system

Abstract

We provide the system. [Solution] A means of collecting video data using a camera attached to a wearable device, A means of encrypting the collected video data and transferring it to the server, A means of decrypting encrypted data on a server and detecting anomalies using AI, A means of filtering detected anomaly information with respect for privacy, A means of notifying designated stakeholders of filtered information, 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 steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003] [[ID=2|1]]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In a conventional monitoring system, there is a problem that the monitoring range of a fixed camera is limited and it cannot exert a sufficient effect in deterring crimes. Also, due to concerns about privacy infringement, the penetration rate of monitoring cameras has been growing slowly, and there is a need for a technology to overcome these problems and protect personal privacy while achieving effective monitoring. [[ID=|F]]

Means for Solving the Problems

[0005] This invention provides a means for collecting wide-area video data using a camera attached to a wearable device. The collected video data is encrypted and transferred to a server, where it is decrypted and then anomalies are detected using AI. Furthermore, the detected anomalies are filtered with consideration for privacy, and means for notifying designated parties as necessary are provided, thereby achieving both wide-area surveillance and privacy protection.

[0006] A "wearable device" is an electronic device that can be worn on the body and used in accordance with the user's movements and circumstances.

[0007] A "camera" is a device that uses optical means to capture and record still images or moving images.

[0008] "Video data" refers to data that represents visual information acquired by a camera in a digital format.

[0009] "Encryption" is the process of transforming data using a specific algorithm to make it difficult for third parties to understand.

[0010] A "server" is a computer system that provides data and services to other devices on a network.

[0011] "Decryption" is the process of restoring encrypted data to its original, useful information.

[0012] "AI" is an abbreviation for artificial intelligence, which is a technology that enables machines to imitate human intellectual activity and perform learning and reasoning.

[0013] "Abnormal" refers to a state or behavior that is not normal, and is a situation that is judged to be in violation of a specific standard.

[0014] "Filtering" is the process of selecting necessary information from data based on specific criteria.

[0015] A "notification" is a message or report for notifying specific information to interested parties.

Brief Description of Drawings

[0016] [Figure 1] It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which multiple emotions are mapped. [Figure 10] It shows an emotion map to which multiple emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14]It is a sequence diagram showing the processing flow of a data processing system in Application Example 2 when a sentiment engine is combined.

Embodiment for Carrying out the Invention

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

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

[0019] In the following embodiments, a numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

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

[0021] In the following embodiments, a numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0022] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0023] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0024] [First Embodiment]

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

[0026] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0027] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0028] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0029] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0030] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0031] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0033] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0034] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0035] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0036] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0037] The present invention constructs a system that collects wide-area video data using a camera installed in a wearable device, and detects anomalies while securely managing that data. The operation of the system and the flow of program processing are described below.

[0038] First, the camera of the wearable device captures the wearer's surroundings in real time, acquiring video data. During this process, the camera continuously records video frames, periodically updating the data buffer. The captured video data is immediately collected in digital format.

[0039] Next, the terminal compresses and encrypts this video data to properly manage its size and prevent unauthorized external access. The compressed and encrypted data is then sent to the server using a secure communication protocol. This process enhances data protection during transmission and enables rapid data transfer.

[0040] The video data that reaches the server is first decoded and restored to its original form. After this, an AI algorithm analyzes the video data and detects any anomalies. The AI ​​analysis utilizes object recognition and motion detection technologies to quickly identify unusual movements and situations. At this stage, the degree of anomaly is scored and prioritized.

[0041] Furthermore, the server filters the analyzed anomaly information to protect privacy. This removes personally identifiable data, ensuring that only necessary information is notified. Finally, the anomaly detection results are notified to relevant parties in a filtered form. Users can then take necessary actions based on this information, enabling swift response.

[0042] As a concrete example, consider its use as a nighttime crime prevention measure in urban areas. A portable camera, acting as a terminal, periodically acquires video footage of areas with little traffic. The server immediately detects any anomalies using AI, and a notification is sent to the user, who is the security officer, thus preventing crime before it occurs. This makes it possible to monitor and deter crime in locations that were previously difficult to address.

[0043] The following describes the processing flow.

[0044] Step 1:

[0045] The device is a camera attached to a wearable device that acquires images of the surroundings in real time. The video frames are recorded continuously, and the data buffer is updated at regular intervals.

[0046] Step 2:

[0047] The video data acquired by the device is compressed to reduce unnecessary data, and then encrypted. Encryption ensures data confidentiality and prevents unauthorized access.

[0048] Step 3:

[0049] The terminal sends encrypted video data to the server using a secure protocol. During this process, data packets are monitored to prevent communication interruptions, and retransmissions are made as needed.

[0050] Step 4:

[0051] The server decodes the received video data and extracts it back into the original useful digital information. The received data is checked for integrity, and if corrupted, a retransmission request is made.

[0052] Step 5:

[0053] The server analyzes the deployed video data using an AI algorithm to detect abnormal movements and situations. The AI ​​uses object recognition and motion detection technologies to identify unusual activity and score the level of anomaly.

[0054] Step 6:

[0055] The server filters out anomaly information it detects, removing personally identifiable elements to protect privacy and organize only the necessary information.

[0056] Step 7:

[0057] The server notifies designated parties of any anomaly information that has been filtered. The notification includes a summary of the anomaly, its location, and time, enabling the parties to respond quickly.

[0058] Step 8:

[0059] Based on notifications received by the user, necessary actions will be taken. If security activities or emergency responses are required, action will be initiated immediately based on that information.

[0060] (Example 1)

[0061] 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."

[0062] Visual data collection systems require the efficient acquisition of a wide range of visual information, secure management of that information, and rapid and accurate detection of anomalies. However, existing systems have challenges in data transmission efficiency, security, and real-time capabilities, and sometimes lack sufficient privacy protection. It is necessary to overcome these challenges and enable reliable monitoring and anomaly detection.

[0063] 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.

[0064] In this invention, the server includes means for collecting visual data using a camera attached to an information acquisition device, means for compressing and encrypting the collected visual data and transmitting it to a computer, and means for decrypting the encrypted data in the computer and identifying anomalies using a data analysis algorithm. This enables secure and efficient management of visual data, real-time anomaly detection, and privacy protection.

[0065] An "information acquisition device" is a portable or fixed device equipped with imaging equipment for collecting visual data in real time.

[0066] A "recording device" is a device that has the function of recording the surrounding environment as a video frame.

[0067] "Visual data" refers to digital information, including video information and related metadata, acquired by photographic equipment.

[0068] "Compression" is a data processing technique that reduces data size to improve the efficiency of communication and storage.

[0069] "Encryption" is a security technology that transforms data to protect it from unauthorized access by third parties.

[0070] An "electronic computing device" is a computer system that has the ability to receive, process, and analyze data.

[0071] "Decryption" is the process of restoring encrypted data to its original state.

[0072] A "data analysis algorithm" is a computational method used to analyze acquired data and identify specific patterns or anomalies.

[0073] An "anomaly" refers to a movement or situation that deviates from normal data patterns, suggesting that special action may be required.

[0074] "Selection" is the process of sorting information from a privacy protection perspective and extracting only the necessary data.

[0075] "Related parties" refer to individuals or organizations that are qualified to receive abnormal information and have the authority to take countermeasures.

[0076] This invention relates to a system that uses an information acquisition device to collect visual data, securely manage it, and detect anomalies. Specific embodiments of this system are described below.

[0077] The terminal, as part of its information acquisition system, uses a camera to capture images of the user's surroundings in real time. This camera has an optical sensor and is designed to acquire wide-range visual data with high accuracy. The acquired visual data is temporarily stored in local memory.

[0078] Visual data is then compressed to improve data transfer efficiency. This compression process uses commonly available software libraries (e.g., H.264 and H.265 codecs). Furthermore, encryption is performed using algorithms such as AES to ensure data security.

[0079] The server receives visual data transmitted via a secure communication protocol (e.g., TLS / SSL). This received data is first decrypted and then subjected to data analysis algorithms. Machine learning models (e.g., YOLO, OpenPose) are used in this analysis to improve the accuracy of anomaly detection.

[0080] Anomaly information detected through analysis is carefully screened to protect privacy. After confirming that no personally identifiable information is included, the screened anomaly data is notified to the appropriate parties. Furthermore, users can take prompt action based on this information.

[0081] One concrete example is its use as a security monitoring system in urban areas. For instance, it can detect suspicious activity on quiet streets at night and notify security personnel, enabling immediate response. As a result, it can contribute to crime prevention.

[0082] An example of a prompt for a generated AI model is, "Explain how AI can be used for nighttime urban surveillance." This prompt helps explain how the AI ​​system works and how it detects anomalies in real time.

[0083] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0084] Step 1:

[0085] The terminal acquires visual data in real time using a camera attached to the information acquisition device. This input visual data is recorded digitally as still images or videos. The camera is equipped with an optical sensor and captures the surrounding environment at high resolution. The output data is temporarily stored in local memory.

[0086] Step 2:

[0087] The terminal compresses the acquired visual data. The input is raw visual data, and video codecs such as H.264 and H.265 are used to reduce the size of this data for efficient transfer. The compressed output data minimizes information degradation while reducing the bandwidth required for data transfer.

[0088] Step 3:

[0089] The terminal encrypts the compressed visual data using an encryption algorithm such as AES. The input to this process is compressed data, and the output is securely encrypted data. This encryption is performed to prevent unauthorized access to the data.

[0090] Step 4:

[0091] The terminal sends encrypted data to the server using a dedicated communication protocol (such as TLS / SSL). In this step, encrypted data is handled as input, and data packets are generated as output, which are sent to the computer. During the communication process, a secure channel is established to prevent data interception.

[0092] Step 5:

[0093] The server receives the transmitted data. This prepares it to decrypt the encrypted input data. The received data is added to a queue for decryption processing.

[0094] Step 6:

[0095] The server decrypts the received data. The input is encrypted data, and the output is visual data returned to its original compressed format. Data consistency is maintained by using the same algorithm and secret key as the terminal for decryption.

[0096] Step 7:

[0097] The server processes the decoded visual data using data analysis algorithms to detect anomalies. The input data is decoded visual information, which is then analyzed by machine learning models (such as YOLO and OpenPose). The output is anomaly detection results, generated as numerical scores or warnings.

[0098] Step 8:

[0099] The server filters the analysis results using a privacy protection filter. The input is the anomaly detection result, and the output is the filtered anomaly information. This filtering process excludes personally identifiable information and generates the necessary notification data.

[0100] Step 9:

[0101] The server notifies the user of filtered anomaly information. The input for this notification is filtered data, and the output is an alert message formatted in an appropriate format. The notification system provides information to the user in a timely manner using means such as email, SMS, and app notifications.

[0102] (Application Example 1)

[0103] 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."

[0104] In real-time monitoring systems using visual devices, achieving rapid anomaly detection and secure data management simultaneously is challenging. Furthermore, appropriately filtering detected anomaly information and promptly notifying relevant parties presents a challenge. In addition, intuitive and real-time warning displays for users of the visual devices are desirable.

[0105] 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.

[0106] In this invention, the server includes means for decrypting encrypted data, means for detecting anomalies using a computational model, and means for filtering with consideration for information protection. This enables secure management of visual data and efficient anomaly detection and notification.

[0107] A "visual device" is a device that has the function of displaying information and visually captures the surrounding environment using a camera.

[0108] A "recording device" is a device that has the function of recording video.

[0109] "Visual data" refers to video information collected by cameras and other devices.

[0110] A "processing unit" is a central component used for data calculation and analysis, and is commonly referred to as a server.

[0111] A "computational model" is an algorithm or program designed to perform a specific analysis or recognition process.

[0112] "Data protection" means maintaining the security and privacy of data and controlling access so that only authorized individuals can access it.

[0113] "Filtering" is the process of selecting necessary information from data and removing unnecessary information.

[0114] "Phenomenon recognition" refers to understanding changes in state or movement from captured data.

[0115] "Scoring" is the process of assigning evaluation values ​​based on data and according to predetermined criteria.

[0116] The system that realizes this application involves a camera attached to a visual device that visualizes the surrounding environment and collects visual data. The visual device compresses and encrypts the recorded video in real time before transferring it to the processing unit. This ensures that the visual data is managed securely. The processing unit decrypts the encrypted data and uses a computational model to detect anomalies. The computational model utilizes object recognition and motion detection technologies to identify unusual behavior in the environment. The user receives notifications from the visual device and can intuitively take action if an anomaly is detected.

[0117] In terms of hardware, the visual system includes a camera and display, as well as a communication module for data encryption and transfer. A server with powerful computing resources is desirable as the processing unit. The server will use a programming language such as Python, along with OpenCV, encryption libraries, and a machine learning framework for AI analysis.

[0118] As a concrete example, consider a scenario where a security guard equipped with a visual device detects suspicious activity in an unoccupied classroom during a nighttime patrol on a university campus. In this case, the anomaly would be immediately notified to the user, enabling prompt verification and response.

[0119] An example of a prompt message would be, "Please provide an example implementation of a generative AI model that detects abnormal behavior in a parking lot."

[0120] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0121] Step 1:

[0122] The device uses a camera to capture images of its surroundings in real time and acquire visual data. This visual data is collected as video frames and temporarily stored in memory. The input is the raw video frames obtained from the camera, and the output is the video data stored in memory.

[0123] Step 2:

[0124] The device compresses and then encrypts the stored visual data. Compression uses a codec to reduce data size, and encryption uses an encryption algorithm to ensure secure communication. The input is the video data stored in memory, and the output is the compressed and encrypted data.

[0125] Step 3:

[0126] Compressed and encrypted visual data is sent from the terminal to the server using a secure communication protocol. The input is compressed and encrypted data, and the output is the same data received on the server.

[0127] Step 4:

[0128] The server first decrypts the received visual data, and then decompresses it back into the original video data. The same encryption algorithm is used for decryption, and the decompression requires the reverse operation of the codec used for compression. The input is compressed and encrypted data, and the output is the decompressed visual data.

[0129] Step 5:

[0130] The server analyzes the unfolded visual data using a computational model to detect anomalies. The computational model employs a generative AI model that analyzes objects and situations to identify unusual patterns. The input is the unfolded visual data, and the output is the presence or absence of anomalies and their scoring results.

[0131] Step 6:

[0132] The server filters detected anomaly information from an information protection perspective, removing personal information and secure data. This filtering selects only the information that needs to be shared. The input is unprocessed anomaly information, and the output is filtered anomaly information.

[0133] Step 7:

[0134] The user receives filtered anomaly information through the terminal and takes action as needed. The terminal displays warnings to the user through a visual device, indicating the location and nature of the anomaly. The input is filtered anomaly information, and the output is the warning information displayed to the user.

[0135] 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.

[0136] This invention's system combines a camera and an emotion engine with a wearable device to analyze the user's emotional state, thereby improving the accuracy of monitoring and anomaly detection. Each component of the system is described below.

[0137] First, the camera of the wearable device simultaneously captures video data of the surroundings and the user's facial expressions. This video data includes subtle changes in facial expressions that indicate the user's emotions, and is used for subsequent analysis.

[0138] The acquired video data is initially analyzed by the emotion engine installed in the device to identify the user's emotional state. The emotion engine utilizes machine learning algorithms and can recognize basic emotions such as smiles, surprise, and fear.

[0139] Next, the device compresses and encrypts this video and emotional data and sends it to the server using a secure communication protocol. During this process, all data is processed appropriately for efficient data management and privacy protection.

[0140] The compressed and encrypted data that reaches the server is first decrypted and expanded back into its original information. The server uses AI algorithms to analyze the video data and integrates and analyzes the emotional data sent from the emotion engine. This enables anomaly detection that takes the user's emotions into account, in addition to object recognition and motion detection.

[0141] When an anomaly is detected, the server filters the anomaly data with privacy in mind. For example, faces and other personally identifiable information in the video are masked, and only the necessary information is included. Finally, the anomaly detection results are notified to the designated parties as filtered information.

[0142] As a concrete example, consider a case where a wearable device continuously collects video and emotional data from a user walking alone at night. If the user suddenly feels surprised or frightened, the emotion engine immediately recognizes this and sends it to the server. Based on this information, the server can perform a more advanced analysis than typical anomaly detection and immediately notify the user, who is a security officer. In this way, dynamic security measures that go beyond simple video surveillance become possible.

[0143] The following describes the processing flow.

[0144] Step 1:

[0145] The device uses a camera attached to the wearable device to acquire images of the surroundings and the user's facial expressions in real time, updating the video buffer.

[0146] Step 2:

[0147] The device uses an emotion engine to analyze the user's facial expressions and estimate basic emotional states such as smiles, surprise, and fear.

[0148] Step 3:

[0149] The device compresses and encrypts the analyzed emotion data and video data, and sends it to the server using a secure protocol.

[0150] Step 4:

[0151] The server decrypts the encrypted data and extracts the original video and emotional information.

[0152] Step 5:

[0153] The server uses AI to detect anomalies from video data and analyzes the results of object recognition and motion detection, incorporating emotional data.

[0154] Step 6:

[0155] Based on anomalies detected by the server, privacy filtering is performed to remove personally identifiable information and configure the system accordingly.

[0156] Step 7:

[0157] The server notifies the designated parties of filtered anomaly information, allowing users to immediately review the details and take necessary actions.

[0158] (Example 2)

[0159] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0160] In video surveillance using wearable devices, there is a need to improve the accuracy of anomaly detection based on changes in the user's emotions, enabling a swift and secure response while protecting personal information. However, conventional systems have struggled to identify subtle emotional changes in real time and respond appropriately to anomalies. Furthermore, ensuring security during data transmission and considering privacy are also important challenges.

[0161] 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.

[0162] In this invention, the server includes means for analyzing facial expression data and identifying emotional states, means for compressing the analysis results, encrypting the data, and transferring it to a base station, and means for using advanced algorithms to detect anomalies. This enables highly accurate anomaly detection based on changes in the user's emotions, while also protecting personal information, and allows for a rapid response.

[0163] A "wearable device" refers to an electronic device that a user can wear and is equipped to perform a specific function.

[0164] A "photography device" is a device used to acquire images using an optical sensor, and typically has the function of recording digital images.

[0165] "Facial expression data" refers to digital information that shows the user's facial expressions and is used to analyze their emotional state.

[0166] "Emotional state" refers to information that indicates the type and degree of the user's psychological emotions, and specifically includes emotions such as joy, surprise, and anger.

[0167] A "center" refers to a centralized management system where data is aggregated and analysis is performed, and it typically functions as a remote server.

[0168] "Advanced algorithms" refer to complex processing methods that utilize machine learning and artificial intelligence, and in particular, include computational methods for accurately detecting anomalies.

[0169] "Personal information protection" refers to methods aimed at preventing the leakage or unauthorized access of specific information within data, while taking into consideration the privacy of the user.

[0170] To implement this invention, a wearable device is first used as the terminal. The wearable device is equipped with a photographic device such as a digital camera to acquire data on the surrounding environment and the user's facial expressions. In addition, an emotion analysis engine equipped with image processing software and machine learning algorithms is incorporated, and the results are used to identify the emotional state in real time. Specifically, OpenCV can be used for image processing and TENSORFLOW® can be used for emotion analysis.

[0171] Next, the terminal compresses and encrypts the acquired data and sends it to the server over the network. The encryption technology used is AES encryption, and the TLS protocol is employed to ensure data security.

[0172] The server decrypts the received data and performs a detailed analysis using advanced algorithms. This analysis process integrates video data and emotional data to determine if any anomalies are present. If an anomaly is detected, the data is filtered with privacy in mind, and blurring or data extraction is performed to prevent the unauthorized exposure of users' personal information. Finally, based on the filtered information, relevant parties requiring immediate attention can be notified.

[0173] As a concrete example, consider a scenario where a user is jogging early in the morning and is monitored for their surroundings and emotional state. If the user suddenly feels fear, the emotion analysis engine immediately detects this change and sends it to the server. Based on this information, an alert is sent to safety personnel, enabling immediate safety checks.

[0174] An example of a prompt message might be: "Please explain what kind of emotional data will be acquired from the surrounding video to monitor the user's emotions and detect anomalies, and also describe the encryption method used when transmitting the data."

[0175] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0176] Step 1:

[0177] The camera of the wearable device captures the surrounding environment and the user's facial expressions. The input is visual information from the real world, and the output is digital image data. The camera uses a high-resolution sensor to acquire frames at regular intervals, generating a real-time image stream.

[0178] Step 2:

[0179] The device passes the acquired image data to an emotion analysis engine, which identifies emotions from the user's facial expressions. The input for this step is image data, and the output is data representing the user's emotional state, such as joy, surprise, or fear. By using a machine learning model powered by TensorFlow, emotions are quickly analyzed and output in numerical or text format.

[0180] Step 3:

[0181] The device efficiently compresses and encrypts the analyzed emotion and image data. The input is raw data, and the output is compressed and encrypted secure data. H.264 is used for compression and AES technology for encryption to protect the data from unauthorized access. This data is then ready to be transmitted to the server over the network.

[0182] Step 4:

[0183] The server receives the transmitted data and first decrypts it to restore the original data. The input to this process is encrypted data, and the output is decrypted image data and emotional state data. Subsequently, AI algorithms are used to begin anomaly detection based on the analyzed data.

[0184] Step 5:

[0185] Based on the results of anomaly detection, the server masks the data to protect privacy. The input for this step is anomaly data, and the output is information with personal information protected. Unnecessary personal information is removed through the filtering process.

[0186] Step 6:

[0187] If an anomaly is detected, the server promptly notifies the relevant parties of the filtered information. The input at this time is filtered information, and the output is a notification message. Notifications are sent via email or a dedicated warning system, prompting relevant parties to take specific action. In this way, user safety is ensured.

[0188] (Application Example 2)

[0189] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0190] Ensuring safety in modern society requires real-time anomaly detection and rapid response. However, conventional security systems have challenges such as delays in detecting anomalies and difficulty in recognizing potential anomalies based on emotions. This hinders early detection and preventative measures against dangers, resulting in insufficient safety in commercial facilities and public spaces.

[0191] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0192] In this invention, the server includes means for collecting environmental data using sensors, means for evaluating the user's state by comprehensively analyzing the collected environmental data and emotional data, and means for encrypting the analyzed information and transferring it to a large-capacity storage device. This enables anomaly detection based on the user's emotional state, resulting in more accurate real-time monitoring and faster response.

[0193] A "wearable device" is a computer-based device that a user can wear and use on a daily basis, and is equipped with sensors and communication functions.

[0194] A "sensor" is a device that detects physical or chemical information and collects it as data.

[0195] "Emotional data" refers to information that indicates a user's emotional state, extracted from their facial expressions and actions.

[0196] "Environmental data" refers to information that indicates the surrounding environment and physical conditions of the user, and is collected using sensors.

[0197] A "high-capacity storage device" is a storage device that can store and manage large amounts of digital data.

[0198] "Encryption" is the process of transforming data into a form that cannot be understood by third parties in order to protect it.

[0199] "Decryption" is the process of restoring encrypted data to its original form.

[0200] An "algorithm that mimics human intelligence" is a program that allows a computer to learn and imitate human intellectual behavior in order to solve problems.

[0201] Anomaly detection is the process of analyzing data to identify behaviors or phenomena that deviate from normal patterns.

[0202] "Selection" is the process of extracting only the necessary and important information, and removing or ignoring other information.

[0203] To implement this invention, a wearable device equipped with sensors is used. The sensors collect environmental data and user emotion data in real time. This data is initially analyzed within the wearable device, encrypted as necessary information, and transmitted to a mass storage device. A mobile communication device efficiently transfers the data using a high-speed communication protocol.

[0204] The server decodes the received data and analyzes it using algorithms that mimic human intelligence. This enables object recognition and motion detection, allowing it to detect unusual situations as anomalies. The anomaly information detected by the server is filtered and selected with privacy in mind, and then notified to specific relevant parties.

[0205] To give a specific example, if security guards in a shopping mall wear this system, they can monitor the emotions of visitors within the mall and notify the security center in advance if any abnormalities are detected. This allows for a quicker response and improves the safety of the facility.

[0206] An example of a prompt that utilizes a generative AI model would be: "Please tell me how to use sentiment analysis to detect suspicious individuals in a shopping mall and respond quickly." This helps the AI ​​model step-by-step explain how to use people's sentiment data to detect anomalies.

[0207] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0208] Step 1:

[0209] The device uses sensors mounted on the wearable to collect ambient environmental data and user emotion data. The input is raw data from the sensors, and the output is a dataset for initial analysis. At this stage, the device performs basic data filtering to remove noise.

[0210] Step 2:

[0211] The device performs an initial evaluation of the collected data using an internal sentiment analysis algorithm. The input is an environmental and sentiment dataset, and the output is an estimated result of the emotional state. The analysis algorithm detects subtle changes in facial expressions and classifies the user's emotional state. Based on this result, it evaluates the possibility of anomalies.

[0212] Step 3:

[0213] The terminal encrypts the initial evaluation results and efficiently transmits the data to a mass storage device. The input consists of the analyzed data and evaluation results, while the output is an encrypted data packet. The mobile communication device compresses the data before transmission to save time and energy.

[0214] Step 4:

[0215] The server decrypts the received encrypted data. The input for this step is the encrypted data packet, and the output is the original parsed data. The server uses a secure decoding algorithm to restore the data to its complete state.

[0216] Step 5:

[0217] The server uses the decrypted data to execute algorithms that mimic human intelligence, performing object recognition and motion detection. The input is the reconstructed analysis data, and the output is identification information of objects and their movements. By utilizing a generative AI model, the urgency level is determined by evaluating the likelihood of anomalies with high scores.

[0218] Step 6:

[0219] The server selects and filters the detected anomaly information with privacy in mind. The input is recognition information with an anomaly score, and the output is filtered data with personal information masked. This ensures that only the minimum necessary information is selected.

[0220] Step 7:

[0221] The server notifies specific stakeholders of filtered data. The input is filtered data, and the output is notification information. Based on a pre-registered list of stakeholders, the server activates a notification mechanism according to the urgency of the situation.

[0222] 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.

[0223] 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.

[0224] 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.

[0225] [Second Embodiment]

[0226] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0227] 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.

[0228] 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).

[0229] 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.

[0230] 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.

[0231] 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).

[0232] 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.

[0233] 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.

[0234] 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.

[0235] 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.

[0236] 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.

[0237] 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".

[0238] The present invention constructs a system that collects wide-area video data using a camera installed in a wearable device, and detects anomalies while securely managing that data. The operation of the system and the flow of program processing are described below.

[0239] First, the camera of the wearable device captures the wearer's surroundings in real time, acquiring video data. During this process, the camera continuously records video frames, periodically updating the data buffer. The captured video data is immediately collected in digital format.

[0240] Next, the terminal compresses and encrypts this video data to properly manage its size and prevent unauthorized external access. The compressed and encrypted data is then sent to the server using a secure communication protocol. This process enhances data protection during transmission and enables rapid data transfer.

[0241] The video data that reaches the server is first decoded and restored to its original form. After this, an AI algorithm analyzes the video data and detects any anomalies. The AI ​​analysis utilizes object recognition and motion detection technologies to quickly identify unusual movements and situations. At this stage, the degree of anomaly is scored and prioritized.

[0242] Furthermore, the server filters the analyzed anomaly information to protect privacy. This removes personally identifiable data, ensuring that only necessary information is notified. Finally, the anomaly detection results are notified to relevant parties in a filtered form. Users can then take necessary actions based on this information, enabling swift response.

[0243] As a concrete example, consider its use as a nighttime crime prevention measure in urban areas. A portable camera, acting as a terminal, periodically acquires video footage of areas with little traffic. The server immediately detects any anomalies using AI, and a notification is sent to the user, who is the security officer, thus preventing crime before it occurs. This makes it possible to monitor and deter crime in locations that were previously difficult to address.

[0244] The following describes the processing flow.

[0245] Step 1:

[0246] The device is a camera attached to a wearable device that acquires images of the surroundings in real time. The video frames are recorded continuously, and the data buffer is updated at regular intervals.

[0247] Step 2:

[0248] The video data acquired by the device is compressed to reduce unnecessary data, and then encrypted. Encryption ensures data confidentiality and prevents unauthorized access.

[0249] Step 3:

[0250] The terminal sends encrypted video data to the server using a secure protocol. During this process, data packets are monitored to prevent communication interruptions, and retransmissions are made as needed.

[0251] Step 4:

[0252] The server decodes the received video data and extracts it back into the original useful digital information. The received data is checked for integrity, and if corrupted, a retransmission request is made.

[0253] Step 5:

[0254] The server analyzes the deployed video data using an AI algorithm to detect abnormal movements and situations. The AI ​​uses object recognition and motion detection technologies to identify unusual activity and score the level of anomaly.

[0255] Step 6:

[0256] The server filters out anomaly information it detects, removing personally identifiable elements to protect privacy and organize only the necessary information.

[0257] Step 7:

[0258] The server notifies designated parties of any anomaly information that has been filtered. The notification includes a summary of the anomaly, its location, and time, enabling the parties to respond quickly.

[0259] Step 8:

[0260] Based on notifications received by the user, necessary actions will be taken. If security activities or emergency responses are required, action will be initiated immediately based on that information.

[0261] (Example 1)

[0262] 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."

[0263] Visual data collection systems require the efficient acquisition of a wide range of visual information, secure management of that information, and rapid and accurate detection of anomalies. However, existing systems have challenges in data transmission efficiency, security, and real-time capabilities, and sometimes lack sufficient privacy protection. It is necessary to overcome these challenges and enable reliable monitoring and anomaly detection.

[0264] 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.

[0265] In this invention, the server includes means for collecting visual data using a camera attached to an information acquisition device, means for compressing and encrypting the collected visual data and transmitting it to a computer, and means for decrypting the encrypted data in the computer and identifying anomalies using a data analysis algorithm. This enables secure and efficient management of visual data, real-time anomaly detection, and privacy protection.

[0266] An "information acquisition device" is a portable or fixed device equipped with imaging equipment for collecting visual data in real time.

[0267] A "recording device" is a device that has the function of recording the surrounding environment as a video frame.

[0268] "Visual data" refers to digital information, including video information and related metadata, acquired by photographic equipment.

[0269] "Compression" is a data processing technique that reduces data size to improve the efficiency of communication and storage.

[0270] "Encryption" is a security technology that transforms data to protect it from unauthorized access by third parties.

[0271] An "electronic computing device" is a computer system that has the ability to receive, process, and analyze data.

[0272] "Decryption" is the process of restoring encrypted data to its original state.

[0273] A "data analysis algorithm" is a computational method used to analyze acquired data and identify specific patterns or anomalies.

[0274] An "anomaly" refers to a movement or situation that deviates from normal data patterns, suggesting that special action may be required.

[0275] "Selection" is the process of sorting information from a privacy protection perspective and extracting only the necessary data.

[0276] "Related parties" refer to individuals or organizations that are qualified to receive abnormal information and have the authority to take countermeasures.

[0277] This invention relates to a system that uses an information acquisition device to collect visual data, securely manage it, and detect anomalies. Specific embodiments of this system are described below.

[0278] As part of an information acquisition device, the terminal captures the surrounding environment of the user in real time using a camera device. This camera device has an optical sensor and is designed to acquire a wide range of visual data with high precision. The acquired visual data is once accumulated in the local memory.

[0279] The visual data is then compressed to improve the efficiency of data transfer. For this compression process, generally used software libraries (e.g., H.264 and H.265 codec) are employed. Also, in order to maintain the security of the data, encryption is performed using algorithms such as the AES algorithm.

[0280] The server receives the visual data transmitted through a secure communication protocol (e.g., TLS / SSL). This received data is first decrypted and then subjected to a data analysis algorithm. For this analysis, machine learning models (e.g., YOLO, OpenPose) are used to enhance the accuracy of anomaly detection.

[0281] The anomaly information detected through the analysis is carefully screened for privacy protection. After confirming that no personally identifiable information is included, the selected anomaly data is notified to the appropriate relevant parties. Also, based on this information, the user can promptly take countermeasures.

[0282] As a specific example, its use as a security monitoring system in an urban area can be cited. For example, by detecting suspicious movements on a quiet street at night and notifying the security personnel, immediate response can be enabled. As a result, it can contribute to preventing crimes.

[0283] An example of a prompt sentence for the generative AI model is "Please explain how to utilize AI for night monitoring in urban areas." This prompt helps to explain how the AI system operates and detects anomalies in real time.

[0284] The flow of the specific process in Example 1 will be described using FIG. 11.

[0285] Step 1:

[0286] The terminal uses the imaging device attached to the information acquisition device to acquire visual data in real time. The input visual data is recorded in digital form as a still image or a video. The imaging device has an optical sensor and captures the surrounding environment with high resolution. Its output data is temporarily stored in the local memory.

[0287] Step 2:

[0288] The terminal compresses the acquired visual data. The input is raw visual data, and video coders such as H.264 or H.265 are used to reduce the size of this data for efficient transfer. The compressed output data reduces the bandwidth required for data transfer while minimizing information degradation.

[0289] Step 3:

[0290] The terminal encrypts the compressed visual data using an encryption algorithm such as AES. The input to this process is the compressed data, and the output is encrypted data with security ensured. This encryption is performed to prevent unauthorized access to the data.

[0291] Step 4:

[0292] The terminal sends the encrypted data to the server using a dedicated communication protocol (such as TLS / SSL). In this step, the encrypted data is handled as input, and data packets transmitted to the electronic computing device are generated as output. During the communication process, a secure channel is set up to prevent the data from being intercepted.

[0293] Step 5:

[0294] The server receives the transmitted data. This prepares it to decrypt the encrypted input data. The received data is added to a queue for decryption processing.

[0295] Step 6:

[0296] The server decrypts the received data. The input is encrypted data, and the output is visual data returned to its original compressed format. Data consistency is maintained by using the same algorithm and secret key as the terminal for decryption.

[0297] Step 7:

[0298] The server processes the decoded visual data using data analysis algorithms to detect anomalies. The input data is decoded visual information, which is then analyzed by machine learning models (such as YOLO and OpenPose). The output is anomaly detection results, generated as numerical scores or warnings.

[0299] Step 8:

[0300] The server filters the analysis results using a privacy protection filter. The input is the anomaly detection result, and the output is the filtered anomaly information. This filtering process excludes personally identifiable information and generates the necessary notification data.

[0301] Step 9:

[0302] The server notifies the user of filtered anomaly information. The input for this notification is filtered data, and the output is an alert message formatted in an appropriate format. The notification system provides information to the user in a timely manner using means such as email, SMS, and app notifications.

[0303] (Application Example 1)

[0304] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as a "server", and the smart glasses 214 are referred to as a "terminal".

[0305] In a real-time monitoring system using a visual device, it is difficult to simultaneously achieve rapid detection of abnormalities and secure data management. Also, the process of appropriately filtering the detected abnormality information and promptly notifying the relevant parties poses a challenge. Furthermore, an intuitive and real-time warning display for the users of the visual device is also desired to be realized.

[0306] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0307] In this invention, the server includes means for decrypting encrypted data, means for detecting abnormalities using a calculation model, and means for filtering with consideration for information protection. Thereby, secure management of visual data and efficient detection and notification of abnormalities become possible.

[0308] A "visual device" is a device that has a function of displaying information and visually captures the surrounding environment using a camera.

[0309] A "photographing device" is a device that has a function for recording video.

[0310] "Visual data" is video information collected by a camera or other devices.

[0311] A "processing device" is a central unit for performing data operations and analysis, and is generally called a server.

[0312] A "calculation model" is an algorithm or program designed to perform specific analysis or recognition processing.

[0313] "Information protection" is to maintain the security and privacy of data and control it so that only authorized persons can access it.

[0314] "Filtering" is the process of selecting necessary information from data and removing unnecessary information.

[0315] "Phenomenon recognition" refers to understanding changes in state or movement from captured data.

[0316] "Scoring" is the process of assigning evaluation values ​​based on data and according to predetermined criteria.

[0317] The system that realizes this application involves a camera attached to a visual device that visualizes the surrounding environment and collects visual data. The visual device compresses and encrypts the recorded video in real time before transferring it to the processing unit. This ensures that the visual data is managed securely. The processing unit decrypts the encrypted data and uses a computational model to detect anomalies. The computational model utilizes object recognition and motion detection technologies to identify unusual behavior in the environment. The user receives notifications from the visual device and can intuitively take action if an anomaly is detected.

[0318] In terms of hardware, the visual system includes a camera and display, as well as a communication module for data encryption and transfer. A server with powerful computing resources is desirable as the processing unit. The server will use a programming language such as Python, along with OpenCV, encryption libraries, and a machine learning framework for AI analysis.

[0319] As a concrete example, consider a scenario where a security guard equipped with a visual device detects suspicious activity in an unoccupied classroom during a nighttime patrol on a university campus. In this case, the anomaly would be immediately notified to the user, enabling prompt verification and response.

[0320] An example of a prompt message would be, "Please provide an example implementation of a generative AI model that detects abnormal behavior in a parking lot."

[0321] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0322] Step 1:

[0323] The device uses a camera to capture images of its surroundings in real time and acquire visual data. This visual data is collected as video frames and temporarily stored in memory. The input is the raw video frames obtained from the camera, and the output is the video data stored in memory.

[0324] Step 2:

[0325] The device compresses and then encrypts the stored visual data. Compression uses a codec to reduce data size, and encryption uses an encryption algorithm to ensure secure communication. The input is the video data stored in memory, and the output is the compressed and encrypted data.

[0326] Step 3:

[0327] Compressed and encrypted visual data is sent from the terminal to the server using a secure communication protocol. The input is compressed and encrypted data, and the output is the same data received on the server.

[0328] Step 4:

[0329] The server first decrypts the received visual data, and then decompresses it back into the original video data. The same encryption algorithm is used for decryption, and the decompression requires the reverse operation of the codec used for compression. The input is compressed and encrypted data, and the output is the decompressed visual data.

[0330] Step 5:

[0331] The server analyzes the unfolded visual data using a computational model to detect anomalies. The computational model employs a generative AI model that analyzes objects and situations to identify unusual patterns. The input is the unfolded visual data, and the output is the presence or absence of anomalies and their scoring results.

[0332] Step 6:

[0333] The server filters detected anomaly information from an information protection perspective, removing personal information and secure data. This filtering selects only the information that needs to be shared. The input is unprocessed anomaly information, and the output is filtered anomaly information.

[0334] Step 7:

[0335] The user receives filtered anomaly information through the terminal and takes action as needed. The terminal displays warnings to the user through a visual device, indicating the location and nature of the anomaly. The input is filtered anomaly information, and the output is the warning information displayed to the user.

[0336] 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.

[0337] This invention's system combines a camera and an emotion engine with a wearable device to analyze the user's emotional state, thereby improving the accuracy of monitoring and anomaly detection. Each component of the system is described below.

[0338] First, the camera of the wearable device simultaneously captures video data of the surroundings and the user's facial expressions. This video data includes subtle changes in facial expressions that indicate the user's emotions, and is used for subsequent analysis.

[0339] The acquired video data is initially analyzed by the emotion engine installed in the device to identify the user's emotional state. The emotion engine utilizes machine learning algorithms and can recognize basic emotions such as smiles, surprise, and fear.

[0340] Next, the device compresses and encrypts this video and emotional data and sends it to the server using a secure communication protocol. During this process, all data is processed appropriately for efficient data management and privacy protection.

[0341] The compressed and encrypted data that reaches the server is first decrypted and expanded back into its original information. The server uses AI algorithms to analyze the video data and integrates and analyzes the emotional data sent from the emotion engine. This enables anomaly detection that takes the user's emotions into account, in addition to object recognition and motion detection.

[0342] When an anomaly is detected, the server filters the anomaly data with privacy in mind. For example, faces and other personally identifiable information in the video are masked, and only the necessary information is included. Finally, the anomaly detection results are notified to the designated parties as filtered information.

[0343] As a concrete example, consider a case where a wearable device continuously collects video and emotional data from a user walking alone at night. If the user suddenly feels surprised or frightened, the emotion engine immediately recognizes this and sends it to the server. Based on this information, the server can perform a more advanced analysis than typical anomaly detection and immediately notify the user, who is a security officer. In this way, dynamic security measures that go beyond simple video surveillance become possible.

[0344] The following describes the processing flow.

[0345] Step 1:

[0346] The device uses a camera attached to the wearable device to acquire images of the surroundings and the user's facial expressions in real time, updating the video buffer.

[0347] Step 2:

[0348] The device uses an emotion engine to analyze the user's facial expressions and estimate basic emotional states such as smiles, surprise, and fear.

[0349] Step 3:

[0350] The device compresses and encrypts the analyzed emotion data and video data, and sends it to the server using a secure protocol.

[0351] Step 4:

[0352] The server decrypts the encrypted data and extracts the original video and emotional information.

[0353] Step 5:

[0354] The server uses AI to detect anomalies from video data and analyzes the results of object recognition and motion detection, incorporating emotional data.

[0355] Step 6:

[0356] Based on anomalies detected by the server, privacy filtering is performed to remove personally identifiable information and configure the system accordingly.

[0357] Step 7:

[0358] The server notifies the designated parties of filtered anomaly information, allowing users to immediately review the details and take necessary actions.

[0359] (Example 2)

[0360] 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".

[0361] In video surveillance using wearable devices, there is a need to improve the accuracy of anomaly detection based on changes in the user's emotions, enabling a swift and secure response while protecting personal information. However, conventional systems have struggled to identify subtle emotional changes in real time and respond appropriately to anomalies. Furthermore, ensuring security during data transmission and considering privacy are also important challenges.

[0362] 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.

[0363] In this invention, the server includes means for analyzing facial expression data and identifying emotional states, means for compressing the analysis results, encrypting the data, and transferring it to a base station, and means for using advanced algorithms to detect anomalies. This enables highly accurate anomaly detection based on changes in the user's emotions, while also protecting personal information, and allows for a rapid response.

[0364] A "wearable device" refers to an electronic device that a user can wear and is equipped to perform a specific function.

[0365] A "photography device" is a device used to acquire images using an optical sensor, and typically has the function of recording digital images.

[0366] "Facial expression data" refers to digital information that shows the user's facial expressions and is used to analyze their emotional state.

[0367] "Emotional state" refers to information that indicates the type and degree of the user's psychological emotions, and specifically includes emotions such as joy, surprise, and anger.

[0368] A "center" refers to a centralized management system where data is aggregated and analysis is performed, and it typically functions as a remote server.

[0369] "Advanced algorithms" refer to complex processing methods that utilize machine learning and artificial intelligence, and in particular, include computational methods for accurately detecting anomalies.

[0370] "Personal information protection" refers to methods aimed at preventing the leakage or unauthorized access of specific information within data, while taking into consideration the privacy of the user.

[0371] To implement this invention, a wearable device is first used as the terminal. The wearable device is equipped with a camera or other imaging device to acquire data on the surrounding environment and the user's facial expressions. It also incorporates an emotion analysis engine with image processing software and machine learning algorithms, and uses the results to identify the emotional state in real time. Specifically, OpenCV can be used for image processing and TensorFlow can be used for emotion analysis.

[0372] Next, the terminal compresses and encrypts the acquired data and sends it to the server over the network. The encryption technology used is AES encryption, and the TLS protocol is employed to ensure data security.

[0373] The server decrypts the received data and performs a detailed analysis using advanced algorithms. This analysis process integrates video data and emotional data to determine if any anomalies are present. If an anomaly is detected, the data is filtered with privacy in mind, and blurring or data extraction is performed to prevent the unauthorized exposure of users' personal information. Finally, based on the filtered information, relevant parties requiring immediate attention can be notified.

[0374] As a concrete example, consider a scenario where a user is jogging early in the morning and is monitored for their surroundings and emotional state. If the user suddenly feels fear, the emotion analysis engine immediately detects this change and sends it to the server. Based on this information, an alert is sent to safety personnel, enabling immediate safety checks.

[0375] An example of a prompt message might be: "Please explain what kind of emotional data will be acquired from the surrounding video to monitor the user's emotions and detect anomalies, and also describe the encryption method used when transmitting the data."

[0376] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0377] Step 1:

[0378] The camera of the wearable device captures the surrounding environment and the user's facial expressions. The input is visual information from the real world, and the output is digital image data. The camera uses a high-resolution sensor to acquire frames at regular intervals, generating a real-time image stream.

[0379] Step 2:

[0380] The device passes the acquired image data to an emotion analysis engine, which identifies emotions from the user's facial expressions. The input for this step is image data, and the output is data representing the user's emotional state, such as joy, surprise, or fear. By using a machine learning model powered by TensorFlow, emotions are quickly analyzed and output in numerical or text format.

[0381] Step 3:

[0382] The device efficiently compresses and encrypts the analyzed emotion and image data. The input is raw data, and the output is compressed and encrypted secure data. H.264 is used for compression and AES technology for encryption to protect the data from unauthorized access. This data is then ready to be transmitted to the server over the network.

[0383] Step 4:

[0384] The server receives the transmitted data and first decrypts it to restore the original data. The input to this process is encrypted data, and the output is decrypted image data and emotional state data. Subsequently, AI algorithms are used to begin anomaly detection based on the analyzed data.

[0385] Step 5:

[0386] Based on the results of anomaly detection, the server masks the data to protect privacy. The input for this step is anomaly data, and the output is information with personal information protected. Unnecessary personal information is removed through the filtering process.

[0387] Step 6:

[0388] If an anomaly is detected, the server promptly notifies the relevant parties of the filtered information. The input at this time is filtered information, and the output is a notification message. Notifications are sent via email or a dedicated warning system, prompting relevant parties to take specific action. In this way, user safety is ensured.

[0389] (Application Example 2)

[0390] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0391] Ensuring safety in modern society requires real-time anomaly detection and rapid response. However, conventional security systems have challenges such as delays in detecting anomalies and difficulty in recognizing potential anomalies based on emotions. This hinders early detection and preventative measures against dangers, resulting in insufficient safety in commercial facilities and public spaces.

[0392] 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.

[0393] In this invention, the server includes means for collecting environmental data using sensors, means for evaluating the user's state by comprehensively analyzing the collected environmental data and emotional data, and means for encrypting the analyzed information and transferring it to a large-capacity storage device. This enables anomaly detection based on the user's emotional state, resulting in more accurate real-time monitoring and faster response.

[0394] A "wearable device" is a computer-based device that a user can wear and use on a daily basis, and is equipped with sensors and communication functions.

[0395] A "sensor" is a device that detects physical or chemical information and collects it as data.

[0396] "Emotional data" refers to information that indicates a user's emotional state, extracted from their facial expressions and actions.

[0397] "Environmental data" refers to information that indicates the surrounding environment and physical conditions of the user, and is collected using sensors.

[0398] A "high-capacity storage device" is a storage device that can store and manage large amounts of digital data.

[0399] "Encryption" is the process of transforming data into a form that cannot be understood by third parties in order to protect it.

[0400] "Decryption" is the process of restoring encrypted data to its original form.

[0401] An "algorithm that mimics human intelligence" is a program that allows a computer to learn and imitate human intellectual behavior in order to solve problems.

[0402] Anomaly detection is the process of analyzing data to identify behaviors or phenomena that deviate from normal patterns.

[0403] "Selection" is the process of extracting only the necessary and important information, and removing or ignoring other information.

[0404] To implement this invention, a wearable device equipped with sensors is used. The sensors collect environmental data and user emotion data in real time. This data is initially analyzed within the wearable device, encrypted as necessary information, and transmitted to a mass storage device. A mobile communication device efficiently transfers the data using a high-speed communication protocol.

[0405] The server decodes the received data and analyzes it using algorithms that mimic human intelligence. This enables object recognition and motion detection, allowing it to detect unusual situations as anomalies. The anomaly information detected by the server is filtered and selected with privacy in mind, and then notified to specific relevant parties.

[0406] To give a specific example, if security guards in a shopping mall wear this system, they can monitor the emotions of visitors within the mall and notify the security center in advance if any abnormalities are detected. This allows for a quicker response and improves the safety of the facility.

[0407] An example of a prompt that utilizes a generative AI model would be: "Please tell me how to use sentiment analysis to detect suspicious individuals in a shopping mall and respond quickly." This helps the AI ​​model step-by-step explain how to use people's sentiment data to detect anomalies.

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

[0409] Step 1:

[0410] The device uses sensors mounted on the wearable to collect ambient environmental data and user emotion data. The input is raw data from the sensors, and the output is a dataset for initial analysis. At this stage, the device performs basic data filtering to remove noise.

[0411] Step 2:

[0412] The device performs an initial evaluation of the collected data using an internal sentiment analysis algorithm. The input is an environmental and sentiment dataset, and the output is an estimated result of the emotional state. The analysis algorithm detects subtle changes in facial expressions and classifies the user's emotional state. Based on this result, it evaluates the possibility of anomalies.

[0413] Step 3:

[0414] The terminal encrypts the initial evaluation results and efficiently transmits the data to a mass storage device. The input consists of the analyzed data and evaluation results, while the output is an encrypted data packet. The mobile communication device compresses the data before transmission to save time and energy.

[0415] Step 4:

[0416] The server decrypts the received encrypted data. The input for this step is the encrypted data packet, and the output is the original parsed data. The server uses a secure decoding algorithm to restore the data to its complete state.

[0417] Step 5:

[0418] The server uses the decrypted data to execute algorithms that mimic human intelligence, performing object recognition and motion detection. The input is the reconstructed analysis data, and the output is identification information of objects and their movements. By utilizing a generative AI model, the urgency level is determined by evaluating the likelihood of anomalies with high scores.

[0419] Step 6:

[0420] The server selects and filters the detected anomaly information with privacy in mind. The input is recognition information with an anomaly score, and the output is filtered data with personal information masked. This ensures that only the minimum necessary information is selected.

[0421] Step 7:

[0422] The server notifies specific stakeholders of filtered data. The input is filtered data, and the output is notification information. Based on a pre-registered list of stakeholders, the server activates a notification mechanism according to the urgency of the situation.

[0423] 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.

[0424] 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.

[0425] 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.

[0426] [Third Embodiment]

[0427] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0428] 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.

[0429] 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).

[0430] 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.

[0431] 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.

[0432] 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).

[0433] 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.

[0434] 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.

[0435] 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.

[0436] 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.

[0437] 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.

[0438] 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".

[0439] The present invention constructs a system that collects wide-area video data using a camera installed in a wearable device, and detects anomalies while securely managing that data. The operation of the system and the flow of program processing are described below.

[0440] First, the camera of the wearable device captures the wearer's surroundings in real time, acquiring video data. During this process, the camera continuously records video frames, periodically updating the data buffer. The captured video data is immediately collected in digital format.

[0441] Next, the terminal compresses and encrypts this video data to properly manage its size and prevent unauthorized external access. The compressed and encrypted data is then sent to the server using a secure communication protocol. This process enhances data protection during transmission and enables rapid data transfer.

[0442] The video data that reaches the server is first decoded and restored to its original form. After this, an AI algorithm analyzes the video data and detects any anomalies. The AI ​​analysis utilizes object recognition and motion detection technologies to quickly identify unusual movements and situations. At this stage, the degree of anomaly is scored and prioritized.

[0443] Furthermore, the server filters the analyzed anomaly information to protect privacy. This removes personally identifiable data, ensuring that only necessary information is notified. Finally, the anomaly detection results are notified to relevant parties in a filtered form. Users can then take necessary actions based on this information, enabling swift response.

[0444] As a concrete example, consider its use as a nighttime crime prevention measure in urban areas. A portable camera, acting as a terminal, periodically acquires video footage of areas with little traffic. The server immediately detects any anomalies using AI, and a notification is sent to the user, who is the security officer, thus preventing crime before it occurs. This makes it possible to monitor and deter crime in locations that were previously difficult to address.

[0445] The following describes the processing flow.

[0446] Step 1:

[0447] The device is a camera attached to a wearable device that acquires images of the surroundings in real time. The video frames are recorded continuously, and the data buffer is updated at regular intervals.

[0448] Step 2:

[0449] The video data acquired by the device is compressed to reduce unnecessary data, and then encrypted. Encryption ensures data confidentiality and prevents unauthorized access.

[0450] Step 3:

[0451] The terminal sends encrypted video data to the server using a secure protocol. During this process, data packets are monitored to prevent communication interruptions, and retransmissions are made as needed.

[0452] Step 4:

[0453] The server decodes the received video data and extracts it back into the original useful digital information. The received data is checked for integrity, and if corrupted, a retransmission request is made.

[0454] Step 5:

[0455] The server analyzes the deployed video data using an AI algorithm to detect abnormal movements and situations. The AI ​​uses object recognition and motion detection technologies to identify unusual activity and score the level of anomaly.

[0456] Step 6:

[0457] The server filters out anomaly information it detects, removing personally identifiable elements to protect privacy and organize only the necessary information.

[0458] Step 7:

[0459] The server notifies designated parties of any anomaly information that has been filtered. The notification includes a summary of the anomaly, its location, and time, enabling the parties to respond quickly.

[0460] Step 8:

[0461] Based on notifications received by the user, necessary actions will be taken. If security activities or emergency responses are required, action will be initiated immediately based on that information.

[0462] (Example 1)

[0463] 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."

[0464] Visual data collection systems require the efficient acquisition of a wide range of visual information, secure management of that information, and rapid and accurate detection of anomalies. However, existing systems have challenges in data transmission efficiency, security, and real-time capabilities, and sometimes lack sufficient privacy protection. It is necessary to overcome these challenges and enable reliable monitoring and anomaly detection.

[0465] 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.

[0466] In this invention, the server includes means for collecting visual data using a camera attached to an information acquisition device, means for compressing and encrypting the collected visual data and transmitting it to a computer, and means for decrypting the encrypted data in the computer and identifying anomalies using a data analysis algorithm. This enables secure and efficient management of visual data, real-time anomaly detection, and privacy protection.

[0467] An "information acquisition device" is a portable or fixed device equipped with imaging equipment for collecting visual data in real time.

[0468] A "recording device" is a device that has the function of recording the surrounding environment as a video frame.

[0469] "Visual data" refers to digital information, including video information and related metadata, acquired by photographic equipment.

[0470] "Compression" is a data processing technique that reduces data size to improve the efficiency of communication and storage.

[0471] "Encryption" is a security technology that transforms data to protect it from unauthorized access by third parties.

[0472] An "electronic computing device" is a computer system that has the ability to receive, process, and analyze data.

[0473] "Decryption" is the process of restoring encrypted data to its original state.

[0474] A "data analysis algorithm" is a computational method used to analyze acquired data and identify specific patterns or anomalies.

[0475] An "anomaly" refers to a movement or situation that deviates from normal data patterns, suggesting that special action may be required.

[0476] "Selection" is the process of sorting information from a privacy protection perspective and extracting only the necessary data.

[0477] "Related parties" refer to individuals or organizations that are qualified to receive abnormal information and have the authority to take countermeasures.

[0478] This invention relates to a system that uses an information acquisition device to collect visual data, securely manage it, and detect anomalies. Specific embodiments of this system are described below.

[0479] The terminal, as part of its information acquisition system, uses a camera to capture images of the user's surroundings in real time. This camera has an optical sensor and is designed to acquire wide-range visual data with high accuracy. The acquired visual data is temporarily stored in local memory.

[0480] Visual data is then compressed to improve data transfer efficiency. This compression process uses commonly available software libraries (e.g., H.264 and H.265 codecs). Furthermore, encryption is performed using algorithms such as AES to ensure data security.

[0481] The server receives visual data transmitted via a secure communication protocol (e.g., TLS / SSL). This received data is first decrypted and then subjected to data analysis algorithms. Machine learning models (e.g., YOLO, OpenPose) are used in this analysis to improve the accuracy of anomaly detection.

[0482] Anomaly information detected through analysis is carefully screened to protect privacy. After confirming that no personally identifiable information is included, the screened anomaly data is notified to the appropriate parties. Furthermore, users can take prompt action based on this information.

[0483] One concrete example is its use as a security monitoring system in urban areas. For instance, it can detect suspicious activity on quiet streets at night and notify security personnel, enabling immediate response. As a result, it can contribute to crime prevention.

[0484] An example of a prompt for a generated AI model is, "Explain how AI can be used for nighttime urban surveillance." This prompt helps explain how the AI ​​system works and how it detects anomalies in real time.

[0485] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0486] Step 1:

[0487] The terminal acquires visual data in real time using a camera attached to the information acquisition device. This input visual data is recorded digitally as still images or videos. The camera is equipped with an optical sensor and captures the surrounding environment at high resolution. The output data is temporarily stored in local memory.

[0488] Step 2:

[0489] The terminal compresses the acquired visual data. The input is raw visual data, and video codecs such as H.264 and H.265 are used to reduce the size of this data for efficient transfer. The compressed output data minimizes information degradation while reducing the bandwidth required for data transfer.

[0490] Step 3:

[0491] The terminal encrypts the compressed visual data using an encryption algorithm such as AES. The input to this process is compressed data, and the output is securely encrypted data. This encryption is performed to prevent unauthorized access to the data.

[0492] Step 4:

[0493] The terminal sends encrypted data to the server using a dedicated communication protocol (such as TLS / SSL). In this step, encrypted data is handled as input, and data packets are generated as output, which are sent to the computer. During the communication process, a secure channel is established to prevent data interception.

[0494] Step 5:

[0495] The server receives the transmitted data. This prepares it to decrypt the encrypted input data. The received data is added to a queue for decryption processing.

[0496] Step 6:

[0497] The server decrypts the received data. The input is encrypted data, and the output is visual data returned to its original compressed format. Data consistency is maintained by using the same algorithm and secret key as the terminal for decryption.

[0498] Step 7:

[0499] The server processes the decoded visual data using data analysis algorithms to detect anomalies. The input data is decoded visual information, which is then analyzed by machine learning models (such as YOLO and OpenPose). The output is anomaly detection results, generated as numerical scores or warnings.

[0500] Step 8:

[0501] The server filters the analysis results using a privacy protection filter. The input is the anomaly detection result, and the output is the filtered anomaly information. This filtering process excludes personally identifiable information and generates the necessary notification data.

[0502] Step 9:

[0503] The server notifies the user of filtered anomaly information. The input for this notification is filtered data, and the output is an alert message formatted in an appropriate format. The notification system provides information to the user in a timely manner using means such as email, SMS, and app notifications.

[0504] (Application Example 1)

[0505] 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."

[0506] In real-time monitoring systems using visual devices, achieving rapid anomaly detection and secure data management simultaneously is challenging. Furthermore, appropriately filtering detected anomaly information and promptly notifying relevant parties presents a challenge. In addition, intuitive and real-time warning displays for users of the visual devices are desirable.

[0507] 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.

[0508] In this invention, the server includes means for decrypting encrypted data, means for detecting anomalies using a computational model, and means for filtering with consideration for information protection. This enables secure management of visual data and efficient anomaly detection and notification.

[0509] A "visual device" is a device that has the function of displaying information and visually captures the surrounding environment using a camera.

[0510] A "recording device" is a device that has the function of recording video.

[0511] "Visual data" refers to video information collected by cameras and other devices.

[0512] A "processing unit" is a central component used for data calculation and analysis, and is commonly referred to as a server.

[0513] A "computational model" is an algorithm or program designed to perform a specific analysis or recognition process.

[0514] "Data protection" means maintaining the security and privacy of data and controlling access so that only authorized individuals can access it.

[0515] "Filtering" is the process of selecting necessary information from data and removing unnecessary information.

[0516] "Phenomenon recognition" refers to understanding changes in state or movement from captured data.

[0517] "Scoring" is the process of assigning evaluation values ​​based on data and according to predetermined criteria.

[0518] The system that realizes this application involves a camera attached to a visual device that visualizes the surrounding environment and collects visual data. The visual device compresses and encrypts the recorded video in real time before transferring it to the processing unit. This ensures that the visual data is managed securely. The processing unit decrypts the encrypted data and uses a computational model to detect anomalies. The computational model utilizes object recognition and motion detection technologies to identify unusual behavior in the environment. The user receives notifications from the visual device and can intuitively take action if an anomaly is detected.

[0519] In terms of hardware, the visual system includes a camera and display, as well as a communication module for data encryption and transfer. A server with powerful computing resources is desirable as the processing unit. The server will use a programming language such as Python, along with OpenCV, encryption libraries, and a machine learning framework for AI analysis.

[0520] As a concrete example, consider a scenario where a security guard equipped with a visual device detects suspicious activity in an unoccupied classroom during a nighttime patrol on a university campus. In this case, the anomaly would be immediately notified to the user, enabling prompt verification and response.

[0521] An example of a prompt message would be, "Please provide an example implementation of a generative AI model that detects abnormal behavior in a parking lot."

[0522] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0523] Step 1:

[0524] The device uses a camera to capture images of its surroundings in real time and acquire visual data. This visual data is collected as video frames and temporarily stored in memory. The input is the raw video frames obtained from the camera, and the output is the video data stored in memory.

[0525] Step 2:

[0526] The device compresses and then encrypts the stored visual data. Compression uses a codec to reduce data size, and encryption uses an encryption algorithm to ensure secure communication. The input is the video data stored in memory, and the output is the compressed and encrypted data.

[0527] Step 3:

[0528] Compressed and encrypted visual data is sent from the terminal to the server using a secure communication protocol. The input is compressed and encrypted data, and the output is the same data received on the server.

[0529] Step 4:

[0530] The server first decrypts the received visual data, and then decompresses it back into the original video data. The same encryption algorithm is used for decryption, and the decompression requires the reverse operation of the codec used for compression. The input is compressed and encrypted data, and the output is the decompressed visual data.

[0531] Step 5:

[0532] The server analyzes the unfolded visual data using a computational model to detect anomalies. The computational model employs a generative AI model that analyzes objects and situations to identify unusual patterns. The input is the unfolded visual data, and the output is the presence or absence of anomalies and their scoring results.

[0533] Step 6:

[0534] The server filters detected anomaly information from an information protection perspective, removing personal information and secure data. This filtering selects only the information that needs to be shared. The input is unprocessed anomaly information, and the output is filtered anomaly information.

[0535] Step 7:

[0536] The user receives filtered anomaly information through the terminal and takes action as needed. The terminal displays warnings to the user through a visual device, indicating the location and nature of the anomaly. The input is filtered anomaly information, and the output is the warning information displayed to the user.

[0537] 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.

[0538] This invention's system combines a camera and an emotion engine with a wearable device to analyze the user's emotional state, thereby improving the accuracy of monitoring and anomaly detection. Each component of the system is described below.

[0539] First, the camera of the wearable device simultaneously captures video data of the surroundings and the user's facial expressions. This video data includes subtle changes in facial expressions that indicate the user's emotions, and is used for subsequent analysis.

[0540] The acquired video data is initially analyzed by the emotion engine installed in the device to identify the user's emotional state. The emotion engine utilizes machine learning algorithms and can recognize basic emotions such as smiles, surprise, and fear.

[0541] Next, the device compresses and encrypts this video and emotional data and sends it to the server using a secure communication protocol. During this process, all data is processed appropriately for efficient data management and privacy protection.

[0542] The compressed and encrypted data that reaches the server is first decrypted and expanded back into its original information. The server uses AI algorithms to analyze the video data and integrates and analyzes the emotional data sent from the emotion engine. This enables anomaly detection that takes the user's emotions into account, in addition to object recognition and motion detection.

[0543] When an anomaly is detected, the server filters the anomaly data with privacy in mind. For example, faces and other personally identifiable information in the video are masked, and only the necessary information is included. Finally, the anomaly detection results are notified to the designated parties as filtered information.

[0544] As a concrete example, consider a case where a wearable device continuously collects video and emotional data from a user walking alone at night. If the user suddenly feels surprised or frightened, the emotion engine immediately recognizes this and sends it to the server. Based on this information, the server can perform a more advanced analysis than typical anomaly detection and immediately notify the user, who is a security officer. In this way, dynamic security measures that go beyond simple video surveillance become possible.

[0545] The following describes the processing flow.

[0546] Step 1:

[0547] The device uses a camera attached to the wearable device to acquire images of the surroundings and the user's facial expressions in real time, updating the video buffer.

[0548] Step 2:

[0549] The device uses an emotion engine to analyze the user's facial expressions and estimate basic emotional states such as smiles, surprise, and fear.

[0550] Step 3:

[0551] The device compresses and encrypts the analyzed emotion data and video data, and sends it to the server using a secure protocol.

[0552] Step 4:

[0553] The server decrypts the encrypted data and extracts the original video and emotional information.

[0554] Step 5:

[0555] The server uses AI to detect anomalies from video data and analyzes the results of object recognition and motion detection, incorporating emotional data.

[0556] Step 6:

[0557] Based on anomalies detected by the server, privacy filtering is performed to remove personally identifiable information and configure the system accordingly.

[0558] Step 7:

[0559] The server notifies the designated parties of filtered anomaly information, allowing users to immediately review the details and take necessary actions.

[0560] (Example 2)

[0561] 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."

[0562] In video surveillance using wearable devices, there is a need to improve the accuracy of anomaly detection based on changes in the user's emotions, enabling a swift and secure response while protecting personal information. However, conventional systems have struggled to identify subtle emotional changes in real time and respond appropriately to anomalies. Furthermore, ensuring security during data transmission and considering privacy are also important challenges.

[0563] 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.

[0564] In this invention, the server includes means for analyzing facial expression data and identifying emotional states, means for compressing the analysis results, encrypting the data, and transferring it to a base station, and means for using advanced algorithms to detect anomalies. This enables highly accurate anomaly detection based on changes in the user's emotions, while also protecting personal information, and allows for a rapid response.

[0565] A "wearable device" refers to an electronic device that a user can wear and is equipped to perform a specific function.

[0566] A "photography device" is a device used to acquire images using an optical sensor, and typically has the function of recording digital images.

[0567] "Facial expression data" refers to digital information that shows the user's facial expressions and is used to analyze their emotional state.

[0568] "Emotional state" refers to information that indicates the type and degree of the user's psychological emotions, and specifically includes emotions such as joy, surprise, and anger.

[0569] A "center" refers to a centralized management system where data is aggregated and analysis is performed, and it typically functions as a remote server.

[0570] "Advanced algorithms" refer to complex processing methods that utilize machine learning and artificial intelligence, and in particular, include computational methods for accurately detecting anomalies.

[0571] "Personal information protection" refers to methods aimed at preventing the leakage or unauthorized access of specific information within data, while taking into consideration the privacy of the user.

[0572] To implement this invention, a wearable device is first used as the terminal. The wearable device is equipped with a camera or other imaging device to acquire data on the surrounding environment and the user's facial expressions. It also incorporates an emotion analysis engine with image processing software and machine learning algorithms, and uses the results to identify the emotional state in real time. Specifically, OpenCV can be used for image processing and TensorFlow can be used for emotion analysis.

[0573] Next, the terminal compresses and encrypts the acquired data and sends it to the server over the network. The encryption technology used is AES encryption, and the TLS protocol is employed to ensure data security.

[0574] The server decrypts the received data and performs a detailed analysis using advanced algorithms. This analysis process integrates video data and emotional data to determine if any anomalies are present. If an anomaly is detected, the data is filtered with privacy in mind, and blurring or data extraction is performed to prevent the unauthorized exposure of users' personal information. Finally, based on the filtered information, relevant parties requiring immediate attention can be notified.

[0575] As a concrete example, consider a scenario where a user is jogging early in the morning and is monitored for their surroundings and emotional state. If the user suddenly feels fear, the emotion analysis engine immediately detects this change and sends it to the server. Based on this information, an alert is sent to safety personnel, enabling immediate safety checks.

[0576] An example of a prompt message might be: "Please explain what kind of emotional data will be acquired from the surrounding video to monitor the user's emotions and detect anomalies, and also describe the encryption method used when transmitting the data."

[0577] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0578] Step 1:

[0579] The camera of the wearable device captures the surrounding environment and the user's facial expressions. The input is visual information from the real world, and the output is digital image data. The camera uses a high-resolution sensor to acquire frames at regular intervals, generating a real-time image stream.

[0580] Step 2:

[0581] The device passes the acquired image data to an emotion analysis engine, which identifies emotions from the user's facial expressions. The input for this step is image data, and the output is data representing the user's emotional state, such as joy, surprise, or fear. By using a machine learning model powered by TensorFlow, emotions are quickly analyzed and output in numerical or text format.

[0582] Step 3:

[0583] The device efficiently compresses and encrypts the analyzed emotion and image data. The input is raw data, and the output is compressed and encrypted secure data. H.264 is used for compression and AES technology for encryption to protect the data from unauthorized access. This data is then ready to be transmitted to the server over the network.

[0584] Step 4:

[0585] The server receives the transmitted data and first decrypts it to restore the original data. The input to this process is encrypted data, and the output is decrypted image data and emotional state data. Subsequently, AI algorithms are used to begin anomaly detection based on the analyzed data.

[0586] Step 5:

[0587] Based on the results of anomaly detection, the server masks the data to protect privacy. The input for this step is anomaly data, and the output is information with personal information protected. Unnecessary personal information is removed through the filtering process.

[0588] Step 6:

[0589] If an anomaly is detected, the server promptly notifies the relevant parties of the filtered information. The input at this time is filtered information, and the output is a notification message. Notifications are sent via email or a dedicated warning system, prompting relevant parties to take specific action. In this way, user safety is ensured.

[0590] (Application Example 2)

[0591] 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."

[0592] Ensuring safety in modern society requires real-time anomaly detection and rapid response. However, conventional security systems have challenges such as delays in detecting anomalies and difficulty in recognizing potential anomalies based on emotions. This hinders early detection and preventative measures against dangers, resulting in insufficient safety in commercial facilities and public spaces.

[0593] 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.

[0594] In this invention, the server includes means for collecting environmental data using sensors, means for evaluating the user's state by comprehensively analyzing the collected environmental data and emotional data, and means for encrypting the analyzed information and transferring it to a large-capacity storage device. This enables anomaly detection based on the user's emotional state, resulting in more accurate real-time monitoring and faster response.

[0595] A "wearable device" is a computer-based device that a user can wear and use on a daily basis, and is equipped with sensors and communication functions.

[0596] A "sensor" is a device that detects physical or chemical information and collects it as data.

[0597] "Emotional data" refers to information that indicates a user's emotional state, extracted from their facial expressions and actions.

[0598] "Environmental data" refers to information that indicates the surrounding environment and physical conditions of the user, and is collected using sensors.

[0599] A "high-capacity storage device" is a storage device that can store and manage large amounts of digital data.

[0600] "Encryption" is the process of transforming data into a form that cannot be understood by third parties in order to protect it.

[0601] "Decryption" is the process of restoring encrypted data to its original form.

[0602] An "algorithm that mimics human intelligence" is a program that allows a computer to learn and imitate human intellectual behavior in order to solve problems.

[0603] Anomaly detection is the process of analyzing data to identify behaviors or phenomena that deviate from normal patterns.

[0604] "Selection" is the process of extracting only the necessary and important information, and removing or ignoring other information.

[0605] To implement this invention, a wearable device equipped with sensors is used. The sensors collect environmental data and user emotion data in real time. This data is initially analyzed within the wearable device, encrypted as necessary information, and transmitted to a mass storage device. A mobile communication device efficiently transfers the data using a high-speed communication protocol.

[0606] The server decodes the received data and analyzes it using algorithms that mimic human intelligence. This enables object recognition and motion detection, allowing it to detect unusual situations as anomalies. The anomaly information detected by the server is filtered and selected with privacy in mind, and then notified to specific relevant parties.

[0607] To give a specific example, if security guards in a shopping mall wear this system, they can monitor the emotions of visitors within the mall and notify the security center in advance if any abnormalities are detected. This allows for a quicker response and improves the safety of the facility.

[0608] An example of a prompt that utilizes a generative AI model would be: "Please tell me how to use sentiment analysis to detect suspicious individuals in a shopping mall and respond quickly." This helps the AI ​​model step-by-step explain how to use people's sentiment data to detect anomalies.

[0609] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0610] Step 1:

[0611] The device uses sensors mounted on the wearable to collect ambient environmental data and user emotion data. The input is raw data from the sensors, and the output is a dataset for initial analysis. At this stage, the device performs basic data filtering to remove noise.

[0612] Step 2:

[0613] The device performs an initial evaluation of the collected data using an internal sentiment analysis algorithm. The input is an environmental and sentiment dataset, and the output is an estimated result of the emotional state. The analysis algorithm detects subtle changes in facial expressions and classifies the user's emotional state. Based on this result, it evaluates the possibility of anomalies.

[0614] Step 3:

[0615] The terminal encrypts the initial evaluation results and efficiently transmits the data to a mass storage device. The input consists of the analyzed data and evaluation results, while the output is an encrypted data packet. The mobile communication device compresses the data before transmission to save time and energy.

[0616] Step 4:

[0617] The server decrypts the received encrypted data. The input for this step is the encrypted data packet, and the output is the original parsed data. The server uses a secure decoding algorithm to restore the data to its complete state.

[0618] Step 5:

[0619] The server uses the decrypted data to execute algorithms that mimic human intelligence, performing object recognition and motion detection. The input is the reconstructed analysis data, and the output is identification information of objects and their movements. By utilizing a generative AI model, the urgency level is determined by evaluating the likelihood of anomalies with high scores.

[0620] Step 6:

[0621] The server selects and filters the detected anomaly information with privacy in mind. The input is recognition information with an anomaly score, and the output is filtered data with personal information masked. This ensures that only the minimum necessary information is selected.

[0622] Step 7:

[0623] The server notifies specific stakeholders of filtered data. The input is filtered data, and the output is notification information. Based on a pre-registered list of stakeholders, the server activates a notification mechanism according to the urgency of the situation.

[0624] 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.

[0625] 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.

[0626] 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.

[0627] [Fourth Embodiment]

[0628] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0629] 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.

[0630] 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).

[0631] 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.

[0632] 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.

[0633] 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).

[0634] 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.

[0635] 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.

[0636] 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.

[0637] 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.

[0638] 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.

[0639] 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.

[0640] 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".

[0641] The present invention constructs a system that collects wide-area video data using a camera installed in a wearable device, and detects anomalies while securely managing that data. The operation of the system and the flow of program processing are described below.

[0642] First, the camera of the wearable device captures the wearer's surroundings in real time, acquiring video data. During this process, the camera continuously records video frames, periodically updating the data buffer. The captured video data is immediately collected in digital format.

[0643] Next, the terminal compresses and encrypts this video data to properly manage its size and prevent unauthorized external access. The compressed and encrypted data is then sent to the server using a secure communication protocol. This process enhances data protection during transmission and enables rapid data transfer.

[0644] The video data that reaches the server is first decoded and restored to its original form. After this, an AI algorithm analyzes the video data and detects any anomalies. The AI ​​analysis utilizes object recognition and motion detection technologies to quickly identify unusual movements and situations. At this stage, the degree of anomaly is scored and prioritized.

[0645] Furthermore, the server filters the analyzed anomaly information to protect privacy. This removes personally identifiable data, ensuring that only necessary information is notified. Finally, the anomaly detection results are notified to relevant parties in a filtered form. Users can then take necessary actions based on this information, enabling swift response.

[0646] As a concrete example, consider its use as a nighttime crime prevention measure in urban areas. A portable camera, acting as a terminal, periodically acquires video footage of areas with little traffic. The server immediately detects any anomalies using AI, and a notification is sent to the user, who is the security officer, thus preventing crime before it occurs. This makes it possible to monitor and deter crime in locations that were previously difficult to address.

[0647] The following describes the processing flow.

[0648] Step 1:

[0649] The device is a camera attached to a wearable device that acquires images of the surroundings in real time. The video frames are recorded continuously, and the data buffer is updated at regular intervals.

[0650] Step 2:

[0651] The video data acquired by the device is compressed to reduce unnecessary data, and then encrypted. Encryption ensures data confidentiality and prevents unauthorized access.

[0652] Step 3:

[0653] The terminal sends encrypted video data to the server using a secure protocol. During this process, data packets are monitored to prevent communication interruptions, and retransmissions are made as needed.

[0654] Step 4:

[0655] The server decodes the received video data and extracts it back into the original useful digital information. The received data is checked for integrity, and if corrupted, a retransmission request is made.

[0656] Step 5:

[0657] The server analyzes the deployed video data using an AI algorithm to detect abnormal movements and situations. The AI ​​uses object recognition and motion detection technologies to identify unusual activity and score the level of anomaly.

[0658] Step 6:

[0659] The server filters out anomaly information it detects, removing personally identifiable elements to protect privacy and organize only the necessary information.

[0660] Step 7:

[0661] The server notifies designated parties of any anomaly information that has been filtered. The notification includes a summary of the anomaly, its location, and time, enabling the parties to respond quickly.

[0662] Step 8:

[0663] Based on notifications received by the user, necessary actions will be taken. If security activities or emergency responses are required, action will be initiated immediately based on that information.

[0664] (Example 1)

[0665] 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".

[0666] Visual data collection systems require the efficient acquisition of a wide range of visual information, secure management of that information, and rapid and accurate detection of anomalies. However, existing systems have challenges in data transmission efficiency, security, and real-time capabilities, and sometimes lack sufficient privacy protection. It is necessary to overcome these challenges and enable reliable monitoring and anomaly detection.

[0667] 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.

[0668] In this invention, the server includes means for collecting visual data using a camera attached to an information acquisition device, means for compressing and encrypting the collected visual data and transmitting it to a computer, and means for decrypting the encrypted data in the computer and identifying anomalies using a data analysis algorithm. This enables secure and efficient management of visual data, real-time anomaly detection, and privacy protection.

[0669] An "information acquisition device" is a portable or fixed device equipped with imaging equipment for collecting visual data in real time.

[0670] A "recording device" is a device that has the function of recording the surrounding environment as a video frame.

[0671] "Visual data" refers to digital information, including video information and related metadata, acquired by photographic equipment.

[0672] "Compression" is a data processing technique that reduces data size to improve the efficiency of communication and storage.

[0673] "Encryption" is a security technology that transforms data to protect it from unauthorized access by third parties.

[0674] An "electronic computing device" is a computer system that has the ability to receive, process, and analyze data.

[0675] "Decryption" is the process of restoring encrypted data to its original state.

[0676] A "data analysis algorithm" is a computational method used to analyze acquired data and identify specific patterns or anomalies.

[0677] An "anomaly" refers to a movement or situation that deviates from normal data patterns, suggesting that special action may be required.

[0678] "Selection" is the process of sorting information from a privacy protection perspective and extracting only the necessary data.

[0679] "Related parties" refer to individuals or organizations that are qualified to receive abnormal information and have the authority to take countermeasures.

[0680] This invention relates to a system that uses an information acquisition device to collect visual data, securely manage it, and detect anomalies. Specific embodiments of this system are described below.

[0681] The terminal, as part of its information acquisition system, uses a camera to capture images of the user's surroundings in real time. This camera has an optical sensor and is designed to acquire wide-range visual data with high accuracy. The acquired visual data is temporarily stored in local memory.

[0682] Visual data is then compressed to improve data transfer efficiency. This compression process uses commonly available software libraries (e.g., H.264 and H.265 codecs). Furthermore, encryption is performed using algorithms such as AES to ensure data security.

[0683] The server receives visual data transmitted via a secure communication protocol (e.g., TLS / SSL). This received data is first decrypted and then subjected to data analysis algorithms. Machine learning models (e.g., YOLO, OpenPose) are used in this analysis to improve the accuracy of anomaly detection.

[0684] Anomaly information detected through analysis is carefully screened to protect privacy. After confirming that no personally identifiable information is included, the screened anomaly data is notified to the appropriate parties. Furthermore, users can take prompt action based on this information.

[0685] One concrete example is its use as a security monitoring system in urban areas. For instance, it can detect suspicious activity on quiet streets at night and notify security personnel, enabling immediate response. As a result, it can contribute to crime prevention.

[0686] An example of a prompt for a generated AI model is, "Explain how AI can be used for nighttime urban surveillance." This prompt helps explain how the AI ​​system works and how it detects anomalies in real time.

[0687] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0688] Step 1:

[0689] The terminal acquires visual data in real time using a camera attached to the information acquisition device. This input visual data is recorded digitally as still images or videos. The camera is equipped with an optical sensor and captures the surrounding environment at high resolution. The output data is temporarily stored in local memory.

[0690] Step 2:

[0691] The terminal compresses the acquired visual data. The input is raw visual data, and video codecs such as H.264 and H.265 are used to reduce the size of this data for efficient transfer. The compressed output data minimizes information degradation while reducing the bandwidth required for data transfer.

[0692] Step 3:

[0693] The terminal encrypts the compressed visual data using an encryption algorithm such as AES. The input to this process is compressed data, and the output is securely encrypted data. This encryption is performed to prevent unauthorized access to the data.

[0694] Step 4:

[0695] The terminal sends encrypted data to the server using a dedicated communication protocol (such as TLS / SSL). In this step, encrypted data is handled as input, and data packets are generated as output, which are sent to the computer. During the communication process, a secure channel is established to prevent data interception.

[0696] Step 5:

[0697] The server receives the transmitted data. This prepares it to decrypt the encrypted input data. The received data is added to a queue for decryption processing.

[0698] Step 6:

[0699] The server decrypts the received data. The input is encrypted data, and the output is visual data returned to its original compressed format. Data consistency is maintained by using the same algorithm and secret key as the terminal for decryption.

[0700] Step 7:

[0701] The server processes the decoded visual data using data analysis algorithms to detect anomalies. The input data is decoded visual information, which is then analyzed by machine learning models (such as YOLO and OpenPose). The output is anomaly detection results, generated as numerical scores or warnings.

[0702] Step 8:

[0703] The server filters the analysis results using a privacy protection filter. The input is the anomaly detection result, and the output is the filtered anomaly information. This filtering process excludes personally identifiable information and generates the necessary notification data.

[0704] Step 9:

[0705] The server notifies the user of filtered anomaly information. The input for this notification is filtered data, and the output is an alert message formatted in an appropriate format. The notification system provides information to the user in a timely manner using means such as email, SMS, and app notifications.

[0706] (Application Example 1)

[0707] 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".

[0708] In real-time monitoring systems using visual devices, achieving rapid anomaly detection and secure data management simultaneously is challenging. Furthermore, appropriately filtering detected anomaly information and promptly notifying relevant parties presents a challenge. In addition, intuitive and real-time warning displays for users of the visual devices are desirable.

[0709] 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.

[0710] In this invention, the server includes means for decrypting encrypted data, means for detecting anomalies using a computational model, and means for filtering with consideration for information protection. This enables secure management of visual data and efficient anomaly detection and notification.

[0711] A "visual device" is a device that has the function of displaying information and visually captures the surrounding environment using a camera.

[0712] A "recording device" is a device that has the function of recording video.

[0713] "Visual data" refers to video information collected by cameras and other devices.

[0714] A "processing unit" is a central component used for data calculation and analysis, and is commonly referred to as a server.

[0715] A "computational model" is an algorithm or program designed to perform a specific analysis or recognition process.

[0716] "Data protection" means maintaining the security and privacy of data and controlling access so that only authorized individuals can access it.

[0717] "Filtering" is the process of selecting necessary information from data and removing unnecessary information.

[0718] "Phenomenon recognition" refers to understanding changes in state or movement from captured data.

[0719] "Scoring" is the process of assigning evaluation values ​​based on data and according to predetermined criteria.

[0720] The system that realizes this application involves a camera attached to a visual device that visualizes the surrounding environment and collects visual data. The visual device compresses and encrypts the recorded video in real time before transferring it to the processing unit. This ensures that the visual data is managed securely. The processing unit decrypts the encrypted data and uses a computational model to detect anomalies. The computational model utilizes object recognition and motion detection technologies to identify unusual behavior in the environment. The user receives notifications from the visual device and can intuitively take action if an anomaly is detected.

[0721] In terms of hardware, the visual system includes a camera and display, as well as a communication module for data encryption and transfer. A server with powerful computing resources is desirable as the processing unit. The server will use a programming language such as Python, along with OpenCV, encryption libraries, and a machine learning framework for AI analysis.

[0722] As a concrete example, consider a scenario where a security guard equipped with a visual device detects suspicious activity in an unoccupied classroom during a nighttime patrol on a university campus. In this case, the anomaly would be immediately notified to the user, enabling prompt verification and response.

[0723] An example of a prompt message would be, "Please provide an example implementation of a generative AI model that detects abnormal behavior in a parking lot."

[0724] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0725] Step 1:

[0726] The device uses a camera to capture images of its surroundings in real time and acquire visual data. This visual data is collected as video frames and temporarily stored in memory. The input is the raw video frames obtained from the camera, and the output is the video data stored in memory.

[0727] Step 2:

[0728] The device compresses and then encrypts the stored visual data. Compression uses a codec to reduce data size, and encryption uses an encryption algorithm to ensure secure communication. The input is the video data stored in memory, and the output is the compressed and encrypted data.

[0729] Step 3:

[0730] Compressed and encrypted visual data is sent from the terminal to the server using a secure communication protocol. The input is compressed and encrypted data, and the output is the same data received on the server.

[0731] Step 4:

[0732] The server first decrypts the received visual data, and then decompresses it back into the original video data. The same encryption algorithm is used for decryption, and the decompression requires the reverse operation of the codec used for compression. The input is compressed and encrypted data, and the output is the decompressed visual data.

[0733] Step 5:

[0734] The server analyzes the unfolded visual data using a computational model to detect anomalies. The computational model employs a generative AI model that analyzes objects and situations to identify unusual patterns. The input is the unfolded visual data, and the output is the presence or absence of anomalies and their scoring results.

[0735] Step 6:

[0736] The server filters detected anomaly information from an information protection perspective, removing personal information and secure data. This filtering selects only the information that needs to be shared. The input is unprocessed anomaly information, and the output is filtered anomaly information.

[0737] Step 7:

[0738] The user receives filtered anomaly information through the terminal and takes action as needed. The terminal displays warnings to the user through a visual device, indicating the location and nature of the anomaly. The input is filtered anomaly information, and the output is the warning information displayed to the user.

[0739] 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.

[0740] This invention's system combines a camera and an emotion engine with a wearable device to analyze the user's emotional state, thereby improving the accuracy of monitoring and anomaly detection. Each component of the system is described below.

[0741] First, the camera of the wearable device simultaneously captures video data of the surroundings and the user's facial expressions. This video data includes subtle changes in facial expressions that indicate the user's emotions, and is used for subsequent analysis.

[0742] The acquired video data is initially analyzed by the emotion engine installed in the device to identify the user's emotional state. The emotion engine utilizes machine learning algorithms and can recognize basic emotions such as smiles, surprise, and fear.

[0743] Next, the device compresses and encrypts this video and emotional data and sends it to the server using a secure communication protocol. During this process, all data is processed appropriately for efficient data management and privacy protection.

[0744] The compressed and encrypted data that reaches the server is first decrypted and expanded back into its original information. The server uses AI algorithms to analyze the video data and integrates and analyzes the emotional data sent from the emotion engine. This enables anomaly detection that takes the user's emotions into account, in addition to object recognition and motion detection.

[0745] When an anomaly is detected, the server filters the anomaly data with privacy in mind. For example, faces and other personally identifiable information in the video are masked, and only the necessary information is included. Finally, the anomaly detection results are notified to the designated parties as filtered information.

[0746] As a concrete example, consider a case where a wearable device continuously collects video and emotional data from a user walking alone at night. If the user suddenly feels surprised or frightened, the emotion engine immediately recognizes this and sends it to the server. Based on this information, the server can perform a more advanced analysis than typical anomaly detection and immediately notify the user, who is a security officer. In this way, dynamic security measures that go beyond simple video surveillance become possible.

[0747] The following describes the processing flow.

[0748] Step 1:

[0749] The device uses a camera attached to the wearable device to acquire images of the surroundings and the user's facial expressions in real time, updating the video buffer.

[0750] Step 2:

[0751] The device uses an emotion engine to analyze the user's facial expressions and estimate basic emotional states such as smiles, surprise, and fear.

[0752] Step 3:

[0753] The device compresses and encrypts the analyzed emotion data and video data, and sends it to the server using a secure protocol.

[0754] Step 4:

[0755] The server decrypts the encrypted data and extracts the original video and emotional information.

[0756] Step 5:

[0757] The server uses AI to detect anomalies from video data and analyzes the results of object recognition and motion detection, incorporating emotional data.

[0758] Step 6:

[0759] Based on anomalies detected by the server, privacy filtering is performed to remove personally identifiable information and configure the system accordingly.

[0760] Step 7:

[0761] The server notifies the designated parties of filtered anomaly information, allowing users to immediately review the details and take necessary actions.

[0762] (Example 2)

[0763] 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".

[0764] In video surveillance using wearable devices, there is a need to improve the accuracy of anomaly detection based on changes in the user's emotions, enabling a swift and secure response while protecting personal information. However, conventional systems have struggled to identify subtle emotional changes in real time and respond appropriately to anomalies. Furthermore, ensuring security during data transmission and considering privacy are also important challenges.

[0765] 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.

[0766] In this invention, the server includes means for analyzing facial expression data and identifying emotional states, means for compressing the analysis results, encrypting the data, and transferring it to a base station, and means for using advanced algorithms to detect anomalies. This enables highly accurate anomaly detection based on changes in the user's emotions, while also protecting personal information, and allows for a rapid response.

[0767] A "wearable device" refers to an electronic device that a user can wear and is equipped to perform a specific function.

[0768] A "photography device" is a device used to acquire images using an optical sensor, and typically has the function of recording digital images.

[0769] "Facial expression data" refers to digital information that shows the user's facial expressions and is used to analyze their emotional state.

[0770] "Emotional state" refers to information that indicates the type and degree of the user's psychological emotions, and specifically includes emotions such as joy, surprise, and anger.

[0771] A "center" refers to a centralized management system where data is aggregated and analysis is performed, and it typically functions as a remote server.

[0772] "Advanced algorithms" refer to complex processing methods that utilize machine learning and artificial intelligence, and in particular, include computational methods for accurately detecting anomalies.

[0773] "Personal information protection" refers to methods aimed at preventing the leakage or unauthorized access of specific information within data, while taking into consideration the privacy of the user.

[0774] To implement this invention, a wearable device is first used as the terminal. The wearable device is equipped with a camera or other imaging device to acquire data on the surrounding environment and the user's facial expressions. It also incorporates an emotion analysis engine with image processing software and machine learning algorithms, and uses the results to identify the emotional state in real time. Specifically, OpenCV can be used for image processing and TensorFlow can be used for emotion analysis.

[0775] Next, the terminal compresses and encrypts the acquired data and sends it to the server over the network. The encryption technology used is AES encryption, and the TLS protocol is employed to ensure data security.

[0776] The server decrypts the received data and performs a detailed analysis using advanced algorithms. This analysis process integrates video data and emotional data to determine if any anomalies are present. If an anomaly is detected, the data is filtered with privacy in mind, and blurring or data extraction is performed to prevent the unauthorized exposure of users' personal information. Finally, based on the filtered information, relevant parties requiring immediate attention can be notified.

[0777] As a concrete example, consider a scenario where a user is jogging early in the morning and is monitored for their surroundings and emotional state. If the user suddenly feels fear, the emotion analysis engine immediately detects this change and sends it to the server. Based on this information, an alert is sent to safety personnel, enabling immediate safety checks.

[0778] An example of a prompt message might be: "Please explain what kind of emotional data will be acquired from the surrounding video to monitor the user's emotions and detect anomalies, and also describe the encryption method used when transmitting the data."

[0779] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0780] Step 1:

[0781] The camera of the wearable device captures the surrounding environment and the user's facial expressions. The input is visual information from the real world, and the output is digital image data. The camera uses a high-resolution sensor to acquire frames at regular intervals, generating a real-time image stream.

[0782] Step 2:

[0783] The device passes the acquired image data to an emotion analysis engine, which identifies emotions from the user's facial expressions. The input for this step is image data, and the output is data representing the user's emotional state, such as joy, surprise, or fear. By using a machine learning model powered by TensorFlow, emotions are quickly analyzed and output in numerical or text format.

[0784] Step 3:

[0785] The device efficiently compresses and encrypts the analyzed emotion and image data. The input is raw data, and the output is compressed and encrypted secure data. H.264 is used for compression and AES technology for encryption to protect the data from unauthorized access. This data is then ready to be transmitted to the server over the network.

[0786] Step 4:

[0787] The server receives the transmitted data and first decrypts it to restore the original data. The input to this process is encrypted data, and the output is decrypted image data and emotional state data. Subsequently, AI algorithms are used to begin anomaly detection based on the analyzed data.

[0788] Step 5:

[0789] Based on the results of anomaly detection, the server masks the data to protect privacy. The input for this step is anomaly data, and the output is information with personal information protected. Unnecessary personal information is removed through the filtering process.

[0790] Step 6:

[0791] If an anomaly is detected, the server promptly notifies the relevant parties of the filtered information. The input at this time is filtered information, and the output is a notification message. Notifications are sent via email or a dedicated warning system, prompting relevant parties to take specific action. In this way, user safety is ensured.

[0792] (Application Example 2)

[0793] 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".

[0794] Ensuring safety in modern society requires real-time anomaly detection and rapid response. However, conventional security systems have challenges such as delays in detecting anomalies and difficulty in recognizing potential anomalies based on emotions. This hinders early detection and preventative measures against dangers, resulting in insufficient safety in commercial facilities and public spaces.

[0795] 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.

[0796] In this invention, the server includes means for collecting environmental data using sensors, means for evaluating the user's state by comprehensively analyzing the collected environmental data and emotional data, and means for encrypting the analyzed information and transferring it to a large-capacity storage device. This enables anomaly detection based on the user's emotional state, resulting in more accurate real-time monitoring and faster response.

[0797] A "wearable device" is a computer-based device that a user can wear and use on a daily basis, and is equipped with sensors and communication functions.

[0798] A "sensor" is a device that detects physical or chemical information and collects it as data.

[0799] "Emotional data" refers to information that indicates a user's emotional state, extracted from their facial expressions and actions.

[0800] "Environmental data" refers to information that indicates the surrounding environment and physical conditions of the user, and is collected using sensors.

[0801] A "high-capacity storage device" is a storage device that can store and manage large amounts of digital data.

[0802] "Encryption" is the process of transforming data into a form that cannot be understood by third parties in order to protect it.

[0803] "Decryption" is the process of restoring encrypted data to its original form.

[0804] An "algorithm that mimics human intelligence" is a program that allows a computer to learn and imitate human intellectual behavior in order to solve problems.

[0805] Anomaly detection is the process of analyzing data to identify behaviors or phenomena that deviate from normal patterns.

[0806] "Selection" is the process of extracting only the necessary and important information, and removing or ignoring other information.

[0807] To implement this invention, a wearable device equipped with sensors is used. The sensors collect environmental data and user emotion data in real time. This data is initially analyzed within the wearable device, encrypted as necessary information, and transmitted to a mass storage device. A mobile communication device efficiently transfers the data using a high-speed communication protocol.

[0808] The server decodes the received data and analyzes it using algorithms that mimic human intelligence. This enables object recognition and motion detection, allowing it to detect unusual situations as anomalies. The anomaly information detected by the server is filtered and selected with privacy in mind, and then notified to specific relevant parties.

[0809] To give a specific example, if security guards in a shopping mall wear this system, they can monitor the emotions of visitors within the mall and notify the security center in advance if any abnormalities are detected. This allows for a quicker response and improves the safety of the facility.

[0810] An example of a prompt that utilizes a generative AI model would be: "Please tell me how to use sentiment analysis to detect suspicious individuals in a shopping mall and respond quickly." This helps the AI ​​model step-by-step explain how to use people's sentiment data to detect anomalies.

[0811] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0812] Step 1:

[0813] The device uses sensors mounted on the wearable to collect ambient environmental data and user emotion data. The input is raw data from the sensors, and the output is a dataset for initial analysis. At this stage, the device performs basic data filtering to remove noise.

[0814] Step 2:

[0815] The device performs an initial evaluation of the collected data using an internal sentiment analysis algorithm. The input is an environmental and sentiment dataset, and the output is an estimated result of the emotional state. The analysis algorithm detects subtle changes in facial expressions and classifies the user's emotional state. Based on this result, it evaluates the possibility of anomalies.

[0816] Step 3:

[0817] The terminal encrypts the initial evaluation results and efficiently transmits the data to a mass storage device. The input consists of the analyzed data and evaluation results, while the output is an encrypted data packet. The mobile communication device compresses the data before transmission to save time and energy.

[0818] Step 4:

[0819] The server decrypts the received encrypted data. The input for this step is the encrypted data packet, and the output is the original parsed data. The server uses a secure decoding algorithm to restore the data to its complete state.

[0820] Step 5:

[0821] The server uses the decrypted data to execute algorithms that mimic human intelligence, performing object recognition and motion detection. The input is the reconstructed analysis data, and the output is identification information of objects and their movements. By utilizing a generative AI model, the urgency level is determined by evaluating the likelihood of anomalies with high scores.

[0822] Step 6:

[0823] The server selects and filters the detected anomaly information with privacy in mind. The input is recognition information with an anomaly score, and the output is filtered data with personal information masked. This ensures that only the minimum necessary information is selected.

[0824] Step 7:

[0825] The server notifies specific stakeholders of filtered data. The input is filtered data, and the output is notification information. Based on a pre-registered list of stakeholders, the server activates a notification mechanism according to the urgency of the situation.

[0826] 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.

[0827] 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.

[0828] 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 robot 414.

[0829] 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.

[0830] 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.

[0831] 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.

[0832] 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.

[0833] 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.

[0834] 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."

[0835] 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.

[0836] 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.

[0837] 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.

[0838] 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.

[0839] 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.

[0840] 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.

[0841] 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.

[0842] 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.

[0843] 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.

[0844] 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.

[0845] 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.

[0846] 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.

[0847] The following is further disclosed regarding the embodiments described above.

[0848] (Claim 1)

[0849] A means of collecting video data using a camera attached to a wearable device,

[0850] A means of encrypting the collected video data and transferring it to the server,

[0851] A means of decrypting encrypted data on a server and detecting anomalies using AI,

[0852] A means of filtering detected anomaly information with respect for privacy,

[0853] A means of notifying designated stakeholders of filtered information,

[0854] A system that includes this.

[0855] (Claim 2)

[0856] The system according to claim 1, which compresses and encrypts video data collected by a camera to enable efficient data transmission.

[0857] (Claim 3)

[0858] The system according to claim 1, which uses AI to perform object recognition and motion detection, and scores anomalies.

[0859] "Example 1"

[0860] (Claim 1)

[0861] A means of collecting visual data using a photographic device attached to an information acquisition device,

[0862] A means for compressing and encrypting collected visual data and transmitting it to a computer,

[0863] A means for decrypting encrypted data in an electronic computer and identifying anomalies using a data analysis algorithm,

[0864] A means of sorting information about identified anomalies while taking into consideration the protection of personal information,

[0865] A means of reporting the filtered information to identified relevant parties,

[0866] A system that includes this.

[0867] (Claim 2)

[0868] The system according to claim 1, which efficiently converts and encrypts visual data collected by a camera, thereby enabling rapid information transmission.

[0869] (Claim 3)

[0870] The system according to claim 1, wherein object identification and moving object detection are performed using a data analysis algorithm, and the identified anomalies are evaluated.

[0871] "Application Example 1"

[0872] (Claim 1)

[0873] A means of collecting visual data using a photographic device attached to a visual device,

[0874] A means for encrypting the collected visual data and transferring it to a processing device,

[0875] A means for decrypting encrypted data in a processing unit and detecting anomalies using a computational model,

[0876] A means of filtering detected anomaly information with consideration for information protection,

[0877] A means of notifying relevant parties of filtered information,

[0878] A means for monitoring the surrounding environment in a visual device and displaying a warning to the user when an anomaly is detected,

[0879] A system that includes this.

[0880] (Claim 2)

[0881] The system according to claim 1, which compresses and encrypts visual data collected by a camera, thereby enabling efficient data transmission.

[0882] (Claim 3)

[0883] The system according to claim 1, which uses a computational model to perform object recognition and motion detection, and scores anomalies.

[0884] "Example 2 of combining an emotion engine"

[0885] (Claim 1)

[0886] A means for acquiring facial expression data of the surroundings and the user using a camera attached to a wearable device,

[0887] A means of analyzing acquired facial expression data to identify emotional states,

[0888] A means of compressing the analysis results, encrypting the data, and transferring it to the base station,

[0889] A means of decrypting encrypted data at a site and detecting anomalies using advanced algorithms,

[0890] A means of filtering detected anomaly information while taking personal information protection into consideration,

[0891] A means of notifying designated stakeholders of filtered information as a warning,

[0892] A system that includes this.

[0893] (Claim 2)

[0894] The system according to claim 1, which identifies changes in the user's emotions in real time through data analysis and improves the accuracy of anomaly detection.

[0895] (Claim 3)

[0896] The system according to claim 1, which uses advanced algorithms to perform object detection and moving object identification, and integrates this with user emotion data to evaluate anomalies.

[0897] "Application example 2 when combining with an emotional engine"

[0898] (Claim 1)

[0899] A means of collecting environmental data using sensors attached to a wearable device,

[0900] A method for evaluating the user's state by comprehensively analyzing collected environmental data and emotional data,

[0901] A means of encrypting the analyzed information and transferring it to a mass storage device,

[0902] A means for decrypting encrypted information in a mass storage device and detecting anomalies using an algorithm that mimics human intelligence,

[0903] A means of selecting and discarding information about detected anomalies while excluding identification information,

[0904] A means of notifying specific stakeholders of selected information,

[0905] A system that includes this.

[0906] (Claim 2)

[0907] The system according to claim 1, which compresses and encrypts environmental data collected by sensors to enable efficient data transmission.

[0908] (Claim 3)

[0909] The system according to claim 1, which uses an algorithm that mimics human intelligence to perform object recognition and motion detection, and evaluates anomalies. [Explanation of Symbols]

[0910] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of collecting video data using a camera attached to a wearable device, A means of encrypting the collected video data and transferring it to the server, A means of decrypting encrypted data on a server and detecting anomalies using AI, A means of filtering detected anomaly information with respect for privacy, A means of notifying designated stakeholders of filtered information, A system that includes this.

2. The system according to claim 1, which compresses and encrypts video data collected by a camera to enable efficient data transmission.

3. The system according to claim 1, which uses AI to perform object recognition and motion detection, and scores anomalies.

Images