system

Abstract

We provide the system. [Solution] Means of acquiring video, Information processing means for pre-processing the video acquired by the video acquisition means, A transmission means for transmitting the anonymized video data from the information processing means to a data center, A detection means that analyzes the video data transmitted by the transmission means using a secure communication protocol in a data center using an AI model to detect abnormal behavior, A notification means for notifying a mobile terminal of the results of detecting the abnormal behavior, 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, the method including: receiving a user utterance; adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot; encoding the prompt; and inputting the encoded prompt into a language model to generate a chatbot utterance as a response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In modern society, problems such as falls and traffic accidents of the elderly and ensuring safety in schools are becoming serious. For these problems, technologies that can detect abnormal behaviors and dangers in advance and enable prompt responses are required. In particular, it is a challenge to achieve this with limited personnel and resources.

Means for Solving the Problems

[0005] In this invention, the environment is monitored in real time using means for acquiring video, and necessary information is organized by information processing means that preprocesses the acquired video. This ensures anonymity, and a transmission means is used to securely transmit the data to a data center. At the data center, the video is analyzed using an advanced AI model, and a detection means that detects abnormal behavior and signs of danger enables a rapid response. Furthermore, security is enhanced by providing a notification means that notifies relevant parties of the detection results.

[0006] "Image acquisition means" refers to a device or process for monitoring the environment and acquiring video data in real time using a camera.

[0007] "Information processing means" refers to methods or technologies for extracting necessary information and pre-processing it for purposes such as privacy protection before analyzing acquired video data.

[0008] "Transmission means" refers to the means for encrypting processed video data and transmitting it to a data center via a secure communication protocol.

[0009] A "data center" is a centralized data processing facility that receives video data sent from transmission devices and performs advanced information analysis on it.

[0010] An "AI model" is a mathematical model that uses machine learning algorithms to detect abnormal behavior or signs of danger from video data.

[0011] The "detection method" is a system that uses an AI model to analyze video data received at a data center and identify abnormal behavior or signs of danger.

[0012] A "notification method" is a method or technology that can immediately inform designated parties of information when abnormal behavior or danger is detected. [Brief explanation of the drawing]

[0013] [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]

[0014] An example of an embodiment of the system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0015] First, the terms used in the following description will be explained.

[0016] 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.

[0017] 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.

[0018] In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0019] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0020] 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."

[0021] [First Embodiment]

[0022] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0023] 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.

[0024] 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).

[0025] 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.

[0026] 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.

[0027] 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.

[0028] 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.

[0029] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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".

[0034] The present invention is realized by a system integrating video acquisition means, information processing means, transmission means, analysis and detection means using an AI model within a data center, and notification means. A specific embodiment thereof is described below.

[0035] This system will primarily be used in elderly care facilities, traffic management systems, and school safety measures. In elderly care facilities, multiple cameras will be installed throughout the facility. These cameras will function as terminals, acquiring video in real time. The acquired video will then be anonymized on the spot by an information processing system, removing any information that could identify faces or individuals.

[0036] Next, the terminal securely transmits this anonymized video data to the data center using a transmission method. Because the transmission method used employs advanced encryption technology, there is no risk of the data being intercepted during transit.

[0037] The server operates within the data center and analyzes received video data using an AI model. The AI ​​model has been trained on past data and can detect abnormal behavior and warning signs with high accuracy. For example, if an elderly person falls, the movement is flagged as abnormal.

[0038] If an anomaly is detected by the detection system, the server immediately issues a warning to the relevant staff or family members via notification. Specifically, notifications are sent using smartphone apps or SMS. Users who receive this notification (e.g., staff or family members) can respond quickly to the scene and ensure the safety of the elderly person.

[0039] As described above, this invention aims to improve safety in various situations in daily life by utilizing AI and camera technology. In particular, it is expected to be used in a variety of settings as it enables efficient detection of anomalies and rapid response within limited resources.

[0040] The following describes the processing flow.

[0041] Step 1:

[0042] The device uses its camera to acquire video footage of the monitored area in real time. High-resolution video data is collected frame by frame to form an initial dataset for processing.

[0043] Step 2:

[0044] The device instantly processes the acquired video data and uses information processing tools to anonymize faces and personal information through methods such as blurring. This allows for the extraction of necessary data while protecting privacy.

[0045] Step 3:

[0046] The terminal transmits anonymized video data to the data center using a transmission method. Encryption technology is used to ensure security during transmission, and the data is transferred using a secure communication protocol.

[0047] Step 4:

[0048] The server inputs the video data received at the data center into the AI ​​model and begins analysis. The AI ​​model uses machine learning algorithms to detect abnormal behavior and signs of danger in the video. In this process, specific behavioral patterns such as falls and violence are flagged.

[0049] Step 5:

[0050] The server detects abnormal behavior flagged by the detection mechanism and immediately sends a warning notification to the relevant parties using the notification mechanism. This notification is sent via email or push notification to smartphones.

[0051] Step 6:

[0052] We will review notifications received by users and take prompt action as needed. For example, facility staff may rush to the location in question to ensure the safety of elderly individuals.

[0053] (Example 1)

[0054] 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."

[0055] In elderly care facilities, traffic management systems, and school safety measures, a secure and efficient system is needed that protects privacy in order to quickly and accurately detect abnormal behavior and immediately notify relevant parties. However, conventional technologies have challenges such as insufficient privacy protection and security of video data, and incomplete accuracy in anomaly detection.

[0056] 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.

[0057] In this invention, the server includes an information processing device for anonymizing video, a transmission device using a secure communication protocol, and a detection device using a generative AI model. This enables highly accurate and rapid detection of abnormal operation and immediate notification while protecting privacy.

[0058] A "video acquisition device" is a device used to record and acquire video in real time within elderly care facilities and other environments.

[0059] An "information processing device" is a device that processes acquired video data and anonymizes information that could identify an individual.

[0060] A "transmission device" is a communication device used to securely transfer processed data to a data center, and it employs advanced encryption technology.

[0061] A "generative AI model" is an artificial intelligence model that learns from past data and detects abnormal behavior or signs of danger.

[0062] A "detection device" is a device that uses a generative AI model to analyze data and identify abnormal behavior.

[0063] A "notification device" is a device used to immediately notify relevant parties of the results of an anomaly detection, and primarily utilizes smartphones or communication devices.

[0064] This invention provides a specific embodiment of an abnormal operation detection system for elderly care facilities and other locations requiring safety management. The system includes a video acquisition device, an information processing device, a secure transmission device, a detection device utilizing a generated AI model, and a notification device for informing relevant parties of abnormalities.

[0065] The terminals install high-resolution cameras in each area of ​​the facility and acquire video in real time. This video is anonymized by an information processing device and processed to prevent the leakage of personal information. Anonymization technologies include face blurring and voice filtering.

[0066] This anonymized data is securely transmitted to the data center by the terminal's transmission device. Advanced encryption techniques, such as AES-256, are used for this transmission to ensure the data cannot be accessed without authorization during transit.

[0067] The server operates within the data center and analyzes incoming data using a generative AI model. This AI model is built using frameworks such as TENSORFLOW® and has the ability to detect abnormal behavior and warning signs with high accuracy. For example, it learns the characteristics of falls among the elderly and immediately flags them as abnormal when detected.

[0068] Any detected anomalies are promptly notified to the user via a notification device. For example, staff within the facility or family members of elderly residents receive warnings via smartphone apps or SMS. This allows users to respond quickly on-site and implement safety measures.

[0069] For example, if an elderly person falls in a facility corridor, the system recognizes the fall and immediately notifies the relevant staff member. This allows the staff to respond quickly and ensure the elderly person's safety.

[0070] Examples of prompt statements to input into a generative AI model include the following:

[0071] "Please describe the specific physical movements that an AI model using TensorFlow focuses on when detecting falls in elderly individuals."

[0072] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0073] Step 1:

[0074] The terminal (camera) acquires real-time video footage from within the elderly care facility. The input is high-resolution video captured by the camera. The terminal has the capability to capture detailed movements within the facility. The output is the raw video data recorded by the camera.

[0075] Step 2:

[0076] The terminal processes the acquired raw video data using an information processing device to anonymize personally identifiable information. Specific operations include face blurring and audio filtering. The input is the raw video data acquired in step 1. The output is anonymized video data with privacy protected.

[0077] Step 3:

[0078] The terminal encrypts the anonymized video data using a transmission device and sends it to the data center. The input is the anonymized video data generated in step 2. Advanced encryption technologies such as AES-256 are used to ensure data security. The output is securely encrypted video data.

[0079] Step 4:

[0080] The server decrypts the encrypted video data received at the data center and begins analysis with the generated AI model. The input is the encrypted data sent to the data center in step 3. The server provides the decrypted data to the AI ​​model for data analysis to detect abnormal behavior or warning signs. The output is whether or not any anomalies were identified.

[0081] Step 5:

[0082] If the server detects abnormal behavior based on the analysis using the detection device, it will notify relevant parties via a notification system. The input is the detection result of the abnormality analyzed in step 4. Specifically, the server generates and sends a warning message using a smartphone app or SMS. The output is the warning notification sent to staff and their families.

[0083] (Application Example 1)

[0084] 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."

[0085] In elderly care facilities, a key challenge is effectively monitoring the safety of elderly residents and enabling prompt responses. Conventional monitoring systems often suffer from delays in detecting abnormal behavior, resulting in delayed responses. Furthermore, ensuring both data anonymity and security simultaneously is crucial.

[0086] 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.

[0087] In this invention, the server includes video acquisition means, information processing means, and transmission means. This enables anonymization of video data, secure data transmission via secure communication, and high-precision detection of abnormal behavior using an AI model.

[0088] "Video acquisition means" refers to a device or system for acquiring video footage of a monitored object in real time.

[0089] "Information processing means" refers to a device or program for anonymizing personally identifiable information from acquired video footage and processing the data.

[0090] "Transmission means" refers to a device or mechanism for transmitting processed video data, using a secure communication protocol, to an external system or data center.

[0091] A "data center" is a facility that includes a group of computers for storing and analyzing received video data.

[0092] An "AI model" is an algorithm that analyzes behavior in video based on past training data and detects abnormal behavior.

[0093] A "detection method" is a function that identifies abnormal behavior from data analyzed using an AI model and flags it.

[0094] A "notification method" refers to a method of informing relevant recipients of detected abnormal behavior, specifically by sending information through apps, messages, etc.

[0095] A "mobile terminal" is a device that a user can carry with them and that can receive data via a network.

[0096] The system for implementing this invention consists of several elements. First, the video acquisition means is an image sensor such as a camera. This allows video data to be collected in real time from the area to be monitored. Next, the terminal is equipped with an information processing means, which removes personally identifiable elements from the acquired video to anonymize it. Software libraries such as OpenCV are used for this information processing.

[0097] Next, the transmission method sends anonymized data to the data center via an encrypted protocol. Communication protocols such as SSL and TLS are used in this process. The data center has a powerful cluster of servers where the AI ​​model operates. A generative AI model using TensorFlow analyzes the video data based on past training data and detects abnormal behavior with high accuracy.

[0098] When abnormal behavior is detected, the server flags it using a dedicated detection mechanism, and a notification is sent to the terminal. Effective notification methods include push notifications via applications on smartphones and tablets, and SMS. This allows users to quickly understand the situation and take necessary actions.

[0099] As a concrete example, if an elderly person falls within a facility, the server immediately detects the movement as abnormal using an AI model. It then sends notifications to staff and family members with smartphones, enabling prompt rescue and care responses. A concrete example of a prompt using the generated AI model is: "Please explain how a fall detection system in an elderly care facility should notify users along with video footage capturing abnormal behavior."

[0100] Thus, the invention can efficiently prioritize the safety of the elderly and other monitored individuals, and improve the quality of daily monitoring systems.

[0101] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0102] Step 1:

[0103] The device uses a camera to acquire video in real time. The input is raw video data from the camera, which is sent to the information processing system. The video data is stored as basic video frames.

[0104] Step 2:

[0105] The device anonymizes video data by removing personally identifiable information from the acquired video data using information processing tools. The input is raw video data, and the output is anonymized video data. Faces and identifiable parts are blurred using the OpenCV library.

[0106] Step 3:

[0107] The terminal transmits anonymized video data to the data center using a transmission method. The input is anonymized video data, and the output is encrypted data. The data is encrypted using the SSL protocol and transmitted securely to the outside.

[0108] Step 4:

[0109] The server decrypts encrypted data arriving at the data center and performs analysis using an AI model. The input is decrypted encrypted video data, and the output is the detection result of abnormal behavior. A generated AI model using TensorFlow analyzes the video and flags abnormal behavior.

[0110] Step 5:

[0111] The server uses notification methods to send notifications to relevant mobile devices regarding detected abnormal behavior. The input is the detected abnormal behavior result, and the output is the notification message. Push notifications and SMS are used to quickly inform users of the anomaly.

[0112] Step 6:

[0113] The user receives a notification, goes directly to the scene if necessary, checks the situation, and takes appropriate action. The input is the notification message, and the output is the user action. Specifically, the user checks the notification and intervenes promptly to ensure the safety of the elderly.

[0114] 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.

[0115] This invention relates to a system for detecting abnormal behavior and recognizing emotions that incorporates an emotion engine in addition to means for acquiring video, means for processing information, means for transmitting information, analysis by an AI model in a data center, and means for processing information and recognizing emotions. This system is intended to contribute to improving safety, particularly in elderly care facilities, traffic management, and educational institutions.

[0116] In this system, the terminal first uses its camera to acquire video data from the target area in real time. The acquired video is anonymized using information processing tools, and important data is extracted. This process ensures that necessary data is secured while firmly protecting individual privacy.

[0117] The anonymized data is securely transmitted to a server located within the data center via a transmission method. Because a secure communication protocol is used for this transmission, data security is robust. On the server, an AI model analyzes the incoming data and detects patterns of abnormal behavior.

[0118] Furthermore, an emotion engine embedded in the server analyzes the emotional state of the subjects using the same dataset. This emotion recognition process makes it possible to understand the emotional factors behind abnormal behavior when it is detected. For example, if anxiety or impatience is detected in the preceding video footage when an elderly person falls, it becomes easier to take measures that include addressing the cause.

[0119] Ultimately, the server generates relevant notifications based on abnormal conditions and detected emotions, and sends them to the relevant parties through notification channels. Users (e.g., facility managers or traffic controllers) can receive these notifications and take quick and appropriate responses that take emotion information into account.

[0120] Thus, by incorporating an emotion engine, the present invention brings further value to conventional anomaly detection systems, achieving improvements in safety and responsiveness.

[0121] The following describes the processing flow.

[0122] Step 1:

[0123] The device monitors the environment and collects video data in real time using its camera. The acquired video data is temporarily stored in memory for processing.

[0124] Step 2:

[0125] The device performs anonymization processing on the stored video data using information processing tools. Specifically, it applies a mosaic effect to faces and parts that can identify individuals, and filters out other unnecessary information.

[0126] Step 3:

[0127] The terminal transmits the anonymized video data to the data center via a transmission method. During this process, encryption technologies such as TLS are used to ensure the data is transferred securely.

[0128] Step 4:

[0129] The server processes the video data received at the data center as input for analysis into an AI model. The model analyzes the movements in the video and detects abnormal behaviors such as falls and sudden movements, which are defined as abnormal actions.

[0130] Step 5:

[0131] The server analyzes the video and simultaneously uses an emotion engine to determine the emotions of the people in the video. Based on the facial expressions and movements recognized by the AI ​​model, it determines whether the subject is showing emotions such as anxiety, anger, or surprise.

[0132] Step 6:

[0133] The server integrates the results of abnormal behavior and emotional states via detection means and sends notifications to relevant parties via notification means. The notifications include details of the detected abnormal behavior and related emotional information.

[0134] Step 7:

[0135] The system reviews notifications received by users and determines a course of action based on abnormal behavior and associated emotional information. For example, if an elderly person falls, facility staff may take measures including psychological support if underlying feelings of anxiety are detected.

[0136] (Example 2)

[0137] 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."

[0138] To improve safety in elderly care facilities, traffic management, and educational institutions, rapid detection of abnormal behavior and understanding the underlying emotions are essential. However, conventional systems have difficulty accurately detecting abnormalities while ensuring individual privacy, and they lack the functionality to analyze emotional factors.

[0139] 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.

[0140] In this invention, the server includes information processing means for anonymizing video data and extracting important information, detection means for detecting abnormal behavior using an AI model, and analysis means equipped with an emotion engine for recognizing emotions from the data. This enables highly accurate anomaly detection and comprehensive situational analysis that takes emotional states into account.

[0141] "Video acquisition means" refers to a device or technology that has the function of capturing video data in real time within a designated area.

[0142] "Information processing means" refers to devices and technologies for anonymizing acquired video data and extracting important information necessary for detecting abnormal behavior.

[0143] "Transmission means" refers to devices and technologies for transmitting anonymized video data to a data center using a secure communication protocol.

[0144] An "artificial intelligence model" is a program based on machine learning and deep learning technologies that is used to analyze large amounts of data and detect abnormal behavior.

[0145] "Detection means" refers to devices or technologies that have the function of identifying abnormal behavior from video data using artificial intelligence models.

[0146] An "emotion engine" is a device or technology that analyzes a subject's behavior and facial expressions to recognize the emotions behind them.

[0147] "Notification means" refers to devices or technologies used to communicate the results of anomaly detection or emotion recognition to relevant users.

[0148] This invention relates to a safety system that detects abnormal behavior and recognizes emotions. The system uses acquired video data to detect abnormal behavior and recognize the underlying emotions. This system is particularly intended for use in elderly care facilities, traffic management, and educational institutions.

[0149] The system uses cameras installed on the terminal to acquire video in real time within a designated area. The video data is acquired at high resolution and an appropriate frame rate, and anonymized using video processing libraries such as OpenCV to prevent the identification of individuals. At the same time, important information is extracted and used to detect abnormal behavior.

[0150] As a means of transmission, the terminal encrypts the data using communication protocols such as TLS to securely send anonymized data to the server. This ensures the security of the data in transit.

[0151] The server analyzes the received data using an artificial intelligence model. Specifically, it uses deep learning technologies such as TensorFlow and PyTorch to identify abnormal behavioral patterns. For example, if an elderly person is judged to be at risk of falling based on certain movements, that information is immediately recorded.

[0152] Furthermore, the server incorporates an emotion engine that analyzes acquired video data to recognize emotional states. For example, it utilizes Microsoft's Azure Emotion Recognition API to estimate emotions from the subject's facial expressions and movements. This process allows for the identification of not only abnormal behavior but also the emotional factors that led to that behavior, which can then be reflected in safety measures.

[0153] Users receive notifications from the server and can take prompt action based on detected abnormal behavior or emotional states. These notifications include details of the relevant events and estimated emotional information, contributing to improved security.

[0154] As a concrete example, a prompt could be input to the AI ​​model in the form of, "Generate prompts to detect abnormal behavior in elderly care facilities and evaluate the associated emotional states." This would enable the system to provide appropriate feedback tailored to the situation on site.

[0155] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0156] Step 1:

[0157] The system uses a camera installed on the terminal to acquire video in real time within a designated area. This process involves processing the video data input by the camera. The video is captured in high resolution, and the frame rate is set as needed. The obtained video data is then extracted as material for anonymization in the next processing step.

[0158] Step 2:

[0159] The system anonymizes the video data acquired by the device using information processing tools and extracts important information. At this stage, a video processing library such as OpenCV is used to blur parts of the subject's face or body, making it impossible to identify individuals. Video data is the input, and anonymized data with masked personal identification information is output. Data related to abnormal behavior, such as falls or suspicious movements, is also extracted simultaneously.

[0160] Step 3:

[0161] The terminal sends anonymized data to the server via a transmission method. During this process, the secure communication protocol TLS is used to encrypt the data. The input is anonymized data, and the output is encrypted data securely transmitted to the server.

[0162] Step 4:

[0163] The server analyzes received data using an artificial intelligence model to detect abnormal behavior. The received data serves as input, and TensorFlow or PyTorch is used to search for abnormal behavior patterns. If abnormal behavior is detected, detailed information is generated as output. This information includes the type of behavior, the time it occurred, and the location.

[0164] Step 5:

[0165] The server uses an emotion engine to analyze the subject's emotional state. The data analyzed is video data related to abnormal behavior that has already been detected. It uses an emotion recognition API, such as Microsoft Azure, to recognize specific emotions (e.g., anxiety, fear). The emotional state is analyzed, and data related to that emotion is generated as output.

[0166] Step 6:

[0167] The server generates a notification based on the detection results and sentiment recognition results, and sends it to the relevant parties. Detected anomaly information and sentiment data are used as input, and output as email or specific application notifications. The notification includes detailed information on abnormal behavior and the results of sentiment analysis.

[0168] Step 7:

[0169] Users receive notifications and take prompt action based on them. The content of the notification is treated as input, and appropriate actions (e.g., on-site verification, safety check for elderly individuals, etc.) are taken as output. This process improves safety and enables quick response.

[0170] (Application Example 2)

[0171] 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".

[0172] Maintaining safety is extremely important in elderly care facilities and other critical management environments. However, conventional abnormal behavior detection systems, while focusing on detecting abnormal behavior, lacked the ability to understand changes in individual emotional states. This made it difficult for facility staff to understand the underlying factors behind the situation, hindering a swift and appropriate response when an abnormality occurred. The present invention aims to solve these problems and provide an abnormal behavior detection and emotion recognition system that enables flexible responses based on a deeper understanding.

[0173] 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.

[0174] In this invention, the server includes a video acquisition means, an information processing means for pre-processing and anonymizing the video acquired by the video acquisition means and extracting important data, and a detection means for analyzing the video using an AI model to detect abnormal behavior and recognize emotional states. This makes it possible to grasp abnormal behavior and emotional changes of residents in elderly care facilities in real time and to take immediate and appropriate action.

[0175] "Image acquisition means" refers to devices or processes that have the function of capturing visual information as digital data via cameras or sensors.

[0176] "Information processing means" refers to devices and algorithms used to process acquired video data, perform anonymization, and extract important data.

[0177] "Transmission means" refers to communication devices and protocols that securely and reliably transfer processed video data to a data center.

[0178] A "data center" is a centralized facility equipped with servers that perform advanced computing processes, and used for managing and analyzing a wide range of data.

[0179] An "AI model" is an algorithm or system trained to analyze data using machine learning techniques and identify specific patterns or abnormal behaviors.

[0180] "Detection means" refers to a function that identifies abnormal behavior or emotional states from video data analyzed using an AI model.

[0181] "Notification means" refers to a method or device for immediately transmitting information about detected abnormal behavior or emotional states to relevant parties.

[0182] "Anonymization" is a processing technique that removes or alters personally identifiable information to protect data privacy.

[0183] "Emotional state" refers to the type and intensity of human emotions identified from the recorded video footage.

[0184] A "communication protocol" is a set of rules and standards used when data is sent and received over a network.

[0185] "Encryption" is a technology that uses a specific algorithm to transform information in order to protect it and prevent third parties from deciphering it.

[0186] The system realizing this invention first acquires video in real time using a camera mounted on a terminal device. This video acquisition means monitors movement within a facility or controlled environment and collects visual information as digital data. The acquired video is anonymized using an information processing means to protect privacy by deleting or modifying personally identifiable information. Image processing libraries such as OpenCV can be used for this process.

[0187] Once processing is complete, the data is sent to a server in the data center via a transmission method. This transmission uses a secure communication protocol, and the data is encrypted, preventing information from being leaked to third parties. The server in the data center uses an AI model to analyze the incoming data and recognize abnormal behavior and emotional states. The AI ​​model is built using machine learning libraries such as TensorFlow and PyTorch, and performs pattern recognition from video data.

[0188] If the server detects abnormal behavior or emotions, a notification system immediately transmits that information to the relevant parties. The notification is sent to mobile devices, etc., and the type of abnormality and the specific actions to be taken are immediately communicated to facility managers and staff, enabling a swift response.

[0189] A concrete example of its application is in nursing homes. Suppose an elderly person falls while walking within the facility, and the preceding video footage detects emotions such as "anxiety" or "confusion." This information is immediately notified to the administrator, allowing for appropriate care and preventative measures to be taken, thereby improving safety within the facility.

[0190] An example of a prompt to be input to a generative AI model is an instruction such as, "Analyze video data that may indicate abnormal behavior in an elderly care facility and identify the associated emotions." This prompt serves as guidance for the AI ​​to perform a specific analytical task.

[0191] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0192] Step 1:

[0193] The device uses its camera to capture real-time video of the environment. The captured video data is input directly into the information processing system. The input data is a raw video stream, and the output is data ready for anonymization.

[0194] Step 2:

[0195] The terminal's information processing means anonymizes the acquired video data and removes elements that could identify individuals. The process used here utilizes an image processing library to mosaic identifiable elements such as faces. This operation generates anonymized video data, allowing processing to continue safely.

[0196] Step 3:

[0197] Anonymized video data is transmitted to the server's data center via a transmission method. During transmission, the data is encrypted using a secure communication protocol, protecting it from unauthorized access and ensuring it arrives at the server safely. The output of the transmission is encrypted data.

[0198] Step 4:

[0199] The server decodes the received data and analyzes the video data using an AI model. The AI ​​model utilizes prompts to detect patterns of abnormal behavior and emotional states using a generative AI model. The data received as input is decoded video information, and the output generates emotional data associated with abnormal behavior.

[0200] Step 5:

[0201] The server generates notifications regarding abnormal behavior and emotional states based on the analysis results. These notifications include a summary of the abnormality and emotions, and are flagged as events requiring immediate attention. The generated notifications are ready to be sent to specific users (e.g., administrators or responsible personnel), and the specific content of the notifications can be viewed on mobile devices, etc.

[0202] Step 6:

[0203] The user receives a notification and takes the necessary action based on its content. The notification includes information such as the time and location of the abnormal behavior and the associated emotional state, enabling a quick and appropriate response. The output information serves as a guideline to support immediate response.

[0204] 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.

[0205] 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.

[0206] 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.

[0207] [Second Embodiment]

[0208] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0209] 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.

[0210] 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).

[0211] 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.

[0212] 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.

[0213] 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).

[0214] 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.

[0215] 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.

[0216] 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.

[0217] 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.

[0218] 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.

[0219] 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".

[0220] The present invention is realized by a system integrating video acquisition means, information processing means, transmission means, analysis and detection means using an AI model within a data center, and notification means. A specific embodiment thereof is described below.

[0221] This system will primarily be used in elderly care facilities, traffic management systems, and school safety measures. In elderly care facilities, multiple cameras will be installed throughout the facility. These cameras will function as terminals, acquiring video in real time. The acquired video will then be anonymized on the spot by an information processing system, removing any information that could identify faces or individuals.

[0222] Next, the terminal securely transmits this anonymized video data to the data center using a transmission method. Because the transmission method used employs advanced encryption technology, there is no risk of the data being intercepted during transit.

[0223] The server operates within the data center and analyzes received video data using an AI model. The AI ​​model has been trained on past data and can detect abnormal behavior and warning signs with high accuracy. For example, if an elderly person falls, the movement is flagged as abnormal.

[0224] If an anomaly is detected by the detection system, the server immediately issues a warning to the relevant staff or family members via notification. Specifically, notifications are sent using smartphone apps or SMS. Users who receive this notification (e.g., staff or family members) can respond quickly to the scene and ensure the safety of the elderly person.

[0225] As described above, this invention aims to improve safety in various situations in daily life by utilizing AI and camera technology. In particular, it is expected to be used in a variety of settings as it enables efficient detection of anomalies and rapid response within limited resources.

[0226] The following describes the processing flow.

[0227] Step 1:

[0228] The device uses its camera to acquire video footage of the monitored area in real time. High-resolution video data is collected frame by frame to form an initial dataset for processing.

[0229] Step 2:

[0230] The device instantly processes the acquired video data and uses information processing tools to anonymize faces and personal information through methods such as blurring. This allows for the extraction of necessary data while protecting privacy.

[0231] Step 3:

[0232] The terminal transmits anonymized video data to the data center using a transmission method. Encryption technology is used to ensure security during transmission, and the data is transferred using a secure communication protocol.

[0233] Step 4:

[0234] The server inputs the video data received at the data center into the AI ​​model and begins analysis. The AI ​​model uses machine learning algorithms to detect abnormal behavior and signs of danger in the video. In this process, specific behavioral patterns such as falls and violence are flagged.

[0235] Step 5:

[0236] The server detects abnormal behavior flagged by the detection mechanism and immediately sends a warning notification to the relevant parties using the notification mechanism. This notification is sent via email or push notification to smartphones.

[0237] Step 6:

[0238] We will review notifications received by users and take prompt action as needed. For example, facility staff may rush to the location in question to ensure the safety of elderly individuals.

[0239] (Example 1)

[0240] 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".

[0241] In elderly care facilities, traffic management systems, and school safety measures, a secure and efficient system is needed that protects privacy in order to quickly and accurately detect abnormal behavior and immediately notify relevant parties. However, conventional technologies have challenges such as insufficient privacy protection and security of video data, and incomplete accuracy in anomaly detection.

[0242] 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.

[0243] In this invention, the server includes an information processing device for anonymizing video, a transmission device using a secure communication protocol, and a detection device using a generative AI model. This enables highly accurate and rapid detection of abnormal operation and immediate notification while protecting privacy.

[0244] A "video acquisition device" is a device used to record and acquire video in real time within elderly care facilities and other environments.

[0245] An "information processing device" is a device that processes acquired video data and anonymizes information that could identify an individual.

[0246] A "transmission device" is a communication device used to securely transfer processed data to a data center, and it employs advanced encryption technology.

[0247] A "generative AI model" is an artificial intelligence model that learns from past data and detects abnormal behavior or signs of danger.

[0248] A "detection device" is a device that uses a generative AI model to analyze data and identify abnormal behavior.

[0249] A "notification device" is a device used to immediately notify relevant parties of the results of an anomaly detection, and primarily utilizes smartphones or communication devices.

[0250] This invention provides a specific embodiment of an abnormal operation detection system for elderly care facilities and other locations requiring safety management. The system includes a video acquisition device, an information processing device, a secure transmission device, a detection device utilizing a generated AI model, and a notification device for informing relevant parties of abnormalities.

[0251] The terminals install high-resolution cameras in each area of ​​the facility and acquire video in real time. This video is anonymized by an information processing device and processed to prevent the leakage of personal information. Anonymization technologies include face blurring and voice filtering.

[0252] This anonymized data is securely transmitted to the data center by the terminal's transmission device. Advanced encryption techniques, such as AES-256, are used for this transmission to ensure the data cannot be accessed without authorization during transit.

[0253] The server operates within the data center and analyzes incoming data using a generative AI model. This AI model is built using frameworks such as TensorFlow and has the ability to detect abnormal behavior and warning signs with high accuracy. For example, it learns the characteristics of falls among the elderly and immediately flags them as abnormal when detected.

[0254] Any detected anomalies are promptly notified to the user via a notification device. For example, staff within the facility or family members of elderly residents receive warnings via smartphone apps or SMS. This allows users to respond quickly on-site and implement safety measures.

[0255] For example, if an elderly person falls in a facility corridor, the system recognizes the fall and immediately notifies the relevant staff member. This allows the staff to respond quickly and ensure the elderly person's safety.

[0256] Examples of prompt statements to input into a generative AI model include the following:

[0257] "Please describe the specific physical movements that an AI model using TensorFlow focuses on when detecting falls in elderly individuals."

[0258] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0259] Step 1:

[0260] The terminal (camera) acquires real-time video footage from within the elderly care facility. The input is high-resolution video captured by the camera. The terminal has the capability to capture detailed movements within the facility. The output is the raw video data recorded by the camera.

[0261] Step 2:

[0262] The terminal processes the acquired raw video data using an information processing device to anonymize personally identifiable information. Specific operations include face blurring and audio filtering. The input is the raw video data acquired in step 1. The output is anonymized video data with privacy protected.

[0263] Step 3:

[0264] The terminal encrypts the anonymized video data using a transmission device and sends it to the data center. The input is the anonymized video data generated in step 2. Advanced encryption technologies such as AES-256 are used to ensure data security. The output is securely encrypted video data.

[0265] Step 4:

[0266] The server decrypts the encrypted video data received at the data center and begins analysis with the generated AI model. The input is the encrypted data sent to the data center in step 3. The server provides the decrypted data to the AI ​​model for data analysis to detect abnormal behavior or warning signs. The output is whether or not any anomalies were identified.

[0267] Step 5:

[0268] If the server detects abnormal behavior based on the analysis using the detection device, it will notify relevant parties via a notification system. The input is the detection result of the abnormality analyzed in step 4. Specifically, the server generates and sends a warning message using a smartphone app or SMS. The output is the warning notification sent to staff and their families.

[0269] (Application Example 1)

[0270] 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."

[0271] In elderly care facilities, a key challenge is effectively monitoring the safety of elderly residents and enabling prompt responses. Conventional monitoring systems often suffer from delays in detecting abnormal behavior, resulting in delayed responses. Furthermore, ensuring both data anonymity and security simultaneously is crucial.

[0272] 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.

[0273] In this invention, the server includes video acquisition means, information processing means, and transmission means. This enables anonymization of video data, secure data transmission via secure communication, and high-precision detection of abnormal behavior using an AI model.

[0274] "Video acquisition means" refers to a device or system for acquiring video footage of a monitored object in real time.

[0275] "Information processing means" refers to a device or program for anonymizing personally identifiable information from acquired video footage and processing the data.

[0276] "Transmission means" refers to a device or mechanism for transmitting processed video data, using a secure communication protocol, to an external system or data center.

[0277] A "data center" is a facility that includes a group of computers for storing and analyzing received video data.

[0278] An "AI model" is an algorithm that analyzes behavior in video based on past training data and detects abnormal behavior.

[0279] A "detection method" is a function that identifies abnormal behavior from data analyzed using an AI model and flags it.

[0280] A "notification method" refers to a method of informing relevant recipients of detected abnormal behavior, specifically by sending information through apps, messages, etc.

[0281] A "mobile terminal" is a device that a user can carry with them and that can receive data via a network.

[0282] The system for implementing this invention consists of several elements. First, the video acquisition means is an image sensor such as a camera. This allows video data to be collected in real time from the area to be monitored. Next, the terminal is equipped with an information processing means, which removes personally identifiable elements from the acquired video to anonymize it. Software libraries such as OpenCV are used for this information processing.

[0283] Next, the transmission method sends anonymized data to the data center via an encrypted protocol. Communication protocols such as SSL and TLS are used in this process. The data center has a powerful cluster of servers where the AI ​​model operates. A generative AI model using TensorFlow analyzes the video data based on past training data and detects abnormal behavior with high accuracy.

[0284] For the detected abnormal behavior, the server uses dedicated detection means to set a flag, and then sends a notification to the terminal. As notification means, push notifications of applications via smartphones or tablets and SMS are effective. This enables the user to quickly grasp the situation and take necessary actions.

[0285] As a specific example, when an elderly person falls within a facility, the server immediately detects the movement as abnormal using an AI model. Then, by sending a notification to staff or family members with smartphones, prompt rescue and care responses become possible. As a specific example of a prompt sentence using the generated AI model, there is a sentence such as "In an elderly care facility, please explain how to send a notification together with the video captured by the fall detection system of abnormal behavior."

[0286] In this way, the invention can efficiently prioritize the safety of the elderly and other monitoring targets and improve the quality of the daily monitoring system.

[0287] The flow of the specific process in Application Example 1 will be described using FIG. 12.

[0288] Step 1:

[0289] The terminal acquires video in real time using a camera. The input is raw video data from the camera, which is sent to the information processing means. The video data is stored as basic video frames.

[0290] Step 2:

[0291] The terminal removes and anonymizes personally identifiable information from the acquired video data using the information processing means. The input is raw video data, and the output is anonymized video data. The face and identifiable parts are blurred using the OpenCV library.

[0292] Step 3:

[0293] The terminal transmits anonymized video data to the data center using a transmission method. The input is anonymized video data, and the output is encrypted data. The data is encrypted using the SSL protocol and transmitted securely to the outside.

[0294] Step 4:

[0295] The server decrypts encrypted data arriving at the data center and performs analysis using an AI model. The input is decrypted encrypted video data, and the output is the detection result of abnormal behavior. A generated AI model using TensorFlow analyzes the video and flags abnormal behavior.

[0296] Step 5:

[0297] The server uses notification methods to send notifications to relevant mobile devices regarding detected abnormal behavior. The input is the detected abnormal behavior result, and the output is the notification message. Push notifications and SMS are used to quickly inform users of the anomaly.

[0298] Step 6:

[0299] The user receives a notification, goes directly to the scene if necessary, checks the situation, and takes appropriate action. The input is the notification message, and the output is the user action. Specifically, the user checks the notification and intervenes promptly to ensure the safety of the elderly.

[0300] 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.

[0301] This invention relates to a system for detecting abnormal behavior and recognizing emotions that incorporates an emotion engine in addition to means for acquiring video, means for processing information, means for transmitting information, analysis by an AI model in a data center, and means for processing information and recognizing emotions. This system is intended to contribute to improving safety, particularly in elderly care facilities, traffic management, and educational institutions.

[0302] In this system, the terminal first uses its camera to acquire video data from the target area in real time. The acquired video is anonymized using information processing tools, and important data is extracted. This process ensures that necessary data is secured while firmly protecting individual privacy.

[0303] The anonymized data is securely transmitted to a server located within the data center via a transmission method. Because a secure communication protocol is used for this transmission, data security is robust. On the server, an AI model analyzes the incoming data and detects patterns of abnormal behavior.

[0304] Furthermore, an emotion engine embedded in the server analyzes the emotional state of the subjects using the same dataset. This emotion recognition process makes it possible to understand the emotional factors behind abnormal behavior when it is detected. For example, if anxiety or impatience is detected in the preceding video footage when an elderly person falls, it becomes easier to take measures that include addressing the cause.

[0305] Ultimately, the server generates relevant notifications based on abnormal conditions and detected emotions, and sends them to the relevant parties through notification channels. Users (e.g., facility managers or traffic controllers) can receive these notifications and take quick and appropriate responses that take emotion information into account.

[0306] Thus, by incorporating an emotion engine, the present invention brings further value to conventional anomaly detection systems, achieving improvements in safety and responsiveness.

[0307] The processing flow will be described below.

[0308] Step 1:

[0309] The terminal monitors the environment and collects video data in real time using a camera. The acquired video data is temporarily stored in memory for processing.

[0310] Step 2:

[0311] The terminal performs anonymization processing on the stored video data using information processing means. Specifically, mosaics are applied to parts that can identify faces or individuals, and other unnecessary information is filtered.

[0312] Step 3:

[0313] The terminal transmits the anonymized video data to the data center by means of transmission. At this time, encryption technology such as TLS is used to ensure that the data is transferred in a secure state.

[0314] Step 4:

[0315] The server processes the video data received at the data center as an input to the AI model for analysis. The model analyzes the actions in the video and detects falls, sudden movements, etc. defined as abnormal behaviors.

[0316] Step 5:

[0317] Simultaneously with the analysis, the server uses an emotion engine to determine the emotions of the people in the video. It is determined whether the subject shows emotions such as anxiety, anger, surprise, etc. from the expressions and movements recognized by the AI model.

[0318] Step 6:

[0319] The server integrates the results of abnormal behaviors and emotional states via detection means and sends notifications to relevant parties through notification means. The notifications include details of the detected abnormal behaviors and related emotional information.

[0320] Step 7:

[0321] The system reviews notifications received by users and determines a course of action based on abnormal behavior and associated emotional information. For example, if an elderly person falls, facility staff may take measures including psychological support if underlying feelings of anxiety are detected.

[0322] (Example 2)

[0323] 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".

[0324] To improve safety in elderly care facilities, traffic management, and educational institutions, rapid detection of abnormal behavior and understanding the underlying emotions are essential. However, conventional systems have difficulty accurately detecting abnormalities while ensuring individual privacy, and they lack the functionality to analyze emotional factors.

[0325] 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.

[0326] In this invention, the server includes information processing means for anonymizing video data and extracting important information, detection means for detecting abnormal behavior using an AI model, and analysis means equipped with an emotion engine for recognizing emotions from the data. This enables highly accurate anomaly detection and comprehensive situational analysis that takes emotional states into account.

[0327] "Video acquisition means" refers to a device or technology that has the function of capturing video data in real time within a designated area.

[0328] "Information processing means" refers to devices and technologies for anonymizing acquired video data and extracting important information necessary for detecting abnormal behavior.

[0329] "Transmission means" refers to devices and technologies for transmitting anonymized video data to a data center using a secure communication protocol.

[0330] An "artificial intelligence model" is a program based on machine learning and deep learning technologies that is used to analyze large amounts of data and detect abnormal behavior.

[0331] "Detection means" refers to devices or technologies that have the function of identifying abnormal behavior from video data using artificial intelligence models.

[0332] An "emotion engine" is a device or technology that analyzes a subject's behavior and facial expressions to recognize the emotions behind them.

[0333] "Notification means" refers to devices or technologies used to communicate the results of anomaly detection or emotion recognition to relevant users.

[0334] This invention relates to a safety system that detects abnormal behavior and recognizes emotions. The system uses acquired video data to detect abnormal behavior and recognize the underlying emotions. This system is particularly intended for use in elderly care facilities, traffic management, and educational institutions.

[0335] The system uses cameras installed on the terminal to acquire video in real time within a designated area. The video data is acquired at high resolution and an appropriate frame rate, and anonymized using video processing libraries such as OpenCV to prevent the identification of individuals. At the same time, important information is extracted and used to detect abnormal behavior.

[0336] As a means of transmission, the terminal encrypts the data using communication protocols such as TLS to securely send anonymized data to the server. This ensures the security of the data in transit.

[0337] The server analyzes the received data using an artificial intelligence model. Specifically, it uses deep learning technologies such as TensorFlow and PyTorch to identify abnormal behavioral patterns. For example, if an elderly person is judged to be at risk of falling based on certain movements, that information is immediately recorded.

[0338] Furthermore, the server incorporates an emotion engine that analyzes acquired video data to recognize emotional states. For example, it utilizes Microsoft's Azure Emotion Recognition API to estimate emotions from the subject's facial expressions and movements. This process allows for the identification of not only abnormal behavior but also the emotional factors that led to that behavior, which can then be reflected in safety measures.

[0339] Users receive notifications from the server and can take prompt action based on detected abnormal behavior or emotional states. These notifications include details of the relevant events and estimated emotional information, contributing to improved security.

[0340] As a concrete example, a prompt could be input to the AI ​​model in the form of, "Generate prompts to detect abnormal behavior in elderly care facilities and evaluate the associated emotional states." This would enable the system to provide appropriate feedback tailored to the situation on site.

[0341] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0342] Step 1:

[0343] The system uses a camera installed on the terminal to acquire video in real time within a designated area. This process involves processing the video data input by the camera. The video is captured in high resolution, and the frame rate is set as needed. The obtained video data is then extracted as material for anonymization in the next processing step.

[0344] Step 2:

[0345] The system anonymizes the video data acquired by the device using information processing tools and extracts important information. At this stage, a video processing library such as OpenCV is used to blur parts of the subject's face or body, making it impossible to identify individuals. Video data is the input, and anonymized data with masked personal identification information is output. Data related to abnormal behavior, such as falls or suspicious movements, is also extracted simultaneously.

[0346] Step 3:

[0347] The terminal sends anonymized data to the server via a transmission method. During this process, the secure communication protocol TLS is used to encrypt the data. The input is anonymized data, and the output is encrypted data securely transmitted to the server.

[0348] Step 4:

[0349] The server analyzes received data using an artificial intelligence model to detect abnormal behavior. The received data serves as input, and TensorFlow or PyTorch is used to search for abnormal behavior patterns. If abnormal behavior is detected, detailed information is generated as output. This information includes the type of behavior, the time it occurred, and the location.

[0350] Step 5:

[0351] The server uses an emotion engine to analyze the subject's emotional state. The data analyzed is video data related to abnormal behavior that has already been detected. It uses an emotion recognition API, such as Microsoft Azure, to recognize specific emotions (e.g., anxiety, fear). The emotional state is analyzed, and data related to that emotion is generated as output.

[0352] Step 6:

[0353] The server generates a notification based on the detection results and sentiment recognition results, and sends it to the relevant parties. Detected anomaly information and sentiment data are used as input, and output as email or specific application notifications. The notification includes detailed information on abnormal behavior and the results of sentiment analysis.

[0354] Step 7:

[0355] Users receive notifications and take prompt action based on them. The content of the notification is treated as input, and appropriate actions (e.g., on-site verification, safety check for elderly individuals, etc.) are taken as output. This process improves safety and enables quick response.

[0356] (Application Example 2)

[0357] 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 as the "terminal".

[0358] Maintaining safety is extremely important in elderly care facilities and other critical management environments. However, conventional abnormal behavior detection systems, while focusing on detecting abnormal behavior, lacked the ability to understand changes in individual emotional states. This made it difficult for facility staff to understand the underlying factors behind the situation, hindering a swift and appropriate response when an abnormality occurred. The present invention aims to solve these problems and provide an abnormal behavior detection and emotion recognition system that enables flexible responses based on a deeper understanding.

[0359] 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.

[0360] In this invention, the server includes a video acquisition means, an information processing means for pre-processing and anonymizing the video acquired by the video acquisition means and extracting important data, and a detection means for analyzing the video using an AI model to detect abnormal behavior and recognize emotional states. This makes it possible to grasp abnormal behavior and emotional changes of residents in elderly care facilities in real time and to take immediate and appropriate action.

[0361] "Image acquisition means" refers to devices or processes that have the function of capturing visual information as digital data via cameras or sensors.

[0362] "Information processing means" refers to devices and algorithms used to process acquired video data, perform anonymization, and extract important data.

[0363] "Transmission means" refers to communication devices and protocols that securely and reliably transfer processed video data to a data center.

[0364] A "data center" is a centralized facility equipped with servers that perform advanced computing processes, and used for managing and analyzing a wide range of data.

[0365] An "AI model" is an algorithm or system trained to analyze data using machine learning techniques and identify specific patterns or abnormal behaviors.

[0366] "Detection means" refers to a function that identifies abnormal behavior or emotional states from video data analyzed using an AI model.

[0367] "Notification means" refers to a method or device for immediately transmitting information about detected abnormal behavior or emotional states to relevant parties.

[0368] "Anonymization" is a processing technique that removes or alters personally identifiable information to protect data privacy.

[0369] "Emotional state" refers to the type and intensity of human emotions identified from the recorded video footage.

[0370] A "communication protocol" is a set of rules and standards used when data is sent and received over a network.

[0371] "Encryption" is a technology that uses a specific algorithm to transform information in order to protect it and prevent third parties from deciphering it.

[0372] The system realizing this invention first acquires video in real time using a camera mounted on a terminal device. This video acquisition means monitors movement within a facility or controlled environment and collects visual information as digital data. The acquired video is anonymized using an information processing means to protect privacy by deleting or modifying personally identifiable information. Image processing libraries such as OpenCV can be used for this process.

[0373] Once processing is complete, the data is sent to a server in the data center via a transmission method. This transmission uses a secure communication protocol, and the data is encrypted, preventing information from being leaked to third parties. The server in the data center uses an AI model to analyze the incoming data and recognize abnormal behavior and emotional states. The AI ​​model is built using machine learning libraries such as TensorFlow and PyTorch, and performs pattern recognition from video data.

[0374] If the server detects abnormal behavior or emotions, a notification system immediately transmits that information to the relevant parties. The notification is sent to mobile devices, etc., and the type of abnormality and the specific actions to be taken are immediately communicated to facility managers and staff, enabling a swift response.

[0375] A concrete example of its application is in nursing homes. Suppose an elderly person falls while walking within the facility, and the preceding video footage detects emotions such as "anxiety" or "confusion." This information is immediately notified to the administrator, allowing for appropriate care and preventative measures to be taken, thereby improving safety within the facility.

[0376] An example of a prompt to be input to a generative AI model is an instruction such as, "Analyze video data that may indicate abnormal behavior in an elderly care facility and identify the associated emotions." This prompt serves as guidance for the AI ​​to perform a specific analytical task.

[0377] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0378] Step 1:

[0379] The device uses its camera to capture real-time video of the environment. The captured video data is input directly into the information processing system. The input data is a raw video stream, and the output is data ready for anonymization.

[0380] Step 2:

[0381] The terminal's information processing means anonymizes the acquired video data and removes elements that could identify individuals. The process used here utilizes an image processing library to mosaic identifiable elements such as faces. This operation generates anonymized video data, allowing processing to continue safely.

[0382] Step 3:

[0383] Anonymized video data is transmitted to the server's data center via a transmission method. During transmission, the data is encrypted using a secure communication protocol, protecting it from unauthorized access and ensuring it arrives at the server safely. The output of the transmission is encrypted data.

[0384] Step 4:

[0385] The server decodes the received data and analyzes the video data using an AI model. The AI ​​model utilizes prompts to detect patterns of abnormal behavior and emotional states using a generative AI model. The data received as input is decoded video information, and the output generates emotional data associated with abnormal behavior.

[0386] Step 5:

[0387] The server generates notifications regarding abnormal behavior and emotional states based on the analysis results. These notifications include a summary of the abnormality and emotions, and are flagged as events requiring immediate attention. The generated notifications are ready to be sent to specific users (e.g., administrators or responsible personnel), and the specific content of the notifications can be viewed on mobile devices, etc.

[0388] Step 6:

[0389] The user receives a notification and takes the necessary action based on its content. The notification includes information such as the time and location of the abnormal behavior and the associated emotional state, enabling a quick and appropriate response. The output information serves as a guideline to support immediate response.

[0390] 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.

[0391] 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.

[0392] 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.

[0393] [Third Embodiment]

[0394] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0395] 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.

[0396] 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).

[0397] 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.

[0398] 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.

[0399] 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).

[0400] 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.

[0401] 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.

[0402] 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.

[0403] 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.

[0404] 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.

[0405] 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".

[0406] The present invention is realized by a system integrating video acquisition means, information processing means, transmission means, analysis and detection means using an AI model within a data center, and notification means. A specific embodiment thereof is described below.

[0407] This system will primarily be used in elderly care facilities, traffic management systems, and school safety measures. In elderly care facilities, multiple cameras will be installed throughout the facility. These cameras will function as terminals, acquiring video in real time. The acquired video will then be anonymized on the spot by an information processing system, removing any information that could identify faces or individuals.

[0408] Next, the terminal securely transmits this anonymized video data to the data center using a transmission method. Because the transmission method used employs advanced encryption technology, there is no risk of the data being intercepted during transit.

[0409] The server operates within the data center and analyzes received video data using an AI model. The AI ​​model has been trained on past data and can detect abnormal behavior and warning signs with high accuracy. For example, if an elderly person falls, the movement is flagged as abnormal.

[0410] If an anomaly is detected by the detection system, the server immediately issues a warning to the relevant staff or family members via notification. Specifically, notifications are sent using smartphone apps or SMS. Users who receive this notification (e.g., staff or family members) can respond quickly to the scene and ensure the safety of the elderly person.

[0411] As described above, this invention aims to improve safety in various situations in daily life by utilizing AI and camera technology. In particular, it is expected to be used in a variety of settings as it enables efficient detection of anomalies and rapid response within limited resources.

[0412] The following describes the processing flow.

[0413] Step 1:

[0414] The device uses its camera to acquire video footage of the monitored area in real time. High-resolution video data is collected frame by frame to form an initial dataset for processing.

[0415] Step 2:

[0416] The device instantly processes the acquired video data and uses information processing tools to anonymize faces and personal information through methods such as blurring. This allows for the extraction of necessary data while protecting privacy.

[0417] Step 3:

[0418] The terminal transmits anonymized video data to the data center using a transmission method. Encryption technology is used to ensure security during transmission, and the data is transferred using a secure communication protocol.

[0419] Step 4:

[0420] The server inputs the video data received at the data center into the AI ​​model and begins analysis. The AI ​​model uses machine learning algorithms to detect abnormal behavior and signs of danger in the video. In this process, specific behavioral patterns such as falls and violence are flagged.

[0421] Step 5:

[0422] The server detects abnormal behavior flagged by the detection mechanism and immediately sends a warning notification to the relevant parties using the notification mechanism. This notification is sent via email or push notification to smartphones.

[0423] Step 6:

[0424] We will review notifications received by users and take prompt action as needed. For example, facility staff may rush to the location in question to ensure the safety of elderly individuals.

[0425] (Example 1)

[0426] 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."

[0427] In elderly care facilities, traffic management systems, and school safety measures, a secure and efficient system is needed that protects privacy in order to quickly and accurately detect abnormal behavior and immediately notify relevant parties. However, conventional technologies have challenges such as insufficient privacy protection and security of video data, and incomplete accuracy in anomaly detection.

[0428] 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.

[0429] In this invention, the server includes an information processing device for anonymizing video, a transmission device using a secure communication protocol, and a detection device using a generative AI model. This enables highly accurate and rapid detection of abnormal operation and immediate notification while protecting privacy.

[0430] A "video acquisition device" is a device used to record and acquire video in real time within elderly care facilities and other environments.

[0431] An "information processing device" is a device that processes acquired video data and anonymizes information that could identify an individual.

[0432] A "transmission device" is a communication device used to securely transfer processed data to a data center, and it employs advanced encryption technology.

[0433] A "generative AI model" is an artificial intelligence model that learns from past data and detects abnormal behavior or signs of danger.

[0434] A "detection device" is a device that uses a generative AI model to analyze data and identify abnormal behavior.

[0435] A "notification device" is a device used to immediately notify relevant parties of the results of an anomaly detection, and primarily utilizes smartphones or communication devices.

[0436] This invention provides a specific embodiment of an abnormal operation detection system for elderly care facilities and other locations requiring safety management. The system includes a video acquisition device, an information processing device, a secure transmission device, a detection device utilizing a generated AI model, and a notification device for informing relevant parties of abnormalities.

[0437] The terminals install high-resolution cameras in each area of ​​the facility and acquire video in real time. This video is anonymized by an information processing device and processed to prevent the leakage of personal information. Anonymization technologies include face blurring and voice filtering.

[0438] This anonymized data is securely transmitted to the data center by the terminal's transmission device. Advanced encryption techniques, such as AES-256, are used for this transmission to ensure the data cannot be accessed without authorization during transit.

[0439] The server operates within the data center and analyzes incoming data using a generative AI model. This AI model is built using frameworks such as TensorFlow and has the ability to detect abnormal behavior and warning signs with high accuracy. For example, it learns the characteristics of falls among the elderly and immediately flags them as abnormal when detected.

[0440] Any detected anomalies are promptly notified to the user via a notification device. For example, staff within the facility or family members of elderly residents receive warnings via smartphone apps or SMS. This allows users to respond quickly on-site and implement safety measures.

[0441] For example, if an elderly person falls in a facility corridor, the system recognizes the fall and immediately notifies the relevant staff member. This allows the staff to respond quickly and ensure the elderly person's safety.

[0442] Examples of prompt statements to input into a generative AI model include the following:

[0443] "Please describe the specific physical movements that an AI model using TensorFlow focuses on when detecting falls in elderly individuals."

[0444] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0445] Step 1:

[0446] The terminal (camera) acquires real-time video footage from within the elderly care facility. The input is high-resolution video captured by the camera. The terminal has the capability to capture detailed movements within the facility. The output is the raw video data recorded by the camera.

[0447] Step 2:

[0448] The terminal processes the acquired raw video data using an information processing device to anonymize personally identifiable information. Specific operations include face blurring and audio filtering. The input is the raw video data acquired in step 1. The output is anonymized video data with privacy protected.

[0449] Step 3:

[0450] The terminal encrypts the anonymized video data using a transmission device and sends it to the data center. The input is the anonymized video data generated in step 2. Advanced encryption technologies such as AES-256 are used to ensure data security. The output is securely encrypted video data.

[0451] Step 4:

[0452] The server decrypts the encrypted video data received at the data center and begins analysis with the generated AI model. The input is the encrypted data sent to the data center in step 3. The server provides the decrypted data to the AI ​​model for data analysis to detect abnormal behavior or warning signs. The output is whether or not any anomalies were identified.

[0453] Step 5:

[0454] If the server detects abnormal behavior based on the analysis using the detection device, it will notify relevant parties via a notification system. The input is the detection result of the abnormality analyzed in step 4. Specifically, the server generates and sends a warning message using a smartphone app or SMS. The output is the warning notification sent to staff and their families.

[0455] (Application Example 1)

[0456] 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."

[0457] In elderly care facilities, a key challenge is effectively monitoring the safety of elderly residents and enabling prompt responses. Conventional monitoring systems often suffer from delays in detecting abnormal behavior, resulting in delayed responses. Furthermore, ensuring both data anonymity and security simultaneously is crucial.

[0458] 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.

[0459] In this invention, the server includes video acquisition means, information processing means, and transmission means. This enables anonymization of video data, secure data transmission via secure communication, and high-precision detection of abnormal behavior using an AI model.

[0460] "Video acquisition means" refers to a device or system for acquiring video footage of a monitored object in real time.

[0461] "Information processing means" refers to a device or program for anonymizing personally identifiable information from acquired video footage and processing the data.

[0462] "Transmission means" refers to a device or mechanism for transmitting processed video data, using a secure communication protocol, to an external system or data center.

[0463] A "data center" is a facility that includes a group of computers for storing and analyzing received video data.

[0464] An "AI model" is an algorithm that analyzes behavior in video based on past training data and detects abnormal behavior.

[0465] A "detection method" is a function that identifies abnormal behavior from data analyzed using an AI model and flags it.

[0466] A "notification method" refers to a method of informing relevant recipients of detected abnormal behavior, specifically by sending information through apps, messages, etc.

[0467] A "mobile terminal" is a device that a user can carry with them and that can receive data via a network.

[0468] The system for implementing this invention consists of several elements. First, the video acquisition means is an image sensor such as a camera. This allows video data to be collected in real time from the area to be monitored. Next, the terminal is equipped with an information processing means, which removes personally identifiable elements from the acquired video to anonymize it. Software libraries such as OpenCV are used for this information processing.

[0469] Next, the transmission method sends anonymized data to the data center via an encrypted protocol. Communication protocols such as SSL and TLS are used in this process. The data center has a powerful cluster of servers where the AI ​​model operates. A generative AI model using TensorFlow analyzes the video data based on past training data and detects abnormal behavior with high accuracy.

[0470] When abnormal behavior is detected, the server flags it using a dedicated detection mechanism, and a notification is sent to the terminal. Effective notification methods include push notifications via applications on smartphones and tablets, and SMS. This allows users to quickly understand the situation and take necessary actions.

[0471] As a concrete example, if an elderly person falls within a facility, the server immediately detects the movement as abnormal using an AI model. It then sends notifications to staff and family members with smartphones, enabling prompt rescue and care responses. A concrete example of a prompt using the generated AI model is: "Please explain how a fall detection system in an elderly care facility should notify users along with video footage capturing abnormal behavior."

[0472] Thus, the invention can efficiently prioritize the safety of the elderly and other monitored individuals, and improve the quality of daily monitoring systems.

[0473] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0474] Step 1:

[0475] The device uses a camera to acquire video in real time. The input is raw video data from the camera, which is sent to the information processing system. The video data is stored as basic video frames.

[0476] Step 2:

[0477] The device anonymizes video data by removing personally identifiable information from the acquired video data using information processing tools. The input is raw video data, and the output is anonymized video data. Faces and identifiable parts are blurred using the OpenCV library.

[0478] Step 3:

[0479] The terminal transmits anonymized video data to the data center using a transmission method. The input is anonymized video data, and the output is encrypted data. The data is encrypted using the SSL protocol and transmitted securely to the outside.

[0480] Step 4:

[0481] The server decrypts encrypted data arriving at the data center and performs analysis using an AI model. The input is decrypted encrypted video data, and the output is the detection result of abnormal behavior. A generated AI model using TensorFlow analyzes the video and flags abnormal behavior.

[0482] Step 5:

[0483] The server uses notification methods to send notifications to relevant mobile devices regarding detected abnormal behavior. The input is the detected abnormal behavior result, and the output is the notification message. Push notifications and SMS are used to quickly inform users of the anomaly.

[0484] Step 6:

[0485] The user receives a notification, goes directly to the scene if necessary, checks the situation, and takes appropriate action. The input is the notification message, and the output is the user action. Specifically, the user checks the notification and intervenes promptly to ensure the safety of the elderly.

[0486] 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.

[0487] This invention relates to a system for detecting abnormal behavior and recognizing emotions that incorporates an emotion engine in addition to means for acquiring video, means for processing information, means for transmitting information, analysis by an AI model in a data center, and means for processing information and recognizing emotions. This system is intended to contribute to improving safety, particularly in elderly care facilities, traffic management, and educational institutions.

[0488] In this system, the terminal first uses its camera to acquire video data from the target area in real time. The acquired video is anonymized using information processing tools, and important data is extracted. This process ensures that necessary data is secured while firmly protecting individual privacy.

[0489] The anonymized data is securely transmitted to a server located within the data center via a transmission method. Because a secure communication protocol is used for this transmission, data security is robust. On the server, an AI model analyzes the incoming data and detects patterns of abnormal behavior.

[0490] Furthermore, an emotion engine embedded in the server analyzes the emotional state of the subjects using the same dataset. This emotion recognition process makes it possible to understand the emotional factors behind abnormal behavior when it is detected. For example, if anxiety or impatience is detected in the preceding video footage when an elderly person falls, it becomes easier to take measures that include addressing the cause.

[0491] Ultimately, the server generates relevant notifications based on abnormal conditions and detected emotions, and sends them to the relevant parties through notification channels. Users (e.g., facility managers or traffic controllers) can receive these notifications and take quick and appropriate responses that take emotion information into account.

[0492] Thus, by incorporating an emotion engine, the present invention brings further value to conventional anomaly detection systems, achieving improvements in safety and responsiveness.

[0493] The following describes the processing flow.

[0494] Step 1:

[0495] The device monitors the environment and collects video data in real time using its camera. The acquired video data is temporarily stored in memory for processing.

[0496] Step 2:

[0497] The device performs anonymization processing on the stored video data using information processing tools. Specifically, it applies a mosaic effect to faces and parts that can identify individuals, and filters out other unnecessary information.

[0498] Step 3:

[0499] The terminal transmits the anonymized video data to the data center via a transmission method. During this process, encryption technologies such as TLS are used to ensure the data is transferred securely.

[0500] Step 4:

[0501] The server processes the video data received at the data center as input for analysis into an AI model. The model analyzes the movements in the video and detects abnormal behaviors such as falls and sudden movements, which are defined as abnormal actions.

[0502] Step 5:

[0503] The server analyzes the video and simultaneously uses an emotion engine to determine the emotions of the people in the video. Based on the facial expressions and movements recognized by the AI ​​model, it determines whether the subject is showing emotions such as anxiety, anger, or surprise.

[0504] Step 6:

[0505] The server integrates the results of abnormal behavior and emotional states via detection means and sends notifications to relevant parties via notification means. The notifications include details of the detected abnormal behavior and related emotional information.

[0506] Step 7:

[0507] The system reviews notifications received by users and determines a course of action based on abnormal behavior and associated emotional information. For example, if an elderly person falls, facility staff may take measures including psychological support if underlying feelings of anxiety are detected.

[0508] (Example 2)

[0509] 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."

[0510] To improve safety in elderly care facilities, traffic management, and educational institutions, rapid detection of abnormal behavior and understanding the underlying emotions are essential. However, conventional systems have difficulty accurately detecting abnormalities while ensuring individual privacy, and they lack the functionality to analyze emotional factors.

[0511] 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.

[0512] In this invention, the server includes information processing means for anonymizing video data and extracting important information, detection means for detecting abnormal behavior using an AI model, and analysis means equipped with an emotion engine for recognizing emotions from the data. This enables highly accurate anomaly detection and comprehensive situational analysis that takes emotional states into account.

[0513] "Video acquisition means" refers to a device or technology that has the function of capturing video data in real time within a designated area.

[0514] "Information processing means" refers to devices and technologies for anonymizing acquired video data and extracting important information necessary for detecting abnormal behavior.

[0515] "Transmission means" refers to devices and technologies for transmitting anonymized video data to a data center using a secure communication protocol.

[0516] An "artificial intelligence model" is a program based on machine learning and deep learning technologies that is used to analyze large amounts of data and detect abnormal behavior.

[0517] "Detection means" refers to devices or technologies that have the function of identifying abnormal behavior from video data using artificial intelligence models.

[0518] An "emotion engine" is a device or technology that analyzes a subject's behavior and facial expressions to recognize the emotions behind them.

[0519] "Notification means" refers to devices or technologies used to communicate the results of anomaly detection or emotion recognition to relevant users.

[0520] This invention relates to a safety system that detects abnormal behavior and recognizes emotions. The system uses acquired video data to detect abnormal behavior and recognize the underlying emotions. This system is particularly intended for use in elderly care facilities, traffic management, and educational institutions.

[0521] The system uses cameras installed on the terminal to acquire video in real time within a designated area. The video data is acquired at high resolution and an appropriate frame rate, and anonymized using video processing libraries such as OpenCV to prevent the identification of individuals. At the same time, important information is extracted and used to detect abnormal behavior.

[0522] As a means of transmission, the terminal encrypts the data using communication protocols such as TLS to securely send anonymized data to the server. This ensures the security of the data in transit.

[0523] The server analyzes the received data using an artificial intelligence model. Specifically, it uses deep learning technologies such as TensorFlow and PyTorch to identify abnormal behavioral patterns. For example, if an elderly person is judged to be at risk of falling based on certain movements, that information is immediately recorded.

[0524] Furthermore, the server incorporates an emotion engine that analyzes acquired video data to recognize emotional states. For example, it utilizes Microsoft's Azure Emotion Recognition API to estimate emotions from the subject's facial expressions and movements. This process allows for the identification of not only abnormal behavior but also the emotional factors that led to that behavior, which can then be reflected in safety measures.

[0525] Users receive notifications from the server and can take prompt action based on detected abnormal behavior or emotional states. These notifications include details of the relevant events and estimated emotional information, contributing to improved security.

[0526] As a concrete example, a prompt could be input to the AI ​​model in the form of, "Generate prompts to detect abnormal behavior in elderly care facilities and evaluate the associated emotional states." This would enable the system to provide appropriate feedback tailored to the situation on site.

[0527] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0528] Step 1:

[0529] The system uses a camera installed on the terminal to acquire video in real time within a designated area. This process involves processing the video data input by the camera. The video is captured in high resolution, and the frame rate is set as needed. The obtained video data is then extracted as material for anonymization in the next processing step.

[0530] Step 2:

[0531] The system anonymizes the video data acquired by the device using information processing tools and extracts important information. At this stage, a video processing library such as OpenCV is used to blur parts of the subject's face or body, making it impossible to identify individuals. Video data is the input, and anonymized data with masked personal identification information is output. Data related to abnormal behavior, such as falls or suspicious movements, is also extracted simultaneously.

[0532] Step 3:

[0533] The terminal sends anonymized data to the server via a transmission method. During this process, the secure communication protocol TLS is used to encrypt the data. The input is anonymized data, and the output is encrypted data securely transmitted to the server.

[0534] Step 4:

[0535] The server analyzes received data using an artificial intelligence model to detect abnormal behavior. The received data serves as input, and TensorFlow or PyTorch is used to search for abnormal behavior patterns. If abnormal behavior is detected, detailed information is generated as output. This information includes the type of behavior, the time it occurred, and the location.

[0536] Step 5:

[0537] The server uses an emotion engine to analyze the subject's emotional state. The data analyzed is video data related to abnormal behavior that has already been detected. It uses an emotion recognition API, such as Microsoft Azure, to recognize specific emotions (e.g., anxiety, fear). The emotional state is analyzed, and data related to that emotion is generated as output.

[0538] Step 6:

[0539] The server generates a notification based on the detection results and sentiment recognition results, and sends it to the relevant parties. Detected anomaly information and sentiment data are used as input, and output as email or specific application notifications. The notification includes detailed information on abnormal behavior and the results of sentiment analysis.

[0540] Step 7:

[0541] Users receive notifications and take prompt action based on them. The content of the notification is treated as input, and appropriate actions (e.g., on-site verification, safety check for elderly individuals, etc.) are taken as output. This process improves safety and enables quick response.

[0542] (Application Example 2)

[0543] 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."

[0544] Maintaining safety is extremely important in elderly care facilities and other critical management environments. However, conventional abnormal behavior detection systems, while focusing on detecting abnormal behavior, lacked the ability to understand changes in individual emotional states. This made it difficult for facility staff to understand the underlying factors behind the situation, hindering a swift and appropriate response when an abnormality occurred. The present invention aims to solve these problems and provide an abnormal behavior detection and emotion recognition system that enables flexible responses based on a deeper understanding.

[0545] 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.

[0546] In this invention, the server includes a video acquisition means, an information processing means for pre-processing and anonymizing the video acquired by the video acquisition means and extracting important data, and a detection means for analyzing the video using an AI model to detect abnormal behavior and recognize emotional states. This makes it possible to grasp abnormal behavior and emotional changes of residents in elderly care facilities in real time and to take immediate and appropriate action.

[0547] "Image acquisition means" refers to devices or processes that have the function of capturing visual information as digital data via cameras or sensors.

[0548] "Information processing means" refers to devices and algorithms used to process acquired video data, perform anonymization, and extract important data.

[0549] "Transmission means" refers to communication devices and protocols that securely and reliably transfer processed video data to a data center.

[0550] A "data center" is a centralized facility equipped with servers that perform advanced computing processes, and used for managing and analyzing a wide range of data.

[0551] An "AI model" is an algorithm or system trained to analyze data using machine learning techniques and identify specific patterns or abnormal behaviors.

[0552] "Detection means" refers to a function that identifies abnormal behavior or emotional states from video data analyzed using an AI model.

[0553] "Notification means" refers to a method or device for immediately transmitting information about detected abnormal behavior or emotional states to relevant parties.

[0554] "Anonymization" is a processing technique that removes or alters personally identifiable information to protect data privacy.

[0555] "Emotional state" refers to the type and intensity of human emotions identified from the recorded video footage.

[0556] A "communication protocol" is a set of rules and standards used when data is sent and received over a network.

[0557] "Encryption" is a technology that uses a specific algorithm to transform information in order to protect it and prevent third parties from deciphering it.

[0558] The system realizing this invention first acquires video in real time using a camera mounted on a terminal device. This video acquisition means monitors movement within a facility or controlled environment and collects visual information as digital data. The acquired video is anonymized using an information processing means to protect privacy by deleting or modifying personally identifiable information. Image processing libraries such as OpenCV can be used for this process.

[0559] Once processing is complete, the data is sent to a server in the data center via a transmission method. This transmission uses a secure communication protocol, and the data is encrypted, preventing information from being leaked to third parties. The server in the data center uses an AI model to analyze the incoming data and recognize abnormal behavior and emotional states. The AI ​​model is built using machine learning libraries such as TensorFlow and PyTorch, and performs pattern recognition from video data.

[0560] If the server detects abnormal behavior or emotions, a notification system immediately transmits that information to the relevant parties. The notification is sent to mobile devices, etc., and the type of abnormality and the specific actions to be taken are immediately communicated to facility managers and staff, enabling a swift response.

[0561] A concrete example of its application is in nursing homes. Suppose an elderly person falls while walking within the facility, and the preceding video footage detects emotions such as "anxiety" or "confusion." This information is immediately notified to the administrator, allowing for appropriate care and preventative measures to be taken, thereby improving safety within the facility.

[0562] An example of a prompt to be input to a generative AI model is an instruction such as, "Analyze video data that may indicate abnormal behavior in an elderly care facility and identify the associated emotions." This prompt serves as guidance for the AI ​​to perform a specific analytical task.

[0563] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0564] Step 1:

[0565] The device uses its camera to capture real-time video of the environment. The captured video data is input directly into the information processing system. The input data is a raw video stream, and the output is data ready for anonymization.

[0566] Step 2:

[0567] The terminal's information processing means anonymizes the acquired video data and removes elements that could identify individuals. The process used here utilizes an image processing library to mosaic identifiable elements such as faces. This operation generates anonymized video data, allowing processing to continue safely.

[0568] Step 3:

[0569] Anonymized video data is transmitted to the server's data center via a transmission method. During transmission, the data is encrypted using a secure communication protocol, protecting it from unauthorized access and ensuring it arrives at the server safely. The output of the transmission is encrypted data.

[0570] Step 4:

[0571] The server decodes the received data and analyzes the video data using an AI model. The AI ​​model utilizes prompts to detect patterns of abnormal behavior and emotional states using a generative AI model. The data received as input is decoded video information, and the output generates emotional data associated with abnormal behavior.

[0572] Step 5:

[0573] The server generates notifications regarding abnormal behavior and emotional states based on the analysis results. These notifications include a summary of the abnormality and emotions, and are flagged as events requiring immediate attention. The generated notifications are ready to be sent to specific users (e.g., administrators or responsible personnel), and the specific content of the notifications can be viewed on mobile devices, etc.

[0574] Step 6:

[0575] The user receives a notification and takes the necessary action based on its content. The notification includes information such as the time and location of the abnormal behavior and the associated emotional state, enabling a quick and appropriate response. The output information serves as a guideline to support immediate response.

[0576] 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.

[0577] 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.

[0578] 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.

[0579] [Fourth Embodiment]

[0580] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0581] 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.

[0582] 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).

[0583] 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.

[0584] 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.

[0585] 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).

[0586] 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.

[0587] 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.

[0588] 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.

[0589] 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.

[0590] 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.

[0591] 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.

[0592] 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".

[0593] The present invention is realized by a system integrating video acquisition means, information processing means, transmission means, analysis and detection means using an AI model within a data center, and notification means. A specific embodiment thereof is described below.

[0594] This system will primarily be used in elderly care facilities, traffic management systems, and school safety measures. In elderly care facilities, multiple cameras will be installed throughout the facility. These cameras will function as terminals, acquiring video in real time. The acquired video will then be anonymized on the spot by an information processing system, removing any information that could identify faces or individuals.

[0595] Next, the terminal securely transmits this anonymized video data to the data center using a transmission method. Because the transmission method used employs advanced encryption technology, there is no risk of the data being intercepted during transit.

[0596] The server operates within the data center and analyzes received video data using an AI model. The AI ​​model has been trained on past data and can detect abnormal behavior and warning signs with high accuracy. For example, if an elderly person falls, the movement is flagged as abnormal.

[0597] If an anomaly is detected by the detection system, the server immediately issues a warning to the relevant staff or family members via notification. Specifically, notifications are sent using smartphone apps or SMS. Users who receive this notification (e.g., staff or family members) can respond quickly to the scene and ensure the safety of the elderly person.

[0598] As described above, this invention aims to improve safety in various situations in daily life by utilizing AI and camera technology. In particular, it is expected to be used in a variety of settings as it enables efficient detection of anomalies and rapid response within limited resources.

[0599] The following describes the processing flow.

[0600] Step 1:

[0601] The device uses its camera to acquire video footage of the monitored area in real time. High-resolution video data is collected frame by frame to form an initial dataset for processing.

[0602] Step 2:

[0603] The device instantly processes the acquired video data and uses information processing tools to anonymize faces and personal information through methods such as blurring. This allows for the extraction of necessary data while protecting privacy.

[0604] Step 3:

[0605] The terminal transmits anonymized video data to the data center using a transmission method. Encryption technology is used to ensure security during transmission, and the data is transferred using a secure communication protocol.

[0606] Step 4:

[0607] The server inputs the video data received at the data center into the AI ​​model and begins analysis. The AI ​​model uses machine learning algorithms to detect abnormal behavior and signs of danger in the video. In this process, specific behavioral patterns such as falls and violence are flagged.

[0608] Step 5:

[0609] The server detects abnormal behavior flagged by the detection mechanism and immediately sends a warning notification to the relevant parties using the notification mechanism. This notification is sent via email or push notification to smartphones.

[0610] Step 6:

[0611] We will review notifications received by users and take prompt action as needed. For example, facility staff may rush to the location in question to ensure the safety of elderly individuals.

[0612] (Example 1)

[0613] 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".

[0614] In elderly care facilities, traffic management systems, and school safety measures, a secure and efficient system is needed that protects privacy in order to quickly and accurately detect abnormal behavior and immediately notify relevant parties. However, conventional technologies have challenges such as insufficient privacy protection and security of video data, and incomplete accuracy in anomaly detection.

[0615] 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.

[0616] In this invention, the server includes an information processing device for anonymizing video, a transmission device using a secure communication protocol, and a detection device using a generative AI model. This enables highly accurate and rapid detection of abnormal operation and immediate notification while protecting privacy.

[0617] A "video acquisition device" is a device used to record and acquire video in real time within elderly care facilities and other environments.

[0618] An "information processing device" is a device that processes acquired video data and anonymizes information that could identify an individual.

[0619] A "transmission device" is a communication device used to securely transfer processed data to a data center, and it employs advanced encryption technology.

[0620] A "generative AI model" is an artificial intelligence model that learns from past data and detects abnormal behavior or signs of danger.

[0621] A "detection device" is a device that uses a generative AI model to analyze data and identify abnormal behavior.

[0622] A "notification device" is a device used to immediately notify relevant parties of the results of an anomaly detection, and primarily utilizes smartphones or communication devices.

[0623] This invention provides a specific embodiment of an abnormal operation detection system for elderly care facilities and other locations requiring safety management. The system includes a video acquisition device, an information processing device, a secure transmission device, a detection device utilizing a generated AI model, and a notification device for informing relevant parties of abnormalities.

[0624] The terminals install high-resolution cameras in each area of ​​the facility and acquire video in real time. This video is anonymized by an information processing device and processed to prevent the leakage of personal information. Anonymization technologies include face blurring and voice filtering.

[0625] This anonymized data is securely transmitted to the data center by the terminal's transmission device. Advanced encryption techniques, such as AES-256, are used for this transmission to ensure the data cannot be accessed without authorization during transit.

[0626] The server operates within the data center and analyzes incoming data using a generative AI model. This AI model is built using frameworks such as TensorFlow and has the ability to detect abnormal behavior and warning signs with high accuracy. For example, it learns the characteristics of falls among the elderly and immediately flags them as abnormal when detected.

[0627] Any detected anomalies are promptly notified to the user via a notification device. For example, staff within the facility or family members of elderly residents receive warnings via smartphone apps or SMS. This allows users to respond quickly on-site and implement safety measures.

[0628] For example, if an elderly person falls in a facility corridor, the system recognizes the fall and immediately notifies the relevant staff member. This allows the staff to respond quickly and ensure the elderly person's safety.

[0629] Examples of prompt statements to input into a generative AI model include the following:

[0630] "Please describe the specific physical movements that an AI model using TensorFlow focuses on when detecting falls in elderly individuals."

[0631] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0632] Step 1:

[0633] The terminal (camera) acquires real-time video footage from within the elderly care facility. The input is high-resolution video captured by the camera. The terminal has the capability to capture detailed movements within the facility. The output is the raw video data recorded by the camera.

[0634] Step 2:

[0635] The terminal processes the acquired raw video data using an information processing device to anonymize personally identifiable information. Specific operations include face blurring and audio filtering. The input is the raw video data acquired in step 1. The output is anonymized video data with privacy protected.

[0636] Step 3:

[0637] The terminal encrypts the anonymized video data using a transmission device and sends it to the data center. The input is the anonymized video data generated in step 2. Advanced encryption technologies such as AES-256 are used to ensure data security. The output is securely encrypted video data.

[0638] Step 4:

[0639] The server decrypts the encrypted video data received at the data center and begins analysis with the generated AI model. The input is the encrypted data sent to the data center in step 3. The server provides the decrypted data to the AI ​​model for data analysis to detect abnormal behavior or warning signs. The output is whether or not any anomalies were identified.

[0640] Step 5:

[0641] If the server detects abnormal behavior based on the analysis using the detection device, it will notify relevant parties via a notification system. The input is the detection result of the abnormality analyzed in step 4. Specifically, the server generates and sends a warning message using a smartphone app or SMS. The output is the warning notification sent to staff and their families.

[0642] (Application Example 1)

[0643] 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".

[0644] In elderly care facilities, a key challenge is effectively monitoring the safety of elderly residents and enabling prompt responses. Conventional monitoring systems often suffer from delays in detecting abnormal behavior, resulting in delayed responses. Furthermore, ensuring both data anonymity and security simultaneously is crucial.

[0645] 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.

[0646] In this invention, the server includes video acquisition means, information processing means, and transmission means. This enables anonymization of video data, secure data transmission via secure communication, and high-precision detection of abnormal behavior using an AI model.

[0647] "Video acquisition means" refers to a device or system for acquiring video footage of a monitored object in real time.

[0648] "Information processing means" refers to a device or program for anonymizing personally identifiable information from acquired video footage and processing the data.

[0649] "Transmission means" refers to a device or mechanism for transmitting processed video data, using a secure communication protocol, to an external system or data center.

[0650] A "data center" is a facility that includes a group of computers for storing and analyzing received video data.

[0651] An "AI model" is an algorithm that analyzes behavior in video based on past training data and detects abnormal behavior.

[0652] A "detection method" is a function that identifies abnormal behavior from data analyzed using an AI model and flags it.

[0653] A "notification method" refers to a method of informing relevant recipients of detected abnormal behavior, specifically by sending information through apps, messages, etc.

[0654] A "mobile terminal" is a device that a user can carry with them and that can receive data via a network.

[0655] The system for implementing this invention consists of several elements. First, the video acquisition means is an image sensor such as a camera. This allows video data to be collected in real time from the area to be monitored. Next, the terminal is equipped with an information processing means, which removes personally identifiable elements from the acquired video to anonymize it. Software libraries such as OpenCV are used for this information processing.

[0656] Next, the transmission method sends anonymized data to the data center via an encrypted protocol. Communication protocols such as SSL and TLS are used in this process. The data center has a powerful cluster of servers where the AI ​​model operates. A generative AI model using TensorFlow analyzes the video data based on past training data and detects abnormal behavior with high accuracy.

[0657] When abnormal behavior is detected, the server flags it using a dedicated detection mechanism, and a notification is sent to the terminal. Effective notification methods include push notifications via applications on smartphones and tablets, and SMS. This allows users to quickly understand the situation and take necessary actions.

[0658] As a concrete example, if an elderly person falls within a facility, the server immediately detects the movement as abnormal using an AI model. It then sends notifications to staff and family members with smartphones, enabling prompt rescue and care responses. A concrete example of a prompt using the generated AI model is: "Please explain how a fall detection system in an elderly care facility should notify users along with video footage capturing abnormal behavior."

[0659] Thus, the invention can efficiently prioritize the safety of the elderly and other monitored individuals, and improve the quality of daily monitoring systems.

[0660] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0661] Step 1:

[0662] The device uses a camera to acquire video in real time. The input is raw video data from the camera, which is sent to the information processing system. The video data is stored as basic video frames.

[0663] Step 2:

[0664] The device anonymizes video data by removing personally identifiable information from the acquired video data using information processing tools. The input is raw video data, and the output is anonymized video data. Faces and identifiable parts are blurred using the OpenCV library.

[0665] Step 3:

[0666] The terminal transmits anonymized video data to the data center using a transmission method. The input is anonymized video data, and the output is encrypted data. The data is encrypted using the SSL protocol and transmitted securely to the outside.

[0667] Step 4:

[0668] The server decrypts encrypted data arriving at the data center and performs analysis using an AI model. The input is decrypted encrypted video data, and the output is the detection result of abnormal behavior. A generated AI model using TensorFlow analyzes the video and flags abnormal behavior.

[0669] Step 5:

[0670] The server uses notification methods to send notifications to relevant mobile devices regarding detected abnormal behavior. The input is the detected abnormal behavior result, and the output is the notification message. Push notifications and SMS are used to quickly inform users of the anomaly.

[0671] Step 6:

[0672] The user receives a notification, goes directly to the scene if necessary, checks the situation, and takes appropriate action. The input is the notification message, and the output is the user action. Specifically, the user checks the notification and intervenes promptly to ensure the safety of the elderly.

[0673] 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.

[0674] This invention relates to a system for detecting abnormal behavior and recognizing emotions that incorporates an emotion engine in addition to means for acquiring video, means for processing information, means for transmitting information, analysis by an AI model in a data center, and means for processing information and recognizing emotions. This system is intended to contribute to improving safety, particularly in elderly care facilities, traffic management, and educational institutions.

[0675] In this system, the terminal first uses its camera to acquire video data from the target area in real time. The acquired video is anonymized using information processing tools, and important data is extracted. This process ensures that necessary data is secured while firmly protecting individual privacy.

[0676] The anonymized data is securely transmitted to a server located within the data center via a transmission method. Because a secure communication protocol is used for this transmission, data security is robust. On the server, an AI model analyzes the incoming data and detects patterns of abnormal behavior.

[0677] Furthermore, an emotion engine embedded in the server analyzes the emotional state of the subjects using the same dataset. This emotion recognition process makes it possible to understand the emotional factors behind abnormal behavior when it is detected. For example, if anxiety or impatience is detected in the preceding video footage when an elderly person falls, it becomes easier to take measures that include addressing the cause.

[0678] Ultimately, the server generates relevant notifications based on abnormal conditions and detected emotions, and sends them to the relevant parties through notification channels. Users (e.g., facility managers or traffic controllers) can receive these notifications and take quick and appropriate responses that take emotion information into account.

[0679] Thus, by incorporating an emotion engine, the present invention brings further value to conventional anomaly detection systems, achieving improvements in safety and responsiveness.

[0680] The following describes the processing flow.

[0681] Step 1:

[0682] The device monitors the environment and collects video data in real time using its camera. The acquired video data is temporarily stored in memory for processing.

[0683] Step 2:

[0684] The device performs anonymization processing on the stored video data using information processing tools. Specifically, it applies a mosaic effect to faces and parts that can identify individuals, and filters out other unnecessary information.

[0685] Step 3:

[0686] The terminal transmits the anonymized video data to the data center via a transmission method. During this process, encryption technologies such as TLS are used to ensure the data is transferred securely.

[0687] Step 4:

[0688] The server processes the video data received at the data center as input for analysis into an AI model. The model analyzes the movements in the video and detects abnormal behaviors such as falls and sudden movements, which are defined as abnormal actions.

[0689] Step 5:

[0690] The server analyzes the video and simultaneously uses an emotion engine to determine the emotions of the people in the video. Based on the facial expressions and movements recognized by the AI ​​model, it determines whether the subject is showing emotions such as anxiety, anger, or surprise.

[0691] Step 6:

[0692] The server integrates the results of abnormal behavior and emotional states via detection means and sends notifications to relevant parties via notification means. The notifications include details of the detected abnormal behavior and related emotional information.

[0693] Step 7:

[0694] The system reviews notifications received by users and determines a course of action based on abnormal behavior and associated emotional information. For example, if an elderly person falls, facility staff may take measures including psychological support if underlying feelings of anxiety are detected.

[0695] (Example 2)

[0696] 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".

[0697] To improve safety in elderly care facilities, traffic management, and educational institutions, rapid detection of abnormal behavior and understanding the underlying emotions are essential. However, conventional systems have difficulty accurately detecting abnormalities while ensuring individual privacy, and they lack the functionality to analyze emotional factors.

[0698] 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.

[0699] In this invention, the server includes information processing means for anonymizing video data and extracting important information, detection means for detecting abnormal behavior using an AI model, and analysis means equipped with an emotion engine for recognizing emotions from the data. This enables highly accurate anomaly detection and comprehensive situational analysis that takes emotional states into account.

[0700] "Video acquisition means" refers to a device or technology that has the function of capturing video data in real time within a designated area.

[0701] "Information processing means" refers to devices and technologies for anonymizing acquired video data and extracting important information necessary for detecting abnormal behavior.

[0702] "Transmission means" refers to devices and technologies for transmitting anonymized video data to a data center using a secure communication protocol.

[0703] An "artificial intelligence model" is a program based on machine learning and deep learning technologies that is used to analyze large amounts of data and detect abnormal behavior.

[0704] "Detection means" refers to devices or technologies that have the function of identifying abnormal behavior from video data using artificial intelligence models.

[0705] An "emotion engine" is a device or technology that analyzes a subject's behavior and facial expressions to recognize the emotions behind them.

[0706] "Notification means" refers to devices or technologies used to communicate the results of anomaly detection or emotion recognition to relevant users.

[0707] This invention relates to a safety system that detects abnormal behavior and recognizes emotions. The system uses acquired video data to detect abnormal behavior and recognize the underlying emotions. This system is particularly intended for use in elderly care facilities, traffic management, and educational institutions.

[0708] The system uses cameras installed on the terminal to acquire video in real time within a designated area. The video data is acquired at high resolution and an appropriate frame rate, and anonymized using video processing libraries such as OpenCV to prevent the identification of individuals. At the same time, important information is extracted and used to detect abnormal behavior.

[0709] As a means of transmission, the terminal encrypts the data using communication protocols such as TLS to securely send anonymized data to the server. This ensures the security of the data in transit.

[0710] The server analyzes the received data using an artificial intelligence model. Specifically, it uses deep learning technologies such as TensorFlow and PyTorch to identify abnormal behavioral patterns. For example, if an elderly person is judged to be at risk of falling based on certain movements, that information is immediately recorded.

[0711] Furthermore, the server incorporates an emotion engine that analyzes acquired video data to recognize emotional states. For example, it utilizes Microsoft's Azure Emotion Recognition API to estimate emotions from the subject's facial expressions and movements. This process allows for the identification of not only abnormal behavior but also the emotional factors that led to that behavior, which can then be reflected in safety measures.

[0712] Users receive notifications from the server and can take prompt action based on detected abnormal behavior or emotional states. These notifications include details of the relevant events and estimated emotional information, contributing to improved security.

[0713] As a concrete example, a prompt could be input to the AI ​​model in the form of, "Generate prompts to detect abnormal behavior in elderly care facilities and evaluate the associated emotional states." This would enable the system to provide appropriate feedback tailored to the situation on site.

[0714] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0715] Step 1:

[0716] The system uses a camera installed on the terminal to acquire video in real time within a designated area. This process involves processing the video data input by the camera. The video is captured in high resolution, and the frame rate is set as needed. The obtained video data is then extracted as material for anonymization in the next processing step.

[0717] Step 2:

[0718] The system anonymizes the video data acquired by the device using information processing tools and extracts important information. At this stage, a video processing library such as OpenCV is used to blur parts of the subject's face or body, making it impossible to identify individuals. Video data is the input, and anonymized data with masked personal identification information is output. Data related to abnormal behavior, such as falls or suspicious movements, is also extracted simultaneously.

[0719] Step 3:

[0720] The terminal sends anonymized data to the server via a transmission method. During this process, the secure communication protocol TLS is used to encrypt the data. The input is anonymized data, and the output is encrypted data securely transmitted to the server.

[0721] Step 4:

[0722] The server analyzes received data using an artificial intelligence model to detect abnormal behavior. The received data serves as input, and TensorFlow or PyTorch is used to search for abnormal behavior patterns. If abnormal behavior is detected, detailed information is generated as output. This information includes the type of behavior, the time it occurred, and the location.

[0723] Step 5:

[0724] The server uses an emotion engine to analyze the subject's emotional state. The data analyzed is video data related to abnormal behavior that has already been detected. It uses an emotion recognition API, such as Microsoft Azure, to recognize specific emotions (e.g., anxiety, fear). The emotional state is analyzed, and data related to that emotion is generated as output.

[0725] Step 6:

[0726] The server generates a notification based on the detection results and sentiment recognition results, and sends it to the relevant parties. Detected anomaly information and sentiment data are used as input, and output as email or specific application notifications. The notification includes detailed information on abnormal behavior and the results of sentiment analysis.

[0727] Step 7:

[0728] Users receive notifications and take prompt action based on them. The content of the notification is treated as input, and appropriate actions (e.g., on-site verification, safety check for elderly individuals, etc.) are taken as output. This process improves safety and enables quick response.

[0729] (Application Example 2)

[0730] 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".

[0731] Maintaining safety is extremely important in elderly care facilities and other critical management environments. However, conventional abnormal behavior detection systems, while focusing on detecting abnormal behavior, lacked the ability to understand changes in individual emotional states. This made it difficult for facility staff to understand the underlying factors behind the situation, hindering a swift and appropriate response when an abnormality occurred. The present invention aims to solve these problems and provide an abnormal behavior detection and emotion recognition system that enables flexible responses based on a deeper understanding.

[0732] 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.

[0733] In this invention, the server includes a video acquisition means, an information processing means for pre-processing and anonymizing the video acquired by the video acquisition means and extracting important data, and a detection means for analyzing the video using an AI model to detect abnormal behavior and recognize emotional states. This makes it possible to grasp abnormal behavior and emotional changes of residents in elderly care facilities in real time and to take immediate and appropriate action.

[0734] "Image acquisition means" refers to devices or processes that have the function of capturing visual information as digital data via cameras or sensors.

[0735] "Information processing means" refers to devices and algorithms used to process acquired video data, perform anonymization, and extract important data.

[0736] "Transmission means" refers to communication devices and protocols that securely and reliably transfer processed video data to a data center.

[0737] A "data center" is a centralized facility equipped with servers that perform advanced computing processes, and used for managing and analyzing a wide range of data.

[0738] An "AI model" is an algorithm or system trained to analyze data using machine learning techniques and identify specific patterns or abnormal behaviors.

[0739] "Detection means" refers to a function that identifies abnormal behavior or emotional states from video data analyzed using an AI model.

[0740] "Notification means" refers to a method or device for immediately transmitting information about detected abnormal behavior or emotional states to relevant parties.

[0741] "Anonymization" is a processing technique that removes or alters personally identifiable information to protect data privacy.

[0742] "Emotional state" refers to the type and intensity of human emotions identified from the recorded video footage.

[0743] A "communication protocol" is a set of rules and standards used when data is sent and received over a network.

[0744] "Encryption" is a technology that uses a specific algorithm to transform information in order to protect it and prevent third parties from deciphering it.

[0745] The system realizing this invention first acquires video in real time using a camera mounted on a terminal device. This video acquisition means monitors movement within a facility or controlled environment and collects visual information as digital data. The acquired video is anonymized using an information processing means to protect privacy by deleting or modifying personally identifiable information. Image processing libraries such as OpenCV can be used for this process.

[0746] Once processing is complete, the data is sent to a server in the data center via a transmission method. This transmission uses a secure communication protocol, and the data is encrypted, preventing information from being leaked to third parties. The server in the data center uses an AI model to analyze the incoming data and recognize abnormal behavior and emotional states. The AI ​​model is built using machine learning libraries such as TensorFlow and PyTorch, and performs pattern recognition from video data.

[0747] If the server detects abnormal behavior or emotions, a notification system immediately transmits that information to the relevant parties. The notification is sent to mobile devices, etc., and the type of abnormality and the specific actions to be taken are immediately communicated to facility managers and staff, enabling a swift response.

[0748] A concrete example of its application is in nursing homes. Suppose an elderly person falls while walking within the facility, and the preceding video footage detects emotions such as "anxiety" or "confusion." This information is immediately notified to the administrator, allowing for appropriate care and preventative measures to be taken, thereby improving safety within the facility.

[0749] An example of a prompt to be input to a generative AI model is an instruction such as, "Analyze video data that may indicate abnormal behavior in an elderly care facility and identify the associated emotions." This prompt serves as guidance for the AI ​​to perform a specific analytical task.

[0750] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0751] Step 1:

[0752] The device uses its camera to capture real-time video of the environment. The captured video data is input directly into the information processing system. The input data is a raw video stream, and the output is data ready for anonymization.

[0753] Step 2:

[0754] The terminal's information processing means anonymizes the acquired video data and removes elements that could identify individuals. The process used here utilizes an image processing library to mosaic identifiable elements such as faces. This operation generates anonymized video data, allowing processing to continue safely.

[0755] Step 3:

[0756] Anonymized video data is transmitted to the server's data center via a transmission method. During transmission, the data is encrypted using a secure communication protocol, protecting it from unauthorized access and ensuring it arrives at the server safely. The output of the transmission is encrypted data.

[0757] Step 4:

[0758] The server decodes the received data and analyzes the video data using an AI model. The AI ​​model utilizes prompts to detect patterns of abnormal behavior and emotional states using a generative AI model. The data received as input is decoded video information, and the output generates emotional data associated with abnormal behavior.

[0759] Step 5:

[0760] The server generates notifications regarding abnormal behavior and emotional states based on the analysis results. These notifications include a summary of the abnormality and emotions, and are flagged as events requiring immediate attention. The generated notifications are ready to be sent to specific users (e.g., administrators or responsible personnel), and the specific content of the notifications can be viewed on mobile devices, etc.

[0761] Step 6:

[0762] The user receives a notification and takes the necessary action based on its content. The notification includes information such as the time and location of the abnormal behavior and the associated emotional state, enabling a quick and appropriate response. The output information serves as a guideline to support immediate response.

[0763] 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.

[0764] 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.

[0765] 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.

[0766] 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.

[0767] 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.

[0768] 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.

[0769] 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.

[0770] 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.

[0771] 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."

[0772] 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.

[0773] 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.

[0774] 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.

[0775] 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.

[0776] 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.

[0777] 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.

[0778] 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.

[0779] 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.

[0780] 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.

[0781] 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.

[0782] 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.

[0783] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0784] The following is further disclosed regarding the embodiments described above.

[0785] (Claim 1)

[0786] Means of acquiring video,

[0787] Information processing means for pre-processing the video acquired by the video acquisition means,

[0788] A transmission means for transmitting the video processed by the information processing means to a data center,

[0789] A detection means that uses an AI model to analyze video in a data center and detect abnormal behavior,

[0790] A notification means for notifying the detection result of the abnormal behavior,

[0791] A system that includes this.

[0792] (Claim 2)

[0793] The system according to claim 1, characterized in that the AI ​​model improves detection accuracy through automatic learning.

[0794] (Claim 3)

[0795] The system according to claim 1, characterized in that the transmission means encrypts and transmits video using a secure communication protocol.

[0796] "Example 1"

[0797] (Claim 1)

[0798] Video acquisition device,

[0799] An information processing device for anonymizing video acquired by the video acquisition device,

[0800] A secure transmission device that transmits anonymized video from the information processing device to a data center,

[0801] A detection device that uses a generated AI model to analyze video in a data center and detect abnormal operation,

[0802] A notification device that immediately notifies relevant parties of the results of detecting the abnormal operation,

[0803] A system that includes this.

[0804] (Claim 2)

[0805] The system according to claim 1, characterized in that the generated AI model improves detection accuracy through automatic learning and enhances the accuracy of anomaly detection.

[0806] (Claim 3)

[0807] The system according to claim 1, characterized in that the transmitting device encrypts the video using a secure communication protocol to prevent unauthorized access to the data.

[0808] "Application Example 1"

[0809] (Claim 1)

[0810] Means of acquiring video,

[0811] Information processing means for pre-processing the video acquired by the video acquisition means,

[0812] A transmission means for transmitting the anonymized video data from the information processing means to a data center,

[0813] A detection means that analyzes the video data transmitted by the transmission means using a secure communication protocol in a data center using an AI model to detect abnormal behavior,

[0814] A notification means for notifying a mobile terminal of the results of detecting the abnormal behavior,

[0815] A system that includes this.

[0816] (Claim 2)

[0817] The system according to claim 1, characterized in that the AI ​​model improves detection accuracy through automatic learning and further supports improved safety for the elderly via a mobile terminal.

[0818] (Claim 3)

[0819] The system according to claim 1, characterized in that the transmission means encrypts and transmits video using a secure communication protocol and analyzes the encrypted data.

[0820] "Example 2 of combining an emotion engine"

[0821] (Claim 1)

[0822] Means of acquiring video,

[0823] An information processing means for anonymizing the video acquired by the video acquisition means and extracting important information,

[0824] A transmission means for transmitting data processed by the information processing means to a data center using a secure communication protocol,

[0825] A detection means that uses an artificial intelligence model to analyze video data in a data center and detect abnormal behavior,

[0826] An analysis means equipped with an emotion engine for recognizing emotions from the data,

[0827] A notification means for notifying the results of detecting the abnormal behavior and the results of recognizing the emotion,

[0828] A system that includes this.

[0829] (Claim 2)

[0830] The system according to claim 1, characterized in that the artificial intelligence model improves detection accuracy through automatic learning.

[0831] (Claim 3)

[0832] The system according to claim 1, characterized in that the transmission means encrypts and transmits data using a secure communication protocol.

[0833] "Application example 2 when combining with an emotional engine"

[0834] (Claim 1)

[0835] Means of acquiring video,

[0836] Information processing means for pre-processing and anonymizing the video acquired by the video acquisition means and extracting important data,

[0837] A transmission means for transmitting the video processed by the information processing means to a data center,

[0838] A detection means that uses an AI model to analyze video in a data center, detects abnormal behavior, and recognizes emotional states.

[0839] A notification means for notifying the detection results of the abnormal behavior and the recognized emotional state,

[0840] A system that includes this.

[0841] (Claim 2)

[0842] The system according to claim 1, characterized in that the AI ​​model improves the accuracy of abnormal behavior detection and emotion recognition through automatic learning.

[0843] (Claim 3)

[0844] The system according to claim 1, characterized in that the transmission means encrypts and transmits anonymized video using a secure communication protocol. [Explanation of Symbols]

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

Claims

1. Means of acquiring video, Information processing means for pre-processing the video acquired by the video acquisition means, A transmission means for transmitting the anonymized video data from the information processing means to a data center, A detection means that analyzes the video data transmitted by the transmission means using a secure communication protocol in a data center using an AI model to detect abnormal behavior, A notification means for notifying a mobile terminal of the results of detecting the abnormal behavior, A system that includes this.

2. The system according to claim 1, characterized in that the AI ​​model improves detection accuracy through automatic learning and further supports the improvement of safety for the elderly via a mobile terminal.

3. The system according to claim 1, characterized in that the transmission means encrypts and transmits video using a secure communication protocol and analyzes the encrypted data.

Images