system

Abstract

We provide the system. [Solution] A means for receiving video from a video acquisition device, A means for identifying behavioral patterns using artificial intelligence for analyzing the aforementioned video, If the identified behavioral pattern is determined to be abnormal, means for generating warning information, Means for transmitting the aforementioned warning information to a management 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 persona chatbot control method performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of the chatbot's character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. 【Prior Art Documents】 【Patent Documents】 【0003】 【Patent Document 1】 Japanese Unexamined Patent Application Publication No. 2022-180282 【Summary of the Invention】 【Problems to be Solved by the Invention】 【0004】 There is a problem that it is difficult to prevent and quickly respond to bullying, violence, and other problem behaviors that may occur during time periods when teachers in elementary, junior high, and senior high schools cannot see, such as self-study time and break time.Conventional methods have difficulty detecting these problems in real time and quickly presenting specific countermeasures. 【Means for Solving the Problems】 【0005】 This invention provides a system that analyzes real-time video obtained from a video acquisition device and automatically detects abnormal behavior using artificial intelligence. Specifically, it identifies behavioral patterns in the acquired video and immediately sends warning information to a management terminal if an abnormal behavioral pattern is confirmed. This warning information includes detailed data on the behavior recognized as abnormal and provides means to support teachers and staff in responding quickly. 【0006】 A "video acquisition device" is a device installed within the school that captures video in real time and outputs it as digital data. 【0007】 "Artificial intelligence" is a general term for programs and algorithms in computer systems that mimic human intelligent processing to efficiently accomplish specific tasks. 【0008】 "Behavioral patterns" refer to a sequence of movements and characteristics of a person detected in video footage, and serve as criteria for identifying abnormal or normal behavior. 【0009】 "Warning information" refers to notifications or data generated when the system detects abnormal behavior, indicating a situation requiring emergency action. 【0010】 A "management terminal" is a device used to operate and monitor the system, and is used to receive warning information and issue instructions for action. [Brief explanation of the drawing] 【0011】 [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4]This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention] 【0012】 Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings. 【0013】 First, let's explain the terminology used in the following explanation. 【0014】 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. 【0015】 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. 【0016】 In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs, various parameters, and the like. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like. 【0017】 In the following embodiments, the numbered communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark), and the like. 【0018】 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." 【0019】 [First Embodiment] 【0020】 Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment. 【0021】 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. 【0022】 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). 【0023】 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. 【0024】 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. 【0025】 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. 【0026】 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. 【0027】 Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14. 【0028】 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. 【0029】 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. 【0030】 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. 【0031】 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". 【0032】 This invention is a system that analyzes video data obtained from multiple video acquisition devices installed within a school in real time to detect abnormal behavior. To achieve this, a server constantly receives data from the video acquisition devices and analyzes that data using a dedicated artificial intelligence program. 【0033】 The server analyzes each frame in the video and uses artificial intelligence to extract multiple features. Based on these features, it identifies behavioral patterns and detects potentially abnormal behavior. For example, if the distance between students suddenly shortens or unnatural movements continue, the server automatically flags that behavior as potentially bullying or violence. 【0034】 If an anomaly is detected, the server immediately generates warning information and sends it to the management terminal. The warning information includes the time and location of the abnormal behavior, as well as an attached video clip, designed to allow teachers and administrators to quickly understand the situation. 【0035】 Users receive warning information on their own devices and take necessary actions. For example, upon receiving a warning, a user can check the exact situation on-site and issue instructions for appropriate intervention. This system helps improve school safety even without direct teacher supervision at specific times. 【0036】 As described above, the embodiments of the present invention enable real-time monitoring and rapid response, and support the prevention of problematic behavior in educational settings. 【0037】 The following describes the processing flow. 【0038】 Step 1: 【0039】 The server receives video data in real time from each video acquisition device installed within the school. The video is transmitted in high resolution in a stream format, and the server is ready for initial processing. 【0040】 Step 2: 【0041】 The server preprocesses the received video data and converts it into a format suitable for analysis. Preprocessing includes noise reduction, image resolution adjustment, and extraction of important frames. This preprocessing prepares the data for smoother subsequent analysis. 【0042】 Step 3: 【0043】 The server sends pre-processed video data to an artificial intelligence module, which performs motion analysis on each frame. The AI ​​detects changes in the students' movements and positions and compares them with pre-set abnormal behavior patterns to determine whether or not there is an abnormality. 【0044】 Step 4: 【0045】 When abnormal behavior is detected, the server focuses its analysis on the relevant video portion to pinpoint the exact time and location where the anomaly occurred. It then automatically generates detailed data on the abnormal behavior and compiles it into a warning. 【0046】 Step 5: 【0047】 The server sends the generated warning information to the management terminal. This warning information includes the specific details of the anomaly and suggested countermeasures as needed. This provides administrators and teachers with clues to quickly understand the situation and take appropriate action. 【0048】 Step 6: 【0049】 Users receive and review warning information on their devices. By playing video clips, they can visually understand the situation on-site and issue instructions for prompt intervention and support. 【0050】 (Example 1) 【0051】 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." 【0052】 There is a need to detect abnormal behavior and safety issues within facilities in real time and respond to them promptly. However, conventional systems require constant manual monitoring, which makes efficient operation difficult. 【0053】 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. 【0054】 In this invention, the server includes means for receiving data from a camera via a computer system, means for detecting the position and movement of a person using image analysis technology based on the data, and means for inputting the generated data into an artificial intelligence model and identifying behavioral patterns. This makes it possible to automatically detect abnormal behavior and safety issues within a facility in real time and respond to them early. 【0055】 A "computer system" is a collection of hardware and software for receiving, processing, and analyzing digital data. 【0056】 A "filming device" is a device used to acquire video data in a specific space or environment. 【0057】 "Data" refers to video information obtained through a camera or camera, which is used for analysis and decision-making. 【0058】 "Image analysis technology" is a general term for methods and techniques used to extract useful information from video data and identify the position and movement of people and objects. 【0059】 An "artificial intelligence model" is a mathematical model trained using machine learning algorithms to identify specific patterns or structures. 【0060】 A "behavioral pattern" is a set of actions or behaviors that describe a series of actions or actions observed in a person or object. 【0061】 "Alert information" is data generated to notify of anomalies or emergencies, and is information that helps administrators respond quickly. 【0062】 A "management device" is a terminal or device used to receive alert information and display and verify its contents. 【0063】 This invention aims to implement a real-time monitoring system for safety management within a facility. The server is constantly connected via a network interface to receive video data from multiple cameras located within the facility. This data reception is designed to be high-speed and real-time. 【0064】 When video data is received by the server, the server uses image analysis libraries such as OpenCV to identify people and objects in the video and analyze their position and movement. This analysis generates behavioral patterns of people. 【0065】 These behavioral patterns are input into an artificial intelligence model using a machine learning framework such as TENSORFLOW®. The server uses this model to identify normal and abnormal behavioral patterns. If abnormal behavior is detected, the server immediately generates alert information and sends it to the management device. This alert information includes the date, time, and location of the abnormal behavior, as well as any relevant video clips, enabling administrators to respond quickly. 【0066】 The administrator, acting as the user, can receive alert information on their device and view the details. For example, if they are notified of a conflict as an abnormal behavior, the user can review the video clip and intervene quickly on-site. 【0067】 As a concrete example, by providing the AI ​​model with the instruction, "Develop a system that analyzes footage from school surveillance cameras and automatically detects abnormal behavior," as a prompt to test the system's operation, it becomes possible to design a more effective system. 【0068】 This system aims to improve facility safety by reducing the burden of manual monitoring and automating safety management. 【0069】 The flow of the specific processing in Example 1 will be explained using Figure 11. 【0070】 Step 1: 【0071】 The server receives real-time video data from the facility's imaging equipment via the network. The input is video data from the imaging equipment, and the output is analyzable video frames. This video data is temporarily stored for use in later analysis steps. Specifically, the server monitors a designated IP address and port to ensure it receives the data stream. 【0072】 Step 2: 【0073】 The server divides the received video data into frames and performs image analysis. The input is video frames, and the output is the position information of people and objects extracted from each frame. This uses image analysis libraries such as OpenCV. Specifically, the server applies an object detection algorithm to the video frames to identify the outlines and movements of people. 【0074】 Step 3: 【0075】 The server uses an artificial intelligence model to identify behavioral patterns based on extracted location information. The input is location information, and the output is the behavioral pattern of each person. Normal and abnormal behavior are identified using a model trained with a framework such as TensorFlow. Specifically, the server inputs the current data into a pre-trained model and performs pattern matching. 【0076】 Step 4: 【0077】 The server determines whether the identified behavioral pattern is abnormal. The input is the behavioral pattern, and the output is a flag indicating whether it was determined to be abnormal. Specific thresholds or conditions are used as the criteria for this determination. The server detects abnormal behavior according to the configured rules and prepares for the next step. 【0078】 Step 5: 【0079】 The server generates alert information when an anomaly is detected and sends it to the management device. The input is a flag indicating the abnormal behavior, and the output is an alert information packet. This information includes the date and time of the occurrence, the location, and a related video clip. Specifically, the server encodes the data into a transmission format and sends it to the address of the specified management device. 【0080】 Step 6: 【0081】 The user checks the alert information received by the management device and takes the necessary actions. The input is the alert information, and the output is the instructions and execution of the response. Specifically, the user assesses the situation based on the provided information and makes decisions for appropriate on-site response. 【0082】 (Application Example 1) 【0083】 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." 【0084】 In modern educational settings, ensuring student safety, especially within schools, is crucial, but constant monitoring is difficult due to limitations in human resources. Therefore, there is a need for a system that can detect abnormal behavior in real time and respond quickly. A particular challenge is creating a system that can instantly send notifications to individual devices, enabling educators to intervene promptly. 【0085】 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. 【0086】 In this invention, the server includes means for receiving visual information from video acquisition means, means for identifying complex behavioral patterns using artificial intelligence for analyzing the visual information, means for generating a warning signal when the identified behavioral pattern is determined to be outside the standard, and means for transmitting a notification to an individual device based on the warning signal. This makes it possible to monitor abnormal student behavior in educational settings in real time and enable rapid intervention. 【0087】 "Image acquisition means" is a general term for a group of devices installed to capture visual information. 【0088】 "Visual information" refers to all image data and video data obtained from image acquisition methods. 【0089】 "Artificial intelligence" refers to a system equipped with a process that analyzes and makes decisions based on specific information using machine learning and deep learning technologies. 【0090】 A "behavioral pattern" refers to a series of characteristics and tendencies in human actions extracted from visual information. 【0091】 A "warning signal" is data generated to alert someone when a behavioral pattern outside the established criteria is detected. 【0092】 An "individual device" refers to a terminal or device used by a specific user. 【0093】 "Out of bounds" refers to a state or situation that deviates from the pre-defined normal range. 【0094】 "Means for transmitting notifications" refers to communication technologies and protocols used to quickly transmit warning signals to individual devices. 【0095】 To implement this invention, the server receives visual information from the video acquisition means and analyzes that visual information. For the analysis, artificial intelligence frameworks such as TensorFlow and PyTorch are used to activate machine learning models and identify behavioral patterns. If the server determines that the identified behavior is outside the standard, it generates a warning signal. This signal is transmitted to the educator's terminal by a communication module that immediately sends notifications to individual devices. 【0096】 To explain this system in more detail, for example, if suspicious activity is detected in a school hallway, the server recognizes the activity as outside the established criteria and generates a warning that suspicious activity has been detected in the second-floor hallway. The warning is sent to teachers' smartphones and tablets, enabling quick situation assessment and countermeasures. 【0097】 The hardware used includes numerous camera devices for acquiring visual information, and network communication utilizes an internet connection. The software includes a camera management system and an AI analysis program. This system enables real-time monitoring and early detection of anomalies in educational settings. 【0098】 An example of a prompt message is: "Identify sudden changes in distance in the hallway and detect suspicious activity. Generate a time- and location-based alert notification." This allows the system to support safety in educational settings. 【0099】 The flow of a specific process in Application Example 1 will be explained using Figure 12. 【0100】 Step 1: 【0101】 The server receives visual information from video acquisition devices installed within the school. The input is video data transmitted in real time from the cameras, and the output is raw data stored in the server's internal temporary memory. 【0102】 Step 2: 【0103】 The server divides the received visual information into frames and extracts features from each frame. The input is the raw data in temporary memory obtained in step 1. The output is a dataset of features corresponding to each frame. Specifically, it performs object detection and motion analysis using libraries such as TensorFlow and PyTorch. 【0104】 Step 3: 【0105】 The server applies an artificial intelligence model based on the extracted features to identify behavioral patterns. The input is the feature dataset from step 2, and the output is the classification result of the corresponding behavioral patterns. In specific actions, a pre-trained generative AI model is used to classify whether an action is abnormal or not. 【0106】 Step 4: 【0107】 If the identification result is outside the criteria, the server generates a warning signal, which includes the necessary detailed data. The input is the classification result obtained in step 3. The output is a data packet containing the warning signal and its detailed information. Specific operation involves detailed settings including the type of anomaly, the time of occurrence, and the location. 【0108】 Step 5: 【0109】 The server sends the generated warning signal to the educator's terminal. The input is the data packet generated in step 4. The output is embodied as a warning message displayed on the terminal. Specifically, data transmission over the internet and push notifications are used. 【0110】 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. 【0111】 This invention relates to a system that analyzes real-time video footage obtained from multiple video acquisition devices installed within a school and uses artificial intelligence and an emotion engine to detect abnormal behavior and emotions. This system processes video data in real time, automatically detects bullying and violent behavior that might be missed by normal monitoring, and provides this information, along with emotional data, to administrators. 【0112】 The server continuously receives data from the video acquisition device and analyzes the behavior of people in the video using artificial intelligence technology. In addition to behavioral patterns, it uses an emotion engine to recognize the user's emotional state from facial expressions and body movements. This recognition result reinforces the analysis of behavioral patterns and improves the accuracy of detecting abnormal behavior. 【0113】 When abnormal behavior is detected, the server generates detailed warning information, including the results of emotion recognition. This warning information includes data such as the time and location of the abnormality and the emotional state of the students involved, and is sent to the management terminal for necessary action. 【0114】 Users (teachers or administrators) who receive warning information can review the warning on their devices and quickly determine appropriate action based on the details of the abnormal behavior and the emotions involved. For example, if a student is expressing feelings of fear or sadness, the user can immediately go to the scene to assess the situation and determine if counseling is necessary. 【0115】 In summary, the embodiments of the present invention enable advanced monitoring and response that takes into account both abnormal behavior and emotions, and are a system that effectively supports school safety and student welfare. 【0116】 The following describes the processing flow. 【0117】 Step 1: 【0118】 The server receives video data in real time from multiple video acquisition devices installed on campus. This data is temporarily stored in a large-capacity storage device for subsequent analysis. 【0119】 Step 2: 【0120】 The server preprocesses the received video and converts it into a format suitable for analysis. For example, it adjusts the image resolution and removes noise as needed. It also improves analysis efficiency by selecting important frames. 【0121】 Step 3: 【0122】 The server sends pre-processed video data to an artificial intelligence module to identify behavioral patterns. The AI ​​analyzes the movements of people in the video and determines whether the behavior is normal or abnormal based on predefined criteria. 【0123】 Step 4: 【0124】 The server uses an emotion engine to analyze the facial expressions and body movements of people in the video and recognize their emotional state. This recognition result complements the detection of anomalies in behavioral patterns. 【0125】 Step 5: 【0126】 The server generates detailed warning information based on the detected abnormal behavior and emotion recognition results. This warning includes the specific time and location of the anomaly detection, as well as the emotional state of the person involved. 【0127】 Step 6: 【0128】 The server sends the generated warning information to the management terminal in real time. This information is presented to the user when a quick response is required. 【0129】 Step 7: 【0130】 After receiving an alert on their device, users can review video clips and recognized emotion data. Based on this, users can make decisions regarding rapid intervention at the scene and appropriate countermeasures. 【0131】 (Example 2) 【0132】 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." 【0133】 In schools and public facilities, conventional monitoring systems have struggled to quickly detect and appropriately respond to abnormal behavior or emotional changes that might be overlooked. This has led to delays in the early detection and intervention of problematic behavior, resulting in situations where the safety of students and users cannot be adequately protected. 【0134】 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. 【0135】 In this invention, the server includes means for acquiring image information from a video input device, means for identifying behavioral patterns using a machine learning model for analyzing the image information, and means for generating emotionally analyzed warning information when the behavioral pattern is determined to be abnormal. This enables rapid detection of abnormal behavior and the provision of warnings accompanied by emotional information. 【0136】 A "video input device" refers to a set of multiple shooting units installed within a facility, which are used to acquire image information in real time. 【0137】 "Image information" refers to visual data acquired from video input devices and serves as fundamental data for analyzing a person's actions and circumstances. 【0138】 A "machine learning model" refers to an algorithm used to learn data patterns and identify actions in video footage. 【0139】 "Behavioral patterns" refer to the sequence or tendency of a person's actions identified from image information, and serve as a criterion for judging abnormal behavior. 【0140】 "Emotional analysis" refers to the process of determining a person's emotional state, such as joy, anger, sadness, or happiness, from their facial expressions and actions. 【0141】 "Warning information" refers to notification data generated when abnormal behavior or a specific emotional state is detected, and which is transmitted to the management device. 【0142】 A "management device" refers to a device that receives and displays warning information and supports decisions for taking action. 【0143】 In this invention, the system is implemented based on the following configuration and procedure. 【0144】 The server acquires image information in real time from multiple video input devices installed throughout the school. This makes it possible to continuously collect video data from various areas such as hallways, classrooms, and the gymnasium. Standard surveillance cameras and other imaging units are used to acquire the image information. 【0145】 The server runs a machine learning model to analyze the acquired image information. This model uses a deep learning framework (e.g., TensorFlow or PyTorch) to identify behavioral patterns of people in the video. Based on this behavioral data, the server detects abnormal behavior. OpenCV and other tools can also be used in this process to perform efficient video analysis. 【0146】 Furthermore, the server identifies facial expressions and body movements to recognize emotional states in order to perform emotion analysis. This emotion recognition utilizes cloud-based service APIs (e.g., Emotion API and Google® Cloud Vision API) to tag emotions quickly and accurately. This enables the combination of behavioral patterns and emotional information, significantly improving the accuracy of warnings against abnormal behavior. 【0147】 If a warning is deemed necessary, the server generates warning information and sends it to the management terminal. The management terminal displays the warning information to the user and provides relevant detailed data (e.g., the time and location of the anomaly, the emotional state of the people involved, etc.). 【0148】 Users (teachers or administrators) can use this information to quickly decide on a course of action. For example, a user can receive a warning notification, go to the scene to check the situation, and determine the need for counseling based on the student's emotional state. 【0149】 An example of a prompt might be, "Please describe the steps to automate a system that sends a notification if a student in a video appears to have a sad expression." This prompt is used to refine anomaly detection by linking emotional information with behavioral patterns. 【0150】 As described in detail above, the present invention enables the construction of a more effective monitoring system and enhances safety and student welfare in the school environment. 【0151】 The flow of the specific processing in Example 2 will be explained using Figure 13. 【0152】 Step 1: 【0153】 The server acquires image information in real time from video input devices installed within the school. The input is video data of students and locations, and the output is clear, temporally continuous video data to enable analysis. Specifically, the server periodically polls the video stream from each camera to confirm stable data reception. 【0154】 Step 2: 【0155】 The server analyzes the acquired image information using a machine learning model. The input is a video stream, and the output is the result of identifying the dynamic behavioral patterns contained within it. Specifically, the server runs a deep learning model using TensorFlow to classify human movements in the video and understand the changes in general behavioral patterns. 【0156】 Step 3: 【0157】 After identifying behavioral patterns, the server performs sentiment analysis. The input is the identified behavioral patterns and corresponding video frames, and the output is tag information indicating the emotional state at that time. The server calls the Google Cloud Vision API to analyze facial expressions in the video and quantify the emotional tendencies. 【0158】 Step 4: 【0159】 The server detects anomalies based on the analyzed behavioral patterns and emotional states. The input is the analysis results from steps 2 and 3, and the output is information regarding whether an anomaly was detected and the degree of that anomaly. Specifically, the server uses an algorithm that compares the current data with past data to determine the anomaly. 【0160】 Step 5: 【0161】 When an anomaly is detected, the server generates warning information and sends it to the management terminal. The input is the anomaly detection result, and the output is a warning message containing details of the anomaly. Specifically, the server packages and sends detailed data of the time, location, and individuals involved in the anomaly. 【0162】 Step 6: 【0163】 The user receives alerts on a management terminal and checks the details. The input is the alert information sent from the server, and the output is the action plan for response. Specifically, the user analyzes the detailed alert information from the dashboard displayed on the terminal and decides on the appropriate response, such as on-site intervention or contacting relevant parties. 【0164】 (Application Example 2) 【0165】 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". 【0166】 In recent years, security in public and commercial facilities has become increasingly important, but conventional monitoring systems have challenges in detecting abnormal behavior in real time and capturing emotional changes associated with that behavior. Furthermore, when anomalies are detected, the lack of rapid and accurate information provision can delay effective responses. To address these challenges, an advanced monitoring system is needed that can analyze abnormal behavior and associated emotional information in real time and immediately notify relevant parties. 【0167】 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. 【0168】 In this invention, the server includes means for receiving visual data and detecting behavioral patterns using machine learning to analyze it; means for generating warning information when the detected behavioral pattern is determined to be abnormal; and means for reinforcing the analysis results of the behavioral pattern using an emotion analysis engine to recognize emotional states. This makes it possible to quickly detect changes in emotion associated with abnormal behavior and provide warning information at an appropriate time. 【0169】 A "video acquisition device" is a device installed to record visual data, and includes surveillance cameras and sensor devices. 【0170】 "Visual data" refers to image and video information obtained from video acquisition devices, and is the data that is analyzed. 【0171】 "Machine learning" is a type of artificial intelligence technology that learns patterns and features based on data and uses them for inference. 【0172】 A "behavioral pattern" refers to a specific form of movement or action of a person or object, and is identified through analysis. 【0173】 "An abnormal state" refers to a condition that differs from the normal state or expected behavior, and signifies an event that requires attention and monitoring. 【0174】 "Warning information" is information generated to alert of the occurrence of an abnormal situation, and includes detailed behavioral and emotional data. 【0175】 An "emotion analysis engine" is software or hardware equipped with technology to recognize emotional states from a person's facial expressions and movements in video data. 【0176】 A "management terminal" is a computer or device used by a system administrator to receive information and verify and process monitoring results. 【0177】 The system realizing this invention uses a machine learning model and sentiment analysis engine installed on a server to receive and analyze real-time visual data obtained from a video acquisition device. After acquiring the visual data, the server uses a machine learning algorithm to detect target behavioral patterns. In this process, open-source machine learning libraries such as TensorFlow are used. 【0178】 The detected behavioral patterns are analyzed using an emotion analysis engine to recognize the target's emotional state by analyzing facial expressions and body movements, and this is then incorporated into the analysis results. The server combines this information and generates warning information if it determines that an abnormality has occurred. This warning information includes the time and location of the abnormal behavior, the associated emotional state, etc., and is sent to the management terminal. The administrator can receive the warning information on this terminal and take countermeasures as needed. 【0179】 As a concrete example, consider a scenario where a surveillance system is installed in a shopping mall. For instance, if abnormal behavior is detected in an area where congestion is expected during a large-scale event, an alert is immediately sent to the security guard's management terminal, enabling a swift response. At this time, if stress or anxiety is identified through emotion analysis, even more appropriate countermeasures can be taken. 【0180】 An example of a prompt for a generative AI model is: "Develop a video-based abnormal behavior and emotion detection system. Also, enhance the necessary features to ensure customer safety." Based on this prompt, the generative AI model can suggest the necessary features and use this information to design the system. 【0181】 The flow of a specific process in Application Example 2 will be explained using Figure 14. 【0182】 Step 1: 【0183】 The server receives visual data in real time from video acquisition devices. The input is visual data from surveillance cameras, etc., and the output is video information to be analyzed. This acquired data is temporarily stored in a buffer for analysis. 【0184】 Step 2: 【0185】 The server uses machine learning algorithms to analyze the visual data stored in the buffer. The input is the visual data from step 1, and the output is the identified behavioral patterns. This process uses technologies such as TensorFlow to analyze the detected movements and actions. 【0186】 Step 3: 【0187】 The server uses an emotion analysis engine to augment the results of the behavioral pattern analysis. The input is the behavioral pattern obtained in step 2, and the output is the enhanced analysis result, including the emotional state. Here, emotions are inferred based on facial expressions and limb movements, and the data is enriched. 【0188】 Step 4: 【0189】 The server generates warning information if it detects an anomaly. The input is the analysis result from step 3, and the output is the warning information. This information includes the time, location, and emotional state at which the anomaly was detected. 【0190】 Step 5: 【0191】 The server sends the generated warning information to the management terminal. The input is the warning information from step 4, and the output is the alert display on the management terminal. Here, information is transmitted in real time using a communication protocol. 【0192】 Step 6: 【0193】 The user (administrator or security guard) checks the warning information on the management terminal and takes appropriate action if necessary. The input is the alert on the management terminal, and the output is the implementation of the appropriate countermeasure. In this step, on-site verification and instructions are given based on the notified information. 【0194】 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. 【0195】 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. 【0196】 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. 【0197】 [Second Embodiment] 【0198】 Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment. 【0199】 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. 【0200】 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). 【0201】 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. 【0202】 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. 【0203】 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). 【0204】 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. 【0205】 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. 【0206】 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. 【0207】 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. 【0208】 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. 【0209】 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". 【0210】 This invention is a system that analyzes video data obtained from multiple video acquisition devices installed within a school in real time to detect abnormal behavior. To achieve this, a server constantly receives data from the video acquisition devices and analyzes that data using a dedicated artificial intelligence program. 【0211】 The server analyzes each frame in the video and uses artificial intelligence to extract multiple features. Based on these features, it identifies behavioral patterns and detects potentially abnormal behavior. For example, if the distance between students suddenly shortens or unnatural movements continue, the server automatically flags that behavior as potentially bullying or violence. 【0212】 If an anomaly is detected, the server immediately generates warning information and sends it to the management terminal. The warning information includes the time and location of the abnormal behavior, as well as an attached video clip, designed to allow teachers and administrators to quickly understand the situation. 【0213】 Users receive warning information on their own devices and take necessary actions. For example, upon receiving a warning, a user can check the exact situation on-site and issue instructions for appropriate intervention. This system helps improve school safety even without direct teacher supervision at specific times. 【0214】 As described above, the embodiments of the present invention enable real-time monitoring and rapid response, and support the prevention of problematic behavior in educational settings. 【0215】 The following describes the processing flow. 【0216】 Step 1: 【0217】 The server receives video data in real time from each video acquisition device installed within the school. The video is transmitted in high resolution in a stream format, and the server is ready for initial processing. 【0218】 Step 2: 【0219】 The server preprocesses the received video data and converts it into a format suitable for analysis. Preprocessing includes noise reduction, image resolution adjustment, and extraction of important frames. This preprocessing prepares the data for smoother subsequent analysis. 【0220】 Step 3: 【0221】 The server sends pre-processed video data to an artificial intelligence module, which performs motion analysis on each frame. The AI ​​detects changes in the students' movements and positions and compares them with pre-set abnormal behavior patterns to determine whether or not there is an abnormality. 【0222】 Step 4: 【0223】 When abnormal behavior is detected, the server focuses its analysis on the relevant video portion to pinpoint the exact time and location where the anomaly occurred. It then automatically generates detailed data on the abnormal behavior and compiles it into a warning. 【0224】 Step 5: 【0225】 The server sends the generated warning information to the management terminal. This warning information includes the specific details of the anomaly and suggested countermeasures as needed. This provides administrators and teachers with clues to quickly understand the situation and take appropriate action. 【0226】 Step 6: 【0227】 Users receive and review warning information on their devices. By playing video clips, they can visually understand the situation on-site and issue instructions for prompt intervention and support. 【0228】 (Example 1) 【0229】 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." 【0230】 There is a need to detect abnormal behavior and safety issues within facilities in real time and respond to them promptly. However, conventional systems require constant manual monitoring, which makes efficient operation difficult. 【0231】 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. 【0232】 In this invention, the server includes means for receiving data from a camera via a computer system, means for detecting the position and movement of a person using image analysis technology based on the data, and means for inputting the generated data into an artificial intelligence model and identifying behavioral patterns. This makes it possible to automatically detect abnormal behavior and safety issues within a facility in real time and respond to them early. 【0233】 A "computer system" is a collection of hardware and software for receiving, processing, and analyzing digital data. 【0234】 A "filming device" is a device used to acquire video data in a specific space or environment. 【0235】 "Data" refers to video information obtained through a camera or camera, which is used for analysis and decision-making. 【0236】 "Image analysis technology" is a general term for methods and techniques used to extract useful information from video data and identify the position and movement of people and objects. 【0237】 An "artificial intelligence model" is a mathematical model trained using machine learning algorithms to identify specific patterns or structures. 【0238】 A "behavioral pattern" is a set of actions or behaviors that describe a series of actions or actions observed in a person or object. 【0239】 "Alert information" is data generated to notify of anomalies or emergencies, and is information that helps administrators respond quickly. 【0240】 A "management device" is a terminal or device used to receive alert information and display and verify its contents. 【0241】 This invention aims to implement a real-time monitoring system for safety management within a facility. The server is constantly connected via a network interface to receive video data from multiple cameras located within the facility. This data reception is designed to be high-speed and real-time. 【0242】 When video data is received by the server, the server uses image analysis libraries such as OpenCV to identify people and objects in the video and analyze their position and movement. This analysis generates behavioral patterns of people. 【0243】 These behavioral patterns are fed into an artificial intelligence model using a machine learning framework such as TensorFlow. The server uses this model to identify normal and abnormal behavioral patterns. If abnormal behavior is detected, the server immediately generates an alert and sends it to the management device. This alert includes the date, time, and location of the abnormal behavior, as well as any relevant video clips, enabling administrators to respond quickly. 【0244】 The administrator, acting as the user, can receive alert information on their device and view the details. For example, if they are notified of a conflict as an abnormal behavior, the user can review the video clip and intervene quickly on-site. 【0245】 As a concrete example, by providing the AI ​​model with the instruction, "Develop a system that analyzes footage from school surveillance cameras and automatically detects abnormal behavior," as a prompt to test the system's operation, it becomes possible to design a more effective system. 【0246】 This system aims to improve facility safety by reducing the burden of manual monitoring and automating safety management. 【0247】 The flow of the specific processing in Example 1 will be explained using Figure 11. 【0248】 Step 1: 【0249】 The server receives real-time video data from the facility's imaging equipment via the network. The input is video data from the imaging equipment, and the output is analyzable video frames. This video data is temporarily stored for use in later analysis steps. Specifically, the server monitors a designated IP address and port to ensure it receives the data stream. 【0250】 Step 2: 【0251】 The server divides the received video data into frames and performs image analysis. The input is video frames, and the output is the position information of people and objects extracted from each frame. This uses image analysis libraries such as OpenCV. Specifically, the server applies an object detection algorithm to the video frames to identify the outlines and movements of people. 【0252】 Step 3: 【0253】 The server uses an artificial intelligence model to identify behavioral patterns based on extracted location information. The input is location information, and the output is the behavioral pattern of each person. Normal and abnormal behavior are identified using a model trained with a framework such as TensorFlow. Specifically, the server inputs the current data into a pre-trained model and performs pattern matching. 【0254】 Step 4: 【0255】 The server determines whether the identified behavioral pattern is abnormal. The input is the behavioral pattern, and the output is a flag indicating whether it was determined to be abnormal. Specific thresholds or conditions are used as the criteria for this determination. The server detects abnormal behavior according to the configured rules and prepares for the next step. 【0256】 Step 5: 【0257】 The server generates alert information when an anomaly is detected and sends it to the management device. The input is a flag indicating the abnormal behavior, and the output is an alert information packet. This information includes the date and time of the occurrence, the location, and a related video clip. Specifically, the server encodes the data into a transmission format and sends it to the address of the specified management device. 【0258】 Step 6: 【0259】 The user checks the alert information received by the management device and takes the necessary actions. The input is the alert information, and the output is the instructions and execution of the response. Specifically, the user assesses the situation based on the provided information and makes decisions for appropriate on-site response. 【0260】 (Application Example 1) 【0261】 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." 【0262】 In modern educational settings, ensuring student safety, especially within schools, is crucial, but constant monitoring is difficult due to limitations in human resources. Therefore, there is a need for a system that can detect abnormal behavior in real time and respond quickly. A particular challenge is creating a system that can instantly send notifications to individual devices, enabling educators to intervene promptly. 【0263】 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. 【0264】 In this invention, the server includes means for receiving visual information from video acquisition means, means for identifying complex behavioral patterns using artificial intelligence for analyzing the visual information, means for generating a warning signal when the identified behavioral pattern is determined to be outside the standard, and means for transmitting a notification to an individual device based on the warning signal. This makes it possible to monitor abnormal student behavior in educational settings in real time and enable rapid intervention. 【0265】 "Image acquisition means" is a general term for a group of devices installed to capture visual information. 【0266】 "Visual information" refers to all image data and video data obtained from image acquisition methods. 【0267】 "Artificial intelligence" refers to a system equipped with a process that analyzes and makes decisions based on specific information using machine learning and deep learning technologies. 【0268】 A "behavioral pattern" refers to a series of characteristics and tendencies in human actions extracted from visual information. 【0269】 A "warning signal" is data generated to alert someone when a behavioral pattern outside the established criteria is detected. 【0270】 An "individual device" refers to a terminal or device used by a specific user. 【0271】 "Out of bounds" refers to a state or situation that deviates from the pre-defined normal range. 【0272】 "Means for transmitting notifications" refers to communication technologies and protocols used to quickly transmit warning signals to individual devices. 【0273】 To implement this invention, the server receives visual information from the video acquisition means and analyzes that visual information. For the analysis, artificial intelligence frameworks such as TensorFlow and PyTorch are used to activate machine learning models and identify behavioral patterns. If the server determines that the identified behavior is outside the standard, it generates a warning signal. This signal is transmitted to the educator's terminal by a communication module that immediately sends notifications to individual devices. 【0274】 To explain this system in more detail, for example, if suspicious activity is detected in a school hallway, the server recognizes the activity as outside the established criteria and generates a warning that suspicious activity has been detected in the second-floor hallway. The warning is sent to teachers' smartphones and tablets, enabling quick situation assessment and countermeasures. 【0275】 The hardware used includes numerous camera devices for acquiring visual information, and network communication utilizes an internet connection. The software includes a camera management system and an AI analysis program. This system enables real-time monitoring and early detection of anomalies in educational settings. 【0276】 An example of a prompt message is: "Identify sudden changes in distance in the hallway and detect suspicious activity. Generate a time- and location-based alert notification." This allows the system to support safety in educational settings. 【0277】 The flow of a specific process in Application Example 1 will be explained using Figure 12. 【0278】 Step 1: 【0279】 The server receives visual information from video acquisition devices installed within the school. The input is video data transmitted in real time from the cameras, and the output is raw data stored in the server's internal temporary memory. 【0280】 Step 2: 【0281】 The server divides the received visual information into frames and extracts feature amounts from each frame. The input is the raw data in the temporary memory obtained in step 1. The output is a dataset of feature amounts corresponding to each frame. As specific operations, object detection and motion analysis are performed using libraries such as TensorFlow and PyTorch. 【0282】 Step 3: 【0283】 The server applies an artificial intelligence model based on the extracted feature amounts to identify behavior patterns. The input is the feature amount dataset in step 2, and the output is the classification result of the corresponding behavior pattern. In a specific operation, a pre-trained generative AI model is utilized to perform classification of whether it is abnormal or not. 【0284】 Step 4: 【0285】 If the identification result is out of the standard, the server generates a warning signal and includes the necessary detailed data. The input is the classification result obtained in step 3. The output is a data packet including the warning signal and its detailed information. In specific operations, detailed settings including the type of abnormality, occurrence time, and location are performed. 【0286】 Step 5: 【0287】 The server transmits the generated warning signal to the educator's terminal. The input is the data packet generated in step 4. The output is embodied as a warning message displayed on the terminal. As specific operations, data transmission via the Internet and push notifications are utilized. 【0288】 Furthermore, an emotion engine for estimating the user's emotion may be combined. That is, the specific processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform specific processing using the user's emotion. 【0289】 This invention relates to a system that analyzes real-time video footage obtained from multiple video acquisition devices installed within a school and uses artificial intelligence and an emotion engine to detect abnormal behavior and emotions. This system processes video data in real time, automatically detects bullying and violent behavior that might be missed by normal monitoring, and provides this information, along with emotional data, to administrators. 【0290】 The server continuously receives data from the video acquisition device and analyzes the behavior of people in the video using artificial intelligence technology. In addition to behavioral patterns, it uses an emotion engine to recognize the user's emotional state from facial expressions and body movements. This recognition result reinforces the analysis of behavioral patterns and improves the accuracy of detecting abnormal behavior. 【0291】 When abnormal behavior is detected, the server generates detailed warning information, including the results of emotion recognition. This warning information includes data such as the time and location of the abnormality and the emotional state of the students involved, and is sent to the management terminal for necessary action. 【0292】 Users (teachers or administrators) who receive warning information can review the warning on their devices and quickly determine appropriate action based on the details of the abnormal behavior and the emotions involved. For example, if a student is expressing feelings of fear or sadness, the user can immediately go to the scene to assess the situation and determine if counseling is necessary. 【0293】 In summary, the embodiments of the present invention enable advanced monitoring and response that takes into account both abnormal behavior and emotions, and are a system that effectively supports school safety and student welfare. 【0294】 The following describes the processing flow. 【0295】 Step 1: 【0296】 The server receives video data in real time from multiple video acquisition devices installed on campus. This data is temporarily stored in a large-capacity storage device for subsequent analysis. 【0297】 Step 2: 【0298】 The server preprocesses the received video and converts it into a format suitable for analysis. For example, it adjusts the resolution of the image and removes noise as needed. Also, by selecting important frames, the analysis efficiency is improved. 【0299】 Step 3: 【0300】 The server sends the preprocessed video data to the artificial intelligence module to identify the behavior pattern. The artificial intelligence analyzes the movements of the people in the video and determines whether the behavior is normal or abnormal based on the set criteria. 【0301】 Step 4: 【0302】 The server uses the emotion engine to analyze the facial expressions and body movements of the people in the video and recognize the emotional state. This recognition result complements the detection of abnormal behavior patterns. 【0303】 Step 5: 【0304】 The server generates detailed warning information based on the detected abnormal behavior and the emotion recognition result. This warning includes the specific time and location of the abnormal detection, as well as the emotional state of the target person. 【0305】 Step 6: 【0306】 The server sends the generated warning information to the management terminal in real time. This information is presented to the user in scenarios that require prompt response. 【0307】 Step 7: 【0308】 After receiving the warning on their own terminal, the user checks the video clip and the recognized emotion data. Based on this, the user can make a judgment on a prompt intervention at the scene or appropriate countermeasures. 【0309】 (Example 2) 【0310】 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". 【0311】 In schools and public facilities, conventional monitoring systems have struggled to quickly detect and appropriately respond to abnormal behavior or emotional changes that might be overlooked. This has led to delays in the early detection and intervention of problematic behavior, resulting in situations where the safety of students and users cannot be adequately protected. 【0312】 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. 【0313】 In this invention, the server includes means for acquiring image information from a video input device, means for identifying behavioral patterns using a machine learning model for analyzing the image information, and means for generating emotionally analyzed warning information when the behavioral pattern is determined to be abnormal. This enables rapid detection of abnormal behavior and the provision of warnings accompanied by emotional information. 【0314】 A "video input device" refers to a set of multiple shooting units installed within a facility, which are used to acquire image information in real time. 【0315】 "Image information" refers to visual data acquired from video input devices and serves as fundamental data for analyzing a person's actions and circumstances. 【0316】 A "machine learning model" refers to an algorithm used to learn data patterns and identify actions in video footage. 【0317】 "Behavioral patterns" refer to the sequence or tendency of a person's actions identified from image information, and serve as a criterion for judging abnormal behavior. 【0318】 "Emotional analysis" refers to the process of determining a person's emotional state, such as joy, anger, sadness, or happiness, from their facial expressions and actions. 【0319】 "Warning information" refers to notification data generated when abnormal behavior or a specific emotional state is detected, and which is transmitted to the management device. 【0320】 A "management device" refers to a device that receives and displays warning information and supports decisions for taking action. 【0321】 In this invention, the system is implemented based on the following configuration and procedure. 【0322】 The server acquires image information in real time from multiple video input devices installed throughout the school. This makes it possible to continuously collect video data from various areas such as hallways, classrooms, and the gymnasium. Standard surveillance cameras and other imaging units are used to acquire the image information. 【0323】 The server runs a machine learning model to analyze the acquired image information. This model uses a deep learning framework (e.g., TensorFlow or PyTorch) to identify behavioral patterns of people in the video. Based on this behavioral data, the server detects abnormal behavior. OpenCV and other tools can also be used in this process to perform efficient video analysis. 【0324】 Furthermore, the server identifies facial expressions and body movements to recognize emotional states in order to perform emotion analysis. This emotion recognition utilizes cloud-based service APIs (e.g., Emotion API and Google Cloud Vision API) to tag emotions quickly and accurately. This enables the combination of behavioral patterns and emotional information, significantly improving the accuracy of warnings against abnormal behavior. 【0325】 If a warning is deemed necessary, the server generates warning information and sends it to the management terminal. The management terminal displays the warning information to the user and provides relevant detailed data (e.g., the time and location of the anomaly, the emotional state of the people involved, etc.). 【0326】 Users (teachers or administrators) can use this information to quickly decide on a course of action. For example, a user can receive a warning notification, go to the scene to check the situation, and determine the need for counseling based on the student's emotional state. 【0327】 An example of a prompt might be, "Please describe the steps to automate a system that sends a notification if a student in a video appears to have a sad expression." This prompt is used to refine anomaly detection by linking emotional information with behavioral patterns. 【0328】 As described in detail above, the present invention enables the construction of a more effective monitoring system and enhances safety and student welfare in the school environment. 【0329】 The flow of the specific processing in Example 2 will be explained using Figure 13. 【0330】 Step 1: 【0331】 The server acquires image information in real time from video input devices installed within the school. The input is video data of students and locations, and the output is clear, temporally continuous video data to enable analysis. Specifically, the server periodically polls the video stream from each camera to confirm stable data reception. 【0332】 Step 2: 【0333】 The server analyzes the acquired image information using a machine learning model. The input is a video stream, and the output is the result of identifying the dynamic behavioral patterns contained within it. Specifically, the server runs a deep learning model using TensorFlow to classify human movements in the video and understand the changes in general behavioral patterns. 【0334】 Step 3: 【0335】 After identifying behavioral patterns, the server performs sentiment analysis. The input is the identified behavioral patterns and corresponding video frames, and the output is tag information indicating the emotional state at that time. The server calls the Google Cloud Vision API to analyze facial expressions in the video and quantify the emotional tendencies. 【0336】 Step 4: 【0337】 The server detects anomalies based on the analyzed behavioral patterns and emotional states. The input is the analysis results from steps 2 and 3, and the output is information regarding whether an anomaly was detected and the degree of that anomaly. Specifically, the server uses an algorithm that compares the current data with past data to determine the anomaly. 【0338】 Step 5: 【0339】 When an anomaly is detected, the server generates warning information and sends it to the management terminal. The input is the anomaly detection result, and the output is a warning message containing details of the anomaly. Specifically, the server packages and sends detailed data of the time, location, and individuals involved in the anomaly. 【0340】 Step 6: 【0341】 The user receives alerts on a management terminal and checks the details. The input is the alert information sent from the server, and the output is the action plan for response. Specifically, the user analyzes the detailed alert information from the dashboard displayed on the terminal and decides on the appropriate response, such as on-site intervention or contacting relevant parties. 【0342】 (Application Example 2) 【0343】 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." 【0344】 In recent years, security in public and commercial facilities has become increasingly important, but conventional monitoring systems have challenges in detecting abnormal behavior in real time and capturing emotional changes associated with that behavior. Furthermore, when anomalies are detected, the lack of rapid and accurate information provision can delay effective responses. To address these challenges, an advanced monitoring system is needed that can analyze abnormal behavior and associated emotional information in real time and immediately notify relevant parties. 【0345】 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. 【0346】 In this invention, the server includes means for receiving visual data and detecting behavioral patterns using machine learning to analyze it; means for generating warning information when the detected behavioral pattern is determined to be abnormal; and means for reinforcing the analysis results of the behavioral pattern using an emotion analysis engine to recognize emotional states. This makes it possible to quickly detect changes in emotion associated with abnormal behavior and provide warning information at an appropriate time. 【0347】 A "video acquisition device" is a device installed to record visual data, and includes surveillance cameras and sensor devices. 【0348】 "Visual data" refers to image and video information obtained from video acquisition devices, and is the data that is analyzed. 【0349】 "Machine learning" is a type of artificial intelligence technology that learns patterns and features based on data and uses them for inference. 【0350】 A "behavioral pattern" refers to a specific form of movement or action of a person or object, and is identified through analysis. 【0351】 "An abnormal state" refers to a condition that differs from the normal state or expected behavior, and signifies an event that requires attention and monitoring. 【0352】 "Warning information" is information generated to alert of the occurrence of an abnormal situation, and includes detailed behavioral and emotional data. 【0353】 An "emotion analysis engine" is software or hardware equipped with technology to recognize emotional states from a person's facial expressions and movements in video data. 【0354】 A "management terminal" is a computer or device used by a system administrator to receive information and verify and process monitoring results. 【0355】 The system realizing this invention uses a machine learning model and sentiment analysis engine installed on a server to receive and analyze real-time visual data obtained from a video acquisition device. After acquiring the visual data, the server uses a machine learning algorithm to detect target behavioral patterns. In this process, open-source machine learning libraries such as TensorFlow are used. 【0356】 The detected behavioral patterns are analyzed using an emotion analysis engine to recognize the target's emotional state by analyzing facial expressions and body movements, and this is then incorporated into the analysis results. The server combines this information and generates warning information if it determines that an abnormality has occurred. This warning information includes the time and location of the abnormal behavior, the associated emotional state, etc., and is sent to the management terminal. The administrator can receive the warning information on this terminal and take countermeasures as needed. 【0357】 As a concrete example, consider a scenario where a surveillance system is installed in a shopping mall. For instance, if abnormal behavior is detected in an area where congestion is expected during a large-scale event, an alert is immediately sent to the security guard's management terminal, enabling a swift response. At this time, if stress or anxiety is identified through emotion analysis, even more appropriate countermeasures can be taken. 【0358】 An example of a prompt for a generative AI model is: "Develop a video-based abnormal behavior and emotion detection system. Also, enhance the necessary features to ensure customer safety." Based on this prompt, the generative AI model can suggest the necessary features and use this information to design the system. 【0359】 The flow of a specific process in Application Example 2 will be explained using Figure 14. 【0360】 Step 1: 【0361】 The server receives visual data in real time from video acquisition devices. The input is visual data from surveillance cameras, etc., and the output is video information to be analyzed. This acquired data is temporarily stored in a buffer for analysis. 【0362】 Step 2: 【0363】 The server uses machine learning algorithms to analyze the visual data stored in the buffer. The input is the visual data from step 1, and the output is the identified behavioral patterns. This process uses technologies such as TensorFlow to analyze the detected movements and actions. 【0364】 Step 3: 【0365】 The server uses an emotion analysis engine to augment the results of the behavioral pattern analysis. The input is the behavioral pattern obtained in step 2, and the output is the enhanced analysis result, including the emotional state. Here, emotions are inferred based on facial expressions and limb movements, and the data is enriched. 【0366】 Step 4: 【0367】 The server generates warning information if it detects an anomaly. The input is the analysis result from step 3, and the output is the warning information. This information includes the time, location, and emotional state at which the anomaly was detected. 【0368】 Step 5: 【0369】 The server sends the generated warning information to the management terminal. The input is the warning information from step 4, and the output is the alert display on the management terminal. Here, information is transmitted in real time using a communication protocol. 【0370】 Step 6: 【0371】 The user (administrator or security guard) checks the warning information on the management terminal and takes appropriate action if necessary. The input is the alert on the management terminal, and the output is the implementation of the appropriate countermeasure. In this step, on-site verification and instructions are given based on the notified information. 【0372】 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. 【0373】 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. 【0374】 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. 【0375】 [Third Embodiment] 【0376】 Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment. 【0377】 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. 【0378】 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). 【0379】 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. 【0380】 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. 【0381】 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). 【0382】 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. 【0383】 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. 【0384】 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. 【0385】 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. 【0386】 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. 【0387】 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". 【0388】 This invention is a system that analyzes video data obtained from multiple video acquisition devices installed within a school in real time to detect abnormal behavior. To achieve this, a server constantly receives data from the video acquisition devices and analyzes that data using a dedicated artificial intelligence program. 【0389】 The server analyzes each frame in the video and uses artificial intelligence to extract multiple features. Based on these features, it identifies behavioral patterns and detects potentially abnormal behavior. For example, if the distance between students suddenly shortens or unnatural movements continue, the server automatically flags that behavior as potentially bullying or violence. 【0390】 If an anomaly is detected, the server immediately generates warning information and sends it to the management terminal. The warning information includes the time and location of the abnormal behavior, as well as an attached video clip, designed to allow teachers and administrators to quickly understand the situation. 【0391】 Users receive warning information on their own devices and take necessary actions. For example, upon receiving a warning, a user can check the exact situation on-site and issue instructions for appropriate intervention. This system helps improve school safety even without direct teacher supervision at specific times. 【0392】 As described above, the embodiments of the present invention enable real-time monitoring and rapid response, and support the prevention of problematic behavior in educational settings. 【0393】 The following describes the processing flow. 【0394】 Step 1: 【0395】 The server receives video data in real time from each video acquisition device installed within the school. The video is transmitted in high resolution in a stream format, and the server is ready for initial processing. 【0396】 Step 2: 【0397】 The server preprocesses the received video data and converts it into a format suitable for analysis. Preprocessing includes noise reduction, image resolution adjustment, and extraction of important frames. This preprocessing prepares the data for smoother subsequent analysis. 【0398】 Step 3: 【0399】 The server sends pre-processed video data to an artificial intelligence module, which performs motion analysis on each frame. The AI ​​detects changes in the students' movements and positions and compares them with pre-set abnormal behavior patterns to determine whether or not there is an abnormality. 【0400】 Step 4: 【0401】 When abnormal behavior is detected, the server focuses its analysis on the relevant video portion to pinpoint the exact time and location where the anomaly occurred. It then automatically generates detailed data on the abnormal behavior and compiles it into a warning. 【0402】 Step 5: 【0403】 The server sends the generated warning information to the management terminal. This warning information includes the specific details of the anomaly and suggested countermeasures as needed. This provides administrators and teachers with clues to quickly understand the situation and take appropriate action. 【0404】 Step 6: 【0405】 Users receive and review warning information on their devices. By playing video clips, they can visually understand the situation on-site and issue instructions for prompt intervention and support. 【0406】 (Example 1) 【0407】 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." 【0408】 There is a need to detect abnormal behavior and safety issues within facilities in real time and respond to them promptly. However, conventional systems require constant manual monitoring, which makes efficient operation difficult. 【0409】 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. 【0410】 In this invention, the server includes means for receiving data from a camera via a computer system, means for detecting the position and movement of a person using image analysis technology based on the data, and means for inputting the generated data into an artificial intelligence model and identifying behavioral patterns. This makes it possible to automatically detect abnormal behavior and safety issues within a facility in real time and respond to them early. 【0411】 A "computer system" is a collection of hardware and software for receiving, processing, and analyzing digital data. 【0412】 A "filming device" is a device used to acquire video data in a specific space or environment. 【0413】 "Data" refers to video information obtained through a camera or camera, which is used for analysis and decision-making. 【0414】 "Image analysis technology" is a general term for methods and techniques used to extract useful information from video data and identify the position and movement of people and objects. 【0415】 An "artificial intelligence model" is a mathematical model trained using machine learning algorithms to identify specific patterns or structures. 【0416】 A "behavioral pattern" is a set of actions or behaviors that describe a series of actions or actions observed in a person or object. 【0417】 "Alert information" is data generated to notify of anomalies or emergencies, and is information that helps administrators respond quickly. 【0418】 A "management device" is a terminal or device used to receive alert information and display and verify its contents. 【0419】 This invention aims to implement a real-time monitoring system for safety management within a facility. The server is constantly connected via a network interface to receive video data from multiple cameras located within the facility. This data reception is designed to be high-speed and real-time. 【0420】 When video data is received by the server, the server uses image analysis libraries such as OpenCV to identify people and objects in the video and analyze their position and movement. This analysis generates behavioral patterns of people. 【0421】 These behavioral patterns are fed into an artificial intelligence model using a machine learning framework such as TensorFlow. The server uses this model to identify normal and abnormal behavioral patterns. If abnormal behavior is detected, the server immediately generates an alert and sends it to the management device. This alert includes the date, time, and location of the abnormal behavior, as well as any relevant video clips, enabling administrators to respond quickly. 【0422】 The administrator, acting as the user, can receive alert information on their device and view the details. For example, if they are notified of a conflict as an abnormal behavior, the user can review the video clip and intervene quickly on-site. 【0423】 As a concrete example, by providing the AI ​​model with the instruction, "Develop a system that analyzes footage from school surveillance cameras and automatically detects abnormal behavior," as a prompt to test the system's operation, it becomes possible to design a more effective system. 【0424】 This system aims to improve facility safety by reducing the burden of manual monitoring and automating safety management. 【0425】 The flow of the specific processing in Example 1 will be explained using Figure 11. 【0426】 Step 1: 【0427】 The server receives real-time video data from the facility's imaging equipment via the network. The input is video data from the imaging equipment, and the output is analyzable video frames. This video data is temporarily stored for use in later analysis steps. Specifically, the server monitors a designated IP address and port to ensure it receives the data stream. 【0428】 Step 2: 【0429】 The server divides the received video data into frames and performs image analysis. The input is video frames, and the output is the position information of people and objects extracted from each frame. This uses image analysis libraries such as OpenCV. Specifically, the server applies an object detection algorithm to the video frames to identify the outlines and movements of people. 【0430】 Step 3: 【0431】 The server uses an artificial intelligence model to identify behavioral patterns based on extracted location information. The input is location information, and the output is the behavioral pattern of each person. Normal and abnormal behavior are identified using a model trained with a framework such as TensorFlow. Specifically, the server inputs the current data into a pre-trained model and performs pattern matching. 【0432】 Step 4: 【0433】 The server determines whether the identified behavioral pattern is abnormal. The input is the behavioral pattern, and the output is a flag indicating whether it was determined to be abnormal. Specific thresholds or conditions are used as the criteria for this determination. The server detects abnormal behavior according to the configured rules and prepares for the next step. 【0434】 Step 5: 【0435】 The server generates alert information when an anomaly is detected and sends it to the management device. The input is a flag indicating the abnormal behavior, and the output is an alert information packet. This information includes the date and time of the occurrence, the location, and a related video clip. Specifically, the server encodes the data into a transmission format and sends it to the address of the specified management device. 【0436】 Step 6: 【0437】 The user checks the alert information received by the management device and takes the necessary actions. The input is the alert information, and the output is the instructions and execution of the response. Specifically, the user assesses the situation based on the provided information and makes decisions for appropriate on-site response. 【0438】 (Application Example 1) 【0439】 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." 【0440】 In modern educational settings, ensuring student safety, especially within schools, is crucial, but constant monitoring is difficult due to limitations in human resources. Therefore, there is a need for a system that can detect abnormal behavior in real time and respond quickly. A particular challenge is creating a system that can instantly send notifications to individual devices, enabling educators to intervene promptly. 【0441】 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. 【0442】 In this invention, the server includes means for receiving visual information from video acquisition means, means for identifying complex behavioral patterns using artificial intelligence for analyzing the visual information, means for generating a warning signal when the identified behavioral pattern is determined to be outside the standard, and means for transmitting a notification to an individual device based on the warning signal. This makes it possible to monitor abnormal student behavior in educational settings in real time and enable rapid intervention. 【0443】 "Image acquisition means" is a general term for a group of devices installed to capture visual information. 【0444】 "Visual information" refers to all image data and video data obtained from image acquisition methods. 【0445】 "Artificial intelligence" refers to a system equipped with a process that analyzes and makes decisions based on specific information using machine learning and deep learning technologies. 【0446】 A "behavioral pattern" refers to a series of characteristics and tendencies in human actions extracted from visual information. 【0447】 A "warning signal" is data generated to alert someone when a behavioral pattern outside the established criteria is detected. 【0448】 An "individual device" refers to a terminal or device used by a specific user. 【0449】 "Out of bounds" refers to a state or situation that deviates from the pre-defined normal range. 【0450】 "Means for transmitting notifications" refers to communication technologies and protocols used to quickly transmit warning signals to individual devices. 【0451】 To implement this invention, the server receives visual information from the video acquisition means and analyzes that visual information. For the analysis, artificial intelligence frameworks such as TensorFlow and PyTorch are used to activate machine learning models and identify behavioral patterns. If the server determines that the identified behavior is outside the standard, it generates a warning signal. This signal is transmitted to the educator's terminal by a communication module that immediately sends notifications to individual devices. 【0452】 To explain this system in more detail, for example, if suspicious activity is detected in a school hallway, the server recognizes the activity as outside the established criteria and generates a warning that suspicious activity has been detected in the second-floor hallway. The warning is sent to teachers' smartphones and tablets, enabling quick situation assessment and countermeasures. 【0453】 The hardware used includes numerous camera devices for acquiring visual information, and network communication utilizes an internet connection. The software includes a camera management system and an AI analysis program. This system enables real-time monitoring and early detection of anomalies in educational settings. 【0454】 An example of a prompt message is: "Identify sudden changes in distance in the hallway and detect suspicious activity. Generate a time- and location-based alert notification." This allows the system to support safety in educational settings. 【0455】 The flow of a specific process in Application Example 1 will be explained using Figure 12. 【0456】 Step 1: 【0457】 The server receives visual information from video acquisition devices installed within the school. The input is video data transmitted in real time from the cameras, and the output is raw data stored in the server's internal temporary memory. 【0458】 Step 2: 【0459】 The server divides the received visual information into frames and extracts features from each frame. The input is the raw data in temporary memory obtained in step 1. The output is a dataset of features corresponding to each frame. Specifically, it performs object detection and motion analysis using libraries such as TensorFlow and PyTorch. 【0460】 Step 3: 【0461】 The server applies an artificial intelligence model based on the extracted features to identify behavioral patterns. The input is the feature dataset from step 2, and the output is the classification result of the corresponding behavioral patterns. In specific actions, a pre-trained generative AI model is used to classify whether an action is abnormal or not. 【0462】 Step 4: 【0463】 If the identification result is outside the criteria, the server generates a warning signal, which includes the necessary detailed data. The input is the classification result obtained in step 3. The output is a data packet containing the warning signal and its detailed information. Specific operation involves detailed settings including the type of anomaly, the time of occurrence, and the location. 【0464】 Step 5: 【0465】 The server sends the generated warning signal to the educator's terminal. The input is the data packet generated in step 4. The output is embodied as a warning message displayed on the terminal. Specifically, data transmission over the internet and push notifications are used. 【0466】 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. 【0467】 This invention relates to a system that analyzes real-time video footage obtained from multiple video acquisition devices installed within a school and uses artificial intelligence and an emotion engine to detect abnormal behavior and emotions. This system processes video data in real time, automatically detects bullying and violent behavior that might be missed by normal monitoring, and provides this information, along with emotional data, to administrators. 【0468】 The server continuously receives data from the video acquisition device and analyzes the behavior of people in the video using artificial intelligence technology. In addition to behavioral patterns, it uses an emotion engine to recognize the user's emotional state from facial expressions and body movements. This recognition result reinforces the analysis of behavioral patterns and improves the accuracy of detecting abnormal behavior. 【0469】 When abnormal behavior is detected, the server generates detailed warning information, including the results of emotion recognition. This warning information includes data such as the time and location of the abnormality and the emotional state of the students involved, and is sent to the management terminal for necessary action. 【0470】 Users (teachers or administrators) who receive warning information can review the warning on their devices and quickly determine appropriate action based on the details of the abnormal behavior and the emotions involved. For example, if a student is expressing feelings of fear or sadness, the user can immediately go to the scene to assess the situation and determine if counseling is necessary. 【0471】 In summary, the embodiments of the present invention enable advanced monitoring and response that takes into account both abnormal behavior and emotions, and are a system that effectively supports school safety and student welfare. 【0472】 The following describes the processing flow. 【0473】 Step 1: 【0474】 The server receives video data in real time from multiple video acquisition devices installed on campus. This data is temporarily stored in a large-capacity storage device for subsequent analysis. 【0475】 Step 2: 【0476】 The server preprocesses the received video and converts it into a format suitable for analysis. For example, it adjusts the image resolution and removes noise as needed. It also improves analysis efficiency by selecting important frames. 【0477】 Step 3: 【0478】 The server sends pre-processed video data to an artificial intelligence module to identify behavioral patterns. The AI ​​analyzes the movements of people in the video and determines whether the behavior is normal or abnormal based on predefined criteria. 【0479】 Step 4: 【0480】 The server uses an emotion engine to analyze the facial expressions and body movements of people in the video and recognize their emotional state. This recognition result complements the detection of anomalies in behavioral patterns. 【0481】 Step 5: 【0482】 The server generates detailed warning information based on the detected abnormal behavior and emotion recognition results. This warning includes the specific time and location of the anomaly detection, as well as the emotional state of the person involved. 【0483】 Step 6: 【0484】 The server sends the generated warning information to the management terminal in real time. This information is presented to the user when a quick response is required. 【0485】 Step 7: 【0486】 After receiving an alert on their device, users can review video clips and recognized emotion data. Based on this, users can make decisions regarding rapid intervention at the scene and appropriate countermeasures. 【0487】 (Example 2) 【0488】 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." 【0489】 In schools and public facilities, conventional monitoring systems have struggled to quickly detect and appropriately respond to abnormal behavior or emotional changes that might be overlooked. This has led to delays in the early detection and intervention of problematic behavior, resulting in situations where the safety of students and users cannot be adequately protected. 【0490】 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. 【0491】 In this invention, the server includes means for acquiring image information from a video input device, means for identifying behavioral patterns using a machine learning model for analyzing the image information, and means for generating emotionally analyzed warning information when the behavioral pattern is determined to be abnormal. This enables rapid detection of abnormal behavior and the provision of warnings accompanied by emotional information. 【0492】 A "video input device" refers to a set of multiple shooting units installed within a facility, which are used to acquire image information in real time. 【0493】 "Image information" refers to visual data acquired from video input devices and serves as fundamental data for analyzing a person's actions and circumstances. 【0494】 A "machine learning model" refers to an algorithm used to learn data patterns and identify actions in video footage. 【0495】 "Behavioral patterns" refer to the sequence or tendency of a person's actions identified from image information, and serve as a criterion for judging abnormal behavior. 【0496】 "Emotional analysis" refers to the process of determining a person's emotional state, such as joy, anger, sadness, or happiness, from their facial expressions and actions. 【0497】 "Warning information" refers to notification data generated when abnormal behavior or a specific emotional state is detected, and which is transmitted to the management device. 【0498】 A "management device" refers to a device that receives and displays warning information and supports decisions for taking action. 【0499】 In this invention, the system is implemented based on the following configuration and procedure. 【0500】 The server acquires image information in real time from multiple video input devices installed throughout the school. This makes it possible to continuously collect video data from various areas such as hallways, classrooms, and the gymnasium. Standard surveillance cameras and other imaging units are used to acquire the image information. 【0501】 The server runs a machine learning model to analyze the acquired image information. This model uses a deep learning framework (e.g., TensorFlow or PyTorch) to identify behavioral patterns of people in the video. Based on this behavioral data, the server detects abnormal behavior. OpenCV and other tools can also be used in this process to perform efficient video analysis. 【0502】 Furthermore, the server identifies facial expressions and body movements to recognize emotional states in order to perform emotion analysis. This emotion recognition utilizes cloud-based service APIs (e.g., Emotion API and Google Cloud Vision API) to tag emotions quickly and accurately. This enables the combination of behavioral patterns and emotional information, significantly improving the accuracy of warnings against abnormal behavior. 【0503】 If a warning is deemed necessary, the server generates warning information and sends it to the management terminal. The management terminal displays the warning information to the user and provides relevant detailed data (e.g., the time and location of the anomaly, the emotional state of the people involved, etc.). 【0504】 Users (teachers or administrators) can use this information to quickly decide on a course of action. For example, a user can receive a warning notification, go to the scene to check the situation, and determine the need for counseling based on the student's emotional state. 【0505】 An example of a prompt might be, "Please describe the steps to automate a system that sends a notification if a student in a video appears to have a sad expression." This prompt is used to refine anomaly detection by linking emotional information with behavioral patterns. 【0506】 As described in detail above, the present invention enables the construction of a more effective monitoring system and enhances safety and student welfare in the school environment. 【0507】 The flow of the specific processing in Example 2 will be explained using Figure 13. 【0508】 Step 1: 【0509】 The server acquires image information in real time from video input devices installed within the school. The input is video data of students and locations, and the output is clear, temporally continuous video data to enable analysis. Specifically, the server periodically polls the video stream from each camera to confirm stable data reception. 【0510】 Step 2: 【0511】 The server analyzes the acquired image information using a machine learning model. The input is a video stream, and the output is the result of identifying the dynamic behavioral patterns contained within it. Specifically, the server runs a deep learning model using TensorFlow to classify human movements in the video and understand the changes in general behavioral patterns. 【0512】 Step 3: 【0513】 After identifying behavioral patterns, the server performs sentiment analysis. The input is the identified behavioral patterns and corresponding video frames, and the output is tag information indicating the emotional state at that time. The server calls the Google Cloud Vision API to analyze facial expressions in the video and quantify the emotional tendencies. 【0514】 Step 4: 【0515】 The server detects anomalies based on the analyzed behavioral patterns and emotional states. The input is the analysis results from steps 2 and 3, and the output is information regarding whether an anomaly was detected and the degree of that anomaly. Specifically, the server uses an algorithm that compares the current data with past data to determine the anomaly. 【0516】 Step 5: 【0517】 When an anomaly is detected, the server generates warning information and sends it to the management terminal. The input is the anomaly detection result, and the output is a warning message containing details of the anomaly. Specifically, the server packages and sends detailed data of the time, location, and individuals involved in the anomaly. 【0518】 Step 6: 【0519】 The user receives alerts on a management terminal and checks the details. The input is the alert information sent from the server, and the output is the action plan for response. Specifically, the user analyzes the detailed alert information from the dashboard displayed on the terminal and decides on the appropriate response, such as on-site intervention or contacting relevant parties. 【0520】 (Application Example 2) 【0521】 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." 【0522】 In recent years, security in public and commercial facilities has become increasingly important, but conventional monitoring systems have challenges in detecting abnormal behavior in real time and capturing emotional changes associated with that behavior. Furthermore, when anomalies are detected, the lack of rapid and accurate information provision can delay effective responses. To address these challenges, an advanced monitoring system is needed that can analyze abnormal behavior and associated emotional information in real time and immediately notify relevant parties. 【0523】 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. 【0524】 In this invention, the server includes means for receiving visual data and detecting behavioral patterns using machine learning to analyze it; means for generating warning information when the detected behavioral pattern is determined to be abnormal; and means for reinforcing the analysis results of the behavioral pattern using an emotion analysis engine to recognize emotional states. This makes it possible to quickly detect changes in emotion associated with abnormal behavior and provide warning information at an appropriate time. 【0525】 A "video acquisition device" is a device installed to record visual data, and includes surveillance cameras and sensor devices. 【0526】 "Visual data" refers to image and video information obtained from video acquisition devices, and is the data that is analyzed. 【0527】 "Machine learning" is a type of artificial intelligence technology that learns patterns and features based on data and uses them for inference. 【0528】 A "behavioral pattern" refers to a specific form of movement or action of a person or object, and is identified through analysis. 【0529】 "An abnormal state" refers to a condition that differs from the normal state or expected behavior, and signifies an event that requires attention and monitoring. 【0530】 "Warning information" is information generated to alert of the occurrence of an abnormal situation, and includes detailed behavioral and emotional data. 【0531】 An "emotion analysis engine" is software or hardware equipped with technology to recognize emotional states from a person's facial expressions and movements in video data. 【0532】 A "management terminal" is a computer or device used by a system administrator to receive information and verify and process monitoring results. 【0533】 The system realizing this invention uses a machine learning model and sentiment analysis engine installed on a server to receive and analyze real-time visual data obtained from a video acquisition device. After acquiring the visual data, the server uses a machine learning algorithm to detect target behavioral patterns. In this process, open-source machine learning libraries such as TensorFlow are used. 【0534】 The detected behavioral patterns are analyzed using an emotion analysis engine to recognize the target's emotional state by analyzing facial expressions and body movements, and this is then incorporated into the analysis results. The server combines this information and generates warning information if it determines that an abnormality has occurred. This warning information includes the time and location of the abnormal behavior, the associated emotional state, etc., and is sent to the management terminal. The administrator can receive the warning information on this terminal and take countermeasures as needed. 【0535】 As a concrete example, consider a scenario where a surveillance system is installed in a shopping mall. For instance, if abnormal behavior is detected in an area where congestion is expected during a large-scale event, an alert is immediately sent to the security guard's management terminal, enabling a swift response. At this time, if stress or anxiety is identified through emotion analysis, even more appropriate countermeasures can be taken. 【0536】 An example of a prompt for a generative AI model is: "Develop a video-based abnormal behavior and emotion detection system. Also, enhance the necessary features to ensure customer safety." Based on this prompt, the generative AI model can suggest the necessary features and use this information to design the system. 【0537】 The flow of a specific process in Application Example 2 will be explained using Figure 14. 【0538】 Step 1: 【0539】 The server receives visual data in real time from video acquisition devices. The input is visual data from surveillance cameras, etc., and the output is video information to be analyzed. This acquired data is temporarily stored in a buffer for analysis. 【0540】 Step 2: 【0541】 The server uses machine learning algorithms to analyze the visual data stored in the buffer. The input is the visual data from step 1, and the output is the identified behavioral patterns. This process uses technologies such as TensorFlow to analyze the detected movements and actions. 【0542】 Step 3: 【0543】 The server uses an emotion analysis engine to augment the results of the behavioral pattern analysis. The input is the behavioral pattern obtained in step 2, and the output is the enhanced analysis result, including the emotional state. Here, emotions are inferred based on facial expressions and limb movements, and the data is enriched. 【0544】 Step 4: 【0545】 The server generates warning information if it detects an anomaly. The input is the analysis result from step 3, and the output is the warning information. This information includes the time, location, and emotional state at which the anomaly was detected. 【0546】 Step 5: 【0547】 The server sends the generated warning information to the management terminal. The input is the warning information from step 4, and the output is the alert display on the management terminal. Here, information is transmitted in real time using a communication protocol. 【0548】 Step 6: 【0549】 The user (administrator or security guard) checks the warning information on the management terminal and takes appropriate action if necessary. The input is the alert on the management terminal, and the output is the implementation of the appropriate countermeasure. In this step, on-site verification and instructions are given based on the notified information. 【0550】 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. 【0551】 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. 【0552】 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. 【0553】 [Fourth Embodiment] 【0554】 Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment. 【0555】 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. 【0556】 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). 【0557】 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. 【0558】 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. 【0559】 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). 【0560】 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. 【0561】 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. 【0562】 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. 【0563】 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. 【0564】 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. 【0565】 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. 【0566】 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". 【0567】 This invention is a system that analyzes video data obtained from multiple video acquisition devices installed within a school in real time to detect abnormal behavior. To achieve this, a server constantly receives data from the video acquisition devices and analyzes that data using a dedicated artificial intelligence program. 【0568】 The server analyzes each frame in the video and uses artificial intelligence to extract multiple features. Based on these features, it identifies behavioral patterns and detects potentially abnormal behavior. For example, if the distance between students suddenly shortens or unnatural movements continue, the server automatically flags that behavior as potentially bullying or violence. 【0569】 If an anomaly is detected, the server immediately generates warning information and sends it to the management terminal. The warning information includes the time and location of the abnormal behavior, as well as an attached video clip, designed to allow teachers and administrators to quickly understand the situation. 【0570】 Users receive warning information on their own devices and take necessary actions. For example, upon receiving a warning, a user can check the exact situation on-site and issue instructions for appropriate intervention. This system helps improve school safety even without direct teacher supervision at specific times. 【0571】 As described above, the embodiments of the present invention enable real-time monitoring and rapid response, and support the prevention of problematic behavior in educational settings. 【0572】 The following describes the processing flow. 【0573】 Step 1: 【0574】 The server receives video data in real time from each video acquisition device installed within the school. The video is transmitted in high resolution in a stream format, and the server is ready for initial processing. 【0575】 Step 2: 【0576】 The server preprocesses the received video data and converts it into a format suitable for analysis. Preprocessing includes noise reduction, image resolution adjustment, and extraction of important frames. This preprocessing prepares the data for smoother subsequent analysis. 【0577】 Step 3: 【0578】 The server sends pre-processed video data to an artificial intelligence module, which performs motion analysis on each frame. The AI ​​detects changes in the students' movements and positions and compares them with pre-set abnormal behavior patterns to determine whether or not there is an abnormality. 【0579】 Step 4: 【0580】 When abnormal behavior is detected, the server focuses its analysis on the relevant video portion to pinpoint the exact time and location where the anomaly occurred. It then automatically generates detailed data on the abnormal behavior and compiles it into a warning. 【0581】 Step 5: 【0582】 The server sends the generated warning information to the management terminal. This warning information includes the specific details of the anomaly and suggested countermeasures as needed. This provides administrators and teachers with clues to quickly understand the situation and take appropriate action. 【0583】 Step 6: 【0584】 Users receive and review warning information on their devices. By playing video clips, they can visually understand the situation on-site and issue instructions for prompt intervention and support. 【0585】 (Example 1) 【0586】 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". 【0587】 There is a need to detect abnormal behavior and safety issues within facilities in real time and respond to them promptly. However, conventional systems require constant manual monitoring, which makes efficient operation difficult. 【0588】 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. 【0589】 In this invention, the server includes means for receiving data from a camera via a computer system, means for detecting the position and movement of a person using image analysis technology based on the data, and means for inputting the generated data into an artificial intelligence model and identifying behavioral patterns. This makes it possible to automatically detect abnormal behavior and safety issues within a facility in real time and respond to them early. 【0590】 A "computer system" is a collection of hardware and software for receiving, processing, and analyzing digital data. 【0591】 A "filming device" is a device used to acquire video data in a specific space or environment. 【0592】 "Data" refers to video information obtained through a camera or camera, which is used for analysis and decision-making. 【0593】 "Image analysis technology" is a general term for methods and techniques used to extract useful information from video data and identify the position and movement of people and objects. 【0594】 An "artificial intelligence model" is a mathematical model trained using machine learning algorithms to identify specific patterns or structures. 【0595】 A "behavioral pattern" is a set of actions or behaviors that describe a series of actions or actions observed in a person or object. 【0596】 "Alert information" is data generated to notify of anomalies or emergencies, and is information that helps administrators respond quickly. 【0597】 A "management device" is a terminal or device used to receive alert information and display and verify its contents. 【0598】 This invention aims to implement a real-time monitoring system for safety management within a facility. The server is constantly connected via a network interface to receive video data from multiple cameras located within the facility. This data reception is designed to be high-speed and real-time. 【0599】 When video data is received by the server, the server uses image analysis libraries such as OpenCV to identify people and objects in the video and analyze their position and movement. This analysis generates behavioral patterns of people. 【0600】 These behavioral patterns are fed into an artificial intelligence model using a machine learning framework such as TensorFlow. The server uses this model to identify normal and abnormal behavioral patterns. If abnormal behavior is detected, the server immediately generates an alert and sends it to the management device. This alert includes the date, time, and location of the abnormal behavior, as well as any relevant video clips, enabling administrators to respond quickly. 【0601】 The administrator, acting as the user, can receive alert information on their device and view the details. For example, if they are notified of a conflict as an abnormal behavior, the user can review the video clip and intervene quickly on-site. 【0602】 As a concrete example, by providing the AI ​​model with the instruction, "Develop a system that analyzes footage from school surveillance cameras and automatically detects abnormal behavior," as a prompt to test the system's operation, it becomes possible to design a more effective system. 【0603】 This system aims to improve facility safety by reducing the burden of manual monitoring and automating safety management. 【0604】 The flow of the specific processing in Example 1 will be explained using Figure 11. 【0605】 Step 1: 【0606】 The server receives real-time video data from the facility's imaging equipment via the network. The input is video data from the imaging equipment, and the output is analyzable video frames. This video data is temporarily stored for use in later analysis steps. Specifically, the server monitors a designated IP address and port to ensure it receives the data stream. 【0607】 Step 2: 【0608】 The server divides the received video data into frames and performs image analysis. The input is video frames, and the output is the position information of people and objects extracted from each frame. This uses image analysis libraries such as OpenCV. Specifically, the server applies an object detection algorithm to the video frames to identify the outlines and movements of people. 【0609】 Step 3: 【0610】 The server uses an artificial intelligence model to identify behavioral patterns based on extracted location information. The input is location information, and the output is the behavioral pattern of each person. Normal and abnormal behavior are identified using a model trained with a framework such as TensorFlow. Specifically, the server inputs the current data into a pre-trained model and performs pattern matching. 【0611】 Step 4: 【0612】 The server determines whether the identified behavioral pattern is abnormal. The input is the behavioral pattern, and the output is a flag indicating whether it was determined to be abnormal. Specific thresholds or conditions are used as the criteria for this determination. The server detects abnormal behavior according to the configured rules and prepares for the next step. 【0613】 Step 5: 【0614】 The server generates alert information when an anomaly is detected and sends it to the management device. The input is a flag indicating the abnormal behavior, and the output is an alert information packet. This information includes the date and time of the occurrence, the location, and a related video clip. Specifically, the server encodes the data into a transmission format and sends it to the address of the specified management device. 【0615】 Step 6: 【0616】 The user checks the alert information received by the management device and takes the necessary actions. The input is the alert information, and the output is the instructions and execution of the response. Specifically, the user assesses the situation based on the provided information and makes decisions for appropriate on-site response. 【0617】 (Application Example 1) 【0618】 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". 【0619】 In modern educational settings, ensuring student safety, especially within schools, is crucial, but constant monitoring is difficult due to limitations in human resources. Therefore, there is a need for a system that can detect abnormal behavior in real time and respond quickly. A particular challenge is creating a system that can instantly send notifications to individual devices, enabling educators to intervene promptly. 【0620】 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. 【0621】 In this invention, the server includes means for receiving visual information from video acquisition means, means for identifying complex behavioral patterns using artificial intelligence for analyzing the visual information, means for generating a warning signal when the identified behavioral pattern is determined to be outside the standard, and means for transmitting a notification to an individual device based on the warning signal. This makes it possible to monitor abnormal student behavior in educational settings in real time and enable rapid intervention. 【0622】 "Image acquisition means" is a general term for a group of devices installed to capture visual information. 【0623】 "Visual information" refers to all image data and video data obtained from image acquisition methods. 【0624】 "Artificial intelligence" refers to a system equipped with a process that analyzes and makes decisions based on specific information using machine learning and deep learning technologies. 【0625】 A "behavioral pattern" refers to a series of characteristics and tendencies in human actions extracted from visual information. 【0626】 A "warning signal" is data generated to alert someone when a behavioral pattern outside the established criteria is detected. 【0627】 An "individual device" refers to a terminal or device used by a specific user. 【0628】 "Out of bounds" refers to a state or situation that deviates from the pre-defined normal range. 【0629】 "Means for transmitting notifications" refers to communication technologies and protocols used to quickly transmit warning signals to individual devices. 【0630】 To implement this invention, the server receives visual information from the video acquisition means and analyzes that visual information. For the analysis, artificial intelligence frameworks such as TensorFlow and PyTorch are used to activate machine learning models and identify behavioral patterns. If the server determines that the identified behavior is outside the standard, it generates a warning signal. This signal is transmitted to the educator's terminal by a communication module that immediately sends notifications to individual devices. 【0631】 To explain this system in more detail, for example, if suspicious activity is detected in a school hallway, the server recognizes the activity as outside the established criteria and generates a warning that suspicious activity has been detected in the second-floor hallway. The warning is sent to teachers' smartphones and tablets, enabling quick situation assessment and countermeasures. 【0632】 The hardware used includes numerous camera devices for acquiring visual information, and network communication utilizes an internet connection. The software includes a camera management system and an AI analysis program. This system enables real-time monitoring and early detection of anomalies in educational settings. 【0633】 An example of a prompt message is: "Identify sudden changes in distance in the hallway and detect suspicious activity. Generate a time- and location-based alert notification." This allows the system to support safety in educational settings. 【0634】 The flow of a specific process in Application Example 1 will be explained using Figure 12. 【0635】 Step 1: 【0636】 The server receives visual information from video acquisition devices installed within the school. The input is video data transmitted in real time from the cameras, and the output is raw data stored in the server's internal temporary memory. 【0637】 Step 2: 【0638】 The server divides the received visual information into frames and extracts features from each frame. The input is the raw data in temporary memory obtained in step 1. The output is a dataset of features corresponding to each frame. Specifically, it performs object detection and motion analysis using libraries such as TensorFlow and PyTorch. 【0639】 Step 3: 【0640】 The server applies an artificial intelligence model based on the extracted features to identify behavioral patterns. The input is the feature dataset from step 2, and the output is the classification result of the corresponding behavioral patterns. In specific actions, a pre-trained generative AI model is used to classify whether an action is abnormal or not. 【0641】 Step 4: 【0642】 If the identification result is outside the criteria, the server generates a warning signal, which includes the necessary detailed data. The input is the classification result obtained in step 3. The output is a data packet containing the warning signal and its detailed information. Specific operation involves detailed settings including the type of anomaly, the time of occurrence, and the location. 【0643】 Step 5: 【0644】 The server sends the generated warning signal to the educator's terminal. The input is the data packet generated in step 4. The output is embodied as a warning message displayed on the terminal. Specifically, data transmission over the internet and push notifications are used. 【0645】 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. 【0646】 This invention relates to a system that analyzes real-time video footage obtained from multiple video acquisition devices installed within a school and uses artificial intelligence and an emotion engine to detect abnormal behavior and emotions. This system processes video data in real time, automatically detects bullying and violent behavior that might be missed by normal monitoring, and provides this information, along with emotional data, to administrators. 【0647】 The server continuously receives data from the video acquisition device and analyzes the behavior of people in the video using artificial intelligence technology. In addition to behavioral patterns, it uses an emotion engine to recognize the user's emotional state from facial expressions and body movements. This recognition result reinforces the analysis of behavioral patterns and improves the accuracy of detecting abnormal behavior. 【0648】 When abnormal behavior is detected, the server generates detailed warning information, including the results of emotion recognition. This warning information includes data such as the time and location of the abnormality and the emotional state of the students involved, and is sent to the management terminal for necessary action. 【0649】 Users (teachers or administrators) who receive warning information can review the warning on their devices and quickly determine appropriate action based on the details of the abnormal behavior and the emotions involved. For example, if a student is expressing feelings of fear or sadness, the user can immediately go to the scene to assess the situation and determine if counseling is necessary. 【0650】 In summary, the embodiments of the present invention enable advanced monitoring and response that takes into account both abnormal behavior and emotions, and are a system that effectively supports school safety and student welfare. 【0651】 The following describes the processing flow. 【0652】 Step 1: 【0653】 The server receives video data in real time from multiple video acquisition devices installed on campus. This data is temporarily stored in a large-capacity storage device for subsequent analysis. 【0654】 Step 2: 【0655】 The server preprocesses the received video and converts it into a format suitable for analysis. For example, it adjusts the image resolution and removes noise as needed. It also improves analysis efficiency by selecting important frames. 【0656】 Step 3: 【0657】 The server sends pre-processed video data to an artificial intelligence module to identify behavioral patterns. The AI ​​analyzes the movements of people in the video and determines whether the behavior is normal or abnormal based on predefined criteria. 【0658】 Step 4: 【0659】 The server uses an emotion engine to analyze the facial expressions and body movements of people in the video and recognize their emotional state. This recognition result complements the detection of anomalies in behavioral patterns. 【0660】 Step 5: 【0661】 The server generates detailed warning information based on the detected abnormal behavior and emotion recognition results. This warning includes the specific time and location of the anomaly detection, as well as the emotional state of the person involved. 【0662】 Step 6: 【0663】 The server sends the generated warning information to the management terminal in real time. This information is presented to the user when a quick response is required. 【0664】 Step 7: 【0665】 After receiving an alert on their device, users can review video clips and recognized emotion data. Based on this, users can make decisions regarding rapid intervention at the scene and appropriate countermeasures. 【0666】 (Example 2) 【0667】 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". 【0668】 In schools and public facilities, conventional monitoring systems have struggled to quickly detect and appropriately respond to abnormal behavior or emotional changes that might be overlooked. This has led to delays in the early detection and intervention of problematic behavior, resulting in situations where the safety of students and users cannot be adequately protected. 【0669】 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. 【0670】 In this invention, the server includes means for acquiring image information from a video input device, means for identifying behavioral patterns using a machine learning model for analyzing the image information, and means for generating emotionally analyzed warning information when the behavioral pattern is determined to be abnormal. This enables rapid detection of abnormal behavior and the provision of warnings accompanied by emotional information. 【0671】 A "video input device" refers to a set of multiple shooting units installed within a facility, which are used to acquire image information in real time. 【0672】 "Image information" refers to visual data acquired from video input devices and serves as fundamental data for analyzing a person's actions and circumstances. 【0673】 A "machine learning model" refers to an algorithm used to learn data patterns and identify actions in video footage. 【0674】 "Behavioral patterns" refer to the sequence or tendency of a person's actions identified from image information, and serve as a criterion for judging abnormal behavior. 【0675】 "Emotional analysis" refers to the process of determining a person's emotional state, such as joy, anger, sadness, or happiness, from their facial expressions and actions. 【0676】 "Warning information" refers to notification data generated when abnormal behavior or a specific emotional state is detected, and which is transmitted to the management device. 【0677】 A "management device" refers to a device that receives and displays warning information and supports decisions for taking action. 【0678】 In this invention, the system is implemented based on the following configuration and procedure. 【0679】 The server acquires image information in real time from multiple video input devices installed throughout the school. This makes it possible to continuously collect video data from various areas such as hallways, classrooms, and the gymnasium. Standard surveillance cameras and other imaging units are used to acquire the image information. 【0680】 The server runs a machine learning model to analyze the acquired image information. This model uses a deep learning framework (e.g., TensorFlow or PyTorch) to identify behavioral patterns of people in the video. Based on this behavioral data, the server detects abnormal behavior. OpenCV and other tools can also be used in this process to perform efficient video analysis. 【0681】 Furthermore, the server identifies facial expressions and body movements to recognize emotional states in order to perform emotion analysis. This emotion recognition utilizes cloud-based service APIs (e.g., Emotion API and Google Cloud Vision API) to tag emotions quickly and accurately. This enables the combination of behavioral patterns and emotional information, significantly improving the accuracy of warnings against abnormal behavior. 【0682】 If a warning is deemed necessary, the server generates warning information and sends it to the management terminal. The management terminal displays the warning information to the user and provides relevant detailed data (e.g., the time and location of the anomaly, the emotional state of the people involved, etc.). 【0683】 Users (teachers or administrators) can use this information to quickly decide on a course of action. For example, a user can receive a warning notification, go to the scene to check the situation, and determine the need for counseling based on the student's emotional state. 【0684】 An example of a prompt might be, "Please describe the steps to automate a system that sends a notification if a student in a video appears to have a sad expression." This prompt is used to refine anomaly detection by linking emotional information with behavioral patterns. 【0685】 As described in detail above, the present invention enables the construction of a more effective monitoring system and enhances safety and student welfare in the school environment. 【0686】 The flow of the specific processing in Example 2 will be explained using Figure 13. 【0687】 Step 1: 【0688】 The server acquires image information in real time from video input devices installed within the school. The input is video data of students and locations, and the output is clear, temporally continuous video data to enable analysis. Specifically, the server periodically polls the video stream from each camera to confirm stable data reception. 【0689】 Step 2: 【0690】 The server analyzes the acquired image information using a machine learning model. The input is a video stream, and the output is the result of identifying the dynamic behavioral patterns contained within it. Specifically, the server runs a deep learning model using TensorFlow to classify human movements in the video and understand the changes in general behavioral patterns. 【0691】 Step 3: 【0692】 After identifying behavioral patterns, the server performs sentiment analysis. The input is the identified behavioral patterns and corresponding video frames, and the output is tag information indicating the emotional state at that time. The server calls the Google Cloud Vision API to analyze facial expressions in the video and quantify the emotional tendencies. 【0693】 Step 4: 【0694】 The server detects anomalies based on the analyzed behavioral patterns and emotional states. The input is the analysis results from steps 2 and 3, and the output is information regarding whether an anomaly was detected and the degree of that anomaly. Specifically, the server uses an algorithm that compares the current data with past data to determine the anomaly. 【0695】 Step 5: 【0696】 When an anomaly is detected, the server generates warning information and sends it to the management terminal. The input is the anomaly detection result, and the output is a warning message containing details of the anomaly. Specifically, the server packages and sends detailed data of the time, location, and individuals involved in the anomaly. 【0697】 Step 6: 【0698】 The user receives alerts on a management terminal and checks the details. The input is the alert information sent from the server, and the output is the action plan for response. Specifically, the user analyzes the detailed alert information from the dashboard displayed on the terminal and decides on the appropriate response, such as on-site intervention or contacting relevant parties. 【0699】 (Application Example 2) 【0700】 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". 【0701】 In recent years, security in public and commercial facilities has become increasingly important, but conventional monitoring systems have challenges in detecting abnormal behavior in real time and capturing emotional changes associated with that behavior. Furthermore, when anomalies are detected, the lack of rapid and accurate information provision can delay effective responses. To address these challenges, an advanced monitoring system is needed that can analyze abnormal behavior and associated emotional information in real time and immediately notify relevant parties. 【0702】 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. 【0703】 In this invention, the server includes means for receiving visual data and detecting behavioral patterns using machine learning to analyze it; means for generating warning information when the detected behavioral pattern is determined to be abnormal; and means for reinforcing the analysis results of the behavioral pattern using an emotion analysis engine to recognize emotional states. This makes it possible to quickly detect changes in emotion associated with abnormal behavior and provide warning information at an appropriate time. 【0704】 A "video acquisition device" is a device installed to record visual data, and includes surveillance cameras and sensor devices. 【0705】 "Visual data" refers to image and video information obtained from video acquisition devices, and is the data that is analyzed. 【0706】 "Machine learning" is a type of artificial intelligence technology that learns patterns and features based on data and uses them for inference. 【0707】 A "behavioral pattern" refers to a specific form of movement or action of a person or object, and is identified through analysis. 【0708】 "An abnormal state" refers to a condition that differs from the normal state or expected behavior, and signifies an event that requires attention and monitoring. 【0709】 "Warning information" is information generated to alert of the occurrence of an abnormal situation, and includes detailed behavioral and emotional data. 【0710】 An "emotion analysis engine" is software or hardware equipped with technology to recognize emotional states from a person's facial expressions and movements in video data. 【0711】 A "management terminal" is a computer or device used by a system administrator to receive information and verify and process monitoring results. 【0712】 The system realizing this invention uses a machine learning model and sentiment analysis engine installed on a server to receive and analyze real-time visual data obtained from a video acquisition device. After acquiring the visual data, the server uses a machine learning algorithm to detect target behavioral patterns. In this process, open-source machine learning libraries such as TensorFlow are used. 【0713】 The detected behavioral patterns are analyzed using an emotion analysis engine to recognize the target's emotional state by analyzing facial expressions and body movements, and this is then incorporated into the analysis results. The server combines this information and generates warning information if it determines that an abnormality has occurred. This warning information includes the time and location of the abnormal behavior, the associated emotional state, etc., and is sent to the management terminal. The administrator can receive the warning information on this terminal and take countermeasures as needed. 【0714】 As a concrete example, consider a scenario where a surveillance system is installed in a shopping mall. For instance, if abnormal behavior is detected in an area where congestion is expected during a large-scale event, an alert is immediately sent to the security guard's management terminal, enabling a swift response. At this time, if stress or anxiety is identified through emotion analysis, even more appropriate countermeasures can be taken. 【0715】 An example of a prompt for a generative AI model is: "Develop a video-based abnormal behavior and emotion detection system. Also, enhance the necessary features to ensure customer safety." Based on this prompt, the generative AI model can suggest the necessary features and use this information to design the system. 【0716】 The flow of a specific process in Application Example 2 will be explained using Figure 14. 【0717】 Step 1: 【0718】 The server receives visual data in real time from video acquisition devices. The input is visual data from surveillance cameras, etc., and the output is video information to be analyzed. This acquired data is temporarily stored in a buffer for analysis. 【0719】 Step 2: 【0720】 The server uses machine learning algorithms to analyze the visual data stored in the buffer. The input is the visual data from step 1, and the output is the identified behavioral patterns. This process uses technologies such as TensorFlow to analyze the detected movements and actions. 【0721】 Step 3: 【0722】 The server uses an emotion analysis engine to augment the results of the behavioral pattern analysis. The input is the behavioral pattern obtained in step 2, and the output is the enhanced analysis result, including the emotional state. Here, emotions are inferred based on facial expressions and limb movements, and the data is enriched. 【0723】 Step 4: 【0724】 The server generates warning information if it detects an anomaly. The input is the analysis result from step 3, and the output is the warning information. This information includes the time, location, and emotional state at which the anomaly was detected. 【0725】 Step 5: 【0726】 The server sends the generated warning information to the management terminal. The input is the warning information from step 4, and the output is the alert display on the management terminal. Here, information is transmitted in real time using a communication protocol. 【0727】 Step 6: 【0728】 The user (administrator or security guard) checks the warning information on the management terminal and takes appropriate action if necessary. The input is the alert on the management terminal, and the output is the implementation of the appropriate countermeasure. In this step, on-site verification and instructions are given based on the notified information. 【0729】 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. 【0730】 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. 【0731】 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. 【0732】 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. 【0733】 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. 【0734】 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. 【0735】 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. 【0736】 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. 【0737】 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." 【0738】 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. 【0739】 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. 【0740】 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. 【0741】 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. 【0742】 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. 【0743】 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. 【0744】 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. 【0745】 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. 【0746】 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. 【0747】 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. 【0748】 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. 【0749】 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 as being incorporated by reference. 【0750】 The following is further disclosed regarding the embodiments described above. 【0751】 (Claim 1) 【0752】 A means for receiving video from a video acquisition device, 【0753】 A means for identifying behavioral patterns using artificial intelligence for analyzing the aforementioned video, 【0754】 If the identified behavioral pattern is determined to be abnormal, means for generating warning information, 【0755】 Means for transmitting the aforementioned warning information to a management terminal, 【0756】 A system that includes this. 【0757】 (Claim 2) 【0758】 The system according to claim 1, characterized in that the video acquisition device includes a plurality of shooting devices installed within the school. 【0759】 (Claim 3) 【0760】 The system according to claim 1, characterized in that the warning information includes detailed data regarding the behavior that was determined to be abnormal. 【0761】 "Example 1" 【0762】 (Claim 1) 【0763】 A means of receiving data from a camera via a computer system, 【0764】 A means for detecting the position and movement of a person using image analysis technology based on the aforementioned data, 【0765】 A means of inputting the generated data into an artificial intelligence model to identify behavioral patterns, 【0766】 A means for generating alert information when the identified behavioral pattern is determined to be abnormal, 【0767】 Means for transmitting the aforementioned alert information to a management device, 【0768】 A system that includes this. 【0769】 (Claim 2) 【0770】 The system according to claim 1, characterized in that the aforementioned imaging device includes a plurality of imaging devices arranged within the facility. 【0771】 (Claim 3) 【0772】 The system according to claim 1, characterized in that the alert information includes detailed information about the behavior that was determined to be abnormal. 【0773】 "Application Example 1" 【0774】 (Claim 1) 【0775】 A means for receiving visual information from an image acquisition means, 【0776】 A means for identifying complex behavioral patterns using artificial intelligence for analyzing the aforementioned visual information, 【0777】 If the identified behavioral pattern is determined to be outside the standard, means for generating a warning signal, 【0778】 Means for transmitting a notification to an individual device based on the aforementioned warning signal, 【0779】 A system that includes this. 【0780】 (Claim 2) 【0781】 The system according to claim 1, characterized in that the image acquisition means includes a number of acquisition devices installed in an internal space. 【0782】 (Claim 3) 【0783】 The system according to claim 1, characterized in that the warning signal includes extended data relating to the behavior determined to be outside the standard. 【0784】 "Example 2 of combining an emotion engine" 【0785】 (Claim 1) 【0786】 A means for acquiring image information from a video input device, 【0787】 A means for identifying behavioral patterns using a machine learning model for analyzing the aforementioned image information, 【0788】 If the aforementioned behavioral pattern is determined to be abnormal, means for generating warning information that has undergone emotional analysis, 【0789】 Means for transferring the aforementioned warning information to a management device, 【0790】 A means for displaying the aforementioned warning information and supporting decisions for taking action, 【0791】 A system that includes this. 【0792】 (Claim 2) 【0793】 The system according to claim 1, characterized in that the video input device includes a plurality of shooting units installed within the facility. 【0794】 (Claim 3) 【0795】 The system according to claim 1, characterized in that the warning information includes detailed information related to the behavior recognized as abnormal. 【0796】 "Application example 2 when combining with an emotional engine" 【0797】 (Claim 1) 【0798】 A means for receiving visual data from an image acquisition device, 【0799】 A means for detecting behavioral patterns using machine learning to analyze the aforementioned visual data, 【0800】 If the detected behavior pattern is determined to be abnormal, means for generating warning information, 【0801】 The analysis results of the aforementioned behavioral patterns are reinforced using an emotion analysis engine, and a means for recognizing emotional states is provided. 【0802】 A means of including emotional state in the aforementioned warning information and notifying the management terminal, 【0803】 A system that includes this. 【0804】 (Claim 2) 【0805】 The system according to claim 1, characterized in that the video acquisition device includes a plurality of recording devices installed within the facility. 【0806】 (Claim 3) 【0807】 The system according to claim 1, characterized in that the warning information includes detailed information and sentiment data regarding the behavior deemed abnormal. [Explanation of Symbols] 【0808】 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

[Claim 1] A means for receiving video from a video acquisition device, A means for identifying behavioral patterns using artificial intelligence for analyzing the aforementioned video, If the identified behavioral pattern is determined to be abnormal, means for generating warning information, Means for transmitting the aforementioned warning information to a management terminal, A system that includes this. [Claim 2] The system according to claim 1, characterized in that the video acquisition device includes a plurality of shooting devices installed within the school. [Claim 3] The system according to claim 1, characterized in that the warning information includes detailed data regarding the behavior deemed abnormal.

Images