system

Abstract

The system according to this embodiment aims to provide an initial response method for injuries or changes in physical condition and to determine appropriate medical options. [Solution] The system according to the embodiment comprises a reception unit, an analysis unit, a provision unit, a triage unit, and a management unit. The reception unit receives medical questionnaire information from the user. The analysis unit analyzes the medical questionnaire information received by the reception unit and images taken by the camera. The provision unit provides an appropriate initial response method based on the information analyzed by the analysis unit. The triage unit performs triage based on the initial response method provided by the provision unit and provides appropriate medical options. The management unit centrally manages the information provided by the triage unit in the cloud and checks past response history.

Description

Technical Field

[0006]

[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, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the prior art, there is a problem that the initial response method for injuries and physical condition changes is unknown, and it is difficult to determine appropriate medical options.

[0005] The system according to the embodiment aims to provide an initial response method for injuries and physical condition changes and to determine appropriate medical options.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a reception unit, an analysis unit, a provision unit, a triage unit, and a management unit. The reception unit receives medical questionnaire information from users. The analysis unit analyzes the medical questionnaire information received by the reception unit and images captured by a camera. The provision unit provides appropriate initial response methods based on the information analyzed by the analysis unit. The triage unit performs triage based on the initial response methods provided by the provision unit and provides appropriate medical options. The management unit centrally manages the information provided by the triage unit in the cloud and checks past response history. [Effects of the Invention]

[0007] The system according to this embodiment provides a method for initial response to injuries or changes in physical condition, and can determine appropriate medical options. [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 numbered communication I / F (Interface) is an interface including a communication processor, an antenna, etc. The communication I / F manages communication between multiple 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) The Home Doctor System according to an embodiment of the present invention is a system that supports the user's health management by utilizing generative AI. In this Home Doctor System, the user initiates a conversation with the AI ​​doctor and asks questions about symptoms and changes in physical condition. Next, the user sends images of the symptoms taken with a camera to the AI ​​doctor. The generative AI analyzes this information and immediately provides appropriate initial response methods. For example, for minor injuries, it provides first aid methods, and for severe symptoms, it recommends visiting a hospital. The generative AI also performs triage and provides medical options according to the urgency of the symptoms. This allows the user to select an appropriate medical institution and avoid unnecessary visits. Furthermore, the generative AI centrally manages the user's health data in the cloud and allows the user to check past response history. This enables efficient daily health management. This mechanism reduces anxiety about injuries and changes in physical condition and allows users to take appropriate initial responses. It also reduces the burden on medical professionals and prevents an increase in medical costs. For example, if a child develops a fever in the middle of the night, the generative AI can provide appropriate response methods, allowing parents to deal with the situation with peace of mind. Furthermore, even when elderly people live alone, the AI-generated information supports their health management, allowing them to live with peace of mind. This enables the Home Doctor system to efficiently support users' health management, reduce the burden on healthcare professionals, and prevent the increase in medical costs.

[0029] The home doctor system according to this embodiment comprises a reception unit, an analysis unit, a provision unit, a triage unit, and a management unit. The reception unit receives medical information from the user. This information includes, but is not limited to, text-based questions and answers, multiple-choice questions, etc. The reception unit also receives, for example, information when the user starts a conversation with the AI ​​doctor. The analysis unit analyzes the medical information received by the reception unit and images taken by the camera. The analysis unit determines the urgency of the symptoms, for example, using image analysis algorithms and text analysis techniques. The provision unit provides appropriate initial response methods based on the information analyzed by the analysis unit. The provision unit provides, for example, first aid procedures and guidance to medical institutions. The triage unit performs triage based on the initial response methods provided by the provision unit and provides appropriate medical options. The triage unit provides medical options according to the urgency of the symptoms, for example, according to criteria for evaluating urgency and methods for determining priorities. The management department centrally manages the information provided by the triage department in the cloud and checks past response history. The management department centrally manages data in the cloud, taking into consideration, for example, the type of database and security measures. As a result, the home doctor system according to this embodiment can efficiently receive and analyze user consultation information, provide appropriate initial response methods, perform triage, and centrally manage the information.

[0030] The reception desk receives medical information from users. This information may include, but is not limited to, text-based questions and answers, or multiple-choice questions. The reception desk receives information when a user initiates a conversation with an AI doctor. Specifically, users provide information by accessing a dedicated application or website using their smartphone or computer and filling out a medical questionnaire form. The questionnaire form includes detailed questions about the user's basic information (age, gender, medical history, etc.) and current symptoms (location of pain, severity of pain, onset date, etc.). This allows the reception desk to collect comprehensive information about the user's health status. Furthermore, the reception desk transmits the information provided by the user to the analysis department in real time, enabling a rapid response. For example, if the information entered by the user is incomplete, the reception desk can automatically generate additional questions and prompt the user to enter the information again. The reception desk also has a function to save the user's input so that it can be reviewed later. This allows users to refer to past medical questionnaire information and make corrections or additions as needed. To enhance user convenience, the reception desk also provides voice input and image upload functions. For example, if a user has difficulty describing their symptoms, they can provide an audio description, which can then be converted into text. Furthermore, for visual symptoms such as skin abnormalities or injuries, users can upload images taken with their camera to provide more accurate information. This allows the reception department to efficiently collect diverse information from users and provide the data to the analysis department quickly.

[0031] The analysis unit analyzes the medical information received by the reception unit and the images captured by the camera. The analysis unit uses, for example, image analysis algorithms and text analysis technologies to determine the urgency of the symptoms. Specifically, the image analysis algorithm analyzes images uploaded by the user and evaluates the condition of skin abnormalities and injuries. For example, it detects features such as pigmentation, swelling, and bleeding, and determines the severity of the symptoms by comparing these patterns with known cases. In addition, text analysis technology analyzes the medical information entered by the user using natural language processing technology to evaluate the urgency of the symptoms. For example, if a user enters keywords such as "chest pain" or "difficulty breathing," the system will determine that these are symptoms of high urgency based on this information. Furthermore, the analysis unit can use AI to compare with past data and make predictions based on similar cases. For example, it can refer to data of users who have complained of similar symptoms in the past and predict the level of risk associated with the current user's symptoms based on subsequent diagnosis results and treatment progress. This allows the analysis unit to quickly and accurately evaluate the user's symptoms and provide the service unit with appropriate initial response methods. Furthermore, the analysis unit updates data in real time and can respond quickly to changes in the user's condition. For example, if the user provides additional information or their symptoms worsen, the analysis unit immediately analyzes the new data and sends the latest evaluation results to the data provider. This allows the analysis unit to always perform highly accurate analyses based on the latest information and accurately understand the user's health status.

[0032] The service provider provides appropriate initial response methods based on information analyzed by the analysis unit. For example, the service provider provides first aid procedures and guidance to medical facilities. Specifically, it explains first aid procedures in detail according to the user's symptoms. For instance, in the case of minor injuries, it provides step-by-step instructions on how to clean and disinfect the wound, and how to apply bandages. If the symptoms are severe, it instructs the user to seek immediate medical attention and provides information on the nearest medical facility. Based on the user's location, the service provider can search for the nearest medical facility and provide detailed information such as maps, contact information, and opening hours. Furthermore, the service provider organizes the information necessary for the user to visit a medical facility and lists key points to convey to the doctor. This allows the user to proceed with the medical consultation smoothly. The service provider utilizes multimedia content to enhance user convenience. For example, it explains first aid procedures using videos and illustrations, providing information in a visually easy-to-understand format. It can also use audio guides to allow users to access information hands-free. This enables the service provider to support users in taking quick and appropriate initial responses. Furthermore, the service provider collects user feedback and continuously improves the accuracy and usefulness of the information it provides. For example, by having users report the results of first aid they have administered or their progress after visiting a medical institution, the service provider can use that information to take more appropriate action next time. In this way, the service provider can always provide users with the best possible initial response and support their health management.

[0033] The triage department performs triage based on the initial response methods provided by the service provider and offers appropriate medical options. For example, the triage department provides medical options according to the urgency of the symptoms, following criteria for evaluating urgency and determining priorities. Specifically, it classifies the user's symptoms according to their urgency and directs a rapid response to highly urgent symptoms. For example, for highly urgent symptoms such as heart attacks or severe bleeding, it instructs the user to immediately call an ambulance and guides them to an emergency medical facility. On the other hand, for less urgent symptoms, it recommends visiting a general clinic or specialist and provides detailed information such as how to make an appointment and consultation hours. The triage department can use AI to automatically evaluate the user's symptoms and recommend the most suitable medical facility or doctor. For example, based on past data and statistical information, it can identify and provide the optimal treatment method or medical facility for a specific symptom. Furthermore, the triage department can provide individually customized medical options, taking into account the user's medical history and current health status. This allows users to receive medical care best suited to their health condition. In addition, the triage department can respond quickly if the user's condition changes. For example, if a user reports additional symptoms or their symptoms worsen, the triage unit immediately analyzes the new information and provides the latest triage results. This allows the triage unit to always perform highly accurate triage based on the most up-to-date information, supporting the user's health management.

[0034] The Management Department centrally manages information provided by the Triage Department in the cloud and reviews past response history. The Management Department centrally manages data in the cloud, taking into consideration factors such as database type and security measures. Specifically, data such as user questionnaire information, analysis results, provided initial response methods, and triage results are stored in a cloud-based database and accessed as needed. This allows users to easily review past response history and compare it to their current health status. To ensure data security, the Management Department implements encryption technology and access control to protect user privacy. For example, data is encrypted during storage and transfer to prevent unauthorized access. Access permissions are also set for each user, allowing them to view only necessary information. Furthermore, the Management Department regularly backs up data to prepare for data loss or corruption. This ensures that user data is stored safely and securely, and can be accessed quickly when needed. Through centralized data management, the Management Department improves the overall efficiency of the system. For example, by enabling the Analysis Department, Provision Department, and Triage Department to quickly access necessary data, collaboration between departments is strengthened, enabling prompt and accurate responses to users. Furthermore, the management department can analyze data to identify areas for system improvement and explore new ways to provide services. This allows the management department to comprehensively support users' health management and improve the overall performance of the system.

[0035] The reception desk can receive information when a user begins a conversation with an AI doctor. For example, the reception desk can receive basic information and a summary of the user's symptoms. For example, when a user begins a conversation with an AI doctor, the reception desk can input basic information such as name, age, and gender. The reception desk can also input a summary of the symptoms the user is currently experiencing. This allows the reception desk to smoothly initiate the consultation by receiving information when a user begins a conversation with an AI doctor. Some or all of the above processing in the reception desk may be performed using AI, or not using AI. For example, the reception desk can input the user's basic information into the AI, and the AI ​​can analyze that information to smoothly initiate the consultation.

[0036] The analysis unit can analyze images captured by a camera and determine the urgency of the symptoms. For example, the analysis unit uses an image analysis algorithm to analyze images captured by a camera. For example, the analysis unit can analyze images of the affected area captured by a camera and determine the urgency of the symptoms. For example, the analysis unit can use an image analysis algorithm to determine the degree of inflammation and the presence or absence of bleeding from images of the affected area. The analysis unit can also use text analysis technology to analyze text information of symptoms entered by the user. For example, the analysis unit analyzes text information of symptoms entered by the user and determines the urgency of the symptoms. As a result, the analysis unit can provide appropriate initial response methods by analyzing images captured by a camera and determining the urgency of the symptoms. Some or all of the above processing in the analysis unit is performed using a generation AI. For example, the analysis unit can input images captured by a camera into the generation AI, and the generation AI can analyze the images and determine the urgency of the symptoms.

[0037] The service provider can provide appropriate initial response methods based on the analysis results. For example, the service provider can provide first aid procedures and guidance to medical institutions. For example, based on the information analyzed by the analysis unit, the service provider can provide first aid methods for minor injuries and recommend hospital visits for severe symptoms. The service provider can also provide initial response methods according to the urgency of the symptoms based on the analysis results. For example, if the symptoms are highly urgent, the service provider can recommend a rapid response and if they are less urgent, it can provide methods for home care. In this way, the service provider can provide appropriate initial response methods based on the analysis results, enabling users to take appropriate initial action. Some or all of the above processing in the service provider may be performed using AI or not. For example, the service provider can input the analysis results into AI, and the AI ​​can provide appropriate initial response methods based on those results.

[0038] The triage unit can provide medical options according to the urgency of the symptoms. For example, the triage unit provides medical options according to the urgency of the symptoms according to criteria for evaluating urgency and methods for determining priority. For example, if the symptoms are highly urgent, the triage unit will arrange for an ambulance or refer the patient to a specialist, and if the symptoms are less urgent, it will recommend visiting a general clinic. The triage unit can also provide information to help the user select an appropriate medical institution according to the urgency of the symptoms. For example, the triage unit will suggest the most suitable medical institution based on the user's place of residence and type of symptoms. In this way, the triage unit can provide medical options according to the urgency of the symptoms, allowing the user to select an appropriate medical institution. Some or all of the above processes in the triage unit may be performed using AI or not. For example, the triage unit can input the urgency of the symptoms into the AI, and the AI ​​can provide appropriate medical options based on that urgency.

[0039] The management department can centrally manage data in the cloud and review past interaction history. The management department centrally manages data in the cloud, taking into consideration, for example, the type of database and security measures. The management department stores, for example, user health data and past interaction history on the cloud and makes it accessible as needed. The management department can also provide an interface for reviewing past interaction history. For example, the management department can make it easy for users to search and review past interaction history. This allows the management department to efficiently manage daily health by centrally managing data in the cloud and reviewing past interaction history. Some or all of the above processes in the management department may be performed using AI or not. For example, the management department can input user health data into AI, and the AI ​​can analyze that data and provide past interaction history.

[0040] The reception desk can analyze the user's past medical history and automatically generate optimal medical questions. For example, the reception desk can generate new, relevant questions based on questions the user has answered in the past. For example, the reception desk can prioritize generating questions about specific symptoms by considering the user's past health condition. The reception desk can also automatically generate questions about frequently occurring symptoms from the user's past medical history. In this way, the reception desk can analyze the user's past medical history to automatically generate optimal medical questions and conduct efficient medical interviews. 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 the user's past medical history into AI, which can then analyze that history and automatically generate optimal medical questions.

[0041] The reception desk can customize the questions asked during the consultation based on the user's current lifestyle and health condition. For example, if the user enters their recent lifestyle habits, the reception desk can generate relevant questions based on that information. For example, if the user enters their current health condition, the reception desk can generate questions about specific symptoms based on that information. The reception desk can also generate questions that take into account the effects of medications the user is taking. In this way, the reception desk can conduct a more appropriate consultation by customizing the questions based on the user's current lifestyle and health condition. 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 data on the user's lifestyle and health condition into the AI, which can then analyze that data to customize the questions.

[0042] The reception desk can prioritize questions that are highly relevant to the user's geographical location during the medical interview. For example, if the user lives in a specific region, the reception desk will prioritize questions about diseases prevalent in that region. If the user is traveling, the reception desk will prioritize questions about health risks in the travel destination. The reception desk can also prioritize questions about health risks associated with a specific environment if the user is in that environment. This allows the reception desk to conduct a more appropriate medical interview by prioritizing questions that are highly relevant to the user's geographical location. Some or all of the above processing at the reception desk may be performed using AI or not. For example, the reception desk can input the user's geographical location information into the AI, which can then analyze that information and prioritize asking highly relevant questions.

[0043] The reception desk can analyze the user's social media activity during the consultation and ask relevant questions. For example, if the user has made health-related posts on social media, the reception desk can ask questions based on that content. For example, if the user has participated in a particular event, the reception desk can ask questions about the health risks associated with that event. The reception desk can also ask questions about a particular symptom if the user has mentioned it on social media. In this way, by analyzing the user's social media activity, the reception desk can ask relevant questions and conduct a more appropriate consultation. Some or all of the above processing at the reception desk may be performed using AI or not. For example, the reception desk can input data on the user's social media activity into an AI, which can then analyze that data and ask relevant questions.

[0044] The analysis unit can adjust the level of detail of the image analysis based on the severity of the symptoms. For example, the analysis unit performs a simple image analysis for mild symptoms. For example, it performs a detailed image analysis for severe symptoms. The analysis unit can also perform a standard image analysis for moderate symptoms. In this way, the analysis unit can provide appropriate analysis results by adjusting the level of detail of the analysis based on the severity of the symptoms. 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 severity of the symptoms into the generating AI, and the generating AI can adjust the level of detail of the analysis based on that severity.

[0045] The analysis unit can apply different analysis algorithms depending on the symptom category during image analysis. For example, in the case of skin symptoms, the analysis unit applies a skin-specific analysis algorithm. For example, in the case of visceral symptoms, the analysis unit applies a visceral-specific analysis algorithm. Furthermore, in the case of bone symptoms, the analysis unit can also apply a bone-specific analysis algorithm. In this way, the analysis unit can provide more appropriate analysis results by applying different analysis algorithms depending on the symptom category. Some or all of the above processing in the analysis unit is performed using a generation AI. For example, the analysis unit inputs the symptom category into the generation AI, and the generation AI can apply a different analysis algorithm depending on that category.

[0046] The analysis unit can determine the priority of image analysis based on the time of capture. For example, the analysis unit may prioritize the analysis of recently captured images. For example, it may postpone the analysis of older images. The analysis unit can also prioritize the analysis of images captured within a specific period. In this way, the analysis unit can prioritize the analysis of the latest information by determining the priority of analysis based on the time of capture. Some or all of the above processing in the analysis unit is performed using a generating AI. For example, the analysis unit can input data on the time of capture into the generating AI, and the generating AI can analyze that data to determine the priority of analysis.

[0047] The analysis unit can adjust the order of analysis based on the relevance of symptoms during image analysis. For example, the analysis unit prioritizes the analysis of images of highly relevant symptoms. For example, it postpones the analysis of images of less relevant symptoms. Furthermore, if multiple symptoms are related, the analysis unit can analyze those images simultaneously. This allows the analysis unit to prioritize the analysis of highly relevant symptoms by adjusting the order of analysis based on the relevance of symptoms. Some or all of the above processing in the analysis unit is performed using a generating AI. For example, the analysis unit can input symptom relevance data into the generating AI, which can then analyze that data and adjust the order of analysis.

[0048] The service provider can adjust the level of detail based on the severity of the symptoms when providing initial response methods. For example, the service provider can provide a simple initial response method for mild symptoms. For example, the service provider can provide a detailed initial response method for severe symptoms. The service provider can also provide a standard initial response method for moderate symptoms. In this way, the service provider can provide an appropriate initial response method by adjusting the level of detail based on the severity of the symptoms. Some or all of the above processing in the service provider may be performed using AI or not. For example, the service provider can input the severity of the symptoms into the AI, and the AI ​​can adjust the level of detail based on that severity.

[0049] The service provider can apply different response methods depending on the category of symptoms when providing initial response methods. For example, in the case of skin symptoms, the service provider can provide an initial response method specifically for skin. For example, in the case of internal organ symptoms, the service provider can provide an initial response method specifically for internal organs. Furthermore, the service provider can also provide an initial response method specifically for bone symptoms. In this way, the service provider can provide a more appropriate initial response method by applying different response methods depending on the category of symptoms. Some or all of the above processing in the service provider may be performed using AI or not. For example, the service provider can input the category of symptoms into the AI, and the AI ​​can apply different response methods according to that category.

[0050] The service provider can determine priorities based on the timing of symptom onset when providing initial response methods. For example, the service provider may prioritize providing initial response methods for recently occurring symptoms, or postpone providing initial response methods for older symptoms. The service provider may also prioritize providing initial response methods for symptoms that occurred within a specific period. This allows the service provider to provide appropriate initial response methods by determining priorities based on the timing of symptom onset. Some or all of the above processing in the service provider may be performed using AI or not. For example, the service provider can input the timing of symptom onset into the AI, and the AI ​​can determine priorities based on that timing.

[0051] The service provider can adjust the order of initial response methods based on the relevance of symptoms when providing them. For example, the service provider can prioritize providing initial response methods for highly relevant symptoms. For example, it can postpone providing initial response methods for less relevant symptoms. Furthermore, if multiple symptoms are related, the service provider can provide initial response methods for all of them simultaneously. In this way, by adjusting the order based on the relevance of symptoms, the service provider can prioritize providing initial response methods for highly relevant symptoms. Some or all of the above processing in the service provider may be performed using AI or not. For example, the service provider can input symptom relevance data into an AI, and the AI ​​can analyze that data and adjust the order.

[0052] The triage unit can improve the accuracy of triage by considering the interrelationships between symptoms during the triage process. For example, if multiple symptoms are related, the triage unit will comprehensively evaluate them and perform triage. For example, the triage unit will analyze the interrelationships between symptoms and prioritize triaging symptoms of higher urgency. The triage unit can also provide appropriate medical options by considering the interrelationships between symptoms. As a result, the triage unit can perform more accurate triage by considering the interrelationships between symptoms. Some or all of the above processes in the triage unit may be performed using AI or not. For example, the triage unit can input data on the interrelationships between symptoms into an AI, which can then analyze the data to improve the accuracy of triage.

[0053] The triage unit can perform triage while considering the user's attribute information. For example, the triage unit can apply appropriate triage criteria by considering the user's age. For example, the triage unit can perform triage for specific symptoms by considering the user's gender. The triage unit can also perform appropriate triage by considering the user's medical history. In this way, the triage unit can perform more appropriate triage by considering the user's attribute information. Some or all of the above processing in the triage unit may be performed using AI or not. For example, the triage unit can input the user's attribute information into the AI, and the AI ​​can analyze that information and perform triage.

[0054] The triage unit can perform triage while considering the geographical distribution of symptoms. For example, the triage unit can prioritize triaging for diseases prevalent in a particular region. For example, the triage unit can perform appropriate triage while considering the user's place of residence. The triage unit can also analyze the geographical distribution and prioritize triaging for symptoms of high urgency. In this way, the triage unit can perform more appropriate triage by considering the geographical distribution of symptoms. Some or all of the above processing in the triage unit may be performed using AI or not. For example, the triage unit can input data on the geographical distribution of symptoms into the AI, and the AI ​​can analyze that data and perform triage.

[0055] The triage unit can improve the accuracy of triage by referring to relevant literature on symptoms during the triage process. For example, the triage unit can perform triage by referring to the latest medical literature related to symptoms. For example, the triage unit can perform triage by referring to past research results on symptoms. The triage unit can also perform appropriate triage by comprehensively evaluating the literature related to symptoms. As a result, the triage unit can perform more accurate triage by referring to relevant literature on symptoms. Some or all of the above processes in the triage unit may be performed using AI or not. For example, the triage unit can input data from relevant literature on symptoms into an AI, and the AI ​​can analyze that data to improve the accuracy of triage.

[0056] The management department can optimize its management algorithms by referring to historical data during data management. For example, the management department can analyze historical data and apply the optimal data management algorithm. For example, the management department can improve the efficiency of data management based on historical data. The management department can also improve the accuracy of data management by referring to historical data. In this way, the management department can optimize its management algorithms and perform efficient data management by referring to historical data. Some or all of the above processes in the management department may be performed using AI or not. For example, the management department can input historical data into AI, and the AI ​​can analyze that data to optimize the management algorithm.

[0057] The management department can weight managed data based on when it was submitted. For example, the management department can prioritize recently submitted data. For example, it can prioritize older data. The management department can also prioritize data submitted within a specific period. This allows the management department to prioritize the management of the latest data by weighting the managed data based on when it was submitted. Some or all of the above processes in the management department may be performed using AI or not. For example, the management department can input the data submission dates into the AI, and the AI ​​can weight the managed data based on those submission dates.

[0058] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0059] The Home Doctor System can also be equipped with a monitoring unit that monitors the user's lifestyle. The monitoring unit collects data such as the user's diet, exercise, and sleep, and provides it to the analysis unit. This allows the analysis unit to more accurately assess the user's health status based on their lifestyle. For example, if the user has irregular eating habits, it can suggest improvements to their nutritional balance. If the user's health risks are increased due to lack of exercise, it can provide an appropriate exercise plan. Furthermore, if the user's sleep quality is poor, it can provide advice on how to improve sleep. In this way, the monitoring unit can comprehensively manage the user's lifestyle and support their health maintenance.

[0060] The Home Doctor System can also include a sharing section that allows users to share their health data with other medical institutions. This sharing section would, for example, share the user's health data with their primary care physician or specialists only with the user's consent. This would enable medical institutions to provide more appropriate diagnoses and treatments based on the user's past health data. For instance, a doctor the user regularly visits could provide a more effective treatment plan by understanding the user's lifestyle and past symptoms. In emergencies, it could also provide information to emergency medical institutions to ensure a rapid response. In this way, the sharing section can properly manage the user's health data and strengthen collaboration with medical institutions.

[0061] The Home Doctor System can also be equipped with a prediction unit that analyzes the user's health data and predicts future health risks. The prediction unit predicts future health risks based, for example, the user's past health data and lifestyle data. This allows the user to take proactive measures against future health risks. For instance, if the prediction unit predicts a high risk of developing high blood pressure in the future, it can suggest improvements to diet and exercise. It can also provide methods for managing blood sugar levels if there is a risk of diabetes. Furthermore, if there is a risk of heart disease, it can recommend regular health checkups. In this way, the prediction unit can support the user's health maintenance by predicting future health risks and suggesting appropriate countermeasures.

[0062] The Home Doctor system can also include a planning unit that creates personalized health plans based on the user's health data. The planning unit creates individual health plans based on data such as the user's diet, exercise, and sleep. This allows users to implement a health plan best suited to them. For example, the planning unit can analyze the user's dietary data and propose a nutritionally balanced meal plan. It can also provide an appropriate exercise plan based on exercise data. Furthermore, it can provide advice on improving sleep quality based on sleep data. In this way, the planning unit can comprehensively analyze the user's health data and support their health maintenance by providing a personalized health plan.

[0063] The Home Doctor system can also be equipped with a reporting unit that generates health reports based on the user's health data. For example, the reporting unit periodically analyzes the user's health data and generates a health status report. This makes it easier for users to understand their own health status. For instance, the reporting unit reports on changes in the user's health status based on data such as diet, exercise, and sleep. It can also compare current data with past health data to highlight areas for improvement and points to watch out for. Furthermore, if health risks are high, it can provide advice for taking early action. In this way, the reporting unit can support users in maintaining their health by comprehensively analyzing their health data and providing reports that help them understand their health status.

[0064] The following briefly describes the processing flow for example form 1.

[0065] Step 1: The reception desk receives information from the user. This information includes, for example, text-based questions and answers, and multiple-choice questions. The reception desk also receives information from the user when they begin a conversation with the AI ​​doctor. Step 2: The analysis unit analyzes the medical information received by the reception unit and the images captured by the camera. The analysis unit uses image analysis algorithms and text analysis techniques to determine the urgency of the symptoms. Step 3: The provisioning department provides appropriate initial response methods based on the information analyzed by the analysis department. The provisioning department provides first aid procedures and guidance to medical facilities. Step 4: The triage department performs triage based on the initial response methods provided by the service provider and offers appropriate medical options. The triage department offers medical options according to the urgency of the symptoms, following the criteria for assessing urgency and determining priorities. Step 5: The management department centrally manages the information provided by the triage department in the cloud and checks past response history. The management department centrally manages the data in the cloud, taking into consideration the type of database and security measures.

[0066] (Example of form 2) The Home Doctor System according to an embodiment of the present invention is a system that supports the user's health management by utilizing generative AI. In this Home Doctor System, the user initiates a conversation with the AI ​​doctor and asks questions about symptoms and changes in physical condition. Next, the user sends images of the symptoms taken with a camera to the AI ​​doctor. The generative AI analyzes this information and immediately provides appropriate initial response methods. For example, for minor injuries, it provides first aid methods, and for severe symptoms, it recommends visiting a hospital. The generative AI also performs triage and provides medical options according to the urgency of the symptoms. This allows the user to select an appropriate medical institution and avoid unnecessary visits. Furthermore, the generative AI centrally manages the user's health data in the cloud and allows the user to check past response history. This enables efficient daily health management. This mechanism reduces anxiety about injuries and changes in physical condition and allows users to take appropriate initial responses. It also reduces the burden on medical professionals and prevents an increase in medical costs. For example, if a child develops a fever in the middle of the night, the generative AI can provide appropriate response methods, allowing parents to deal with the situation with peace of mind. Furthermore, even when elderly people live alone, the AI-generated information supports their health management, allowing them to live with peace of mind. This enables the Home Doctor system to efficiently support users' health management, reduce the burden on healthcare professionals, and prevent the increase in medical costs.

[0067] The home doctor system according to this embodiment comprises a reception unit, an analysis unit, a provision unit, a triage unit, and a management unit. The reception unit receives medical information from the user. This information includes, but is not limited to, text-based questions and answers, multiple-choice questions, etc. The reception unit also receives, for example, information when the user starts a conversation with the AI ​​doctor. The analysis unit analyzes the medical information received by the reception unit and images taken by the camera. The analysis unit determines the urgency of the symptoms, for example, using image analysis algorithms and text analysis techniques. The provision unit provides appropriate initial response methods based on the information analyzed by the analysis unit. The provision unit provides, for example, first aid procedures and guidance to medical institutions. The triage unit performs triage based on the initial response methods provided by the provision unit and provides appropriate medical options. The triage unit provides medical options according to the urgency of the symptoms, for example, according to criteria for evaluating urgency and methods for determining priorities. The management department centrally manages the information provided by the triage department in the cloud and checks past response history. The management department centrally manages data in the cloud, taking into consideration, for example, the type of database and security measures. As a result, the home doctor system according to this embodiment can efficiently receive and analyze user consultation information, provide appropriate initial response methods, perform triage, and centrally manage the information.

[0068] The reception desk receives medical information from users. This information may include, but is not limited to, text-based questions and answers, or multiple-choice questions. The reception desk receives information when a user initiates a conversation with an AI doctor. Specifically, users provide information by accessing a dedicated application or website using their smartphone or computer and filling out a medical questionnaire form. The questionnaire form includes detailed questions about the user's basic information (age, gender, medical history, etc.) and current symptoms (location of pain, severity of pain, onset date, etc.). This allows the reception desk to collect comprehensive information about the user's health status. Furthermore, the reception desk transmits the information provided by the user to the analysis department in real time, enabling a rapid response. For example, if the information entered by the user is incomplete, the reception desk can automatically generate additional questions and prompt the user to enter the information again. The reception desk also has a function to save the user's input so that it can be reviewed later. This allows users to refer to past medical questionnaire information and make corrections or additions as needed. To enhance user convenience, the reception desk also provides voice input and image upload functions. For example, if a user has difficulty describing their symptoms, they can provide an audio description, which can then be converted into text. Furthermore, for visual symptoms such as skin abnormalities or injuries, users can upload images taken with their camera to provide more accurate information. This allows the reception department to efficiently collect diverse information from users and provide the data to the analysis department quickly.

[0069] The analysis unit analyzes the medical information received by the reception unit and the images captured by the camera. The analysis unit uses, for example, image analysis algorithms and text analysis technologies to determine the urgency of the symptoms. Specifically, the image analysis algorithm analyzes images uploaded by the user and evaluates the condition of skin abnormalities and injuries. For example, it detects features such as pigmentation, swelling, and bleeding, and determines the severity of the symptoms by comparing these patterns with known cases. In addition, text analysis technology analyzes the medical information entered by the user using natural language processing technology to evaluate the urgency of the symptoms. For example, if a user enters keywords such as "chest pain" or "difficulty breathing," the system will determine that these are symptoms of high urgency based on this information. Furthermore, the analysis unit can use AI to compare with past data and make predictions based on similar cases. For example, it can refer to data of users who have complained of similar symptoms in the past and predict the level of risk associated with the current user's symptoms based on subsequent diagnosis results and treatment progress. This allows the analysis unit to quickly and accurately evaluate the user's symptoms and provide the service unit with appropriate initial response methods. Furthermore, the analysis unit updates data in real time and can respond quickly to changes in the user's condition. For example, if the user provides additional information or their symptoms worsen, the analysis unit immediately analyzes the new data and sends the latest evaluation results to the data provider. This allows the analysis unit to always perform highly accurate analyses based on the latest information and accurately understand the user's health status.

[0070] The service provider provides appropriate initial response methods based on information analyzed by the analysis unit. For example, the service provider provides first aid procedures and guidance to medical facilities. Specifically, it explains first aid procedures in detail according to the user's symptoms. For instance, in the case of minor injuries, it provides step-by-step instructions on how to clean and disinfect the wound, and how to apply bandages. If the symptoms are severe, it instructs the user to seek immediate medical attention and provides information on the nearest medical facility. Based on the user's location, the service provider can search for the nearest medical facility and provide detailed information such as maps, contact information, and opening hours. Furthermore, the service provider organizes the information necessary for the user to visit a medical facility and lists key points to convey to the doctor. This allows the user to proceed with the medical consultation smoothly. The service provider utilizes multimedia content to enhance user convenience. For example, it explains first aid procedures using videos and illustrations, providing information in a visually easy-to-understand format. It can also use audio guides to allow users to access information hands-free. This enables the service provider to support users in taking quick and appropriate initial responses. Furthermore, the service provider collects user feedback and continuously improves the accuracy and usefulness of the information it provides. For example, by having users report the results of first aid they have administered or their progress after visiting a medical institution, the service provider can use that information to take more appropriate action next time. In this way, the service provider can always provide users with the best possible initial response and support their health management.

[0071] The triage department performs triage based on the initial response methods provided by the service provider and offers appropriate medical options. For example, the triage department provides medical options according to the urgency of the symptoms, following criteria for evaluating urgency and determining priorities. Specifically, it classifies the user's symptoms according to their urgency and directs a rapid response to highly urgent symptoms. For example, for highly urgent symptoms such as heart attacks or severe bleeding, it instructs the user to immediately call an ambulance and guides them to an emergency medical facility. On the other hand, for less urgent symptoms, it recommends visiting a general clinic or specialist and provides detailed information such as how to make an appointment and consultation hours. The triage department can use AI to automatically evaluate the user's symptoms and recommend the most suitable medical facility or doctor. For example, based on past data and statistical information, it can identify and provide the optimal treatment method or medical facility for a specific symptom. Furthermore, the triage department can provide individually customized medical options, taking into account the user's medical history and current health status. This allows users to receive medical care best suited to their health condition. In addition, the triage department can respond quickly if the user's condition changes. For example, if a user reports additional symptoms or their symptoms worsen, the triage unit immediately analyzes the new information and provides the latest triage results. This allows the triage unit to always perform highly accurate triage based on the most up-to-date information, supporting the user's health management.

[0072] The Management Department centrally manages information provided by the Triage Department in the cloud and reviews past response history. The Management Department centrally manages data in the cloud, taking into consideration factors such as database type and security measures. Specifically, data such as user questionnaire information, analysis results, provided initial response methods, and triage results are stored in a cloud-based database and accessed as needed. This allows users to easily review past response history and compare it to their current health status. To ensure data security, the Management Department implements encryption technology and access control to protect user privacy. For example, data is encrypted during storage and transfer to prevent unauthorized access. Access permissions are also set for each user, allowing them to view only necessary information. Furthermore, the Management Department regularly backs up data to prepare for data loss or corruption. This ensures that user data is stored safely and securely, and can be accessed quickly when needed. Through centralized data management, the Management Department improves the overall efficiency of the system. For example, by enabling the Analysis Department, Provision Department, and Triage Department to quickly access necessary data, collaboration between departments is strengthened, enabling prompt and accurate responses to users. Furthermore, the management department can analyze data to identify areas for system improvement and explore new ways to provide services. This allows the management department to comprehensively support users' health management and improve the overall performance of the system.

[0073] The reception desk can receive information when a user begins a conversation with an AI doctor. For example, the reception desk can receive basic information and a summary of the user's symptoms. For example, when a user begins a conversation with an AI doctor, the reception desk can input basic information such as name, age, and gender. The reception desk can also input a summary of the symptoms the user is currently experiencing. This allows the reception desk to smoothly initiate the consultation by receiving information when a user begins a conversation with an AI doctor. Some or all of the above processing in the reception desk may be performed using AI, or not using AI. For example, the reception desk can input the user's basic information into the AI, and the AI ​​can analyze that information to smoothly initiate the consultation.

[0074] The analysis unit can analyze images captured by a camera and determine the urgency of the symptoms. For example, the analysis unit uses an image analysis algorithm to analyze images captured by a camera. For example, the analysis unit can analyze images of the affected area captured by a camera and determine the urgency of the symptoms. For example, the analysis unit can use an image analysis algorithm to determine the degree of inflammation and the presence or absence of bleeding from images of the affected area. The analysis unit can also use text analysis technology to analyze text information of symptoms entered by the user. For example, the analysis unit analyzes text information of symptoms entered by the user and determines the urgency of the symptoms. As a result, the analysis unit can provide appropriate initial response methods by analyzing images captured by a camera and determining the urgency of the symptoms. Some or all of the above processing in the analysis unit is performed using a generation AI. For example, the analysis unit can input images captured by a camera into the generation AI, and the generation AI can analyze the images and determine the urgency of the symptoms.

[0075] The service provider can provide appropriate initial response methods based on the analysis results. For example, the service provider can provide first aid procedures and guidance to medical institutions. For example, based on the information analyzed by the analysis unit, the service provider can provide first aid methods for minor injuries and recommend hospital visits for severe symptoms. The service provider can also provide initial response methods according to the urgency of the symptoms based on the analysis results. For example, if the symptoms are highly urgent, the service provider can recommend a rapid response and if they are less urgent, it can provide methods for home care. In this way, the service provider can provide appropriate initial response methods based on the analysis results, enabling users to take appropriate initial action. Some or all of the above processing in the service provider may be performed using AI or not. For example, the service provider can input the analysis results into AI, and the AI ​​can provide appropriate initial response methods based on those results.

[0076] The triage unit can provide medical options according to the urgency of the symptoms. For example, the triage unit provides medical options according to the urgency of the symptoms according to criteria for evaluating urgency and methods for determining priority. For example, if the symptoms are highly urgent, the triage unit will arrange for an ambulance or refer the patient to a specialist, and if the symptoms are less urgent, it will recommend visiting a general clinic. The triage unit can also provide information to help the user select an appropriate medical institution according to the urgency of the symptoms. For example, the triage unit will suggest the most suitable medical institution based on the user's place of residence and type of symptoms. In this way, the triage unit can provide medical options according to the urgency of the symptoms, allowing the user to select an appropriate medical institution. Some or all of the above processes in the triage unit may be performed using AI or not. For example, the triage unit can input the urgency of the symptoms into the AI, and the AI ​​can provide appropriate medical options based on that urgency.

[0077] The management department can centrally manage data in the cloud and review past interaction history. The management department centrally manages data in the cloud, taking into consideration, for example, the type of database and security measures. The management department stores, for example, user health data and past interaction history on the cloud and makes it accessible as needed. The management department can also provide an interface for reviewing past interaction history. For example, the management department can make it easy for users to search and review past interaction history. This allows the management department to efficiently manage daily health by centrally managing data in the cloud and reviewing past interaction history. Some or all of the above processes in the management department may be performed using AI or not. For example, the management department can input user health data into AI, and the AI ​​can analyze that data and provide past interaction history.

[0078] The reception desk can estimate the user's emotions and adjust the pace of the consultation based on the estimated emotions. For example, if the user is nervous, the reception desk will proceed with the consultation at a slow pace to help them relax. If the user is in a hurry, the reception desk will proceed with the consultation quickly to collect the necessary information in a short time. Also, if the user is relaxed, the reception desk can proceed with the consultation including detailed questions to collect more information. In this way, the reception desk can adjust the pace of the consultation according to the user's emotions, allowing the user to receive the consultation in a relaxed state. 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 user's facial expression data into a generative AI, which can analyze the data to estimate the user's emotions and adjust the pace of the consultation based on those emotions.

[0079] The reception desk can analyze the user's past medical history and automatically generate optimal medical questions. For example, the reception desk can generate new, relevant questions based on questions the user has answered in the past. For example, the reception desk can prioritize generating questions about specific symptoms by considering the user's past health condition. The reception desk can also automatically generate questions about frequently occurring symptoms from the user's past medical history. In this way, the reception desk can analyze the user's past medical history to automatically generate optimal medical questions and conduct efficient medical interviews. 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 the user's past medical history into AI, which can then analyze that history and automatically generate optimal medical questions.

[0080] The reception desk can customize the questions asked during the consultation based on the user's current lifestyle and health condition. For example, if the user enters their recent lifestyle habits, the reception desk can generate relevant questions based on that information. For example, if the user enters their current health condition, the reception desk can generate questions about specific symptoms based on that information. The reception desk can also generate questions that take into account the effects of medications the user is taking. In this way, the reception desk can conduct a more appropriate consultation by customizing the questions based on the user's current lifestyle and health condition. 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 data on the user's lifestyle and health condition into the AI, which can then analyze that data to customize the questions.

[0081] The reception desk can estimate the user's emotions and determine the priority of the consultation based on the estimated emotions. For example, if the user is feeling anxious, the reception desk will prioritize urgent questions. If the user is relaxed, the reception desk will prioritize detailed questions. The reception desk can also prioritize important questions if the user is in a hurry. In this way, the reception desk can prioritize urgent questions by determining the priority of the consultation according to the user'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 user's facial expression data into a generative AI, which can analyze the data to estimate the user's emotions and determine the priority of the consultation based on those emotions.

[0082] The reception desk can prioritize questions that are highly relevant to the user's geographical location during the medical interview. For example, if the user lives in a specific region, the reception desk will prioritize questions about diseases prevalent in that region. If the user is traveling, the reception desk will prioritize questions about health risks in the travel destination. The reception desk can also prioritize questions about health risks associated with a specific environment if the user is in that environment. This allows the reception desk to conduct a more appropriate medical interview by prioritizing questions that are highly relevant to the user's geographical location. Some or all of the above processing at the reception desk may be performed using AI or not. For example, the reception desk can input the user's geographical location information into the AI, which can then analyze that information and prioritize asking highly relevant questions.

[0083] The reception desk can analyze the user's social media activity during the consultation and ask relevant questions. For example, if the user has made health-related posts on social media, the reception desk can ask questions based on that content. For example, if the user has participated in a particular event, the reception desk can ask questions about the health risks associated with that event. The reception desk can also ask questions about a particular symptom if the user has mentioned it on social media. In this way, by analyzing the user's social media activity, the reception desk can ask relevant questions and conduct a more appropriate consultation. Some or all of the above processing at the reception desk may be performed using AI or not. For example, the reception desk can input data on the user's social media activity into an AI, which can then analyze that data and ask relevant questions.

[0084] The analysis unit can estimate the user's emotions and adjust the accuracy of the image analysis based on the estimated emotions. For example, if the user is feeling anxious, the analysis unit can perform a detailed image analysis and provide accurate results. For example, if the user is relaxed, the analysis unit can perform a standard image analysis. The analysis unit can also perform a rapid image analysis and provide results quickly if the user is in a hurry. In this way, the analysis unit can provide more accurate analysis results by adjusting the accuracy of the image analysis according to the user'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 analysis unit is performed using generative AI. For example, the analysis unit can input user facial expression data into the generative AI, the generative AI can analyze the data to estimate the user's emotions, and adjust the accuracy of the image analysis based on those emotions.

[0085] The analysis unit can adjust the level of detail of the image analysis based on the severity of the symptoms. For example, the analysis unit performs a simple image analysis for mild symptoms. For example, it performs a detailed image analysis for severe symptoms. The analysis unit can also perform a standard image analysis for moderate symptoms. In this way, the analysis unit can provide appropriate analysis results by adjusting the level of detail of the analysis based on the severity of the symptoms. 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 severity of the symptoms into the generating AI, and the generating AI can adjust the level of detail of the analysis based on that severity.

[0086] The analysis unit can apply different analysis algorithms depending on the symptom category during image analysis. For example, in the case of skin symptoms, the analysis unit applies a skin-specific analysis algorithm. For example, in the case of visceral symptoms, the analysis unit applies a visceral-specific analysis algorithm. Furthermore, in the case of bone symptoms, the analysis unit can also apply a bone-specific analysis algorithm. In this way, the analysis unit can provide more appropriate analysis results by applying different analysis algorithms depending on the symptom category. Some or all of the above processing in the analysis unit is performed using a generation AI. For example, the analysis unit inputs the symptom category into the generation AI, and the generation AI can apply a different analysis algorithm depending on that category.

[0087] The analysis unit can estimate the user's emotions and adjust how the analysis results are displayed based on the estimated emotions. For example, if the user is feeling anxious, the analysis unit can display analysis results that include a detailed explanation. If the user is relaxed, for example, the analysis unit can display concise analysis results. Furthermore, if the user is in a hurry, the analysis unit can display analysis results that highlight the key points. In this way, the analysis unit can provide results in a way that is easy for the user to understand by adjusting how the analysis results are displayed according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI may include, 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 generative AI. For example, the analysis unit can input user facial expression data into the generative AI, which can analyze the data to estimate the user's emotions and adjust how the analysis results are displayed based on those emotions.

[0088] The analysis unit can determine the priority of image analysis based on the time of capture. For example, the analysis unit may prioritize the analysis of recently captured images. For example, it may postpone the analysis of older images. The analysis unit can also prioritize the analysis of images captured within a specific period. In this way, the analysis unit can prioritize the analysis of the latest information by determining the priority of analysis based on the time of capture. Some or all of the above processing in the analysis unit is performed using a generating AI. For example, the analysis unit can input data on the time of capture into the generating AI, and the generating AI can analyze that data to determine the priority of analysis.

[0089] The analysis unit can adjust the order of analysis based on the relevance of symptoms during image analysis. For example, the analysis unit prioritizes the analysis of images of highly relevant symptoms. For example, it postpones the analysis of images of less relevant symptoms. Furthermore, if multiple symptoms are related, the analysis unit can analyze those images simultaneously. This allows the analysis unit to prioritize the analysis of highly relevant symptoms by adjusting the order of analysis based on the relevance of symptoms. Some or all of the above processing in the analysis unit is performed using a generating AI. For example, the analysis unit can input symptom relevance data into the generating AI, which can then analyze that data and adjust the order of analysis.

[0090] The service provider can estimate the user's emotions and adjust the way it presents the initial response based on those emotions. For example, if the user is feeling anxious, the service provider can provide an initial response that includes a detailed explanation. If the user is relaxed, the service provider can provide a concise initial response. The service provider can also provide a quick and concise initial response if the user is in a hurry. In this way, by adjusting the way the initial response is presented according to the user's emotions, the service provider can provide an initial response in a way that is easy for the user to understand. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or 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 service provider may be performed using AI or not. For example, the service provider can input user facial expression data into a generative AI, the generative AI can analyze that data to estimate the user's emotions, and adjust the way the initial response is presented based on those emotions.

[0091] The service provider can adjust the level of detail based on the severity of the symptoms when providing initial response methods. For example, the service provider can provide a simple initial response method for mild symptoms. For example, the service provider can provide a detailed initial response method for severe symptoms. The service provider can also provide a standard initial response method for moderate symptoms. In this way, the service provider can provide an appropriate initial response method by adjusting the level of detail based on the severity of the symptoms. Some or all of the above processing in the service provider may be performed using AI or not. For example, the service provider can input the severity of the symptoms into the AI, and the AI ​​can adjust the level of detail based on that severity.

[0092] The service provider can apply different response methods depending on the category of symptoms when providing initial response methods. For example, in the case of skin symptoms, the service provider can provide an initial response method specifically for skin. For example, in the case of internal organ symptoms, the service provider can provide an initial response method specifically for internal organs. Furthermore, the service provider can also provide an initial response method specifically for bone symptoms. In this way, the service provider can provide a more appropriate initial response method by applying different response methods depending on the category of symptoms. Some or all of the above processing in the service provider may be performed using AI or not. For example, the service provider can input the category of symptoms into the AI, and the AI ​​can apply different response methods according to that category.

[0093] The service provider can estimate the user's emotions and adjust the length of the initial response based on the estimated emotions. For example, if the user is feeling anxious, the service provider can provide a longer initial response that includes a detailed explanation. For example, if the user is relaxed, the service provider can provide a concise initial response. The service provider can also provide a quick and concise initial response if the user is in a hurry. In this way, by adjusting the length of the initial response according to the user's emotions, the service provider can provide an initial response in a way that is easy for the user to understand. 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 service provider may be performed using AI or not. For example, the service provider can input user facial expression data into a generative AI, the generative AI can analyze the data to estimate the user's emotions, and adjust the length of the initial response based on those emotions.

[0094] The service provider can determine priorities based on the timing of symptom onset when providing initial response methods. For example, the service provider may prioritize providing initial response methods for recently occurring symptoms, or postpone providing initial response methods for older symptoms. The service provider may also prioritize providing initial response methods for symptoms that occurred within a specific period. This allows the service provider to provide appropriate initial response methods by determining priorities based on the timing of symptom onset. Some or all of the above processing in the service provider may be performed using AI or not. For example, the service provider can input the timing of symptom onset into the AI, and the AI ​​can determine priorities based on that timing.

[0095] The service provider can adjust the order of initial response methods based on the relevance of symptoms when providing them. For example, the service provider can prioritize providing initial response methods for highly relevant symptoms. For example, it can postpone providing initial response methods for less relevant symptoms. Furthermore, if multiple symptoms are related, the service provider can provide initial response methods for all of them simultaneously. In this way, by adjusting the order based on the relevance of symptoms, the service provider can prioritize providing initial response methods for highly relevant symptoms. Some or all of the above processing in the service provider may be performed using AI or not. For example, the service provider can input symptom relevance data into an AI, and the AI ​​can analyze that data and adjust the order.

[0096] The triage unit can estimate the user's emotions and adjust the triage criteria based on the estimated emotions. For example, if the user is feeling anxious, the triage unit will prioritize triaging symptoms of high urgency. If the user is relaxed, the triage unit will apply standard triage criteria. The triage unit can also perform rapid triage and provide results quickly if the user is in a hurry. This allows the triage unit to perform more appropriate triage by adjusting the triage criteria according to the user'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 triage unit may be performed using AI or not. For example, the triage unit can input user facial expression data into a generative AI, which can analyze the data to estimate the user's emotions and adjust the triage criteria based on those emotions.

[0097] The triage unit can improve the accuracy of triage by considering the interrelationships between symptoms during the triage process. For example, if multiple symptoms are related, the triage unit will comprehensively evaluate them and perform triage. For example, the triage unit will analyze the interrelationships between symptoms and prioritize triaging symptoms of higher urgency. The triage unit can also provide appropriate medical options by considering the interrelationships between symptoms. As a result, the triage unit can perform more accurate triage by considering the interrelationships between symptoms. Some or all of the above processes in the triage unit may be performed using AI or not. For example, the triage unit can input data on the interrelationships between symptoms into an AI, which can then analyze the data to improve the accuracy of triage.

[0098] The triage unit can perform triage while considering the user's attribute information. For example, the triage unit can apply appropriate triage criteria by considering the user's age. For example, the triage unit can perform triage for specific symptoms by considering the user's gender. The triage unit can also perform appropriate triage by considering the user's medical history. In this way, the triage unit can perform more appropriate triage by considering the user's attribute information. Some or all of the above processing in the triage unit may be performed using AI or not. For example, the triage unit can input the user's attribute information into the AI, and the AI ​​can analyze that information and perform triage.

[0099] The triage unit can estimate the user's emotions and adjust the order in which triage results are displayed based on the estimated emotions. For example, if the user is feeling anxious, the triage unit will prioritize displaying results of high urgency. If the user is relaxed, the triage unit will display results in a standard order. The triage unit can also display results quickly if the user is in a hurry. In this way, the triage unit can provide results in a way that is easy for the user to understand by adjusting the order in which triage results are displayed according to the user'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 triage unit may be performed using AI or not. For example, the triage unit can input user facial expression data into a generative AI, the generative AI can analyze the data to estimate the user's emotions, and adjust the order in which triage results are displayed based on those emotions.

[0100] The triage unit can perform triage while considering the geographical distribution of symptoms. For example, the triage unit can prioritize triaging for diseases prevalent in a particular region. For example, the triage unit can perform appropriate triage while considering the user's place of residence. The triage unit can also analyze the geographical distribution and prioritize triaging for symptoms of high urgency. In this way, the triage unit can perform more appropriate triage by considering the geographical distribution of symptoms. Some or all of the above processing in the triage unit may be performed using AI or not. For example, the triage unit can input data on the geographical distribution of symptoms into the AI, and the AI ​​can analyze that data and perform triage.

[0101] The triage unit can improve the accuracy of triage by referring to relevant literature on symptoms during the triage process. For example, the triage unit can perform triage by referring to the latest medical literature related to symptoms. For example, the triage unit can perform triage by referring to past research results on symptoms. The triage unit can also perform appropriate triage by comprehensively evaluating the literature related to symptoms. As a result, the triage unit can perform more accurate triage by referring to relevant literature on symptoms. Some or all of the above processes in the triage unit may be performed using AI or not. For example, the triage unit can input data from relevant literature on symptoms into an AI, and the AI ​​can analyze that data to improve the accuracy of triage.

[0102] The management unit can estimate the user's emotions and adjust the data management method based on the estimated emotions. For example, if the user is feeling anxious, the management unit can provide a detailed data management method. For example, if the user is relaxed, the management unit can provide a concise data management method. The management unit can also provide a rapid data management method if the user is in a hurry. In this way, the management unit can manage data in a way that is easy for the user to understand by adjusting the data management method according to the user'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 management unit may be performed using AI or not. For example, the management unit can input user facial expression data into a generative AI, the generative AI can analyze the data to estimate the user's emotions, and adjust the data management method based on those emotions.

[0103] The management department can optimize its management algorithms by referring to historical data during data management. For example, the management department can analyze historical data and apply the optimal data management algorithm. For example, the management department can improve the efficiency of data management based on historical data. The management department can also improve the accuracy of data management by referring to historical data. In this way, the management department can optimize its management algorithms and perform efficient data management by referring to historical data. Some or all of the above processes in the management department may be performed using AI or not. For example, the management department can input historical data into AI, and the AI ​​can analyze that data to optimize the management algorithm.

[0104] The management unit can estimate the user's emotions and adjust the frequency of data management based on the estimated emotions. For example, if the user is feeling anxious, the management unit will manage the data more frequently. If the user is relaxed, the management unit will manage the data at a standard frequency. The management unit can also manage the data quickly if the user is in a hurry. This allows the management unit to adjust the frequency of data management according to the user's emotions, enabling the user to manage their data with peace of mind. 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 management unit may be performed using AI or not. For example, the management unit can input user facial expression data into a generative AI, which can analyze the data to estimate the user's emotions and adjust the frequency of data management based on those emotions.

[0105] The management department can weight managed data based on when it was submitted. For example, the management department can prioritize recently submitted data. For example, it can prioritize older data. The management department can also prioritize data submitted within a specific period. This allows the management department to prioritize the management of the latest data by weighting the managed data based on when it was submitted. Some or all of the above processes in the management department may be performed using AI or not. For example, the management department can input the data submission dates into the AI, and the AI ​​can weight the managed data based on those submission dates.

[0106] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0107] The Home Doctor System can also be equipped with a monitoring unit that monitors the user's lifestyle. The monitoring unit collects data such as the user's diet, exercise, and sleep, and provides it to the analysis unit. This allows the analysis unit to more accurately assess the user's health status based on their lifestyle. For example, if the user has irregular eating habits, it can suggest improvements to their nutritional balance. If the user's health risks are increased due to lack of exercise, it can provide an appropriate exercise plan. Furthermore, if the user's sleep quality is poor, it can provide advice on how to improve sleep. In this way, the monitoring unit can comprehensively manage the user's lifestyle and support their health maintenance.

[0108] The Home Doctor system can also include an advice unit that estimates the user's emotions and provides health advice based on those emotions. For example, if the user is feeling stressed, the advice unit can suggest relaxation methods. If the user is feeling down, it can provide positive messages and words of encouragement. If the user is feeling energetic, it can also suggest proactive activities to maintain their health. In this way, the advice unit can comprehensively support the user's physical and mental health by providing health advice tailored to the user's emotions. Emotion estimation can be achieved using, for example, an emotion engine or generative AI.

[0109] The Home Doctor System can also include a sharing section that allows users to share their health data with other medical institutions. This sharing section would, for example, share the user's health data with their primary care physician or specialists only with the user's consent. This would enable medical institutions to provide more appropriate diagnoses and treatments based on the user's past health data. For instance, a doctor the user regularly visits could provide a more effective treatment plan by understanding the user's lifestyle and past symptoms. In emergencies, it could also provide information to emergency medical institutions to ensure a rapid response. In this way, the sharing section can properly manage the user's health data and strengthen collaboration with medical institutions.

[0110] The Home Doctor system can also include a reminder unit that estimates the user's emotions and provides health reminders based on those emotions. For example, if the user is feeling stressed, the reminder unit will send a reminder to encourage them to take a break to relax. If the user is tired, it will send a reminder to encourage them to rest earlier. It can also send reminders to encourage exercise and healthy eating if the user is feeling well. In this way, the reminder unit can support the user in maintaining healthy lifestyle habits by providing health reminders that are tailored to the user's emotions. Emotion estimation can be achieved, for example, using an emotion engine or generative AI.

[0111] The Home Doctor System can also be equipped with a prediction unit that analyzes the user's health data and predicts future health risks. The prediction unit predicts future health risks based, for example, the user's past health data and lifestyle data. This allows the user to take proactive measures against future health risks. For instance, if the prediction unit predicts a high risk of developing high blood pressure in the future, it can suggest improvements to diet and exercise. It can also provide methods for managing blood sugar levels if there is a risk of diabetes. Furthermore, if there is a risk of heart disease, it can recommend regular health checkups. In this way, the prediction unit can support the user's health maintenance by predicting future health risks and suggesting appropriate countermeasures.

[0112] The Home Doctor system can also include an Education Department that estimates the user's emotions and provides health education content based on those emotions. For example, the Education Department can provide information on health topics that the user is interested in. If the user is feeling anxious, it can provide reassuring health information. If the user is relaxed, it can also provide more detailed health knowledge. This allows the Education Department to support users in deepening their health knowledge by providing health education content tailored to their emotions. Emotion estimation can be achieved using, for example, an emotion engine or generative AI.

[0113] The Home Doctor system can also include a planning unit that creates personalized health plans based on the user's health data. The planning unit creates individual health plans based on data such as the user's diet, exercise, and sleep. This allows users to implement a health plan best suited to them. For example, the planning unit can analyze the user's dietary data and propose a nutritionally balanced meal plan. It can also provide an appropriate exercise plan based on exercise data. Furthermore, it can provide advice on improving sleep quality based on sleep data. In this way, the planning unit can comprehensively analyze the user's health data and support their health maintenance by providing a personalized health plan.

[0114] The Home Doctor system can also include a goal-setting unit that estimates the user's emotions and sets health goals based on those emotions. For example, if the user is feeling motivated, the goal-setting unit will set challenging health goals. If the user is feeling anxious, it will set easily achievable health goals. It can also set long-term health goals if the user is relaxed. In this way, the goal-setting unit can support the user in achieving their health goals without undue stress by setting health goals that are appropriate to the user's emotions. Emotion estimation can be achieved, for example, using an emotion engine or generative AI.

[0115] The Home Doctor system can also be equipped with a reporting unit that generates health reports based on the user's health data. For example, the reporting unit periodically analyzes the user's health data and generates a health status report. This makes it easier for users to understand their own health status. For instance, the reporting unit reports on changes in the user's health status based on data such as diet, exercise, and sleep. It can also compare current data with past health data to highlight areas for improvement and points to watch out for. Furthermore, if health risks are high, it can provide advice for taking early action. In this way, the reporting unit can support users in maintaining their health by comprehensively analyzing their health data and providing reports that help them understand their health status.

[0116] The Home Doctor system can also include a community department that estimates the user's emotions and operates a health community based on those estimated emotions. For example, if a user is feeling lonely, the community department can facilitate interaction with other users. If a user is feeling motivated, it can suggest health challenges. It can also introduce support groups if a user is feeling anxious. In this way, the community department can provide support for users to lead healthy lives by operating a health community tailored to their emotions. Emotion estimation can be achieved, for example, using an emotion engine or generative AI.

[0117] The following briefly describes the processing flow for example form 2.

[0118] Step 1: The reception desk receives information from the user. This information includes, for example, text-based questions and answers, and multiple-choice questions. The reception desk also receives information from the user when they begin a conversation with the AI ​​doctor. Step 2: The analysis unit analyzes the medical information received by the reception unit and the images captured by the camera. The analysis unit uses image analysis algorithms and text analysis techniques to determine the urgency of the symptoms. Step 3: The provisioning department provides appropriate initial response methods based on the information analyzed by the analysis department. The provisioning department provides first aid procedures and guidance to medical facilities. Step 4: The triage department performs triage based on the initial response methods provided by the service provider and offers appropriate medical options. The triage department offers medical options according to the urgency of the symptoms, following the criteria for assessing urgency and determining priorities. Step 5: The management department centrally manages the information provided by the triage department in the cloud and checks past response history. The management department centrally manages the data in the cloud, taking into consideration the type of database and security measures.

[0119] 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.

[0120] 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.

[0121] 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.

[0122] Each of the multiple elements described above, including the reception unit, analysis unit, provision unit, triage unit, and management unit, is implemented by, for example, at least one of the smart device 14 and the data processing unit 12. For example, the reception unit is implemented by the control unit 46A of the smart device 14 and receives medical information from the user. The analysis unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and analyzes the medical information and images captured by the camera. The provision unit is implemented by, for example, the control unit 46A of the smart device 14 and provides an appropriate initial response method based on the analyzed information. The triage unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and performs triage based on the initial response method and provides appropriate medical options. The management unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and centrally manages data in the cloud and checks past response history. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0123] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0124] 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.

[0125] 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.

[0126] 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.

[0127] 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.

[0128] 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).

[0129] 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.

[0130] 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.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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.).

[0135] 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.

[0136] 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.

[0137] 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.

[0138] Each of the multiple elements described above, including the reception unit, analysis unit, provision unit, triage unit, and management unit, is implemented, for example, by at least one of the smart glasses 214 and the data processing unit 12. For example, the reception unit is implemented by the control unit 46A of the smart glasses 214 and receives medical information from the user. The analysis unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12 and analyzes the medical information and images captured by the camera. The provision unit is implemented, for example, by the control unit 46A of the smart glasses 214 and provides an appropriate initial response method based on the analyzed information. The triage unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12 and performs triage based on the initial response method and provides appropriate medical options. The management unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12 and centrally manages data in the cloud and checks past response history. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0139] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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).

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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.).

[0151] 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.

[0152] 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.

[0153] 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.

[0154] Each of the multiple elements described above, including the reception unit, analysis unit, provision unit, triage unit, and management unit, is implemented by, for example, at least one of the headset terminal 314 and the data processing unit 12. For example, the reception unit is implemented by the control unit 46A of the headset terminal 314 and receives medical information from the user. The analysis unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and analyzes the medical information and images captured by the camera. The provision unit is implemented by, for example, the control unit 46A of the headset terminal 314 and provides an appropriate initial response method based on the analyzed information. The triage unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and performs triage based on the initial response method and provides appropriate medical options. The management unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and centrally manages data in the cloud and checks past response history. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0155] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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).

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.).

[0168] 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.

[0169] 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.

[0170] 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.

[0171] Each of the multiple elements described above, including the reception unit, analysis unit, provision unit, triage unit, and management unit, is implemented by, for example, at least one of the robot 414 and the data processing unit 12. For example, the reception unit is implemented by the control unit 46A of the robot 414 and receives medical information from the user. The analysis unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and analyzes the medical information and images captured by the camera. The provision unit is implemented by, for example, the control unit 46A of the robot 414 and provides an appropriate initial response method based on the analyzed information. The triage unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and performs triage based on the initial response method and provides appropriate medical options. The management unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and centrally manages data in the cloud and checks past response history. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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.

[0177] 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."

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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.

[0184] 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.

[0185] 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.

[0186] 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.

[0187] 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.

[0188] 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.

[0189] 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.

[0190] (Note 1) A reception area that receives medical information from users, An analysis unit analyzes the medical interview information received by the reception unit and the images taken by the camera. A providing unit that provides an appropriate initial response method based on the information analyzed by the aforementioned analysis unit, A triage unit performs triage based on the initial response method provided by the aforementioned supply unit and provides appropriate medical options. The system includes a management unit that centrally manages the information provided by the triage unit in the cloud and allows for the review of past response history. A system characterized by the following features. (Note 2) The aforementioned reception unit is The system accepts information from the user when they begin a conversation with the AI ​​doctor. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned analysis unit, The system analyzes images captured by a camera to determine the urgency of the symptoms. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned supply unit is, Based on the analysis results, we provide appropriate initial response methods. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned triage unit is, We provide medical options tailored to the urgency of the symptoms. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned management department, Centralized data management in the cloud allows you to review past service history. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned reception unit is The system estimates the user's emotions and adjusts the pace of the interview based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned reception unit is The system analyzes the user's past medical history and automatically generates optimal medical questions. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned reception unit is During the medical interview, the questions are customized based on the user's current lifestyle and health condition. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned reception unit is The system estimates the user's emotions and prioritizes the questions based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned reception unit is During the medical interview, we prioritize asking highly relevant questions, taking into account the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned reception unit is During the consultation, we analyze the user's social media activity and ask relevant questions. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned analysis unit, It estimates the user's emotions and adjusts the accuracy of image analysis based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned analysis unit, During image analysis, the level of detail of the analysis is adjusted based on the severity of the symptoms. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned analysis unit, During image analysis, different analysis algorithms are applied depending on the symptom category. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned analysis unit, It estimates the user'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 17) The aforementioned analysis unit, During image analysis, the priority of analysis is determined based on the time the image was taken. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned analysis unit, During image analysis, the order of analysis is adjusted based on the relevance of symptoms. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned supply unit is, The system estimates the user's emotions and adjusts the way initial responses are expressed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned supply unit is, When providing initial response methods, adjust the level of detail based on the severity of the symptoms. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned supply unit is, When providing initial response methods, different methods will be applied depending on the category of symptoms. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned supply unit is, The system estimates the user's emotions and adjusts the length of the initial response based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned supply unit is, When providing initial response methods, prioritize based on when the symptoms started. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned supply unit is, When providing initial response methods, the order will be adjusted based on the relevance of the symptoms. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned triage unit is, The system estimates the user's emotions and adjusts the triage criteria based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned triage unit is, During triage, consider the interrelationships between symptoms to improve the accuracy of the triage process. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned triage unit is, During triage, triage is performed while taking into account the user's attribute information. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned triage unit is, It estimates the user's emotions and adjusts the order in which triage results are displayed based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned triage unit is, When performing triage, consider the geographical distribution of symptoms. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned triage unit is, During triage, refer to relevant literature on symptoms to improve the accuracy of the triage process. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned management department, We estimate user sentiment and adjust data management methods based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 32) The aforementioned management department, When managing data, refer to past data to optimize the management algorithm. The system described in Appendix 1, characterized by the features described herein. (Note 33) The aforementioned management department, It estimates user sentiment and adjusts the frequency of data management based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 34) The aforementioned management department, When managing data, weight the data based on when it was submitted. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0191] 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. A reception area that receives medical information from users, An analysis unit analyzes the medical interview information received by the reception unit and the images taken by the camera. A providing unit that provides an appropriate initial response method based on the information analyzed by the aforementioned analysis unit, A triage unit performs triage based on the initial response method provided by the aforementioned supply unit and provides appropriate medical options. The system includes a management unit that centrally manages the information provided by the triage unit in the cloud and allows for the review of past response history. A system characterized by the following features.

2. The aforementioned reception unit is The system accepts information when the user initiates a conversation with the AI ​​doctor. The system according to feature 1.

3. The aforementioned analysis unit, The system analyzes images captured by a camera to determine the urgency of the symptoms. The system according to feature 1.

4. The aforementioned supply unit is, Based on the analysis results, we provide appropriate initial response methods. The system according to feature 1.

5. The aforementioned triage unit is, We provide medical options tailored to the urgency of the symptoms. The system according to feature 1.

6. The aforementioned management department, Centralized data management in the cloud allows you to review past service history. The system according to feature 1.

7. The aforementioned reception unit is The system estimates the user's emotions and adjusts the pace of the interview based on those emotions. The system according to feature 1.

8. The aforementioned reception unit is The system analyzes the user's past medical history and automatically generates optimal medical questions. The system according to feature 1.

9. The aforementioned reception unit is During the medical interview, the questions are customized based on the user's current lifestyle and health condition. The system according to feature 1.

10. The aforementioned reception unit is The system estimates the user's emotions and prioritizes the questions based on those emotions. The system according to feature 1.

Images