system

Abstract

We provide the system. [Solution] In an early childhood education facility, a means for receiving video information acquired from a camera installed within the facility, A means for recognizing the movements of educators and the behavior of children and detecting anomalies using an artificial intelligence model for analyzing the aforementioned video information, A means for generating a warning based on detected anomalies and notifying educators via their mobile devices, A means of accumulating daily behavioral data and generating information related to individual children as profiles, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, the method including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In modern childcare facilities, there are problems such as overwork due to a shortage of educational staff, difficulty in child safety management, and lack of transparency. Educational staff are forced to bear excessive burdens while performing various tasks, which is likely to lead to a shortage of personnel. Furthermore, it is difficult to grasp the activities of children in the facility in real time and prevent potential dangers. In addition, since guardians have limited means of obtaining detailed information about their children's growth and daily activities, there is also a problem that it is difficult to ensure the reliability of the facility.

Means for Solving the Problems

[0005] This invention provides a system that receives video information acquired from cameras installed within early childhood education facilities and analyzes it using an artificial intelligence model, thereby solving problems in such facilities. This makes it possible to recognize the movements of educators and the behavior of children, detect anomalies, and generate warnings. Warnings are sent to educators' mobile devices, allowing for immediate action. Furthermore, by accumulating daily behavioral data and generating and analyzing profiles of each child, aptitudes and behavioral patterns can be clarified. Reports based on these profiles and analyses can be provided to parents and administrators, improving transparency and safety.

[0006] An "early childhood education facility" is a facility that provides childcare and education primarily for young children.

[0007] A "camera" is a device used to acquire video data and plays a role in monitoring the situation within a facility.

[0008] "Video information" refers to video and still image data acquired by a camera, which is the subject of analysis and recording.

[0009] An "artificial intelligence model" is an algorithm or computer program used to analyze video information and perform pattern recognition or anomaly detection.

[0010] "Educational staff" refers to employees who work within a facility and are responsible for the care and education of young children.

[0011] "Behavioral data" refers to recorded information about the activities of young children and educators, which is accumulated for analysis.

[0012] A "profile" is detailed information about each child, generated based on behavioral data, and indicates their aptitudes and behavioral patterns.

[0013] A "warning" is a notification issued when an abnormal event is detected, and it functions as a way to alert educators.

[0014] A "portable information terminal" is a digital device that can be carried by educators and is used as a medium for receiving warnings and instructions. [Brief explanation of the drawing]

[0015] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14]It is a sequence diagram showing the processing flow of a data processing system in Application Example 2 when a sentiment engine is combined.

Embodiments for Carrying Out the Invention

[0016] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0017] First, the terms used in the following description will be explained.

[0018] In the following embodiments, a numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0019] In the following embodiments, a numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0020] In the following embodiments, a numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0021] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0022] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0023] [First Embodiment]

[0024] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0025] As shown in Figure 1, the 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.

[0026] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0027] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0028] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and 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.

[0029] 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 perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0030] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0031] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 according to the specific processing program 56 executed on the RAM 30.

[0033] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0034] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0035] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0036] This invention is a system that utilizes AI technology in early childhood education facilities to reduce the burden on educators and enhance the safety management of young children. The system operates by acquiring real-time video information of the facility's environment through a camera installed in the facility and transmitting it to a server.

[0037] When the server receives video information, it analyzes the data using an artificial intelligence model. Specifically, it recognizes the movements of educators and the behavior of children, and detects abnormal behavior or dangerous situations. For example, if it detects that a child is approaching dangerous play equipment or that an educator is moving around excessively, it generates a warning.

[0038] This warning is notified in real time on devices carried by educators, and is presented visually and audibly. The device enables a quick and appropriate response, supporting educators in resolving the issue immediately.

[0039] Furthermore, the server accumulates daily behavioral data within the facility and generates profiles for each child. This allows for the analysis of each child's aptitudes and behavioral patterns, and provides these findings as reports to educators and parents. This profile information can be used to gain a deeper understanding of each child's development and to provide appropriate education.

[0040] This system can not only improve the quality of education but also enhance transparency within the school and serve as an important means of gaining the trust of parents.

[0041] The following describes the processing flow.

[0042] Step 1:

[0043] The server receives video information transmitted from the camera. The server quickly reads this data and prepares to convert it into a format suitable for analysis.

[0044] Step 2:

[0045] The server analyzes video information using an artificial intelligence model. The AI ​​model identifies the movements of educators and the behavior of young children, detecting abnormal or dangerous situations. For example, it can determine if a child has entered a dangerous area or if an educator has deviated from their established routine.

[0046] Step 3:

[0047] The server generates a warning message based on the detected anomalies and risks. The generated warning requires immediate action and includes detailed information about the anomaly.

[0048] Step 4:

[0049] The server sends a warning message to the educator's mobile device. The device receives this message and displays it as a visual and auditory notification, allowing the educator to respond quickly on the spot.

[0050] Step 5:

[0051] The server continuously accumulates daily behavioral data. This includes the behavioral history of each child and related important indicators.

[0052] Step 6:

[0053] The server analyzes accumulated behavioral data and generates a profile for each child. This profile shows the child's aptitudes and behavioral patterns, which can be used to inform educational guidance.

[0054] Step 7:

[0055] Users can access the generated profiles and reports. Based on this information, parents and educational administrators can gain a deeper understanding of each child's characteristics and consider more appropriate educational and support measures.

[0056] (Example 1)

[0057] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0058] In early childhood education facilities, there is a need to efficiently manage the safety of young children while reducing the burden on educators. Traditional methods require educators to constantly monitor the children, which is labor-intensive. Furthermore, it can delay the prevention of dangerous situations, making a quick response difficult.

[0059] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0060] In this invention, the server includes processing means for receiving video data obtained from a video recording device, analysis means for recognizing personnel movements and children's behavior and detecting anomalies using a machine learning model to analyze the video data, and warning generation and notification means for generating warnings based on the detection results and notifying mobile terminals for educators. This makes it possible to efficiently manage the safety of children without educators having to constantly monitor them.

[0061] A "video recording device" is a device that acquires visual information through shooting or recording and outputs it as digital data.

[0062] "Video data" refers to digital data acquired by a video recording device to represent visual information.

[0063] A "machine learning model" is an algorithm trained to perform a specific task and is used for pattern recognition and prediction.

[0064] "Personnel actions and children's behavior" refers to the physical movements and actions exhibited by educators and children in educational facilities.

[0065] An "abnormality" refers to any action or behavior that falls outside the normal range, or an event or situation that deviates from predefined safety standards.

[0066] "Warning generation and notification means" refers to a method that includes technology for creating a corresponding warning when an anomaly is detected and for notifying the recipient of that warning.

[0067] A "portable device" is an electronic device that is easy to carry and can connect to and receive information via wireless communication.

[0068] "Behavioral data" refers to data that records, classifies, and stores the behavior of children and educators over a specific period.

[0069] A "profile" is a collection of information constructed based on an individual child's past behavioral data and characteristics, and is useful for individual analysis and understanding.

[0070] This system is designed to efficiently and safely manage children in early childhood education facilities. The server receives video data from video recording devices installed in the facility and utilizes machine learning models to analyze this data. The machine learning models used here are implemented using frameworks such as Tensorflow® and PyTorch.

[0071] The server uses a computer system with a high-performance processor and ample memory. This enables the processing of video data transmitted in real time from numerous cameras. The server also analyzes the movements and behaviors of educators and children in the video data to detect anomalies. If an anomaly is detected, it generates an alert and notifies the educators' mobile devices. These mobile devices receive visual and auditory notifications, prompting educators to take prompt action.

[0072] Educators, as users of the system, can easily respond when they receive warnings from the device. Situations where educators might respond include, for example, when a child approaches dangerous playground equipment. This system can also accumulate daily behavioral data and generate individual profiles for each child. These profiles can analyze the child's aptitudes and behavioral characteristics and provide reports to parents and educators.

[0073] As a concrete example, here is an example of a prompt: "Develop a program that recognizes when a toddler approaches a slide in a playground and issues an alert." By training an AI model based on this prompt, the system can efficiently detect specific abnormal behaviors and issue warnings.

[0074] This invention serves as a means to improve the quality of education by reducing the burden on educators and strengthening the safety management of young children.

[0075] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0076] Step 1:

[0077] The server receives video data in real time from multiple video recording devices installed within the facility. The input for this step is the video stream from each camera, and the output is the raw video data stored on the server. Specifically, multiple video inputs are aggregated to the server via the network.

[0078] Step 2:

[0079] The server preprocesses the received video data for analysis. The input is the unprocessed video data, which is the output of step 1, and the output is the video data converted into an analyzable format. Specifically, it removes noise and adjusts the frame resolution as needed.

[0080] Step 3:

[0081] The server performs behavioral analysis using a machine learning model based on pre-processed video data. The input is the video data prepared in step 2, and the output is the analysis results of the behavior and movements of the educators and children. In terms of movement, a behavior recognition algorithm analyzes the movements and performs a process to look for specific patterns or anomalies.

[0082] Step 4:

[0083] The server detects the presence or absence of anomalies based on the results obtained from the behavioral analysis. The input is the analysis results from step 3, and the output is information about the detected anomalies. The server identifies the anomalies by comparing them with pre-programmed criteria, for example, confirming that a child has approached a dangerous area.

[0084] Step 5:

[0085] The server generates an alert based on the detected anomaly and notifies the mobile device used by the educator. The input is the anomaly information from step 4, and the output is the alert message sent to the mobile device. Specifically, the generated alert is delivered as a push notification to the device, and visual and auditory alerts are issued.

[0086] Step 6:

[0087] The user, an educator, receives alerts from the terminal. The input is the alert message from the server, and the output is the appropriate response from the educator. This operation allows educators to check the alerts on the terminal and quickly assess and respond to the situation on-site.

[0088] Step 7:

[0089] The server accumulates behavioral data received on a daily basis and generates a profile for each child. The input is the behavioral data obtained in steps 3 and 4, and the output is the information saved as a profile. Specifically, each child's behavioral history is recorded in the database, and their performance and trends are reflected in the profile through analysis.

[0090] (Application Example 1)

[0091] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0092] In modern brick-and-mortar stores, accurately understanding customer behavior and providing efficient staffing and personalized service are essential. However, traditional methods fail to provide sufficient information for improving customer satisfaction and efficient operations, posing challenges to store management. In particular, responding quickly during peak hours is difficult, which can lead to a loss of customer experience.

[0093] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0094] In this invention, the server includes means for receiving video information acquired from a camera, means for recognizing the movements of staff and the behavior of customers and detecting anomalies using an artificial intelligence model for analyzing the video information, and means for generating warnings based on the detected anomalies and notifying a mobile information terminal. This enables real-time monitoring of customer behavior in physical stores, facilitating prompt responses by staff and improving customer satisfaction.

[0095] A "filming device" is a device used to acquire video information from inside a physical store.

[0096] "Video information" refers to real-time image data showing the situation inside the store.

[0097] An "artificial intelligence model" is a collection of machine learning algorithms used to analyze video information.

[0098] "Staff movements" refers to the actions of staff members performing their duties within the store.

[0099] "Customer behavior" refers to the actions and movements of consumers when they visit a physical store.

[0100] "Anomaly" refers to an unexpected situation in normal business operations or customer service.

[0101] A "warning" is information that is generated to alert someone when an anomaly is detected.

[0102] A "portable information terminal" is an electronic device that an employee can carry and use to receive information.

[0103] "Behavioral data" refers to data obtained from the daily activities of customers and employees.

[0104] A "profile" is a collection of information related to an individual, generated based on accumulated behavioral data.

[0105] The system implementing this invention is designed to monitor customer behavior and employee activities within physical stores and optimize store operations. A server receives video information in real time from cameras installed within the store. The received video information is analyzed using an artificial intelligence model. This model utilizes a machine learning platform such as TensorFlow. Through this analysis, customer movements and employee actions are recognized, and unusual behavior or congestion is detected.

[0106] Furthermore, the server immediately generates an alert based on detected anomalies. This alert is visually and audibly communicated to the employee's mobile device, which includes smart glasses and tablet devices. Data is accumulated as daily behavior, generating individual customer profiles. This profile information contributes to improving personalized service at the store.

[0107] As a concrete example, suppose a physical store becomes crowded on a weekend, and the server analyzes customer traffic patterns and detects congestion near the cash registers. The server then immediately generates a warning prompting staffing changes, which is sent to employees' mobile devices. Employees can receive this warning and respond quickly, thereby improving the customer experience.

[0108] An example of a prompt message is: "Create a program to analyze customer flow and optimize staff allocation during store congestion. Use cameras and smart glasses to perform real-time video analysis and provide warning notifications."

[0109] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0110] Step 1:

[0111] The server receives video information in real time from cameras installed within the store. It takes continuous video data from the cameras as input and sends this video data as output to subsequent analysis processes.

[0112] Step 2:

[0113] The server inputs the received video information into an artificial intelligence model to analyze the behavior of staff and customers. Specifically, it uses an AI model (e.g., a YOLO model using TensorFlow) to recognize people and movements within the video data. This analysis detects unusual behavior or movements, as well as congestion in specific areas.

[0114] Step 3:

[0115] The server detects anomalies based on the analysis results and generates warning messages as needed. The generated warnings include specific messages indicating congestion and are output.

[0116] Step 4:

[0117] The terminal receives generated alerts and displays visual and auditory notifications to staff. It receives alert messages from the server as input and displays alerts on devices worn by staff (smart glasses or tablets) as output.

[0118] Step 5:

[0119] The employee, acting as the user, takes immediate action based on the received notification. Specifically, this might involve going to a crowded checkout counter to provide additional assistance or selecting an appropriate response to improve customer service. This stage requires quick decision-making and action from the employee.

[0120] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0121] This invention provides a system that combines an emotion engine to improve safety and the quality of education in early childhood education facilities. This system operates by receiving video information transmitted in real time from a camera installed in the facility and analyzing the movements and facial expressions of educators and children.

[0122] The server analyzes the received video information using an artificial intelligence model. Specifically, it recognizes not only the movements of educators and the behavior of children, but also their emotional states from their facial expressions and gestures. For example, if a child looks like they are about to cry or an educator appears anxious, the emotion engine identifies that state and generates an analysis result.

[0123] If the server detects anomalies or necessary feedback from the analysis results, it generates warning messages and emotional feedback and immediately sends them to the educator's terminal. The terminal displays these notifications visually and audibly, enabling educators to respond quickly to the emotional state of the child in question or their own.

[0124] Furthermore, the server uses continuously accumulated behavioral and emotional data to generate individual child profiles, analyzing aptitudes, behavioral patterns, and emotional tendencies. These analysis results are provided as reports to administrators and parents, which can be used to develop educational programs tailored to individual needs.

[0125] Furthermore, this system will be an important means of enabling educational institutions to allocate resources efficiently, helping educators build better relationships with children, and enhancing safety and emotional care.

[0126] The following describes the processing flow.

[0127] Step 1:

[0128] The server receives video information transmitted from the camera. The server quickly processes the data and prepares it to extract the information necessary for real-time analysis.

[0129] Step 2:

[0130] The server uses an artificial intelligence model to analyze video information and recognize the movements of educators and children. Furthermore, it utilizes an emotion engine to determine emotional states from facial expressions and gestures. For example, it can recognize whether a child is smiling or whether an educator appears tired.

[0131] Step 3:

[0132] The server detects inappropriate situations and areas for improvement based on the analysis of emotional states and behavior. For example, it can identify situations where a child is not getting attention for extended periods or where an educator is showing signs of stress.

[0133] Step 4:

[0134] Based on the detected results, the server generates warning messages and emotional feedback for educators. This includes recommendations for behavioral adjustments and improvement of emotional state.

[0135] Step 5:

[0136] The device receives messages sent from the server and notifies educators. The notifications are presented visually and audibly, prompting immediate action. For example, they might say, "Add an activity to capture the children's attention" or "Take a deep breath and relax."

[0137] Step 6:

[0138] The server continuously collects behavioral and emotional data from video footage. This data is used to generate individual child profiles.

[0139] Step 7:

[0140] The server uses accumulated data to generate and provide users with analytical reports that help optimize educational programs and provide individualized support. Users (educators and parents) use these reports to understand children's development and adjust educational plans.

[0141] (Example 2)

[0142] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0143] Early childhood education facilities require appropriate monitoring and feedback to improve the quality of education while ensuring the safety of children. However, traditional methods make it difficult for educators to immediately identify abnormalities in children's emotions or behavior and take appropriate action. Furthermore, there is a lack of detailed profile generation to provide educational support tailored to each individual child.

[0144] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0145] In this invention, the server includes means for receiving video information from optical equipment placed within the facility; means for analyzing the video information with a machine learning model to identify the actions of educators and the activities of children and to recognize their emotional states; means for generating warnings and feedback based on the identified abnormal or significant emotional states and notifying educators via portable devices; and means for recording behavioral and emotional data and profiling information related to individual children. This enables educators to immediately grasp the state of children and improve safety and the quality of education while providing optimal educational programs.

[0146] "Optical equipment" refers to devices used to acquire image information, including cameras and sensors.

[0147] "Visual information" refers to visual data acquired from optical equipment, including information such as the actions and facial expressions of children and educational staff.

[0148] A "machine learning model" is a collection of algorithms used to analyze patterns and features in data and perform predictions and recognition, and it constitutes a part of artificial intelligence.

[0149] "Movement" refers to the physical movements and actions performed by educational staff and children, and specifically includes walking, gestures, and other similar actions.

[0150] "Activities" refer to the actions, play, and learning activities that children engage in within the facility.

[0151] "Emotional state" refers to the psychological state of children and educators as inferred from their facial expressions and gestures, and includes emotions such as joy, sadness, and anxiety.

[0152] "Abnormal" refers to behaviors or emotional states that deviate from normal patterns, and indicates situations that require special attention or intervention.

[0153] A "warning" is a message containing information to notify educational staff of detected anomalies or risks and to encourage attention and intervention.

[0154] "Feedback" refers to specific instructions and suggestions generated based on the analysis results, including information on how educational staff should respond to students.

[0155] "Portable devices" refer to communication devices used personally by educational staff, including smartphones and tablets.

[0156] "Behavioral data" refers to recorded information about children's daily actions and activities.

[0157] "Emotional data" refers to recorded information about a child's emotional state.

[0158] "Profiling" refers to the process of organizing the characteristics and tendencies of individual children based on recorded behavioral and emotional data, and compiling them into a single, comprehensive set of information.

[0159] This invention aims to improve the safety of children and the quality of education in early childhood education facilities. Specifically, it provides a system that utilizes video information acquired from optical equipment (such as cameras) placed within the facility to analyze the actions and emotional states of educators and children.

[0160] The server acquires video information in real time from optical equipment installed within the facility. This video information is analyzed using a machine learning model. The machine learning model used utilizes, for example, TensorFlow and OpenCV to analyze movements and facial expressions and identify the emotional state of children and educational staff. Through this analysis, the server can detect abnormal behavior and emotional anomalies.

[0161] Based on identified anomalies or significant emotional states, the server generates warnings and feedback and notifies educators via handheld devices. These notifications are presented to educators visually and audibly, enabling immediate and appropriate responses. For example, if a child appears to be on the verge of tears, the server might notify the handheld device with specific instructions such as, "The child looks like they are about to cry. Please comfort them."

[0162] Furthermore, the server uses accumulated behavioral and emotional data to generate profiles for each child. These profiles summarize aptitudes, behavioral patterns, and emotional tendencies, and are used as reports for administrators and parents. This makes it possible to provide an optimal educational program for each individual child.

[0163] An example of a prompt would be: "Create a program that analyzes the movements and facial expressions of children and educators from video footage, particularly detecting feelings of anxiety and sadness. Then, generate and deliver notifications based on the identified emotions in real time to the device." Using such prompts, the generating AI model will operate efficiently, achieving improved safety and quality of education in educational settings.

[0164] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0165] Step 1:

[0166] The server receives video information from optical equipment installed within the facility. A high-resolution video stream is supplied as input. To process this stream data quickly, the server temporarily stores it in storage.

[0167] Step 2:

[0168] The server analyzes the received video information using a machine learning model. This process first detects faces in the video using OpenCV, and then estimates the emotion associated with each face using a TensorFlow model. Preprocessed image data is provided as input, and the output returns labels for the identified actions and emotions. This process reveals the actions of educators and the emotional states of children.

[0169] Step 3:

[0170] The server identifies anomalies and important emotional states based on the analysis results. For example, if a child is in an emotional state of being about to cry, the server labels it as an "anomaly." The input is data of emotional labels, and the output is a flag indicating whether or not an anomaly exists. At this stage, the server's specific action is to generate conditional warnings.

[0171] Step 4:

[0172] The server generates feedback to send a notification to the educational staff's mobile device if an anomaly is detected. The input here is an anomaly flag, and the output is a notification message containing specific instructions. The server then sends this message to the device in real time.

[0173] Step 5:

[0174] The terminal presents notifications received from the server to educational staff visually and audibly. The input is the notification message, and the output is an alert displayed on the screen or an audible alert. Specifically, the terminal uses an appropriate UI (user interface) to make the notifications stand out.

[0175] Step 6:

[0176] The server continuously records behavioral and emotional data to generate individual child profiles. Using the accumulated dataset as input, it generates detailed profile information for each child as output. This process includes operations that analyze long-term aptitudes and behavioral patterns.

[0177] (Application Example 2)

[0178] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0179] In the work environment, it is necessary to appropriately monitor workers' stress levels and emotional states to create a safe and efficient work environment. However, conventional systems have difficulty grasping workers' emotional states in real time, which hinders the rapid provision of appropriate feedback and improvement suggestions.

[0180] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0181] In this invention, the server includes means for receiving image information acquired from imaging equipment installed in the work environment, means for recognizing the worker's movements and facial expressions and determining their emotional state using an artificial intelligence model for analyzing the image information, and means for generating improvement suggestions based on the determined emotional state and notifying the administrator's mobile information terminal. This makes it possible to grasp the worker's emotional state in real time and to quickly provide appropriate feedback and improvement suggestions.

[0182] "Recording equipment" refers to devices installed in a work environment to acquire video information.

[0183] "Image information" refers to visual data acquired by photographic equipment, and serves as the basis for analyzing the movements and facial expressions of workers.

[0184] An "artificial intelligence model" is a program used to analyze digital information, and it is a system that uses machine learning techniques to recognize the emotional state of a worker from their actions and facial expressions.

[0185] "Worker's movements and facial expressions" refer to the physical movements and facial expressions of a person in the work environment, and are a source of information for judging their emotional state.

[0186] "Emotional state" refers to the internal psychological state of a worker, including psychological conditions such as stress, anxiety, and satisfaction.

[0187] An "improvement suggestion" is a proposal for specific actions to be taken to improve the work environment or working conditions based on one's emotional state.

[0188] A "personal information terminal for administrators" is a device used by those who manage the work environment, and it is capable of receiving and notifying information in real time.

[0189] A "profile" is a dataset that compiles behavioral data and trends related to individual workers, and is useful for improving the work environment in the future.

[0190] The system that realizes this invention aims to provide a comfortable and safe working environment by monitoring the emotional state of workers in a factory in real time. The system utilizes image processing technology and artificial intelligence technology and operates in the following steps.

[0191] The server is the central hub of the system that continuously receives and processes video information from the cameras installed within the factory. A commonly used video camera is used as the camera, acquiring the video as digital data.

[0192] The received image information is analyzed by an artificial intelligence model installed on the server. This AI model is built using deep learning frameworks such as TensorFlow and PyTorch, and recognizes the emotional state from the worker's movements and facial expressions. For example, if the worker's facial expression indicates stress, it identifies the situation and generates analysis results through appropriate data calculations.

[0193] The analysis results are notified to a mobile device used by the administrator. This device is expected to be a smartphone or tablet. This notification is provided visually and audibly, allowing the administrator to understand the worker's status in real time and immediately identify any necessary improvement suggestions.

[0194] For example, if a worker's facial expression indicates severe fatigue, a specific improvement suggestion such as "Please allow this worker to take a break at an appropriate time" will be displayed on the terminal. Furthermore, daily activity data is stored on a cloud server, and individual worker profiles are generated based on this stored data. This provides information that contributes to long-term improvements to the work environment.

[0195] An example of a prompt to be input to the generating AI model would be an instruction such as, "Analyze the camera footage and evaluate the worker's stress level." Based on this prompt, the AI ​​performs the optimal analysis and provides the necessary feedback.

[0196] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0197] Step 1:

[0198] The server receives video information from imaging equipment installed within the factory. This video information is real-time visual data captured by the cameras. This data is then imported digitally and converted into a format suitable for analysis. Here, the input is raw data from the imaging equipment, and the output is digital image data that can be processed by the AI ​​model.

[0199] Step 2:

[0200] The server processes the received image information using an artificial intelligence model. Specifically, it uses deep learning frameworks such as TensorFlow and PyTorch to recognize the worker's movements and facial expressions. It receives digital image data converted from raw data as input and generates analysis results indicating the worker's emotional state as output. In this step, the AI ​​analyzes the data based on the prompt message in the generated AI model: "Analyze the camera footage and evaluate the worker's stress level."

[0201] Step 3:

[0202] The server sends the generated analysis results to the administrator's terminal. The terminal receives these results and displays improvement suggestions derived from the analysis in a visual and auditory way. The input is the AI ​​analysis results, and the output is an appropriate feedback message for the administrator. In this case, a suggestion such as "Please give this worker a break immediately" might be displayed on the screen.

[0203] Step 4:

[0204] The server accumulates daily operational data and creates profiles for each worker. The input is a history of past analysis results, and the output is profile data indicating each worker's aptitude and behavioral tendencies. These profiles are stored in the cloud and serve as an information resource useful for future improvements to the work environment.

[0205] Step 5:

[0206] The user (administrator) efficiently manages worker assignments and breaks based on improvement suggestions received from terminals. Input is notification information from terminals, and output is optimized resource allocation based on the workers' emotional states. A concrete example is setting additional break times for specific workers.

[0207] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0208] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0209] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0210] [Second Embodiment]

[0211] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0212] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0213] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0214] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0215] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0216] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0217] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0218] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0219] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0220] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0221] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0222] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. 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".

[0223] This invention is a system that utilizes AI technology in early childhood education facilities to reduce the burden on educators and enhance the safety management of young children. The system operates by acquiring real-time video information of the facility's environment through a camera installed in the facility and transmitting it to a server.

[0224] When the server receives video information, it analyzes the data using an artificial intelligence model. Specifically, it recognizes the movements of educators and the behavior of children, and detects abnormal behavior or dangerous situations. For example, if it detects that a child is approaching dangerous play equipment or that an educator is moving around excessively, it generates a warning.

[0225] This warning is notified in real time on devices carried by educators, and is presented visually and audibly. The device enables a quick and appropriate response, supporting educators in resolving the issue immediately.

[0226] Furthermore, the server accumulates daily behavioral data within the facility and generates profiles for each child. This allows for the analysis of each child's aptitudes and behavioral patterns, and provides these findings as reports to educators and parents. This profile information can be used to gain a deeper understanding of each child's development and to provide appropriate education.

[0227] This system can not only improve the quality of education but also enhance transparency within the school and serve as an important means of gaining the trust of parents.

[0228] The following describes the processing flow.

[0229] Step 1:

[0230] The server receives video information transmitted from the camera. The server quickly reads this data and prepares to convert it into a format suitable for analysis.

[0231] Step 2:

[0232] The server analyzes video information using an artificial intelligence model. The AI ​​model identifies the movements of educators and the behavior of young children, detecting abnormal or dangerous situations. For example, it can determine if a child has entered a dangerous area or if an educator has deviated from their established routine.

[0233] Step 3:

[0234] The server generates a warning message based on the detected anomalies and risks. The generated warning requires immediate action and includes detailed information about the anomaly.

[0235] Step 4:

[0236] The server sends a warning message to the educator's mobile device. The device receives this message and displays it as a visual and auditory notification, allowing the educator to respond quickly on the spot.

[0237] Step 5:

[0238] The server continuously accumulates daily behavioral data. This includes the behavioral history of individual infants and related important indicators.

[0239] Step 6:

[0240] The server analyzes accumulated behavioral data and generates a profile for each child. This profile shows the child's aptitudes and behavioral patterns, which can be used to inform educational guidance.

[0241] Step 7:

[0242] Users can access the generated profiles and reports. Based on this information, parents and educational administrators can gain a deeper understanding of each child's characteristics and consider more appropriate educational and support measures.

[0243] (Example 1)

[0244] Next, we will describe Example 1. 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."

[0245] In early childhood education facilities, there is a need to efficiently manage the safety of young children while reducing the burden on educators. Traditional methods require educators to constantly keep an eye on the children, which is labor-intensive. Furthermore, it can be difficult to respond quickly because it may delay the prevention of dangerous situations.

[0246] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0247] In this invention, the server includes processing means for receiving video data obtained from a video recording device, analysis means for recognizing personnel movements and children's behavior and detecting anomalies using a machine learning model to analyze the video data, and warning generation and notification means for generating warnings based on the detection results and notifying mobile terminals for educators. This makes it possible to efficiently manage the safety of children without educators having to constantly monitor them.

[0248] A "video recording device" is a device that acquires visual information through shooting or recording and outputs it as digital data.

[0249] "Video data" refers to digital data acquired by a video recording device to represent visual information.

[0250] A "machine learning model" is an algorithm trained to perform a specific task and is used for pattern recognition and prediction.

[0251] "Personnel actions and children's behavior" refers to the physical movements and actions exhibited by educators and children in educational facilities.

[0252] An "abnormality" refers to any action or behavior that falls outside the normal range, or an event or situation that deviates from predefined safety standards.

[0253] "Warning generation and notification means" refers to a method that includes technology for creating a corresponding warning when an anomaly is detected and for notifying the recipient of that warning.

[0254] A "portable device" is an electronic device that is easy to carry and can connect to and receive information via wireless communication.

[0255] "Behavioral data" refers to data that records, classifies, and stores the behavior of children and educators over a specific period.

[0256] A "profile" is a collection of information constructed based on an individual child's past behavioral data and characteristics, and is useful for individual analysis and understanding.

[0257] This system is designed to efficiently and safely manage children in early childhood education facilities. The server receives video data from video recording devices installed in the facility and utilizes machine learning models to analyze this data. The machine learning models used here are implemented using frameworks such as TensorFlow and PyTorch.

[0258] The server uses a computer system with a high-performance processor and ample memory. This enables the processing of video data transmitted in real time from numerous cameras. The server also analyzes the movements and behaviors of educators and children in the video data to detect anomalies. If an anomaly is detected, it generates an alert and notifies the educators' mobile devices. These mobile devices receive visual and auditory notifications, prompting educators to take prompt action.

[0259] Educators, as users of the system, can easily respond when they receive warnings from the device. Situations where educators might respond include, for example, when a child approaches dangerous playground equipment. This system can also accumulate daily behavioral data and generate individual profiles for each child. These profiles can analyze the child's aptitudes and behavioral characteristics and provide reports to parents and educators.

[0260] As a concrete example, here is an example of a prompt: "Develop a program that recognizes when a toddler approaches a slide in a playground and issues an alert." By training an AI model based on this prompt, the system can efficiently detect specific abnormal behaviors and issue warnings.

[0261] This invention serves as a means to improve the quality of education by reducing the burden on educators and strengthening the safety management of young children.

[0262] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0263] Step 1:

[0264] The server receives video data in real time from multiple video recording devices installed within the facility. The input for this step is the video stream from each camera, and the output is the raw video data stored on the server. Specifically, multiple video inputs are aggregated to the server via the network.

[0265] Step 2:

[0266] The server preprocesses the received video data for analysis. The input is the unprocessed video data, which is the output of step 1, and the output is the video data converted into an analyzable format. Specifically, it removes noise and adjusts the frame resolution as needed.

[0267] Step 3:

[0268] The server performs behavioral analysis using a machine learning model based on pre-processed video data. The input is the video data prepared in step 2, and the output is the analysis results of the behavior and movements of the educators and children. In terms of movement, a behavior recognition algorithm analyzes the movements and performs a process to look for specific patterns or anomalies.

[0269] Step 4:

[0270] The server detects the presence or absence of anomalies based on the results obtained from the behavioral analysis. The input is the analysis results from step 3, and the output is information about the detected anomalies. The server identifies the anomalies by comparing them with pre-programmed criteria, for example, confirming that a child has approached a dangerous area.

[0271] Step 5:

[0272] The server generates an alert based on the detected anomaly and notifies the mobile device used by the educator. The input is the anomaly information from step 4, and the output is the alert message sent to the mobile device. Specifically, the generated alert is delivered as a push notification to the device, and visual and auditory alerts are issued.

[0273] Step 6:

[0274] The user, an educator, receives alerts from the terminal. The input is the alert message from the server, and the output is the educator's appropriate response. This operation allows educators to check the terminal alerts and quickly assess the situation on-site and take action.

[0275] Step 7:

[0276] The server accumulates behavioral data received on a daily basis and generates a profile for each child. The input is the behavioral data obtained in steps 3 and 4, and the output is the information saved as a profile. Specifically, each child's behavioral history is recorded in the database, and their performance and trends are reflected in the profile through analysis.

[0277] (Application Example 1)

[0278] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0279] In modern physical stores, it is necessary to accurately grasp customer trends, efficiently allocate personnel, and provide personalized services. However, with conventional methods, sufficient information for improving customer satisfaction and operating efficiently cannot be obtained, which poses a challenge in store management. In particular, it is difficult to respond promptly during congestion, which may lead to a loss of the customer experience.

[0280] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following respective means.

[0281] In this invention, the server includes means for receiving video information acquired from a photographing device, means for recognizing the movements of staff and the behaviors of customers and detecting abnormalities using an artificial intelligence model for analyzing the video information, and means for generating a warning based on the detected abnormalities and notifying a portable information terminal. Thereby, it becomes possible to monitor customer trends in real time in a physical store, enabling prompt responses from staff and an improvement in customer satisfaction.

[0282] The "photographing device" is a device for acquiring video information within a physical store.

[0283] The "video information" is real-time image data indicating the situation within the store.

[0284] The "artificial intelligence model" is a collection of machine learning algorithms for analyzing video information.

[0285] The "movements of staff" refers to the actions of the staff performing tasks within the store.

[0286] The "behaviors of customers" are the behaviors and movements of consumers visiting a physical store.

[0287] An "abnormality" represents an unexpected situation in normal business operations and customer service.

[0288] A "warning" is information for raising awareness generated when an abnormality is detected.

[0289] A "portable information terminal" is an electronic device that an employee can carry and that can receive information.

[0290] "Behavioral data" refers to data obtained from the daily activities of customers and employees.

[0291] A "profile" is a collection of information related to an individual, generated based on accumulated behavioral data.

[0292] The system implementing this invention is designed to monitor customer behavior and employee activities within physical stores and optimize store operations. A server receives video information in real time from cameras installed within the store. The received video information is analyzed using an artificial intelligence model. This model utilizes a machine learning platform such as TensorFlow. Through this analysis, customer movements and employee actions are recognized, and unusual behavior or congestion is detected.

[0293] Furthermore, the server immediately generates an alert based on detected anomalies. This alert is visually and audibly communicated to the employee's mobile device, which includes smart glasses and tablet devices. Data is accumulated as daily behavior, generating individual customer profiles. This profile information contributes to improving personalized service at the store.

[0294] As a concrete example, suppose a physical store becomes crowded on a weekend, and the server analyzes customer traffic patterns and detects congestion near the cash registers. The server then immediately generates a warning prompting staffing changes, which is sent to employees' mobile devices. Employees can receive this warning and respond quickly, thereby improving the customer experience.

[0295] An example of a prompt message is: "Create a program to analyze customer flow and optimize staff allocation during store congestion. Use cameras and smart glasses to perform real-time video analysis and provide warning notifications."

[0296] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0297] Step 1:

[0298] The server receives video information in real time from cameras installed within the store. It takes continuous video data from the cameras as input and sends this video data as output to subsequent analysis processes.

[0299] Step 2:

[0300] The server inputs the received video information into an artificial intelligence model to analyze the behavior of staff and customers. Specifically, it uses an AI model (e.g., a YOLO model using TensorFlow) to recognize people and movements within the video data. This analysis detects unusual behavior or movements, as well as congestion in specific areas.

[0301] Step 3:

[0302] The server detects anomalies based on the analysis results and generates warning messages as needed. The generated warnings include specific messages indicating congestion and are output.

[0303] Step 4:

[0304] The terminal receives generated alerts and displays visual and auditory notifications to staff. It receives alert messages from the server as input and displays alerts on devices worn by staff (smart glasses or tablets) as output.

[0305] Step 5:

[0306] The employee, acting as the user, takes immediate action based on the received notification. Specifically, this might involve going to a crowded checkout counter to provide additional assistance or selecting an appropriate response to improve customer service. This stage requires quick decision-making and action from the employee.

[0307] Furthermore, an emotion engine for estimating the user's emotions may be combined. That is, the specific processing unit 290 may estimate the user's emotions using the emotion identification model 59 and perform specific processing using the user's emotions.

[0308] The present invention provides a system combined with an emotion engine in order to improve the safety and the quality of education in an early childhood education facility. This system operates by receiving in real time video information transmitted from a photographing device installed in the facility and analyzing the movements and expressions of educators and children.

[0309] The server analyzes the received video information using an artificial intelligence model. Specifically, it recognizes the emotional state not only from the movements of educators and the actions of children, but also from expressions and gestures. For example, when a child looks like he / she is about to cry or an educator shows signs of uneasiness, the emotion engine identifies that state and generates an analysis result.

[0310] When the server detects an abnormality or necessary feedback from this analysis result, it generates a warning message and emotional feedback and immediately transmits them to the terminal of the educator. The terminal visually and audibly displays these notifications, enabling the educator to quickly respond to the emotions of the target child and himself / herself.

[0311] Also, the server uses the continuously accumulated behavior data and emotion data to generate a profile for each child and analyzes the aptitude, behavior patterns, and emotional tendencies. This analysis result is provided as a report to administrators and guardians and can be used to formulate an educational program tailored to individual needs.

[0312] Furthermore, this system is an important means for educational institutions to efficiently allocate resources, help educators build better relationships with children, and strengthen safety and mental care.

[0313] The processing flow will be described below.

[0314] Step 1:

[0315] The server receives video information transmitted from the camera. The server quickly processes the data and prepares it to extract the information necessary for real-time analysis.

[0316] Step 2:

[0317] The server uses an artificial intelligence model to analyze video information and recognize the movements of educators and children. Furthermore, it utilizes an emotion engine to determine emotional states from facial expressions and gestures. For example, it can recognize whether a child is smiling or whether an educator appears tired.

[0318] Step 3:

[0319] The server detects inappropriate situations and areas for improvement based on the analysis of emotional states and behavior. For example, it can identify situations where a child is not getting attention for extended periods or where an educator is showing signs of stress.

[0320] Step 4:

[0321] Based on the detected results, the server generates warning messages and emotional feedback for educators. This includes recommendations for behavioral adjustments and improvement of emotional state.

[0322] Step 5:

[0323] The device receives messages sent from the server and notifies educators. The notifications are presented visually and audibly, prompting immediate action. For example, they might say, "Add an activity to capture the children's attention" or "Take a deep breath and relax."

[0324] Step 6:

[0325] The server continuously collects behavioral and emotional data from video footage. This data is used to generate individual child profiles.

[0326] Step 7:

[0327] The server uses accumulated data to generate and provide users with analytical reports that help optimize educational programs and provide individualized support. Users (educators and parents) use these reports to understand children's development and adjust educational plans.

[0328] (Example 2)

[0329] Next, we will describe Example 2. 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".

[0330] Early childhood education facilities require appropriate monitoring and feedback to improve the quality of education while ensuring the safety of children. However, traditional methods make it difficult for educators to immediately identify abnormalities in children's emotions or behavior and take appropriate action. Furthermore, there is a lack of detailed profile generation to provide educational support tailored to each individual child.

[0331] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0332] In this invention, the server includes means for receiving video information from optical equipment placed within the facility; means for analyzing the video information with a machine learning model to identify the actions of educators and the activities of children and to recognize their emotional states; means for generating warnings and feedback based on the identified abnormal or significant emotional states and notifying educators via portable devices; and means for recording behavioral and emotional data and profiling information related to individual children. This enables educators to immediately grasp the state of children and improve safety and the quality of education while providing optimal educational programs.

[0333] "Optical equipment" refers to devices used to acquire image information, including cameras and sensors.

[0334] "Visual information" refers to visual data acquired from optical equipment, including information such as the actions and facial expressions of children and educational staff.

[0335] A "machine learning model" is a collection of algorithms used to analyze patterns and features in data and perform predictions and recognition, and it constitutes a part of artificial intelligence.

[0336] "Movement" refers to the physical movements and actions performed by educational staff and children, and specifically includes walking, gestures, and other similar actions.

[0337] "Activities" refer to the actions, play, and learning activities that children engage in within the facility.

[0338] "Emotional state" refers to the psychological state of children and educators as inferred from their facial expressions and gestures, and includes emotions such as joy, sadness, and anxiety.

[0339] "Abnormal" refers to behaviors or emotional states that deviate from normal patterns, and indicates situations that require special attention or intervention.

[0340] A "warning" is a message containing information to notify educational staff of detected anomalies or risks and to encourage attention and intervention.

[0341] "Feedback" refers to specific instructions and suggestions generated based on the analysis results, including information on how educational staff should respond to students.

[0342] "Portable devices" refer to communication devices used personally by educational staff, including smartphones and tablets.

[0343] "Behavioral data" refers to recorded information about children's daily actions and activities.

[0344] "Emotional data" refers to recorded information about a child's emotional state.

[0345] "Profiling" refers to the process of organizing the characteristics and tendencies of individual children based on recorded behavioral and emotional data, and compiling them into a single, comprehensive set of information.

[0346] This invention aims to improve the safety of children and the quality of education in early childhood education facilities. Specifically, it provides a system that utilizes video information acquired from optical equipment (such as cameras) placed within the facility to analyze the actions and emotional states of educators and children.

[0347] The server acquires video information in real time from optical equipment installed within the facility. This video information is analyzed using a machine learning model. The machine learning model used utilizes, for example, TensorFlow and OpenCV to analyze movements and facial expressions and identify the emotional state of children and educational staff. Through this analysis, the server can detect abnormal behavior and emotional anomalies.

[0348] Based on identified anomalies or significant emotional states, the server generates warnings and feedback and notifies educators via handheld devices. These notifications are presented to educators visually and audibly, enabling immediate and appropriate responses. For example, if a child appears to be on the verge of tears, the server might notify the handheld device with specific instructions such as, "The child looks like they are about to cry. Please comfort them."

[0349] Furthermore, the server uses accumulated behavioral and emotional data to generate profiles for each child. These profiles summarize aptitudes, behavioral patterns, and emotional tendencies, and are used as reports for administrators and parents. This makes it possible to provide an optimal educational program for each individual child.

[0350] An example of a prompt would be: "Create a program that analyzes the movements and facial expressions of children and educators from video footage, particularly detecting feelings of anxiety and sadness. Then, generate and deliver notifications based on the identified emotions in real time to the device." Using such prompts, the generating AI model will operate efficiently, achieving improved safety and quality of education in educational settings.

[0351] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0352] Step 1:

[0353] The server receives video information from optical equipment installed within the facility. A high-resolution video stream is supplied as input. To process this stream data quickly, the server temporarily stores it in storage.

[0354] Step 2:

[0355] The server analyzes the received video information using a machine learning model. This process first detects faces in the video using OpenCV, and then estimates the emotion associated with each face using a TensorFlow model. Preprocessed image data is provided as input, and the output returns labels for the identified actions and emotions. This process reveals the actions of educators and the emotional states of children.

[0356] Step 3:

[0357] The server identifies anomalies and important emotional states based on the analysis results. For example, if a child is in an emotional state of being about to cry, the server labels it as an "anomaly." The input is data of emotional labels, and the output is a flag indicating whether or not an anomaly exists. At this stage, the server's specific action is to generate conditional warnings.

[0358] Step 4:

[0359] The server generates feedback to send a notification to the educational staff's mobile device if an anomaly is detected. The input here is an anomaly flag, and the output is a notification message containing specific instructions. The server then sends this message to the device in real time.

[0360] Step 5:

[0361] The terminal presents notifications received from the server to educational staff visually and audibly. The input is the notification message, and the output is an alert displayed on the screen or an audible alert. Specifically, the terminal uses an appropriate UI (user interface) to make the notifications stand out.

[0362] Step 6:

[0363] The server continuously records behavioral and emotional data to generate individual child profiles. Using the accumulated dataset as input, it generates detailed profile information for each child as output. This process includes operations that analyze long-term aptitudes and behavioral patterns.

[0364] (Application Example 2)

[0365] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0366] In the work environment, it is necessary to appropriately monitor workers' stress levels and emotional states to create a safe and efficient work environment. However, conventional systems have difficulty grasping workers' emotional states in real time, which hinders the rapid provision of appropriate feedback and improvement suggestions.

[0367] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0368] In this invention, the server includes means for receiving image information acquired from imaging equipment installed in the work environment, means for recognizing the worker's movements and facial expressions and determining their emotional state using an artificial intelligence model for analyzing the image information, and means for generating improvement suggestions based on the determined emotional state and notifying the administrator's mobile information terminal. This makes it possible to grasp the worker's emotional state in real time and to quickly provide appropriate feedback and improvement suggestions.

[0369] "Recording equipment" refers to devices installed in a work environment to acquire video information.

[0370] "Image information" refers to visual data acquired by photographic equipment, and serves as the basis for analyzing the movements and facial expressions of workers.

[0371] An "artificial intelligence model" is a program used to analyze digital information, and it is a system that uses machine learning techniques to recognize the emotional state of a worker from their actions and facial expressions.

[0372] "Worker's movements and facial expressions" refer to the physical movements and facial expressions of a person in the work environment, and are a source of information for judging their emotional state.

[0373] "Emotional state" refers to the internal psychological state of a worker, including psychological conditions such as stress, anxiety, and satisfaction.

[0374] An "improvement suggestion" is a proposal for specific actions to be taken to improve the work environment or working conditions based on one's emotional state.

[0375] A "personal information terminal for administrators" is a device used by those who manage the work environment, and it is capable of receiving and notifying information in real time.

[0376] A "profile" is a dataset that compiles behavioral data and trends related to individual workers, and is useful for improving the work environment in the future.

[0377] The system that realizes this invention aims to provide a comfortable and safe working environment by monitoring the emotional state of workers in a factory in real time. The system utilizes image processing technology and artificial intelligence technology and operates in the following steps.

[0378] The server is the central hub of the system that continuously receives and processes video information from the cameras installed within the factory. A commonly used video camera is used as the camera, acquiring the video as digital data.

[0379] The received image information is analyzed by an artificial intelligence model installed on the server. This AI model is built using deep learning frameworks such as TensorFlow and PyTorch, and recognizes the emotional state from the worker's movements and facial expressions. For example, if the worker's facial expression indicates stress, it identifies the situation and generates analysis results through appropriate data calculations.

[0380] The analysis results are notified to a mobile device used by the administrator. This device is expected to be a smartphone or tablet. This notification is provided visually and audibly, allowing the administrator to understand the worker's status in real time and immediately identify any necessary improvement suggestions.

[0381] For example, if a worker's facial expression indicates severe fatigue, a specific improvement suggestion such as "Please allow this worker to take a break at an appropriate time" will be displayed on the terminal. Furthermore, daily activity data is stored on a cloud server, and individual worker profiles are generated based on this stored data. This provides information that contributes to long-term improvements to the work environment.

[0382] An example of a prompt to be input to the generating AI model would be an instruction such as, "Analyze the camera footage and evaluate the worker's stress level." Based on this prompt, the AI ​​performs the optimal analysis and provides the necessary feedback.

[0383] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0384] Step 1:

[0385] The server receives video information from imaging equipment installed within the factory. This video information is real-time visual data captured by the cameras. This data is then imported digitally and converted into a format suitable for analysis. Here, the input is raw data from the imaging equipment, and the output is digital image data that can be processed by the AI ​​model.

[0386] Step 2:

[0387] The server processes the received image information using an artificial intelligence model. Specifically, it uses deep learning frameworks such as TensorFlow and PyTorch to recognize the worker's movements and facial expressions. It receives digital image data converted from raw data as input and generates analysis results indicating the worker's emotional state as output. In this step, the AI ​​analyzes the data based on the prompt message in the generated AI model: "Analyze the camera footage and evaluate the worker's stress level."

[0388] Step 3:

[0389] The server sends the generated analysis results to the administrator's terminal. The terminal receives these results and displays improvement suggestions derived from the analysis in a visual and auditory way. The input is the AI ​​analysis results, and the output is an appropriate feedback message for the administrator. In this case, a suggestion such as "Please give this worker a break immediately" might be displayed on the screen.

[0390] Step 4:

[0391] The server accumulates daily operational data and creates profiles for each worker. The input is a history of past analysis results, and the output is profile data indicating each worker's aptitude and behavioral tendencies. These profiles are stored in the cloud and serve as an information resource useful for future improvements to the work environment.

[0392] Step 5:

[0393] The user (administrator) efficiently manages worker assignments and breaks based on improvement suggestions received from terminals. Input is notification information from terminals, and output is optimized resource allocation based on the workers' emotional states. A concrete example is setting additional break times for specific workers.

[0394] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0395] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0396] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0397] [Third Embodiment]

[0398] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0399] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0400] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0401] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0402] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0403] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0404] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0405] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0406] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0407] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0408] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0409] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0410] This invention is a system that utilizes AI technology in early childhood education facilities to reduce the burden on educators and enhance the safety management of young children. The system operates by acquiring real-time video information of the facility's environment through a camera installed in the facility and transmitting it to a server.

[0411] When the server receives video information, it analyzes the data using an artificial intelligence model. Specifically, it recognizes the movements of educators and the behavior of children, and detects abnormal behavior or dangerous situations. For example, if it detects that a child is approaching dangerous play equipment or that an educator is moving around excessively, it generates a warning.

[0412] This warning is notified in real time on devices carried by educators, and is presented visually and audibly. The device enables a quick and appropriate response, supporting educators in resolving the issue immediately.

[0413] Furthermore, the server accumulates daily behavioral data within the facility and generates profiles for each child. This allows for the analysis of each child's aptitudes and behavioral patterns, and provides these findings as reports to educators and parents. This profile information can be used to gain a deeper understanding of each child's development and to provide appropriate education.

[0414] This system can not only improve the quality of education but also enhance transparency within the school and serve as an important means of gaining the trust of parents.

[0415] The following describes the processing flow.

[0416] Step 1:

[0417] The server receives video information transmitted from the camera. The server quickly reads this data and prepares to convert it into a format suitable for analysis.

[0418] Step 2:

[0419] The server analyzes video information using an artificial intelligence model. The AI ​​model identifies the movements of educators and the behavior of young children, detecting abnormal or dangerous situations. For example, it can determine if a child has entered a dangerous area or if an educator has deviated from their established routine.

[0420] Step 3:

[0421] The server generates a warning message based on the detected anomalies and risks. The generated warning requires immediate action and includes detailed information about the anomaly.

[0422] Step 4:

[0423] The server sends a warning message to the educator's mobile device. The device receives this message and displays it as a visual and auditory notification, allowing the educator to respond quickly on the spot.

[0424] Step 5:

[0425] The server continuously accumulates daily behavioral data. This includes the behavioral history of individual infants and related important indicators.

[0426] Step 6:

[0427] The server analyzes accumulated behavioral data and generates a profile for each child. This profile shows the child's aptitudes and behavioral patterns, which can be used to inform educational guidance.

[0428] Step 7:

[0429] Users can access the generated profiles and reports. Based on this information, parents and educational administrators can gain a deeper understanding of each child's characteristics and consider more appropriate educational and support measures.

[0430] (Example 1)

[0431] Next, we will describe Example 1. 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."

[0432] In early childhood education facilities, there is a need to efficiently manage the safety of young children while reducing the burden on educators. Traditional methods require educators to constantly keep an eye on the children, which is labor-intensive. Furthermore, it can be difficult to respond quickly because it may delay the prevention of dangerous situations.

[0433] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0434] In this invention, the server includes processing means for receiving video data obtained from a video recording device, analysis means for recognizing personnel movements and children's behavior and detecting anomalies using a machine learning model to analyze the video data, and warning generation and notification means for generating warnings based on the detection results and notifying mobile terminals for educators. This makes it possible to efficiently manage the safety of children without educators having to constantly monitor them.

[0435] A "video recording device" is a device that acquires visual information through shooting or recording and outputs it as digital data.

[0436] "Video data" refers to digital data acquired by a video recording device to represent visual information.

[0437] A "machine learning model" is an algorithm trained to perform a specific task and is used for pattern recognition and prediction.

[0438] "Personnel actions and children's behavior" refers to the physical movements and actions exhibited by educators and children in educational facilities.

[0439] An "abnormality" refers to any action or behavior that falls outside the normal range, or an event or situation that deviates from predefined safety standards.

[0440] "Warning generation and notification means" refers to a method that includes technology for creating a corresponding warning when an anomaly is detected and for notifying the recipient of that warning.

[0441] A "portable device" is an electronic device that is easy to carry and can connect to and receive information via wireless communication.

[0442] "Behavioral data" refers to data that records, classifies, and stores the behavior of children and educators over a specific period.

[0443] A "profile" is a collection of information constructed based on an individual child's past behavioral data and characteristics, and is useful for individual analysis and understanding.

[0444] This system is designed to efficiently and safely manage children in early childhood education facilities. The server receives video data from video recording devices installed in the facility and utilizes machine learning models to analyze this data. The machine learning models used here are implemented using frameworks such as TensorFlow and PyTorch.

[0445] The server uses a computer system with a high-performance processor and ample memory. This enables the processing of video data transmitted in real time from numerous cameras. The server also analyzes the movements and behaviors of educators and children in the video data to detect anomalies. If an anomaly is detected, it generates an alert and notifies the educators' mobile devices. These mobile devices receive visual and auditory notifications, prompting educators to take prompt action.

[0446] Educators, as users of the system, can easily respond when they receive warnings from the device. Situations where educators might respond include, for example, when a child approaches dangerous playground equipment. This system can also accumulate daily behavioral data and generate individual profiles for each child. These profiles can analyze the child's aptitudes and behavioral characteristics and provide reports to parents and educators.

[0447] As a concrete example, here is an example of a prompt: "Develop a program that recognizes when a toddler approaches a slide in a playground and issues an alert." By training an AI model based on this prompt, the system can efficiently detect specific abnormal behaviors and issue warnings.

[0448] This invention serves as a means to improve the quality of education by reducing the burden on educators and strengthening the safety management of young children.

[0449] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0450] Step 1:

[0451] The server receives video data in real time from multiple video recording devices installed within the facility. The input for this step is the video stream from each camera, and the output is the raw video data stored on the server. Specifically, multiple video inputs are aggregated to the server via the network.

[0452] Step 2:

[0453] The server preprocesses the received video data for analysis. The input is the unprocessed video data, which is the output of step 1, and the output is the video data converted into an analyzable format. Specifically, it removes noise and adjusts the frame resolution as needed.

[0454] Step 3:

[0455] The server performs behavioral analysis using a machine learning model based on pre-processed video data. The input is the video data prepared in step 2, and the output is the analysis results of the behavior and movements of the educators and children. In terms of movement, a behavior recognition algorithm analyzes the movements and performs a process to look for specific patterns or anomalies.

[0456] Step 4:

[0457] The server detects the presence or absence of anomalies based on the results obtained from the behavioral analysis. The input is the analysis results from step 3, and the output is information about the detected anomalies. The server identifies the anomalies by comparing them with pre-programmed criteria, for example, confirming that a child has approached a dangerous area.

[0458] Step 5:

[0459] The server generates an alert based on the detected anomaly and notifies the mobile device used by the educator. The input is the anomaly information from step 4, and the output is the alert message sent to the mobile device. Specifically, the generated alert is delivered as a push notification to the device, and visual and auditory alerts are issued.

[0460] Step 6:

[0461] The user, an educator, receives alerts from the terminal. The input is the alert message from the server, and the output is the educator's appropriate response. This operation allows educators to check the terminal alerts and quickly assess the situation on-site and take action.

[0462] Step 7:

[0463] The server accumulates behavioral data received on a daily basis and generates a profile for each child. The input is the behavioral data obtained in steps 3 and 4, and the output is the information saved as a profile. Specifically, each child's behavioral history is recorded in the database, and their performance and trends are reflected in the profile through analysis.

[0464] (Application Example 1)

[0465] Next, we will explain Application Example 1. In the following explanation, 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."

[0466] In modern brick-and-mortar stores, accurately understanding customer behavior and providing efficient staffing and personalized service are essential. However, traditional methods fail to provide sufficient information for improving customer satisfaction and efficient operations, posing challenges to store management. In particular, responding quickly during peak hours is difficult, which can lead to a loss of customer experience.

[0467] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0468] In this invention, the server includes means for receiving video information acquired from a camera, means for recognizing the movements of staff and the behavior of customers and detecting anomalies using an artificial intelligence model for analyzing the video information, and means for generating warnings based on the detected anomalies and notifying a mobile information terminal. This enables real-time monitoring of customer behavior in physical stores, facilitating prompt responses by staff and improving customer satisfaction.

[0469] A "filming device" is a device used to acquire video information from inside a physical store.

[0470] "Video information" refers to real-time image data showing the situation inside the store.

[0471] An "artificial intelligence model" is a collection of machine learning algorithms used to analyze video information.

[0472] "Staff movements" refers to the actions of staff members performing their duties within the store.

[0473] "Customer behavior" refers to the actions and movements of consumers when they visit a physical store.

[0474] "Anomaly" refers to an unexpected situation in normal business operations or customer service.

[0475] A "warning" is information generated to alert someone when an anomaly is detected.

[0476] A "portable information terminal" is an electronic device that an employee can carry and that can receive information.

[0477] "Behavioral data" refers to data obtained from the daily activities of customers and employees.

[0478] A "profile" is a collection of information related to an individual, generated based on accumulated behavioral data.

[0479] The system implementing this invention is designed to monitor customer behavior and employee activities within physical stores and optimize store operations. A server receives video information in real time from cameras installed within the store. The received video information is analyzed using an artificial intelligence model. This model utilizes a machine learning platform such as TensorFlow. Through this analysis, customer movements and employee actions are recognized, and unusual behavior or congestion is detected.

[0480] Furthermore, the server immediately generates an alert based on detected anomalies. This alert is visually and audibly communicated to the employee's mobile device, which includes smart glasses and tablet devices. Data is accumulated as daily behavior, generating individual customer profiles. This profile information contributes to improving personalized service at the store.

[0481] As a concrete example, suppose a physical store becomes crowded on a weekend, and the server analyzes customer traffic patterns and detects congestion near the cash registers. The server then immediately generates a warning prompting staffing changes, which is sent to employees' mobile devices. Employees can receive this warning and respond quickly, thereby improving the customer experience.

[0482] An example of a prompt message is: "Create a program to analyze customer flow and optimize staff allocation during store congestion. Use cameras and smart glasses to perform real-time video analysis and provide warning notifications."

[0483] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0484] Step 1:

[0485] The server receives video information in real time from cameras installed within the store. It takes continuous video data from the cameras as input and sends this video data as output to subsequent analysis processes.

[0486] Step 2:

[0487] The server inputs the received video information into an artificial intelligence model to analyze the behavior of staff and customers. Specifically, it uses an AI model (e.g., a YOLO model using TensorFlow) to recognize people and movements within the video data. This analysis detects unusual behavior or movements, as well as congestion in specific areas.

[0488] Step 3:

[0489] The server detects anomalies based on the analysis results and generates warning messages as needed. The generated warnings include specific messages indicating congestion and are output.

[0490] Step 4:

[0491] The terminal receives generated alerts and displays visual and auditory notifications to staff. It receives alert messages from the server as input and displays alerts on devices worn by staff (smart glasses or tablets) as output.

[0492] Step 5:

[0493] The employee, acting as the user, takes immediate action based on the received notification. Specifically, this might involve going to a crowded checkout counter to provide additional assistance or selecting an appropriate response to improve customer service. This stage requires quick decision-making and action from the employee.

[0494] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0495] This invention provides a system that combines an emotion engine to improve safety and the quality of education in early childhood education facilities. This system operates by receiving video information transmitted in real time from a camera installed in the facility and analyzing the movements and facial expressions of educators and children.

[0496] The server analyzes the received video information using an artificial intelligence model. Specifically, it recognizes not only the movements of educators and the behavior of children, but also their emotional states from their facial expressions and gestures. For example, if a child looks like they are about to cry or an educator appears anxious, the emotion engine identifies that state and generates an analysis result.

[0497] If the server detects anomalies or necessary feedback from the analysis results, it generates warning messages and emotional feedback and immediately sends them to the educator's terminal. The terminal displays these notifications visually and audibly, enabling educators to respond quickly to the emotional state of the child in question or their own.

[0498] Furthermore, the server uses continuously accumulated behavioral and emotional data to generate individual child profiles, analyzing aptitudes, behavioral patterns, and emotional tendencies. These analysis results are provided as reports to administrators and parents, which can be used to develop educational programs tailored to individual needs.

[0499] Furthermore, this system will be an important means of enabling educational institutions to allocate resources efficiently, helping educators build better relationships with children, and enhancing safety and emotional care.

[0500] The following describes the processing flow.

[0501] Step 1:

[0502] The server receives video information transmitted from the camera. The server quickly processes the data and prepares it to extract the information necessary for real-time analysis.

[0503] Step 2:

[0504] The server uses an artificial intelligence model to analyze video information and recognize the movements of educators and children. Furthermore, it utilizes an emotion engine to determine emotional states from facial expressions and gestures. For example, it can recognize whether a child is smiling or whether an educator appears tired.

[0505] Step 3:

[0506] The server detects inappropriate situations and areas for improvement based on the analysis of emotional states and behavior. For example, it can identify situations where a child is not getting attention for extended periods or where an educator is showing signs of stress.

[0507] Step 4:

[0508] Based on the detected results, the server generates warning messages and emotional feedback for educators. This includes recommendations for behavioral adjustments and improvement of emotional state.

[0509] Step 5:

[0510] The device receives messages sent from the server and notifies educators. The notifications are presented visually and audibly, prompting immediate action. For example, they might say, "Add an activity to capture the children's attention" or "Take a deep breath and relax."

[0511] Step 6:

[0512] The server continuously collects behavioral and emotional data from video footage. This data is used to generate individual child profiles.

[0513] Step 7:

[0514] The server uses accumulated data to generate and provide users with analytical reports that help optimize educational programs and provide individualized support. Users (educators and parents) use these reports to understand children's development and adjust educational plans.

[0515] (Example 2)

[0516] Next, we will describe Example 2. 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."

[0517] Early childhood education facilities require appropriate monitoring and feedback to improve the quality of education while ensuring the safety of children. However, traditional methods make it difficult for educators to immediately identify abnormalities in children's emotions or behavior and take appropriate action. Furthermore, there is a lack of detailed profile generation to provide educational support tailored to each individual child.

[0518] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0519] In this invention, the server includes means for receiving video information from optical equipment placed within the facility; means for analyzing the video information with a machine learning model to identify the actions of educators and the activities of children and to recognize their emotional states; means for generating warnings and feedback based on the identified abnormal or significant emotional states and notifying educators via portable devices; and means for recording behavioral and emotional data and profiling information related to individual children. This enables educators to immediately grasp the state of children and improve safety and the quality of education while providing optimal educational programs.

[0520] "Optical equipment" refers to devices used to acquire image information, including cameras and sensors.

[0521] "Visual information" refers to visual data acquired from optical equipment, including information such as the actions and facial expressions of children and educational staff.

[0522] A "machine learning model" is a collection of algorithms used to analyze patterns and features in data and perform predictions and recognition, and it constitutes a part of artificial intelligence.

[0523] "Movement" refers to the physical movements and actions performed by educational staff and children, and specifically includes walking, gestures, and other similar actions.

[0524] "Activities" refer to the actions, play, and learning activities that children engage in within the facility.

[0525] "Emotional state" refers to the psychological state of children and educators as inferred from their facial expressions and gestures, and includes emotions such as joy, sadness, and anxiety.

[0526] "Abnormal" refers to behaviors or emotional states that deviate from normal patterns, and indicates situations that require special attention or intervention.

[0527] A "warning" is a message containing information to notify educational staff of detected anomalies or risks and to encourage attention and intervention.

[0528] "Feedback" refers to specific instructions and suggestions generated based on the analysis results, including information on how educational staff should respond to students.

[0529] "Portable devices" refer to communication devices used personally by educational staff, including smartphones and tablets.

[0530] "Behavioral data" refers to recorded information about children's daily actions and activities.

[0531] "Emotional data" refers to recorded information about a child's emotional state.

[0532] "Profiling" refers to the process of organizing the characteristics and tendencies of individual children based on recorded behavioral and emotional data, and compiling them into a single, comprehensive set of information.

[0533] This invention aims to improve the safety of children and the quality of education in early childhood education facilities. Specifically, it provides a system that utilizes video information acquired from optical equipment (such as cameras) placed within the facility to analyze the actions and emotional states of educators and children.

[0534] The server acquires video information in real time from optical equipment installed within the facility. This video information is analyzed using a machine learning model. The machine learning model used utilizes, for example, TensorFlow and OpenCV to analyze movements and facial expressions and identify the emotional state of children and educational staff. Through this analysis, the server can detect abnormal behavior and emotional anomalies.

[0535] Based on identified anomalies or significant emotional states, the server generates warnings and feedback and notifies educators via handheld devices. These notifications are presented to educators visually and audibly, enabling immediate and appropriate responses. For example, if a child appears to be on the verge of tears, the server might notify the handheld device with specific instructions such as, "The child looks like they are about to cry. Please comfort them."

[0536] Furthermore, the server uses accumulated behavioral and emotional data to generate profiles for each child. These profiles summarize aptitudes, behavioral patterns, and emotional tendencies, and are used as reports for administrators and parents. This makes it possible to provide an optimal educational program for each individual child.

[0537] An example of a prompt would be: "Create a program that analyzes the movements and facial expressions of children and educators from video footage, particularly detecting feelings of anxiety and sadness. Then, generate and deliver notifications based on the identified emotions in real time to the device." Using such prompts, the generating AI model will operate efficiently, achieving improved safety and quality of education in educational settings.

[0538] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0539] Step 1:

[0540] The server receives video information from optical equipment installed within the facility. A high-resolution video stream is supplied as input. To process this stream data quickly, the server temporarily stores it in storage.

[0541] Step 2:

[0542] The server analyzes the received video information using a machine learning model. This process first detects faces in the video using OpenCV, and then estimates the emotion associated with each face using a TensorFlow model. Preprocessed image data is provided as input, and the output returns labels for the identified actions and emotions. This process reveals the actions of educators and the emotional states of children.

[0543] Step 3:

[0544] The server identifies anomalies and important emotional states based on the analysis results. For example, if a child is in an emotional state of being about to cry, the server labels it as an "anomaly." The input is data of emotional labels, and the output is a flag indicating whether or not an anomaly exists. At this stage, the server's specific action is to generate conditional warnings.

[0545] Step 4:

[0546] The server generates feedback to send a notification to the educational staff's mobile device if an anomaly is detected. The input here is an anomaly flag, and the output is a notification message containing specific instructions. The server then sends this message to the device in real time.

[0547] Step 5:

[0548] The terminal presents notifications received from the server to educational staff visually and audibly. The input is the notification message, and the output is an alert displayed on the screen or an audible alert. Specifically, the terminal uses an appropriate UI (user interface) to make the notifications stand out.

[0549] Step 6:

[0550] The server continuously records behavioral and emotional data to generate individual child profiles. Using the accumulated dataset as input, it generates detailed profile information for each child as output. This process includes operations that analyze long-term aptitudes and behavioral patterns.

[0551] (Application Example 2)

[0552] Next, we will explain application example 2. In the following explanation, 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."

[0553] In the work environment, it is necessary to appropriately monitor workers' stress levels and emotional states to create a safe and efficient work environment. However, conventional systems have difficulty grasping workers' emotional states in real time, which hinders the rapid provision of appropriate feedback and improvement suggestions.

[0554] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0555] In this invention, the server includes means for receiving image information acquired from imaging equipment installed in the work environment, means for recognizing the worker's movements and facial expressions and determining their emotional state using an artificial intelligence model for analyzing the image information, and means for generating improvement suggestions based on the determined emotional state and notifying the administrator's mobile information terminal. This makes it possible to grasp the worker's emotional state in real time and to quickly provide appropriate feedback and improvement suggestions.

[0556] "Recording equipment" refers to devices installed in a work environment to acquire video information.

[0557] "Image information" refers to visual data acquired by photographic equipment, and serves as the basis for analyzing the movements and facial expressions of workers.

[0558] An "artificial intelligence model" is a program used to analyze digital information, and it is a system that uses machine learning techniques to recognize the emotional state of a worker from their actions and facial expressions.

[0559] "Worker's movements and facial expressions" refer to the physical movements and facial expressions of a person in the work environment, and are a source of information for judging their emotional state.

[0560] "Emotional state" refers to the internal psychological state of a worker, including psychological conditions such as stress, anxiety, and satisfaction.

[0561] An "improvement suggestion" is a proposal for specific actions to be taken to improve the work environment or working conditions based on one's emotional state.

[0562] A "personal information terminal for administrators" is a device used by those who manage the work environment, and it is capable of receiving and notifying information in real time.

[0563] A "profile" is a dataset that compiles behavioral data and trends related to individual workers, and is useful for improving the work environment in the future.

[0564] The system that realizes this invention aims to provide a comfortable and safe working environment by monitoring the emotional state of workers in a factory in real time. The system utilizes image processing technology and artificial intelligence technology and operates in the following steps.

[0565] The server is the central hub of the system that continuously receives and processes video information from the cameras installed within the factory. A commonly used video camera is used as the camera, acquiring the video as digital data.

[0566] The received image information is analyzed by an artificial intelligence model installed on the server. This AI model is built using deep learning frameworks such as TensorFlow and PyTorch, and recognizes the emotional state from the worker's movements and facial expressions. For example, if the worker's facial expression indicates stress, it identifies the situation and generates analysis results through appropriate data calculations.

[0567] The analysis results are notified to a mobile device used by the administrator. This device is expected to be a smartphone or tablet. This notification is provided visually and audibly, allowing the administrator to understand the worker's status in real time and immediately identify any necessary improvement suggestions.

[0568] For example, if a worker's facial expression indicates severe fatigue, a specific improvement suggestion such as "Please allow this worker to take a break at an appropriate time" will be displayed on the terminal. Furthermore, daily activity data is stored on a cloud server, and individual worker profiles are generated based on this stored data. This provides information that contributes to long-term improvements to the work environment.

[0569] An example of a prompt to be input to the generating AI model would be an instruction such as, "Analyze the camera footage and evaluate the worker's stress level." Based on this prompt, the AI ​​performs the optimal analysis and provides the necessary feedback.

[0570] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0571] Step 1:

[0572] The server receives video information from imaging equipment installed within the factory. This video information is real-time visual data captured by the cameras. This data is then imported digitally and converted into a format suitable for analysis. Here, the input is raw data from the imaging equipment, and the output is digital image data that can be processed by the AI ​​model.

[0573] Step 2:

[0574] The server processes the received image information using an artificial intelligence model. Specifically, it uses deep learning frameworks such as TensorFlow and PyTorch to recognize the worker's movements and facial expressions. It receives digital image data converted from raw data as input and generates analysis results indicating the worker's emotional state as output. In this step, the AI ​​analyzes the data based on the prompt message in the generated AI model: "Analyze the camera footage and evaluate the worker's stress level."

[0575] Step 3:

[0576] The server sends the generated analysis results to the administrator's terminal. The terminal receives these results and displays improvement suggestions derived from the analysis in a visual and auditory way. The input is the AI ​​analysis results, and the output is an appropriate feedback message for the administrator. In this case, a suggestion such as "Please give this worker a break immediately" might be displayed on the screen.

[0577] Step 4:

[0578] The server accumulates daily operational data and creates profiles for each worker. The input is a history of past analysis results, and the output is profile data indicating each worker's aptitude and behavioral tendencies. These profiles are stored in the cloud and serve as an information resource useful for future improvements to the work environment.

[0579] Step 5:

[0580] The user (administrator) efficiently manages worker assignments and breaks based on improvement suggestions received from terminals. Input is notification information from terminals, and output is optimized resource allocation based on the workers' emotional states. A concrete example is setting additional break times for specific workers.

[0581] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0582] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0583] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0584] [Fourth Embodiment]

[0585] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0586] As shown in Figure 7, the 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.

[0587] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0588] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0589] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0590] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0591] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0592] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive 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 robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0593] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0594] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0595] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0596] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0597] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0598] This invention is a system that utilizes AI technology in early childhood education facilities to reduce the burden on educators and enhance the safety management of young children. The system operates by acquiring real-time video information of the facility's environment through a camera installed in the facility and transmitting it to a server.

[0599] When the server receives video information, it analyzes the data using an artificial intelligence model. Specifically, it recognizes the movements of educators and the behavior of children, and detects abnormal behavior or dangerous situations. For example, if it detects that a child is approaching dangerous play equipment or that an educator is moving around excessively, it generates a warning.

[0600] This warning is notified in real time on devices carried by educators, and is presented visually and audibly. The device enables a quick and appropriate response, supporting educators in resolving the issue immediately.

[0601] Furthermore, the server accumulates daily behavioral data within the facility and generates profiles for each child. This allows for the analysis of each child's aptitudes and behavioral patterns, and provides these findings as reports to educators and parents. This profile information can be used to gain a deeper understanding of each child's development and to provide appropriate education.

[0602] This system can not only improve the quality of education but also enhance transparency within the school and serve as an important means of gaining the trust of parents.

[0603] The following describes the processing flow.

[0604] Step 1:

[0605] The server receives video information transmitted from the camera. The server quickly reads this data and prepares to convert it into a format suitable for analysis.

[0606] Step 2:

[0607] The server analyzes video information using an artificial intelligence model. The AI ​​model identifies the movements of educators and the behavior of young children, detecting abnormal or dangerous situations. For example, it can determine if a child has entered a dangerous area or if an educator has deviated from their established routine.

[0608] Step 3:

[0609] The server generates a warning message based on the detected anomalies and risks. The generated warning requires immediate action and includes detailed information about the anomaly.

[0610] Step 4:

[0611] The server sends a warning message to the educator's mobile device. The device receives this message and displays it as a visual and auditory notification, allowing the educator to respond quickly on the spot.

[0612] Step 5:

[0613] The server continuously accumulates daily behavioral data. This includes the behavioral history of individual infants and related important indicators.

[0614] Step 6:

[0615] The server analyzes accumulated behavioral data and generates a profile for each child. This profile shows the child's aptitudes and behavioral patterns, which can be used to inform educational guidance.

[0616] Step 7:

[0617] Users can access the generated profiles and reports. Based on this information, parents and educational administrators can gain a deeper understanding of each child's characteristics and consider more appropriate educational and support measures.

[0618] (Example 1)

[0619] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0620] In early childhood education facilities, there is a need to efficiently manage the safety of young children while reducing the burden on educators. Traditional methods require educators to constantly keep an eye on the children, which is labor-intensive. Furthermore, it can be difficult to respond quickly because it may delay the prevention of dangerous situations.

[0621] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0622] In this invention, the server includes processing means for receiving video data obtained from a video recording device, analysis means for recognizing personnel movements and children's behavior and detecting anomalies using a machine learning model to analyze the video data, and warning generation and notification means for generating warnings based on the detection results and notifying mobile terminals for educators. This makes it possible to efficiently manage the safety of children without educators having to constantly monitor them.

[0623] A "video recording device" is a device that acquires visual information through shooting or recording and outputs it as digital data.

[0624] "Video data" refers to digital data acquired by a video recording device to represent visual information.

[0625] A "machine learning model" is an algorithm trained to perform a specific task and is used for pattern recognition and prediction.

[0626] "Personnel actions and children's behavior" refers to the physical movements and actions exhibited by educators and children in educational facilities.

[0627] An "abnormality" refers to any action or behavior that falls outside the normal range, or an event or situation that deviates from predefined safety standards.

[0628] "Warning generation and notification means" refers to a method that includes technology for creating a corresponding warning when an anomaly is detected and for notifying the recipient of that warning.

[0629] A "portable device" is an electronic device that is easy to carry and can connect to and receive information via wireless communication.

[0630] "Behavioral data" refers to data that records, classifies, and stores the behavior of children and educators over a specific period.

[0631] A "profile" is a collection of information constructed based on an individual child's past behavioral data and characteristics, and is useful for individual analysis and understanding.

[0632] This system is designed to efficiently and safely manage children in early childhood education facilities. The server receives video data from video recording devices installed in the facility and utilizes machine learning models to analyze this data. The machine learning models used here are implemented using frameworks such as TensorFlow and PyTorch.

[0633] The server uses a computer system with a high-performance processor and ample memory. This enables the processing of video data transmitted in real time from numerous cameras. The server also analyzes the movements and behaviors of educators and children in the video data to detect anomalies. If an anomaly is detected, it generates an alert and notifies the educators' mobile devices. These mobile devices receive visual and auditory notifications, prompting educators to take prompt action.

[0634] Educators, as users of the system, can easily respond when they receive warnings from the device. Situations where educators might respond include, for example, when a child approaches dangerous playground equipment. This system can also accumulate daily behavioral data and generate individual profiles for each child. These profiles can analyze the child's aptitudes and behavioral characteristics and provide reports to parents and educators.

[0635] As a concrete example, here is an example of a prompt: "Develop a program that recognizes when a toddler approaches a slide in a playground and issues an alert." By training an AI model based on this prompt, the system can efficiently detect specific abnormal behaviors and issue warnings.

[0636] This invention serves as a means to improve the quality of education by reducing the burden on educators and strengthening the safety management of young children.

[0637] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0638] Step 1:

[0639] The server receives video data in real time from multiple video recording devices installed within the facility. The input for this step is the video stream from each camera, and the output is the raw video data stored on the server. Specifically, multiple video inputs are aggregated to the server via the network.

[0640] Step 2:

[0641] The server preprocesses the received video data for analysis. The input is the unprocessed video data, which is the output of step 1, and the output is the video data converted into an analyzable format. Specifically, it removes noise and adjusts the frame resolution as needed.

[0642] Step 3:

[0643] The server performs behavioral analysis using a machine learning model based on pre-processed video data. The input is the video data prepared in step 2, and the output is the analysis results of the behavior and movements of the educators and children. In terms of movement, a behavior recognition algorithm analyzes the movements and performs a process to look for specific patterns or anomalies.

[0644] Step 4:

[0645] The server detects the presence or absence of anomalies based on the results obtained from the behavioral analysis. The input is the analysis results from step 3, and the output is information about the detected anomalies. The server identifies the anomalies by comparing them with pre-programmed criteria, for example, confirming that a child has approached a dangerous area.

[0646] Step 5:

[0647] The server generates an alert based on the detected anomaly and notifies the mobile device used by the educator. The input is the anomaly information from step 4, and the output is the alert message sent to the mobile device. Specifically, the generated alert is delivered as a push notification to the device, and visual and auditory alerts are issued.

[0648] Step 6:

[0649] The user, an educator, receives alerts from the terminal. The input is the alert message from the server, and the output is the educator's appropriate response. This operation allows educators to check the terminal alerts and quickly assess the situation on-site and take action.

[0650] Step 7:

[0651] The server accumulates behavioral data received on a daily basis and generates a profile for each child. The input is the behavioral data obtained in steps 3 and 4, and the output is the information saved as a profile. Specifically, each child's behavioral history is recorded in the database, and their performance and trends are reflected in the profile through analysis.

[0652] (Application Example 1)

[0653] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0654] In modern brick-and-mortar stores, accurately understanding customer behavior and providing efficient staffing and personalized service are essential. However, traditional methods fail to provide sufficient information for improving customer satisfaction and efficient operations, posing challenges to store management. In particular, responding quickly during peak hours is difficult, which can lead to a loss of customer experience.

[0655] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0656] In this invention, the server includes means for receiving video information acquired from a camera, means for recognizing the movements of staff and the behavior of customers and detecting anomalies using an artificial intelligence model for analyzing the video information, and means for generating warnings based on the detected anomalies and notifying a mobile information terminal. This enables real-time monitoring of customer behavior in physical stores, facilitating prompt responses by staff and improving customer satisfaction.

[0657] A "filming device" is a device used to acquire video information from inside a physical store.

[0658] "Video information" refers to real-time image data showing the situation inside the store.

[0659] An "artificial intelligence model" is a collection of machine learning algorithms used to analyze video information.

[0660] "Staff movements" refers to the actions of staff members performing their duties within the store.

[0661] "Customer behavior" refers to the actions and movements of consumers when they visit a physical store.

[0662] "Anomaly" refers to an unexpected situation in normal business operations or customer service.

[0663] A "warning" is information generated to alert someone when an anomaly is detected.

[0664] A "portable information terminal" is an electronic device that an employee can carry and that can receive information.

[0665] "Behavioral data" refers to data obtained from the daily activities of customers and employees.

[0666] A "profile" is a collection of information related to an individual, generated based on accumulated behavioral data.

[0667] The system implementing this invention is designed to monitor customer behavior and employee activities within physical stores and optimize store operations. A server receives video information in real time from cameras installed within the store. The received video information is analyzed using an artificial intelligence model. This model utilizes a machine learning platform such as TensorFlow. Through this analysis, customer movements and employee actions are recognized, and unusual behavior or congestion is detected.

[0668] Furthermore, the server immediately generates an alert based on detected anomalies. This alert is visually and audibly communicated to the employee's mobile device, which includes smart glasses and tablet devices. Data is accumulated as daily behavior, generating individual customer profiles. This profile information contributes to improving personalized service at the store.

[0669] As a concrete example, suppose a physical store becomes crowded on a weekend, and the server analyzes customer traffic patterns and detects congestion near the cash registers. The server then immediately generates a warning prompting staffing changes, which is sent to employees' mobile devices. Employees can receive this warning and respond quickly, thereby improving the customer experience.

[0670] An example of a prompt message is: "Create a program to analyze customer flow and optimize staff allocation during store congestion. Use cameras and smart glasses to perform real-time video analysis and provide warning notifications."

[0671] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0672] Step 1:

[0673] The server receives video information in real time from cameras installed within the store. It takes continuous video data from the cameras as input and sends this video data as output to subsequent analysis processes.

[0674] Step 2:

[0675] The server inputs the received video information into an artificial intelligence model to analyze the behavior of staff and customers. Specifically, it uses an AI model (e.g., a YOLO model using TensorFlow) to recognize people and movements within the video data. This analysis detects unusual behavior or movements, as well as congestion in specific areas.

[0676] Step 3:

[0677] The server detects anomalies based on the analysis results and generates warning messages as needed. The generated warnings include specific messages indicating congestion and are output.

[0678] Step 4:

[0679] The terminal receives generated alerts and displays visual and auditory notifications to staff. It receives alert messages from the server as input and displays alerts on devices worn by staff (smart glasses or tablets) as output.

[0680] Step 5:

[0681] The employee, acting as the user, takes immediate action based on the received notification. Specifically, this might involve going to a crowded checkout counter to provide additional assistance or selecting an appropriate response to improve customer service. This stage requires quick decision-making and action from the employee.

[0682] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0683] This invention provides a system that combines an emotion engine to improve safety and the quality of education in early childhood education facilities. This system operates by receiving video information transmitted in real time from a camera installed in the facility and analyzing the movements and facial expressions of educators and children.

[0684] The server analyzes the received video information using an artificial intelligence model. Specifically, it recognizes not only the movements of educators and the behavior of children, but also their emotional states from their facial expressions and gestures. For example, if a child looks like they are about to cry or an educator appears anxious, the emotion engine identifies that state and generates an analysis result.

[0685] If the server detects anomalies or necessary feedback from the analysis results, it generates warning messages and emotional feedback and immediately sends them to the educator's terminal. The terminal displays these notifications visually and audibly, enabling educators to respond quickly to the emotional state of the child in question or their own.

[0686] Furthermore, the server uses continuously accumulated behavioral and emotional data to generate individual child profiles, analyzing aptitudes, behavioral patterns, and emotional tendencies. These analysis results are provided as reports to administrators and parents, which can be used to develop educational programs tailored to individual needs.

[0687] Furthermore, this system will be an important means of enabling educational institutions to allocate resources efficiently, helping educators build better relationships with children, and enhancing safety and emotional care.

[0688] The following describes the processing flow.

[0689] Step 1:

[0690] The server receives video information transmitted from the camera. The server quickly processes the data and prepares it to extract the information necessary for real-time analysis.

[0691] Step 2:

[0692] The server uses an artificial intelligence model to analyze video information and recognize the movements of educators and children. Furthermore, it utilizes an emotion engine to determine emotional states from facial expressions and gestures. For example, it can recognize whether a child is smiling or whether an educator appears tired.

[0693] Step 3:

[0694] The server detects inappropriate situations and areas for improvement based on the analysis of emotional states and behavior. For example, it can identify situations where a child is not getting attention for extended periods or where an educator is showing signs of stress.

[0695] Step 4:

[0696] Based on the detected results, the server generates warning messages and emotional feedback for educators. This includes recommendations for behavioral adjustments and improvement of emotional state.

[0697] Step 5:

[0698] The device receives messages sent from the server and notifies educators. The notifications are presented visually and audibly, prompting immediate action. For example, they might say, "Add an activity to capture the children's attention" or "Take a deep breath and relax."

[0699] Step 6:

[0700] The server continuously collects behavioral and emotional data from video footage. This data is used to generate individual child profiles.

[0701] Step 7:

[0702] The server uses accumulated data to generate and provide users with analytical reports that help optimize educational programs and provide individualized support. Users (educators and parents) use these reports to understand children's development and adjust educational plans.

[0703] (Example 2)

[0704] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0705] Early childhood education facilities require appropriate monitoring and feedback to improve the quality of education while ensuring the safety of children. However, traditional methods make it difficult for educators to immediately identify abnormalities in children's emotions or behavior and take appropriate action. Furthermore, there is a lack of detailed profile generation to provide educational support tailored to each individual child.

[0706] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0707] In this invention, the server includes means for receiving video information from optical equipment placed within the facility; means for analyzing the video information with a machine learning model to identify the actions of educators and the activities of children and to recognize their emotional states; means for generating warnings and feedback based on the identified abnormal or significant emotional states and notifying educators via portable devices; and means for recording behavioral and emotional data and profiling information related to individual children. This enables educators to immediately grasp the state of children and improve safety and the quality of education while providing optimal educational programs.

[0708] "Optical equipment" refers to devices used to acquire image information, including cameras and sensors.

[0709] "Visual information" refers to visual data acquired from optical equipment, including information such as the actions and facial expressions of children and educational staff.

[0710] A "machine learning model" is a collection of algorithms used to analyze patterns and features in data and perform predictions and recognition, and it constitutes a part of artificial intelligence.

[0711] "Movement" refers to the physical movements and actions performed by educational staff and children, and specifically includes walking, gestures, and other similar actions.

[0712] "Activities" refer to the actions, play, and learning activities that children engage in within the facility.

[0713] "Emotional state" refers to the psychological state of children and educators as inferred from their facial expressions and gestures, and includes emotions such as joy, sadness, and anxiety.

[0714] "Abnormal" refers to behaviors or emotional states that deviate from normal patterns, and indicates situations that require special attention or intervention.

[0715] A "warning" is a message containing information to notify educational staff of detected anomalies or risks and to encourage attention and intervention.

[0716] "Feedback" refers to specific instructions and suggestions generated based on the analysis results, including information on how educational staff should respond to students.

[0717] "Portable devices" refer to communication devices used personally by educational staff, including smartphones and tablets.

[0718] "Behavioral data" refers to recorded information about children's daily actions and activities.

[0719] "Emotional data" refers to recorded information about a child's emotional state.

[0720] "Profiling" refers to the process of organizing the characteristics and tendencies of individual children based on recorded behavioral and emotional data, and compiling them into a single, comprehensive set of information.

[0721] This invention aims to improve the safety of children and the quality of education in early childhood education facilities. Specifically, it provides a system that utilizes video information acquired from optical equipment (such as cameras) placed within the facility to analyze the actions and emotional states of educators and children.

[0722] The server acquires video information in real time from optical equipment installed within the facility. This video information is analyzed using a machine learning model. The machine learning model used utilizes, for example, TensorFlow and OpenCV to analyze movements and facial expressions and identify the emotional state of children and educational staff. Through this analysis, the server can detect abnormal behavior and emotional anomalies.

[0723] Based on identified anomalies or significant emotional states, the server generates warnings and feedback and notifies educators via handheld devices. These notifications are presented to educators visually and audibly, enabling immediate and appropriate responses. For example, if a child appears to be on the verge of tears, the server might notify the handheld device with specific instructions such as, "The child looks like they are about to cry. Please comfort them."

[0724] Furthermore, the server uses accumulated behavioral and emotional data to generate profiles for each child. These profiles summarize aptitudes, behavioral patterns, and emotional tendencies, and are used as reports for administrators and parents. This makes it possible to provide an optimal educational program for each individual child.

[0725] An example of a prompt would be: "Create a program that analyzes the movements and facial expressions of children and educators from video footage, particularly detecting feelings of anxiety and sadness. Then, generate and deliver notifications based on the identified emotions in real time to the device." Using such prompts, the generating AI model will operate efficiently, achieving improved safety and quality of education in educational settings.

[0726] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0727] Step 1:

[0728] The server receives video information from optical equipment installed within the facility. A high-resolution video stream is supplied as input. To process this stream data quickly, the server temporarily stores it in storage.

[0729] Step 2:

[0730] The server analyzes the received video information using a machine learning model. This process first detects faces in the video using OpenCV, and then estimates the emotion associated with each face using a TensorFlow model. Preprocessed image data is provided as input, and the output returns labels for the identified actions and emotions. This process reveals the actions of educators and the emotional states of children.

[0731] Step 3:

[0732] The server identifies anomalies and important emotional states based on the analysis results. For example, if a child is in an emotional state of being about to cry, the server labels it as an "anomaly." The input is data of emotional labels, and the output is a flag indicating whether or not an anomaly exists. At this stage, the server's specific action is to generate conditional warnings.

[0733] Step 4:

[0734] The server generates feedback to send a notification to the educational staff's mobile device if an anomaly is detected. The input here is an anomaly flag, and the output is a notification message containing specific instructions. The server then sends this message to the device in real time.

[0735] Step 5:

[0736] The terminal presents notifications received from the server to educational staff visually and audibly. The input is the notification message, and the output is an alert displayed on the screen or an audible alert. Specifically, the terminal uses an appropriate UI (user interface) to make the notifications stand out.

[0737] Step 6:

[0738] The server continuously records behavioral and emotional data to generate individual child profiles. Using the accumulated dataset as input, it generates detailed profile information for each child as output. This process includes operations that analyze long-term aptitudes and behavioral patterns.

[0739] (Application Example 2)

[0740] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0741] In the work environment, it is necessary to appropriately monitor workers' stress levels and emotional states to create a safe and efficient work environment. However, conventional systems have difficulty grasping workers' emotional states in real time, which hinders the rapid provision of appropriate feedback and improvement suggestions.

[0742] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0743] In this invention, the server includes means for receiving image information acquired from imaging equipment installed in the work environment, means for recognizing the worker's movements and facial expressions and determining their emotional state using an artificial intelligence model for analyzing the image information, and means for generating improvement suggestions based on the determined emotional state and notifying the administrator's mobile information terminal. This makes it possible to grasp the worker's emotional state in real time and to quickly provide appropriate feedback and improvement suggestions.

[0744] "Recording equipment" refers to devices installed in a work environment to acquire video information.

[0745] "Image information" refers to visual data acquired by photographic equipment, and serves as the basis for analyzing the movements and facial expressions of workers.

[0746] An "artificial intelligence model" is a program used to analyze digital information, and it is a system that uses machine learning techniques to recognize the emotional state of a worker from their actions and facial expressions.

[0747] "Worker's movements and facial expressions" refer to the physical movements and facial expressions of a person in the work environment, and are a source of information for judging their emotional state.

[0748] "Emotional state" refers to the internal psychological state of a worker, including psychological conditions such as stress, anxiety, and satisfaction.

[0749] An "improvement suggestion" is a proposal for specific actions to be taken to improve the work environment or working conditions based on one's emotional state.

[0750] A "personal information terminal for administrators" is a device used by those who manage the work environment, and it is capable of receiving and notifying information in real time.

[0751] A "profile" is a dataset that compiles behavioral data and trends related to individual workers, and is useful for improving the work environment in the future.

[0752] The system that realizes this invention aims to provide a comfortable and safe working environment by monitoring the emotional state of workers in a factory in real time. The system utilizes image processing technology and artificial intelligence technology and operates in the following steps.

[0753] The server is the central hub of the system that continuously receives and processes video information from the cameras installed within the factory. A commonly used video camera is used as the camera, acquiring the video as digital data.

[0754] The received image information is analyzed by an artificial intelligence model installed on the server. This AI model is built using deep learning frameworks such as TensorFlow and PyTorch, and recognizes the emotional state from the worker's movements and facial expressions. For example, if the worker's facial expression indicates stress, it identifies the situation and generates analysis results through appropriate data calculations.

[0755] The analysis results are notified to a mobile device used by the administrator. This device is expected to be a smartphone or tablet. This notification is provided visually and audibly, allowing the administrator to understand the worker's status in real time and immediately identify any necessary improvement suggestions.

[0756] For example, if a worker's facial expression indicates severe fatigue, a specific improvement suggestion such as "Please allow this worker to take a break at an appropriate time" will be displayed on the terminal. Furthermore, daily activity data is stored on a cloud server, and individual worker profiles are generated based on this stored data. This provides information that contributes to long-term improvements to the work environment.

[0757] An example of a prompt to be input to the generating AI model would be an instruction such as, "Analyze the camera footage and evaluate the worker's stress level." Based on this prompt, the AI ​​performs the optimal analysis and provides the necessary feedback.

[0758] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0759] Step 1:

[0760] The server receives video information from imaging equipment installed within the factory. This video information is real-time visual data captured by the cameras. This data is then imported digitally and converted into a format suitable for analysis. Here, the input is raw data from the imaging equipment, and the output is digital image data that can be processed by the AI ​​model.

[0761] Step 2:

[0762] The server processes the received image information using an artificial intelligence model. Specifically, it uses deep learning frameworks such as TensorFlow and PyTorch to recognize the worker's movements and facial expressions. It receives digital image data converted from raw data as input and generates analysis results indicating the worker's emotional state as output. In this step, the AI ​​analyzes the data based on the prompt message in the generated AI model: "Analyze the camera footage and evaluate the worker's stress level."

[0763] Step 3:

[0764] The server sends the generated analysis results to the administrator's terminal. The terminal receives these results and displays improvement suggestions derived from the analysis in a visual and auditory way. The input is the AI ​​analysis results, and the output is an appropriate feedback message for the administrator. In this case, a suggestion such as "Please give this worker a break immediately" might be displayed on the screen.

[0765] Step 4:

[0766] The server accumulates daily operational data and creates profiles for each worker. The input is a history of past analysis results, and the output is profile data indicating each worker's aptitude and behavioral tendencies. These profiles are stored in the cloud and serve as an information resource useful for future improvements to the work environment.

[0767] Step 5:

[0768] The user (administrator) efficiently manages worker assignments and breaks based on improvement suggestions received from terminals. Input is notification information from terminals, and output is optimized resource allocation based on the workers' emotional states. A concrete example is setting additional break times for specific workers.

[0769] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0770] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0771] 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 this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0772] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0773] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0774] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0775] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0776] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0777] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0778] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0779] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0780] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0781] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0782] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0783] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0784] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0785] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0786] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0787] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0788] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0789] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0790] The following is further disclosed regarding the embodiments described above.

[0791] (Claim 1)

[0792] In an early childhood education facility, a means for receiving video information acquired from a camera installed within the facility,

[0793] A means for recognizing the movements of educators and the behavior of children and detecting anomalies using an artificial intelligence model for analyzing the aforementioned video information,

[0794] A means for generating a warning based on detected anomalies and notifying educators via their mobile devices,

[0795] A means of accumulating daily behavioral data and generating information related to individual children as profiles,

[0796] A system that includes this.

[0797] (Claim 2)

[0798] The system according to claim 1, further comprising means for analyzing the aptitudes and behavioral patterns of individual children and generating reports based on accumulated behavioral data.

[0799] (Claim 3)

[0800] The system according to claim 1, comprising means of using a portable information terminal for educators in which warnings based on detected anomalies are displayed as visual and auditory notifications.

[0801] "Example 1"

[0802] (Claim 1)

[0803] Processing means for receiving video data obtained from a video recording device,

[0804] An analysis means that uses a machine learning model to analyze the aforementioned video data, recognizes the movements of personnel and the behavior of children, and detects anomalies.

[0805] A warning generation and notification means that generates a warning based on the detection results and notifies a mobile device for educators,

[0806] An information generation means that accumulates daily behavioral data and generates information related to each child as a profile,

[0807] A system that includes this.

[0808] (Claim 2)

[0809] The system according to claim 1, further comprising analytical means for analyzing each child's aptitude and behavioral characteristics based on accumulated behavioral data and generating a report.

[0810] (Claim 3)

[0811] The system according to claim 1, comprising means of using a portable terminal for educators in which warnings based on detected anomalies are presented as visual and auditory notifications.

[0812] "Application Example 1"

[0813] (Claim 1)

[0814] A means for receiving video information acquired from a camera,

[0815] A means for recognizing the movements of staff and the behavior of customers and detecting anomalies using an artificial intelligence model for analyzing the aforementioned video information,

[0816] A means for generating a warning based on the detected anomaly and notifying a mobile device,

[0817] A means of accumulating daily behavioral data and generating information related to individual customers as profiles,

[0818] A system that includes this.

[0819] (Claim 2)

[0820] The system according to claim 1, further comprising means for analyzing the trends and behavioral patterns of individual customers based on accumulated behavioral data and generating a report.

[0821] (Claim 3)

[0822] The system according to claim 1, comprising means of using a portable information terminal that displays warnings based on detected anomalies as visual and auditory notifications.

[0823] "Example 2 of combining an emotion engine"

[0824] (Claim 1)

[0825] A means for receiving video information acquired from optical equipment placed within the park,

[0826] A machine learning model for analyzing the aforementioned video information is used to identify the actions of educational staff and the activities of children, and to recognize their emotional states.

[0827] A means for generating warnings or feedback based on identified abnormal or significant emotional states and notifying them to portable devices for educational staff,

[0828] A means of recording behavioral and emotional data and profiling information related to individual children,

[0829] A system that includes this.

[0830] (Claim 2)

[0831] The system according to claim 1, further comprising means for evaluating the aptitudes, activity patterns, and emotional tendencies of individual children based on profiled data, and generating a report.

[0832] (Claim 3)

[0833] The system according to claim 1, comprising means of using a portable device that outputs the generated warnings and feedback as visual and auditory notifications.

[0834] "Application example 2 when combining with an emotional engine"

[0835] (Claim 1)

[0836] A means for receiving image information acquired from a camera installed in the work environment,

[0837] A means for recognizing the worker's movements and facial expressions and determining their emotional state using an artificial intelligence model for analyzing the aforementioned image information,

[0838] A means for generating improvement suggestions based on the determined emotional state and notifying the administrator's mobile device,

[0839] A means for accumulating daily activity data and generating information related to individual workers as profiles,

[0840] A system that includes this.

[0841] (Claim 2)

[0842] The system according to claim 1, further comprising means for analyzing the aptitude and behavioral tendencies of individual workers based on accumulated operational data and generating a report.

[0843] (Claim 3)

[0844] The system according to claim 1, comprising means of using a portable information terminal for administrators in which improvement suggestions based on the determined emotional state are displayed as visual and auditory notifications. [Explanation of Symbols]

[0845] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. In an early childhood education facility, a means for receiving video information acquired from a camera installed within the facility, A means for recognizing the movements of educators and the behavior of children and detecting anomalies using an artificial intelligence model for analyzing the aforementioned video information, A means for generating a warning based on detected anomalies and notifying educators via their mobile devices, A means of accumulating daily behavioral data and generating information related to individual children as profiles, A system that includes this.

2. The system according to claim 1, further comprising means for analyzing the aptitudes and behavioral patterns of individual children and generating a report based on accumulated behavioral data.

3. The system according to claim 1, comprising means of using a portable information terminal for educators in which warnings based on detected anomalies are displayed as visual and auditory notifications.

Images