System

Abstract

A system is provided.SOLUTION: A system comprising: means for obtaining head impact information using a sensor; means for obtaining video data of a head using a camera; means for pre-processing the obtained impact information and video data; means for transmitting the pre-processed data to an analysis platform to determine the likelihood of a concussion; and means for suggesting appropriate action for a user based on the determination.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the 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] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] Concussions can occur as a result of impact to the head during sports, traffic accidents, or everyday life, and appropriate detection and treatment are crucial. However, current methods struggle to effectively detect concussions, often overlooking them, especially in conscious individuals. Furthermore, appropriate treatment for concussions is not standardized and is often left to the user's discretion. In such situations, there is a high risk of overlooking the onset of a concussion or failing to provide appropriate treatment, posing a significant risk to the user's health. To address this issue, a system is needed that uses head impact information and video data to detect concussions and recommend appropriate subsequent treatment. [Means for solving the problem]

[0005] In order to solve the above-mentioned problems, the present invention provides the following means. First, a means is provided for acquiring information about an impact on a user's head using a sensor, and furthermore, a means for acquiring video data of the head using a camera. Next, a means for preprocessing the impact information and video data is used to normalize the data and remove noise. The preprocessed data is sent to an analysis platform, and an AI model is used to determine the possibility of a concussion. Based on this determination result, a means is provided for suggesting appropriate measures to the user (e.g., rest, go to the hospital, etc.). Furthermore, by incorporating a means for integrating the impact information and video data and inputting it into an AI model to calculate a concussion risk score, and a means for accumulating past data and updating the AI ​​model through machine learning, more accurate concussion determination and appropriate treatment suggestions can be achieved.

[0006] This makes it possible to provide a system that automates the detection of concussion and appropriate treatment, significantly reducing the health risks to users.

[0007] A "sensor" is a device that detects physical impacts or displacements and converts them into electrical signals.

[0008] A "camera" is a device that captures and records images as image data.

[0009] "Impact information" is data related to the force and acceleration applied to the head, and is mainly obtained from sensors.

[0010] "Video data" refers to digital data of images or videos captured by a camera.

[0011] "Preprocessing" is the process of removing noise from raw data and converting its format to prepare it in a form suitable for analysis.

[0012] An "analysis platform" refers to a computer system or server that analyzes data and makes decisions based on the results.

[0013] A "concussion" is a medical condition in which a forceful impact to the head causes temporary dysfunction.

[0014] An "AI model" is a mathematical model that has been trained to perform a specific task using machine learning or artificial intelligence algorithms.

[0015] A "risk score" is a numerical representation of the probability of a particular event occurring or the degree of risk.

[0016] "Appropriate treatment" refers to the actions and measures recommended when an athlete is determined to be at risk of concussion, such as resting or seeking medical attention.

[0017] "Notification" is the process of sending messages to inform or alert users.

[0018] "Machine learning" is a general term for technology that uses data to train algorithms and makes predictions and judgments based on the results.

[0019] "Data accumulation" is the process of storing acquired data within the system and making it available for later analysis and learning. [Brief explanation of the drawings]

[0020] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6]FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0021] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0022] First, the terms used in the following description will be explained.

[0023] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0024] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0025] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0026] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0027] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0028] [First embodiment]

[0029] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0030] 1, a 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.

[0031] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0032] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0033] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the 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.

[0034] 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 of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0035] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0036] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0037] 2, in the data processing device 12, a specific process 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" according to the technology of the present 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 process 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.

[0038] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0039] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0040] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0041] System Overview

[0042] The system of the present invention detects impacts to the head, assesses the possibility of a concussion, and suggests appropriate measures to the user, thereby reducing the health risks associated with a concussion. The system is primarily composed of a sensor, a camera, a data preprocessing module, an AI analysis platform, and a notification module.

[0043] System configuration

[0044] 1. Sensors and cameras

[0045] The device uses sensors on the hemat band and other devices to acquire information about the impact on the user's head, including an accelerometer and gyroscope, and a camera to capture video data of the impact.

[0046] 2. Data Preprocessing Module

[0047] The device preprocesses the collected raw data, including denoising impact information and normalising the data, and also extracts the required frames from the video data and converts them into a format suitable for analysis.

[0048] 3. Data Analysis

[0049] The server receives the pre-processed data and passes it to the AI ​​analysis platform. The AI ​​model, which has been pre-trained with a large amount of data, analyzes the impact and video data to calculate a concussion risk score. This analysis takes into account certain parameters (such as the magnitude, direction, and duration of the impact).

[0050] 4. Proposal of appropriate measures

[0051] The server then sends a notification message to the user's device suggesting appropriate measures depending on the likelihood of a concussion. For example, if the risk of a concussion is high, the following message will be displayed:

[0052] "Warning! A strong head impact has been detected. Stop playing immediately and rest. Medical attention is strongly recommended."

[0053] 5. Data accumulation and machine learning

[0054] The server collects user feedback and newly collected data and stores it in a database. Machine learning algorithms are used to continuously retrain the AI ​​model to improve its accuracy.

[0055] Specific processing examples of the system

[0056] Example 1: Application during a rugby match

[0057] Suppose a user is tackled during a rugby match. At this time, the device receives large acceleration data from the sensor in the Hematband and detects the impact. The device also simultaneously receives video data of the user's head.

[0058] The pre-processing module normalizes the data and removes noise before sending it to the server. The server receives the data, and the AI ​​analysis platform evaluates the risk of concussion. For example, if the server determines that there is an 80% chance of a concussion, it sends the next instruction to the user's smartphone.

[0059] "Warning! A severe head impact has been detected. Stop playing immediately and rest. Medical attention is strongly recommended."

[0060] The user checks the notification and follows the instructions to stop playing, rest, and seek medical attention.

[0061] Example 2: Falls in daily life

[0062] A similar process is applied when a user falls and hits their head in everyday life. The device's sensors and camera detect the impact and capture video data. The preprocessed data is sent to a server, where the risk of concussion is assessed.

[0063] If the server determines that the user is at high risk of concussion, it will send a notification to the user's device suggesting appropriate measures. The content of the notification will vary depending on the circumstances of the fall, but will generally recommend resting and seeking medical attention.

[0064] In this way, the present invention provides a system that combines data collection by sensors and cameras with rapid evaluation of concussion using an AI analysis platform, enabling early detection of concussion risk and suggesting appropriate treatment, thereby significantly reducing the health risks to users.

[0065] The processing flow will be explained below.

[0066] Step 1:

[0067] The device acquires information about head impacts from sensors installed in the Hemat band worn by the user, specifically, collecting data in real time from an accelerometer and gyroscope.

[0068] Step 2:

[0069] When an impact is detected, the device simultaneously activates the camera to capture video data of the head, recording footage from a few seconds before and after the impact.

[0070] Step 3:

[0071] The device preprocesses the acquired impact data by denoising, normalizing, and formatting it to make it suitable for analysis.

[0072] Step 4:

[0073] The device preprocesses the captured video data, extracting important frames, compressing them, and preparing them for transmission to the analysis platform.

[0074] Step 5:

[0075] The device encrypts and transmits the pre-processed impact data and video data to a server using a secure communication protocol.

[0076] Step 6:

[0077] The server receives the data sent from the device and temporarily stores it in a database, so that all the data necessary for analysis is gathered.

[0078] Step 7:

[0079] The server inputs the received data into an AI analysis platform, which uses an AI model to assess the risk of concussion, taking into account parameters such as the magnitude, direction, and duration of the impact.

[0080] Step 8:

[0081] The server calculates a concussion risk score based on the results of the AI ​​analysis platform. For example, if the risk score exceeds a certain threshold, it will be judged as a high risk.

[0082] Step 9:

[0083] The server generates appropriate treatment suggestions for the user based on the risk assessment results, such as creating a notification message recommending rest or visiting a hospital.

[0084] Step 10:

[0085] The server sends the generated notification message to the user's terminal. The notification is performed in real time, helping the user to respond quickly.

[0086] Step 11:

[0087] The user checks the notification from the device and acts according to the instructions, such as stopping play and resting, or going to the hospital for a medical examination if necessary.

[0088] Step 12:

[0089] The server stores user feedback and usage results in a database, which will be used for future analysis and to improve the AI ​​model.

[0090] Step 13:

[0091] The server uses the accumulated data to retrain the AI ​​model and improve its analysis accuracy, which will result in even more accurate risk assessments from the next time onwards.

[0092] Example 1

[0093] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0094] Concussions caused by impacts to the head can pose serious health risks if appropriate measures are not taken. However, conventional methods require users to detect the impact and determine the appropriate measures themselves, which often makes it difficult to respond quickly. In addition, there are limited means of assessing the risk of concussion, making it difficult to make accurate judgments. Therefore, there is a need for a system that can quickly and accurately assess the risk of concussion and suggest appropriate measures to users.

[0095] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0096] In this invention, the server includes means for acquiring head impact information using a sensor, means for acquiring head video data using a camera, means for preprocessing the acquired impact information and video data, means for transmitting the preprocessed data to an analysis platform and determining the possibility of concussion using a generative AI model, and means for suggesting appropriate measures to the user based on the determination results, thereby enabling rapid and accurate assessment of concussion risk and suggesting appropriate measures.

[0097] A "sensor" is a device that detects physical movement, such as an accelerometer or gyroscope.

[0098] A "camera" is a device that captures images or videos and is used to obtain video data of the head.

[0099] "Impact information" is data on physical movements and forces applied to the head obtained by sensors.

[0100] "Video data" refers to information about images and videos captured by a camera.

[0101] "Preprocessing" refers to the process of removing noise from acquired data and converting it into a format suitable for analysis.

[0102] "Analysis platform" refers to systems and software for analyzing data, including generative AI models.

[0103] A "generative AI model" is an algorithm that learns from large amounts of data and evaluates the risk of concussion from the input data.

[0104] "Concussion probability" refers to the probability or risk of a concussion occurring as a result of an impact.

[0105] "Appropriate Actions" are suggested actions or treatment instructions for the user based on their risk of concussion.

[0106] A "user device" is a device such as a smartphone or tablet that allows a user to receive notifications.

[0107] The "judgment result" is the result of the concussion risk assessment analyzed by the generative AI model.

[0108] System Overview

[0109] The system of the present invention detects impacts to the head, assesses the possibility of a concussion, and suggests appropriate measures to the user, thereby reducing the health risks associated with concussions. This system is primarily composed of a sensor, a camera, a data preprocessing module, an AI analysis platform, and a notification module.

[0110] System configuration

[0111] Sensors and Cameras

[0112] The device uses sensors in the hematological band and other devices to capture information about the impact on the user's head, including an accelerometer and gyroscope, which collect data on the physical movement and force of the head, and a camera to capture video data of the impact.

[0113] Data Preprocessing Module

[0114] The device preprocesses the acquired impact information and video data. Specifically, it removes noise, normalizes the data, and converts it into a format suitable for analysis. It also extracts the necessary frames from the video data.

[0115] Data analysis

[0116] The server receives the pre-processed data and passes it to a generative AI model, which is trained on a large amount of data in advance and analyzes the impact and video data to calculate a concussion risk score, taking into account parameters such as the magnitude, direction, and duration of the impact.

[0117] Proposal of appropriate measures

[0118] The server generates a notification message suggesting appropriate measures based on the concussion risk score calculated by the AI ​​model and sends it to the user device. For example, if the server determines that the risk of a concussion is high, it sends a message saying, "Warning! A strong impact to the head has been detected. Stop playing immediately and rest. We strongly recommend that you seek medical attention."

[0119] Data accumulation and machine learning

[0120] The server continuously accumulates user feedback and newly collected data and stores it in a database, which continuously retrains the generative AI model and improves its accuracy. Through this feedback loop, the accuracy of concussion risk assessment is further improved.

[0121] Specific processing examples of the system

[0122] Example 1: Application during a rugby match

[0123] Suppose a user is tackled during a rugby match. At this time, the device receives large acceleration data from the sensor in the Hematband and detects the impact. The device also simultaneously receives video data of the user's head.

[0124] The pre-processing module normalizes and removes noise from the data before sending it to the server, which receives it and uses a generative AI model to assess the risk of a concussion. For example, if the server determines there is an 80% chance of a concussion, it sends the following instructions to the user's smartphone:

[0125] "Warning! A severe head impact has been detected. Stop playing immediately and rest. Medical attention is strongly recommended."

[0126] The user checks the notification and follows the instructions to stop playing, rest, and seek medical attention.

[0127] Example 2: Falls in daily life

[0128] A similar process is applied when a user falls and hits their head in everyday life. The device's sensors and camera detect the impact and capture video data. The preprocessed data is sent to a server, where the risk of concussion is assessed.

[0129] If the server determines that the user is at high risk of concussion, it will send a notification to the user's device suggesting appropriate measures. The content of the notification will vary depending on the circumstances of the fall, but will generally recommend resting and seeking medical attention.

[0130] In this way, the present invention provides a system that combines data collection by sensors and cameras with rapid assessment of concussion using generative AI models to enable early detection of concussion risk and suggest appropriate treatment, thereby significantly reducing the health risks to users.

[0131] Examples of prompt statements

[0132] "Please explain the procedure for the system that assesses the risk of concussion when tackled during a rugby match."

[0133] "Please explain in detail how this system will assess the risk of concussion and suggest appropriate measures to the user when they fall and hit their head in daily life."

[0134] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0135] Step 1: Collect data

[0136] The device uses sensors and a camera to collect information about the impact to the head and video data. Specifically, the accelerometer and gyroscope collect impact information, and the camera collects video data.

[0137] Input: Impact to the user's head

[0138] Output: Impact data (acceleration, direction), video data

[0139] Specific example of operation: When a user is tackled during sports, the acceleration sensor installed in the Hematband measures a large acceleration and the camera records the moment.

[0140] Step 2: Preprocessing the data

[0141] The device preprocesses the collected raw data, specifically removing noise and normalizing the data. For video data, it extracts the necessary frames and converts them into a format suitable for analysis.

[0142] Input: Impact data, video data

[0143] Output: Preprocessed data

[0144] Specific example of operation: The device removes noise from accelerometer data and cuts unnecessary frames from video data to extract important moments.

[0145] Step 3: Analyze the data

[0146] The server receives the pre-processed data and passes it to a generative AI model, which analyzes the impact and video data to calculate a concussion risk score, taking into account parameters such as impact magnitude, direction, and duration.

[0147] Input: Preprocessed data

[0148] Output: Concussion risk score

[0149] Specific example of operation: The server receives preprocessed data sent from the device and uses the generative AI model to determine that the risk of concussion is 80%.

[0150] Step 4: Propose appropriate action

[0151] The server generates and transmits a notification message to the user device suggesting appropriate treatment based on the concussion risk score.

[0152] Input: Concussion Risk Score

[0153] Output: Notification message

[0154] Specific example of operation: If the server determines that there is a high risk of concussion, it will send a message to the user's smartphone stating, "Warning! A strong impact to the head has been detected. Stop playing immediately and rest. We strongly recommend that you seek medical attention."

[0155] Step 5: Data accumulation and machine learning

[0156] The server accumulates user feedback and newly collected data and stores it in a database. Machine learning algorithms are used to continuously retrain the generative AI model to improve its accuracy.

[0157] Input: User feedback, collected data

[0158] Output: Updated generative AI model

[0159] Specific example of operation: When a user enters the results of a medical examination at a hospital into the app, the server stores the data in a database and uses it to retrain the AI ​​model.

[0160] (Application example 1)

[0161] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0162] Head impacts to workers during factory work can lead to serious accidents and health risks. Currently, there is a lack of systems that can take prompt and appropriate measures when a head impact occurs. In particular, it is difficult to ensure worker safety unless appropriate measures and risk assessments can be quickly carried out after an impact. This can lead to work interruptions, reduced productivity, and even damage to the worker's health. Therefore, there is a strong demand for a system that can immediately detect head impacts during factory work and take appropriate measures.

[0163] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0164] In this invention, the server includes means for acquiring head impact information using a sensor, means for acquiring head video data using a camera, means for preprocessing the acquired impact information and video data, means for transmitting data to personal devices used by workers, and means for monitoring the head safety of workers in a factory environment. This makes it possible to immediately detect head impacts during work, quickly assess the risk, and propose appropriate measures.

[0165] "Sensor" refers to a device for acquiring information about impacts to the head, and includes an acceleration sensor and a gyroscope.

[0166] A "camera" is a device for acquiring image data of the head.

[0167] "Preprocessing" refers to the process of removing noise from the acquired impact information and video data and converting the data into a format suitable for analysis.

[0168] The "analysis platform" is a system equipped with an AI model that receives preprocessed data and performs impact risk assessment.

[0169] "Impact information" is data on the impact on the head obtained by the sensor.

[0170] "Video data" is video information of the head captured by a camera.

[0171] A "user terminal" is a personal terminal used by a worker, and includes a smartphone or tablet.

[0172] "Appropriate measures" are actions and precautions suggested to the user depending on the situation after the impact.

[0173] The "means for monitoring worker head safety in a factory environment" is a system that immediately detects and analyzes any impact to the head of a worker in a factory, and suggests appropriate countermeasures.

[0174] To implement this invention, it is necessary to build a system including the following components: The system is mainly composed of a sensor, a camera, a data preprocessing module, an AI analysis platform, and a notification module.

[0175] 1. Equipped with sensors and cameras

[0176] The sensors will be installed in the smart helmets worn by the workers, including accelerometers and gyroscopes to capture information about head impacts, and a camera will also be installed in the smart helmets to capture video data at the time of impact.

[0177] 2. Data Preprocessing

[0178] The device (smartphone or tablet) receives the impact information and video data sent from the helmet. This data undergoes preprocessing such as noise removal and normalization. The necessary frames from the video data are also extracted and converted into a format suitable for analysis.

[0179] 3. Sending data to the server

[0180] The preprocessed data is sent from the device to a server, which receives it and analyzes it using an AI analysis platform.

[0181] 4. Data Analysis

[0182] The AI ​​analysis platform on the server uses the pre-processed data to perform a risk assessment of head impacts. This analysis uses a generative AI model that has been trained on a large amount of data in advance, taking into account specific parameters (such as the magnitude, direction, and duration of the impact).

[0183] 5. Notification and Proposal of Appropriate Action

[0184] The server then notifies the user of appropriate measures based on the risk score. For example, if the risk of a concussion is high, a message will be displayed saying, "Warning! A strong impact to the head has been detected. Stop work and check for safety."

[0185] Specific examples

[0186] When a factory worker receives an impact to the head, the smart helmet detects the impact and collects data. The data is preprocessed on the smartphone and sent to a server. The AI ​​analysis platform on the server analyzes the data and calculates a risk score. As a result, an appropriate action is determined and a notification is sent to the user's device.

[0187] Prompt Sentence Examples

[0188] "Design an application that detects when a factory worker has received a hard blow to the head and provides an immediate risk assessment."

[0189] By designing and implementing this system, it will be possible to quickly suggest appropriate measures to be taken when a factory worker suffers a blow to the head, thereby reducing health risks.

[0190] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0191] Step 1:

[0192] The sensors and cameras collect information about the impact on the worker's head and video data. Specifically, the acceleration sensor and gyroscope collect data on the impact to the head, and the camera captures the video at that time. This provides the input impact data and video data.

[0193] Step 2:

[0194] The device preprocesses the acquired impact information and video data. Specifically, it removes noise from the data, normalizes it, and extracts the necessary frames from the video data and converts them into a format suitable for analysis. This process results in clean, analyzable data being output.

[0195] Step 3:

[0196] The device sends the preprocessed data to a server. Specifically, the data is sent in real time using Wi-Fi or cellular communication. Here, the preprocessed impact data and video data are input and then sent to the server.

[0197] Step 4:

[0198] The server then analyzes the received data using an AI analysis platform. Specifically, it uses a generative AI model to integrate the impact data and video data and calculate a risk score. In this step, the data is passed as input to the AI ​​model, and a concussion risk score is obtained as output.

[0199] Step 5:

[0200] The server determines the appropriate action based on the risk score and sends a notification to the user's device. Specifically, if the risk score is high, it generates a message saying, "Warning! A strong impact to the head has been detected. Stop work and check for safety." and sends it to the user's device. This allows the worker to take immediate action.

[0201] Step 6:

[0202] The user checks the notification on the device and acts according to the instructions. Specifically, they stop their work, check for safety, and contact a medical institution if necessary. This allows for prompt and appropriate treatment.

[0203] This series of processes makes it possible to take prompt and appropriate measures when a worker receives an impact to the head.

[0204] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0205] System Overview

[0206] The system of the present invention detects impacts to the head, assesses the possibility of a concussion, and suggests appropriate measures taking into account the user's emotions. The system mainly consists of a sensor, a camera, a data preprocessing module, an AI analysis platform, an emotion engine, and a notification module.

[0207] System configuration

[0208] 1. Sensors and cameras

[0209] The device uses sensors on the hemat band and other devices to acquire information about the impact on the user's head, including an accelerometer and gyroscope, and a camera to capture video data of the impact.

[0210] 2. Data Preprocessing Module

[0211] The device preprocesses the collected raw data, including denoising impact information and normalising the data, and also extracts the required frames from the video data and converts them into a format suitable for analysis.

[0212] 3. Data Analysis

[0213] The server receives the pre-processed data and temporarily stores it in a database. The data is then input into an AI analysis platform, where an AI model is used to assess the risk of concussion, taking into account parameters such as the magnitude, direction, and duration of the impact.

[0214] 4. Operation of the Emotion Engine

[0215] The server analyzes the user's video and audio data and uses an emotion engine to assess the user's emotional state, thereby understanding how a possible concussion is affecting the user's emotions.

[0216] 5. Proposal of appropriate measures

[0217] The server generates a notification message suggesting appropriate actions to the user based on the results of the concussion risk assessment and emotion engine, and the notification is worded in a way that takes into account the user's current emotional state.

[0218] For example, if a user is feeling anxious, the following thoughtful message may be sent:

[0219] "Warning! A strong head impact has been detected. Do not worry, stop playing immediately and rest. Medical examination is strongly recommended."

[0220] 6. Data accumulation and machine learning

[0221] The server stores user feedback and usage results in a database, which is used for future analysis and to improve the AI ​​model. Emotion data is also stored, and machine learning algorithms are used to continuously retrain the emotion engine and AI model.

[0222] Specific processing examples of the system

[0223] Example 1: Application during a rugby match

[0224] Suppose a user is tackled during a rugby match. At this time, the device receives large acceleration data from the sensor mounted on the Hematband to detect the impact. At the same time, the device also receives video data of the user's head.

[0225] The pre-processing module normalizes and removes noise from the data before sending it to the server, where the AI ​​analysis platform evaluates the risk of concussion. Meanwhile, the emotion engine also analyzes the user's video data and evaluates their emotional state.

[0226] For example, if the AI ​​analysis platform assesses the risk of concussion at 80% and the emotion engine determines that the user is feeling anxious, the server will send a notification like the one below.

[0227] "Warning! A strong head impact has been detected. Do not worry, stop playing immediately and rest. Medical examination is strongly recommended."

[0228] The user checks the notification and follows the instructions to stop playing, rest, and seek medical attention.

[0229] Example 2: Falls in daily life

[0230] A similar process is applied when a user falls and hits their head in everyday life. The device's sensors and camera detect the impact and capture video data. The preprocessed data is sent to a server, where the risk of concussion is assessed.

[0231] As a result, if the risk of concussion is determined to be high and the emotion engine assesses that the user is surprised, the server will send a notification like this:

[0232] "Caution! A severe impact to the head has been detected. Please do not be afraid, but first stay calm and rest. We also recommend that you seek medical attention at a hospital as soon as possible."

[0233] In this way, the present invention provides a system that realizes early detection of concussion risk and proposes appropriate treatment by combining data collection using sensors and cameras, rapid evaluation of concussion using an AI analysis platform, and proposal of appropriate treatment taking into account the user's emotional state using an emotion engine, thereby significantly reducing the health risks to the user.

[0234] The processing flow will be explained below.

[0235] Step 1:

[0236] The device collects real-time information about the impact on the user's head from sensors installed in the Hematband, specifically, data collected from an accelerometer and gyroscope.

[0237] Step 2:

[0238] The moment an impact is detected, the device activates the camera and captures the user's video data, including a few seconds of footage before and after the impact.

[0239] Step 3:

[0240] The device preprocesses the captured impact data and video data: for impact data, noise removal, normalization, and format conversion are performed, and for video data, important frames are extracted and compressed.

[0241] Step 4:

[0242] The device encrypts and transmits the pre-processed data to the server using a secure communication protocol.

[0243] Step 5:

[0244] The server receives the data sent from the device and temporarily stores it in a database, so that all the data necessary for analysis is gathered.

[0245] Step 6:

[0246] The server inputs the received data into an AI analysis platform, which uses an AI model to assess concussion risk, taking into account parameters such as the magnitude, direction and duration of the impact.

[0247] Step 7:

[0248] The server calculates a risk score based on the concussion risk assessment results. For example, if the score exceeds a certain threshold, it is determined to be high risk.

[0249] Step 8:

[0250] The server analyzes the user's voice data and facial expressions from the captured video data and uses an emotion engine to evaluate the user's emotional state, thereby determining whether the user is feeling anxious, surprised, panicked, or other emotions.

[0251] Step 9:

[0252] The server combines the concussion risk assessment with the emotion assessment to generate a notification message suggesting appropriate actions for the user. For example, if the user is feeling anxious, the server will generate a message like this: "Warning! A strong head impact has been detected. Do not worry, stop playing immediately and rest. Medical examination is strongly recommended."

[0253] Step 10:

[0254] The server then sends the generated notification message to the user's terminal. The notification is sent in real time, allowing the user to respond promptly.

[0255] Step 11:

[0256] The user checks the notification from the device and acts according to the instructions, such as stopping play and resting, or going to the hospital for a checkup if necessary.

[0257] Step 12:

[0258] The server stores user feedback and usage results in a database, which will be used for future analysis and to improve the AI ​​model.

[0259] Step 13:

[0260] The server uses the accumulated data to retrain the AI ​​model and emotion engine to improve analysis accuracy, resulting in even more accurate risk and emotion assessments in future.

[0261] Example 2

[0262] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0263] In today's world, the risk of sustaining a strong impact to the head is increasing in sports and daily life, making early detection of concussion and appropriate treatment necessary. However, current technology is insufficient in assessing the risk of concussion or proposing appropriate treatment that takes into account the user's emotional state, and a system to ensure user safety is needed.

[0264] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0265] In this invention, the server includes means for acquiring head impact information using a sensor, means for acquiring head video data using a camera, means for preprocessing the acquired impact information and video data, means for transmitting the preprocessed data to an analysis platform and determining the possibility of a concussion, means for analyzing the user's video data and audio data and evaluating their emotional state, and means for proposing appropriate treatment for the user based on the determination result and emotional evaluation. This makes it possible to quickly and accurately assess the risk of concussion and propose appropriate treatment taking into account the user's emotional state.

[0266] The "sensor" is a device that includes an acceleration sensor, a gyroscope, etc., and acquires information about the impact on the user's head.

[0267] The "camera" is an image capturing device for acquiring image data of the head.

[0268] "Preprocessing" refers to the process of removing noise and normalizing the acquired raw data, converting it into a format suitable for analysis.

[0269] The "analysis platform" is a system that includes machine learning and AI technology to assess concussion risk based on collected data.

[0270] "Determining the likelihood of a concussion" means analyzing impact data to assess the risk of concussion and predict the degree of risk.

[0271] "Evaluating the emotional state" means analyzing the user's video and audio data to infer their emotions at that time.

[0272] "Suggest appropriate action" means informing the user of actions or steps to take based on an assessment of their concussion risk and emotional state.

[0273] "Impact information" is data obtained from an acceleration sensor, gyroscope, etc., that indicates the force applied to the user's head and changes in that force.

[0274] "Video data" refers to data relating to an image of the user's head and its surroundings, captured using a camera.

[0275] MODE FOR CARRYING OUT THE INVENTION

[0276] This system detects impacts to the head during sports and daily life, assesses the possibility of a concussion, and suggests appropriate treatment taking into account the user's emotional state. The system is composed of a sensor, a camera, a data preprocessing module, an analysis platform, an emotion engine, and a notification module.

[0277] System configuration

[0278] Each module functions as follows:

[0279] 1. Sensors and cameras

[0280] The device uses accelerometers and gyroscopes installed in the hemat band and other devices to obtain information about impacts to the user's head. For example, when a player is tackled during a rugby match, the device's sensors record data such as the magnitude, direction, and duration of the impact. The device also uses a camera to obtain video data of the impact.

[0281] 2. Data Preprocessing

[0282] The device preprocesses the acquired impact information and video data. This preprocessing includes noise removal and normalization. For example, noise contained in acceleration data is removed and normalization is performed to maintain data integrity. Furthermore, important frames of the video data are extracted and converted into a format that is easy for the analysis platform to process.

[0283] 3. Concussion risk assessment

[0284] The server receives the preprocessed data and temporarily stores it in a database. It then uses deep learning models built with Tensorflow (registered trademark) and PyTorch to assess concussion risk. Parameters such as the magnitude, direction, and duration of the impact are used for the assessment. For example, if the strength of the impact exceeds a certain threshold, it is deemed to be at high risk.

[0285] 4. Emotional assessment

[0286] The server analyzes the user's video and audio data, and the emotion engine uses OpenCV and TensorFlow to evaluate the user's emotional state. Specifically, it analyzes the user's facial expressions and tone of voice and classifies the emotion as "anxiety" or "surprise."

[0287] 5. Notification Message Generation

[0288] The server generates a notification message suggesting appropriate measures based on the concussion risk assessment result and the emotional state. For example, if the concussion risk is high and the emotional assessment is "anxious," the server generates a notification saying, "Warning! A strong impact to the head has been detected. Do not worry, but stop playing immediately and rest. A medical examination is strongly recommended."

[0289] 6. Data accumulation and machine learning

[0290] The server accumulates user feedback and usage results in a database, which is used to continuously retrain the analysis platform and emotion engine, improving the system's accuracy and user experience.

[0291] Prompt Sentence Examples

[0292] "Please explain how your system can assess the risk of a concussion if the user experiences a severe impact and suggest appropriate responses based on their emotional state."

[0293] In this way, the present invention is a system that utilizes sensors and AI technology to quickly and accurately assess the risk of concussion and propose appropriate treatment taking into account the user's emotional state, thereby significantly reducing the user's health risks.

[0294] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0295] Step 1:

[0296] Obtaining impact information

[0297] The device uses an accelerometer and gyroscope mounted on a hemat band or other device worn by the user to obtain information about the impact on the user's head. For example, when a player is tackled during a rugby match, the device's sensors record data on the magnitude, direction, and duration of the impact. The input data is the raw data obtained from the sensor, and the output data is the obtained impact data (acceleration, direction, and duration).

[0298] Step 2:

[0299] Acquiring video data

[0300] The device uses a camera to capture video data at the time of impact. For example, it records video of the user's head at the moment of impact. The input data is raw video data captured by the camera, and the output data is the captured video frames.

[0301] Step 3:

[0302] Data Preprocessing

[0303] The device preprocesses the acquired impact information and video data. Specifically, it removes noise from the acceleration data and normalizes it. It also extracts important frames from the video data and converts them into a format that is easy for the analysis platform to process. The input data is raw impact data and raw video data, and the output data is preprocessed impact data and video data.

[0304] Step 4:

[0305] Concussion risk assessment using AI analysis platform

[0306] The server receives the preprocessed data and temporarily stores it in a database. The preprocessed data is then input into a deep learning model built with TensorFlow and PyTorch to assess concussion risk. Specific processing involves inputting impact data (magnitude, direction, and duration) into the model and calculating a concussion risk score. The input data are the preprocessed impact data and video data, and the output data is a concussion risk score.

[0307] Step 5:

[0308] Emotion evaluation by emotion engine

[0309] The server analyzes the user's video and audio data and evaluates the user's emotional state using an emotion engine. Specific processing involves analyzing the user's facial expressions and tone of voice using OpenCV and TensorFlow, and evaluating the emotion as "anxiety" or "surprise." The input data are preprocessed video and audio data, and the output data are the emotion evaluation results.

[0310] Step 6:

[0311] Generate notification messages

[0312] The server generates a notification message suggesting appropriate measures based on the concussion risk assessment result and the emotion assessment result. Specifically, if the concussion risk is high and the user's emotion assessment is "anxious," a notification is generated stating, "Warning! A strong impact to the head has been detected. Do not worry, but stop playing immediately and rest. We strongly recommend that you seek medical advice." The input data are the concussion risk score and the emotion assessment result, and the output data is the generated notification message.

[0313] Step 7:

[0314] Data accumulation and machine learning

[0315] The server stores user feedback and usage results in a database, and the analysis platform and emotion engine are continuously retrained. Specific processing involves learning to improve the accuracy of the model based on past evaluation results and feedback stored in the database. The input data is user feedback and usage results data, and the output data is the retrained AI model and emotion engine.

[0316] (Application example 2)

[0317] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0318] In high-risk environments such as factories, there is a need to quickly and accurately assess the risk of concussion when a worker suffers a head impact and propose appropriate measures. Furthermore, there is a need for messages that take into account the emotional state of the worker who received the impact, but conventional systems have not been able to do this properly. Therefore, a method is needed to ensure worker safety efficiently and effectively.

[0319] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for acquiring head impact information using a sensor, means for acquiring head video data using a camera, means for preprocessing the acquired impact information and video data, means for transmitting the preprocessed data to an analysis platform and determining the possibility of a concussion, means for proposing appropriate measures to the user based on the determination result, means for evaluating the user's emotional state using an emotion analysis module, and means for generating a notification message based on the emotional state. This makes it possible to quickly and accurately assess the risk of a concussion when a worker suffers a head impact and to propose appropriate measures that take the user's emotional state into consideration.

[0320] A "sensor" is a device that detects physical environmental information and outputs it as a signal.

[0321] A "camera" is a device that captures light and records it as a still image or video.

[0322] "Impact information" is data such as the magnitude and direction of a physical impact obtained through sensors.

[0323] "Video data" refers to still image and video data captured through a camera.

[0324] "Preprocessing" refers to the process of converting the acquired raw data into a format suitable for analysis.

[0325] An "analysis platform" is a system that processes data and outputs analysis results.

[0326] A "concussion" is a temporary brain dysfunction caused by a blow to the head.

[0327] The "emotion analysis module" is software for analyzing and evaluating a user's emotional state from video and audio data.

[0328] "Proposal of action" refers to providing specific instructions or advice to the user to encourage action based on the analysis results.

[0329] A "notification message" is a text or voice message that conveys important information or instructions to the user.

[0330] The system of the present invention quickly and accurately assesses the risk of concussion when a worker suffers a head impact in a high-risk environment such as a factory, and proposes appropriate measures. The system's components include a sensor, a camera, a data preprocessing module, an AI analysis platform, an emotion analysis module, and a notification module.

[0331] Hardware and Software

[0332] Hardware: Smart helmet, smartphone, head-mounted display (HMD), accelerometer, gyroscope, camera

[0333] Software: Python, TensorFlow (AI analysis platform), OpenCV (video analysis), Amazon Rekognition (sentiment analysis)

[0334] System Operation

[0335] 1. Data Collection and Preprocessing

[0336] The device collects data from the accelerometer and gyroscope installed in the smart helmet, and also captures video data from the camera at the time of impact. This raw data is first preprocessed on the device, which includes data normalization and noise removal.

[0337] 2. Concussion risk assessment using AI analysis

[0338] The pre-processed data is sent to a server, which then inputs it into an AI analysis platform to assess concussion risk. The AI ​​analysis platform uses TensorFlow and takes into account parameters such as the magnitude, direction, and duration of the impact.

[0339] 3. Emotion analysis

[0340] The server uses Amazon Rekognition to assess the worker's emotional state from the video data, which also assesses the impact of a possible concussion on the worker's emotions.

[0341] 4. Notification and Proposed Actions

[0342] Based on the results of the concussion risk assessment and emotion analysis, the notification module generates appropriate treatment suggestions for the worker. These suggestions include wording that takes into account the worker's current emotional state. For example, if the worker is feeling anxious, a message such as "Warning! A strong head impact has been detected. Please remain calm, take a break, and seek medical attention immediately" will be sent.

[0343] Specific examples

[0344] For example, if a worker hits his head while working at height in a factory, the smart helmet's sensors will detect large acceleration data and the camera will record the incident. The preprocessed data is sent to a server, where the AI ​​analysis platform will assess the risk of concussion at 80%. Meanwhile, if emotion analysis determines that the worker is feeling anxious, a notification message like the one below will be generated.

[0345] "Warning! A severe head impact has been detected. Please remain calm, you need to rest and seek medical attention immediately."

[0346] Prompt Sentence Examples

[0347] "Assess the worker's emotional state from camera footage, assess concussion risk from impact data, and generate appropriate notification messages."

[0348] The system is expected to significantly improve worker safety and provide more personalized care based on emotional state.

[0349] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0350] Step 1:

[0351] The device uses the accelerometer and gyroscope installed in the smart helmet to obtain information about the impact on the head. Specifically, it reads signals from the sensors to obtain the magnitude and direction of the impact. It also uses a camera to obtain video data at the time of impact. This data is temporarily stored within the device. The inputs are the sensor signals and camera images, and the outputs are raw impact data and video data.

[0352] Step 2:

[0353] The terminal preprocesses the acquired raw data. Specifically, it removes noise from the impact data and normalizes the data. It also extracts necessary frames from the video data and converts them into a format suitable for analysis. The inputs are raw impact data and video data, and the outputs are normalized impact data and preprocessed video data.

[0354] Step 3:

[0355] The terminal sends the preprocessed data to the server, which receives and temporarily stores it. The input is the preprocessed impact data and video data, and the output is the data stored on the server.

[0356] Step 4:

[0357] The server inputs the preprocessed impact data into an AI analysis platform to assess concussion risk. Specifically, TensorFlow is used to input data into an AI model, which calculates a concussion risk score based on parameters such as the magnitude, direction, and duration of the impact. The input is the preprocessed impact data, and the output is a concussion risk score.

[0358] Step 5:

[0359] The server uses Amazon Rekognition to analyze the worker's emotional state from the video data. Specifically, the video data is input into an emotion analysis module, and the emotional state is evaluated from facial expressions and voice. The input is preprocessed video data, and the output is the evaluation result of the worker's emotional state.

[0360] Step 6:

[0361] The server generates a notification message based on the concussion risk score and the emotional state assessment result. Specifically, the notification module references the risk score and the emotional assessment and creates a message including appropriate treatment suggestions. The input is the concussion risk score and the emotional state assessment result, and the output is the notification message sent to the user.

[0362] Step 7:

[0363] The terminal displays the notification message sent from the server and prompts the user to take appropriate action. Specifically, the message is displayed on a display device (smartphone or head-mounted display) and instructs the user on how to respond. The input is the notification message sent from the server, and the output is the user's recognition and corresponding action.

[0364] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the 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.

[0365] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0366] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0367] [Second embodiment]

[0368] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0369] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0370] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0371] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0372] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0373] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0374] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0375] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0376] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[0377] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0378] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0379] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[0380] System Overview

[0381] The system of the present invention detects impacts to the head, assesses the possibility of a concussion, and suggests appropriate measures to the user, thereby reducing the health risks associated with a concussion. The system is primarily composed of a sensor, a camera, a data preprocessing module, an AI analysis platform, and a notification module.

[0382] System configuration

[0383] 1. Sensors and cameras

[0384] The device uses sensors on the hemat band and other devices to acquire information about the impact on the user's head, including an accelerometer and gyroscope, and a camera to capture video data of the impact.

[0385] 2. Data Preprocessing Module

[0386] The device preprocesses the collected raw data, including denoising impact information and normalising the data, and also extracts the required frames from the video data and converts them into a format suitable for analysis.

[0387] 3. Data Analysis

[0388] The server receives the pre-processed data and passes it to the AI ​​analysis platform. The AI ​​model, which has been pre-trained with a large amount of data, analyzes the impact and video data to calculate a concussion risk score. This analysis takes into account certain parameters (such as the magnitude, direction, and duration of the impact).

[0389] 4. Proposal of appropriate measures

[0390] The server then sends a notification message to the user's device suggesting appropriate measures depending on the likelihood of a concussion. For example, if the risk of a concussion is high, the following message will be displayed:

[0391] "Warning! A strong head impact has been detected. Stop playing immediately and rest. Medical attention is strongly recommended."

[0392] 5. Data accumulation and machine learning

[0393] The server collects user feedback and newly collected data and stores it in a database. Machine learning algorithms are used to continuously retrain the AI ​​model to improve its accuracy.

[0394] Specific processing examples of the system

[0395] Example 1: Application during a rugby match

[0396] Suppose a user is tackled during a rugby match. At this time, the device receives large acceleration data from the sensor in the Hematband and detects the impact. The device also simultaneously receives video data of the user's head.

[0397] The pre-processing module normalizes the data and removes noise before sending it to the server. The server receives the data, and the AI ​​analysis platform evaluates the risk of concussion. For example, if the server determines that there is an 80% chance of a concussion, it sends the next instruction to the user's smartphone.

[0398] "Warning! A severe head impact has been detected. Stop playing immediately and rest. Medical attention is strongly recommended."

[0399] The user checks the notification and follows the instructions to stop playing, rest, and seek medical attention.

[0400] Example 2: Falls in daily life

[0401] A similar process is applied when a user falls and hits their head in everyday life. The device's sensors and camera detect the impact and capture video data. The preprocessed data is sent to a server, where the risk of concussion is assessed.

[0402] If the server determines that the user is at high risk of concussion, it will send a notification to the user's device suggesting appropriate measures. The content of the notification will vary depending on the circumstances of the fall, but will generally recommend resting and seeking medical attention.

[0403] In this way, the present invention provides a system that combines data collection by sensors and cameras with rapid evaluation of concussion using an AI analysis platform, enabling early detection of concussion risk and suggesting appropriate treatment, thereby significantly reducing the health risks to users.

[0404] The processing flow will be explained below.

[0405] Step 1:

[0406] The device acquires information about head impacts from sensors installed in the Hemat band worn by the user, specifically, collecting data in real time from an accelerometer and gyroscope.

[0407] Step 2:

[0408] When an impact is detected, the device simultaneously activates the camera to capture video data of the head, recording footage from a few seconds before and after the impact.

[0409] Step 3:

[0410] The device preprocesses the acquired impact data by denoising, normalizing, and formatting it to make it suitable for analysis.

[0411] Step 4:

[0412] The device preprocesses the captured video data, extracting important frames, compressing them, and preparing them for transmission to the analysis platform.

[0413] Step 5:

[0414] The device encrypts and transmits the pre-processed impact data and video data to a server using a secure communication protocol.

[0415] Step 6:

[0416] The server receives the data sent from the device and temporarily stores it in a database, so that all the data necessary for analysis is gathered.

[0417] Step 7:

[0418] The server inputs the received data into an AI analysis platform, which uses an AI model to assess the risk of concussion, taking into account parameters such as the magnitude, direction, and duration of the impact.

[0419] Step 8:

[0420] The server calculates a concussion risk score based on the results of the AI ​​analysis platform. For example, if the risk score exceeds a certain threshold, it will be judged as a high risk.

[0421] Step 9:

[0422] The server generates appropriate treatment suggestions for the user based on the risk assessment results, such as creating a notification message recommending rest or visiting a hospital.

[0423] Step 10:

[0424] The server sends the generated notification message to the user's terminal. The notification is performed in real time, helping the user to respond quickly.

[0425] Step 11:

[0426] The user checks the notification from the device and acts according to the instructions, such as stopping play and resting, or going to the hospital for a medical examination if necessary.

[0427] Step 12:

[0428] The server stores user feedback and usage results in a database, which will be used for future analysis and to improve the AI ​​model.

[0429] Step 13:

[0430] The server uses the accumulated data to retrain the AI ​​model and improve its analysis accuracy, which will result in even more accurate risk assessments from the next time onwards.

[0431] Example 1

[0432] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0433] Concussions caused by impacts to the head can pose serious health risks if appropriate measures are not taken. However, conventional methods require users to detect the impact and determine the appropriate measures themselves, which often makes it difficult to respond quickly. In addition, there are limited means of assessing the risk of concussion, making it difficult to make accurate judgments. Therefore, there is a need for a system that can quickly and accurately assess the risk of concussion and suggest appropriate measures to users.

[0434] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0435] In this invention, the server includes means for acquiring head impact information using a sensor, means for acquiring head video data using a camera, means for preprocessing the acquired impact information and video data, means for transmitting the preprocessed data to an analysis platform and determining the possibility of concussion using a generative AI model, and means for suggesting appropriate measures to the user based on the determination results, thereby enabling rapid and accurate assessment of concussion risk and suggesting appropriate measures.

[0436] A "sensor" is a device that detects physical movement, such as an accelerometer or gyroscope.

[0437] A "camera" is a device that captures images or videos and is used to obtain video data of the head.

[0438] "Impact information" is data on physical movements and forces applied to the head obtained by sensors.

[0439] "Video data" refers to information about images and videos captured by a camera.

[0440] "Preprocessing" refers to the process of removing noise from acquired data and converting it into a format suitable for analysis.

[0441] "Analysis platform" refers to systems and software for analyzing data, including generative AI models.

[0442] A "generative AI model" is an algorithm that learns from large amounts of data and evaluates the risk of concussion from the input data.

[0443] "Concussion probability" refers to the probability or risk of a concussion occurring as a result of an impact.

[0444] "Appropriate Actions" are suggested actions or treatment instructions for the user based on their risk of concussion.

[0445] A "user device" is a device such as a smartphone or tablet that allows a user to receive notifications.

[0446] The "judgment result" is the result of the concussion risk assessment analyzed by the generative AI model.

[0447] System Overview

[0448] The system of the present invention detects impacts to the head, assesses the possibility of a concussion, and suggests appropriate measures to the user, thereby reducing the health risks associated with concussions. This system is primarily composed of a sensor, a camera, a data preprocessing module, an AI analysis platform, and a notification module.

[0449] System configuration

[0450] Sensors and Cameras

[0451] The device uses sensors in the hematological band and other devices to capture information about the impact on the user's head, including an accelerometer and gyroscope, which collect data on the physical movement and force of the head, and a camera to capture video data of the impact.

[0452] Data Preprocessing Module

[0453] The device preprocesses the acquired impact information and video data. Specifically, it removes noise, normalizes the data, and converts it into a format suitable for analysis. It also extracts the necessary frames from the video data.

[0454] Data analysis

[0455] The server receives the pre-processed data and passes it to a generative AI model, which is trained on a large amount of data in advance and analyzes the impact and video data to calculate a concussion risk score, taking into account parameters such as the magnitude, direction, and duration of the impact.

[0456] Proposal of appropriate measures

[0457] The server generates a notification message suggesting appropriate measures based on the concussion risk score calculated by the AI ​​model and sends it to the user device. For example, if the server determines that the risk of a concussion is high, it sends a message saying, "Warning! A strong impact to the head has been detected. Stop playing immediately and rest. We strongly recommend that you seek medical attention."

[0458] Data accumulation and machine learning

[0459] The server continuously accumulates user feedback and newly collected data and stores it in a database, which continuously retrains the generative AI model and improves its accuracy. Through this feedback loop, the accuracy of concussion risk assessment is further improved.

[0460] Specific processing examples of the system

[0461] Example 1: Application during a rugby match

[0462] Suppose a user is tackled during a rugby match. At this time, the device receives large acceleration data from the sensor in the Hematband and detects the impact. The device also simultaneously receives video data of the user's head.

[0463] The pre-processing module normalizes and removes noise from the data before sending it to the server, which receives it and uses a generative AI model to assess the risk of a concussion. For example, if the server determines there is an 80% chance of a concussion, it sends the following instructions to the user's smartphone:

[0464] "Warning! A severe head impact has been detected. Stop playing immediately and rest. Medical attention is strongly recommended."

[0465] The user checks the notification and follows the instructions to stop playing, rest, and seek medical attention.

[0466] Example 2: Falls in daily life

[0467] A similar process is applied when a user falls and hits their head in everyday life. The device's sensors and camera detect the impact and capture video data. The preprocessed data is sent to a server, where the risk of concussion is assessed.

[0468] If the server determines that the user is at high risk of concussion, it will send a notification to the user's device suggesting appropriate measures. The content of the notification will vary depending on the circumstances of the fall, but will generally recommend resting and seeking medical attention.

[0469] In this way, the present invention provides a system that combines data collection by sensors and cameras with rapid assessment of concussion using generative AI models to enable early detection of concussion risk and suggest appropriate treatment, thereby significantly reducing the health risks to users.

[0470] Examples of prompt statements

[0471] "Please explain the procedure for the system that assesses the risk of concussion when tackled during a rugby match."

[0472] "Please explain in detail how this system will assess the risk of concussion and suggest appropriate measures to the user when they fall and hit their head in daily life."

[0473] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0474] Step 1: Collect data

[0475] The device uses sensors and a camera to collect information about the impact to the head and video data. Specifically, the accelerometer and gyroscope collect impact information, and the camera collects video data.

[0476] Input: Impact to the user's head

[0477] Output: Impact data (acceleration, direction), video data

[0478] Specific example of operation: When a user is tackled during sports, the acceleration sensor installed in the Hematband measures a large acceleration and the camera records the moment.

[0479] Step 2: Preprocessing the data

[0480] The device preprocesses the collected raw data, specifically removing noise and normalizing the data. For video data, it extracts the necessary frames and converts them into a format suitable for analysis.

[0481] Input: Impact data, video data

[0482] Output: Preprocessed data

[0483] Specific example of operation: The device removes noise from accelerometer data and cuts unnecessary frames from video data to extract important moments.

[0484] Step 3: Analyze the data

[0485] The server receives the pre-processed data and passes it to a generative AI model, which analyzes the impact and video data to calculate a concussion risk score, taking into account parameters such as impact magnitude, direction, and duration.

[0486] Input: Preprocessed data

[0487] Output: Concussion risk score

[0488] Specific example of operation: The server receives preprocessed data sent from the device and uses the generative AI model to determine that the risk of concussion is 80%.

[0489] Step 4: Propose appropriate action

[0490] The server generates and transmits a notification message to the user device suggesting appropriate treatment based on the concussion risk score.

[0491] Input: Concussion Risk Score

[0492] Output: Notification message

[0493] Specific example of operation: If the server determines that there is a high risk of concussion, it will send a message to the user's smartphone stating, "Warning! A strong impact to the head has been detected. Stop playing immediately and rest. We strongly recommend that you seek medical attention."

[0494] Step 5: Data accumulation and machine learning

[0495] The server accumulates user feedback and newly collected data and stores it in a database. Machine learning algorithms are used to continuously retrain the generative AI model to improve its accuracy.

[0496] Input: User feedback, collected data

[0497] Output: Updated generative AI model

[0498] Specific example of operation: When a user enters the results of a medical examination at a hospital into the app, the server stores the data in a database and uses it to retrain the AI ​​model.

[0499] (Application example 1)

[0500] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0501] Head impacts to workers during factory work can lead to serious accidents and health risks. Currently, there is a lack of systems that can take prompt and appropriate measures when a head impact occurs. In particular, it is difficult to ensure worker safety unless appropriate measures and risk assessments can be quickly carried out after an impact. This can lead to work interruptions, reduced productivity, and even damage to the worker's health. Therefore, there is a strong demand for a system that can immediately detect head impacts during factory work and take appropriate measures.

[0502] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0503] In this invention, the server includes means for acquiring head impact information using a sensor, means for acquiring head video data using a camera, means for preprocessing the acquired impact information and video data, means for transmitting data to personal devices used by workers, and means for monitoring the head safety of workers in a factory environment. This makes it possible to immediately detect head impacts during work, quickly assess the risk, and propose appropriate measures.

[0504] "Sensor" refers to a device for acquiring information about impacts to the head, and includes an acceleration sensor and a gyroscope.

[0505] A "camera" is a device for acquiring image data of the head.

[0506] "Preprocessing" refers to the process of removing noise from the acquired impact information and video data and converting the data into a format suitable for analysis.

[0507] The "analysis platform" is a system equipped with an AI model that receives preprocessed data and performs impact risk assessment.

[0508] "Impact information" is data on the impact on the head obtained by the sensor.

[0509] "Video data" is video information of the head captured by a camera.

[0510] A "user terminal" is a personal terminal used by a worker, and includes a smartphone or tablet.

[0511] "Appropriate measures" are actions and precautions suggested to the user depending on the situation after the impact.

[0512] The "means for monitoring worker head safety in a factory environment" is a system that immediately detects and analyzes any impact to the head of a worker in a factory, and suggests appropriate countermeasures.

[0513] To implement this invention, it is necessary to build a system including the following components: The system is mainly composed of a sensor, a camera, a data preprocessing module, an AI analysis platform, and a notification module.

[0514] 1. Equipped with sensors and cameras

[0515] The sensors will be installed in the smart helmets worn by the workers, including accelerometers and gyroscopes to capture information about head impacts, and a camera will also be installed in the smart helmets to capture video data at the time of impact.

[0516] 2. Data Preprocessing

[0517] The device (smartphone or tablet) receives the impact information and video data sent from the helmet. This data undergoes preprocessing such as noise removal and normalization. The necessary frames from the video data are also extracted and converted into a format suitable for analysis.

[0518] 3. Sending data to the server

[0519] The preprocessed data is sent from the device to a server, which receives it and analyzes it using an AI analysis platform.

[0520] 4. Data Analysis

[0521] The AI ​​analysis platform on the server uses the pre-processed data to perform a risk assessment of head impacts. This analysis uses a generative AI model that has been trained on a large amount of data in advance, taking into account specific parameters (such as the magnitude, direction, and duration of the impact).

[0522] 5. Notification and Proposal of Appropriate Action

[0523] The server then notifies the user of appropriate measures based on the risk score. For example, if the risk of a concussion is high, a message will be displayed saying, "Warning! A strong impact to the head has been detected. Stop work and check for safety."

[0524] Specific examples

[0525] When a factory worker receives an impact to the head, the smart helmet detects the impact and collects data. The data is preprocessed on the smartphone and sent to a server. The AI ​​analysis platform on the server analyzes the data and calculates a risk score. As a result, an appropriate action is determined and a notification is sent to the user's device.

[0526] Prompt Sentence Examples

[0527] "Design an application that detects when a factory worker has received a hard blow to the head and provides an immediate risk assessment."

[0528] By designing and implementing this system, it will be possible to quickly suggest appropriate measures to be taken when a factory worker suffers a blow to the head, thereby reducing health risks.

[0529] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0530] Step 1:

[0531] The sensors and cameras collect information about the impact on the worker's head and video data. Specifically, the acceleration sensor and gyroscope collect data on the impact to the head, and the camera captures the video at that time. This provides the input impact data and video data.

[0532] Step 2:

[0533] The device preprocesses the acquired impact information and video data. Specifically, it removes noise from the data, normalizes it, and extracts the necessary frames from the video data and converts them into a format suitable for analysis. This process results in clean, analyzable data being output.

[0534] Step 3:

[0535] The device sends the preprocessed data to a server. Specifically, the data is sent in real time using Wi-Fi or cellular communication. Here, the preprocessed impact data and video data are input and then sent to the server.

[0536] Step 4:

[0537] The server then analyzes the received data using an AI analysis platform. Specifically, it uses a generative AI model to integrate the impact data and video data and calculate a risk score. In this step, the data is passed as input to the AI ​​model, and a concussion risk score is obtained as output.

[0538] Step 5:

[0539] The server determines the appropriate action based on the risk score and sends a notification to the user's device. Specifically, if the risk score is high, it generates a message saying, "Warning! A strong impact to the head has been detected. Stop work and check for safety." and sends it to the user's device. This allows the worker to take immediate action.

[0540] Step 6:

[0541] The user checks the notification on the device and acts according to the instructions. Specifically, they stop their work, check for safety, and contact a medical institution if necessary. This allows for prompt and appropriate treatment.

[0542] This series of processes makes it possible to take prompt and appropriate measures when a worker receives an impact to the head.

[0543] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0544] System Overview

[0545] The system of the present invention detects impacts to the head, assesses the possibility of a concussion, and suggests appropriate measures taking into account the user's emotions. The system mainly consists of a sensor, a camera, a data preprocessing module, an AI analysis platform, an emotion engine, and a notification module.

[0546] System configuration

[0547] 1. Sensors and cameras

[0548] The device uses sensors on the hemat band and other devices to acquire information about the impact on the user's head, including an accelerometer and gyroscope, and a camera to capture video data of the impact.

[0549] 2. Data Preprocessing Module

[0550] The device preprocesses the collected raw data, including denoising impact information and normalising the data, and also extracts the required frames from the video data and converts them into a format suitable for analysis.

[0551] 3. Data Analysis

[0552] The server receives the pre-processed data and temporarily stores it in a database. The data is then input into an AI analysis platform, where an AI model is used to assess the risk of concussion, taking into account parameters such as the magnitude, direction, and duration of the impact.

[0553] 4. Operation of the Emotion Engine

[0554] The server analyzes the user's video and audio data and uses an emotion engine to assess the user's emotional state, thereby understanding how a possible concussion is affecting the user's emotions.

[0555] 5. Proposal of appropriate measures

[0556] The server generates a notification message suggesting appropriate actions to the user based on the results of the concussion risk assessment and emotion engine, and the notification is worded in a way that takes into account the user's current emotional state.

[0557] For example, if a user is feeling anxious, the following thoughtful message may be sent:

[0558] "Warning! A strong head impact has been detected. Do not worry, stop playing immediately and rest. Medical examination is strongly recommended."

[0559] 6. Data accumulation and machine learning

[0560] The server stores user feedback and usage results in a database, which is used for future analysis and to improve the AI ​​model. Emotion data is also stored, and machine learning algorithms are used to continuously retrain the emotion engine and AI model.

[0561] Specific processing examples of the system

[0562] Example 1: Application during a rugby match

[0563] Suppose a user is tackled during a rugby match. At this time, the device receives large acceleration data from the sensor mounted on the Hematband to detect the impact. At the same time, the device also receives video data of the user's head.

[0564] The pre-processing module normalizes and removes noise from the data before sending it to the server, where the AI ​​analysis platform evaluates the risk of concussion. Meanwhile, the emotion engine also analyzes the user's video data and evaluates their emotional state.

[0565] For example, if the AI ​​analysis platform assesses the risk of concussion at 80% and the emotion engine determines that the user is feeling anxious, the server will send a notification like the one below.

[0566] "Warning! A strong head impact has been detected. Do not worry, stop playing immediately and rest. Medical examination is strongly recommended."

[0567] The user checks the notification and follows the instructions to stop playing, rest, and seek medical attention.

[0568] Example 2: Falls in daily life

[0569] A similar process is applied when a user falls and hits their head in everyday life. The device's sensors and camera detect the impact and capture video data. The preprocessed data is sent to a server, where the risk of concussion is assessed.

[0570] As a result, if the risk of concussion is determined to be high and the emotion engine assesses that the user is surprised, the server will send a notification like this:

[0571] "Caution! A severe impact to the head has been detected. Please do not be afraid, but first stay calm and rest. We also recommend that you seek medical attention at a hospital as soon as possible."

[0572] In this way, the present invention provides a system that realizes early detection of concussion risk and proposes appropriate treatment by combining data collection using sensors and cameras, rapid evaluation of concussion using an AI analysis platform, and proposal of appropriate treatment taking into account the user's emotional state using an emotion engine, thereby significantly reducing the health risks to the user.

[0573] The processing flow will be explained below.

[0574] Step 1:

[0575] The device collects real-time information about the impact on the user's head from sensors installed in the Hematband, specifically, data collected from an accelerometer and gyroscope.

[0576] Step 2:

[0577] The moment an impact is detected, the device activates the camera and captures the user's video data, including a few seconds of footage before and after the impact.

[0578] Step 3:

[0579] The device preprocesses the captured impact data and video data: for impact data, noise removal, normalization, and format conversion are performed, and for video data, important frames are extracted and compressed.

[0580] Step 4:

[0581] The device encrypts and transmits the pre-processed data to the server using a secure communication protocol.

[0582] Step 5:

[0583] The server receives the data sent from the device and temporarily stores it in a database, so that all the data necessary for analysis is gathered.

[0584] Step 6:

[0585] The server inputs the received data into an AI analysis platform, which uses an AI model to assess concussion risk, taking into account parameters such as the magnitude, direction and duration of the impact.

[0586] Step 7:

[0587] The server calculates a risk score based on the concussion risk assessment results. For example, if the score exceeds a certain threshold, it is determined to be high risk.

[0588] Step 8:

[0589] The server analyzes the user's voice data and facial expressions from the captured video data and uses an emotion engine to evaluate the user's emotional state, thereby determining whether the user is feeling anxious, surprised, panicked, or other emotions.

[0590] Step 9:

[0591] The server combines the concussion risk assessment with the emotion assessment to generate a notification message suggesting appropriate actions for the user. For example, if the user is feeling anxious, the server will generate a message like this: "Warning! A strong head impact has been detected. Do not worry, stop playing immediately and rest. Medical examination is strongly recommended."

[0592] Step 10:

[0593] The server then sends the generated notification message to the user's terminal. The notification is sent in real time, allowing the user to respond promptly.

[0594] Step 11:

[0595] The user checks the notification from the device and acts according to the instructions, such as stopping play and resting, or going to the hospital for a checkup if necessary.

[0596] Step 12:

[0597] The server stores user feedback and usage results in a database, which will be used for future analysis and to improve the AI ​​model.

[0598] Step 13:

[0599] The server uses the accumulated data to retrain the AI ​​model and emotion engine to improve analysis accuracy, resulting in even more accurate risk and emotion assessments in future.

[0600] Example 2

[0601] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0602] In today's world, the risk of sustaining a strong impact to the head is increasing in sports and daily life, making early detection of concussion and appropriate treatment necessary. However, current technology is insufficient in assessing the risk of concussion or proposing appropriate treatment that takes into account the user's emotional state, and a system to ensure user safety is needed.

[0603] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0604] In this invention, the server includes means for acquiring head impact information using a sensor, means for acquiring head video data using a camera, means for preprocessing the acquired impact information and video data, means for transmitting the preprocessed data to an analysis platform and determining the possibility of a concussion, means for analyzing the user's video data and audio data and evaluating their emotional state, and means for proposing appropriate treatment for the user based on the determination result and emotional evaluation. This makes it possible to quickly and accurately assess the risk of concussion and propose appropriate treatment taking into account the user's emotional state.

[0605] The "sensor" is a device that includes an acceleration sensor, a gyroscope, etc., and acquires information about the impact on the user's head.

[0606] The "camera" is an image capturing device for acquiring image data of the head.

[0607] "Preprocessing" refers to the process of removing noise and normalizing the acquired raw data, converting it into a format suitable for analysis.

[0608] The "analysis platform" is a system that includes machine learning and AI technology to assess concussion risk based on collected data.

[0609] "Determining the likelihood of a concussion" means analyzing impact data to assess the risk of concussion and predict the degree of risk.

[0610] "Evaluating the emotional state" means analyzing the user's video and audio data to infer their emotions at that time.

[0611] "Suggest appropriate action" means informing the user of actions or steps to take based on an assessment of their concussion risk and emotional state.

[0612] "Impact information" is data obtained from an acceleration sensor, gyroscope, etc., that indicates the force applied to the user's head and changes in that force.

[0613] "Video data" refers to data relating to an image of the user's head and its surroundings, captured using a camera.

[0614] MODE FOR CARRYING OUT THE INVENTION

[0615] This system detects impacts to the head during sports and daily life, assesses the possibility of a concussion, and suggests appropriate treatment taking into account the user's emotional state. The system is composed of a sensor, a camera, a data preprocessing module, an analysis platform, an emotion engine, and a notification module.

[0616] System configuration

[0617] Each module functions as follows:

[0618] 1. Sensors and cameras

[0619] The device uses accelerometers and gyroscopes installed in the hemat band and other devices to obtain information about impacts to the user's head. For example, when a player is tackled during a rugby match, the device's sensors record data such as the magnitude, direction, and duration of the impact. The device also uses a camera to obtain video data of the impact.

[0620] 2. Data Preprocessing

[0621] The device preprocesses the acquired impact information and video data. This preprocessing includes noise removal and normalization. For example, noise contained in acceleration data is removed and normalization is performed to maintain data integrity. Furthermore, important frames of the video data are extracted and converted into a format that is easy for the analysis platform to process.

[0622] 3. Concussion risk assessment

[0623] The server receives the preprocessed data and temporarily stores it in a database. It then uses a deep learning model built with TensorFlow and PyTorch to assess concussion risk. Parameters such as the magnitude, direction, and duration of the impact are used for the assessment. For example, if the strength of the impact exceeds a certain threshold, it is deemed to be at high risk.

[0624] 4. Emotional assessment

[0625] The server analyzes the user's video and audio data, and the emotion engine uses OpenCV and TensorFlow to evaluate the user's emotional state. Specifically, it analyzes the user's facial expressions and tone of voice and classifies the emotion as "anxiety" or "surprise."

[0626] 5. Notification Message Generation

[0627] The server generates a notification message suggesting appropriate measures based on the concussion risk assessment result and the emotional state. For example, if the concussion risk is high and the emotional assessment is "anxious," the server generates a notification saying, "Warning! A strong impact to the head has been detected. Do not worry, but stop playing immediately and rest. A medical examination is strongly recommended."

[0628] 6. Data accumulation and machine learning

[0629] The server accumulates user feedback and usage results in a database, which is used to continuously retrain the analysis platform and emotion engine, improving the system's accuracy and user experience.

[0630] Prompt Sentence Examples

[0631] "Please explain how your system can assess the risk of a concussion if the user experiences a severe impact and suggest appropriate responses based on their emotional state."

[0632] In this way, the present invention is a system that utilizes sensors and AI technology to quickly and accurately assess the risk of concussion and propose appropriate treatment taking into account the user's emotional state, thereby significantly reducing the user's health risks.

[0633] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0634] Step 1:

[0635] Obtaining impact information

[0636] The device uses an accelerometer and gyroscope mounted on a hemat band or other device worn by the user to obtain information about the impact on the user's head. For example, when a player is tackled during a rugby match, the device's sensors record data on the magnitude, direction, and duration of the impact. The input data is the raw data obtained from the sensor, and the output data is the obtained impact data (acceleration, direction, and duration).

[0637] Step 2:

[0638] Acquiring video data

[0639] The device uses a camera to capture video data at the time of impact. For example, it records video of the user's head at the moment of impact. The input data is raw video data captured by the camera, and the output data is the captured video frames.

[0640] Step 3:

[0641] Data Preprocessing

[0642] The device preprocesses the acquired impact information and video data. Specifically, it removes noise from the acceleration data and normalizes it. It also extracts important frames from the video data and converts them into a format that is easy for the analysis platform to process. The input data is raw impact data and raw video data, and the output data is preprocessed impact data and video data.

[0643] Step 4:

[0644] Concussion risk assessment using AI analysis platform

[0645] The server receives the preprocessed data and temporarily stores it in a database. The preprocessed data is then input into a deep learning model built with TensorFlow and PyTorch to assess concussion risk. Specific processing involves inputting impact data (magnitude, direction, and duration) into the model and calculating a concussion risk score. The input data are the preprocessed impact data and video data, and the output data is a concussion risk score.

[0646] Step 5:

[0647] Emotion evaluation by emotion engine

[0648] The server analyzes the user's video and audio data and evaluates the user's emotional state using an emotion engine. Specific processing involves analyzing the user's facial expressions and tone of voice using OpenCV and TensorFlow, and evaluating the emotion as "anxiety" or "surprise." The input data are preprocessed video and audio data, and the output data are the emotion evaluation results.

[0649] Step 6:

[0650] Generate notification messages

[0651] The server generates a notification message suggesting appropriate measures based on the concussion risk assessment result and the emotion assessment result. Specifically, if the concussion risk is high and the user's emotion assessment is "anxious," a notification is generated stating, "Warning! A strong impact to the head has been detected. Do not worry, but stop playing immediately and rest. We strongly recommend that you seek medical advice." The input data are the concussion risk score and the emotion assessment result, and the output data is the generated notification message.

[0652] Step 7:

[0653] Data accumulation and machine learning

[0654] The server stores user feedback and usage results in a database, and the analysis platform and emotion engine are continuously retrained. Specific processing involves learning to improve the accuracy of the model based on past evaluation results and feedback stored in the database. The input data is user feedback and usage results data, and the output data is the retrained AI model and emotion engine.

[0655] (Application example 2)

[0656] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0657] In high-risk environments such as factories, there is a need to quickly and accurately assess the risk of concussion when a worker suffers a head impact and propose appropriate measures. Furthermore, there is a need for messages that take into account the emotional state of the worker who received the impact, but conventional systems have not been able to do this properly. Therefore, a method is needed to ensure worker safety efficiently and effectively.

[0658] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for acquiring head impact information using a sensor, means for acquiring head video data using a camera, means for preprocessing the acquired impact information and video data, means for transmitting the preprocessed data to an analysis platform and determining the possibility of a concussion, means for proposing appropriate measures to the user based on the determination result, means for evaluating the user's emotional state using an emotion analysis module, and means for generating a notification message based on the emotional state. This makes it possible to quickly and accurately assess the risk of a concussion when a worker suffers a head impact and to propose appropriate measures that take the user's emotional state into consideration.

[0659] A "sensor" is a device that detects physical environmental information and outputs it as a signal.

[0660] A "camera" is a device that captures light and records it as a still image or video.

[0661] "Impact information" is data such as the magnitude and direction of a physical impact obtained through sensors.

[0662] "Video data" refers to still image and video data captured through a camera.

[0663] "Preprocessing" refers to the process of converting the acquired raw data into a format suitable for analysis.

[0664] An "analysis platform" is a system that processes data and outputs analysis results.

[0665] A "concussion" is a temporary brain dysfunction caused by a blow to the head.

[0666] The "emotion analysis module" is software for analyzing and evaluating a user's emotional state from video and audio data.

[0667] "Proposal of action" refers to providing specific instructions or advice to the user to encourage action based on the analysis results.

[0668] A "notification message" is a text or voice message that conveys important information or instructions to the user.

[0669] The system of the present invention quickly and accurately assesses the risk of concussion when a worker suffers a head impact in a high-risk environment such as a factory, and proposes appropriate measures. The system's components include a sensor, a camera, a data preprocessing module, an AI analysis platform, an emotion analysis module, and a notification module.

[0670] Hardware and Software

[0671] Hardware: Smart helmet, smartphone, head-mounted display (HMD), accelerometer, gyroscope, camera

[0672] Software: Python, TensorFlow (AI analysis platform), OpenCV (video analysis), Amazon Rekognition (sentiment analysis)

[0673] System Operation

[0674] 1. Data Collection and Preprocessing

[0675] The device collects data from the accelerometer and gyroscope installed in the smart helmet, and also captures video data from the camera at the time of impact. This raw data is first preprocessed on the device, which includes data normalization and noise removal.

[0676] 2. Concussion risk assessment using AI analysis

[0677] The pre-processed data is sent to a server, which then inputs it into an AI analysis platform to assess concussion risk. The AI ​​analysis platform uses TensorFlow and takes into account parameters such as the magnitude, direction, and duration of the impact.

[0678] 3. Emotion analysis

[0679] The server uses Amazon Rekognition to assess the worker's emotional state from the video data, which also assesses the impact of a possible concussion on the worker's emotions.

[0680] 4. Notification and Proposed Actions

[0681] Based on the results of the concussion risk assessment and emotion analysis, the notification module generates appropriate treatment suggestions for the worker. These suggestions include wording that takes into account the worker's current emotional state. For example, if the worker is feeling anxious, a message such as "Warning! A strong head impact has been detected. Please remain calm, take a break, and seek medical attention immediately" will be sent.

[0682] Specific examples

[0683] For example, if a worker hits his head while working at height in a factory, the smart helmet's sensors will detect large acceleration data and the camera will record the incident. The preprocessed data is sent to a server, where the AI ​​analysis platform will assess the risk of concussion at 80%. Meanwhile, if emotion analysis determines that the worker is feeling anxious, a notification message like the one below will be generated.

[0684] "Warning! A severe head impact has been detected. Please remain calm, you need to rest and seek medical attention immediately."

[0685] Prompt Sentence Examples

[0686] "Assess the worker's emotional state from camera footage, assess concussion risk from impact data, and generate appropriate notification messages."

[0687] The system is expected to significantly improve worker safety and provide more personalized care based on emotional state.

[0688] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0689] Step 1:

[0690] The device uses the accelerometer and gyroscope installed in the smart helmet to obtain information about the impact on the head. Specifically, it reads signals from the sensors to obtain the magnitude and direction of the impact. It also uses a camera to obtain video data at the time of impact. This data is temporarily stored within the device. The inputs are the sensor signals and camera images, and the outputs are raw impact data and video data.

[0691] Step 2:

[0692] The terminal preprocesses the acquired raw data. Specifically, it removes noise from the impact data and normalizes the data. It also extracts necessary frames from the video data and converts them into a format suitable for analysis. The inputs are raw impact data and video data, and the outputs are normalized impact data and preprocessed video data.

[0693] Step 3:

[0694] The terminal sends the preprocessed data to the server, which receives and temporarily stores it. The input is the preprocessed impact data and video data, and the output is the data stored on the server.

[0695] Step 4:

[0696] The server inputs the preprocessed impact data into an AI analysis platform to assess concussion risk. Specifically, TensorFlow is used to input data into an AI model, which calculates a concussion risk score based on parameters such as the magnitude, direction, and duration of the impact. The input is the preprocessed impact data, and the output is a concussion risk score.

[0697] Step 5:

[0698] The server uses Amazon Rekognition to analyze the worker's emotional state from the video data. Specifically, the video data is input into an emotion analysis module, and the emotional state is evaluated from facial expressions and voice. The input is preprocessed video data, and the output is the evaluation result of the worker's emotional state.

[0699] Step 6:

[0700] The server generates a notification message based on the concussion risk score and the emotional state assessment result. Specifically, the notification module references the risk score and the emotional assessment and creates a message including appropriate treatment suggestions. The input is the concussion risk score and the emotional state assessment result, and the output is the notification message sent to the user.

[0701] Step 7:

[0702] The terminal displays the notification message sent from the server and prompts the user to take appropriate action. Specifically, the message is displayed on a display device (smartphone or head-mounted display) and instructs the user on how to respond. The input is the notification message sent from the server, and the output is the user's recognition and corresponding action.

[0703] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0704] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0705] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0706] [Third embodiment]

[0707] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0708] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0709] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0710] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0711] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0712] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0713] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0714] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0715] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[0716] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0717] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0718] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[0719] System Overview

[0720] The system of the present invention detects impacts to the head, assesses the possibility of a concussion, and suggests appropriate measures to the user, thereby reducing the health risks associated with a concussion. The system is primarily composed of a sensor, a camera, a data preprocessing module, an AI analysis platform, and a notification module.

[0721] System configuration

[0722] 1. Sensors and cameras

[0723] The device uses sensors on the hemat band and other devices to acquire information about the impact on the user's head, including an accelerometer and gyroscope, and a camera to capture video data of the impact.

[0724] 2. Data Preprocessing Module

[0725] The device preprocesses the collected raw data, including denoising impact information and normalising the data, and also extracts the required frames from the video data and converts them into a format suitable for analysis.

[0726] 3. Data Analysis

[0727] The server receives the pre-processed data and passes it to the AI ​​analysis platform. The AI ​​model, which has been pre-trained with a large amount of data, analyzes the impact and video data to calculate a concussion risk score. This analysis takes into account certain parameters (such as the magnitude, direction, and duration of the impact).

[0728] 4. Proposal of appropriate measures

[0729] The server then sends a notification message to the user's device suggesting appropriate measures depending on the likelihood of a concussion. For example, if the risk of a concussion is high, the following message will be displayed:

[0730] "Warning! A strong head impact has been detected. Stop playing immediately and rest. Medical attention is strongly recommended."

[0731] 5. Data accumulation and machine learning

[0732] The server collects user feedback and newly collected data and stores it in a database. Machine learning algorithms are used to continuously retrain the AI ​​model to improve its accuracy.

[0733] Specific processing examples of the system

[0734] Example 1: Application during a rugby match

[0735] Suppose a user is tackled during a rugby match. At this time, the device receives large acceleration data from the sensor in the Hematband and detects the impact. The device also simultaneously receives video data of the user's head.

[0736] The pre-processing module normalizes the data and removes noise before sending it to the server. The server receives the data, and the AI ​​analysis platform evaluates the risk of concussion. For example, if the server determines that there is an 80% chance of a concussion, it sends the next instruction to the user's smartphone.

[0737] "Warning! A severe head impact has been detected. Stop playing immediately and rest. Medical attention is strongly recommended."

[0738] The user checks the notification and follows the instructions to stop playing, rest, and seek medical attention.

[0739] Example 2: Falls in daily life

[0740] A similar process is applied when a user falls and hits their head in everyday life. The device's sensors and camera detect the impact and capture video data. The preprocessed data is sent to a server, where the risk of concussion is assessed.

[0741] If the server determines that the user is at high risk of concussion, it will send a notification to the user's device suggesting appropriate measures. The content of the notification will vary depending on the circumstances of the fall, but will generally recommend resting and seeking medical attention.

[0742] In this way, the present invention provides a system that combines data collection by sensors and cameras with rapid evaluation of concussion using an AI analysis platform, enabling early detection of concussion risk and suggesting appropriate treatment, thereby significantly reducing the health risks to users.

[0743] The processing flow will be explained below.

[0744] Step 1:

[0745] The device acquires information about head impacts from sensors installed in the Hemat band worn by the user, specifically, collecting data in real time from an accelerometer and gyroscope.

[0746] Step 2:

[0747] When an impact is detected, the device simultaneously activates the camera to capture video data of the head, recording footage from a few seconds before and after the impact.

[0748] Step 3:

[0749] The device preprocesses the acquired impact data by denoising, normalizing, and formatting it to make it suitable for analysis.

[0750] Step 4:

[0751] The device preprocesses the captured video data, extracting important frames, compressing them, and preparing them for transmission to the analysis platform.

[0752] Step 5:

[0753] The device encrypts and transmits the pre-processed impact data and video data to a server using a secure communication protocol.

[0754] Step 6:

[0755] The server receives the data sent from the device and temporarily stores it in a database, so that all the data necessary for analysis is gathered.

[0756] Step 7:

[0757] The server inputs the received data into an AI analysis platform, which uses an AI model to assess the risk of concussion, taking into account parameters such as the magnitude, direction, and duration of the impact.

[0758] Step 8:

[0759] The server calculates a concussion risk score based on the results of the AI ​​analysis platform. For example, if the risk score exceeds a certain threshold, it will be judged as a high risk.

[0760] Step 9:

[0761] The server generates appropriate treatment suggestions for the user based on the risk assessment results, such as creating a notification message recommending rest or visiting a hospital.

[0762] Step 10:

[0763] The server sends the generated notification message to the user's terminal. The notification is performed in real time, helping the user to respond quickly.

[0764] Step 11:

[0765] The user checks the notification from the device and acts according to the instructions, such as stopping play and resting, or going to the hospital for a medical examination if necessary.

[0766] Step 12:

[0767] The server stores user feedback and usage results in a database, which will be used for future analysis and to improve the AI ​​model.

[0768] Step 13:

[0769] The server uses the accumulated data to retrain the AI ​​model and improve its analysis accuracy, which will result in even more accurate risk assessments from the next time onwards.

[0770] Example 1

[0771] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0772] Concussions caused by impacts to the head can pose serious health risks if appropriate measures are not taken. However, conventional methods require users to detect the impact and determine the appropriate measures themselves, which often makes it difficult to respond quickly. In addition, there are limited means of assessing the risk of concussion, making it difficult to make accurate judgments. Therefore, there is a need for a system that can quickly and accurately assess the risk of concussion and suggest appropriate measures to users.

[0773] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0774] In this invention, the server includes means for acquiring head impact information using a sensor, means for acquiring head video data using a camera, means for preprocessing the acquired impact information and video data, means for transmitting the preprocessed data to an analysis platform and determining the possibility of concussion using a generative AI model, and means for suggesting appropriate measures to the user based on the determination results, thereby enabling rapid and accurate assessment of concussion risk and suggesting appropriate measures.

[0775] A "sensor" is a device that detects physical movement, such as an accelerometer or gyroscope.

[0776] A "camera" is a device that captures images or videos and is used to obtain video data of the head.

[0777] "Impact information" is data on physical movements and forces applied to the head obtained by sensors.

[0778] "Video data" refers to information about images and videos captured by a camera.

[0779] "Preprocessing" refers to the process of removing noise from acquired data and converting it into a format suitable for analysis.

[0780] "Analysis platform" refers to systems and software for analyzing data, including generative AI models.

[0781] A "generative AI model" is an algorithm that learns from large amounts of data and evaluates the risk of concussion from the input data.

[0782] "Concussion probability" refers to the probability or risk of a concussion occurring as a result of an impact.

[0783] "Appropriate Actions" are suggested actions or treatment instructions for the user based on their risk of concussion.

[0784] A "user device" is a device such as a smartphone or tablet that allows a user to receive notifications.

[0785] The "judgment result" is the result of the concussion risk assessment analyzed by the generative AI model.

[0786] System Overview

[0787] The system of the present invention detects impacts to the head, assesses the possibility of a concussion, and suggests appropriate measures to the user, thereby reducing the health risks associated with concussions. This system is primarily composed of a sensor, a camera, a data preprocessing module, an AI analysis platform, and a notification module.

[0788] System configuration

[0789] Sensors and Cameras

[0790] The device uses sensors in the hematological band and other devices to capture information about the impact on the user's head, including an accelerometer and gyroscope, which collect data on the physical movement and force of the head, and a camera to capture video data of the impact.

[0791] Data Preprocessing Module

[0792] The device preprocesses the acquired impact information and video data. Specifically, it removes noise, normalizes the data, and converts it into a format suitable for analysis. It also extracts the necessary frames from the video data.

[0793] Data analysis

[0794] The server receives the pre-processed data and passes it to a generative AI model, which is trained on a large amount of data in advance and analyzes the impact and video data to calculate a concussion risk score, taking into account parameters such as the magnitude, direction, and duration of the impact.

[0795] Proposal of appropriate measures

[0796] The server generates a notification message suggesting appropriate measures based on the concussion risk score calculated by the AI ​​model and sends it to the user device. For example, if the server determines that the risk of a concussion is high, it sends a message saying, "Warning! A strong impact to the head has been detected. Stop playing immediately and rest. We strongly recommend that you seek medical attention."

[0797] Data accumulation and machine learning

[0798] The server continuously accumulates user feedback and newly collected data and stores it in a database, which continuously retrains the generative AI model and improves its accuracy. Through this feedback loop, the accuracy of concussion risk assessment is further improved.

[0799] Specific processing examples of the system

[0800] Example 1: Application during a rugby match

[0801] Suppose a user is tackled during a rugby match. At this time, the device receives large acceleration data from the sensor in the Hematband and detects the impact. The device also simultaneously receives video data of the user's head.

[0802] The pre-processing module normalizes and removes noise from the data before sending it to the server, which receives it and uses a generative AI model to assess the risk of a concussion. For example, if the server determines there is an 80% chance of a concussion, it sends the following instructions to the user's smartphone:

[0803] "Warning! A severe head impact has been detected. Stop playing immediately and rest. Medical attention is strongly recommended."

[0804] The user checks the notification and follows the instructions to stop playing, rest, and seek medical attention.

[0805] Example 2: Falls in daily life

[0806] A similar process is applied when a user falls and hits their head in everyday life. The device's sensors and camera detect the impact and capture video data. The preprocessed data is sent to a server, where the risk of concussion is assessed.

[0807] If the server determines that the user is at high risk of concussion, it will send a notification to the user's device suggesting appropriate measures. The content of the notification will vary depending on the circumstances of the fall, but will generally recommend resting and seeking medical attention.

[0808] In this way, the present invention provides a system that combines data collection by sensors and cameras with rapid assessment of concussion using generative AI models to enable early detection of concussion risk and suggest appropriate treatment, thereby significantly reducing the health risks to users.

[0809] Examples of prompt statements

[0810] "Please explain the procedure for the system that assesses the risk of concussion when tackled during a rugby match."

[0811] "Please explain in detail how this system will assess the risk of concussion and suggest appropriate measures to the user when they fall and hit their head in daily life."

[0812] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0813] Step 1: Collect data

[0814] The device uses sensors and a camera to collect information about the impact to the head and video data. Specifically, the accelerometer and gyroscope collect impact information, and the camera collects video data.

[0815] Input: Impact to the user's head

[0816] Output: Impact data (acceleration, direction), video data

[0817] Specific example of operation: When a user is tackled during sports, the acceleration sensor installed in the Hematband measures a large acceleration and the camera records the moment.

[0818] Step 2: Preprocessing the data

[0819] The device preprocesses the collected raw data, specifically removing noise and normalizing the data. For video data, it extracts the necessary frames and converts them into a format suitable for analysis.

[0820] Input: Impact data, video data

[0821] Output: Preprocessed data

[0822] Specific example of operation: The device removes noise from accelerometer data and cuts unnecessary frames from video data to extract important moments.

[0823] Step 3: Analyze the data

[0824] The server receives the pre-processed data and passes it to a generative AI model, which analyzes the impact and video data to calculate a concussion risk score, taking into account parameters such as impact magnitude, direction, and duration.

[0825] Input: Preprocessed data

[0826] Output: Concussion risk score

[0827] Specific example of operation: The server receives preprocessed data sent from the device and uses the generative AI model to determine that the risk of concussion is 80%.

[0828] Step 4: Propose appropriate action

[0829] The server generates and transmits a notification message to the user device suggesting appropriate treatment based on the concussion risk score.

[0830] Input: Concussion Risk Score

[0831] Output: Notification message

[0832] Specific example of operation: If the server determines that there is a high risk of concussion, it will send a message to the user's smartphone stating, "Warning! A strong impact to the head has been detected. Stop playing immediately and rest. We strongly recommend that you seek medical attention."

[0833] Step 5: Data accumulation and machine learning

[0834] The server accumulates user feedback and newly collected data and stores it in a database. Machine learning algorithms are used to continuously retrain the generative AI model to improve its accuracy.

[0835] Input: User feedback, collected data

[0836] Output: Updated generative AI model

[0837] Specific example of operation: When a user enters the results of a medical examination at a hospital into the app, the server stores the data in a database and uses it to retrain the AI ​​model.

[0838] (Application example 1)

[0839] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0840] Head impacts to workers during factory work can lead to serious accidents and health risks. Currently, there is a lack of systems that can take prompt and appropriate measures when a head impact occurs. In particular, it is difficult to ensure worker safety unless appropriate measures and risk assessments can be quickly carried out after an impact. This can lead to work interruptions, reduced productivity, and even damage to the worker's health. Therefore, there is a strong demand for a system that can immediately detect head impacts during factory work and take appropriate measures.

[0841] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0842] In this invention, the server includes means for acquiring head impact information using a sensor, means for acquiring head video data using a camera, means for preprocessing the acquired impact information and video data, means for transmitting data to personal devices used by workers, and means for monitoring the head safety of workers in a factory environment. This makes it possible to immediately detect head impacts during work, quickly assess the risk, and propose appropriate measures.

[0843] "Sensor" refers to a device for acquiring information about impacts to the head, and includes an acceleration sensor and a gyroscope.

[0844] A "camera" is a device for acquiring image data of the head.

[0845] "Preprocessing" refers to the process of removing noise from the acquired impact information and video data and converting the data into a format suitable for analysis.

[0846] The "analysis platform" is a system equipped with an AI model that receives preprocessed data and performs impact risk assessment.

[0847] "Impact information" is data on the impact on the head obtained by the sensor.

[0848] "Video data" is video information of the head captured by a camera.

[0849] A "user terminal" is a personal terminal used by a worker, and includes a smartphone or tablet.

[0850] "Appropriate measures" are actions and precautions suggested to the user depending on the situation after the impact.

[0851] The "means for monitoring worker head safety in a factory environment" is a system that immediately detects and analyzes any impact to the head of a worker in a factory, and suggests appropriate countermeasures.

[0852] To implement this invention, it is necessary to build a system including the following components: The system is mainly composed of a sensor, a camera, a data preprocessing module, an AI analysis platform, and a notification module.

[0853] 1. Equipped with sensors and cameras

[0854] The sensors will be installed in the smart helmets worn by the workers, including accelerometers and gyroscopes to capture information about head impacts, and a camera will also be installed in the smart helmets to capture video data at the time of impact.

[0855] 2. Data Preprocessing

[0856] The device (smartphone or tablet) receives the impact information and video data sent from the helmet. This data undergoes preprocessing such as noise removal and normalization. The necessary frames from the video data are also extracted and converted into a format suitable for analysis.

[0857] 3. Sending data to the server

[0858] The preprocessed data is sent from the device to a server, which receives it and analyzes it using an AI analysis platform.

[0859] 4. Data Analysis

[0860] The AI ​​analysis platform on the server uses the pre-processed data to perform a risk assessment of head impacts. This analysis uses a generative AI model that has been trained on a large amount of data in advance, taking into account specific parameters (such as the magnitude, direction, and duration of the impact).

[0861] 5. Notification and Proposal of Appropriate Action

[0862] The server then notifies the user of appropriate measures based on the risk score. For example, if the risk of a concussion is high, a message will be displayed saying, "Warning! A strong impact to the head has been detected. Stop work and check for safety."

[0863] Specific examples

[0864] When a factory worker receives an impact to the head, the smart helmet detects the impact and collects data. The data is preprocessed on the smartphone and sent to a server. The AI ​​analysis platform on the server analyzes the data and calculates a risk score. As a result, an appropriate action is determined and a notification is sent to the user's device.

[0865] Prompt Sentence Examples

[0866] "Design an application that detects when a factory worker has received a hard blow to the head and provides an immediate risk assessment."

[0867] By designing and implementing this system, it will be possible to quickly suggest appropriate measures to be taken when a factory worker suffers a blow to the head, thereby reducing health risks.

[0868] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0869] Step 1:

[0870] The sensors and cameras collect information about the impact on the worker's head and video data. Specifically, the acceleration sensor and gyroscope collect data on the impact to the head, and the camera captures the video at that time. This provides the input impact data and video data.

[0871] Step 2:

[0872] The device preprocesses the acquired impact information and video data. Specifically, it removes noise from the data, normalizes it, and extracts the necessary frames from the video data and converts them into a format suitable for analysis. This process results in clean, analyzable data being output.

[0873] Step 3:

[0874] The device sends the preprocessed data to a server. Specifically, the data is sent in real time using Wi-Fi or cellular communication. Here, the preprocessed impact data and video data are input and then sent to the server.

[0875] Step 4:

[0876] The server then analyzes the received data using an AI analysis platform. Specifically, it uses a generative AI model to integrate the impact data and video data and calculate a risk score. In this step, the data is passed as input to the AI ​​model, and a concussion risk score is obtained as output.

[0877] Step 5:

[0878] The server determines the appropriate action based on the risk score and sends a notification to the user's device. Specifically, if the risk score is high, it generates a message saying, "Warning! A strong impact to the head has been detected. Stop work and check for safety." and sends it to the user's device. This allows the worker to take immediate action.

[0879] Step 6:

[0880] The user checks the notification on the device and acts according to the instructions. Specifically, they stop their work, check for safety, and contact a medical institution if necessary. This allows for prompt and appropriate treatment.

[0881] This series of processes makes it possible to take prompt and appropriate measures when a worker receives an impact to the head.

[0882] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0883] System Overview

[0884] The system of the present invention detects impacts to the head, assesses the possibility of a concussion, and suggests appropriate measures taking into account the user's emotions. The system mainly consists of a sensor, a camera, a data preprocessing module, an AI analysis platform, an emotion engine, and a notification module.

[0885] System configuration

[0886] 1. Sensors and cameras

[0887] The device uses sensors on the hemat band and other devices to acquire information about the impact on the user's head, including an accelerometer and gyroscope, and a camera to capture video data of the impact.

[0888] 2. Data Preprocessing Module

[0889] The device preprocesses the collected raw data, including denoising impact information and normalising the data, and also extracts the required frames from the video data and converts them into a format suitable for analysis.

[0890] 3. Data Analysis

[0891] The server receives the pre-processed data and temporarily stores it in a database. The data is then input into an AI analysis platform, where an AI model is used to assess the risk of concussion, taking into account parameters such as the magnitude, direction, and duration of the impact.

[0892] 4. Operation of the Emotion Engine

[0893] The server analyzes the user's video and audio data and uses an emotion engine to assess the user's emotional state, thereby understanding how a possible concussion is affecting the user's emotions.

[0894] 5. Proposal of appropriate measures

[0895] The server generates a notification message suggesting appropriate actions to the user based on the results of the concussion risk assessment and emotion engine, and the notification is worded in a way that takes into account the user's current emotional state.

[0896] For example, if a user is feeling anxious, the following thoughtful message may be sent:

[0897] "Warning! A strong head impact has been detected. Do not worry, stop playing immediately and rest. Medical examination is strongly recommended."

[0898] 6. Data accumulation and machine learning

[0899] The server stores user feedback and usage results in a database, which is used for future analysis and to improve the AI ​​model. Emotion data is also stored, and machine learning algorithms are used to continuously retrain the emotion engine and AI model.

[0900] Specific processing examples of the system

[0901] Example 1: Application during a rugby match

[0902] Suppose a user is tackled during a rugby match. At this time, the device receives large acceleration data from the sensor mounted on the Hematband to detect the impact. At the same time, the device also receives video data of the user's head.

[0903] The pre-processing module normalizes and removes noise from the data before sending it to the server, where the AI ​​analysis platform evaluates the risk of concussion. Meanwhile, the emotion engine also analyzes the user's video data and evaluates their emotional state.

[0904] For example, if the AI ​​analysis platform assesses the risk of concussion at 80% and the emotion engine determines that the user is feeling anxious, the server will send a notification like the one below.

[0905] "Warning! A strong head impact has been detected. Do not worry, stop playing immediately and rest. Medical examination is strongly recommended."

[0906] The user checks the notification and follows the instructions to stop playing, rest, and seek medical attention.

[0907] Example 2: Falls in daily life

[0908] A similar process is applied when a user falls and hits their head in everyday life. The device's sensors and camera detect the impact and capture video data. The preprocessed data is sent to a server, where the risk of concussion is assessed.

[0909] As a result, if the risk of concussion is determined to be high and the emotion engine assesses that the user is surprised, the server will send a notification like this:

[0910] "Caution! A severe impact to the head has been detected. Please do not be afraid, but first stay calm and rest. We also recommend that you seek medical attention at a hospital as soon as possible."

[0911] In this way, the present invention provides a system that realizes early detection of concussion risk and proposes appropriate treatment by combining data collection using sensors and cameras, rapid evaluation of concussion using an AI analysis platform, and proposal of appropriate treatment taking into account the user's emotional state using an emotion engine, thereby significantly reducing the health risks to the user.

[0912] The processing flow will be explained below.

[0913] Step 1:

[0914] The device collects real-time information about the impact on the user's head from sensors installed in the Hematband, specifically, data collected from an accelerometer and gyroscope.

[0915] Step 2:

[0916] The moment an impact is detected, the device activates the camera and captures the user's video data, including a few seconds of footage before and after the impact.

[0917] Step 3:

[0918] The device preprocesses the captured impact data and video data: for impact data, noise removal, normalization, and format conversion are performed, and for video data, important frames are extracted and compressed.

[0919] Step 4:

[0920] The device encrypts and transmits the pre-processed data to the server using a secure communication protocol.

[0921] Step 5:

[0922] The server receives the data sent from the device and temporarily stores it in a database, so that all the data necessary for analysis is gathered.

[0923] Step 6:

[0924] The server inputs the received data into an AI analysis platform, which uses an AI model to assess concussion risk, taking into account parameters such as the magnitude, direction and duration of the impact.

[0925] Step 7:

[0926] The server calculates a risk score based on the concussion risk assessment results. For example, if the score exceeds a certain threshold, it is determined to be high risk.

[0927] Step 8:

[0928] The server analyzes the user's voice data and facial expressions from the captured video data and uses an emotion engine to evaluate the user's emotional state, thereby determining whether the user is feeling anxious, surprised, panicked, or other emotions.

[0929] Step 9:

[0930] The server combines the concussion risk assessment with the emotion assessment to generate a notification message suggesting appropriate actions for the user. For example, if the user is feeling anxious, the server will generate a message like this: "Warning! A strong head impact has been detected. Do not worry, stop playing immediately and rest. Medical examination is strongly recommended."

[0931] Step 10:

[0932] The server then sends the generated notification message to the user's terminal. The notification is sent in real time, allowing the user to respond promptly.

[0933] Step 11:

[0934] The user checks the notification from the device and acts according to the instructions, such as stopping play and resting, or going to the hospital for a checkup if necessary.

[0935] Step 12:

[0936] The server stores user feedback and usage results in a database, which will be used for future analysis and to improve the AI ​​model.

[0937] Step 13:

[0938] The server uses the accumulated data to retrain the AI ​​model and emotion engine to improve analysis accuracy, resulting in even more accurate risk and emotion assessments in future.

[0939] Example 2

[0940] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0941] In today's world, the risk of sustaining a strong impact to the head is increasing in sports and daily life, making early detection of concussion and appropriate treatment necessary. However, current technology is insufficient in assessing the risk of concussion or proposing appropriate treatment that takes into account the user's emotional state, and a system to ensure user safety is needed.

[0942] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0943] In this invention, the server includes means for acquiring head impact information using a sensor, means for acquiring head video data using a camera, means for preprocessing the acquired impact information and video data, means for transmitting the preprocessed data to an analysis platform and determining the possibility of a concussion, means for analyzing the user's video data and audio data and evaluating their emotional state, and means for proposing appropriate treatment for the user based on the determination result and emotional evaluation. This makes it possible to quickly and accurately assess the risk of concussion and propose appropriate treatment taking into account the user's emotional state.

[0944] The "sensor" is a device that includes an acceleration sensor, a gyroscope, etc., and acquires information about the impact on the user's head.

[0945] The "camera" is an image capturing device for acquiring image data of the head.

[0946] "Preprocessing" refers to the process of removing noise and normalizing the acquired raw data, converting it into a format suitable for analysis.

[0947] The "analysis platform" is a system that includes machine learning and AI technology to assess concussion risk based on collected data.

[0948] "Determining the likelihood of a concussion" means analyzing impact data to assess the risk of concussion and predict the degree of risk.

[0949] "Evaluating the emotional state" means analyzing the user's video and audio data to infer their emotions at that time.

[0950] "Suggest appropriate action" means informing the user of actions or steps to take based on an assessment of their concussion risk and emotional state.

[0951] "Impact information" is data obtained from an acceleration sensor, gyroscope, etc., that indicates the force applied to the user's head and changes in that force.

[0952] "Video data" refers to data relating to an image of the user's head and its surroundings, captured using a camera.

[0953] MODE FOR CARRYING OUT THE INVENTION

[0954] This system detects impacts to the head during sports and daily life, assesses the possibility of a concussion, and suggests appropriate treatment taking into account the user's emotional state. The system is composed of a sensor, a camera, a data preprocessing module, an analysis platform, an emotion engine, and a notification module.

[0955] System configuration

[0956] Each module functions as follows:

[0957] 1. Sensors and cameras

[0958] The device uses accelerometers and gyroscopes installed in the hemat band and other devices to obtain information about impacts to the user's head. For example, when a player is tackled during a rugby match, the device's sensors record data such as the magnitude, direction, and duration of the impact. The device also uses a camera to obtain video data of the impact.

[0959] 2. Data Preprocessing

[0960] The device preprocesses the acquired impact information and video data. This preprocessing includes noise removal and normalization. For example, noise contained in acceleration data is removed and normalization is performed to maintain data integrity. Furthermore, important frames of the video data are extracted and converted into a format that is easy for the analysis platform to process.

[0961] 3. Concussion risk assessment

[0962] The server receives the preprocessed data and temporarily stores it in a database. It then uses a deep learning model built with TensorFlow and PyTorch to assess concussion risk. Parameters such as the magnitude, direction, and duration of the impact are used for the assessment. For example, if the strength of the impact exceeds a certain threshold, it is deemed to be at high risk.

[0963] 4. Emotional assessment

[0964] The server analyzes the user's video and audio data, and the emotion engine uses OpenCV and TensorFlow to evaluate the user's emotional state. Specifically, it analyzes the user's facial expressions and tone of voice and classifies the emotion as "anxiety" or "surprise."

[0965] 5. Notification Message Generation

[0966] The server generates a notification message suggesting appropriate measures based on the concussion risk assessment result and the emotional state. For example, if the concussion risk is high and the emotional assessment is "anxious," the server generates a notification saying, "Warning! A strong impact to the head has been detected. Do not worry, but stop playing immediately and rest. A medical examination is strongly recommended."

[0967] 6. Data accumulation and machine learning

[0968] The server accumulates user feedback and usage results in a database, which is used to continuously retrain the analysis platform and emotion engine, improving the system's accuracy and user experience.

[0969] Prompt Sentence Examples

[0970] "Please explain how your system can assess the risk of a concussion if the user experiences a severe impact and suggest appropriate responses based on their emotional state."

[0971] In this way, the present invention is a system that utilizes sensors and AI technology to quickly and accurately assess the risk of concussion and propose appropriate treatment taking into account the user's emotional state, thereby significantly reducing the user's health risks.

[0972] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0973] Step 1:

[0974] Obtaining impact information

[0975] The device uses an accelerometer and gyroscope mounted on a hemat band or other device worn by the user to obtain information about the impact on the user's head. For example, when a player is tackled during a rugby match, the device's sensors record data on the magnitude, direction, and duration of the impact. The input data is the raw data obtained from the sensor, and the output data is the obtained impact data (acceleration, direction, and duration).

[0976] Step 2:

[0977] Acquiring video data

[0978] The device uses a camera to capture video data at the time of impact. For example, it records video of the user's head at the moment of impact. The input data is raw video data captured by the camera, and the output data is the captured video frames.

[0979] Step 3:

[0980] Data Preprocessing

[0981] The device preprocesses the acquired impact information and video data. Specifically, it removes noise from the acceleration data and normalizes it. It also extracts important frames from the video data and converts them into a format that is easy for the analysis platform to process. The input data is raw impact data and raw video data, and the output data is preprocessed impact data and video data.

[0982] Step 4:

[0983] Concussion risk assessment using AI analysis platform

[0984] The server receives the preprocessed data and temporarily stores it in a database. The preprocessed data is then input into a deep learning model built with TensorFlow and PyTorch to assess concussion risk. Specific processing involves inputting impact data (magnitude, direction, and duration) into the model and calculating a concussion risk score. The input data are the preprocessed impact data and video data, and the output data is a concussion risk score.

[0985] Step 5:

[0986] Emotion evaluation by emotion engine

[0987] The server analyzes the user's video and audio data and evaluates the user's emotional state using an emotion engine. Specific processing involves analyzing the user's facial expressions and tone of voice using OpenCV and TensorFlow, and evaluating the emotion as "anxiety" or "surprise." The input data are preprocessed video and audio data, and the output data are the emotion evaluation results.

[0988] Step 6:

[0989] Generate notification messages

[0990] The server generates a notification message suggesting appropriate measures based on the concussion risk assessment result and the emotion assessment result. Specifically, if the concussion risk is high and the user's emotion assessment is "anxious," a notification is generated stating, "Warning! A strong impact to the head has been detected. Do not worry, but stop playing immediately and rest. We strongly recommend that you seek medical advice." The input data are the concussion risk score and the emotion assessment result, and the output data is the generated notification message.

[0991] Step 7:

[0992] Data accumulation and machine learning

[0993] The server stores user feedback and usage results in a database, and the analysis platform and emotion engine are continuously retrained. Specific processing involves learning to improve the accuracy of the model based on past evaluation results and feedback stored in the database. The input data is user feedback and usage results data, and the output data is the retrained AI model and emotion engine.

[0994] (Application example 2)

[0995] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0996] In high-risk environments such as factories, there is a need to quickly and accurately assess the risk of concussion when a worker suffers a head impact and propose appropriate measures. Furthermore, there is a need for messages that take into account the emotional state of the worker who received the impact, but conventional systems have not been able to do this properly. Therefore, a method is needed to ensure worker safety efficiently and effectively.

[0997] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for acquiring head impact information using a sensor, means for acquiring head video data using a camera, means for preprocessing the acquired impact information and video data, means for transmitting the preprocessed data to an analysis platform and determining the possibility of a concussion, means for proposing appropriate measures to the user based on the determination result, means for evaluating the user's emotional state using an emotion analysis module, and means for generating a notification message based on the emotional state. This makes it possible to quickly and accurately assess the risk of a concussion when a worker suffers a head impact and to propose appropriate measures that take the user's emotional state into consideration.

[0998] A "sensor" is a device that detects physical environmental information and outputs it as a signal.

[0999] A "camera" is a device that captures light and records it as a still image or video.

[1000] "Impact information" is data such as the magnitude and direction of a physical impact obtained through sensors.

[1001] "Video data" refers to still image and video data captured through a camera.

[1002] "Preprocessing" refers to the process of converting the acquired raw data into a format suitable for analysis.

[1003] An "analysis platform" is a system that processes data and outputs analysis results.

[1004] A "concussion" is a temporary brain dysfunction caused by a blow to the head.

[1005] The "emotion analysis module" is software for analyzing and evaluating a user's emotional state from video and audio data.

[1006] "Proposal of action" refers to providing specific instructions or advice to the user to encourage action based on the analysis results.

[1007] A "notification message" is a text or voice message that conveys important information or instructions to the user.

[1008] The system of the present invention quickly and accurately assesses the risk of concussion when a worker suffers a head impact in a high-risk environment such as a factory, and proposes appropriate measures. The system's components include a sensor, a camera, a data preprocessing module, an AI analysis platform, an emotion analysis module, and a notification module.

[1009] Hardware and Software

[1010] Hardware: Smart helmet, smartphone, head-mounted display (HMD), accelerometer, gyroscope, camera

[1011] Software: Python, TensorFlow (AI analysis platform), OpenCV (video analysis), Amazon Rekognition (sentiment analysis)

[1012] System Operation

[1013] 1. Data Collection and Preprocessing

[1014] The device collects data from the accelerometer and gyroscope installed in the smart helmet, and also captures video data from the camera at the time of impact. This raw data is first preprocessed on the device, which includes data normalization and noise removal.

[1015] 2. Concussion risk assessment using AI analysis

[1016] The pre-processed data is sent to a server, which then inputs it into an AI analysis platform to assess concussion risk. The AI ​​analysis platform uses TensorFlow and takes into account parameters such as the magnitude, direction, and duration of the impact.

[1017] 3. Emotion analysis

[1018] The server uses Amazon Rekognition to assess the worker's emotional state from the video data, which also assesses the impact of a possible concussion on the worker's emotions.

[1019] 4. Notification and Proposed Actions

[1020] Based on the results of the concussion risk assessment and emotion analysis, the notification module generates appropriate treatment suggestions for the worker. These suggestions include wording that takes into account the worker's current emotional state. For example, if the worker is feeling anxious, a message such as "Warning! A strong head impact has been detected. Please remain calm, take a break, and seek medical attention immediately" will be sent.

[1021] Specific examples

[1022] For example, if a worker hits his head while working at height in a factory, the smart helmet's sensors will detect large acceleration data and the camera will record the incident. The preprocessed data is sent to a server, where the AI ​​analysis platform will assess the risk of concussion at 80%. Meanwhile, if emotion analysis determines that the worker is feeling anxious, a notification message like the one below will be generated.

[1023] "Warning! A severe head impact has been detected. Please remain calm, you need to rest and seek medical attention immediately."

[1024] Prompt Sentence Examples

[1025] "Assess the worker's emotional state from camera footage, assess concussion risk from impact data, and generate appropriate notification messages."

[1026] The system is expected to significantly improve worker safety and provide more personalized care based on emotional state.

[1027] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1028] Step 1:

[1029] The device uses the accelerometer and gyroscope installed in the smart helmet to obtain information about the impact on the head. Specifically, it reads signals from the sensors to obtain the magnitude and direction of the impact. It also uses a camera to obtain video data at the time of impact. This data is temporarily stored within the device. The inputs are the sensor signals and camera images, and the outputs are raw impact data and video data.

[1030] Step 2:

[1031] The terminal preprocesses the acquired raw data. Specifically, it removes noise from the impact data and normalizes the data. It also extracts necessary frames from the video data and converts them into a format suitable for analysis. The inputs are raw impact data and video data, and the outputs are normalized impact data and preprocessed video data.

[1032] Step 3:

[1033] The terminal sends the preprocessed data to the server, which receives and temporarily stores it. The input is the preprocessed impact data and video data, and the output is the data stored on the server.

[1034] Step 4:

[1035] The server inputs the preprocessed impact data into an AI analysis platform to assess concussion risk. Specifically, TensorFlow is used to input data into an AI model, which calculates a concussion risk score based on parameters such as the magnitude, direction, and duration of the impact. The input is the preprocessed impact data, and the output is a concussion risk score.

[1036] Step 5:

[1037] The server uses Amazon Rekognition to analyze the worker's emotional state from the video data. Specifically, the video data is input into an emotion analysis module, and the emotional state is evaluated from facial expressions and voice. The input is preprocessed video data, and the output is the evaluation result of the worker's emotional state.

[1038] Step 6:

[1039] The server generates a notification message based on the concussion risk score and the emotional state assessment result. Specifically, the notification module references the risk score and the emotional assessment and creates a message including appropriate treatment suggestions. The input is the concussion risk score and the emotional state assessment result, and the output is the notification message sent to the user.

[1040] Step 7:

[1041] The terminal displays the notification message sent from the server and prompts the user to take appropriate action. Specifically, the message is displayed on a display device (smartphone or head-mounted display) and instructs the user on how to respond. The input is the notification message sent from the server, and the output is the user's recognition and corresponding action.

[1042] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1043] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1044] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1045] [Fourth embodiment]

[1046] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1047] 7, a 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.

[1048] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1049] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1050] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1051] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1052] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1053] The control object 443 includes a display device, LEDs in the eyes, and motors for driving 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 emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1054] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1055] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[1056] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1057] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1058] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1059] System Overview

[1060] The system of the present invention detects impacts to the head, assesses the possibility of a concussion, and suggests appropriate measures to the user, thereby reducing the health risks associated with a concussion. The system is primarily composed of a sensor, a camera, a data preprocessing module, an AI analysis platform, and a notification module.

[1061] System configuration

[1062] 1. Sensors and cameras

[1063] The device uses sensors on the hemat band and other devices to acquire information about the impact on the user's head, including an accelerometer and gyroscope, and a camera to capture video data of the impact.

[1064] 2. Data Preprocessing Module

[1065] The device preprocesses the collected raw data, including denoising impact information and normalising the data, and also extracts the required frames from the video data and converts them into a format suitable for analysis.

[1066] 3. Data Analysis

[1067] The server receives the pre-processed data and passes it to the AI ​​analysis platform. The AI ​​model, which has been pre-trained with a large amount of data, analyzes the impact and video data to calculate a concussion risk score. This analysis takes into account certain parameters (such as the magnitude, direction, and duration of the impact).

[1068] 4. Proposal of appropriate measures

[1069] The server then sends a notification message to the user's device suggesting appropriate measures depending on the likelihood of a concussion. For example, if the risk of a concussion is high, the following message will be displayed:

[1070] "Warning! A strong head impact has been detected. Stop playing immediately and rest. Medical attention is strongly recommended."

[1071] 5. Data accumulation and machine learning

[1072] The server collects user feedback and newly collected data and stores it in a database. Machine learning algorithms are used to continuously retrain the AI ​​model to improve its accuracy.

[1073] Specific processing examples of the system

[1074] Example 1: Application during a rugby match

[1075] Suppose a user is tackled during a rugby match. At this time, the device receives large acceleration data from the sensor in the Hematband and detects the impact. The device also simultaneously receives video data of the user's head.

[1076] The pre-processing module normalizes the data and removes noise before sending it to the server. The server receives the data, and the AI ​​analysis platform evaluates the risk of concussion. For example, if the server determines that there is an 80% chance of a concussion, it sends the next instruction to the user's smartphone.

[1077] "Warning! A severe head impact has been detected. Stop playing immediately and rest. Medical attention is strongly recommended."

[1078] The user checks the notification and follows the instructions to stop playing, rest, and seek medical attention.

[1079] Example 2: Falls in daily life

[1080] A similar process is applied when a user falls and hits their head in everyday life. The device's sensors and camera detect the impact and capture video data. The preprocessed data is sent to a server, where the risk of concussion is assessed.

[1081] If the server determines that the user is at high risk of concussion, it will send a notification to the user's device suggesting appropriate measures. The content of the notification will vary depending on the circumstances of the fall, but will generally recommend resting and seeking medical attention.

[1082] In this way, the present invention provides a system that combines data collection by sensors and cameras with rapid evaluation of concussion using an AI analysis platform, enabling early detection of concussion risk and suggesting appropriate treatment, thereby significantly reducing the health risks to users.

[1083] The processing flow will be explained below.

[1084] Step 1:

[1085] The device acquires information about head impacts from sensors installed in the Hemat band worn by the user, specifically, collecting data in real time from an accelerometer and gyroscope.

[1086] Step 2:

[1087] When an impact is detected, the device simultaneously activates the camera to capture video data of the head, recording footage from a few seconds before and after the impact.

[1088] Step 3:

[1089] The device preprocesses the acquired impact data by denoising, normalizing, and formatting it to make it suitable for analysis.

[1090] Step 4:

[1091] The device preprocesses the captured video data, extracting important frames, compressing them, and preparing them for transmission to the analysis platform.

[1092] Step 5:

[1093] The device encrypts and transmits the pre-processed impact data and video data to a server using a secure communication protocol.

[1094] Step 6:

[1095] The server receives the data sent from the device and temporarily stores it in a database, so that all the data necessary for analysis is gathered.

[1096] Step 7:

[1097] The server inputs the received data into an AI analysis platform, which uses an AI model to assess the risk of concussion, taking into account parameters such as the magnitude, direction, and duration of the impact.

[1098] Step 8:

[1099] The server calculates a concussion risk score based on the results of the AI ​​analysis platform. For example, if the risk score exceeds a certain threshold, it will be judged as a high risk.

[1100] Step 9:

[1101] The server generates appropriate treatment suggestions for the user based on the risk assessment results, such as creating a notification message recommending rest or visiting a hospital.

[1102] Step 10:

[1103] The server sends the generated notification message to the user's terminal. The notification is performed in real time, helping the user to respond quickly.

[1104] Step 11:

[1105] The user checks the notification from the device and acts according to the instructions, such as stopping play and resting, or going to the hospital for a medical examination if necessary.

[1106] Step 12:

[1107] The server stores user feedback and usage results in a database, which will be used for future analysis and to improve the AI ​​model.

[1108] Step 13:

[1109] The server uses the accumulated data to retrain the AI ​​model and improve its analysis accuracy, which will result in even more accurate risk assessments from the next time onwards.

[1110] Example 1

[1111] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1112] Concussions caused by impacts to the head can pose serious health risks if appropriate measures are not taken. However, conventional methods require users to detect the impact and determine the appropriate measures themselves, which often makes it difficult to respond quickly. In addition, there are limited means of assessing the risk of concussion, making it difficult to make accurate judgments. Therefore, there is a need for a system that can quickly and accurately assess the risk of concussion and suggest appropriate measures to users.

[1113] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1114] In this invention, the server includes means for acquiring head impact information using a sensor, means for acquiring head video data using a camera, means for preprocessing the acquired impact information and video data, means for transmitting the preprocessed data to an analysis platform and determining the possibility of concussion using a generative AI model, and means for suggesting appropriate measures to the user based on the determination results, thereby enabling rapid and accurate assessment of concussion risk and suggesting appropriate measures.

[1115] A "sensor" is a device that detects physical movement, such as an accelerometer or gyroscope.

[1116] A "camera" is a device that captures images or videos and is used to obtain video data of the head.

[1117] "Impact information" is data on physical movements and forces applied to the head obtained by sensors.

[1118] "Video data" refers to information about images and videos captured by a camera.

[1119] "Preprocessing" refers to the process of removing noise from acquired data and converting it into a format suitable for analysis.

[1120] "Analysis platform" refers to systems and software for analyzing data, including generative AI models.

[1121] A "generative AI model" is an algorithm that learns from large amounts of data and evaluates the risk of concussion from the input data.

[1122] "Concussion probability" refers to the probability or risk of a concussion occurring as a result of an impact.

[1123] "Appropriate Actions" are suggested actions or treatment instructions for the user based on their risk of concussion.

[1124] A "user device" is a device such as a smartphone or tablet that allows a user to receive notifications.

[1125] The "judgment result" is the result of the concussion risk assessment analyzed by the generative AI model.

[1126] System Overview

[1127] The system of the present invention detects impacts to the head, assesses the possibility of a concussion, and suggests appropriate measures to the user, thereby reducing the health risks associated with concussions. This system is primarily composed of a sensor, a camera, a data preprocessing module, an AI analysis platform, and a notification module.

[1128] System configuration

[1129] Sensors and Cameras

[1130] The device uses sensors in the hematological band and other devices to capture information about the impact on the user's head, including an accelerometer and gyroscope, which collect data on the physical movement and force of the head, and a camera to capture video data of the impact.

[1131] Data Preprocessing Module

[1132] The device preprocesses the acquired impact information and video data. Specifically, it removes noise, normalizes the data, and converts it into a format suitable for analysis. It also extracts the necessary frames from the video data.

[1133] Data analysis

[1134] The server receives the pre-processed data and passes it to a generative AI model, which is trained on a large amount of data in advance and analyzes the impact and video data to calculate a concussion risk score, taking into account parameters such as the magnitude, direction, and duration of the impact.

[1135] Proposal of appropriate measures

[1136] The server generates a notification message suggesting appropriate measures based on the concussion risk score calculated by the AI ​​model and sends it to the user device. For example, if the server determines that the risk of a concussion is high, it sends a message saying, "Warning! A strong impact to the head has been detected. Stop playing immediately and rest. We strongly recommend that you seek medical attention."

[1137] Data accumulation and machine learning

[1138] The server continuously accumulates user feedback and newly collected data and stores it in a database, which continuously retrains the generative AI model and improves its accuracy. Through this feedback loop, the accuracy of concussion risk assessment is further improved.

[1139] Specific processing examples of the system

[1140] Example 1: Application during a rugby match

[1141] Suppose a user is tackled during a rugby match. At this time, the device receives large acceleration data from the sensor in the Hematband and detects the impact. The device also simultaneously receives video data of the user's head.

[1142] The pre-processing module normalizes and removes noise from the data before sending it to the server, which receives it and uses a generative AI model to assess the risk of a concussion. For example, if the server determines there is an 80% chance of a concussion, it sends the following instructions to the user's smartphone:

[1143] "Warning! A severe head impact has been detected. Stop playing immediately and rest. Medical attention is strongly recommended."

[1144] The user checks the notification and follows the instructions to stop playing, rest, and seek medical attention.

[1145] Example 2: Falls in daily life

[1146] A similar process is applied when a user falls and hits their head in everyday life. The device's sensors and camera detect the impact and capture video data. The preprocessed data is sent to a server, where the risk of concussion is assessed.

[1147] If the server determines that the user is at high risk of concussion, it will send a notification to the user's device suggesting appropriate measures. The content of the notification will vary depending on the circumstances of the fall, but will generally recommend resting and seeking medical attention.

[1148] In this way, the present invention provides a system that combines data collection by sensors and cameras with rapid assessment of concussion using generative AI models to enable early detection of concussion risk and suggest appropriate treatment, thereby significantly reducing the health risks to users.

[1149] Examples of prompt statements

[1150] "Please explain the procedure for the system that assesses the risk of concussion when tackled during a rugby match."

[1151] "Please explain in detail how this system will assess the risk of concussion and suggest appropriate measures to the user when they fall and hit their head in daily life."

[1152] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1153] Step 1: Collect data

[1154] The device uses sensors and a camera to collect information about the impact to the head and video data. Specifically, the accelerometer and gyroscope collect impact information, and the camera collects video data.

[1155] Input: Impact to the user's head

[1156] Output: Impact data (acceleration, direction), video data

[1157] Specific example of operation: When a user is tackled during sports, the acceleration sensor installed in the Hematband measures a large acceleration and the camera records the moment.

[1158] Step 2: Preprocessing the data

[1159] The device preprocesses the collected raw data, specifically removing noise and normalizing the data. For video data, it extracts the necessary frames and converts them into a format suitable for analysis.

[1160] Input: Impact data, video data

[1161] Output: Preprocessed data

[1162] Specific example of operation: The device removes noise from accelerometer data and cuts unnecessary frames from video data to extract important moments.

[1163] Step 3: Analyze the data

[1164] The server receives the pre-processed data and passes it to a generative AI model, which analyzes the impact and video data to calculate a concussion risk score, taking into account parameters such as impact magnitude, direction, and duration.

[1165] Input: Preprocessed data

[1166] Output: Concussion risk score

[1167] Specific example of operation: The server receives preprocessed data sent from the device and uses the generative AI model to determine that the risk of concussion is 80%.

[1168] Step 4: Propose appropriate action

[1169] The server generates and transmits a notification message to the user device suggesting appropriate treatment based on the concussion risk score.

[1170] Input: Concussion Risk Score

[1171] Output: Notification message

[1172] Specific example of operation: If the server determines that there is a high risk of concussion, it will send a message to the user's smartphone stating, "Warning! A strong impact to the head has been detected. Stop playing immediately and rest. We strongly recommend that you seek medical attention."

[1173] Step 5: Data accumulation and machine learning

[1174] The server accumulates user feedback and newly collected data and stores it in a database. Machine learning algorithms are used to continuously retrain the generative AI model to improve its accuracy.

[1175] Input: User feedback, collected data

[1176] Output: Updated generative AI model

[1177] Specific example of operation: When a user enters the results of a medical examination at a hospital into the app, the server stores the data in a database and uses it to retrain the AI ​​model.

[1178] (Application example 1)

[1179] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1180] Head impacts to workers during factory work can lead to serious accidents and health risks. Currently, there is a lack of systems that can take prompt and appropriate measures when a head impact occurs. In particular, it is difficult to ensure worker safety unless appropriate measures and risk assessments can be quickly carried out after an impact. This can lead to work interruptions, reduced productivity, and even damage to the worker's health. Therefore, there is a strong demand for a system that can immediately detect head impacts during factory work and take appropriate measures.

[1181] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1182] In this invention, the server includes means for acquiring head impact information using a sensor, means for acquiring head video data using a camera, means for preprocessing the acquired impact information and video data, means for transmitting data to personal devices used by workers, and means for monitoring the head safety of workers in a factory environment. This makes it possible to immediately detect head impacts during work, quickly assess the risk, and propose appropriate measures.

[1183] "Sensor" refers to a device for acquiring information about impacts to the head, and includes an acceleration sensor and a gyroscope.

[1184] A "camera" is a device for acquiring image data of the head.

[1185] "Preprocessing" refers to the process of removing noise from the acquired impact information and video data and converting the data into a format suitable for analysis.

[1186] The "analysis platform" is a system equipped with an AI model that receives preprocessed data and performs impact risk assessment.

[1187] "Impact information" is data on the impact on the head obtained by the sensor.

[1188] "Video data" is video information of the head captured by a camera.

[1189] A "user terminal" is a personal terminal used by a worker, and includes a smartphone or tablet.

[1190] "Appropriate measures" are actions and precautions suggested to the user depending on the situation after the impact.

[1191] The "means for monitoring worker head safety in a factory environment" is a system that immediately detects and analyzes any impact to the head of a worker in a factory, and suggests appropriate countermeasures.

[1192] To implement this invention, it is necessary to build a system including the following components: The system is mainly composed of a sensor, a camera, a data preprocessing module, an AI analysis platform, and a notification module.

[1193] 1. Equipped with sensors and cameras

[1194] The sensors will be installed in the smart helmets worn by the workers, including accelerometers and gyroscopes to capture information about head impacts, and a camera will also be installed in the smart helmets to capture video data at the time of impact.

[1195] 2. Data Preprocessing

[1196] The device (smartphone or tablet) receives the impact information and video data sent from the helmet. This data undergoes preprocessing such as noise removal and normalization. The necessary frames from the video data are also extracted and converted into a format suitable for analysis.

[1197] 3. Sending data to the server

[1198] The preprocessed data is sent from the device to a server, which receives it and analyzes it using an AI analysis platform.

[1199] 4. Data Analysis

[1200] The AI ​​analysis platform on the server uses the pre-processed data to perform a risk assessment of head impacts. This analysis uses a generative AI model that has been trained on a large amount of data in advance, taking into account specific parameters (such as the magnitude, direction, and duration of the impact).

[1201] 5. Notification and Proposal of Appropriate Action

[1202] The server then notifies the user of appropriate measures based on the risk score. For example, if the risk of a concussion is high, a message will be displayed saying, "Warning! A strong impact to the head has been detected. Stop work and check for safety."

[1203] Specific examples

[1204] When a factory worker receives an impact to the head, the smart helmet detects the impact and collects data. The data is preprocessed on the smartphone and sent to a server. The AI ​​analysis platform on the server analyzes the data and calculates a risk score. As a result, an appropriate action is determined and a notification is sent to the user's device.

[1205] Prompt Sentence Examples

[1206] "Design an application that detects when a factory worker has received a hard blow to the head and provides an immediate risk assessment."

[1207] By designing and implementing this system, it will be possible to quickly suggest appropriate measures to be taken when a factory worker suffers a blow to the head, thereby reducing health risks.

[1208] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1209] Step 1:

[1210] The sensors and cameras collect information about the impact on the worker's head and video data. Specifically, the acceleration sensor and gyroscope collect data on the impact to the head, and the camera captures the video at that time. This provides the input impact data and video data.

[1211] Step 2:

[1212] The device preprocesses the acquired impact information and video data. Specifically, it removes noise from the data, normalizes it, and extracts the necessary frames from the video data and converts them into a format suitable for analysis. This process results in clean, analyzable data being output.

[1213] Step 3:

[1214] The device sends the preprocessed data to a server. Specifically, the data is sent in real time using Wi-Fi or cellular communication. Here, the preprocessed impact data and video data are input and then sent to the server.

[1215] Step 4:

[1216] The server then analyzes the received data using an AI analysis platform. Specifically, it uses a generative AI model to integrate the impact data and video data and calculate a risk score. In this step, the data is passed as input to the AI ​​model, and a concussion risk score is obtained as output.

[1217] Step 5:

[1218] The server determines the appropriate action based on the risk score and sends a notification to the user's device. Specifically, if the risk score is high, it generates a message saying, "Warning! A strong impact to the head has been detected. Stop work and check for safety." and sends it to the user's device. This allows the worker to take immediate action.

[1219] Step 6:

[1220] The user checks the notification on the device and acts according to the instructions. Specifically, they stop their work, check for safety, and contact a medical institution if necessary. This allows for prompt and appropriate treatment.

[1221] This series of processes makes it possible to take prompt and appropriate measures when a worker receives an impact to the head.

[1222] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1223] System Overview

[1224] The system of the present invention detects impacts to the head, assesses the possibility of a concussion, and suggests appropriate measures taking into account the user's emotions. The system mainly consists of a sensor, a camera, a data preprocessing module, an AI analysis platform, an emotion engine, and a notification module.

[1225] System configuration

[1226] 1. Sensors and cameras

[1227] The device uses sensors on the hemat band and other devices to acquire information about the impact on the user's head, including an accelerometer and gyroscope, and a camera to capture video data of the impact.

[1228] 2. Data Preprocessing Module

[1229] The device preprocesses the collected raw data, including denoising impact information and normalising the data, and also extracts the required frames from the video data and converts them into a format suitable for analysis.

[1230] 3. Data Analysis

[1231] The server receives the pre-processed data and temporarily stores it in a database. The data is then input into an AI analysis platform, where an AI model is used to assess the risk of concussion, taking into account parameters such as the magnitude, direction, and duration of the impact.

[1232] 4. Operation of the Emotion Engine

[1233] The server analyzes the user's video and audio data and uses an emotion engine to assess the user's emotional state, thereby understanding how a possible concussion is affecting the user's emotions.

[1234] 5. Proposal of appropriate measures

[1235] The server generates a notification message suggesting appropriate actions to the user based on the results of the concussion risk assessment and emotion engine, and the notification is worded in a way that takes into account the user's current emotional state.

[1236] For example, if a user is feeling anxious, the following thoughtful message may be sent:

[1237] "Warning! A strong head impact has been detected. Do not worry, stop playing immediately and rest. Medical examination is strongly recommended."

[1238] 6. Data accumulation and machine learning

[1239] The server stores user feedback and usage results in a database, which is used for future analysis and to improve the AI ​​model. Emotion data is also stored, and machine learning algorithms are used to continuously retrain the emotion engine and AI model.

[1240] Specific processing examples of the system

[1241] Example 1: Application during a rugby match

[1242] Suppose a user is tackled during a rugby match. At this time, the device receives large acceleration data from the sensor mounted on the Hematband to detect the impact. At the same time, the device also receives video data of the user's head.

[1243] The pre-processing module normalizes and removes noise from the data before sending it to the server, where the AI ​​analysis platform evaluates the risk of concussion. Meanwhile, the emotion engine also analyzes the user's video data and evaluates their emotional state.

[1244] For example, if the AI ​​analysis platform assesses the risk of concussion at 80% and the emotion engine determines that the user is feeling anxious, the server will send a notification like the one below.

[1245] "Warning! A strong head impact has been detected. Do not worry, stop playing immediately and rest. Medical examination is strongly recommended."

[1246] The user checks the notification and follows the instructions to stop playing, rest, and seek medical attention.

[1247] Example 2: Falls in daily life

[1248] A similar process is applied when a user falls and hits their head in everyday life. The device's sensors and camera detect the impact and capture video data. The preprocessed data is sent to a server, where the risk of concussion is assessed.

[1249] As a result, if the risk of concussion is determined to be high and the emotion engine assesses that the user is surprised, the server will send a notification like this:

[1250] "Caution! A severe impact to the head has been detected. Please do not be afraid, but first stay calm and rest. We also recommend that you seek medical attention at a hospital as soon as possible."

[1251] In this way, the present invention provides a system that realizes early detection of concussion risk and proposes appropriate treatment by combining data collection using sensors and cameras, rapid evaluation of concussion using an AI analysis platform, and proposal of appropriate treatment taking into account the user's emotional state using an emotion engine, thereby significantly reducing the health risks to the user.

[1252] The processing flow will be explained below.

[1253] Step 1:

[1254] The device collects real-time information about the impact on the user's head from sensors installed in the Hematband, specifically, data collected from an accelerometer and gyroscope.

[1255] Step 2:

[1256] The moment an impact is detected, the device activates the camera and captures the user's video data, including a few seconds of footage before and after the impact.

[1257] Step 3:

[1258] The device preprocesses the captured impact data and video data: for impact data, noise removal, normalization, and format conversion are performed, and for video data, important frames are extracted and compressed.

[1259] Step 4:

[1260] The device encrypts and transmits the pre-processed data to the server using a secure communication protocol.

[1261] Step 5:

[1262] The server receives the data sent from the device and temporarily stores it in a database, so that all the data necessary for analysis is gathered.

[1263] Step 6:

[1264] The server inputs the received data into an AI analysis platform, which uses an AI model to assess concussion risk, taking into account parameters such as the magnitude, direction and duration of the impact.

[1265] Step 7:

[1266] The server calculates a risk score based on the concussion risk assessment results. For example, if the score exceeds a certain threshold, it is determined to be high risk.

[1267] Step 8:

[1268] The server analyzes the user's voice data and facial expressions from the captured video data and uses an emotion engine to evaluate the user's emotional state, thereby determining whether the user is feeling anxious, surprised, panicked, or other emotions.

[1269] Step 9:

[1270] The server combines the concussion risk assessment with the emotion assessment to generate a notification message suggesting appropriate actions for the user. For example, if the user is feeling anxious, the server will generate a message like this: "Warning! A strong head impact has been detected. Do not worry, stop playing immediately and rest. Medical examination is strongly recommended."

[1271] Step 10:

[1272] The server then sends the generated notification message to the user's terminal. The notification is sent in real time, allowing the user to respond promptly.

[1273] Step 11:

[1274] The user checks the notification from the device and acts according to the instructions, such as stopping play and resting, or going to the hospital for a checkup if necessary.

[1275] Step 12:

[1276] The server stores user feedback and usage results in a database, which will be used for future analysis and to improve the AI ​​model.

[1277] Step 13:

[1278] The server uses the accumulated data to retrain the AI ​​model and emotion engine to improve analysis accuracy, resulting in even more accurate risk and emotion assessments in future.

[1279] Example 2

[1280] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1281] In today's world, the risk of sustaining a strong impact to the head is increasing in sports and daily life, making early detection of concussion and appropriate treatment necessary. However, current technology is insufficient in assessing the risk of concussion or proposing appropriate treatment that takes into account the user's emotional state, and a system to ensure user safety is needed.

[1282] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1283] In this invention, the server includes means for acquiring head impact information using a sensor, means for acquiring head video data using a camera, means for preprocessing the acquired impact information and video data, means for transmitting the preprocessed data to an analysis platform and determining the possibility of a concussion, means for analyzing the user's video data and audio data and evaluating their emotional state, and means for proposing appropriate treatment for the user based on the determination result and emotional evaluation. This makes it possible to quickly and accurately assess the risk of concussion and propose appropriate treatment taking into account the user's emotional state.

[1284] The "sensor" is a device that includes an acceleration sensor, a gyroscope, etc., and acquires information about the impact on the user's head.

[1285] The "camera" is an image capturing device for acquiring image data of the head.

[1286] "Preprocessing" refers to the process of removing noise and normalizing the acquired raw data, converting it into a format suitable for analysis.

[1287] The "analysis platform" is a system that includes machine learning and AI technology to assess concussion risk based on collected data.

[1288] "Determining the likelihood of a concussion" means analyzing impact data to assess the risk of concussion and predict the degree of risk.

[1289] "Evaluating the emotional state" means analyzing the user's video and audio data to infer their emotions at that time.

[1290] "Suggest appropriate action" means informing the user of actions or steps to take based on an assessment of their concussion risk and emotional state.

[1291] "Impact information" is data obtained from an acceleration sensor, gyroscope, etc., that indicates the force applied to the user's head and changes in that force.

[1292] "Video data" refers to data relating to an image of the user's head and its surroundings, captured using a camera.

[1293] MODE FOR CARRYING OUT THE INVENTION

[1294] This system detects impacts to the head during sports and daily life, assesses the possibility of a concussion, and suggests appropriate treatment taking into account the user's emotional state. The system is composed of a sensor, a camera, a data preprocessing module, an analysis platform, an emotion engine, and a notification module.

[1295] System configuration

[1296] Each module functions as follows:

[1297] 1. Sensors and cameras

[1298] The device uses accelerometers and gyroscopes installed in the hemat band and other devices to obtain information about impacts to the user's head. For example, when a player is tackled during a rugby match, the device's sensors record data such as the magnitude, direction, and duration of the impact. The device also uses a camera to obtain video data of the impact.

[1299] 2. Data Preprocessing

[1300] The device preprocesses the acquired impact information and video data. This preprocessing includes noise removal and normalization. For example, noise contained in acceleration data is removed and normalization is performed to maintain data integrity. Furthermore, important frames of the video data are extracted and converted into a format that is easy for the analysis platform to process.

[1301] 3. Concussion risk assessment

[1302] The server receives the preprocessed data and temporarily stores it in a database. It then uses a deep learning model built with TensorFlow and PyTorch to assess concussion risk. Parameters such as the magnitude, direction, and duration of the impact are used for the assessment. For example, if the strength of the impact exceeds a certain threshold, it is deemed to be at high risk.

[1303] 4. Emotional assessment

[1304] The server analyzes the user's video and audio data, and the emotion engine uses OpenCV and TensorFlow to evaluate the user's emotional state. Specifically, it analyzes the user's facial expressions and tone of voice and classifies the emotion as "anxiety" or "surprise."

[1305] 5. Notification Message Generation

[1306] The server generates a notification message suggesting appropriate measures based on the concussion risk assessment result and the emotional state. For example, if the concussion risk is high and the emotional assessment is "anxious," the server generates a notification saying, "Warning! A strong impact to the head has been detected. Do not worry, but stop playing immediately and rest. A medical examination is strongly recommended."

[1307] 6. Data accumulation and machine learning

[1308] The server accumulates user feedback and usage results in a database, which is used to continuously retrain the analysis platform and emotion engine, improving the system's accuracy and user experience.

[1309] Prompt Sentence Examples

[1310] "Please explain how your system can assess the risk of a concussion if the user experiences a severe impact and suggest appropriate responses based on their emotional state."

[1311] In this way, the present invention is a system that utilizes sensors and AI technology to quickly and accurately assess the risk of concussion and propose appropriate treatment taking into account the user's emotional state, thereby significantly reducing the user's health risks.

[1312] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1313] Step 1:

[1314] Obtaining impact information

[1315] The device uses an accelerometer and gyroscope mounted on a hemat band or other device worn by the user to obtain information about the impact on the user's head. For example, when a player is tackled during a rugby match, the device's sensors record data on the magnitude, direction, and duration of the impact. The input data is the raw data obtained from the sensor, and the output data is the obtained impact data (acceleration, direction, and duration).

[1316] Step 2:

[1317] Acquiring video data

[1318] The device uses a camera to capture video data at the time of impact. For example, it records video of the user's head at the moment of impact. The input data is raw video data captured by the camera, and the output data is the captured video frames.

[1319] Step 3:

[1320] Data Preprocessing

[1321] The device preprocesses the acquired impact information and video data. Specifically, it removes noise from the acceleration data and normalizes it. It also extracts important frames from the video data and converts them into a format that is easy for the analysis platform to process. The input data is raw impact data and raw video data, and the output data is preprocessed impact data and video data.

[1322] Step 4:

[1323] Concussion risk assessment using AI analysis platform

[1324] The server receives the preprocessed data and temporarily stores it in a database. The preprocessed data is then input into a deep learning model built with TensorFlow and PyTorch to assess concussion risk. Specific processing involves inputting impact data (magnitude, direction, and duration) into the model and calculating a concussion risk score. The input data are the preprocessed impact data and video data, and the output data is a concussion risk score.

[1325] Step 5:

[1326] Emotion evaluation by emotion engine

[1327] The server analyzes the user's video and audio data and evaluates the user's emotional state using an emotion engine. Specific processing involves analyzing the user's facial expressions and tone of voice using OpenCV and TensorFlow, and evaluating the emotion as "anxiety" or "surprise." The input data are preprocessed video and audio data, and the output data are the emotion evaluation results.

[1328] Step 6:

[1329] Generate notification messages

[1330] The server generates a notification message suggesting appropriate measures based on the concussion risk assessment result and the emotion assessment result. Specifically, if the concussion risk is high and the user's emotion assessment is "anxious," a notification is generated stating, "Warning! A strong impact to the head has been detected. Do not worry, but stop playing immediately and rest. We strongly recommend that you seek medical advice." The input data are the concussion risk score and the emotion assessment result, and the output data is the generated notification message.

[1331] Step 7:

[1332] Data accumulation and machine learning

[1333] The server stores user feedback and usage results in a database, and the analysis platform and emotion engine are continuously retrained. Specific processing involves learning to improve the accuracy of the model based on past evaluation results and feedback stored in the database. The input data is user feedback and usage results data, and the output data is the retrained AI model and emotion engine.

[1334] (Application example 2)

[1335] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1336] In high-risk environments such as factories, there is a need to quickly and accurately assess the risk of concussion when a worker suffers a head impact and propose appropriate measures. Furthermore, there is a need for messages that take into account the emotional state of the worker who received the impact, but conventional systems have not been able to do this properly. Therefore, a method is needed to ensure worker safety efficiently and effectively.

[1337] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for acquiring head impact information using a sensor, means for acquiring head video data using a camera, means for preprocessing the acquired impact information and video data, means for transmitting the preprocessed data to an analysis platform and determining the possibility of a concussion, means for proposing appropriate measures to the user based on the determination result, means for evaluating the user's emotional state using an emotion analysis module, and means for generating a notification message based on the emotional state. This makes it possible to quickly and accurately assess the risk of a concussion when a worker suffers a head impact and to propose appropriate measures that take the user's emotional state into consideration.

[1338] A "sensor" is a device that detects physical environmental information and outputs it as a signal.

[1339] A "camera" is a device that captures light and records it as a still image or video.

[1340] "Impact information" is data such as the magnitude and direction of a physical impact obtained through sensors.

[1341] "Video data" refers to still image and video data captured through a camera.

[1342] "Preprocessing" refers to the process of converting the acquired raw data into a format suitable for analysis.

[1343] An "analysis platform" is a system that processes data and outputs analysis results.

[1344] A "concussion" is a temporary brain dysfunction caused by a blow to the head.

[1345] The "emotion analysis module" is software for analyzing and evaluating a user's emotional state from video and audio data.

[1346] "Proposal of action" refers to providing specific instructions or advice to the user to encourage action based on the analysis results.

[1347] A "notification message" is a text or voice message that conveys important information or instructions to the user.

[1348] The system of the present invention quickly and accurately assesses the risk of concussion when a worker suffers a head impact in a high-risk environment such as a factory, and proposes appropriate measures. The system's components include a sensor, a camera, a data preprocessing module, an AI analysis platform, an emotion analysis module, and a notification module.

[1349] Hardware and Software

[1350] Hardware: Smart helmet, smartphone, head-mounted display (HMD), accelerometer, gyroscope, camera

[1351] Software: Python, TensorFlow (AI analysis platform), OpenCV (video analysis), Amazon Rekognition (sentiment analysis)

[1352] System Operation

[1353] 1. Data Collection and Preprocessing

[1354] The device collects data from the accelerometer and gyroscope installed in the smart helmet, and also captures video data from the camera at the time of impact. This raw data is first preprocessed on the device, which includes data normalization and noise removal.

[1355] 2. Concussion risk assessment using AI analysis

[1356] The pre-processed data is sent to a server, which then inputs it into an AI analysis platform to assess concussion risk. The AI ​​analysis platform uses TensorFlow and takes into account parameters such as the magnitude, direction, and duration of the impact.

[1357] 3. Emotion analysis

[1358] The server uses Amazon Rekognition to assess the worker's emotional state from the video data, which also assesses the impact of a possible concussion on the worker's emotions.

[1359] 4. Notification and Proposed Actions

[1360] Based on the results of the concussion risk assessment and emotion analysis, the notification module generates appropriate treatment suggestions for the worker. These suggestions include wording that takes into account the worker's current emotional state. For example, if the worker is feeling anxious, a message such as "Warning! A strong head impact has been detected. Please remain calm, take a break, and seek medical attention immediately" will be sent.

[1361] Specific examples

[1362] For example, if a worker hits his head while working at height in a factory, the smart helmet's sensors will detect large acceleration data and the camera will record the incident. The preprocessed data is sent to a server, where the AI ​​analysis platform will assess the risk of concussion at 80%. Meanwhile, if emotion analysis determines that the worker is feeling anxious, a notification message like the one below will be generated.

[1363] "Warning! A severe head impact has been detected. Please remain calm, you need to rest and seek medical attention immediately."

[1364] Prompt Sentence Examples

[1365] "Assess the worker's emotional state from camera footage, assess concussion risk from impact data, and generate appropriate notification messages."

[1366] The system is expected to significantly improve worker safety and provide more personalized care based on emotional state.

[1367] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1368] Step 1:

[1369] The device uses the accelerometer and gyroscope installed in the smart helmet to obtain information about the impact on the head. Specifically, it reads signals from the sensors to obtain the magnitude and direction of the impact. It also uses a camera to obtain video data at the time of impact. This data is temporarily stored within the device. The inputs are the sensor signals and camera images, and the outputs are raw impact data and video data.

[1370] Step 2:

[1371] The terminal preprocesses the acquired raw data. Specifically, it removes noise from the impact data and normalizes the data. It also extracts necessary frames from the video data and converts them into a format suitable for analysis. The inputs are raw impact data and video data, and the outputs are normalized impact data and preprocessed video data.

[1372] Step 3:

[1373] The terminal sends the preprocessed data to the server, which receives and temporarily stores it. The input is the preprocessed impact data and video data, and the output is the data stored on the server.

[1374] Step 4:

[1375] The server inputs the preprocessed impact data into an AI analysis platform to assess concussion risk. Specifically, TensorFlow is used to input data into an AI model, which calculates a concussion risk score based on parameters such as the magnitude, direction, and duration of the impact. The input is the preprocessed impact data, and the output is a concussion risk score.

[1376] Step 5:

[1377] The server uses Amazon Rekognition to analyze the worker's emotional state from the video data. Specifically, the video data is input into an emotion analysis module, and the emotional state is evaluated from facial expressions and voice. The input is preprocessed video data, and the output is the evaluation result of the worker's emotional state.

[1378] Step 6:

[1379] The server generates a notification message based on the concussion risk score and the emotional state assessment result. Specifically, the notification module references the risk score and the emotional assessment and creates a message including appropriate treatment suggestions. The input is the concussion risk score and the emotional state assessment result, and the output is the notification message sent to the user.

[1380] Step 7:

[1381] The terminal displays the notification message sent from the server and prompts the user to take appropriate action. Specifically, the message is displayed on a display device (smartphone or head-mounted display) and instructs the user on how to respond. The input is the notification message sent from the server, and the output is the user's recognition and corresponding action.

[1382] 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 control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1383] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1384] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1385] The emotion identification model 59 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 an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1386] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1387] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1388] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1389] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1390] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs 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 a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1391] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1392] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1393] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1394] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1395] 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.

[1396] It is not necessary to store all 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 all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1397] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1398] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with 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). Also, the hardware resource that executes the specific processing may be a single processor.

[1399] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1400] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1401] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1402] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1403] The following is further disclosed regarding the above embodiment.

[1404] (Claim 1)

[1405] a means for acquiring information about an impact to the head using a sensor;

[1406] A means for acquiring image data of the head using a camera;

[1407] means for pre-processing the acquired impact information and video data;

[1408] means for transmitting the preprocessed data to an analytical platform to determine the likelihood of a concussion;

[1409] means for suggesting appropriate measures to the user based on the determination result;

[1410] A system including:

[1411] (Claim 2)

[1412] 10. The system of claim 1, further comprising means for integrating the impact information and video data and inputting them into an AI model to calculate a concussion risk score.

[1413] (Claim 3)

[1414] 10. The system according to claim 1, further comprising means for notifying a user terminal of the determination result and an appropriate treatment suggestion.

[1415] (Claim 4)

[1416] 10. The system of claim 1, further comprising means for accumulating historical data and updating the AI ​​model through machine learning.

[1417] "Example 1"

[1418] (Claim 1)

[1419] a means for acquiring information about an impact to the head using a sensor;

[1420] A means for acquiring image data of the head using a camera;

[1421] means for pre-processing the acquired impact information and video data;

[1422] A means of sending pre-processed data to an analytical platform and using a generative AI model to determine the likelihood of a concussion;

[1423] means for suggesting appropriate measures to the user based on the determination result;

[1424] A system including:

[1425] (Claim 2)

[1426] 10. The system of claim 1, further comprising means for integrating the impact information and video data and inputting them into a generative AI model to calculate a concussion risk score.

[1427] (Claim 3)

[1428] 10. The system of claim 1, further comprising means for notifying a user device of the determination result and appropriate treatment suggestions.

[1429] "Application Example 1"

[1430] (Claim 1)

[1431] a means for acquiring information about an impact to the head using a sensor;

[1432] A means for acquiring image data of the head using a camera;

[1433] means for pre-processing the acquired impact information and video data;

[1434] means for transmitting the preprocessed data to an analytical platform to determine the likelihood of a concussion;

[1435] means for suggesting appropriate measures to the user based on the determination result;

[1436] a means for transmitting data to a personal device used by the worker;

[1437] a means for monitoring worker head safety in a factory environment;

[1438] A system including:

[1439] (Claim 2)

[1440] 10. The system of claim 1, further comprising means for integrating the impact information and video data and inputting them into an AI model to calculate a concussion risk score.

[1441] (Claim 3)

[1442] 10. The system according to claim 1, further comprising means for notifying a user terminal of the determination result and an appropriate treatment suggestion.

[1443] "Example 2: Combining Emotion Engines"

[1444] (Claim 1)

[1445] a means for acquiring information about an impact to the head using a sensor;

[1446] A means for acquiring image data of the head using a camera;

[1447] means for pre-processing the acquired impact information and video data;

[1448] means for transmitting the preprocessed data to an analytical platform to determine the likelihood of a concussion;

[1449] means for analyzing video data and audio data of a user and assessing the user's emotional state;

[1450] means for suggesting appropriate actions to the user based on the determination result and the emotion evaluation;

[1451] A system including:

[1452] (Claim 2)

[1453] 10. The system of claim 1, further comprising means for integrating the impact information and video data and inputting them into an AI model to calculate a concussion risk score.

[1454] (Claim 3)

[1455] 10. The system according to claim 1, further comprising means for notifying a user terminal of the determination result and an appropriate treatment suggestion.

[1456] "Application example 2 when combining emotion engines"

[1457] (Claim 1)

[1458] a means for acquiring information about an impact to the head using a sensor;

[1459] A means for acquiring image data of the head using a camera;

[1460] means for pre-processing the acquired impact information and video data;

[1461] means for transmitting the preprocessed data to an analytical platform to determine the likelihood of a concussion;

[1462] means for suggesting appropriate measures to the user based on the determination result;

[1463] means for assessing the emotional state of the user using an emotion analysis module;

[1464] means for generating a notification message based on the emotional state;

[1465] A system including:

[1466] (Claim 2)

[1467] 10. The system of claim 1, further comprising means for integrating the impact information and video data and inputting them into an AI model to calculate a concussion risk score.

[1468] (Claim 3)

[1469] 10. The system according to claim 1, further comprising means for notifying a user terminal of the determination result and an appropriate treatment suggestion. [Explanation of symbols]

[1470] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a means for acquiring information about an impact to the head using a sensor; A means for acquiring image data of the head using a camera; means for pre-processing the acquired impact information and video data; means for transmitting the preprocessed data to an analytical platform to determine the likelihood of a concussion; means for suggesting appropriate measures to the user based on the determination result; A system including:

2. 2. The system of claim 1, further comprising means for integrating impact information and video data and inputting the combined data into an AI model to calculate a concussion risk score.

3. The system according to claim 1 , further comprising means for notifying a user terminal of the determination result and an appropriate treatment suggestion.

4. The system of claim 1 , further comprising means for accumulating historical data and updating the AI ​​model through machine learning.

Images