system

Abstract

We provide the system. [Solution] A device that receives information acquired from a video acquisition device, An artificial intelligence analysis device that analyzes behavioral patterns based on the aforementioned information and identifies specific behaviors, A device that detects identified behavior as problematic behavior if it exceeds a predetermined standard, A device that generates response procedures and warnings based on detected problematic behavior, A device that transmits the aforementioned warning to a portable terminal, 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 and includes 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 educational institutions, the occurrence of bullying, violence, and other problem behaviors is a serious social problem. In particular, there is a problem that these behaviors tend to be overlooked when teachers are absent or out of sight. Since such problems may have a long-term impact on the physical and mental health of students, it is required to take prompt and effective measures. However, the current monitoring system relies largely on manual labor and has limitations. Therefore, there is a need for a system that can detect problem behaviors in real time and respond promptly.

Means for Solving the Problems

[0005] This invention provides a system that identifies specific behaviors by obtaining video data from video acquisition devices installed within educational institutions and analyzing it in real time using AI analysis means. This system detects problematic behaviors when they exceed pre-set criteria, immediately generates a response flow based on the detected problematic behavior, and generates an alert. The generated alert is sent to the teacher's terminal, allowing teachers to quickly understand and respond to the problem. This enables the prevention and early detection of problematic behaviors even in the absence of teachers, thereby improving safety in educational institutions.

[0006] A "video acquisition device" is a device installed on school grounds to capture video of the surrounding environment.

[0007] "Video data" refers to image and video information acquired from a video acquisition device.

[0008] An "AI analysis method" is a system that takes video data as input and uses computer vision technology and machine learning models to analyze behavioral patterns.

[0009] "Behavioral patterns" refer to the characteristics of individual or group movements within video data.

[0010] "Specific behaviors" refer to behaviors that are candidates for problematic behaviors identified by AI analysis tools.

[0011] "Problem behavior" refers to behavior that is considered undesirable or dangerous in an educational setting.

[0012] A "criteria" refers to a threshold or condition set to classify a particular behavior as problematic behavior.

[0013] A "response flow" outlines the steps and methods that should be taken in response to detected problematic behaviors.

[0014] An "alert" is a notification generated to prompt the detection of problem behaviors and the execution of response flows.

[0015] A "teacher terminal" is a computer or mobile device used by a teacher and is for receiving alerts.

Brief Explanation of Drawings

[0016] [Figure 1] It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It 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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It 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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It 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] It shows an emotion map to which multiple emotions are mapped. [Figure 10] It shows an emotion map to which multiple emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13]It is a sequence diagram showing the processing flow of the data processing system in Example 2 when the emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when the emotion engine is combined.

Mode for Carrying Out the Invention

[0017] Hereinafter, an example of an embodiment of the system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

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

[0019] In the following embodiments, the 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.

[0020] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0021] In the following embodiments, the 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.

[0022] 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).

[0023] 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."

[0024] [First Embodiment]

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

[0026] 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.

[0027] 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).

[0028] 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.

[0029] 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.

[0030] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form 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.

[0031] 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.

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

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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".

[0037] One embodiment of this invention involves connecting multiple video acquisition devices installed within a school via a network and configuring each device to capture video data in real time.

[0038] The terminal collects video data obtained from the video acquisition device at regular intervals and transmits it to the server. For security reasons, the transmitted data is communicated in an encrypted format.

[0039] When the server receives video data, it uses AI analysis tools to analyze the data and identify behavioral patterns. The AI ​​analysis tools apply deep learning technology to improve their ability to identify specific behaviors from past data.

[0040] If the analysis reveals that an identified behavior exceeds a set threshold and is recognized as problematic behavior, the server immediately generates a response flow. This response flow includes specific steps on how to address the issue and information to be communicated to relevant parties.

[0041] Based on the generated response flow, the server creates an alert and sends the information to the terminal. Users (teachers) can check the alert displayed on their terminal and take swift action. The alert includes a summary of the detected action, location, stakeholders, and necessary countermeasures, allowing teachers to respond immediately to the situation.

[0042] For example, if multiple students gather in a specific location during recess and violent behavior patterns are detected, the server will recognize the situation and send an alert with suggested actions. This allows users to intervene quickly and prevent the situation from escalating.

[0043] This system is effective in identifying problematic behavior early and safely addressing it, even in situations where teachers cannot directly supervise. By applying AI technology, it is possible to set the urgency of the response and take appropriate action when necessary.

[0044] The following describes the processing flow.

[0045] Step 1:

[0046] The device captures video data in real time via security cameras. The captured data is stored in temporary storage, encrypted, and then sent to a server over the network.

[0047] Step 2:

[0048] The server decodes the received video data and inputs it into the AI ​​analysis system. The AI ​​analysis system analyzes behavioral patterns in the video based on a deep learning model. Because this model is pre-trained with a vast amount of historical data, it can identify specific behaviors with high accuracy.

[0049] Step 3:

[0050] The server identifies problematic behaviors from the behavioral patterns detected by AI analysis tools, based on predefined thresholds and rules. For example, if behaviors such as violence or bullying are detected, it determines whether their score exceeds the standard.

[0051] Step 4:

[0052] When problematic behavior is identified, the server automatically generates a response flow. This response flow includes information on the steps to take to address the issue and the teachers and parents who should be involved.

[0053] Step 5:

[0054] The server creates an alert along with the generated response flow and sends it to the terminal. The alert includes a summary of the detected activity, location, time, and necessary actions.

[0055] Step 6:

[0056] Users (teachers) receive alerts on their devices and check the content. This allows them to quickly go to the location of the problem and take appropriate action.

[0057] (Example 1)

[0058] 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."

[0059] In modern educational settings, managing student activities and behavior in situations where teachers and staff cannot directly supervise is a challenging task. In particular, there is a need for an effective system to detect unexpected problematic behavior and safety-related incidents early and to respond quickly. Traditional monitoring methods are time-consuming, difficult to cover all situations, and hinder rapid response.

[0060] 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.

[0061] In this invention, the server includes a medium for receiving digital video information, means for collecting, encrypting, and transmitting video information at regular intervals, means for analyzing behavioral patterns using artificial intelligence analysis means, and means for detecting problematic behavior based on the identified behavior. This makes it possible to efficiently monitor students' behavior in educational settings, detect problematic behavior early, and take prompt and appropriate action.

[0062] A "video acquisition device" is a device used to capture digital video information in real time.

[0063] "Digital video information" refers to visual data in digital format acquired from a video acquisition device.

[0064] A "medium" is a communication device or platform for receiving and processing digital video information.

[0065] An "encryption protocol" is a set of encryption techniques and procedures used to maintain the security of data being transmitted.

[0066] "Artificial intelligence analysis means" refers to algorithms and technologies used to analyze behavioral patterns based on digital video information and identify specific behaviors.

[0067] A "learning algorithm" is a data processing method used to make predictions and classifications based on past data, and is a part of machine learning.

[0068] A "behavioral pattern" is a specific style of movement or behavior extracted from collected digital video information.

[0069] "Problem behavior" refers to behavior that requires attention and is detected when the identified behavior exceeds a predetermined standard.

[0070] "Handling procedures" refer to the specific methods and procedures that should be followed when problematic behavior is detected.

[0071] A "warning" is information intended to inform you of the details of the detected problematic behavior and recommended countermeasures.

[0072] "Educational staff terminals" refer to computers or mobile devices used by teachers and staff to receive and verify information.

[0073] This invention is a system for effectively implementing safety and monitoring student behavior within educational institutions. The system consists of several main components, including a video acquisition device, terminals, a server, and a terminal for educational staff.

[0074] The terminal collects digital video information in real time from various video acquisition devices installed within the school. This digital video information is organized at regular intervals and securely transmitted to the server using encryption protocols. For security purposes, the terminal uses encryption technologies such as AES-256 to prevent unauthorized access to the information.

[0075] The server receives encrypted digital video information transmitted from the terminal, decrypts it, and processes it. The server integrates deep learning frameworks such as TENSORFLOW® and PyTorch, and artificial intelligence analysis methods using these frameworks analyze behavioral patterns. During the analysis, a learning algorithm built on past data is used to identify specific behaviors and detect problematic behaviors if they exceed set criteria. The server also automatically generates processing procedures based on the detected problematic behaviors and organizes them as warnings.

[0076] Users (educators) receive warnings sent from the server on their staff terminals and review their contents. The warnings include details of the detected problematic behavior, the location where it occurred, and recommended countermeasures, enabling teachers to take prompt and appropriate action.

[0077] For example, if students are crowded together in a specific area during recess and suspicious behavior is detected, the system will immediately identify it as problematic behavior. The generated warning, along with necessary countermeasures, will be sent to the teacher's terminal, allowing teachers to check the situation and take appropriate action.

[0078] An example of a prompt statement is, "Describe an AI system that monitors behavioral patterns in a specific area of ​​a school in real time and generates a response flow when problematic behavior is detected." Using this prompt statement provides guidance for the AI ​​analysis tool to properly configure the system and execute its actions.

[0079] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0080] Step 1:

[0081] The terminal acquires digital video information from video acquisition devices. The input is real-time video data from each video acquisition device, which is collected frame by frame at specific intervals. The output is organized time-series video data. This data undergoes noise filtering to maintain a consistent data quality.

[0082] Step 2:

[0083] The terminal encrypts the collected digital video information. The input is the organized video data obtained in step 1. The output is data encrypted using a protocol such as AES-256. This ensures the security of the information and prevents unauthorized access.

[0084] Step 3:

[0085] The terminal sends encrypted digital video information to the server. The input is the data encrypted in step 2. The output is the data transmitted over a secure communication channel. A transmission confirmation process is included to ensure that the data reaches the server.

[0086] Step 4:

[0087] The server decrypts the encrypted digital video information received from the terminal. The input is the encrypted data received in step 3. The output is the original decrypted video data. Through this process, the server also verifies the integrity of the data.

[0088] Step 5:

[0089] The server processes the decoded digital video information using AI analysis tools. The input is the video data decoded in step 4. The output is the analysis results regarding behavioral patterns. This analysis uses a deep learning framework to extract features from the data and identify behaviors.

[0090] Step 6:

[0091] The server detects problem behavior if the identified behavior exceeds a set criterion. The input is the behavior pattern analysis result obtained in step 5. The output is information about the problem behavior to be passed to step 7. This criterion is systematically set based on past event data.

[0092] Step 7:

[0093] The server generates a set of action steps and creates a warning based on the detected problematic behavior. The input is the problematic behavior identified in step 6. The output is the generated warning and details of the action steps. The server generates an action list specifying the necessary countermeasures.

[0094] Step 8:

[0095] The server sends the generated warning to the teacher's terminal. The input is the warning created in step 7. The output is the alert information received on the teacher's terminal. This information includes specific steps to take and recommended actions.

[0096] Step 9:

[0097] The user checks the warning on the teacher's terminal and takes appropriate action. The input is the alert received in step 8. The output is the immediate response action taken at the school. This response ensures student safety and improves the situation.

[0098] (Application Example 1)

[0099] 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."

[0100] Conventional monitoring systems take time to analyze behavior and detect problematic behaviors, which can lead to delays in situations requiring rapid response. There is a need for a system that can solve this problem, detect problematic behaviors in real time, and respond quickly.

[0101] 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.

[0102] In this invention, the server includes a device for receiving information acquired from a video acquisition device, an artificial intelligence analysis device for analyzing behavioral patterns based on the information and identifying specific behaviors, and a device for detecting problematic behavior when the identified behavior exceeds a preset standard. This enables safe and rapid monitoring and immediate response.

[0103] A "video acquisition device" is a device that captures movement and activity within the environment and converts it into digital signals as information.

[0104] A "device that receives information" is a device that receives data from an external source and performs the necessary processing.

[0105] An "artificial intelligence analysis device" is a device that uses technologies such as deep learning and machine learning to analyze data and identify specific patterns or behaviors.

[0106] A "device that detects problematic behavior" is a device that detects behavior that exceeds pre-set criteria within the system and reports it as a problem.

[0107] A "portable terminal" is a small, portable information and communication device that a user can carry with them and that has the function of displaying and manipulating data.

[0108] A "learning algorithm" is a computational method used to analyze data patterns and identify specific behaviors or characteristics.

[0109] A "warning" is a notification that informs the user of problematic behavior detected by the system, prompting them to take necessary action.

[0110] To implement this invention, first, multiple video acquisition devices are required within the installation environment. These devices capture the surrounding environment in real time and collect information as digital signals. This information is transmitted to a server via edge devices.

[0111] The server is equipped with an artificial intelligence analysis system using Python and TensorFlow. This system utilizes deep learning algorithms to analyze behavioral patterns contained in video data. In this process, if a behavior exceeds a certain threshold, it is detected as problematic behavior.

[0112] The detected information is immediately generated as an alert. This alert is sent to a mobile device via a notification system such as Firebase Cloud Messaging. Users with a mobile device can take prompt action based on this information.

[0113] As a concrete example, it can detect unusual human movement in specific areas of a commercial facility in real time. For instance, if someone is found to be handling merchandise in a store, a notification is immediately sent to security staff, allowing them to take necessary action.

[0114] An example of a prompt message to give instructions to the generating AI model is: "Analyze the behavior of people within the facility and detect any abnormal patterns. Generate immediate warnings as needed and devise a response flow."

[0115] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0116] Step 1:

[0117] The edge device acquires video data in real time from video acquisition devices in the environment. It receives the video signal as input, applies a noise reduction filter, and compresses the data. As output, it prepares the processed data for the next server transmission step.

[0118] Step 2:

[0119] The edge device sends processed video data to the server using a secure communication protocol (e.g., TLS). It receives compressed data as input, encrypts it with AES, and then transmits it over the internet. The output is the transmission of video data in a securely encrypted state.

[0120] Step 3:

[0121] The server decrypts the received encrypted video data and then processes it using an AI analysis device. It receives encrypted data as input, and after decryption, a deep learning model analyzes the behavioral patterns. The output is the analyzed behavioral pattern data.

[0122] Step 4:

[0123] The server identifies behaviors that exceed specific criteria as problematic behaviors based on deep learning analysis results. It receives analyzed behavior patterns as input and applies threshold judgment logic. As output, it generates a list of events considered problematic behaviors.

[0124] Step 5:

[0125] The server immediately generates an alert and creates an effective response flow when problematic behavior is detected. The input is an event list, and a response flow creation algorithm is applied. The output is notification data containing an alert message and specific response steps.

[0126] Step 6:

[0127] The server sends the generated alerts to mobile devices via a notification service such as Firebase Cloud Messaging. It receives alert notification data as input and outputs it using the Cloud Notification API. As output, users can quickly receive alerts on their mobile devices.

[0128] Step 7:

[0129] Users can review warnings received on their mobile devices and take appropriate action based on the provided response flow. The input is the content of the warning sent to the user, and the output generates an action for prompt response.

[0130] 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.

[0131] As an embodiment of this invention, a system is provided that operates by combining an AI analysis means and an emotion engine based on video data acquired by a video acquisition device.

[0132] The terminal collects real-time video data from multiple video acquisition devices installed within the school, encrypts it, and sends it to the server.

[0133] The server supplies the received video data to an AI analysis system. This analysis system uses a machine learning model employing deep learning to analyze behavioral patterns and has the ability to distinguish between normal and abnormal behavior. Furthermore, the emotion engine recognizes emotions through user facial expression analysis and voice analysis, and understands changes and states of emotions.

[0134] For example, if a student makes an aggressive gesture, the AI ​​analysis tool identifies that action as violent behavior. Meanwhile, the emotion engine analyzes the student's facial expressions and tone of voice to detect emotions such as anger or frustration.

[0135] Based on these results, the server integrates the identified behavioral and emotional information and flags it as problematic behavior. Next, the server generates an optimal response flow. This flow includes considerations and countermeasures tailored to the identified problematic behavior and the associated emotions. For example, it might incorporate steps to encourage calming discussions or, if necessary, psychological counseling.

[0136] The server sends the generated response flow and its details as an alert to the teacher's terminal. The user (teacher) receives the alert, checks its contents, immediately understands the situation on the ground, and can take the instructed action. This enables teachers to provide effective responses, including emotional considerations.

[0137] As a concrete example, if video footage is captured of a student yelling at another student during a break after class, the system would recognize this behavior as violent, and simultaneously, the emotion engine would confirm the student's anger. Based on these results, the server would immediately generate a response flow and notify the teacher as an alert. The teacher would then rush to the scene, assess the situation, and respond quickly according to the alert's instructions, thus preventing the problem from escalating.

[0138] The following describes the processing flow.

[0139] Step 1:

[0140] The device captures video data in real time via security cameras. This video data is saved as clips every few seconds and sent to the server using a secure protocol.

[0141] Step 2:

[0142] The server feeds the received video data into an AI analysis system for analysis. The AI ​​analysis system uses a machine learning model to analyze behavioral patterns in the video in real time and detect abnormal behavior.

[0143] Step 3:

[0144] Simultaneously, the server uses an emotion engine to analyze the user's facial expressions and voice from the video data and recognize their emotional state. In this process, facial expression analysis and voice analysis work together to classify emotions such as anger, joy, and sadness.

[0145] Step 4:

[0146] The server combines behaviors identified by AI analysis tools with emotions recognized by an emotion engine to identify problematic behaviors. These identified problematic behaviors are then flagged as actions that require intervention.

[0147] Step 5:

[0148] The server generates an appropriate response flow based on the identified problematic behavior and the associated emotional information. This flow includes specific action steps, emotionally appropriate approaches, and procedures for contacting relevant parties as needed.

[0149] Step 6:

[0150] The server sends this response flow as an alert to the terminal. This alert is immediately sent to the terminals used by teachers to enable appropriate responses based on the urgency of the situation.

[0151] Step 7:

[0152] The user (teacher) checks the alert on their device and understands the information and recommended response steps indicated in the alert. Based on this, the teacher goes to the site and promptly takes the instructed action.

[0153] This process allows for timely, emotionally sensitive, and appropriate responses when problematic behavior occurs.

[0154] (Example 2)

[0155] 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 will be referred to as the "terminal."

[0156] Ensuring safety in educational settings is crucial, but human resources and visual monitoring alone have their limitations. In particular, detecting and appropriately addressing abnormal student behavior and emotional changes in real time is difficult. Furthermore, delays in the early detection and appropriate response to problematic behavior increase the risk of further problems. To solve these problems, automated analysis of behavior and emotions, along with the generation of appropriate warnings and response measures, are needed.

[0157] 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.

[0158] In this invention, the server includes means for encrypting, receiving, and transmitting data acquired from a video acquisition device; means including an analysis device that analyzes behavioral patterns based on the data and identifies specific behaviors; and means including a device that recognizes emotions based on the analyzed behaviors. This enables real-time detection of abnormal behavior and emotional changes in educational settings and the provision of appropriate countermeasures based on the results.

[0159] A "video acquisition device" is a hardware device for acquiring video data and is equipped with the function of collecting surrounding visual information in real time.

[0160] A "device that encrypts and transmits data" is a device that performs encryption processing to securely protect acquired data and prevent unauthorized access during transmission.

[0161] An "analysis device" is a device that analyzes behavioral patterns based on received data and has the function of distinguishing between normal and abnormal behavior.

[0162] A "device that recognizes emotions" is a device that determines a user's emotional state from their facial expressions and voice, and tracks changes in that state.

[0163] A "device that identifies behavior as a problem when it exceeds a certain standard" is a device that detects data that exceeds pre-set normal behavioral standards and identifies that behavior as problematic behavior.

[0164] A "response-generating and warning-generating device" is a device that creates appropriate countermeasures based on identified problematic behaviors and quickly issues warnings to relevant parties.

[0165] An "educator terminal" is a computer terminal used by teachers and other related personnel, providing an interface for receiving warnings and instructions and enabling quick responses.

[0166] To implement this invention, it is essential to use video acquisition equipment installed in schools and educational institutions. Specifically, a high-resolution IP camera is used to acquire video data of classrooms, corridors, etc., in real time. Since it is difficult to verify the data collected by this equipment on the spot, it is first encrypted at a terminal. In the encryption process, AES, a common encryption algorithm, is used to ensure the security of the data.

[0167] The encrypted data acquired is securely transmitted from the terminal to the server. The server uses a deep learning framework (e.g., TensorFlow or PyTorch) to analyze the received data and identify behavioral patterns. This analysis identifies student movements, gestures, etc., and distinguishes between normal and abnormal behavior. Furthermore, the server uses OpenCV or commercial emotion recognition APIs (e.g., Microsoft® Azure® Cognitive Services) to analyze and recognize emotions from the acquired video and audio.

[0168] If this analysis identifies behaviors or emotions that exceed the established criteria, the server quickly generates a response flow using tools such as OptaPlanner. This response flow includes specific actions tailored to the student's situation and is sent as an alert to the educator's terminal. Upon receiving the alert, the educator can immediately grasp the situation on the ground and take swift and appropriate action according to the instructions.

[0169] For example, if a student argument during break time is captured on camera, the system might identify the behavior as abnormal and detect anger through emotion analysis. As a result, the server would suggest a response flow to the educator, such as "first, have the students talk to each other and encourage them to calm down," and send a warning to the terminal.

[0170] Example prompt: "Using a generative AI model, how would you generate the optimal response to abnormal behavior detected in school surveillance camera data?"

[0171] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0172] Step 1:

[0173] The terminal collects video in real time from video acquisition devices installed within the school facilities. The input is video data, and the output is encrypted data. The terminal secures this video data by encrypting it using the AES encryption algorithm, and then prepares it for transmission to the server.

[0174] Step 2:

[0175] The server receives encrypted data from the terminal. The input is encrypted video data. The server decrypts this data and converts it into a format usable for analyzing behavioral patterns. The output is analyzable video data. The server prepares the decrypted data for the next analysis process.

[0176] Step 3:

[0177] The server uses analyzable video data to perform AI analysis on behavioral patterns. The input is analyzable video data. The server uses a deep learning framework (e.g., TensorFlow or PyTorch) to input this data into a behavioral analysis model, extract behavioral features, and distinguish between normal and abnormal behavior. The output is the identified behavioral information.

[0178] Step 4:

[0179] The server recognizes emotions based on behavioral information. The input is identified behavioral information. The server uses OpenCV and an emotion recognition API to analyze facial expressions and voice tone to determine the user's emotional state. The output is the analyzed emotion data. This allows for understanding the emotional changes associated with behavior.

[0180] Step 5:

[0181] The server combines identified behavioral and emotional data and identifies anomalies as problems. Input consists of behavioral and emotional data. Problem behaviors are flagged, preparing for the next response generation step. Output is problem behavior information.

[0182] Step 6:

[0183] The server automatically generates response flows based on problem behavior information. The input is problem behavior information. Using tools like OptaPlanner, it develops appropriate response scenarios for the behavior and emotions, and prepares instructions for educators. The output is a specific response flow.

[0184] Step 7:

[0185] The server sends the generated response flow and associated warnings to the teacher's terminal. The input is a specific response flow. Warning information is constructed in a format optimized for display on the teacher's terminal and distributed instantly. The output is a warning notification to the teacher.

[0186] Step 8:

[0187] The user (teacher) checks the warning received on their terminal and takes the instructed action. The input is the warning notification sent to the teacher's terminal. The user uses this information to quickly resolve the problem on-site. The output is the appropriate response to the problem.

[0188] (Application Example 2)

[0189] 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".

[0190] To improve security in public facilities, there is a need for a system that can detect abnormal behavior and emotional states in real time and enable a rapid response. However, current technology makes it difficult to simultaneously analyze multiple emotional states and behavioral patterns and derive appropriate responses.

[0191] 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.

[0192] In this invention, the server includes means for receiving image data acquired from a video acquisition device, artificial intelligence analysis means for analyzing behavioral patterns based on the image data and identifying specific actions, and means for generating a response flow and issuing a warning based on the detected problematic actions and emotional states. This enables simultaneous analysis of abnormal actions and emotional states at the scene, allowing for a quick and appropriate response.

[0193] A "video acquisition device" is a device that collects image data from a physical space; for example, a surveillance camera falls into this category.

[0194] "Image data" refers to digital data containing visual information collected by an image acquisition device.

[0195] "Artificial intelligence analysis means" refers to analysis means that use image data to analyze behavioral patterns and emotions, and use machine learning models to identify specific actions.

[0196] A "behavioral pattern" is a pattern identified as a series of actions or behaviors exhibited by an individual or group.

[0197] "Emotional state" refers to an individual's emotional state as analyzed from factors such as voice and facial expressions.

[0198] A "standard" is a predetermined guideline or scale used to determine what is normal and what is abnormal.

[0199] "Problematic behavior" refers to abnormal behavior that is detected as exceeding established criteria.

[0200] A "response flow" is a series of processes generated to guide appropriate response steps to detected problematic behaviors.

[0201] A "warning" is a notification or alert issued when a problematic behavior is detected.

[0202] A "terminal" is an electronic device used to receive and display information; examples include smartphones and tablets.

[0203] This invention describes an embodiment of a system aimed at improving security in public places. This system includes a video acquisition device, a server, and a terminal as its main components.

[0204] First, the video acquisition system uses surveillance cameras and sensors to collect real-time image data within public facilities. The collected data is encrypted for enhanced security and then transmitted to a server.

[0205] The server utilizes artificial intelligence analysis methods based on deep learning techniques to process received image data. This analysis uses machine learning libraries such as TensorFlow and PyTorch to analyze behavioral patterns and emotional states, and detect abnormal behavior. Based on the analysis results, the server generates a response flow that takes both behavior and emotional state into consideration, and creates a warning.

[0206] Next, the generated warning is sent to a device. This device could be a smartphone or tablet, and the user (security officer) who receives it can check the situation and take a quick response. This significantly improves security within public facilities.

[0207] For example, suspicious behavior in a shopping mall may be captured on surveillance cameras. If a particular individual is moving around unusually in a crowded area, this behavior can be quickly detected, and an appropriate warning can be sent to the person in charge, preventing the problem from occurring.

[0208] One example of a prompt message to be fed into a generation AI model is, "Please generate real-time alerts for the AI ​​that analyzes customer movements and facial expressions obtained from surveillance cameras and evaluates safety risks." This allows the AI ​​to make situational judgments based on on-site data and support appropriate responses.

[0209] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0210] Step 1:

[0211] The video acquisition device captures real-time image data within public facilities. This data is obtained through surveillance cameras and immediately encrypted. The encrypted image data is then ready to be sent to the server.

[0212] Step 2:

[0213] The server receives encrypted image data and performs data decryption. It then receives the decrypted image data as input and preprocesses it for use with a deep learning model. This preprocessing includes image normalization and noise reduction.

[0214] Step 3:

[0215] The server supplies pre-processed image data to the artificial intelligence analysis system. The analysis model uses frameworks such as TensorFlow or PyTorch to analyze behavioral patterns and emotional states. Here, multiple specific actions and changes in facial expression are extracted to distinguish between normal and abnormal behavior.

[0216] Step 4:

[0217] The server detects abnormal behavior and emotions based on the analysis results and generates a response flow. Within the generated AI model, the prompt message "Please have the AI ​​analyze customer behavior and facial expressions obtained from surveillance cameras and evaluate safety risks to generate alerts in real time." is used to automatically determine the appropriate warning content.

[0218] Step 5:

[0219] The generated alerts are sent to the terminal by the server. On the terminal, the alerts are notified to security personnel in real time. This allows users to quickly grasp the situation via their mobile devices and take a rapid response on-site.

[0220] 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.

[0221] 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.

[0222] 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.

[0223] [Second Embodiment]

[0224] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0225] 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.

[0226] 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).

[0227] 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.

[0228] 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.

[0229] 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).

[0230] 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.

[0231] 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.

[0232] 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.

[0233] 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.

[0234] 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.

[0235] 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".

[0236] One embodiment of this invention involves connecting multiple video acquisition devices installed within a school via a network and configuring each device to capture video data in real time.

[0237] The terminal collects video data obtained from the video acquisition device at regular intervals and transmits it to the server. For security reasons, the transmitted data is communicated in an encrypted format.

[0238] When the server receives video data, it uses AI analysis tools to analyze the data and identify behavioral patterns. The AI ​​analysis tools apply deep learning technology to improve their ability to identify specific behaviors from past data.

[0239] If the analysis reveals that an identified behavior exceeds a set threshold and is recognized as problematic behavior, the server immediately generates a response flow. This response flow includes specific steps on how to address the issue and information to be communicated to relevant parties.

[0240] Based on the generated response flow, the server creates an alert and sends the information to the terminal. Users (teachers) can check the alert displayed on their terminal and take swift action. The alert includes a summary of the detected action, location, stakeholders, and necessary countermeasures, allowing teachers to respond immediately to the situation.

[0241] For example, if multiple students gather in a specific location during recess and violent behavior patterns are detected, the server will recognize the situation and send an alert with suggested actions. This allows users to intervene quickly and prevent the situation from escalating.

[0242] This system is effective in identifying problematic behavior early and safely addressing it, even in situations where teachers cannot directly supervise. By applying AI technology, it is possible to set the urgency of the response and take appropriate action when necessary.

[0243] The following describes the processing flow.

[0244] Step 1:

[0245] The device captures video data in real time via security cameras. The captured data is stored in temporary storage, encrypted, and then sent to a server over the network.

[0246] Step 2:

[0247] The server decodes the received video data and inputs it into the AI ​​analysis system. The AI ​​analysis system analyzes behavioral patterns in the video based on a deep learning model. Because this model is pre-trained with a vast amount of historical data, it can identify specific behaviors with high accuracy.

[0248] Step 3:

[0249] The server identifies problematic behaviors from the behavioral patterns detected by AI analysis tools, based on predefined thresholds and rules. For example, if behaviors such as violence or bullying are detected, it determines whether their score exceeds the standard.

[0250] Step 4:

[0251] When problematic behavior is identified, the server automatically generates a response flow. This response flow includes information on the steps to take to address the issue and the teachers and parents who should be involved.

[0252] Step 5:

[0253] The server creates an alert along with the generated response flow and sends it to the terminal. The alert includes a summary of the detected activity, location, time, and necessary actions.

[0254] Step 6:

[0255] Users (teachers) receive alerts on their devices and check the content. This allows them to quickly go to the location of the problem and take appropriate action.

[0256] (Example 1)

[0257] 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."

[0258] In modern educational settings, managing student activities and behavior in situations where teachers and staff cannot directly supervise is a challenging task. In particular, there is a need for an effective system to detect unexpected problematic behavior and safety-related incidents early and to respond quickly. Traditional monitoring methods are time-consuming, difficult to cover all situations, and hinder rapid response.

[0259] 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.

[0260] In this invention, the server includes a medium for receiving digital video information, means for collecting, encrypting, and transmitting video information at regular intervals, means for analyzing behavioral patterns using artificial intelligence analysis means, and means for detecting problematic behavior based on the identified behavior. This makes it possible to efficiently monitor students' behavior in educational settings, detect problematic behavior early, and take prompt and appropriate action.

[0261] A "video acquisition device" is a device used to capture digital video information in real time.

[0262] "Digital video information" refers to visual data in digital format acquired from a video acquisition device.

[0263] A "medium" is a communication device or platform for receiving and processing digital video information.

[0264] An "encryption protocol" is a set of encryption techniques and procedures used to maintain the security of data being transmitted.

[0265] "Artificial intelligence analysis means" refers to algorithms and technologies used to analyze behavioral patterns based on digital video information and identify specific behaviors.

[0266] A "learning algorithm" is a data processing method used to make predictions and classifications based on past data, and is a part of machine learning.

[0267] A "behavioral pattern" is a specific style of movement or behavior extracted from collected digital video information.

[0268] "Problem behavior" refers to behavior that requires attention and is detected when the identified behavior exceeds a predetermined standard.

[0269] "Handling procedures" refer to the specific methods and procedures that should be followed when problematic behavior is detected.

[0270] A "warning" is information intended to inform you of the details of the detected problematic behavior and recommended countermeasures.

[0271] "Educational staff terminals" refer to computers or mobile devices used by teachers and staff to receive and verify information.

[0272] This invention is a system for effectively implementing safety and monitoring student behavior within educational institutions. The system consists of several main components, including a video acquisition device, terminals, a server, and a terminal for educational staff.

[0273] The terminal collects digital video information in real time from various video acquisition devices installed within the school. This digital video information is organized at regular intervals and securely transmitted to the server using encryption protocols. For security purposes, the terminal uses encryption technologies such as AES-256 to prevent unauthorized access to the information.

[0274] The server receives encrypted digital video information transmitted from the terminal, decrypts it, and processes it. The server integrates deep learning frameworks such as TensorFlow and PyTorch, and uses artificial intelligence analysis tools to analyze behavioral patterns. During analysis, a learning algorithm built on past data is used to identify specific behaviors and detect problematic behaviors if they exceed set criteria. The server also automatically generates processing procedures based on the detected problematic behaviors and organizes them as warnings.

[0275] Users (educators) receive warnings sent from the server on their staff terminals and review their contents. The warnings include details of the detected problematic behavior, the location where it occurred, and recommended countermeasures, enabling teachers to take prompt and appropriate action.

[0276] For example, if students are crowded together in a specific area during recess and suspicious behavior is detected, the system will immediately identify it as problematic behavior. The generated warning, along with necessary countermeasures, will be sent to the teacher's terminal, allowing teachers to check the situation and take appropriate action.

[0277] An example of a prompt statement is, "Describe an AI system that monitors behavioral patterns in a specific area of ​​a school in real time and generates a response flow when problematic behavior is detected." Using this prompt statement provides guidance for the AI ​​analysis tool to properly configure the system and execute its actions.

[0278] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0279] Step 1:

[0280] The terminal acquires digital video information from the video acquisition device. The input is the real-time video data from each video acquisition device, and this is collected frame by frame at specific intervals. The output is the organized video data in time series. This data undergoes noise filtering and processing to maintain the quality of the data consistently.

[0281] Step 2:

[0282] The terminal encrypts the collected digital video information. The input is the organized video data obtained in Step 1. The output is the data encrypted with a protocol such as AES - 256. This can ensure the security of the information and prevent unauthorized access.

[0283] Step 3:

[0284] The terminal sends the encrypted digital video information to the server. The input is the data encrypted in Step 2. The output is the data transmitted via a secure communication channel. Include a process for confirmation of transmission to ensure that the data reaches the server.

[0285] Step 4:

[0286] The server decrypts the encrypted digital video information received from the terminal. The input is the encrypted data received in Step 3. The output is the original decrypted video data. Through this process, the server also checks the integrity of the data.

[0287] Step 5:

[0288] The server processes the decrypted digital video information with AI analysis means. The input is the video data decrypted in Step 4. The output is the analysis result regarding the behavior pattern. This analysis uses a deep learning framework to extract features from the data and identify the behavior.

[0289] Step 6:

[0290] The server detects problem behavior if the identified behavior exceeds a set criterion. The input is the behavior pattern analysis result obtained in step 5. The output is information about the problem behavior to be passed to step 7. This criterion is systematically set based on past event data.

[0291] Step 7:

[0292] The server generates a set of action steps and creates a warning based on the detected problematic behavior. The input is the problematic behavior identified in step 6. The output is the generated warning and details of the action steps. The server generates an action list specifying the necessary countermeasures.

[0293] Step 8:

[0294] The server sends the generated warning to the teacher's terminal. The input is the warning created in step 7. The output is the alert information received on the teacher's terminal. This information includes specific steps to take and recommended actions.

[0295] Step 9:

[0296] The user checks the warning on the teacher's terminal and takes appropriate action. The input is the alert received in step 8. The output is the immediate response action taken at the school. This response ensures student safety and improves the situation.

[0297] (Application Example 1)

[0298] 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."

[0299] Conventional monitoring systems take time to analyze behavior and detect problematic behaviors, which can lead to delays in situations requiring rapid response. There is a need for a system that can solve this problem, detect problematic behaviors in real time, and respond quickly.

[0300] The specific processing by the specific processing unit 290 of the data processing apparatus 12 in Application Example 1 is realized by the following means respectively.

[0301] In this invention, the server includes: a device that receives information acquired from an image acquisition device; an artificial intelligence analysis device that analyzes a behavior pattern based on the information and identifies a specific behavior; and a device that detects a problem behavior when the identified behavior exceeds a preset criterion. Thereby, safe and rapid monitoring and immediate response become possible.

[0302] The "image acquisition device" is a device having a function of capturing the movement and stillness in the environment and converting them into digital signals as information.

[0303] The "device that receives information" is a device that receives external data and performs necessary processing.

[0304] The "artificial intelligence analysis device" is a device that analyzes data using technologies such as deep learning and machine learning and identifies specific patterns and behaviors.

[0305] The "device that detects as a problem behavior" is a device that detects a behavior exceeding a preset criterion within the system and reports it as a problem.

[0306] The "portable terminal" is a small information communication device that can be carried by a user and has functions of displaying and operating data.

[0307] The "learning algorithm" is a calculation method for analyzing data patterns and identifying specific behaviors and features.

[0308] A "warning" is notification information for informing a user of a problem behavior detected by the system and prompting necessary countermeasures to be taken.

[0309] To implement this invention, first, multiple video acquisition devices are required within the installation environment. These devices capture the surrounding environment in real time and collect information as digital signals. This information is transmitted to a server via edge devices.

[0310] The server is equipped with an artificial intelligence analysis system using Python and TensorFlow. This system utilizes deep learning algorithms to analyze behavioral patterns contained in video data. In this process, if a behavior exceeds a certain threshold, it is detected as problematic behavior.

[0311] The detected information is immediately generated as an alert. This alert is sent to a mobile device via a notification system such as Firebase Cloud Messaging. Users with a mobile device can take prompt action based on this information.

[0312] As a concrete example, it can detect unusual human movement in specific areas of a commercial facility in real time. For instance, if someone is found to be handling merchandise in a store, a notification is immediately sent to security staff, allowing them to take necessary action.

[0313] An example of a prompt message to give instructions to the generating AI model is: "Analyze the behavior of people within the facility and detect any abnormal patterns. Generate immediate warnings as needed and devise a response flow."

[0314] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0315] Step 1:

[0316] The edge device acquires video data in real time from video acquisition devices in the environment. It receives the video signal as input, applies a noise reduction filter, and compresses the data. As output, it prepares the processed data for the next server transmission step.

[0317] Step 2:

[0318] The edge device sends processed video data to the server using a secure communication protocol (e.g., TLS). It receives compressed data as input, encrypts it with AES, and then transmits it over the internet. The output is the transmission of video data in a securely encrypted state.

[0319] Step 3:

[0320] The server decrypts the received encrypted video data and then processes it using an AI analysis device. It receives encrypted data as input, and after decryption, a deep learning model analyzes the behavioral patterns. The output is the analyzed behavioral pattern data.

[0321] Step 4:

[0322] The server identifies behaviors that exceed specific criteria as problematic behaviors based on deep learning analysis results. It receives analyzed behavior patterns as input and applies threshold judgment logic. As output, it generates a list of events considered problematic behaviors.

[0323] Step 5:

[0324] The server immediately generates an alert and creates an effective response flow when problematic behavior is detected. The input is an event list, and a response flow creation algorithm is applied. The output is notification data containing an alert message and specific response steps.

[0325] Step 6:

[0326] The server sends the generated alerts to mobile devices via a notification service such as Firebase Cloud Messaging. It receives alert notification data as input and outputs it using the Cloud Notification API. As output, users can quickly receive alerts on their mobile devices.

[0327] Step 7:

[0328] Users can review warnings received on their mobile devices and take appropriate action based on the provided response flow. The input is the content of the warning sent to the user, and the output generates an action for prompt response.

[0329] 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.

[0330] As an embodiment of this invention, a system is provided that operates by combining an AI analysis means and an emotion engine based on video data acquired by a video acquisition device.

[0331] The terminal collects real-time video data from multiple video acquisition devices installed within the school, encrypts it, and sends it to the server.

[0332] The server supplies the received video data to an AI analysis system. This analysis system uses a machine learning model employing deep learning to analyze behavioral patterns and has the ability to distinguish between normal and abnormal behavior. Furthermore, the emotion engine recognizes emotions through user facial expression analysis and voice analysis, and understands changes and states of emotions.

[0333] For example, if a student makes an aggressive gesture, the AI ​​analysis tool identifies that action as violent behavior. Meanwhile, the emotion engine analyzes the student's facial expressions and tone of voice to detect emotions such as anger or frustration.

[0334] Based on these results, the server integrates the identified behavioral and emotional information and flags it as problematic behavior. Next, the server generates an optimal response flow. This flow includes considerations and countermeasures tailored to the identified problematic behavior and the associated emotions. For example, it might incorporate steps to encourage calming discussions or, if necessary, psychological counseling.

[0335] The server sends the generated response flow and its details as an alert to the teacher's terminal. The user (teacher) receives the alert, checks its contents, immediately understands the situation on the ground, and can take the instructed action. This enables teachers to provide effective responses, including emotional considerations.

[0336] As a concrete example, if video footage is captured of a student yelling at another student during a break after class, the system would recognize this behavior as violent, and simultaneously, the emotion engine would confirm the student's anger. Based on these results, the server would immediately generate a response flow and notify the teacher as an alert. The teacher would then rush to the scene, assess the situation, and respond quickly according to the alert's instructions, thus preventing the problem from escalating.

[0337] The following describes the processing flow.

[0338] Step 1:

[0339] The device captures video data in real time via security cameras. This video data is saved as clips every few seconds and sent to the server using a secure protocol.

[0340] Step 2:

[0341] The server feeds the received video data into an AI analysis system for analysis. The AI ​​analysis system uses a machine learning model to analyze behavioral patterns in the video in real time and detect abnormal behavior.

[0342] Step 3:

[0343] Simultaneously, the server uses an emotion engine to analyze the user's facial expressions and voice from the video data and recognize their emotional state. In this process, facial expression analysis and voice analysis work together to classify emotions such as anger, joy, and sadness.

[0344] Step 4:

[0345] The server combines behaviors identified by AI analysis tools with emotions recognized by an emotion engine to identify problematic behaviors. These identified problematic behaviors are then flagged as actions that require intervention.

[0346] Step 5:

[0347] The server generates an appropriate response flow based on the identified problematic behavior and the associated emotional information. This flow includes specific action steps, emotionally appropriate approaches, and procedures for contacting relevant parties as needed.

[0348] Step 6:

[0349] The server sends this response flow as an alert to the terminal. This alert is immediately sent to the terminals used by teachers to enable appropriate responses based on the urgency of the situation.

[0350] Step 7:

[0351] The user (teacher) checks the alert on their device and understands the information and recommended response steps indicated in the alert. Based on this, the teacher goes to the site and promptly takes the instructed action.

[0352] This process allows for timely, emotionally sensitive, and appropriate responses when problematic behavior occurs.

[0353] (Example 2)

[0354] 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".

[0355] Ensuring safety in educational settings is crucial, but human resources and visual monitoring alone have their limitations. In particular, detecting and appropriately addressing abnormal student behavior and emotional changes in real time is difficult. Furthermore, delays in the early detection and appropriate response to problematic behavior increase the risk of further problems. To solve these problems, automated analysis of behavior and emotions, along with the generation of appropriate warnings and response measures, are needed.

[0356] 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.

[0357] In this invention, the server includes means for encrypting, receiving, and transmitting data acquired from a video acquisition device; means including an analysis device that analyzes behavioral patterns based on the data and identifies specific behaviors; and means including a device that recognizes emotions based on the analyzed behaviors. This enables real-time detection of abnormal behavior and emotional changes in educational settings and the provision of appropriate countermeasures based on the results.

[0358] A "video acquisition device" is a hardware device for acquiring video data and is equipped with the function of collecting surrounding visual information in real time.

[0359] A "device that encrypts and transmits data" is a device that performs encryption processing to securely protect acquired data and prevent unauthorized access during transmission.

[0360] An "analysis device" is a device that analyzes behavioral patterns based on received data and has the function of distinguishing between normal and abnormal behavior.

[0361] A "device that recognizes emotions" is a device that determines a user's emotional state from their facial expressions and voice, and tracks changes in that state.

[0362] A "device that identifies behavior as a problem when it exceeds a certain standard" is a device that detects data that exceeds pre-set normal behavioral standards and identifies that behavior as problematic behavior.

[0363] A "response-generating and warning-generating device" is a device that creates appropriate countermeasures based on identified problematic behaviors and quickly issues warnings to relevant parties.

[0364] An "educator terminal" is a computer terminal used by teachers and other related personnel, providing an interface for receiving warnings and instructions and enabling quick responses.

[0365] To implement this invention, it is essential to use video acquisition equipment installed in schools and educational institutions. Specifically, a high-resolution IP camera is used to acquire video data of classrooms, corridors, etc., in real time. Since it is difficult to verify the data collected by this equipment on the spot, it is first encrypted at a terminal. In the encryption process, AES, a common encryption algorithm, is used to ensure the security of the data.

[0366] The encrypted data acquired is securely transmitted from the terminal to the server. The server uses a deep learning framework (e.g., TensorFlow or PyTorch) to analyze the received data and identify behavioral patterns. This analysis identifies student movements, gestures, etc., and distinguishes between normal and abnormal behavior. Furthermore, the server uses OpenCV or commercial emotion recognition APIs (e.g., Microsoft Azure Cognitive Services) to analyze and recognize emotions from the acquired video and audio.

[0367] If this analysis identifies behaviors or emotions that exceed the established criteria, the server quickly generates a response flow using tools such as OptaPlanner. This response flow includes specific actions tailored to the student's situation and is sent as an alert to the educator's terminal. Upon receiving the alert, the educator can immediately grasp the situation on the ground and take swift and appropriate action according to the instructions.

[0368] For example, if a student argument during break time is captured on camera, the system might identify the behavior as abnormal and detect anger through emotion analysis. As a result, the server would suggest a response flow to the educator, such as "first, have the students talk to each other and encourage them to calm down," and send a warning to the terminal.

[0369] Example prompt: "Using a generative AI model, how would you generate the optimal response to abnormal behavior detected in school surveillance camera data?"

[0370] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0371] Step 1:

[0372] The terminal collects video in real time from video acquisition devices installed within the school facilities. The input is video data, and the output is encrypted data. The terminal secures this video data by encrypting it using the AES encryption algorithm, and then prepares it for transmission to the server.

[0373] Step 2:

[0374] The server receives encrypted data from the terminal. The input is encrypted video data. The server decrypts this data and converts it into a format usable for analyzing behavioral patterns. The output is analyzable video data. The server prepares the decrypted data for the next analysis process.

[0375] Step 3:

[0376] The server uses analyzable video data to perform AI analysis on behavioral patterns. The input is analyzable video data. The server uses a deep learning framework (e.g., TensorFlow or PyTorch) to input this data into a behavioral analysis model, extract behavioral features, and distinguish between normal and abnormal behavior. The output is the identified behavioral information.

[0377] Step 4:

[0378] The server recognizes emotions based on behavioral information. The input is identified behavioral information. The server uses OpenCV and an emotion recognition API to analyze facial expressions and voice tone to determine the user's emotional state. The output is the analyzed emotion data. This allows for understanding the emotional changes associated with behavior.

[0379] Step 5:

[0380] The server combines identified behavioral and emotional data and identifies anomalies as problems. Input consists of behavioral and emotional data. Problem behaviors are flagged, preparing for the next response generation step. Output is problem behavior information.

[0381] Step 6:

[0382] The server automatically generates response flows based on problem behavior information. The input is problem behavior information. Using tools like OptaPlanner, it develops appropriate response scenarios for the behavior and emotions, and prepares instructions for educators. The output is a specific response flow.

[0383] Step 7:

[0384] The server sends the generated response flow and associated warnings to the teacher's terminal. The input is a specific response flow. Warning information is constructed in a format optimized for display on the teacher's terminal and distributed instantly. The output is a warning notification to the teacher.

[0385] Step 8:

[0386] The user (teacher) checks the warning received on their terminal and takes the instructed action. The input is the warning notification sent to the teacher's terminal. The user uses this information to quickly resolve the problem on-site. The output is the appropriate response to the problem.

[0387] (Application Example 2)

[0388] 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."

[0389] To improve security in public facilities, there is a need for a system that can detect abnormal behavior and emotional states in real time and enable a rapid response. However, current technology makes it difficult to simultaneously analyze multiple emotional states and behavioral patterns and derive appropriate responses.

[0390] 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.

[0391] In this invention, the server includes means for receiving image data acquired from a video acquisition device, artificial intelligence analysis means for analyzing behavioral patterns based on the image data and identifying specific actions, and means for generating a response flow and issuing a warning based on the detected problematic actions and emotional states. This enables simultaneous analysis of abnormal actions and emotional states at the scene, allowing for a quick and appropriate response.

[0392] A "video acquisition device" is a device that collects image data from a physical space; for example, a surveillance camera falls into this category.

[0393] "Image data" refers to digital data containing visual information collected by an image acquisition device.

[0394] "Artificial intelligence analysis means" refers to analysis means that use image data to analyze behavioral patterns and emotions, and use machine learning models to identify specific actions.

[0395] A "behavioral pattern" is a pattern identified as a series of actions or behaviors exhibited by an individual or group.

[0396] "Emotional state" refers to an individual's emotional state as analyzed from factors such as voice and facial expressions.

[0397] A "standard" is a predetermined guideline or scale used to determine what is normal and what is abnormal.

[0398] "Problematic behavior" refers to abnormal behavior that is detected as exceeding established criteria.

[0399] A "response flow" is a series of processes generated to guide appropriate response steps to detected problematic behaviors.

[0400] A "warning" is a notification or alert issued when a problematic behavior is detected.

[0401] A "terminal" is an electronic device used to receive and display information; examples include smartphones and tablets.

[0402] This invention describes an embodiment of a system aimed at improving security in public places. This system includes a video acquisition device, a server, and a terminal as its main components.

[0403] First, the video acquisition system uses surveillance cameras and sensors to collect real-time image data within public facilities. The collected data is encrypted for enhanced security and then transmitted to a server.

[0404] The server utilizes artificial intelligence analysis methods based on deep learning techniques to process received image data. This analysis uses machine learning libraries such as TensorFlow and PyTorch to analyze behavioral patterns and emotional states, and detect abnormal behavior. Based on the analysis results, the server generates a response flow that takes both behavior and emotional state into consideration, and creates a warning.

[0405] Next, the generated warning is sent to a device. This device could be a smartphone or tablet, and the user (security officer) who receives it can check the situation and take a quick response. This significantly improves security within public facilities.

[0406] For example, suspicious behavior in a shopping mall may be captured on surveillance cameras. If a particular individual is moving around unusually in a crowded area, this behavior can be quickly detected, and an appropriate warning can be sent to the person in charge, preventing the problem from occurring.

[0407] One example of a prompt message to be fed into a generation AI model is, "Please generate real-time alerts for the AI ​​that analyzes customer movements and facial expressions obtained from surveillance cameras and evaluates safety risks." This allows the AI ​​to make situational judgments based on on-site data and support appropriate responses.

[0408] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0409] Step 1:

[0410] The video acquisition device captures real-time image data within public facilities. This data is obtained through surveillance cameras and immediately encrypted. The encrypted image data is then ready to be sent to the server.

[0411] Step 2:

[0412] The server receives encrypted image data and performs data decryption. It then receives the decrypted image data as input and preprocesses it for use with a deep learning model. This preprocessing includes image normalization and noise reduction.

[0413] Step 3:

[0414] The server supplies pre-processed image data to the artificial intelligence analysis system. The analysis model uses frameworks such as TensorFlow or PyTorch to analyze behavioral patterns and emotional states. Here, multiple specific actions and changes in facial expression are extracted to distinguish between normal and abnormal behavior.

[0415] Step 4:

[0416] The server detects abnormal behavior and emotions based on the analysis results and generates a response flow. Within the generated AI model, the prompt message "Please have the AI ​​analyze customer behavior and facial expressions obtained from surveillance cameras and evaluate safety risks to generate alerts in real time." is used to automatically determine the appropriate warning content.

[0417] Step 5:

[0418] The generated alerts are sent to the terminal by the server. On the terminal, the alerts are notified to security personnel in real time. This allows users to quickly grasp the situation via their mobile devices and take a rapid response on-site.

[0419] 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.

[0420] 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.

[0421] 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.

[0422] [Third Embodiment]

[0423] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0424] 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.

[0425] 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).

[0426] 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.

[0427] 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.

[0428] 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).

[0429] 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.

[0430] 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.

[0431] 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.

[0432] 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.

[0433] 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.

[0434] 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".

[0435] One embodiment of this invention involves connecting multiple video acquisition devices installed within a school via a network and configuring each device to capture video data in real time.

[0436] The terminal collects video data obtained from the video acquisition device at regular intervals and transmits it to the server. For security reasons, the transmitted data is communicated in an encrypted format.

[0437] When the server receives video data, it uses AI analysis tools to analyze the data and identify behavioral patterns. The AI ​​analysis tools apply deep learning technology to improve their ability to identify specific behaviors from past data.

[0438] If the analysis reveals that an identified behavior exceeds a set threshold and is recognized as problematic behavior, the server immediately generates a response flow. This response flow includes specific steps on how to address the issue and information to be communicated to relevant parties.

[0439] Based on the generated response flow, the server creates an alert and sends the information to the terminal. Users (teachers) can check the alert displayed on their terminal and take swift action. The alert includes a summary of the detected action, location, stakeholders, and necessary countermeasures, allowing teachers to respond immediately to the situation.

[0440] For example, if multiple students gather in a specific location during recess and violent behavior patterns are detected, the server will recognize the situation and send an alert with suggested actions. This allows users to intervene quickly and prevent the situation from escalating.

[0441] This system is effective in identifying problematic behavior early and safely addressing it, even in situations where teachers cannot directly supervise. By applying AI technology, it is possible to set the urgency of the response and take appropriate action when necessary.

[0442] The following describes the processing flow.

[0443] Step 1:

[0444] The device captures video data in real time via security cameras. The captured data is stored in temporary storage, encrypted, and then sent to a server over the network.

[0445] Step 2:

[0446] The server decodes the received video data and inputs it into the AI ​​analysis system. The AI ​​analysis system analyzes behavioral patterns in the video based on a deep learning model. Because this model is pre-trained with a vast amount of historical data, it can identify specific behaviors with high accuracy.

[0447] Step 3:

[0448] The server identifies problematic behaviors from the behavioral patterns detected by AI analysis tools, based on predefined thresholds and rules. For example, if behaviors such as violence or bullying are detected, it determines whether their score exceeds the standard.

[0449] Step 4:

[0450] When problematic behavior is identified, the server automatically generates a response flow. This response flow includes information on the steps to take to address the issue and the teachers and parents who should be involved.

[0451] Step 5:

[0452] The server creates an alert along with the generated response flow and sends it to the terminal. The alert includes a summary of the detected activity, location, time, and necessary actions.

[0453] Step 6:

[0454] Users (teachers) receive alerts on their devices and check the content. This allows them to quickly go to the location of the problem and take appropriate action.

[0455] (Example 1)

[0456] 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."

[0457] In modern educational settings, managing student activities and behavior in situations where teachers and staff cannot directly supervise is a challenging task. In particular, there is a need for an effective system to detect unexpected problematic behavior and safety-related incidents early and to respond quickly. Traditional monitoring methods are time-consuming, difficult to cover all situations, and hinder rapid response.

[0458] 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.

[0459] In this invention, the server includes a medium for receiving digital video information, means for collecting, encrypting, and transmitting video information at regular intervals, means for analyzing behavioral patterns using artificial intelligence analysis means, and means for detecting problematic behavior based on the identified behavior. This makes it possible to efficiently monitor students' behavior in educational settings, detect problematic behavior early, and take prompt and appropriate action.

[0460] A "video acquisition device" is a device used to capture digital video information in real time.

[0461] "Digital video information" refers to visual data in digital format acquired from a video acquisition device.

[0462] A "medium" is a communication device or platform for receiving and processing digital video information.

[0463] An "encryption protocol" is a set of encryption techniques and procedures used to maintain the security of data being transmitted.

[0464] "Artificial intelligence analysis means" refers to algorithms and technologies used to analyze behavioral patterns based on digital video information and identify specific behaviors.

[0465] A "learning algorithm" is a data processing method used to make predictions and classifications based on past data, and is a part of machine learning.

[0466] A "behavioral pattern" is a specific style of movement or behavior extracted from collected digital video information.

[0467] "Problem behavior" refers to behavior that requires attention and is detected when the identified behavior exceeds a predetermined standard.

[0468] "Handling procedures" refer to the specific methods and procedures that should be followed when problematic behavior is detected.

[0469] A "warning" is information intended to inform you of the details of the detected problematic behavior and recommended countermeasures.

[0470] "Educational staff terminals" refer to computers or mobile devices used by teachers and staff to receive and verify information.

[0471] This invention is a system for effectively implementing safety and monitoring student behavior within educational institutions. The system consists of several main components, including a video acquisition device, terminals, a server, and a terminal for educational staff.

[0472] The terminal collects digital video information in real time from various video acquisition devices installed within the school. This digital video information is organized at regular intervals and securely transmitted to the server using encryption protocols. For security purposes, the terminal uses encryption technologies such as AES-256 to prevent unauthorized access to the information.

[0473] The server receives encrypted digital video information transmitted from the terminal, decrypts it, and processes it. The server integrates deep learning frameworks such as TensorFlow and PyTorch, and uses artificial intelligence analysis tools to analyze behavioral patterns. During analysis, a learning algorithm built on past data is used to identify specific behaviors and detect problematic behaviors if they exceed set criteria. The server also automatically generates processing procedures based on the detected problematic behaviors and organizes them as warnings.

[0474] Users (educators) receive warnings sent from the server on their staff terminals and review their contents. The warnings include details of the detected problematic behavior, the location where it occurred, and recommended countermeasures, enabling teachers to take prompt and appropriate action.

[0475] For example, if students are crowded together in a specific area during recess and suspicious behavior is detected, the system will immediately identify it as problematic behavior. The generated warning, along with necessary countermeasures, will be sent to the teacher's terminal, allowing teachers to check the situation and take appropriate action.

[0476] An example of a prompt statement is, "Describe an AI system that monitors behavioral patterns in a specific area of ​​a school in real time and generates a response flow when problematic behavior is detected." Using this prompt statement provides guidance for the AI ​​analysis tool to properly configure the system and execute its actions.

[0477] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0478] Step 1:

[0479] The terminal acquires digital video information from video acquisition devices. The input is real-time video data from each video acquisition device, which is collected frame by frame at specific intervals. The output is organized time-series video data. This data undergoes noise filtering to maintain a consistent data quality.

[0480] Step 2:

[0481] The terminal encrypts the collected digital video information. The input is the organized video data obtained in step 1. The output is data encrypted using a protocol such as AES-256. This ensures the security of the information and prevents unauthorized access.

[0482] Step 3:

[0483] The terminal sends encrypted digital video information to the server. The input is the data encrypted in step 2. The output is the data transmitted over a secure communication channel. A transmission confirmation process is included to ensure that the data reaches the server.

[0484] Step 4:

[0485] The server decrypts the encrypted digital video information received from the terminal. The input is the encrypted data received in step 3. The output is the original decrypted video data. Through this process, the server also verifies the integrity of the data.

[0486] Step 5:

[0487] The server processes the decoded digital video information using AI analysis tools. The input is the video data decoded in step 4. The output is the analysis results regarding behavioral patterns. This analysis uses a deep learning framework to extract features from the data and identify behaviors.

[0488] Step 6:

[0489] The server detects problem behavior if the identified behavior exceeds a set criterion. The input is the behavior pattern analysis result obtained in step 5. The output is information about the problem behavior to be passed to step 7. This criterion is systematically set based on past event data.

[0490] Step 7:

[0491] The server generates a set of action steps and creates a warning based on the detected problematic behavior. The input is the problematic behavior identified in step 6. The output is the generated warning and details of the action steps. The server generates an action list specifying the necessary countermeasures.

[0492] Step 8:

[0493] The server sends the generated warning to the teacher's terminal. The input is the warning created in step 7. The output is the alert information received on the teacher's terminal. This information includes specific steps to take and recommended actions.

[0494] Step 9:

[0495] The user checks the warning on the teacher's terminal and takes appropriate action. The input is the alert received in step 8. The output is the immediate response action taken at the school. This response ensures student safety and improves the situation.

[0496] (Application Example 1)

[0497] 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."

[0498] Conventional monitoring systems take time to analyze behavior and detect problematic behaviors, which can lead to delays in situations requiring rapid response. There is a need for a system that can solve this problem, detect problematic behaviors in real time, and respond quickly.

[0499] 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.

[0500] In this invention, the server includes a device for receiving information acquired from a video acquisition device, an artificial intelligence analysis device for analyzing behavioral patterns based on the information and identifying specific behaviors, and a device for detecting problematic behavior when the identified behavior exceeds a preset standard. This enables safe and rapid monitoring and immediate response.

[0501] A "video acquisition device" is a device that captures movement and activity within the environment and converts it into digital signals as information.

[0502] A "device that receives information" is a device that receives data from an external source and performs the necessary processing.

[0503] An "artificial intelligence analysis device" is a device that uses technologies such as deep learning and machine learning to analyze data and identify specific patterns or behaviors.

[0504] A "device that detects problematic behavior" is a device that detects behavior that exceeds pre-set criteria within the system and reports it as a problem.

[0505] A "portable terminal" is a small, portable information and communication device that a user can carry with them and that has the function of displaying and manipulating data.

[0506] A "learning algorithm" is a computational method used to analyze data patterns and identify specific behaviors or characteristics.

[0507] A "warning" is a notification that informs the user of problematic behavior detected by the system, prompting them to take necessary action.

[0508] To implement this invention, first, multiple video acquisition devices are required within the installation environment. These devices capture the surrounding environment in real time and collect information as digital signals. This information is transmitted to a server via edge devices.

[0509] The server is equipped with an artificial intelligence analysis system using Python and TensorFlow. This system utilizes deep learning algorithms to analyze behavioral patterns contained in video data. In this process, if a behavior exceeds a certain threshold, it is detected as problematic behavior.

[0510] The detected information is immediately generated as an alert. This alert is sent to a mobile device via a notification system such as Firebase Cloud Messaging. Users with a mobile device can take prompt action based on this information.

[0511] As a concrete example, it can detect unusual human movement in specific areas of a commercial facility in real time. For instance, if someone is found to be handling merchandise in a store, a notification is immediately sent to security staff, allowing them to take necessary action.

[0512] An example of a prompt message to give instructions to the generating AI model is: "Analyze the behavior of people within the facility and detect any abnormal patterns. Generate immediate warnings as needed and devise a response flow."

[0513] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0514] Step 1:

[0515] The edge device acquires video data in real time from video acquisition devices in the environment. It receives the video signal as input, applies a noise reduction filter, and compresses the data. As output, it prepares the processed data for the next server transmission step.

[0516] Step 2:

[0517] The edge device sends processed video data to the server using a secure communication protocol (e.g., TLS). It receives compressed data as input, encrypts it with AES, and then transmits it over the internet. The output is the transmission of video data in a securely encrypted state.

[0518] Step 3:

[0519] The server decrypts the received encrypted video data and then processes it using an AI analysis device. It receives encrypted data as input, and after decryption, a deep learning model analyzes the behavioral patterns. The output is the analyzed behavioral pattern data.

[0520] Step 4:

[0521] The server identifies behaviors that exceed specific criteria as problematic behaviors based on deep learning analysis results. It receives analyzed behavior patterns as input and applies threshold judgment logic. As output, it generates a list of events considered problematic behaviors.

[0522] Step 5:

[0523] The server immediately generates an alert and creates an effective response flow when problematic behavior is detected. The input is an event list, and a response flow creation algorithm is applied. The output is notification data containing an alert message and specific response steps.

[0524] Step 6:

[0525] The server sends the generated alerts to mobile devices via a notification service such as Firebase Cloud Messaging. It receives alert notification data as input and outputs it using the Cloud Notification API. As output, users can quickly receive alerts on their mobile devices.

[0526] Step 7:

[0527] Users can review warnings received on their mobile devices and take appropriate action based on the provided response flow. The input is the content of the warning sent to the user, and the output generates an action for prompt response.

[0528] 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.

[0529] As an embodiment of this invention, a system is provided that operates by combining an AI analysis means and an emotion engine based on video data acquired by a video acquisition device.

[0530] The terminal collects real-time video data from multiple video acquisition devices installed within the school, encrypts it, and sends it to the server.

[0531] The server supplies the received video data to an AI analysis system. This analysis system uses a machine learning model employing deep learning to analyze behavioral patterns and has the ability to distinguish between normal and abnormal behavior. Furthermore, the emotion engine recognizes emotions through user facial expression analysis and voice analysis, and understands changes and states of emotions.

[0532] For example, if a student makes an aggressive gesture, the AI ​​analysis tool identifies that action as violent behavior. Meanwhile, the emotion engine analyzes the student's facial expressions and tone of voice to detect emotions such as anger or frustration.

[0533] Based on these results, the server integrates the identified behavioral and emotional information and flags it as problematic behavior. Next, the server generates an optimal response flow. This flow includes considerations and countermeasures tailored to the identified problematic behavior and the associated emotions. For example, it might incorporate steps to encourage calming discussions or, if necessary, psychological counseling.

[0534] The server sends the generated response flow and its details as an alert to the teacher's terminal. The user (teacher) receives the alert, checks its contents, immediately understands the situation on the ground, and can take the instructed action. This enables teachers to provide effective responses, including emotional considerations.

[0535] As a concrete example, if video footage is captured of a student yelling at another student during a break after class, the system would recognize this behavior as violent, and simultaneously, the emotion engine would confirm the student's anger. Based on these results, the server would immediately generate a response flow and notify the teacher as an alert. The teacher would then rush to the scene, assess the situation, and respond quickly according to the alert's instructions, thus preventing the problem from escalating.

[0536] The following describes the processing flow.

[0537] Step 1:

[0538] The device captures video data in real time via security cameras. This video data is saved as clips every few seconds and sent to the server using a secure protocol.

[0539] Step 2:

[0540] The server feeds the received video data into an AI analysis system for analysis. The AI ​​analysis system uses a machine learning model to analyze behavioral patterns in the video in real time and detect abnormal behavior.

[0541] Step 3:

[0542] Simultaneously, the server uses an emotion engine to analyze the user's facial expressions and voice from the video data and recognize their emotional state. In this process, facial expression analysis and voice analysis work together to classify emotions such as anger, joy, and sadness.

[0543] Step 4:

[0544] The server combines behaviors identified by AI analysis tools with emotions recognized by an emotion engine to identify problematic behaviors. These identified problematic behaviors are then flagged as actions that require intervention.

[0545] Step 5:

[0546] The server generates an appropriate response flow based on the identified problematic behavior and the associated emotional information. This flow includes specific action steps, emotionally appropriate approaches, and procedures for contacting relevant parties as needed.

[0547] Step 6:

[0548] The server sends this response flow as an alert to the terminal. This alert is immediately sent to the terminals used by teachers to enable appropriate responses based on the urgency of the situation.

[0549] Step 7:

[0550] The user (teacher) checks the alert on their device and understands the information and recommended response steps indicated in the alert. Based on this, the teacher goes to the site and promptly takes the instructed action.

[0551] This process allows for timely, emotionally sensitive, and appropriate responses when problematic behavior occurs.

[0552] (Example 2)

[0553] 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."

[0554] Ensuring safety in educational settings is crucial, but human resources and visual monitoring alone have their limitations. In particular, detecting and appropriately addressing abnormal student behavior and emotional changes in real time is difficult. Furthermore, delays in the early detection and appropriate response to problematic behavior increase the risk of further problems. To solve these problems, automated analysis of behavior and emotions, along with the generation of appropriate warnings and response measures, are needed.

[0555] 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.

[0556] In this invention, the server includes means for encrypting, receiving, and transmitting data acquired from a video acquisition device; means including an analysis device that analyzes behavioral patterns based on the data and identifies specific behaviors; and means including a device that recognizes emotions based on the analyzed behaviors. This enables real-time detection of abnormal behavior and emotional changes in educational settings and the provision of appropriate countermeasures based on the results.

[0557] A "video acquisition device" is a hardware device for acquiring video data and is equipped with the function of collecting surrounding visual information in real time.

[0558] A "device that encrypts and transmits data" is a device that performs encryption processing to securely protect acquired data and prevent unauthorized access during transmission.

[0559] An "analysis device" is a device that analyzes behavioral patterns based on received data and has the function of distinguishing between normal and abnormal behavior.

[0560] A "device that recognizes emotions" is a device that determines a user's emotional state from their facial expressions and voice, and tracks changes in that state.

[0561] A "device that identifies behavior as a problem when it exceeds a certain standard" is a device that detects data that exceeds pre-set normal behavioral standards and identifies that behavior as problematic behavior.

[0562] A "response-generating and warning-generating device" is a device that creates appropriate countermeasures based on identified problematic behaviors and quickly issues warnings to relevant parties.

[0563] An "educator terminal" is a computer terminal used by teachers and other related personnel, providing an interface for receiving warnings and instructions and enabling quick responses.

[0564] To implement this invention, it is essential to use video acquisition equipment installed in schools and educational institutions. Specifically, a high-resolution IP camera is used to acquire video data of classrooms, corridors, etc., in real time. Since it is difficult to verify the data collected by this equipment on the spot, it is first encrypted at a terminal. In the encryption process, AES, a common encryption algorithm, is used to ensure the security of the data.

[0565] The encrypted data acquired is securely transmitted from the terminal to the server. The server uses a deep learning framework (e.g., TensorFlow or PyTorch) to analyze the received data and identify behavioral patterns. This analysis identifies student movements, gestures, etc., and distinguishes between normal and abnormal behavior. Furthermore, the server uses OpenCV or commercial emotion recognition APIs (e.g., Microsoft Azure Cognitive Services) to analyze and recognize emotions from the acquired video and audio.

[0566] If this analysis identifies behaviors or emotions that exceed the established criteria, the server quickly generates a response flow using tools such as OptaPlanner. This response flow includes specific actions tailored to the student's situation and is sent as an alert to the educator's terminal. Upon receiving the alert, the educator can immediately grasp the situation on the ground and take swift and appropriate action according to the instructions.

[0567] For example, if a student argument during break time is captured on camera, the system might identify the behavior as abnormal and detect anger through emotion analysis. As a result, the server would suggest a response flow to the educator, such as "first, have the students talk to each other and encourage them to calm down," and send a warning to the terminal.

[0568] Example prompt: "Using a generative AI model, how would you generate the optimal response to abnormal behavior detected in school surveillance camera data?"

[0569] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0570] Step 1:

[0571] The terminal collects video in real time from video acquisition devices installed within the school facilities. The input is video data, and the output is encrypted data. The terminal secures this video data by encrypting it using the AES encryption algorithm, and then prepares it for transmission to the server.

[0572] Step 2:

[0573] The server receives encrypted data from the terminal. The input is encrypted video data. The server decrypts this data and converts it into a format usable for analyzing behavioral patterns. The output is analyzable video data. The server prepares the decrypted data for the next analysis process.

[0574] Step 3:

[0575] The server uses analyzable video data to perform AI analysis on behavioral patterns. The input is analyzable video data. The server uses a deep learning framework (e.g., TensorFlow or PyTorch) to input this data into a behavioral analysis model, extract behavioral features, and distinguish between normal and abnormal behavior. The output is the identified behavioral information.

[0576] Step 4:

[0577] The server recognizes emotions based on behavioral information. The input is identified behavioral information. The server uses OpenCV and an emotion recognition API to analyze facial expressions and voice tone to determine the user's emotional state. The output is the analyzed emotion data. This allows for understanding the emotional changes associated with behavior.

[0578] Step 5:

[0579] The server combines identified behavioral and emotional data and identifies anomalies as problems. Input consists of behavioral and emotional data. Problem behaviors are flagged, preparing for the next response generation step. Output is problem behavior information.

[0580] Step 6:

[0581] The server automatically generates response flows based on problem behavior information. The input is problem behavior information. Using tools like OptaPlanner, it develops appropriate response scenarios for the behavior and emotions, and prepares instructions for educators. The output is a specific response flow.

[0582] Step 7:

[0583] The server sends the generated response flow and associated warnings to the teacher's terminal. The input is a specific response flow. Warning information is constructed in a format optimized for display on the teacher's terminal and distributed instantly. The output is a warning notification to the teacher.

[0584] Step 8:

[0585] The user (teacher) checks the warning received on their terminal and takes the instructed action. The input is the warning notification sent to the teacher's terminal. The user uses this information to quickly resolve the problem on-site. The output is the appropriate response to the problem.

[0586] (Application Example 2)

[0587] 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."

[0588] To improve security in public facilities, there is a need for a system that can detect abnormal behavior and emotional states in real time and enable a rapid response. However, current technology makes it difficult to simultaneously analyze multiple emotional states and behavioral patterns and derive appropriate responses.

[0589] 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.

[0590] In this invention, the server includes means for receiving image data acquired from a video acquisition device, artificial intelligence analysis means for analyzing behavioral patterns based on the image data and identifying specific actions, and means for generating a response flow and issuing a warning based on the detected problematic actions and emotional states. This enables simultaneous analysis of abnormal actions and emotional states at the scene, allowing for a quick and appropriate response.

[0591] A "video acquisition device" is a device that collects image data from a physical space; for example, a surveillance camera falls into this category.

[0592] "Image data" refers to digital data containing visual information collected by an image acquisition device.

[0593] "Artificial intelligence analysis means" refers to analysis means that use image data to analyze behavioral patterns and emotions, and use machine learning models to identify specific actions.

[0594] A "behavioral pattern" is a pattern identified as a series of actions or behaviors exhibited by an individual or group.

[0595] "Emotional state" refers to an individual's emotional state as analyzed from factors such as voice and facial expressions.

[0596] A "standard" is a predetermined guideline or scale used to determine what is normal and what is abnormal.

[0597] "Problematic behavior" refers to abnormal behavior that is detected as exceeding established criteria.

[0598] A "response flow" is a series of processes generated to guide appropriate response steps to detected problematic behaviors.

[0599] A "warning" is a notification or alert issued when a problematic behavior is detected.

[0600] A "terminal" is an electronic device used to receive and display information; examples include smartphones and tablets.

[0601] This invention describes an embodiment of a system aimed at improving security in public places. This system includes a video acquisition device, a server, and a terminal as its main components.

[0602] First, the video acquisition system uses surveillance cameras and sensors to collect real-time image data within public facilities. The collected data is encrypted for enhanced security and then transmitted to a server.

[0603] The server utilizes artificial intelligence analysis methods based on deep learning techniques to process received image data. This analysis uses machine learning libraries such as TensorFlow and PyTorch to analyze behavioral patterns and emotional states, and detect abnormal behavior. Based on the analysis results, the server generates a response flow that takes both behavior and emotional state into consideration, and creates a warning.

[0604] Next, the generated warning is sent to a device. This device could be a smartphone or tablet, and the user (security officer) who receives it can check the situation and take a quick response. This significantly improves security within public facilities.

[0605] For example, suspicious behavior in a shopping mall may be captured on surveillance cameras. If a particular individual is moving around unusually in a crowded area, this behavior can be quickly detected, and an appropriate warning can be sent to the person in charge, preventing the problem from occurring.

[0606] One example of a prompt message to be fed into a generation AI model is, "Please generate real-time alerts for the AI ​​that analyzes customer movements and facial expressions obtained from surveillance cameras and evaluates safety risks." This allows the AI ​​to make situational judgments based on on-site data and support appropriate responses.

[0607] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0608] Step 1:

[0609] The video acquisition device captures real-time image data within public facilities. This data is obtained through surveillance cameras and immediately encrypted. The encrypted image data is then ready to be sent to the server.

[0610] Step 2:

[0611] The server receives encrypted image data and performs data decryption. It then receives the decrypted image data as input and preprocesses it for use with a deep learning model. This preprocessing includes image normalization and noise reduction.

[0612] Step 3:

[0613] The server supplies pre-processed image data to the artificial intelligence analysis system. The analysis model uses frameworks such as TensorFlow or PyTorch to analyze behavioral patterns and emotional states. Here, multiple specific actions and changes in facial expression are extracted to distinguish between normal and abnormal behavior.

[0614] Step 4:

[0615] The server detects abnormal behavior and emotions based on the analysis results and generates a response flow. Within the generated AI model, the prompt message "Please have the AI ​​analyze customer behavior and facial expressions obtained from surveillance cameras and evaluate safety risks to generate alerts in real time." is used to automatically determine the appropriate warning content.

[0616] Step 5:

[0617] The generated alerts are sent to the terminal by the server. On the terminal, the alerts are notified to security personnel in real time. This allows users to quickly grasp the situation via their mobile devices and take a rapid response on-site.

[0618] 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.

[0619] 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.

[0620] 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.

[0621] [Fourth Embodiment]

[0622] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0623] 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.

[0624] 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).

[0625] 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.

[0626] 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.

[0627] 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).

[0628] 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.

[0629] 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.

[0630] 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.

[0631] 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.

[0632] 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.

[0633] 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.

[0634] 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".

[0635] One embodiment of this invention involves connecting multiple video acquisition devices installed within a school via a network and configuring each device to capture video data in real time.

[0636] The terminal collects video data obtained from the video acquisition device at regular intervals and transmits it to the server. For security reasons, the transmitted data is communicated in an encrypted format.

[0637] When the server receives video data, it uses AI analysis tools to analyze the data and identify behavioral patterns. The AI ​​analysis tools apply deep learning technology to improve their ability to identify specific behaviors from past data.

[0638] If the analysis reveals that an identified behavior exceeds a set threshold and is recognized as problematic behavior, the server immediately generates a response flow. This response flow includes specific steps on how to address the issue and information to be communicated to relevant parties.

[0639] Based on the generated response flow, the server creates an alert and sends the information to the terminal. Users (teachers) can check the alert displayed on their terminal and take swift action. The alert includes a summary of the detected action, location, stakeholders, and necessary countermeasures, allowing teachers to respond immediately to the situation.

[0640] For example, if multiple students gather in a specific location during recess and violent behavior patterns are detected, the server will recognize the situation and send an alert with suggested actions. This allows users to intervene quickly and prevent the situation from escalating.

[0641] This system is effective in identifying problematic behavior early and safely addressing it, even in situations where teachers cannot directly supervise. By applying AI technology, it is possible to set the urgency of the response and take appropriate action when necessary.

[0642] The following describes the processing flow.

[0643] Step 1:

[0644] The device captures video data in real time via security cameras. The captured data is stored in temporary storage, encrypted, and then sent to a server over the network.

[0645] Step 2:

[0646] The server decodes the received video data and inputs it into the AI ​​analysis system. The AI ​​analysis system analyzes behavioral patterns in the video based on a deep learning model. Because this model is pre-trained with a vast amount of historical data, it can identify specific behaviors with high accuracy.

[0647] Step 3:

[0648] The server identifies problematic behaviors from the behavioral patterns detected by AI analysis tools, based on predefined thresholds and rules. For example, if behaviors such as violence or bullying are detected, it determines whether their score exceeds the standard.

[0649] Step 4:

[0650] When problematic behavior is identified, the server automatically generates a response flow. This response flow includes information on the steps to take to address the issue and the teachers and parents who should be involved.

[0651] Step 5:

[0652] The server creates an alert along with the generated response flow and sends it to the terminal. The alert includes a summary of the detected activity, location, time, and necessary actions.

[0653] Step 6:

[0654] Users (teachers) receive alerts on their devices and check the content. This allows them to quickly go to the location of the problem and take appropriate action.

[0655] (Example 1)

[0656] 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".

[0657] In modern educational settings, managing student activities and behavior in situations where teachers and staff cannot directly supervise is a challenging task. In particular, there is a need for an effective system to detect unexpected problematic behavior and safety-related incidents early and to respond quickly. Traditional monitoring methods are time-consuming, difficult to cover all situations, and hinder rapid response.

[0658] 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.

[0659] In this invention, the server includes a medium for receiving digital video information, means for collecting, encrypting, and transmitting video information at regular intervals, means for analyzing behavioral patterns using artificial intelligence analysis means, and means for detecting problematic behavior based on the identified behavior. This makes it possible to efficiently monitor students' behavior in educational settings, detect problematic behavior early, and take prompt and appropriate action.

[0660] A "video acquisition device" is a device used to capture digital video information in real time.

[0661] "Digital video information" refers to visual data in digital format acquired from a video acquisition device.

[0662] A "medium" is a communication device or platform for receiving and processing digital video information.

[0663] An "encryption protocol" is a set of encryption techniques and procedures used to maintain the security of data being transmitted.

[0664] "Artificial intelligence analysis means" refers to algorithms and technologies used to analyze behavioral patterns based on digital video information and identify specific behaviors.

[0665] A "learning algorithm" is a data processing method used to make predictions and classifications based on past data, and is a part of machine learning.

[0666] A "behavioral pattern" is a specific style of movement or behavior extracted from collected digital video information.

[0667] "Problem behavior" refers to behavior that requires attention and is detected when the identified behavior exceeds a predetermined standard.

[0668] "Handling procedures" refer to the specific methods and procedures that should be followed when problematic behavior is detected.

[0669] A "warning" is information intended to inform you of the details of the detected problematic behavior and recommended countermeasures.

[0670] "Educational staff terminals" refer to computers or mobile devices used by teachers and staff to receive and verify information.

[0671] This invention is a system for effectively implementing safety and monitoring student behavior within educational institutions. The system consists of several main components, including a video acquisition device, terminals, a server, and a terminal for educational staff.

[0672] The terminal collects digital video information in real time from various video acquisition devices installed within the school. This digital video information is organized at regular intervals and securely transmitted to the server using encryption protocols. For security purposes, the terminal uses encryption technologies such as AES-256 to prevent unauthorized access to the information.

[0673] The server receives encrypted digital video information transmitted from the terminal, decrypts it, and processes it. The server integrates deep learning frameworks such as TensorFlow and PyTorch, and uses artificial intelligence analysis tools to analyze behavioral patterns. During analysis, a learning algorithm built on past data is used to identify specific behaviors and detect problematic behaviors if they exceed set criteria. The server also automatically generates processing procedures based on the detected problematic behaviors and organizes them as warnings.

[0674] Users (educators) receive warnings sent from the server on their staff terminals and review their contents. The warnings include details of the detected problematic behavior, the location where it occurred, and recommended countermeasures, enabling teachers to take prompt and appropriate action.

[0675] For example, if students are crowded together in a specific area during recess and suspicious behavior is detected, the system will immediately identify it as problematic behavior. The generated warning, along with necessary countermeasures, will be sent to the teacher's terminal, allowing teachers to check the situation and take appropriate action.

[0676] An example of a prompt statement is, "Describe an AI system that monitors behavioral patterns in a specific area of ​​a school in real time and generates a response flow when problematic behavior is detected." Using this prompt statement provides guidance for the AI ​​analysis tool to properly configure the system and execute its actions.

[0677] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0678] Step 1:

[0679] The terminal acquires digital video information from video acquisition devices. The input is real-time video data from each video acquisition device, which is collected frame by frame at specific intervals. The output is organized time-series video data. This data undergoes noise filtering to maintain a consistent data quality.

[0680] Step 2:

[0681] The terminal encrypts the collected digital video information. The input is the organized video data obtained in step 1. The output is data encrypted using a protocol such as AES-256. This ensures the security of the information and prevents unauthorized access.

[0682] Step 3:

[0683] The terminal sends encrypted digital video information to the server. The input is the data encrypted in step 2. The output is the data transmitted over a secure communication channel. A transmission confirmation process is included to ensure that the data reaches the server.

[0684] Step 4:

[0685] The server decrypts the encrypted digital video information received from the terminal. The input is the encrypted data received in step 3. The output is the original decrypted video data. Through this process, the server also verifies the integrity of the data.

[0686] Step 5:

[0687] The server processes the decoded digital video information using AI analysis tools. The input is the video data decoded in step 4. The output is the analysis results regarding behavioral patterns. This analysis uses a deep learning framework to extract features from the data and identify behaviors.

[0688] Step 6:

[0689] The server detects problem behavior if the identified behavior exceeds a set criterion. The input is the behavior pattern analysis result obtained in step 5. The output is information about the problem behavior to be passed to step 7. This criterion is systematically set based on past event data.

[0690] Step 7:

[0691] The server generates a set of action steps and creates a warning based on the detected problematic behavior. The input is the problematic behavior identified in step 6. The output is the generated warning and details of the action steps. The server generates an action list specifying the necessary countermeasures.

[0692] Step 8:

[0693] The server sends the generated warning to the teacher's terminal. The input is the warning created in step 7. The output is the alert information received on the teacher's terminal. This information includes specific steps to take and recommended actions.

[0694] Step 9:

[0695] The user checks the warning on the teacher's terminal and takes appropriate action. The input is the alert received in step 8. The output is the immediate response action taken at the school. This response ensures student safety and improves the situation.

[0696] (Application Example 1)

[0697] 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".

[0698] Conventional monitoring systems take time to analyze behavior and detect problematic behaviors, which can lead to delays in situations requiring rapid response. There is a need for a system that can solve this problem, detect problematic behaviors in real time, and respond quickly.

[0699] 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.

[0700] In this invention, the server includes a device for receiving information acquired from a video acquisition device, an artificial intelligence analysis device for analyzing behavioral patterns based on the information and identifying specific behaviors, and a device for detecting problematic behavior when the identified behavior exceeds a preset standard. This enables safe and rapid monitoring and immediate response.

[0701] A "video acquisition device" is a device that captures movement and activity within the environment and converts it into digital signals as information.

[0702] A "device that receives information" is a device that receives data from an external source and performs the necessary processing.

[0703] An "artificial intelligence analysis device" is a device that uses technologies such as deep learning and machine learning to analyze data and identify specific patterns or behaviors.

[0704] A "device that detects problematic behavior" is a device that detects behavior that exceeds pre-set criteria within the system and reports it as a problem.

[0705] A "portable terminal" is a small, portable information and communication device that a user can carry with them and that has the function of displaying and manipulating data.

[0706] A "learning algorithm" is a computational method used to analyze data patterns and identify specific behaviors or characteristics.

[0707] A "warning" is a notification that informs the user of problematic behavior detected by the system, prompting them to take necessary action.

[0708] To implement this invention, first, multiple video acquisition devices are required within the installation environment. These devices capture the surrounding environment in real time and collect information as digital signals. This information is transmitted to a server via edge devices.

[0709] The server is equipped with an artificial intelligence analysis system using Python and TensorFlow. This system utilizes deep learning algorithms to analyze behavioral patterns contained in video data. In this process, if a behavior exceeds a certain threshold, it is detected as problematic behavior.

[0710] The detected information is immediately generated as an alert. This alert is sent to a mobile device via a notification system such as Firebase Cloud Messaging. Users with a mobile device can take prompt action based on this information.

[0711] As a concrete example, it can detect unusual human movement in specific areas of a commercial facility in real time. For instance, if someone is found to be handling merchandise in a store, a notification is immediately sent to security staff, allowing them to take necessary action.

[0712] An example of a prompt message to give instructions to the generating AI model is: "Analyze the behavior of people within the facility and detect any abnormal patterns. Generate immediate warnings as needed and devise a response flow."

[0713] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0714] Step 1:

[0715] The edge device acquires video data in real time from video acquisition devices in the environment. It receives the video signal as input, applies a noise reduction filter, and compresses the data. As output, it prepares the processed data for the next server transmission step.

[0716] Step 2:

[0717] The edge device sends processed video data to the server using a secure communication protocol (e.g., TLS). It receives compressed data as input, encrypts it with AES, and then transmits it over the internet. The output is the transmission of video data in a securely encrypted state.

[0718] Step 3:

[0719] The server decrypts the received encrypted video data and then processes it using an AI analysis device. It receives encrypted data as input, and after decryption, a deep learning model analyzes the behavioral patterns. The output is the analyzed behavioral pattern data.

[0720] Step 4:

[0721] The server identifies behaviors that exceed specific criteria as problematic behaviors based on deep learning analysis results. It receives analyzed behavior patterns as input and applies threshold judgment logic. As output, it generates a list of events considered problematic behaviors.

[0722] Step 5:

[0723] The server immediately generates an alert and creates an effective response flow when problematic behavior is detected. The input is an event list, and a response flow creation algorithm is applied. The output is notification data containing an alert message and specific response steps.

[0724] Step 6:

[0725] The server sends the generated alerts to mobile devices via a notification service such as Firebase Cloud Messaging. It receives alert notification data as input and outputs it using the Cloud Notification API. As output, users can quickly receive alerts on their mobile devices.

[0726] Step 7:

[0727] Users can review warnings received on their mobile devices and take appropriate action based on the provided response flow. The input is the content of the warning sent to the user, and the output generates an action for prompt response.

[0728] 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.

[0729] As an embodiment of this invention, a system is provided that operates by combining an AI analysis means and an emotion engine based on video data acquired by a video acquisition device.

[0730] The terminal collects real-time video data from multiple video acquisition devices installed within the school, encrypts it, and sends it to the server.

[0731] The server supplies the received video data to an AI analysis system. This analysis system uses a machine learning model employing deep learning to analyze behavioral patterns and has the ability to distinguish between normal and abnormal behavior. Furthermore, the emotion engine recognizes emotions through user facial expression analysis and voice analysis, and understands changes and states of emotions.

[0732] For example, if a student makes an aggressive gesture, the AI ​​analysis tool identifies that action as violent behavior. Meanwhile, the emotion engine analyzes the student's facial expressions and tone of voice to detect emotions such as anger or frustration.

[0733] Based on these results, the server integrates the identified behavioral and emotional information and flags it as problematic behavior. Next, the server generates an optimal response flow. This flow includes considerations and countermeasures tailored to the identified problematic behavior and the associated emotions. For example, it might incorporate steps to encourage calming discussions or, if necessary, psychological counseling.

[0734] The server sends the generated response flow and its details as an alert to the teacher's terminal. The user (teacher) receives the alert, checks its contents, immediately understands the situation on the ground, and can take the instructed action. This enables teachers to provide effective responses, including emotional considerations.

[0735] As a concrete example, if video footage is captured of a student yelling at another student during a break after class, the system would recognize this behavior as violent, and simultaneously, the emotion engine would confirm the student's anger. Based on these results, the server would immediately generate a response flow and notify the teacher as an alert. The teacher would then rush to the scene, assess the situation, and respond quickly according to the alert's instructions, thus preventing the problem from escalating.

[0736] The following describes the processing flow.

[0737] Step 1:

[0738] The device captures video data in real time via security cameras. This video data is saved as clips every few seconds and sent to the server using a secure protocol.

[0739] Step 2:

[0740] The server feeds the received video data into an AI analysis system for analysis. The AI ​​analysis system uses a machine learning model to analyze behavioral patterns in the video in real time and detect abnormal behavior.

[0741] Step 3:

[0742] Simultaneously, the server uses an emotion engine to analyze the user's facial expressions and voice from the video data and recognize their emotional state. In this process, facial expression analysis and voice analysis work together to classify emotions such as anger, joy, and sadness.

[0743] Step 4:

[0744] The server combines behaviors identified by AI analysis tools with emotions recognized by an emotion engine to identify problematic behaviors. These identified problematic behaviors are then flagged as actions that require intervention.

[0745] Step 5:

[0746] The server generates an appropriate response flow based on the identified problematic behavior and the associated emotional information. This flow includes specific action steps, emotionally appropriate approaches, and procedures for contacting relevant parties as needed.

[0747] Step 6:

[0748] The server sends this response flow as an alert to the terminal. This alert is immediately sent to the terminals used by teachers to enable appropriate responses based on the urgency of the situation.

[0749] Step 7:

[0750] The user (teacher) checks the alert on their device and understands the information and recommended response steps indicated in the alert. Based on this, the teacher goes to the site and promptly takes the instructed action.

[0751] This process allows for timely, emotionally sensitive, and appropriate responses when problematic behavior occurs.

[0752] (Example 2)

[0753] 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".

[0754] Ensuring safety in educational settings is crucial, but human resources and visual monitoring alone have their limitations. In particular, detecting and appropriately addressing abnormal student behavior and emotional changes in real time is difficult. Furthermore, delays in the early detection and appropriate response to problematic behavior increase the risk of further problems. To solve these problems, automated analysis of behavior and emotions, along with the generation of appropriate warnings and response measures, are needed.

[0755] 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.

[0756] In this invention, the server includes means for encrypting, receiving, and transmitting data acquired from a video acquisition device; means including an analysis device that analyzes behavioral patterns based on the data and identifies specific behaviors; and means including a device that recognizes emotions based on the analyzed behaviors. This enables real-time detection of abnormal behavior and emotional changes in educational settings and the provision of appropriate countermeasures based on the results.

[0757] A "video acquisition device" is a hardware device for acquiring video data and is equipped with the function of collecting surrounding visual information in real time.

[0758] A "device that encrypts and transmits data" is a device that performs encryption processing to securely protect acquired data and prevent unauthorized access during transmission.

[0759] An "analysis device" is a device that analyzes behavioral patterns based on received data and has the function of distinguishing between normal and abnormal behavior.

[0760] A "device that recognizes emotions" is a device that determines a user's emotional state from their facial expressions and voice, and tracks changes in that state.

[0761] A "device that identifies behavior as a problem when it exceeds a certain standard" is a device that detects data that exceeds pre-set normal behavioral standards and identifies that behavior as problematic behavior.

[0762] A "response-generating and warning-generating device" is a device that creates appropriate countermeasures based on identified problematic behaviors and quickly issues warnings to relevant parties.

[0763] An "educator terminal" is a computer terminal used by teachers and other related personnel, providing an interface for receiving warnings and instructions and enabling quick responses.

[0764] To implement this invention, it is essential to use video acquisition equipment installed in schools and educational institutions. Specifically, a high-resolution IP camera is used to acquire video data of classrooms, corridors, etc., in real time. Since it is difficult to verify the data collected by this equipment on the spot, it is first encrypted at a terminal. In the encryption process, AES, a common encryption algorithm, is used to ensure the security of the data.

[0765] The encrypted data acquired is securely transmitted from the terminal to the server. The server uses a deep learning framework (e.g., TensorFlow or PyTorch) to analyze the received data and identify behavioral patterns. This analysis identifies student movements, gestures, etc., and distinguishes between normal and abnormal behavior. Furthermore, the server uses OpenCV or commercial emotion recognition APIs (e.g., Microsoft Azure Cognitive Services) to analyze and recognize emotions from the acquired video and audio.

[0766] If this analysis identifies behaviors or emotions that exceed the established criteria, the server quickly generates a response flow using tools such as OptaPlanner. This response flow includes specific actions tailored to the student's situation and is sent as an alert to the educator's terminal. Upon receiving the alert, the educator can immediately grasp the situation on the ground and take swift and appropriate action according to the instructions.

[0767] For example, if a student argument during break time is captured on camera, the system might identify the behavior as abnormal and detect anger through emotion analysis. As a result, the server would suggest a response flow to the educator, such as "first, have the students talk to each other and encourage them to calm down," and send a warning to the terminal.

[0768] Example prompt: "Using a generative AI model, how would you generate the optimal response to abnormal behavior detected in school surveillance camera data?"

[0769] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0770] Step 1:

[0771] The terminal collects video in real time from video acquisition devices installed within the school facilities. The input is video data, and the output is encrypted data. The terminal secures this video data by encrypting it using the AES encryption algorithm, and then prepares it for transmission to the server.

[0772] Step 2:

[0773] The server receives encrypted data from the terminal. The input is encrypted video data. The server decrypts this data and converts it into a format usable for analyzing behavioral patterns. The output is analyzable video data. The server prepares the decrypted data for the next analysis process.

[0774] Step 3:

[0775] The server uses analyzable video data to perform AI analysis on behavioral patterns. The input is analyzable video data. The server uses a deep learning framework (e.g., TensorFlow or PyTorch) to input this data into a behavioral analysis model, extract behavioral features, and distinguish between normal and abnormal behavior. The output is the identified behavioral information.

[0776] Step 4:

[0777] The server recognizes emotions based on behavioral information. The input is identified behavioral information. The server uses OpenCV and an emotion recognition API to analyze facial expressions and voice tone to determine the user's emotional state. The output is the analyzed emotion data. This allows for understanding the emotional changes associated with behavior.

[0778] Step 5:

[0779] The server combines identified behavioral and emotional data and identifies anomalies as problems. Input consists of behavioral and emotional data. Problem behaviors are flagged, preparing for the next response generation step. Output is problem behavior information.

[0780] Step 6:

[0781] The server automatically generates response flows based on problem behavior information. The input is problem behavior information. Using tools like OptaPlanner, it develops appropriate response scenarios for the behavior and emotions, and prepares instructions for educators. The output is a specific response flow.

[0782] Step 7:

[0783] The server sends the generated response flow and associated warnings to the teacher's terminal. The input is a specific response flow. Warning information is constructed in a format optimized for display on the teacher's terminal and distributed instantly. The output is a warning notification to the teacher.

[0784] Step 8:

[0785] The user (teacher) checks the warning received on their terminal and takes the instructed action. The input is the warning notification sent to the teacher's terminal. The user uses this information to quickly resolve the problem on-site. The output is the appropriate response to the problem.

[0786] (Application Example 2)

[0787] 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".

[0788] To improve security in public facilities, there is a need for a system that can detect abnormal behavior and emotional states in real time and enable a rapid response. However, current technology makes it difficult to simultaneously analyze multiple emotional states and behavioral patterns and derive appropriate responses.

[0789] 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.

[0790] In this invention, the server includes means for receiving image data acquired from a video acquisition device, artificial intelligence analysis means for analyzing behavioral patterns based on the image data and identifying specific actions, and means for generating a response flow and issuing a warning based on the detected problematic actions and emotional states. This enables simultaneous analysis of abnormal actions and emotional states at the scene, allowing for a quick and appropriate response.

[0791] A "video acquisition device" is a device that collects image data from a physical space; for example, a surveillance camera falls into this category.

[0792] "Image data" refers to digital data containing visual information collected by an image acquisition device.

[0793] "Artificial intelligence analysis means" refers to analysis means that use image data to analyze behavioral patterns and emotions, and use machine learning models to identify specific actions.

[0794] A "behavioral pattern" is a pattern identified as a series of actions or behaviors exhibited by an individual or group.

[0795] "Emotional state" refers to an individual's emotional state as analyzed from factors such as voice and facial expressions.

[0796] A "standard" is a predetermined guideline or scale used to determine what is normal and what is abnormal.

[0797] "Problematic behavior" refers to abnormal behavior that is detected as exceeding established criteria.

[0798] A "response flow" is a series of processes generated to guide appropriate response steps to detected problematic behaviors.

[0799] A "warning" is a notification or alert issued when a problematic behavior is detected.

[0800] A "terminal" is an electronic device used to receive and display information; examples include smartphones and tablets.

[0801] This invention describes an embodiment of a system aimed at improving security in public places. This system includes a video acquisition device, a server, and a terminal as its main components.

[0802] First, the video acquisition system uses surveillance cameras and sensors to collect real-time image data within public facilities. The collected data is encrypted for enhanced security and then transmitted to a server.

[0803] The server utilizes artificial intelligence analysis methods based on deep learning techniques to process received image data. This analysis uses machine learning libraries such as TensorFlow and PyTorch to analyze behavioral patterns and emotional states, and detect abnormal behavior. Based on the analysis results, the server generates a response flow that takes both behavior and emotional state into consideration, and creates a warning.

[0804] Next, the generated warning is sent to a device. This device could be a smartphone or tablet, and the user (security officer) who receives it can check the situation and take a quick response. This significantly improves security within public facilities.

[0805] For example, suspicious behavior in a shopping mall may be captured on surveillance cameras. If a particular individual is moving around unusually in a crowded area, this behavior can be quickly detected, and an appropriate warning can be sent to the person in charge, preventing the problem from occurring.

[0806] One example of a prompt message to be fed into a generation AI model is, "Please generate real-time alerts for the AI ​​that analyzes customer movements and facial expressions obtained from surveillance cameras and evaluates safety risks." This allows the AI ​​to make situational judgments based on on-site data and support appropriate responses.

[0807] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0808] Step 1:

[0809] The video acquisition device captures real-time image data within public facilities. This data is obtained through surveillance cameras and immediately encrypted. The encrypted image data is then ready to be sent to the server.

[0810] Step 2:

[0811] The server receives encrypted image data and performs data decryption. It then receives the decrypted image data as input and preprocesses it for use with a deep learning model. This preprocessing includes image normalization and noise reduction.

[0812] Step 3:

[0813] The server supplies pre-processed image data to the artificial intelligence analysis system. The analysis model uses frameworks such as TensorFlow or PyTorch to analyze behavioral patterns and emotional states. Here, multiple specific actions and changes in facial expression are extracted to distinguish between normal and abnormal behavior.

[0814] Step 4:

[0815] The server detects abnormal behavior and emotions based on the analysis results and generates a response flow. Within the generated AI model, the prompt message "Please have the AI ​​analyze customer behavior and facial expressions obtained from surveillance cameras and evaluate safety risks to generate alerts in real time." is used to automatically determine the appropriate warning content.

[0816] Step 5:

[0817] The generated alerts are sent to the terminal by the server. On the terminal, the alerts are notified to security personnel in real time. This allows users to quickly grasp the situation via their mobile devices and take a rapid response on-site.

[0818] 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.

[0819] 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.

[0820] 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.

[0821] 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.

[0822] 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.

[0823] 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.

[0824] 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.

[0825] 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.

[0826] 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."

[0827] 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.

[0828] 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.

[0829] 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.

[0830] 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.

[0831] 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.

[0832] 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.

[0833] 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.

[0834] 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.

[0835] 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.

[0836] 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.

[0837] 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.

[0838] 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.

[0839] The following is further disclosed regarding the embodiments described above.

[0840] (Claim 1)

[0841] A means for receiving video data acquired from a video acquisition device,

[0842] An AI analysis means analyzes behavioral patterns based on the aforementioned video data and identifies specific behaviors,

[0843] A means for detecting an identified behavior as a problem behavior if it exceeds a predetermined standard,

[0844] A means for generating a response flow and an alert based on detected problematic behavior,

[0845] A means for sending the aforementioned alert to the teacher's terminal,

[0846] A system that includes this.

[0847] (Claim 2)

[0848] The system according to claim 1, wherein the AI ​​analysis means analyzes behavioral patterns using a machine learning model.

[0849] (Claim 3)

[0850] The system according to claim 1, wherein the aforementioned alert includes details of the response flow and is notified to the teacher's terminal.

[0851] "Example 1"

[0852] (Claim 1)

[0853] A medium that receives digital video information acquired from a video acquisition device,

[0854] A means for collecting the aforementioned digital video information at regular intervals and transmitting it to a server via an encryption protocol,

[0855] An artificial intelligence analysis means that analyzes behavioral patterns based on the aforementioned digital video information and identifies specific behaviors,

[0856] A means for detecting an identified behavior as a problem behavior if it exceeds a predetermined standard,

[0857] A means for generating processing procedures and warnings based on detected problematic behavior,

[0858] A means for transmitting the aforementioned warning to the teacher's terminal,

[0859] A system that includes this.

[0860] (Claim 2)

[0861] The system according to claim 1, wherein the artificial intelligence analysis means analyzes behavioral patterns using a learning algorithm.

[0862] (Claim 3)

[0863] The system according to claim 1, wherein the aforementioned warning includes details of the processing procedure and is notified to the teacher's terminal.

[0864] "Application Example 1"

[0865] (Claim 1)

[0866] A device that receives information acquired from a video acquisition device,

[0867] An artificial intelligence analysis device that analyzes behavioral patterns based on the aforementioned information and identifies specific behaviors,

[0868] A device that detects identified behavior as problematic behavior if it exceeds a predetermined standard,

[0869] A device that generates response procedures and warnings based on detected problematic behavior,

[0870] A device that transmits the aforementioned warning to a portable terminal,

[0871] A system that includes this.

[0872] (Claim 2)

[0873] The artificial intelligence analysis device is the system according to claim 1, wherein the artificial intelligence analysis device analyzes behavioral patterns using a learning algorithm.

[0874] (Claim 3)

[0875] The system according to claim 1, wherein the aforementioned warning includes details of the response procedure and is notified to a portable terminal.

[0876] "Example 2 of combining an emotion engine"

[0877] (Claim 1)

[0878] A device that receives data acquired from a video acquisition device,

[0879] A device that encrypts and transmits the aforementioned data,

[0880] An analysis device that analyzes behavioral patterns based on the aforementioned data and identifies specific behaviors,

[0881] A device that recognizes emotions based on analyzed behavior,

[0882] A device that identifies behavioral and emotional information as a problem when it exceeds a certain threshold,

[0883] A device that generates responses and warnings based on identified problems,

[0884] A device that transmits the aforementioned warning to an educator's terminal,

[0885] A system that includes this.

[0886] (Claim 2)

[0887] The analysis device is the system according to claim 1, which analyzes behavior using a learning model.

[0888] (Claim 3)

[0889] The system according to claim 1, wherein the aforementioned warning includes details of the response and is notified to the educator's terminal.

[0890] "Application example 2 when combining with an emotional engine"

[0891] (Claim 1)

[0892] A means for receiving image data acquired from a video acquisition device,

[0893] An artificial intelligence analysis means analyzes behavioral patterns based on the aforementioned image data and identifies specific actions,

[0894] A means for detecting an identified operation as a problematic operation if it exceeds a predetermined criterion,

[0895] A means for generating a response flow and an alert based on detected problematic behavior and emotional state,

[0896] Means for sending the aforementioned warning to the terminal,

[0897] A system that includes this.

[0898] (Claim 2)

[0899] The system according to claim 1, wherein the artificial intelligence analysis means analyzes behavioral patterns and emotional states using a machine learning model.

[0900] (Claim 3)

[0901] The system according to claim 1, wherein the aforementioned warning includes details of the response flow and is notified to the responsible person's terminal. [Explanation of symbols]

[0902] 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. A device that receives information acquired from a video acquisition device, An artificial intelligence analysis device that analyzes behavioral patterns based on the aforementioned information and identifies specific behaviors, A device that detects identified behavior as problematic behavior if it exceeds a predetermined standard, A device that generates response procedures and warnings based on detected problematic behavior, A device that transmits the aforementioned warning to a portable terminal, A system that includes this.

2. The artificial intelligence analysis device is the system according to claim 1, wherein the artificial intelligence analysis device analyzes behavioral patterns using a learning algorithm.

3. The system according to claim 1, wherein the aforementioned warning includes details of the response procedure and is notified to a portable terminal.

Images