 4:

[1877] The server lists children who have not arrived by the designated arrival time (e.g., 9:00).

[1878] The server compares the childcare facility's schedule with the child's attendance data and lists children who have not attended.

[1879] Step 5:

[1880] The server sends an automatic message to the parents of children who are not attending school.

[1881] The server uses a generative AI to create a phone call or message and send it to the parent saying, "Your child has not come to school. Please let us know the reason."

[1882] Parental Response Management

[1883] Step 6:

[1884] The user (parent) receives the message and replies using a smartphone app to indicate whether or not the child will attend school and the reason for the attendance.

[1885] Parents check the notification in the app, enter the reason (e.g., "absent due to illness"), and submit.

[1886] Step 7:

[1887] The server receives the response from the parents and updates the attendance status database.

[1888] The server records the received reason in a database and updates the status of the corresponding child.

[1889] Notification in case of an abnormality

[1890] Step 8:

[1891] If the server does not receive a response from the parent within a certain period of time (e.g., 15 minutes) or detects an abnormality, it notifies the caregiver.

[1892] The server generates a warning message saying, "We are unable to confirm attendance for child ID 12345, who has not responded. Action is required."

[1893] The server sends this message to the childcare provider's terminal.

[1894] Processing steps of the school bus monitoring system

[1895] Ride data collection and monitoring

[1896] Step 1:

[1897] The device (camera inside the bus) records the time the child boards the bus and sends the data to the server.

[1898] Cameras are installed at the entrances to the buses and automatically capture images of children boarding.

[1899] The camera sends a facial image to a server and records the time of boarding.

[1900] Step 2:

[1901] The server receives the boarding time data and updates the boarding status database.

[1902] The server performs facial recognition and records the ID of the child riding and the time of boarding in a database.

[1903] Behavior monitoring and anomaly detection

[1904] Step 3:

[1905] The device (a camera inside the bus) periodically captures images of children's behavior and sends the data to a server.

[1906] The cameras inside the bus monitor the children's movements and capture and transmit image data at regular intervals.

[1907] Step 4:

[1908] The server receives behavioral data from the camera and uses AI technology to detect abnormalities.

[1909] The server analyzes behavioral data and detects abnormalities such as no activity for a certain period of time.

[1910] Notification and confirmation in case of an abnormality

[1911] Step 5:

[1912] If the server detects an abnormality, it will send a notification to the caregiver.

[1913] Based on the anomaly detection algorithm, the server generates a notification stating, "There has been no activity from ID12345 on the bus for more than 10 minutes. Check is required." and sends it to the caregiver's device.

[1914] Step 6:

[1915] The user (caregiver) receives a notification and checks the camera footage inside the bus.

[1916] Caregivers can check notifications on their smartphones or tablets and use the app's camera feed function to view real-time footage.

[1917] If necessary, the childcare provider will contact the bus driver or other staff to determine the actual situation and respond accordingly.

[1918] Based on these processing steps, the system of the present invention can ensure a high level of child safety in childcare facilities and on buses.

[1919] Example 1

[1920] 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."

[1921] Conventional attendance management systems at childcare facilities require manual confirmation of children's attendance status and communication of that information to parents and caregivers, which is extremely time-consuming and labor-intensive. Furthermore, bus attendance is also primarily monitored manually, making it difficult to detect abnormalities early on. This increases the burden on caregivers and makes it difficult to ensure the safety of children, which has been an issue.

[1922] 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.

[1923] In this invention, the server includes a means for monitoring the attendance status of children at the childcare facility using a face recognition camera, a means for automatically contacting the parents of children who have not arrived by a specified time, a means for receiving responses from the parents and updating the database based on the responses, and a means for notifying the childcare worker if there is no response from the parents or if an abnormality is detected. This reduces the burden on the childcare worker and ensures a high level of child safety.

[1924] A "facial recognition camera" is a camera that captures a child's face and identifies the child using a facial recognition algorithm.

[1925] "Childcare facility" refers to any facility that provides childcare, such as kindergartens and nursery schools.

[1926] "Attendance status" is information indicating whether or not a child has attended a childcare facility.

[1927] "Guardian" means a child's parent or legal guardian.

[1928] "Automatic notification" is the process by which a system uses generative AI models to automatically create and send messages to specific recipients.

[1929] A "database" is a collection of information that is used to systematically manage and store information in a system.

[1930] "Abnormal" refers to a state that differs from a child's normal behavior or situation, such as not showing up to school or not moving around on the bus.

[1931] "Notification" is an operation in which the system sends specific information to a terminal to notify it.

[1932] "Means" refers to a set of methods or devices used to achieve a particular purpose.

[1933] An "in-bus camera" is a camera installed inside a school bus to monitor children's boarding times and behavior.

[1934] "Artificial intelligence technology" refers to all technologies that use machine learning and data analysis algorithms to automatically process and analyze data and support decision-making.

[1935] MODE FOR CARRYING OUT THE INVENTION

[1936] System Overview

[1937] The system of the present invention uses facial recognition cameras, AI technology, and an automatic notification system to ensure the safety of children at childcare facilities and on buses. The system consists of a server, terminals (facial recognition cameras and bus cameras), and users (caregivers and parents), and aims to monitor children's attendance in real time and detect any abnormalities early, while reducing the burden on caregivers.

[1938] Hardware and software used

[1939] The server is the central control unit of the attendance management system, managing the database, running the facial recognition algorithm, and sending notifications. In this case, a generative AI model is used.

[1940] The terminal (facial recognition camera) is installed at the entrance of the childcare facility, photographs the faces of children arriving at the facility, and identifies them in real time.

[1941] The device (bus camera) is installed inside the school bus and monitors the children's boarding times and behavior.

[1942] Users (caregivers and parents) receive information through the system's app and perform the necessary operations.

[1943] Program processing explanation

[1944] 1. When the system is started, the server loads the childcare facility's schedule and begins managing the day's attendance status. The server uses a generative AI model to analyze various data and generate notification messages.

[1945] 2. The device (face recognition camera) takes a real-time picture of the child as they arrive at the daycare center and identifies them using a face recognition algorithm. The face recognition results are sent to the server, which updates the child attendance database.

[1946] 3. The device (in-bus camera) records the time the child boards the bus and sends the data to a server. The server records this in a database and uses AI technology to detect any abnormalities.

[1947] 4. The server creates a list of children who have not arrived by the designated time and automatically sends a message to their parents using a generative AI model to create a message for parents and send it via email, SMS, etc.

[1948] 5. The user (parent) receives the notification and replies via the smartphone app whether or not the child will attend school and the reason for their attendance. The server receives the reply from the parent and updates the attendance database.

[1949] 6. If the server detects an abnormality or if there is no response from the parent, it will notify the caregiver, allowing the caregiver to understand the situation in real time and respond quickly.

[1950] Specific examples

[1951] As a concrete example, here is a simulation of a day at kindergarten:

[1952] At 8:00 a.m., the user (caregiver) starts the system and begins monitoring the day the children attend school.

[1953] When a child arrives at the entrance, a device (face recognition camera) takes a picture of their face and sends the data to the server.

[1954] At 8:30, the server performs facial recognition and updates the database of children who have already arrived at the school.

[1955] At 9:00, the server will list the children who have not attended school and automatically send a message to their parents. Example prompt: "Your child has not attended school. Please tell us the reason."

[1956] The user (parent) receives the message and replies from the app at 8:50 a.m. explaining the reason for attending school.

[1957] At 9:15, the server checks the response from the parents and updates the attendance database.

[1958] At 10:00, the device (the camera inside the bus) sends some data on the children's behavior to the server, which analyzes it.

[1959] At 10:30, the server detects an abnormality (e.g., a motionless child) and sends a notification to the user (caregiver).

[1960] The user (caregiver) receives the notification, checks the camera footage inside the bus, and takes the necessary action.

[1961] The above is an embodiment of the invention, which reduces the burden on caregivers and ensures a high level of child safety.

[1962] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1963] Step 1:

[1964] The user (caregiver or administrator) starts the system and begins monitoring the new day of attendance.

[1965] Input: The user taps the system wake-up button and enters schedule information.

[1966] Specific operation: The system starts when the user presses the start button on the management screen on their smartphone or PC.

[1967] Data processing / calculation: The server retrieves the current date and schedule information from the internal database and displays it.

[1968] Output: The childcare facility schedule is displayed on the admin page.

[1969] Step 2:

[1970] The device (facial recognition camera) takes real-time photos of the faces of children arriving at the childcare facility and identifies them using a facial recognition algorithm.

[1971] Input: Child's face image, previously registered face image data.

[1972] Specific operation: The camera detects motion and captures the child's face automatically.

[1973] Data processing / computation: A facial recognition algorithm runs on the server and matches the captured facial image with existing data in a database.

[1974] Output: The attendance information of children who match the matched result is updated.

[1975] Step 3:

[1976] The server lists the children who have not arrived by the designated arrival time (e.g. 9:00).

[1977] Input: School attendance database, specified time.

[1978] Specific operation: The server scans the attendance database and extracts children whose attendance could not be confirmed.

[1979] Data processing / calculation: Filter the attendance status in the database and generate a list of children who have not attended.

[1980] Output: At 9:00, the list of children who have not yet attended school is complete.

[1981] Step 4:

[1982] The server automatically sends a message to the parents of the listed children who have not attended school.

[1983] Input: List of non-attendance students, parent contact information.

[1984] How it works: Using a generative AI model, messages are automatically generated for each parent.

[1985] Data processing / computation: The AI ​​model creates a message and sends it via email, SMS, etc.

[1986] Output: A message is sent to the parent contact.

[1987] Step 5:

[1988] The user (parent) receives a notification and replies via a smartphone app whether or not their child will attend school and the reason for doing so.

[1989] Input: Parent response message.

[1990] Specific actions: Parents check the notification on their smartphone, open the reply form within the app, enter the reason, and submit.

[1991] Data processing / calculation: The server receives the reply and updates the attendance database.

[1992] Output: The updated attendance database is displayed.

[1993] Step 6:

[1994] If the server detects an abnormality, it will notify the caregiver.

[1995] Input: If there is no reply from the parent within a certain period of time, the AI ​​detects an anomaly.

[1996] Specific operation: The server monitors the response status and anomaly detection results.

[1997] Data processing / calculation: If an abnormality is detected or there is no response for a certain period of time, a notification will be automatically generated to the caregiver.

[1998] Output: A warning message is displayed on the caregiver's device.

[1999] Step 7:

[2000] The device (camera inside the bus) records the time the child boards the bus and sends the data to the server.

[2001] Input: Child boarding time data.

[2002] What it does: Cameras monitor children on the bus and record the time they board.

[2003] Data processing / calculation: The server receives the boarding time data and records it in the database.

[2004] Output: The registered boarding time data is updated.

[2005] Step 8:

[2006] The device (a camera inside the bus) monitors the children's behavior and periodically sends data to the server.

[2007] Input: Child behavior data.

[2008] How it works: Cameras inside the bus monitor children's behavior and record video data.

[2009] Data processing / calculation: The server receives behavioral data from the camera and analyzes it using AI technology.

[2010] Output: The analysis results are recorded in a database.

[2011] Step 9:

[2012] If the server detects no activity for a certain period of time or detects an abnormality, it will send a notification to the caregiver.

[2013] Input: Child activity data, anomaly detection results.

[2014] What it does: The server monitors the analysis results and generates a notification if it detects an anomaly.

[2015] Data processing / calculation: Run anomaly detection algorithms and create notifications if anomalies are detected.

[2016] Output: An abnormality notification is sent to the caregiver's device.

[2017] Step 10:

[2018] The user (caregiver) receives a notification and checks the internal camera footage of the bus.

[2019] Input: Anomaly notification, camera footage.

[2020] Specific operations: Childcare workers check notifications through the app and view real-time camera footage from inside the bus.

[2021] Data processing / calculation: Camera video data is streamed and provided to caregivers.

[2022] Output: The childcare worker can grasp the situation inside the bus in real time.

[2023] The above are the specific processing steps of the system and their detailed operations.

[2024] (Application example 1)

[2025] 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."

[2026] Ensuring passenger safety is important in autonomous vehicles, but conventional systems have been insufficient in monitoring passenger status and the interior of the vehicle. It has also been difficult to detect abnormalities in the passenger status or the interior of the vehicle in a timely manner and take necessary measures. This has led to a demand for an efficient method to ensure a high level of passenger safety.

[2027] 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.

[2028] In this invention, the server includes a means for monitoring the riding status of passengers using a face recognition camera installed at the entrance of the means of transportation, a means for automatically contacting passengers who have not boarded by a predetermined time, and a means for receiving responses from passengers and updating the system based on the responses. This makes it possible to quickly contact passengers even if they have not boarded by the predetermined time, and to grasp the riding status of passengers in real time.

[2029] "Transportation" refers to any means of transportation for carrying passengers, including autonomous vehicles.

[2030] A "face recognition camera" is a camera device that photographs and identifies the faces of passengers.

[2031] "Riding status" refers to the process and results of passengers boarding a means of transportation.

[2032] "Predetermined Time" means a specific time set for a Passenger to board a Transportation Vehicle.

[2033] "Automatic contact means" refers to a device or program that automatically communicates without human intervention when contact is required.

[2034] "Response" means a response from a passenger or observer who has received a communication.

[2035] "Means for updating the system" means a device or program that keeps the database and settings up to date based on passenger responses.

[2036] "Supervisor" means a person who monitors the safety of a means of transport and its passengers and takes any necessary action.

[2037] "In-camera video analysis means" refers to a device or program that analyzes video captured by a camera and detects abnormal movements or specific actions.

[2038] "In-vehicle behavior" refers to the actions and movements of passengers within a mode of transportation.

[2039] "AI technology" refers to technology that uses artificial intelligence to process data and perform identification and anomaly detection.

[2040] This invention is a system for ensuring passenger safety in autonomous vehicles, which uses a facial recognition camera, AI technology, and an automatic notification system. The system is configured as follows:

[2041] System Overview

[2042] The server is the central control unit of the system, managing the database, running the facial recognition algorithm, and sending notifications. Specifically, it can use a cloud-based system (e.g., AWS, Google Cloud).

[2043] The terminal (face recognition camera) is installed at the entrance of the transportation vehicle and takes pictures of the faces of passengers boarding the vehicle and identifies them in real time, using high-performance cameras and face recognition algorithms (e.g., OpenCV, TensorFlow).

[2044] Users (passengers and observers) receive information and perform necessary operations through the system's app, which is designed to work on both iOS and Android.

[2045] Program processing explanation

[2046] Ride monitoring

[2047] The device (a facial recognition camera) takes a picture of the passenger's face when boarding the transportation vehicle at the entrance and sends the data to a server, which uses a facial recognition algorithm to identify the passenger and update the passenger database. This process occurs in real time.

[2048] Automated Contact System

[2049] The server will list passengers who have not boarded by the designated time and automatically contact them. The server will then use a generative AI model to send a message to the passenger's contacts. For example, it could send a message saying, "You have not boarded. Please tell us why."

[2050] Passenger response

[2051] The user (passenger) receives the message and replies via the smartphone app whether or not they want to ride and the reason for the ride. The server receives this reply and updates the ride database.

[2052] Anomaly Detection System

[2053] The server receives data from the device (face recognition camera) and the in-car camera and uses AI technology to detect abnormalities. In particular, it analyzes unusually small movements and abnormal movements in real time, and if an abnormality is detected, it sends a notification to the monitor.

[2054] Specific implementation example

[2055] One day, an autonomous vehicle begins operation, and a facial recognition camera at the entrance monitors passengers. For example, Passenger A boards the vehicle at 8:00 AM, and the camera recognizes his face and sends the data to the server. At 8:30 AM, Passenger B, who has not boarded the vehicle, automatically receives a message saying, "You are not boarding. Please tell us the reason."

[2056] At 10:00 a.m., the camera detects unusual activity inside the vehicle (e.g., unusually little movement) and sends a notification to the supervisor, who then reviews the camera footage through the app and takes appropriate action.

[2057] Prompt Sentence Examples

[2058] "Apply a facial recognition algorithm to the input camera feed, identify the passenger's face, and send the results to a server."

[2059] "Apply anomaly detection algorithms to the in-car camera feed to detect anomalies and send you a notification."

[2060] As described above, this system can ensure a high level of passenger safety in self-driving vehicles.

[2061] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[2062] Step 1:

[2063] The terminal (face recognition camera) takes a picture of the face of the passenger boarding the transportation at the entrance.

[2064] Input: Video feed from facial recognition camera.

[2065] Output: Passenger face image.

[2066] How it works: Using a high-performance camera (e.g., Sony IMX sensor), the system captures the faces of passengers in real time as they board the vehicle. This video feed is then used by subsequent facial recognition algorithms.

[2067] Step 2:

[2068] The facial image captured by the device (face recognition camera) is sent to the server.

[2069] Input: Passenger face image.

[2070] Output: Facial image data sent to the server.

[2071] Specific operation: Using the edge computing function on the device, the captured facial image is uploaded to the server in real time (e.g., using 5G communication).

[2072] Step 3:

[2073] The server uses a facial recognition algorithm to identify the passenger.

[2074] Input: Submitted face image data.

[2075] Output: Identified passenger information.

[2076] Specific operation: A facial recognition algorithm (e.g., OpenCV or TensorFlow) is executed on the server to recognize the passenger's face from the transmitted facial image data. The recognized face is reflected in the passenger database.

[2077] Step 4:

[2078] The server lists passengers who have not boarded by a specified time.

[2079] Input: Ride database.

[2080] Output: A list of passengers who have not boarded.

[2081] What it does: It checks the current trip database against the default schedule and compiles a list of passengers who have not boarded by a given time.

[2082] Step 5:

[2083] The server automatically contacts passengers who have not yet boarded the train.

[2084] Input: List of absent passengers, contact information, generative AI model.

[2085] Output: The contact message sent.

[2086] Specific operation: Using a generative AI model, automatically generate a message for passengers who have not yet boarded the car, saying "You have not boarded. Please tell us the reason." and send it to registered contacts (e.g., using the Twilio API).

[2087] Step 6:

[2088] The user (passenger) receives the message and replies via a smartphone app whether or not they would like to board and the reason for doing so.

[2089] Input: The contact message sent by the server.

[2090] Output: Reply message from passenger.

[2091] Specific operation: The user (passenger) receives a message via the smartphone app and responds with information about the ride status. This reply is sent to the server.

[2092] Step 7:

[2093] The server receives the passenger's reply and updates the ride database.

[2094] Input: Reply message from passenger, current ride database.

[2095] Output: Updated trip database.

[2096] Specific operation: The server analyzes the received reply message and updates the ride database, thereby keeping the ride status up to date in real time.

[2097] Step 8:

[2098] The device (in-vehicle camera) monitors the interior of the transportation vehicle and detects abnormal or infrequent movement.

[2099] Input: In-car camera video feed.

[2100] Output: Anomaly detection data.

[2101] How it works: Cameras installed inside the vehicle monitor passenger movements and analyze the captured footage using AI technology. If any unusual or minor movements are detected, the information is sent to a server.

[2102] Step 9:

[2103] The server detects an anomaly and sends a notification to the monitor.

[2104] Input: Anomaly detection data, monitor contact information.

[2105] Output: The error notification message sent.

[2106] Specific operation: The server receives the anomaly detection data, and if an anomaly is detected, it sends a notification to the monitor (for example, by email or SMS). The monitor receives this notification and takes the necessary action.

[2107] The above steps can ensure a high level of passenger safety in autonomous vehicles.

[2108] 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.

[2109] This invention uses facial recognition cameras, AI technology, an automatic notification system, and an emotion engine to ensure the safety of children in childcare facilities and on school buses. The combination of the emotion engine enables the system to recognize the emotions of children and users, enabling more accurate anomaly detection and response. The system aims to monitor children's safety in real time while reducing the burden on caregivers.

[2110] An embodiment of a kindergarten attendance management system

[2111] System Overview

[2112] The server serves as the central control unit of the attendance management system, managing the database, running the face recognition algorithm, and the emotion engine.

[2113] The terminal (facial recognition camera) is installed at the entrance of the childcare facility, photographs the faces of children arriving at the facility, and identifies them in real time.

[2114] Users (caregivers and parents) receive information through the system's app and perform the necessary operations.

[2115] The emotion engine provides additional functionality to analyze the emotions of children and parents and detect anomalies.

[2116] Program processing explanation

[2117] 1. The user (caregiver or administrator) starts the system and begins monitoring a new day of attendance.

[2118] The server reads the schedule of the daycare facility and starts managing the attendance status for today.

[2119] 2. The device (face recognition camera) takes real-time photos of children arriving at the childcare facility and identifies them using a facial recognition algorithm.

[2120] The server receives the facial recognition results and updates the child's attendance database.

[2121] 3. The emotion engine analyzes the child's emotions from the acquired facial images and behavioral data.

[2122] The server records the child's emotional state in a database based on the analysis results of the emotion engine.

[2123] 4. The server lists children who have not arrived by the designated arrival time (e.g., 9:00).

[2124] The server checks the attendance status and generates a list of children who have not arrived by the specified time.

[2125] 5. The server sends an automatic message to the parents of children who are not attending school.

[2126] The server uses a generative AI to create a phone call or message and send it to the parent saying, "Your child has not come to school. Please let us know the reason."

[2127] 6. The user (parent) receives the message and replies using the smartphone app whether or not the child will attend school and the reason.

[2128] The server receives the response from the parents and updates the attendance status database.

[2129] 7. The emotion engine analyzes the text data contained in the parent's reply and recognizes the parent's emotions.

[2130] The server records the parent's emotional state in a database based on the analysis results of the emotion engine.

[2131] 8. If the server does not receive a response from the parent within a certain period of time (e.g., 15 minutes) or detects an abnormality, it will notify the caregiver.

[2132] The server generates a warning message stating, "We are unable to confirm attendance for the child with unanswered ID 12345. Action is required," and sends it to the caregiver's device.

[2133] Embodiment of school bus monitoring system

[2134] System Overview

[2135] The device (bus camera) is installed inside the school bus and monitors the children's boarding times and behavior.

[2136] The server collects data from the on-board cameras and runs algorithms to detect anomalies.

[2137] Users (caregivers) can view the internal camera footage from the bus in real time on their smartphones or tablets.

[2138] The emotion engine analyzes the emotions of children on the bus and assists in anomaly detection.

[2139] Program processing explanation

[2140] 1. The device (in-bus camera) records the time the child boards the bus and sends the data to the server.

[2141] The server receives the boarding time data and updates the boarding status database.

[2142] 2. The device (in-bus camera) monitors the children's behavior and periodically sends data to the server.

[2143] The server receives behavioral data from the camera and uses AI technology to detect abnormalities.

[2144] 3. The emotion engine analyzes the emotions of the children on the bus from the acquired facial images and behavioral data.

[2145] The server records the child's emotional state in a database based on the analysis results of the emotion engine.

[2146] 4. If the server detects no activity for a certain period of time or detects an abnormality, it will send a notification to the caregiver.

[2147] The server runs an anomaly detection algorithm and sends real-time notifications to caregivers if an anomaly is detected.

[2148] 5. The user (caregiver) receives a notification and checks the camera footage inside the bus.

[2149] Childcare workers will check the situation on the bus through the app and respond as necessary.

[2150] Specific examples

[2151] As a concrete example, here is a simulation of a day at kindergarten:

[2152] At 8:00 a.m., the user (caregiver) starts the system and begins monitoring the day the children attend school.

[2153] When a child arrives at the entrance, a device (face recognition camera) takes a picture of their face and sends the data to the server.

[2154] At 8:30, the server performs facial recognition and updates the database of children who have already arrived at the school.

[2155] At 8:35, the emotion engine analyzes the facial image and behavioral data and recognizes the child's emotion as "anxiety."

[2156] At 9:00, the server lists the children who have not attended school and automatically sends a message to their parents.

[2157] The user (parent) receives the message and replies from the app at 8:50 a.m. explaining the reason for the child's absence, such as "I'm not feeling well."

[2158] At 9:15, the server checks the response from the parents and updates the attendance database.

[2159] The emotion engine analyzes the parents' replies and recognizes the emotion "worry."

[2160] At 10:00, the device (camera inside the bus) sends data on the children's behavior to the server, which analyzes it.

[2161] At 10:10, the emotion engine recognizes the emotion of the children on the bus as "excited."

[2162] At 10:30, the server detects an abnormality (e.g., a motionless child) and sends a notification to the user (caregiver).

[2163] The user (caregiver) receives the notification, checks the camera footage inside the bus, and takes the necessary action.

[2164] The above is an embodiment of the invention. By combining an emotion engine, it is possible to detect and respond to abnormalities with higher accuracy, thereby ensuring a high level of child safety while reducing the burden on caregivers.

[2165] The processing flow will be explained below.

[2166] Processing steps of the attendance management system

[2167] Step 1:

[2168] The user (caregiver or administrator) starts the system and begins monitoring the new day of attendance.

[2169] The caregiver presses the "Start Day of School" button on the system screen to start the system.

[2170] The server checks the daycare schedule, initializes the database based on today's date, and sets the "day of school start" status.

[2171] Step 2:

[2172] The device (face recognition camera) takes real-time photos of children arriving at the daycare facility.

[2173] A camera installed at the entrance automatically detects the faces of children arriving at the school and sends image data to a server in real time.

[2174] Step 3:

[2175] The server runs a facial recognition algorithm to analyze the transmitted facial image data.

[2176] The server compares the facial image data with existing facial data in the database.

[2177] Get the matching child's ID and update the corresponding database entry to "already in school."

[2178] Step 4:

[2179] The server sends the facial images and behavioral data to the emotion engine.

[2180] The emotion engine analyzes a child's emotions from facial expressions, movements, and other behavioral data.

[2181] Based on the analysis results, the server records the child's emotional state in a database.

[2182] Step 5:

[2183] The server lists children who have not arrived by the designated arrival time (e.g., 9:00).

[2184] The server checks the attendance status and generates a list of children who have not arrived by the specified time.

[2185] Step 6:

[2186] The server sends an automatic message to the parents of children who are not attending school.

[2187] The server uses a generative AI to create a phone call or message and send it to the parent saying, "Your child has not come to school. Please let us know the reason."

[2188] Step 7:

[2189] The user (parent) receives the message and replies using a smartphone app to indicate whether or not the child will attend school and the reason for the attendance.

[2190] Parents check the notification in the app, enter the reason (e.g., "absent due to illness"), and submit.

[2191] Step 8:

[2192] The server receives the response from the parents and updates the attendance status database.

[2193] The server records the received reason in a database and updates the corresponding child's status to "absent" or "late", etc.

[2194] Step 9:

[2195] The server sends the text data contained in the response from the parent to the emotion engine.

[2196] The emotion engine analyzes the parent's response and recognizes their emotional state (e.g., "worried" or "relieved").

[2197] Based on the analysis results, the server records the parent's emotional state in a database.

[2198] Step 10:

[2199] If the server does not receive a response from the parent within a certain period of time (e.g., 15 minutes) or detects an abnormality, it notifies the caregiver.

[2200] The server generates a warning message stating, "We are unable to confirm attendance for the child with unanswered ID 12345. Action is required," and sends it to the caregiver's device.

[2201] Processing steps of the school bus monitoring system

[2202] Step 1:

[2203] The device (camera inside the bus) records the time the child boards the bus and sends the data to the server.

[2204] A camera installed at the bus entrance automatically photographs children boarding the bus and sends the boarding time data to a server.

[2205] Step 2:

[2206] The server receives the boarding time data and updates the boarding status database.

[2207] The server performs facial recognition and records the ID of the child riding and the time of boarding in a database.

[2208] Step 3:

[2209] The device (a camera inside the bus) monitors the children's behavior and periodically sends data to the server.

[2210] Cameras inside the bus monitor children's movements in real time, capturing and transmitting image data at regular intervals.

[2211] Step 4:

[2212] The server receives behavioral data from the camera and uses AI technology to detect abnormalities.

[2213] The server analyzes behavioral data and detects abnormalities such as no activity for a certain period of time.

[2214] Step 5:

[2215] The server sends the facial images and behavioral data to the emotion engine.

[2216] The emotion engine analyzes the emotions of children on the bus from facial expressions, movements, and other behavioral data.

[2217] Based on the analysis results, the server records the child's emotional state in a database.

[2218] Step 6:

[2219] If the server detects an abnormality, it will send a notification to the caregiver.

[2220] Based on the anomaly detection algorithm, the server generates a notification stating, "There has been no activity from ID12345 on the bus for more than 10 minutes. Check is required." and sends it to the caregiver's device.

[2221] Step 7:

[2222] The user (caregiver) receives a notification and checks the camera footage inside the bus.

[2223] Caregivers can check notifications on their smartphones or tablets and use the app's camera feed function to view real-time footage.

[2224] If necessary, the childcare provider will contact the bus driver or other staff to determine the actual situation and respond accordingly.

[2225] Based on these processing steps, the system of the present invention can ensure a high level of safety for children in childcare facilities and on school buses. By combining it with an emotion engine, more accurate anomaly detection and appropriate responses can be achieved.

[2226] Example 2

[2227] 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."

[2228] Conventional child safety management systems in childcare facilities and vehicles used to transport children only monitor the children's arrival and departure status and behavior, but do not analyze and respond to their emotions. This makes it difficult to grasp the emotional state of children and their parents and to accurately detect and respond to abnormalities. In addition, notifications and contact with parents are done manually, which places a heavy burden on childcare workers and makes it difficult to respond in real time.

[2229] 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.

[2230] In this invention, the server includes means for monitoring the attendance status of children at the childcare facility using a face recognition camera, means for automatically contacting parents of children who have not arrived by a specified time, means for receiving responses from parents and updating the system based on the responses, means for notifying caregivers when there is no response from the parents or when an abnormality is detected, and means for analyzing the emotions of the children and parents using an emotion engine to detect abnormalities.This makes it possible to respond based on the emotional states of the children and parents, allowing for early detection of abnormalities and rapid response, as well as reducing the burden on caregivers.

[2231] A "face recognition camera" is a camera device that photographs the faces of children arriving at kindergarten and analyzes the images in real time.

[2232] "Automatic contact means" is a function that uses an automatic notification system to contact parents of children who have not arrived at the school by a specified time.

[2233] "Means for receiving responses from parents" refers to a function that inputs information provided by parents into the system and updates the attendance status database based on that information.

[2234] "Means for detecting abnormalities" refers to a function for identifying abnormal conditions based on the behavior and emotional analysis results of children and parents.

[2235] "Means for notifying caregivers" is a function that sends warnings and notifications to caregivers when an abnormality is detected or when there is no response from the parent.

[2236] The "emotion engine" is a function that analyzes the emotions of children and parents from facial images and text data and determines their state.

[2237] "Camera installed in a vehicle used for transporting children to school" refers to a camera device installed inside a bus or vehicle used for transporting children to school, to monitor the boarding time and behavior of children.

[2238] "Artificial intelligence technology" refers to algorithms and models that enable highly automated data analysis, recognition, prediction, and other processes.

[2239] A "generative AI model" is an AI system equipped with natural language generation technology that is used to create notification content for parents.

[2240] The present invention is a system for ensuring the safety of children in childcare facilities and vehicles that transport them to and from school, and uses facial recognition cameras, AI technology, an automatic notification system, and an emotion engine. Specific methods for implementing the invention are described below.

[2241] System Configuration

[2242] 1. Server

[2243] The server functions as the central control device of the attendance management system. Specifically, it performs the following processes:

[2244] Facial recognition algorithm: Analyzes image data sent from facial recognition cameras in real time to identify children.

[2245] Emotion engine: Analyzes the emotions of children and parents from captured facial images and behavioral data.

[2246] Automated notification system: Generates and sends messages to contact parents of children who have not arrived at school by the designated time. Uses generative AI models to create notifications in natural language.

[2247] Database management: Centrally manages attendance data, children's emotional data, parental response data, etc.

[2248] 2. Device (face recognition camera)

[2249] The facial recognition camera is installed at the entrance of the childcare facility and takes real-time pictures of the faces of children as they arrive. The captured facial images are immediately sent to a server. The camera also has a time stamp function that adds time information to the image data.

[2250] 3. Terminal (Bus Camera)

[2251] The cameras in...

Claims

1. A means for monitoring attendance status of children attending a childcare facility using a facial recognition camera; A means of automatically contacting parents of children who have not arrived at school by the designated time; a means for receiving responses from the parent and updating the system accordingly; A means for notifying the caregiver if there is no response from the parent or if an abnormality is detected; A system including:

2. A method of monitoring children's boarding times and behavior by installing cameras on buses that take them to daycare facilities, and A means of notifying the caregiver if there is no activity for a certain period of time or if an abnormality is detected; The system of claim 1 further comprising:

3. A means for processing data from the facial recognition camera and the camera installed on the school bus and using AI technology to monitor the safety of children; The system of claim 1 further comprising:

Images