system

Abstract

The system according to this embodiment aims to enable callers to quickly and accurately provide appropriate first aid in emergency situations. [Solution] The system according to the embodiment comprises a reception unit, an analysis unit, an advice unit, and a monitoring unit. The reception unit receives information from the caller. The analysis unit analyzes the information received by the reception unit. The advice unit provides advice on first aid based on the information analyzed by the analysis unit. The monitoring unit monitors the results of the first aid advised by the advice unit.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, there is a problem that it is difficult for a reporter to quickly and accurately receive instructions for taking appropriate emergency measures in an emergency.

[0005] The system according to the embodiment aims to enable a reporter to quickly and accurately take appropriate emergency measures in an emergency.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a reception unit, an analysis unit, an advice unit, and a monitoring unit. The reception unit receives information from the caller. The analysis unit analyzes the information received by the reception unit. The advice unit provides advice on first aid based on the information analyzed by the analysis unit. The monitoring unit monitors the results of the first aid advised by the advice unit. [Effects of the Invention]

[0007] The system according to this embodiment allows callers to quickly and accurately perform appropriate first aid in an emergency. [Brief explanation of the drawing]

[0008] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Modes for carrying out the invention]

[0009] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0010] First, let's explain the terminology used in the following explanation.

[0011] In the following embodiments, the signed processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Furthermore, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), APU (Accelerated Processing Unit), or TPU (Tensor Processing Unit).

[0012] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0013] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0014] In the following embodiments, the labeled communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F controls communication between a plurality of computers. Examples of communication standards applied to the communication I / F include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B". That is, "A and / or B" means that it may be only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

[0016] [First Embodiment] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0017] As shown in FIG. 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. 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. Also, the database 24 and the communication I / F 26 are 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).

[0019] The smart device 14 comprises a computer 36, a receiving device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The receiving device 38, output device 40, and camera 42 are also connected to the bus 52.

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0023] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0024] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0025] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0026] In the smart device 14, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart device 14 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0027] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device (e.g., a generation server) may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device having the data generation model 58. The data processing device 12 may also be a server device or a terminal device owned by a user (e.g., a mobile phone, robot, home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example of form 1) An emergency medical instruction system according to an embodiment of the present invention is a system that uses a generating AI to issue instructions for emergency medical actions to callers. The emergency medical instruction system allows callers to communicate the patient's condition at the scene to the AI, which then advises on appropriate first aid. This system improves the current situation where appropriate medical care is not provided in emergencies due to a shortage of ambulances and doctors at night, and strengthens support for callers when they themselves perform emergency responses. For example, a caller communicates the patient's condition at the scene to the AI. At this time, the caller inputs detailed information about the patient's symptoms and condition. For example, information such as "the patient has lost consciousness" or "the patient's breathing is shallow" is input. This information is input to the generating AI. Next, the generating AI analyzes the input information. The generating AI understands the patient's symptoms and condition and advises on appropriate first aid. For example, it gives specific instructions such as "start cardiopulmonary resuscitation" or "secure the airway." This enables effective responses in emergencies even if the caller is not a medical professional. Furthermore, the generating AI monitors the results of the first aid performed by the caller and gives additional instructions as needed. For example, it gives instructions such as "continue cardiopulmonary resuscitation" or "if the patient's breathing recovers, keep them at rest." This will enable callers to take appropriate action continuously. This system will improve delays in initial response during emergencies and compensate for the shortage of personnel in medical settings. It will also improve the quality and efficiency of emergency medical care, improving the quality and speed of emergency responses. For example, it is expected that the time it takes for ambulances to arrive will be shortened, and more lives will be saved. This system is intended for use in emergency medical facilities nationwide, including medical institutions, emergency services, and public safety agencies. This will use technology to compensate for the overwhelming shortage of medical resources, enabling even non-medical personnel to take effective action in emergencies. For example, even in areas where there is a severe shortage of doctors at night, the quality of emergency medical care will be improved as callers can take appropriate first aid according to instructions generated by AI. In this way, the emergency medical instruction system can support callers in taking appropriate medical action in emergencies and improve the quality and efficiency of emergency medical care.

[0029] The emergency medical instruction system according to this embodiment comprises a reception unit, an analysis unit, an advice unit, and a monitoring unit. The reception unit receives information from callers. Information from callers includes, but is not limited to, voice calls, text messages, and images. The reception unit may, for example, use voice recognition technology to receive voice calls. The reception unit may also use natural language processing technology to receive text messages. Furthermore, the reception unit may also use image recognition technology to receive images. For example, the reception unit converts voice calls into text in real time and transmits it to the analysis unit. Text messages are transmitted to the analysis unit using natural language processing technology. Images are transmitted to the analysis unit using image recognition technology. The analysis unit analyzes the information received by the reception unit using generative AI. The analysis is performed based on, for example, data analysis methods and algorithms used, but is not limited to such examples. For example, the analysis unit uses generative AI to analyze the patient's symptoms and condition. The analysis unit can also use generative AI to understand the patient's symptoms and condition. The analysis unit can also use generative AI to classify the patient's symptoms and condition. For example, the analysis unit uses generative AI to classify the patient's symptoms and advise on appropriate first aid. The advice unit uses generative AI to advise on first aid based on the information analyzed by the analysis unit. First aid includes, but is not limited to, cardiopulmonary resuscitation (CPR) and hemostasis. For example, the advice unit uses generative AI to advise on CPR. The advice unit can also use generative AI to advise on hemostasis. The advice unit can also use generative AI to advise on airway management. For example, the advice unit uses generative AI to explain the steps of CPR in detail. For hemostasis, it uses generative AI to advise on specific steps. For airway management, it uses generative AI to advise on appropriate steps. The monitoring unit monitors the results of the first aid advised by the advice unit. Monitoring includes, but is not limited to, real-time monitoring and periodic checks. For example, the monitoring unit monitors heart rate and respiratory rate in real time.Furthermore, the monitoring unit can periodically check the patient's condition. The monitoring unit can also issue additional instructions as needed. For example, it may issue additional instructions if the heart rate is unstable, or if the respiratory rate does not return to normal. This allows the emergency medical instruction system according to the embodiment to assist callers in performing appropriate medical actions in emergencies, thereby improving the quality and efficiency of emergency medical care.

[0030] The reception department receives information from callers. This information may include, but is not limited to, voice calls, text messages, and images. For example, the reception department uses speech recognition technology to receive voice calls. Specifically, the speech recognition technology converts the caller's voice into text in real time and sends it to the analysis department. This speech recognition technology uses advanced algorithms to remove noise and background sounds and clearly recognize the caller's voice. The reception department can also use natural language processing technology to receive text messages. This technology analyzes the text messages sent by the caller, extracts important information, and sends it to the analysis department. This technology also has the ability to understand context and correct typos and omissions. Furthermore, the reception department can also use image recognition technology to receive images. This technology analyzes images sent by the caller and extracts information to identify the patient's condition and symptoms. For example, the image recognition technology evaluates the size of a wound and the degree of bleeding and sends it to the analysis department. This allows the reception department to efficiently receive diverse forms of information and quickly transmit it to the analysis department. Furthermore, the reception department provides a user interface to facilitate smooth interaction with callers. For example, in the case of voice calls, it can ask appropriate questions to the caller and extract necessary information. In the case of text messages, it can use an automatic reply function to confirm necessary information with the caller. This allows the reception department to accurately and quickly collect information from callers and transmit it to the analysis department, thereby maximizing the effectiveness of the emergency medical instruction system.

[0031] The analysis unit uses generative AI to analyze information received by the reception unit. The analysis is performed based on, for example, data analysis methods and algorithms used, but is not limited to these examples. Specifically, the generative AI analyzes text and text messages converted from voice calls to understand the patient's symptoms and condition. Using natural language processing technology, the generative AI extracts important keywords and phrases from the caller's words and evaluates the patient's condition. It also uses image recognition technology to analyze transmitted images and identify the patient's injuries and symptoms. For example, the generative AI evaluates the degree of bleeding and the depth of wounds from images to determine appropriate first aid. Furthermore, the generative AI can classify the patient's symptoms and condition. For example, it can classify the patient's symptoms into mild, moderate, and severe, and suggest appropriate first aid for each. This allows the analysis unit to quickly and accurately analyze information received from the reception unit and understand the patient's condition in real time. Additionally, the analysis unit can predict the patient's condition by utilizing past data and statistical information. For example, based on past case data, it can evaluate the likelihood of a specific symptom progressing and take appropriate measures early. Furthermore, the analysis unit can use anomaly detection algorithms to detect unusual patterns and abnormal data, enabling it to issue warnings early. This allows the analysis unit to not only grasp the situation in real time but also to handle long-term risk management and anomaly detection, thereby improving the reliability and safety of the emergency medical instruction system.

[0032] The advice unit uses a generating AI to provide first aid advice based on information analyzed by the analysis unit. First aid includes, but is not limited to, cardiopulmonary resuscitation (CPR) and hemostasis. Specifically, the generating AI proposes the most appropriate first aid based on the patient's condition information provided by the analysis unit. For example, if CPR is needed, the generating AI will explain the CPR procedure in detail and provide specific instructions to the caller. The generating AI will use voice guidance and text messages to explain in detail the rhythm and strength of chest compressions and the method of artificial respiration. If hemostasis is needed, the generating AI will propose an appropriate hemostasis method depending on the location of the bleeding. For example, it will explain in detail how to apply pressure to stop bleeding and how to use a tourniquet, and instruct the caller on the appropriate procedure. Furthermore, if airway management is needed, the generating AI will explain the airway management procedure in detail and provide specific instructions to the caller. For example, it will explain in detail the procedures for the head tilt-chin lift maneuver and the jaw lift maneuver, and instruct the caller on the appropriate procedure. This allows the advisory unit to use generative AI to provide callers with rapid and accurate first aid instructions, stabilizing the patient's condition. Furthermore, the advisory unit can collect feedback from callers and evaluate the effectiveness of first aid. For example, callers can report the results of first aid, and the generative AI can evaluate its effectiveness based on this information. This allows the advisory unit to continuously improve the accuracy and effectiveness of first aid, thereby enhancing the reliability and effectiveness of the emergency medical instruction system.

[0033] The monitoring unit monitors the results of first aid measures advised by the advisory unit. Monitoring includes, but is not limited to, real-time monitoring and periodic checks. Specifically, the monitoring unit uses sensors to monitor heart rate and respiratory rate in real time. These sensors are attached to the patient's body and continuously measure heart rate and respiratory rate, transmitting the data to the monitoring unit. The monitoring unit analyzes this data to understand the patient's condition in real time. The monitoring unit can also periodically check the patient's condition. For example, it can check the patient's level of consciousness, skin color, and body temperature at regular intervals and transmit this information to the analysis unit. Furthermore, the monitoring unit can issue additional instructions as needed. For example, if the heart rate is unstable, the monitoring unit will instruct additional first aid measures. If the respiratory rate does not return to normal, the monitoring unit will instruct additional airway management methods. This allows the monitoring unit to continuously monitor the patient's condition and respond quickly as needed. In addition, the monitoring unit can store patient condition data long-term for later analysis and evaluation. For example, based on patient condition data, the effectiveness of first aid can be evaluated, and areas for future improvement can be identified. Furthermore, the monitoring unit can use anomaly detection algorithms to detect unusual patterns or abnormal data, enabling early warnings. This allows the monitoring unit to not only grasp the situation in real time but also to handle long-term risk management and anomaly detection, thereby improving the reliability and safety of the emergency medical instruction system.

[0034] The reception desk can receive information about the patient's symptoms and condition entered by the caller. For example, the reception desk can receive information entered by the caller such as "the patient is unconscious." It can also receive information entered by the caller such as "the patient is breathing shallowly." It can also receive information entered by the caller such as "the patient is bleeding." By receiving information about the patient's symptoms and condition entered by the caller, the reception desk can obtain information to advise on appropriate first aid. The patient's symptoms and condition include, but are not limited to, fever, difficulty breathing, and bleeding. Some or all of the above processing in the reception desk may be performed using AI, for example, or not using AI. For example, the reception desk can input the information entered by the caller into a generating AI, and the generating AI can analyze the information.

[0035] The analysis unit can analyze a patient's symptoms and condition using generative AI. For example, the analysis unit can analyze a patient's symptoms using generative AI. The analysis unit can also analyze a patient's condition using generative AI. Furthermore, the analysis unit can classify a patient's symptoms and condition using generative AI. For example, the analysis unit can classify a patient's symptoms using generative AI and advise on appropriate first aid. In this way, the analysis unit can accurately analyze a patient's symptoms and condition by using generative AI. Generative AI includes, but is not limited to, natural language processing and image recognition. Some or all of the above-mentioned processes in the analysis unit are performed using generative AI. For example, the analysis unit can input information entered by the caller into the generative AI and have the generative AI analyze the information.

[0036] The advice unit can provide appropriate first aid advice using generative AI. For example, the advice unit can use generative AI to advise on cardiopulmonary resuscitation (CPR). It can also use generative AI to advise on methods of stopping bleeding. Furthermore, it can use generative AI to advise on methods of securing the airway. For example, the advice unit can use generative AI to explain the steps of CPR in detail. For methods of stopping bleeding, it will provide specific steps using generative AI. For methods of securing the airway, it will provide appropriate steps using generative AI. This allows for the rapid provision of appropriate first aid advice using generative AI. Generative AI includes, but is not limited to, natural language processing and image recognition. Some or all of the above-described processes in the advice unit are performed using generative AI. For example, the advice unit can input information entered by the caller into the generative AI, which can then provide first aid advice.

[0037] The monitoring unit can monitor the results of the first aid performed by the caller and issue additional instructions as needed. For example, if the caller performs cardiopulmonary resuscitation (CPR), the monitoring unit can monitor the heart rate and issue additional instructions as needed. The monitoring unit can also monitor the bleeding status and issue additional instructions if the caller attempts to stop bleeding. Furthermore, if the caller secures the airway, the monitoring unit can monitor the respiratory status and issue additional instructions as needed. For example, the monitoring unit may issue additional instructions if the heart rate is unstable or if the respiratory rate does not return to normal. This allows for continuous and appropriate responses by monitoring the results of first aid and issuing additional instructions as needed. Monitoring includes, but is not limited to, real-time monitoring and periodic checks. Some or all of the above-described processes in the monitoring unit may be performed using AI or not. For example, the monitoring unit can input the results of the first aid performed by the caller into a generating AI, which can then perform the monitoring.

[0038] The reception department can analyze the caller's past reporting history and select the optimal method for receiving information. For example, the reception department can suggest the optimal input method based on the content the caller has frequently reported in the past. The reception department can also prioritize displaying input methods for specific symptoms or conditions based on the caller's past reporting history. Furthermore, the reception department can analyze the caller's past reporting history and suggest input methods to be used during specific time periods. For example, the reception department can input the caller's past reporting history into an AI, which then selects the optimal method for receiving information. This allows for the selection of the optimal method for receiving information by analyzing the caller's past reporting history. The optimal method for receiving information includes, but is not limited to, prioritization and filtering. Some or all of the above-described processes in the reception department may be performed using AI or not. For example, the reception department can input the caller's past reporting history into a generating AI, which then selects the optimal method for receiving information.

[0039] The reception desk can automatically receive patient symptoms and conditions using voice input and image analysis. For example, when a caller describes a patient's symptoms verbally, the AI ​​analyzes the voice and converts it to text for reception. The reception desk can also automatically recognize symptoms when a caller takes a picture of the patient with a smartphone and the AI ​​performs image analysis. Furthermore, the reception desk can receive real-time information on the patient's condition when a caller records a video and the AI ​​performs video analysis. For example, the reception desk can analyze voice input using voice recognition software and convert it into text data. It can analyze images using image recognition algorithms to recognize symptoms. It can analyze videos using video analysis technology and receive real-time information on the patient's condition. This allows the reception desk to automatically receive patient symptoms and conditions using voice input and image analysis. Some or all of the above processes in the reception desk may be performed using AI or not. For example, the reception desk can input voice data or image data into a generating AI and have the generating AI perform the analysis.

[0040] The reception desk can prioritize receiving region-specific symptoms and conditions by considering the caller's geographical location. For example, if the caller is in a specific area, the reception desk will prioritize receiving information about diseases and symptoms prevalent in that area. The reception desk can also receive information considering local medical resources based on the caller's location. Furthermore, if the caller is in a disaster area, the reception desk can prioritize receiving information about disaster-specific symptoms and conditions. For example, the reception desk can input the caller's location information into an AI, which will then prioritize receiving region-specific symptoms and conditions. This allows for priority receiving of region-specific symptoms and conditions by considering the caller's geographical location. Geographical location information includes, but is not limited to, GPS data and location services. Some or all of the above processing in the reception desk may be performed using AI or not. For example, the reception desk can input the caller's location information into a generating AI, which will then prioritize receiving region-specific symptoms and conditions.

[0041] The reception department can analyze the whistleblower's social media activity and receive relevant information. For example, the reception department can analyze the whistleblower's social media posts and receive information about their health status. The reception department can also receive relevant symptoms or conditions based on location information shared by the whistleblower on social media. Furthermore, the reception department can analyze the whistleblower's social media activity history and receive information about their past health status. For example, the reception department can input social media posts into an AI and receive information about their health status through the AI. It can receive relevant symptoms or conditions based on location information. It can analyze activity history and receive information about their past health status. In this way, relevant information can be received by analyzing the whistleblower's social media activity. Social media activity includes, but is not limited to, analyzing post content or followers. Some or all of the above processing in the reception department may be performed using AI or not. For example, the reception department can input social media data into a generating AI and receive relevant information through the generating AI.

[0042] The analysis unit can analyze a patient's symptoms and condition in real time and prioritize outputting the analysis results according to their urgency. For example, the analysis unit can analyze a patient's heart rate and respiratory rate in real time and prioritize outputting any abnormalities detected. It can also analyze a patient's blood pressure and body temperature in real time and prioritize outputting any highly urgent abnormalities detected. Furthermore, it can analyze a patient's level of consciousness in real time and prioritize outputting any loss of consciousness detected. For example, the analysis unit can monitor heart rate in real time and issue an alert if an abnormality is detected. It can analyze respiratory rate in real time and issue an alert if an abnormality is detected. It can analyze blood pressure and body temperature in real time and issue an alert if an abnormality is detected. This allows for the provision of highly urgent information by analyzing the patient's symptoms and condition in real time. Real-time analysis includes, but is not limited to, streaming data analysis and real-time data processing. Some or all of the above-mentioned processing in the analysis unit is performed using a generative AI. For example, the analysis unit can input real-time patient data into the generative AI, which then performs the analysis.

[0043] The analysis unit can perform more accurate analyses by referring to the patient's past medical history. For example, the analysis unit can refer to the patient's past medical history and analyze its relationship to the current symptoms. The analysis unit can also refer to the patient's past treatment history and select the most suitable analysis method for the current condition. Furthermore, the analysis unit can refer to the patient's past test results to improve the accuracy of the analysis for the current symptoms. For example, the analysis unit inputs the patient's past medical history into the AI, and the AI ​​analyzes its relationship to the current symptoms. It refers to the treatment history and selects the most suitable analysis method. It refers to the test results and improves the accuracy of the analysis. In this way, more accurate analyses can be performed by referring to the patient's past medical history. Past medical history includes, but is not limited to, electronic medical records and medical databases. Some or all of the above processing in the analysis unit is performed using a generating AI. For example, the analysis unit can input the patient's past medical history into the generating AI and have the generating AI perform the analysis.

[0044] The analysis unit can prioritize the analysis of region-specific diseases and symptoms by considering the patient's geographical location. For example, if the patient is in a specific region, the analysis unit will prioritize the analysis of diseases and symptoms prevalent in that region. The analysis unit can also perform analysis considering regional medical resources based on the patient's location information. Furthermore, if the patient is in a disaster area, the analysis unit can prioritize the analysis of disaster-specific diseases and symptoms. For example, the analysis unit inputs the patient's location information into the AI, and the AI ​​prioritizes the analysis of region-specific diseases and symptoms. This allows for the prioritization of region-specific diseases and symptoms by considering the patient's geographical location information. Geographical location information includes, but is not limited to, GPS data and location information services. Some or all of the above processing in the analysis unit is performed using a generating AI. For example, the analysis unit can input the patient's location information into the generating AI, and the generating AI can perform the analysis.

[0045] The analysis unit can improve the accuracy of its analysis by referring to relevant literature and databases related to the patient. For example, the analysis unit can improve the accuracy of its analysis by referring to the latest medical literature related to the patient's symptoms. It can also improve the accuracy of its analysis by referring to databases related to the patient's condition. It can also improve the accuracy of its analysis by referring to past case studies related to the patient's symptoms. For example, the analysis unit can input relevant literature into the AI ​​and improve the accuracy of its analysis using the AI. It can improve the accuracy of its analysis by referring to databases. It can improve the accuracy of its analysis by referring to past case studies. In this way, the accuracy of the analysis can be improved by referring to relevant literature and databases related to the patient. Relevant literature and databases include, but are not limited to, academic paper databases and medical databases. Some or all of the above processing in the analysis unit is performed using a generating AI. For example, the analysis unit can input relevant literature and databases into the generating AI and perform the analysis using the generating AI.

[0046] The advice unit can adjust the level of detail in its advice according to the patient's symptoms and condition. For example, if the patient's symptoms are mild, the advice unit will provide concise advice. If the patient's symptoms are severe, the advice unit can also provide detailed advice. Furthermore, if the patient's condition is unstable, the advice unit can provide urgent advice. For example, the advice unit inputs the patient's symptoms into the AI, and the AI ​​adjusts the level of detail in the advice. This allows for more appropriate first aid to be provided by adjusting the level of detail in the advice according to the patient's symptoms and condition. The level of detail in the advice unit includes, but is not limited to, detailed or simplified procedures. Some or all of the above processing in the advice unit is performed using a generating AI. For example, the advice unit inputs the patient's symptoms and condition into the generating AI, and the generating AI adjusts the level of detail in the advice.

[0047] The advice unit can refer to the patient's past medical history to advise on more appropriate first aid. For example, the advice unit can refer to the patient's past medical history and advise on the most appropriate first aid for the current symptoms. The advice unit can also refer to the patient's past treatment history and advise on the most appropriate first aid for the current condition. Furthermore, the advice unit can refer to the patient's past test results and advise on first aid for the current symptoms. For example, the advice unit can input the patient's past medical history into the AI, and the AI ​​will advise on the most appropriate first aid for the current symptoms. It will refer to the treatment history and advise on the most appropriate first aid. It will refer to the test results and advise on first aid. This allows for the provision of more appropriate first aid by referring to the patient's past medical history. Past medical history includes, but is not limited to, electronic medical records and medical databases. Some or all of the above processing in the advice unit is performed using a generating AI. For example, the advice unit can input the patient's past medical history into the generating AI, and the generating AI can provide first aid advice.

[0048] The advice unit can prioritize providing region-specific first aid advice, taking into account the patient's geographical location. For example, if the patient is in a specific region, the advice unit will prioritize providing first aid advice for diseases or symptoms prevalent in that region. The advice unit can also provide first aid advice considering local medical resources based on the patient's location. Furthermore, if the patient is in a disaster area, the advice unit can prioritize providing disaster-specific first aid advice. For example, the advice unit inputs the patient's location information into an AI, which then prioritizes providing region-specific first aid advice. This allows for prioritizing region-specific first aid advice by considering the patient's geographical location. Geographical location information includes, but is not limited to, GPS data and location services. Some or all of the above processing in the advice unit is performed using a generative AI. For example, the advice unit can input the patient's location information into a generative AI, which then provides first aid advice.

[0049] The advice unit can improve the accuracy of its advice by referring to relevant literature and databases related to the patient. For example, the advice unit can improve the accuracy of its advice by referring to the latest medical literature related to the patient's symptoms. It can also improve the accuracy of its advice by referring to databases related to the patient's condition. It can also improve the accuracy of its advice by referring to past case studies related to the patient's symptoms. For example, the advice unit can input relevant literature into the AI, and the AI ​​can improve the accuracy of its advice. It can improve the accuracy of its advice by referring to databases. It can improve the accuracy of its advice by referring to past case studies. In this way, the accuracy of advice can be improved by referring to relevant literature and databases related to the patient. Relevant literature and databases include, but are not limited to, academic paper databases and medical databases. Some or all of the above processing in the advice unit is performed using a generative AI. For example, the advice unit can input relevant literature and databases into the generative AI, and the generative AI can provide advice.

[0050] The monitoring unit can monitor the results of first aid performed by the caller in real time and issue additional instructions depending on the urgency. For example, if the caller performs cardiopulmonary resuscitation (CPR), the AI ​​will monitor the heart rate in real time and issue additional instructions as needed. The monitoring unit can also monitor the bleeding status if the caller attempts to stop bleeding and issue additional instructions as needed. Furthermore, if the caller secures the airway, the AI ​​will monitor the respiratory status and issue additional instructions as needed. For example, the monitoring unit will issue additional instructions if the heart rate is unstable, or if the respiratory rate does not return to normal. This allows for continuous and appropriate responses by monitoring the results of first aid in real time and issuing additional instructions according to the urgency. Real-time monitoring includes, but is not limited to, streaming data analysis and real-time data processing. Some or all of the above-described processes in the monitoring unit may be performed using AI or not. For example, the monitoring unit can input the results of first aid performed by the caller into a generating AI, which can then perform the monitoring.

[0051] The monitoring unit can improve the accuracy of monitoring by referring to the patient's past medical history. For example, the monitoring unit can refer to the patient's past medical history and monitor its relevance to the current symptoms. The monitoring unit can also refer to the patient's past treatment history and select the most suitable monitoring method for the current condition. Furthermore, the monitoring unit can refer to the patient's past test results and improve the accuracy of monitoring for the current symptoms. For example, the monitoring unit inputs the patient's past medical history into an AI, and the AI ​​monitors its relevance to the current symptoms. It refers to the treatment history and selects the most suitable monitoring method. It refers to the test results and improves the accuracy of monitoring. In this way, the accuracy of monitoring can be improved by referring to the patient's past medical history. Past medical history includes, but is not limited to, electronic medical records and medical databases. Some or all of the above processing in the monitoring unit may be performed using AI or not. For example, the monitoring unit can input the patient's past medical history into a generating AI, and the generating AI can perform monitoring.

[0052] The monitoring unit can prioritize monitoring region-specific symptoms and conditions by considering the patient's geographical location. For example, if the patient is in a specific region, the monitoring unit will prioritize monitoring for diseases and symptoms prevalent in that region. The monitoring unit can also perform monitoring considering regional medical resources based on the patient's location information. Furthermore, if the patient is in a disaster area, the monitoring unit can prioritize monitoring for disaster-specific diseases and symptoms. For example, the monitoring unit can input the patient's location information into an AI, which will then prioritize monitoring for region-specific symptoms and conditions. This allows for priority monitoring of region-specific symptoms and conditions by considering the patient's geographical location information. Geographical location information includes, but is not limited to, GPS data and location services. Some or all of the above processing in the monitoring unit may be performed using AI or not. For example, the monitoring unit can input the patient's location information into a generating AI, which will then perform the monitoring.

[0053] The monitoring unit can improve the accuracy of monitoring by referring to relevant literature and databases related to the patient. For example, the monitoring unit can improve the accuracy of monitoring by referring to the latest medical literature related to the patient's symptoms. The monitoring unit can also improve the accuracy of monitoring by referring to databases related to the patient's condition. The monitoring unit can also improve the accuracy of monitoring by referring to past case studies related to the patient's symptoms. For example, the monitoring unit can input relevant literature into an AI and improve the accuracy of monitoring using the AI. It can improve the accuracy of monitoring by referring to databases. It can improve the accuracy of monitoring by referring to past case studies. In this way, the accuracy of monitoring can be improved by referring to relevant literature and databases related to the patient. Relevant literature and databases include, but are not limited to, academic paper databases and medical databases. Some or all of the above processing in the monitoring unit may be performed using AI or not using AI. For example, the monitoring unit can input relevant literature and databases into a generating AI and perform monitoring using the generating AI.

[0054] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0055] The analysis unit can perform more accurate analyses by referring to the patient's past medical history. For example, it can refer to the patient's past medical history and analyze its relationship to current symptoms. It can also refer to the patient's past treatment history and select the most appropriate analysis method for the current condition. Furthermore, it can refer to the patient's past test results to improve the accuracy of the analysis for current symptoms. In this way, more accurate analyses can be performed by referring to the patient's past medical history. Past medical history includes, but is not limited to, electronic medical records and medical databases. Some or all of the above processing in the analysis unit is performed using a generating AI. For example, the analysis unit can input the patient's past medical history into the generating AI and have the generating AI perform the analysis.

[0056] The reception department can analyze the caller's past reporting history and select the most appropriate method for receiving information. For example, it can suggest the most suitable input method based on the content of reports the caller has frequently made in the past. It can also prioritize displaying input methods for specific symptoms or conditions based on the caller's past reporting history. Furthermore, it can analyze the caller's past reporting history and suggest input methods to be used during specific time periods. In this way, the most appropriate method for receiving information can be selected by analyzing the caller's past reporting history. The most appropriate method for receiving information includes, but is not limited to, prioritization and filtering. Some or all of the above processing in the reception department may be performed using AI or not. For example, the reception department can input the caller's past reporting history into a generating AI, which can then select the most appropriate method for receiving information.

[0057] The analysis unit can analyze a patient's symptoms and condition in real time and prioritize outputting the analysis results according to their urgency. For example, it can analyze a patient's heart rate and respiratory rate in real time and prioritize outputting any abnormalities detected. It can also analyze a patient's blood pressure and body temperature in real time and prioritize outputting any highly urgent abnormalities detected. Furthermore, it can analyze a patient's level of consciousness in real time and prioritize outputting any loss of consciousness detected. This allows for the provision of highly urgent information by analyzing a patient's symptoms and condition in real time. Real-time analysis includes, but is not limited to, streaming data analysis and real-time data processing. Some or all of the above-mentioned processes in the analysis unit are performed using a generation AI. For example, the analysis unit can input real-time patient data into the generation AI and have the generation AI perform the analysis.

[0058] The advice unit can adjust the level of detail in its advice according to the patient's symptoms and condition. For example, if the patient's symptoms are mild, it can provide concise advice. If the patient's symptoms are severe, it can provide detailed advice. Furthermore, if the patient's condition is unstable, it can provide urgent advice. By adjusting the level of detail in the advice according to the patient's symptoms and condition, more appropriate first aid can be provided. The level of detail in the advice includes, but is not limited to, detailed or simplified procedures. Some or all of the above processing in the advice unit is performed using a generating AI. For example, the advice unit can input the patient's symptoms and condition into the generating AI, which can then adjust the level of detail in the advice.

[0059] The monitoring unit can monitor the results of first aid performed by the caller in real time and issue additional instructions depending on the urgency. For example, if the caller performs cardiopulmonary resuscitation, the AI ​​can monitor the heart rate in real time and issue additional instructions as needed. Similarly, if the caller stops bleeding, the AI ​​can monitor the bleeding and issue additional instructions as needed. Furthermore, if the caller secures the airway, the AI ​​can monitor the respiratory status and issue additional instructions as needed. This allows for continuous and appropriate responses by monitoring the results of first aid in real time and issuing additional instructions according to the urgency. Real-time monitoring includes, but is not limited to, streaming data analysis and real-time data processing. Some or all of the above-mentioned processes in the monitoring unit may be performed using AI or not. For example, the monitoring unit can input the results of first aid performed by the caller into a generating AI, which can then perform the monitoring.

[0060] The reception desk can automatically receive patient symptoms and conditions using voice input and image analysis. For example, when a caller describes a patient's symptoms verbally, the AI ​​analyzes the voice, converts it to text, and receives it. Alternatively, the caller can take a picture of the patient with a smartphone, and the AI ​​can perform image analysis to automatically recognize the symptoms. Furthermore, the caller can record a video, and the AI ​​can perform video analysis to receive the patient's condition in real time. This allows for the automatic receipt of patient symptoms and conditions using voice input and image analysis. Some or all of the above-described processes in the reception desk may be performed using AI, or they may not. For example, the reception desk can input voice data or image data into a generating AI, which can then perform analysis.

[0061] The following briefly describes the processing flow for example form 1.

[0062] Step 1: The reception department receives information from the caller. This information includes voice reports, text messages, and images. The reception department uses voice recognition technology, natural language processing technology, and image recognition technology to receive this information, convert it to text in real time, and send it to the analysis department. Step 2: The analysis unit uses a generation AI to analyze the information received by the reception unit. The analysis is performed based on data analysis methods and algorithms to understand and classify the patient's symptoms and condition. Step 3: The advice unit uses a generation AI to provide first aid advice based on the information analyzed by the analysis unit. First aid includes cardiopulmonary resuscitation (CPR), bleeding control methods, and airway management methods. Step 4: The monitoring unit monitors the results of the emergency response advised by the advisory unit. Monitoring includes real-time monitoring and periodic checks, and provides additional instructions as needed.

[0063] (Example of form 2) An emergency medical instruction system according to an embodiment of the present invention is a system that uses a generating AI to issue instructions for emergency medical actions to callers. The emergency medical instruction system allows callers to communicate the patient's condition at the scene to the AI, which then advises on appropriate first aid. This system improves the current situation where appropriate medical care is not provided in emergencies due to a shortage of ambulances and doctors at night, and strengthens support for callers when they themselves perform emergency responses. For example, a caller communicates the patient's condition at the scene to the AI. At this time, the caller inputs detailed information about the patient's symptoms and condition. For example, information such as "the patient has lost consciousness" or "the patient's breathing is shallow" is input. This information is input to the generating AI. Next, the generating AI analyzes the input information. The generating AI understands the patient's symptoms and condition and advises on appropriate first aid. For example, it gives specific instructions such as "start cardiopulmonary resuscitation" or "secure the airway." This enables effective responses in emergencies even if the caller is not a medical professional. Furthermore, the generating AI monitors the results of the first aid performed by the caller and gives additional instructions as needed. For example, it gives instructions such as "continue cardiopulmonary resuscitation" or "if the patient's breathing recovers, keep them at rest." This will enable callers to take appropriate action continuously. This system will improve delays in initial response during emergencies and compensate for the shortage of personnel in medical settings. It will also improve the quality and efficiency of emergency medical care, improving the quality and speed of emergency responses. For example, it is expected that the time it takes for ambulances to arrive will be shortened, and more lives will be saved. This system is intended for use in emergency medical facilities nationwide, including medical institutions, emergency services, and public safety agencies. This will use technology to compensate for the overwhelming shortage of medical resources, enabling even non-medical personnel to take effective action in emergencies. For example, even in areas where there is a severe shortage of doctors at night, the quality of emergency medical care will be improved as callers can take appropriate first aid according to instructions generated by AI. In this way, the emergency medical instruction system can support callers in taking appropriate medical action in emergencies and improve the quality and efficiency of emergency medical care.

[0064] The emergency medical instruction system according to this embodiment comprises a reception unit, an analysis unit, an advice unit, and a monitoring unit. The reception unit receives information from callers. Information from callers includes, but is not limited to, voice calls, text messages, and images. The reception unit may, for example, use voice recognition technology to receive voice calls. The reception unit may also use natural language processing technology to receive text messages. Furthermore, the reception unit may also use image recognition technology to receive images. For example, the reception unit converts voice calls into text in real time and transmits it to the analysis unit. Text messages are transmitted to the analysis unit using natural language processing technology. Images are transmitted to the analysis unit using image recognition technology. The analysis unit analyzes the information received by the reception unit using generative AI. The analysis is performed based on, for example, data analysis methods and algorithms used, but is not limited to such examples. For example, the analysis unit uses generative AI to analyze the patient's symptoms and condition. The analysis unit can also use generative AI to understand the patient's symptoms and condition. The analysis unit can also use generative AI to classify the patient's symptoms and condition. For example, the analysis unit uses generative AI to classify the patient's symptoms and advise on appropriate first aid. The advice unit uses generative AI to advise on first aid based on the information analyzed by the analysis unit. First aid includes, but is not limited to, cardiopulmonary resuscitation (CPR) and hemostasis. For example, the advice unit uses generative AI to advise on CPR. The advice unit can also use generative AI to advise on hemostasis. The advice unit can also use generative AI to advise on airway management. For example, the advice unit uses generative AI to explain the steps of CPR in detail. For hemostasis, it uses generative AI to advise on specific steps. For airway management, it uses generative AI to advise on appropriate steps. The monitoring unit monitors the results of the first aid advised by the advice unit. Monitoring includes, but is not limited to, real-time monitoring and periodic checks. For example, the monitoring unit monitors heart rate and respiratory rate in real time.Furthermore, the monitoring unit can periodically check the patient's condition. The monitoring unit can also issue additional instructions as needed. For example, it may issue additional instructions if the heart rate is unstable, or if the respiratory rate does not return to normal. This allows the emergency medical instruction system according to the embodiment to assist callers in performing appropriate medical actions in emergencies, thereby improving the quality and efficiency of emergency medical care.

[0065] The reception department receives information from callers. This information may include, but is not limited to, voice calls, text messages, and images. For example, the reception department uses speech recognition technology to receive voice calls. Specifically, the speech recognition technology converts the caller's voice into text in real time and sends it to the analysis department. This speech recognition technology uses advanced algorithms to remove noise and background sounds and clearly recognize the caller's voice. The reception department can also use natural language processing technology to receive text messages. This technology analyzes the text messages sent by the caller, extracts important information, and sends it to the analysis department. This technology also has the ability to understand context and correct typos and omissions. Furthermore, the reception department can also use image recognition technology to receive images. This technology analyzes images sent by the caller and extracts information to identify the patient's condition and symptoms. For example, the image recognition technology evaluates the size of a wound and the degree of bleeding and sends it to the analysis department. This allows the reception department to efficiently receive diverse forms of information and quickly transmit it to the analysis department. Furthermore, the reception department provides a user interface to facilitate smooth interaction with callers. For example, in the case of voice calls, it can ask appropriate questions to the caller and extract necessary information. In the case of text messages, it can use an automatic reply function to confirm necessary information with the caller. This allows the reception department to accurately and quickly collect information from callers and transmit it to the analysis department, thereby maximizing the effectiveness of the emergency medical instruction system.

[0066] The analysis unit uses generative AI to analyze information received by the reception unit. The analysis is performed based on, for example, data analysis methods and algorithms used, but is not limited to these examples. Specifically, the generative AI analyzes text and text messages converted from voice calls to understand the patient's symptoms and condition. Using natural language processing technology, the generative AI extracts important keywords and phrases from the caller's words and evaluates the patient's condition. It also uses image recognition technology to analyze transmitted images and identify the patient's injuries and symptoms. For example, the generative AI evaluates the degree of bleeding and the depth of wounds from images to determine appropriate first aid. Furthermore, the generative AI can classify the patient's symptoms and condition. For example, it can classify the patient's symptoms into mild, moderate, and severe, and suggest appropriate first aid for each. This allows the analysis unit to quickly and accurately analyze information received from the reception unit and understand the patient's condition in real time. Additionally, the analysis unit can predict the patient's condition by utilizing past data and statistical information. For example, based on past case data, it can evaluate the likelihood of a specific symptom progressing and take appropriate measures early. Furthermore, the analysis unit can use anomaly detection algorithms to detect unusual patterns and abnormal data, enabling it to issue warnings early. This allows the analysis unit to not only grasp the situation in real time but also to handle long-term risk management and anomaly detection, thereby improving the reliability and safety of the emergency medical instruction system.

[0067] The advice unit uses a generating AI to provide first aid advice based on information analyzed by the analysis unit. First aid includes, but is not limited to, cardiopulmonary resuscitation (CPR) and hemostasis. Specifically, the generating AI proposes the most appropriate first aid based on the patient's condition information provided by the analysis unit. For example, if CPR is needed, the generating AI will explain the CPR procedure in detail and provide specific instructions to the caller. The generating AI will use voice guidance and text messages to explain in detail the rhythm and strength of chest compressions and the method of artificial respiration. If hemostasis is needed, the generating AI will propose an appropriate hemostasis method depending on the location of the bleeding. For example, it will explain in detail how to apply pressure to stop bleeding and how to use a tourniquet, and instruct the caller on the appropriate procedure. Furthermore, if airway management is needed, the generating AI will explain the airway management procedure in detail and provide specific instructions to the caller. For example, it will explain in detail the procedures for the head tilt-chin lift maneuver and the jaw lift maneuver, and instruct the caller on the appropriate procedure. This allows the advisory unit to use generative AI to provide callers with rapid and accurate first aid instructions, stabilizing the patient's condition. Furthermore, the advisory unit can collect feedback from callers and evaluate the effectiveness of first aid. For example, callers can report the results of first aid, and the generative AI can evaluate its effectiveness based on this information. This allows the advisory unit to continuously improve the accuracy and effectiveness of first aid, thereby enhancing the reliability and effectiveness of the emergency medical instruction system.

[0068] The monitoring unit monitors the results of first aid measures advised by the advisory unit. Monitoring includes, but is not limited to, real-time monitoring and periodic checks. Specifically, the monitoring unit uses sensors to monitor heart rate and respiratory rate in real time. These sensors are attached to the patient's body and continuously measure heart rate and respiratory rate, transmitting the data to the monitoring unit. The monitoring unit analyzes this data to understand the patient's condition in real time. The monitoring unit can also periodically check the patient's condition. For example, it can check the patient's level of consciousness, skin color, and body temperature at regular intervals and transmit this information to the analysis unit. Furthermore, the monitoring unit can issue additional instructions as needed. For example, if the heart rate is unstable, the monitoring unit will instruct additional first aid measures. If the respiratory rate does not return to normal, the monitoring unit will instruct additional airway management methods. This allows the monitoring unit to continuously monitor the patient's condition and respond quickly as needed. In addition, the monitoring unit can store patient condition data long-term for later analysis and evaluation. For example, based on patient condition data, the effectiveness of first aid can be evaluated, and areas for future improvement can be identified. Furthermore, the monitoring unit can use anomaly detection algorithms to detect unusual patterns or abnormal data, enabling early warnings. This allows the monitoring unit to not only grasp the situation in real time but also to handle long-term risk management and anomaly detection, thereby improving the reliability and safety of the emergency medical instruction system.

[0069] The reception desk can receive information about the patient's symptoms and condition entered by the caller. For example, the reception desk can receive information entered by the caller such as "the patient is unconscious." It can also receive information entered by the caller such as "the patient is breathing shallowly." It can also receive information entered by the caller such as "the patient is bleeding." By receiving information about the patient's symptoms and condition entered by the caller, the reception desk can obtain information to advise on appropriate first aid. The patient's symptoms and condition include, but are not limited to, fever, difficulty breathing, and bleeding. Some or all of the above processing in the reception desk may be performed using AI, for example, or not using AI. For example, the reception desk can input the information entered by the caller into a generating AI, and the generating AI can analyze the information.

[0070] The analysis unit can analyze a patient's symptoms and condition using generative AI. For example, the analysis unit can analyze a patient's symptoms using generative AI. The analysis unit can also analyze a patient's condition using generative AI. Furthermore, the analysis unit can classify a patient's symptoms and condition using generative AI. For example, the analysis unit can classify a patient's symptoms using generative AI and advise on appropriate first aid. In this way, the analysis unit can accurately analyze a patient's symptoms and condition by using generative AI. Generative AI includes, but is not limited to, natural language processing and image recognition. Some or all of the above-mentioned processes in the analysis unit are performed using generative AI. For example, the analysis unit can input information entered by the caller into the generative AI and have the generative AI analyze the information.

[0071] The advice unit can provide appropriate first aid advice using generative AI. For example, the advice unit can use generative AI to advise on cardiopulmonary resuscitation (CPR). It can also use generative AI to advise on methods of stopping bleeding. Furthermore, it can use generative AI to advise on methods of securing the airway. For example, the advice unit can use generative AI to explain the steps of CPR in detail. For methods of stopping bleeding, it will provide specific steps using generative AI. For methods of securing the airway, it will provide appropriate steps using generative AI. This allows for the rapid provision of appropriate first aid advice using generative AI. Generative AI includes, but is not limited to, natural language processing and image recognition. Some or all of the above-described processes in the advice unit are performed using generative AI. For example, the advice unit can input information entered by the caller into the generative AI, which can then provide first aid advice.

[0072] The monitoring unit can monitor the results of the first aid performed by the caller and issue additional instructions as needed. For example, if the caller performs cardiopulmonary resuscitation (CPR), the monitoring unit can monitor the heart rate and issue additional instructions as needed. The monitoring unit can also monitor the bleeding status and issue additional instructions if the caller attempts to stop bleeding. Furthermore, if the caller secures the airway, the monitoring unit can monitor the respiratory status and issue additional instructions as needed. For example, the monitoring unit may issue additional instructions if the heart rate is unstable or if the respiratory rate does not return to normal. This allows for continuous and appropriate responses by monitoring the results of first aid and issuing additional instructions as needed. Monitoring includes, but is not limited to, real-time monitoring and periodic checks. Some or all of the above-described processes in the monitoring unit may be performed using AI or not. For example, the monitoring unit can input the results of the first aid performed by the caller into a generating AI, which can then perform the monitoring.

[0073] The reception desk can estimate the caller's emotions and adjust how information is received based on the estimated emotions. For example, if the caller is nervous, the reception desk can provide a simple and intuitive interface and minimize the input steps. If the caller is calm, the reception desk can provide detailed input options and collect more specific information. If the caller is in a panic, the reception desk can prioritize voice input and receive information quickly. For example, the reception desk can analyze the caller's voice and estimate their emotions. It can also analyze the caller's facial expressions using facial recognition technology and estimate their emotions. This allows for the collection of more appropriate information by adjusting how information is received according to the caller's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the reception desk may be performed using AI or not. For example, the reception desk can input the caller's voice data into a generating AI, which can then use the AI ​​to estimate the caller's emotions.

[0074] The reception department can analyze the caller's past reporting history and select the optimal method for receiving information. For example, the reception department can suggest the optimal input method based on the content the caller has frequently reported in the past. The reception department can also prioritize displaying input methods for specific symptoms or conditions based on the caller's past reporting history. Furthermore, the reception department can analyze the caller's past reporting history and suggest input methods to be used during specific time periods. For example, the reception department can input the caller's past reporting history into an AI, which then selects the optimal method for receiving information. This allows for the selection of the optimal method for receiving information by analyzing the caller's past reporting history. The optimal method for receiving information includes, but is not limited to, prioritization and filtering. Some or all of the above-described processes in the reception department may be performed using AI or not. For example, the reception department can input the caller's past reporting history into a generating AI, which then selects the optimal method for receiving information.

[0075] The reception desk can automatically receive patient symptoms and conditions using voice input and image analysis. For example, when a caller describes a patient's symptoms verbally, the AI ​​analyzes the voice and converts it to text for reception. The reception desk can also automatically recognize symptoms when a caller takes a picture of the patient with a smartphone and the AI ​​performs image analysis. Furthermore, the reception desk can receive real-time information on the patient's condition when a caller records a video and the AI ​​performs video analysis. For example, the reception desk can analyze voice input using voice recognition software and convert it into text data. It can analyze images using image recognition algorithms to recognize symptoms. It can analyze videos using video analysis technology and receive real-time information on the patient's condition. This allows the reception desk to automatically receive patient symptoms and conditions using voice input and image analysis. Some or all of the above processes in the reception desk may be performed using AI or not. For example, the reception desk can input voice data or image data into a generating AI and have the generating AI perform the analysis.

[0076] The reception desk can estimate the caller's emotions and prioritize the information to be received based on the estimated emotions. For example, if the caller is nervous, the reception desk will prioritize receiving information of high urgency. If the caller is calm, the reception desk may also prioritize receiving detailed information. Furthermore, if the caller is in a state of panic, the reception desk may also quickly receive the most important information. For example, the reception desk can analyze the caller's voice and estimate their emotions. It can also use facial recognition technology to analyze the caller's facial expressions and estimate their emotions. This allows the reception desk to prioritize the information to be received according to the caller's emotions, thereby prioritizing the receipt of information of high urgency. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the reception desk may be performed using AI or not. For example, the reception desk can input the caller's voice data into a generative AI, which can then perform emotion estimation.

[0077] The reception desk can prioritize receiving region-specific symptoms and conditions by considering the caller's geographical location. For example, if the caller is in a specific area, the reception desk will prioritize receiving information about diseases and symptoms prevalent in that area. The reception desk can also receive information considering local medical resources based on the caller's location. Furthermore, if the caller is in a disaster area, the reception desk can prioritize receiving information about disaster-specific symptoms and conditions. For example, the reception desk can input the caller's location information into an AI, which will then prioritize receiving region-specific symptoms and conditions. This allows for priority receiving of region-specific symptoms and conditions by considering the caller's geographical location. Geographical location information includes, but is not limited to, GPS data and location services. Some or all of the above processing in the reception desk may be performed using AI or not. For example, the reception desk can input the caller's location information into a generating AI, which will then prioritize receiving region-specific symptoms and conditions.

[0078] The reception department can analyze the whistleblower's social media activity and receive relevant information. For example, the reception department can analyze the whistleblower's social media posts and receive information about their health status. The reception department can also receive relevant symptoms or conditions based on location information shared by the whistleblower on social media. Furthermore, the reception department can analyze the whistleblower's social media activity history and receive information about their past health status. For example, the reception department can input social media posts into an AI and receive information about their health status through the AI. It can receive relevant symptoms or conditions based on location information. It can analyze activity history and receive information about their past health status. In this way, relevant information can be received by analyzing the whistleblower's social media activity. Social media activity includes, but is not limited to, analyzing post content or followers. Some or all of the above processing in the reception department may be performed using AI or not. For example, the reception department can input social media data into a generating AI and receive relevant information through the generating AI.

[0079] The analysis unit can estimate the caller's emotions and adjust the accuracy of the analysis based on the estimated emotions. For example, if the caller is nervous, the analysis unit can increase the accuracy of the analysis to provide more precise information. If the caller is calm, the analysis unit can also provide information with normal accuracy. Furthermore, if the caller is in a state of panic, the analysis unit can perform a rapid analysis and prioritize providing information of high urgency. For example, the analysis unit can analyze the caller's voice and estimate their emotions. It can also analyze the caller's facial expressions using facial recognition technology and estimate their emotions. This allows for the provision of more accurate information by adjusting the accuracy of the analysis according to the caller's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the analysis unit are performed using generative AI. For example, the analysis unit can input the caller's voice data into the generative AI, and the generative AI can perform emotion estimation.

[0080] The analysis unit can analyze a patient's symptoms and condition in real time and prioritize outputting the analysis results according to their urgency. For example, the analysis unit can analyze a patient's heart rate and respiratory rate in real time and prioritize outputting any abnormalities detected. It can also analyze a patient's blood pressure and body temperature in real time and prioritize outputting any highly urgent abnormalities detected. Furthermore, it can analyze a patient's level of consciousness in real time and prioritize outputting any loss of consciousness detected. For example, the analysis unit can monitor heart rate in real time and issue an alert if an abnormality is detected. It can analyze respiratory rate in real time and issue an alert if an abnormality is detected. It can analyze blood pressure and body temperature in real time and issue an alert if an abnormality is detected. This allows for the provision of highly urgent information by analyzing the patient's symptoms and condition in real time. Real-time analysis includes, but is not limited to, streaming data analysis and real-time data processing. Some or all of the above-mentioned processing in the analysis unit is performed using a generative AI. For example, the analysis unit can input real-time patient data into the generative AI, which then performs the analysis.

[0081] The analysis unit can perform more accurate analyses by referring to the patient's past medical history. For example, the analysis unit can refer to the patient's past medical history and analyze its relationship to the current symptoms. The analysis unit can also refer to the patient's past treatment history and select the most suitable analysis method for the current condition. Furthermore, the analysis unit can refer to the patient's past test results to improve the accuracy of the analysis for the current symptoms. For example, the analysis unit inputs the patient's past medical history into the AI, and the AI ​​analyzes its relationship to the current symptoms. It refers to the treatment history and selects the most suitable analysis method. It refers to the test results and improves the accuracy of the analysis. In this way, more accurate analyses can be performed by referring to the patient's past medical history. Past medical history includes, but is not limited to, electronic medical records and medical databases. Some or all of the above processing in the analysis unit is performed using a generating AI. For example, the analysis unit can input the patient's past medical history into the generating AI and have the generating AI perform the analysis.

[0082] The analysis unit can estimate the caller's emotions and adjust the display method of the analysis results based on the estimated emotions. For example, if the caller is nervous, the analysis unit provides a simple and highly visible display method. If the caller is calm, the analysis unit can also provide a display method that includes detailed information. If the caller is in a state of panic, the analysis unit can also provide a display method that focuses on the essentials. For example, the analysis unit analyzes the caller's voice and estimates their emotions. It can also analyze the caller's facial expressions using facial recognition technology and estimate their emotions. This allows for the provision of more appropriate information by adjusting the display method of the analysis results according to the caller's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processing in the analysis unit is performed using the generative AI. For example, the analysis unit can input the caller's voice data into the generative AI, and the generative AI can perform emotion estimation.

[0083] The analysis unit can prioritize the analysis of region-specific diseases and symptoms by considering the patient's geographical location. For example, if the patient is in a specific region, the analysis unit will prioritize the analysis of diseases and symptoms prevalent in that region. The analysis unit can also perform analysis considering regional medical resources based on the patient's location information. Furthermore, if the patient is in a disaster area, the analysis unit can prioritize the analysis of disaster-specific diseases and symptoms. For example, the analysis unit inputs the patient's location information into the AI, and the AI ​​prioritizes the analysis of region-specific diseases and symptoms. This allows for the prioritization of region-specific diseases and symptoms by considering the patient's geographical location information. Geographical location information includes, but is not limited to, GPS data and location information services. Some or all of the above processing in the analysis unit is performed using a generating AI. For example, the analysis unit can input the patient's location information into the generating AI, and the generating AI can perform the analysis.

[0084] The analysis unit can improve the accuracy of its analysis by referring to relevant literature and databases related to the patient. For example, the analysis unit can improve the accuracy of its analysis by referring to the latest medical literature related to the patient's symptoms. It can also improve the accuracy of its analysis by referring to databases related to the patient's condition. It can also improve the accuracy of its analysis by referring to past case studies related to the patient's symptoms. For example, the analysis unit can input relevant literature into the AI ​​and improve the accuracy of its analysis using the AI. It can improve the accuracy of its analysis by referring to databases. It can improve the accuracy of its analysis by referring to past case studies. In this way, the accuracy of the analysis can be improved by referring to relevant literature and databases related to the patient. Relevant literature and databases include, but are not limited to, academic paper databases and medical databases. Some or all of the above processing in the analysis unit is performed using a generating AI. For example, the analysis unit can input relevant literature and databases into the generating AI and perform the analysis using the generating AI.

[0085] The advice unit can estimate the caller's emotions and adjust the way it expresses advice based on the estimated emotions. For example, if the caller is nervous, the advice unit will provide simple and intuitive advice. If the caller is calm, the advice unit can also provide detailed advice. If the caller is in a state of panic, the advice unit can provide quick and concise advice. For example, the advice unit can analyze the caller's voice and estimate their emotions. It can also analyze the caller's facial expressions using facial recognition technology and estimate their emotions. This allows the advice unit to provide more appropriate advice by adjusting the way it expresses advice according to the caller's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the advice unit is performed using generative AI. For example, the advice unit can input the caller's voice data into the generative AI, which can then estimate the emotions.

[0086] The advice unit can adjust the level of detail in its advice according to the patient's symptoms and condition. For example, if the patient's symptoms are mild, the advice unit will provide concise advice. If the patient's symptoms are severe, the advice unit can also provide detailed advice. Furthermore, if the patient's condition is unstable, the advice unit can provide urgent advice. For example, the advice unit inputs the patient's symptoms into the AI, and the AI ​​adjusts the level of detail in the advice. This allows for more appropriate first aid to be provided by adjusting the level of detail in the advice according to the patient's symptoms and condition. The level of detail in the advice unit includes, but is not limited to, detailed or simplified procedures. Some or all of the above processing in the advice unit is performed using a generating AI. For example, the advice unit inputs the patient's symptoms and condition into the generating AI, and the generating AI adjusts the level of detail in the advice.

[0087] The advice unit can refer to the patient's past medical history to advise on more appropriate first aid. For example, the advice unit can refer to the patient's past medical history and advise on the most appropriate first aid for the current symptoms. The advice unit can also refer to the patient's past treatment history and advise on the most appropriate first aid for the current condition. Furthermore, the advice unit can refer to the patient's past test results and advise on first aid for the current symptoms. For example, the advice unit can input the patient's past medical history into the AI, and the AI ​​will advise on the most appropriate first aid for the current symptoms. It will refer to the treatment history and advise on the most appropriate first aid. It will refer to the test results and advise on first aid. This allows for the provision of more appropriate first aid by referring to the patient's past medical history. Past medical history includes, but is not limited to, electronic medical records and medical databases. Some or all of the above processing in the advice unit is performed using a generating AI. For example, the advice unit can input the patient's past medical history into the generating AI, and the generating AI can provide first aid advice.

[0088] The advice unit can estimate the caller's emotions and prioritize advice based on those emotions. For example, if the caller is nervous, the advice unit will prioritize providing urgent advice. If the caller is calm, the advice unit can also prioritize providing detailed advice. Furthermore, if the caller is in a state of panic, the advice unit can quickly provide the most important advice. For example, the advice unit can analyze the caller's voice and estimate their emotions. It can also analyze the caller's facial expressions using facial recognition technology and estimate their emotions. This allows the advice unit to prioritize advice according to the caller's emotions, thereby prioritizing urgent advice. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the advice unit is performed using generative AI. For example, the advice unit can input the caller's voice data into the generative AI, which can then perform emotion estimation.

[0089] The advice unit can prioritize providing region-specific first aid advice, taking into account the patient's geographical location. For example, if the patient is in a specific region, the advice unit will prioritize providing first aid advice for diseases or symptoms prevalent in that region. The advice unit can also provide first aid advice considering local medical resources based on the patient's location. Furthermore, if the patient is in a disaster area, the advice unit can prioritize providing disaster-specific first aid advice. For example, the advice unit inputs the patient's location information into an AI, which then prioritizes providing region-specific first aid advice. This allows for prioritizing region-specific first aid advice by considering the patient's geographical location. Geographical location information includes, but is not limited to, GPS data and location services. Some or all of the above processing in the advice unit is performed using a generative AI. For example, the advice unit can input the patient's location information into a generative AI, which then provides first aid advice.

[0090] The advice unit can improve the accuracy of its advice by referring to relevant literature and databases related to the patient. For example, the advice unit can improve the accuracy of its advice by referring to the latest medical literature related to the patient's symptoms. It can also improve the accuracy of its advice by referring to databases related to the patient's condition. It can also improve the accuracy of its advice by referring to past case studies related to the patient's symptoms. For example, the advice unit can input relevant literature into the AI, and the AI ​​can improve the accuracy of its advice. It can improve the accuracy of its advice by referring to databases. It can improve the accuracy of its advice by referring to past case studies. In this way, the accuracy of advice can be improved by referring to relevant literature and databases related to the patient. Relevant literature and databases include, but are not limited to, academic paper databases and medical databases. Some or all of the above processing in the advice unit is performed using a generative AI. For example, the advice unit can input relevant literature and databases into the generative AI, and the generative AI can provide advice.

[0091] The monitoring unit can estimate the caller's emotions and adjust the monitoring method based on the estimated emotions. For example, if the caller is nervous, the monitoring unit can provide a simple and intuitive monitoring method. If the caller is calm, the monitoring unit can also provide a detailed monitoring method. If the caller is in a state of panic, the monitoring unit can also provide a quick and concise monitoring method. For example, the monitoring unit can analyze the caller's voice and estimate their emotions. It can also analyze the caller's facial expressions using facial recognition technology and estimate their emotions. This allows for more appropriate monitoring by adjusting the monitoring method according to the caller's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the monitoring unit is performed using generative AI. For example, the monitoring unit can input the caller's voice data into the generative AI, and the generative AI can estimate the emotions.

[0092] The monitoring unit can monitor the results of first aid performed by the caller in real time and issue additional instructions depending on the urgency. For example, if the caller performs cardiopulmonary resuscitation (CPR), the AI ​​will monitor the heart rate in real time and issue additional instructions as needed. The monitoring unit can also monitor the bleeding status if the caller attempts to stop bleeding and issue additional instructions as needed. Furthermore, if the caller secures the airway, the AI ​​will monitor the respiratory status and issue additional instructions as needed. For example, the monitoring unit will issue additional instructions if the heart rate is unstable, or if the respiratory rate does not return to normal. This allows for continuous and appropriate responses by monitoring the results of first aid in real time and issuing additional instructions according to the urgency. Real-time monitoring includes, but is not limited to, streaming data analysis and real-time data processing. Some or all of the above-described processes in the monitoring unit may be performed using AI or not. For example, the monitoring unit can input the results of first aid performed by the caller into a generating AI, which can then perform the monitoring.

[0093] The monitoring unit can improve the accuracy of monitoring by referring to the patient's past medical history. For example, the monitoring unit can refer to the patient's past medical history and monitor its relevance to the current symptoms. The monitoring unit can also refer to the patient's past treatment history and select the most suitable monitoring method for the current condition. Furthermore, the monitoring unit can refer to the patient's past test results and improve the accuracy of monitoring for the current symptoms. For example, the monitoring unit inputs the patient's past medical history into an AI, and the AI ​​monitors its relevance to the current symptoms. It refers to the treatment history and selects the most suitable monitoring method. It refers to the test results and improves the accuracy of monitoring. In this way, the accuracy of monitoring can be improved by referring to the patient's past medical history. Past medical history includes, but is not limited to, electronic medical records and medical databases. Some or all of the above processing in the monitoring unit may be performed using AI or not. For example, the monitoring unit can input the patient's past medical history into a generating AI, and the generating AI can perform monitoring.

[0094] The monitoring unit can estimate the caller's emotions and adjust the display method of the monitoring results based on the estimated emotions. For example, if the caller is nervous, the monitoring unit provides a simple and highly visible display method. If the caller is calm, the monitoring unit can also provide a display method that includes detailed information. If the caller is in a state of panic, the monitoring unit can also provide a display method that focuses on the essentials. For example, the monitoring unit analyzes the caller's voice and estimates their emotions. It can also analyze the caller's facial expressions using facial recognition technology and estimate their emotions. This allows for the provision of more appropriate information by adjusting the display method of the monitoring results according to the caller's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the monitoring unit are performed using generative AI. For example, the monitoring unit can input the caller's voice data into the generative AI, and the generative AI can perform emotion estimation.

[0095] The monitoring unit can prioritize monitoring region-specific symptoms and conditions by considering the patient's geographical location. For example, if the patient is in a specific region, the monitoring unit will prioritize monitoring for diseases and symptoms prevalent in that region. The monitoring unit can also perform monitoring considering regional medical resources based on the patient's location information. Furthermore, if the patient is in a disaster area, the monitoring unit can prioritize monitoring for disaster-specific diseases and symptoms. For example, the monitoring unit can input the patient's location information into an AI, which will then prioritize monitoring for region-specific symptoms and conditions. This allows for priority monitoring of region-specific symptoms and conditions by considering the patient's geographical location information. Geographical location information includes, but is not limited to, GPS data and location services. Some or all of the above processing in the monitoring unit may be performed using AI or not. For example, the monitoring unit can input the patient's location information into a generating AI, which will then perform the monitoring.

[0096] The monitoring unit can improve the accuracy of monitoring by referring to relevant literature and databases related to the patient. For example, the monitoring unit can improve the accuracy of monitoring by referring to the latest medical literature related to the patient's symptoms. The monitoring unit can also improve the accuracy of monitoring by referring to databases related to the patient's condition. The monitoring unit can also improve the accuracy of monitoring by referring to past case studies related to the patient's symptoms. For example, the monitoring unit can input relevant literature into an AI and improve the accuracy of monitoring using the AI. It can improve the accuracy of monitoring by referring to databases. It can improve the accuracy of monitoring by referring to past case studies. In this way, the accuracy of monitoring can be improved by referring to relevant literature and databases related to the patient. Relevant literature and databases include, but are not limited to, academic paper databases and medical databases. Some or all of the above processing in the monitoring unit may be performed using AI or not using AI. For example, the monitoring unit can input relevant literature and databases into a generating AI and perform monitoring using the generating AI.

[0097] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0098] The reception desk can estimate the caller's emotions and adjust how information is received based on the estimated emotions. For example, if the caller is nervous, a simple and intuitive interface can be provided, minimizing the input steps. If the caller is calm, detailed input options can be provided, allowing for the collection of more specific information. Furthermore, if the caller is in a state of panic, voice input can be prioritized to receive information quickly. This allows for the collection of more appropriate information by adjusting how information is received according to the caller's emotions. Emotion estimation can be achieved using, for example, an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the reception desk may be performed using AI or not. For example, the reception desk can input the caller's voice data into a generative AI, which can then estimate the caller's emotions.

[0099] The analysis unit can perform more accurate analyses by referring to the patient's past medical history. For example, it can refer to the patient's past medical history and analyze its relationship to current symptoms. It can also refer to the patient's past treatment history and select the most appropriate analysis method for the current condition. Furthermore, it can refer to the patient's past test results to improve the accuracy of the analysis for current symptoms. In this way, more accurate analyses can be performed by referring to the patient's past medical history. Past medical history includes, but is not limited to, electronic medical records and medical databases. Some or all of the above processing in the analysis unit is performed using a generating AI. For example, the analysis unit can input the patient's past medical history into the generating AI and have the generating AI perform the analysis.

[0100] The advice unit can estimate the caller's emotions and adjust the way it expresses advice based on those emotions. For example, if the caller is nervous, it can provide simple and intuitive advice. If the caller is calm, it can provide detailed advice. Furthermore, if the caller is panicking, it can provide quick and concise advice. By adjusting the way advice is expressed according to the caller's emotions, more appropriate advice can be provided. Emotion estimation is achieved using, for example, an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the advice unit is performed using generative AI. For example, the advice unit can input the caller's voice data into the generative AI, which can then estimate the emotions.

[0101] The monitoring unit can estimate the caller's emotions and adjust the monitoring method based on the estimated emotions. For example, if the caller is nervous, it can provide a simple and intuitive monitoring method. If the caller is calm, it can provide a detailed monitoring method. Furthermore, if the caller is in a state of panic, it can provide a quick and concise monitoring method. This allows for more appropriate monitoring by adjusting the monitoring method according to the caller's emotions. Emotion estimation is achieved using, for example, an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processing in the monitoring unit is performed using generative AI. For example, the monitoring unit can input the caller's voice data into the generative AI, which can then estimate the emotions.

[0102] The reception department can analyze the caller's past reporting history and select the most appropriate method for receiving information. For example, it can suggest the most suitable input method based on the content of reports the caller has frequently made in the past. It can also prioritize displaying input methods for specific symptoms or conditions based on the caller's past reporting history. Furthermore, it can analyze the caller's past reporting history and suggest input methods to be used during specific time periods. In this way, the most appropriate method for receiving information can be selected by analyzing the caller's past reporting history. The most appropriate method for receiving information includes, but is not limited to, prioritization and filtering. Some or all of the above processing in the reception department may be performed using AI or not. For example, the reception department can input the caller's past reporting history into a generating AI, which can then select the most appropriate method for receiving information.

[0103] The analysis unit can analyze a patient's symptoms and condition in real time and prioritize outputting the analysis results according to their urgency. For example, it can analyze a patient's heart rate and respiratory rate in real time and prioritize outputting any abnormalities detected. It can also analyze a patient's blood pressure and body temperature in real time and prioritize outputting any highly urgent abnormalities detected. Furthermore, it can analyze a patient's level of consciousness in real time and prioritize outputting any loss of consciousness detected. This allows for the provision of highly urgent information by analyzing a patient's symptoms and condition in real time. Real-time analysis includes, but is not limited to, streaming data analysis and real-time data processing. Some or all of the above-mentioned processes in the analysis unit are performed using a generation AI. For example, the analysis unit can input real-time patient data into the generation AI and have the generation AI perform the analysis.

[0104] The advice unit can adjust the level of detail in its advice according to the patient's symptoms and condition. For example, if the patient's symptoms are mild, it can provide concise advice. If the patient's symptoms are severe, it can provide detailed advice. Furthermore, if the patient's condition is unstable, it can provide urgent advice. By adjusting the level of detail in the advice according to the patient's symptoms and condition, more appropriate first aid can be provided. The level of detail in the advice includes, but is not limited to, detailed or simplified procedures. Some or all of the above processing in the advice unit is performed using a generating AI. For example, the advice unit can input the patient's symptoms and condition into the generating AI, which can then adjust the level of detail in the advice.

[0105] The monitoring unit can monitor the results of first aid performed by the caller in real time and issue additional instructions depending on the urgency. For example, if the caller performs cardiopulmonary resuscitation, the AI ​​can monitor the heart rate in real time and issue additional instructions as needed. Similarly, if the caller stops bleeding, the AI ​​can monitor the bleeding and issue additional instructions as needed. Furthermore, if the caller secures the airway, the AI ​​can monitor the respiratory status and issue additional instructions as needed. This allows for continuous and appropriate responses by monitoring the results of first aid in real time and issuing additional instructions according to the urgency. Real-time monitoring includes, but is not limited to, streaming data analysis and real-time data processing. Some or all of the above-mentioned processes in the monitoring unit may be performed using AI or not. For example, the monitoring unit can input the results of first aid performed by the caller into a generating AI, which can then perform the monitoring.

[0106] The reception desk can automatically receive patient symptoms and conditions using voice input and image analysis. For example, when a caller describes a patient's symptoms verbally, the AI ​​analyzes the voice, converts it to text, and receives it. Alternatively, the caller can take a picture of the patient with a smartphone, and the AI ​​can perform image analysis to automatically recognize the symptoms. Furthermore, the caller can record a video, and the AI ​​can perform video analysis to receive the patient's condition in real time. This allows for the automatic receipt of patient symptoms and conditions using voice input and image analysis. Some or all of the above-described processes in the reception desk may be performed using AI, or they may not. For example, the reception desk can input voice data or image data into a generating AI, which can then perform analysis.

[0107] The analysis unit can estimate the caller's emotions and adjust the accuracy of the analysis based on the estimated emotions. For example, if the caller is nervous, the analysis accuracy can be increased to provide more accurate information. If the caller is calm, information can be provided with normal analysis accuracy. Furthermore, if the caller is in a state of panic, the analysis can be performed quickly to prioritize the provision of information of high urgency. In this way, more accurate information can be provided by adjusting the accuracy of the analysis according to the caller's emotions. Emotion estimation is achieved using, for example, an emotion engine or a generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the analysis unit is performed using the generative AI. For example, the analysis unit can input the caller's voice data into the generative AI, and the generative AI can estimate the emotions.

[0108] The following briefly describes the processing flow for example form 2.

[0109] Step 1: The reception department receives information from the caller. This information includes voice reports, text messages, and images. The reception department uses voice recognition technology, natural language processing technology, and image recognition technology to receive this information, convert it to text in real time, and send it to the analysis department. Step 2: The analysis unit uses a generation AI to analyze the information received by the reception unit. The analysis is performed based on data analysis methods and algorithms to understand and classify the patient's symptoms and condition. Step 3: The advice unit uses a generation AI to provide first aid advice based on the information analyzed by the analysis unit. First aid includes cardiopulmonary resuscitation (CPR), bleeding control methods, and airway management methods. Step 4: The monitoring unit monitors the results of the emergency response advised by the advisory unit. Monitoring includes real-time monitoring and periodic checks, and provides additional instructions as needed.

[0110] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0111] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0112] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0113] Each of the multiple elements described above, including the reception unit, analysis unit, advice unit, and monitoring unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the reception unit receives voice and images from the caller using the microphone 38B and camera 42 of the smart device 14 and transmits them to the data processing unit 12 via the control unit 46A. The analysis unit is implemented in the specific processing unit 290 of the data processing unit 12 and analyzes the received information using a generating AI. The advice unit is implemented in the specific processing unit 290 of the data processing unit 12 and advises on appropriate first aid based on the analysis results. The monitoring unit is implemented in the specific processing unit 46A of the smart device 14 and monitors the results of the first aid performed by the caller in real time and issues additional instructions as needed. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0114] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0115] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0116] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0117] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0118] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0119] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0120] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0121] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0122] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0123] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0124] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0125] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0126] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0127] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0128] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0129] Each of the multiple elements described above, including the reception unit, analysis unit, advice unit, and monitoring unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the reception unit receives voice and images from the caller using the microphone 238 and camera 42 of the smart glasses 214 and transmits them to the data processing unit 12 via the control unit 46A. The analysis unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12 and analyzes the received information using a generating AI. The advice unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12 and advises on appropriate first aid based on the analysis results. The monitoring unit is implemented, for example, by the control unit 46A of the smart glasses 214 and monitors the results of the first aid performed by the caller in real time and issues additional instructions as needed. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0130] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0131] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0132] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0133] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0134] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0135] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0136] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0137] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0138] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0139] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0140] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0141] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0142] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0143] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0144] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0145] Each of the multiple elements described above, including the reception unit, analysis unit, advice unit, and monitoring unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the reception unit receives voice and images from the caller using the microphone 238 and camera 42 of the headset terminal 314 and transmits them to the data processing unit 12 via the control unit 46A. The analysis unit is implemented in the specific processing unit 290 of the data processing unit 12 and analyzes the received information using a generating AI. The advice unit is implemented in the specific processing unit 290 of the data processing unit 12 and advises on appropriate first aid based on the analysis results. The monitoring unit is implemented in the specific processing unit 46A of the headset terminal 314 and monitors the results of the first aid performed by the caller in real time and issues additional instructions as needed. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0146] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0147] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0148] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0149] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0150] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0151] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0152] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0153] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0154] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0155] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0156] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0157] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0158] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0159] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0160] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0161] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0162] Each of the multiple elements described above, including the reception unit, analysis unit, advice unit, and monitoring unit, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the reception unit receives voice and images from the caller using the microphone 238 and camera 42 of the robot 414 and transmits them to the data processing unit 12 via the control unit 46A. The analysis unit is implemented in the specific processing unit 290 of the data processing unit 12 and analyzes the received information using a generated AI. The advice unit is implemented in the specific processing unit 290 of the data processing unit 12 and advises on appropriate first aid based on the analysis results. The monitoring unit is implemented in the control unit 46A of the robot 414 and monitors the results of the first aid performed by the caller in real time and issues additional instructions as needed. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0163] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0164] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0165] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0166] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0167] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0168] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0169] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0170] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0171] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0172] 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.

[0173] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0174] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0175] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0176] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0177] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0178] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0179] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0180] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0181] (Note 1) The reception department receives information from whistleblowers, An analysis unit that analyzes the information received by the reception unit, An advice unit provides advice on first aid based on the information analyzed by the aforementioned analysis unit, The system includes a monitoring unit that monitors the results of emergency measures advised by the aforementioned advice unit. A system characterized by the following features. (Note 2) The aforementioned reception unit is The system accepts the patient's symptoms and condition entered by the caller. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned analysis unit, The AI ​​generates data to analyze the patient's symptoms and condition. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned advice section, The generated AI provides advice on appropriate first aid. The system described in Appendix 1, characterized by the features described herein. (Note 5) The monitoring unit, Monitor the results of the first aid administered by the caller and issue additional instructions as needed. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned reception unit is We estimate the feelings of the whistleblower and adjust how we receive information based on those estimated feelings. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned reception unit is Analyze the whistleblower's past reporting history and select the most suitable method for receiving information. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned reception unit is The system automatically receives patient symptoms and conditions using voice input and image analysis. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned reception unit is The system estimates the caller's emotions and prioritizes the information to be received based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned reception unit is Taking into account the geographical location of the caller, priority will be given to receiving reports of symptoms and conditions specific to that region. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned reception unit is We analyze the whistleblower's social media activity and collect relevant information. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned analysis unit, The system estimates the caller's emotions and adjusts the accuracy of the analysis based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned analysis unit, The system analyzes the patient's symptoms and condition in real time and prioritizes outputting analysis results according to their urgency. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned analysis unit, By referring to the patient's past medical history, a more accurate analysis can be performed. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned analysis unit, The system estimates the caller's emotions and adjusts how the analysis results are displayed based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned analysis unit, By considering the patient's geographical location, the analysis prioritizes region-specific diseases and symptoms. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned analysis unit, Referencing relevant patient literature and databases improves the accuracy of the analysis. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned advice section, The system estimates the caller's emotions and adjusts the way advice is expressed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned advice section, The level of detail in the advice will be adjusted according to the patient's symptoms and condition. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned advice section, Referencing the patient's past medical history will help provide more appropriate first aid advice. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned advice section, The system estimates the caller's emotions and prioritizes advice based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned advice section, Considering the patient's geographical location, priority will be given to advising on region-specific first aid measures. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned advice section, Referencing relevant patient literature and databases improves the accuracy of advice. The system described in Appendix 1, characterized by the features described herein. (Note 24) The monitoring unit, Estimate the caller's emotions and adjust the monitoring method based on the estimated emotions of the caller. The system described in Appendix 1, characterized by the features described herein. (Note 25) The monitoring unit, The system monitors the results of first aid administered by the caller in real time and issues additional instructions depending on the urgency. The system described in Appendix 1, characterized by the features described herein. (Note 26) The monitoring unit, Referencing the patient's past medical history improves the accuracy of monitoring. The system described in Appendix 1, characterized by the features described herein. (Note 27) The monitoring unit, The system estimates the caller's emotions and adjusts how monitoring results are displayed based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 28) The monitoring unit, By considering the patient's geographical location, monitoring of region-specific symptoms and conditions will be prioritized. The system described in Appendix 1, characterized by the features described herein. (Note 29) The monitoring unit, Referencing relevant patient literature and databases improves the accuracy of monitoring. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0182] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. The reception department receives information from whistleblowers, An analysis unit that analyzes the information received by the reception unit, An advice unit provides advice on first aid based on the information analyzed by the aforementioned analysis unit, The system includes a monitoring unit that monitors the results of emergency measures advised by the aforementioned advice unit. A system characterized by the following features.

2. The aforementioned reception unit is The system accepts the patient's symptoms and condition entered by the caller. The system according to feature 1.

3. The aforementioned analysis unit, Generative AI is used to analyze the patient's symptoms and condition. The system according to feature 1.

4. The aforementioned advice section, The AI ​​generates information to provide advice on appropriate first aid. The system according to feature 1.

5. The monitoring unit, Monitor the results of the first aid administered by the caller and issue additional instructions as needed. The system according to feature 1.

6. The aforementioned reception unit is We estimate the feelings of the whistleblower and adjust how we receive information based on those estimated feelings. The system according to feature 1.

7. The aforementioned reception unit is Analyze the whistleblower's past reporting history and select the most suitable method for receiving information. The system according to feature 1.

8. The aforementioned reception unit is The system automatically receives patient symptoms and conditions using voice input and image analysis. The system according to feature 1.

Images